Dataset Viewer
dataset
stringclasses 22
values | id
stringlengths 18
53
| messages
listlengths 2
2
|
|---|---|---|
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.10715
|
[
{
"content": "Given a short query with keyphrases about a research idea in 2014 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from options provided. A short description of the datasets is also provided to help you.\n\nQuery: I want to improve a state-of-the-art depth ordering algorithm for single\n\nKeyphrases: depth ordering single images\n\nDataset description:\nRFW: To validate the racial bias of four commercial APIs and four state-of-the-art (SOTA) algorithms.\nBSDS500: Berkeley Segmentation Data Set 500 (BSDS500) is a standard benchmark for contour detection. This dataset is designed for evaluating natural edge detection that includes not only object contours but also object interior boundaries and background boundaries.\nDialogue State Tracking Challenge: The Dialog State Tracking Challenges 2 & 3 (DSTC2&3) were research challenge focused on improving the state of the art in tracking the state of spoken dialog systems. State tracking, sometimes called belief tracking, refers to accurately estimating the user's goal as a dialog progresses.\nHollywood 3D dataset: A dataset for benchmarking action recognition algorithms in natural environments, while making use of 3D information. The dataset contains around 650 video clips, across 14 classes.\n\nOptions:- A: RFW B: BSDS500 C: Dialogue State Tracking Challenge D: Hollywood 3D dataset",
"role": "user"
},
{
"content": "BSDS500",
"role": "assistant"
}
] |
science.bioasq_factoid_qa
|
science.bioasq_factoid_qa.921
|
[
{
"content": "You will be shown biomedical passages and your task is to the answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: Name a CFL2 mutation which is associated with nemaline myopathy?\n\nContext: Because a mutation in CFL2 was identified in a family with nemaline myopathy, we performed sequence analysis of the gene and a novel homozygous missense mutation in exon 2 (c.19G>A, p.Val7Met) of CFL2 was identified in both siblings.",
"role": "user"
},
{
"content": "c.19G>A, or p.Val7Met",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.1817
|
[
{
"content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"HealthCareActivity\", \"InjuryOrPoisoning\", \"BodySubstance\", \"IntellectualProduct\", \"AnatomicalStructure\", \"SpatialConcept\", \"Chemical\", \"Bacterium\", \"MedicalDevice\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Finding\", \"BiologicFunction\", \"Virus\", \"ResearchActivity\", \"ClinicalAttribute\", \"PopulationGroup\", \"Eukaryote\", \"BodySystem\", \"Food\", \"ProfessionalOrOccupationalGroup\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nBlubber transcriptome response to acute stress axis activation involves transient changes in adipogenesis and lipolysis in a fasting -adapted marine mammal Stress can compromise an animal's ability to conserve metabolic stores and participate in energy -demanding activities that are critical for fitness. Understanding how wild animals, especially those already experiencing physiological extremes (e.g. fasting), regulate stress responses is critical for evaluating the impacts of anthropogenic disturbance on physiology and fitness, key challenges for conservation. However, studies of stress in wildlife are often limited to baseline endocrine measurements and few have investigated stress effects in fasting -adapted species. We examined downstream molecular consequences of hypothalamic-pituitary-adrenal (HPA) axis activation by exogenous adrenocorticotropic hormone (ACTH) in blubber of northern elephant seals due to the ease of blubber sampling and its key role in metabolic regulation in marine mammals. We report the first phocid blubber transcriptome produced by RNAseq, containing over 140,000 annotated transcripts, including metabolic and adipocytokine genes of interest. The acute response of blubber to stress axis activation, measured 2 hours after ACTH administration, involved highly specific, transient (lasting <24 hours) induction of gene networks that promote lipolysis and adipogenesis in mammalian adipocytes. Differentially expressed genes included key adipogenesis factors which can be used as blubber -specific markers of acute stress in marine mammals of concern for which sampling of other tissues is not possible.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [\"adipocytes\", \"tissues\", \"metabolic\", \"genes\", \"Blubber\", \"adipocytokine genes\", \"blubber\"], \"Bacterium\": [], \"BiologicFunction\": [\"activation\", \"regulate\", \"lipolysis\", \"expressed\", \"physiology\", \"stress axis activation\", \"adipogenesis\", \"gene networks\", \"acute stress axis activation\", \"stress responses\"], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [\"hypothalamic-pituitary-adrenal (HPA) axis\"], \"Chemical\": [\"ACTH\", \"adrenocorticotropic hormone\", \"transcripts\"], \"ClinicalAttribute\": [\"markers\"], \"Eukaryote\": [\"animal\\u0027s\", \"wildlife\", \"marine mammals\", \"mammalian\", \"wild animals\", \"marine mammal\", \"phocid\", \"elephant seals\"], \"Finding\": [\"stress\", \"fasting\", \"physiological extremes\", \"Stress\"], \"Food\": [], \"HealthCareActivity\": [\"RNAseq\", \"administration\", \"downstream molecular consequences\", \"baseline endocrine measurements\"], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [\"species\"], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [], \"SpatialConcept\": [\"transcriptome\", \"northern\"], \"Virus\": []}",
"role": "assistant"
}
] |
science.scitldr_aic
|
science.scitldr_aic.338
|
[
{
"content": "Below are the abstract, introduction, and conclusion of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary and no additional text.\n\nPaper text:\n\nOver the past four years, neural networks have been proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions.\nWe show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs.\nFor most current network architectures, we prove that the L1-norm of these gradients grows as the square root of the input size.\nThese nets therefore become increasingly vulnerable with growing image size.\nOur proofs rely on the network’s weight distribution at initialization, but extensive experiments confirm that our conclusions still hold after usual training.\nFollowing the work of BID7 , Convolutional Neural Networks (CNNs) have been found vulnerable to adversarial examples: an adversary can drive the performance of state-of-the art CNNs down to chance level with imperceptible changes of the inputs.\nA number of studies have tried to address this issue, but only few have stressed that, because adversarial examples are essentially small input changes that create large output variations, they are inherently caused by large gradients of the neural network with respect to its inputs.\nOf course, this view, which we will focus on here, assumes that the network and loss are differentiable.\nIt has the advantage to yield a large body of specific mathematical tools, but might not be easily extendable to masked gradients, non-smooth models or the 0-1-loss.\nNevertheless, our conclusions might even hold for non-smooth models, given that the latter can often be viewed as smooth at a coarser level.Contributions.\nMore specifically, we provide theoretical and empirical arguments supporting the existence of a monotonic relationship between the gradient norm of the training objective (of a differentiable classifier) and its adversarial vulnerability.\nEvaluating this norm based on the weight statistics at initialization, we show that CNNs and most feed-forward networks, by design, exhibit increasingly large gradients with input dimension d, almost independently of their architecture.\nThat leaves them increasingly vulnerable to adversarial noise.\nWe corroborate our theoretical results by extensive experiments.\nAlthough some of those experiments involve adversarial regularization schemes, our goal is not to advocate a new adversarial defense (these schemes are already known), but to show how their effect can be explained by our first order analysis.\nWe do not claim to explain all aspects of adversarial vulnerability, but we claim that our first order argument suffices to explain a significant part of the empirical findings on adversarial vulnerability.\nThis calls for researching the design of neural network architectures with inherently smaller gradients and provides useful guidelines to practitioners and network designers.\nFor differentiable classifiers and losses, we showed that adversarial vulnerability increases with the gradients ∂ x L of the loss, which is confirmed by the near-perfect functional relationship between gradient norms and vulnerability FIG1 We then evaluated the size of ∂ x L q and showed that, at initialization, usual feed-forward nets (convolutional or fully connected) are increasingly vulnerable to p -attacks with growing input dimension d (the image-size), almost independently of their architecture.\nOur experiments show that, on the tested architectures, usual training escapes those prior gradient (and vulnerability) properties on the training, but not on the test set.\nBID14 suggest that alleviating this generalization gap requires more data.\nBut a natural (complementary) alternative would be to search for architectures with naturally smaller gradients, and in particular, with well-behaved priors.\nDespite all their limitations (being only first-order, assuming a prior weight-distribution and a differentiable loss and architecture), our theoretical insights may thereby still prove to be precious future allies.",
"role": "user"
},
{
"content": "Neural nets have large gradients by design; that makes them adversarially vulnerable.",
"role": "assistant"
}
] |
science.qasa_abstractive_qa
|
science.qasa_abstractive_qa.1009
|
[
{
"content": "You will be shown an excerpt from a computer science scientific research paper, followed by a question about the paper. Please answer the question. Do not include any text in your response other than the answer.\n\nContext: One of the main benefits of transfer learning is being able to train a model for a task with a small number of labels. We evaluate ULMFiT on different numbers of labeled examples in two settings: only labeled examples are used for LM fine-tuning (‘supervised’); and all task data is available and can be used to fine-tune the LM (‘semi-supervised’). We compare ULMFiT to training from scratch—which is necessary for hypercolumn-based approaches. We split off balanced fractions of the training data, keep the validation set fixed, and use the same hyperparameters as before. We show the results in Figure 3.\n\nQuestion: Is weak supervision a subset or type of regular supervised learning?",
"role": "user"
},
{
"content": "In this work, fine-tuning an LM only on labeled examples is considered to be supervised learning. The general definitions of supervised learning and weak supervision, and whether weak supervision is a subset of regular supervised learning cannot be answered in this paper.",
"role": "assistant"
}
] |
science.linnaeus_ner
|
science.linnaeus_ner.34
|
[
{
"content": "You will be shown the full-text from a biomedical research paper. Given this text, your task is to extract all unique entities of the following types: [\"Species\"].\n\nPlease return the output as a JSON object of the format: {\"Species\": [\"rat\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nDocument text:\n\nPiezoelectric osteotomy in hand surgery: first experiences with a new technique\nAbstract\nBackground\nIn hand and spinal surgery nerve lesions are feared complications with the use of standard oscillating saws. Oral surgeons have started using a newly developed ultrasound bone scalpel when performing precise osteotomies. By using a frequency of 25–29 kHz only mineralized tissue is cut, sparing the soft tissue. This reduces the risk of nerve lesions. As there is a lack of experience with this technique in the field of orthopaedic bone surgery, we performed the first ultrasound osteotomy in hand surgery.\n\nMethod\nWhile performing a correctional osteotomy of the 5th metacarpal bone we used the Piezosurgery® Device from Mectron [Italy] instead of the usual oscillating saw. We will report on our experience with one case, with a follow up time of one year.\n\nResults\nThe cut was highly precise and there were no vibrations of the bone. The time needed for the operation was slightly longer than the time needed while using the usual saw. Bone healing was good and at no point were there any neurovascular disturbances.\n\nConclusion\nThe Piezosurgery® Device is useful for small long bone osteotomies. Using the fine tip enables curved cutting and provides an opportunity for new osteotomy techniques. As the device selectively cuts bone we feel that this device has great potential in the field of hand- and spinal surgery.\n\n\n\nBackground\nFor osteotomies of the hand oscillating saws are usually used [1]. Even though they are varied in size, they are not very precise for use in the vicinity of nerves and arteries. They also pose problems while being used in conjunction with magnification, as one's range of sight and focus is restricted when wearing magnifying glasses. For that reason oral surgeons have moved to using the newly developed piezoelectrical bone scalpel when operating in the near vicinity of nerves or arteries. The tip of this instrument oscillates in the frequency of ultrasound [2]. The mechanism of this device is based on the so called Piezo – Effect. French Physicists Jean and Marie Curie first mentioned the direct Piezo-Effect 1880, whereby certain crystals produce electrical current while under mechanical pressure. The reciprocal effect, by which the crystals are deformed when under electrical current, was then discovered a while later. This is the effect being used by the Piezosurgery Device®. In this device, the electrical field is located in the handle of the saw [3]. Due to the deformation caused by the electrical current, a cutting – hammering movement is produced at the tip of the instrument. These micro movements are in the frequency range of 25 to 29 kHz and, depending on the insert, with an amplitude of 60 to 210 μm. This way only mineralized tissue is selectively cut. Neurovascular tissue and other soft tissue would only be cut by a frequency of above 50 kHz [3-5]. Depending on the strength of the bone and the blade geometry, the efficiency of the cutting can be regulated by the frequency modulator and the power level. For cooling there is an integrated pump with five different working levels. This pump automatically washes physiological solution to the area being cut. The cost of the device is about 7.000 USD. Additional costs per operation are for the cooling liquid and are in the range of a few dollars. We have used the Piezosurgery Device® by Mectron [Italy] [3] for the first time in osteotomies of the long bone in the field of hand surgery. We will report on our experience with one case, with a follow up time of one year.\n\nMethod\nThe correctional osteotomy was performed on a 23 year old worker who suffered a malunited metacarpal bone fracture of the fifth finger on his dominant hand. The X-ray revealed a 45 degree angular deformity of the fifth metacarpal neck with internal rotation. (Figure 1). The operation was performed under regional anesthesia. A longitudinal incision was made over the fifth metacarpal. The tendon of the extensor digiti minimi was found and on its radial side the periosteum of metacarpal five was reached. The periosteum was opened longitudinally over the defect as usual. For the correction of the defect of 45 degrees, a bone wedge was excised. Instead of using the traditional oscillating saw, the Piezosurgery Device® [3] was used (Figure 2). We used a sharp hardened saw coated with titannitrid (Figure 3). For most of the surgery the highest power level, the boosted burst c, was used. We set the automatic cooling of the area with water to its highest level. The angulation and rotation was corrected and fixed with a 1.5 mm titanium five-hole plate and four screws. Closure of the wound was done in layers. Mobilization was started on the 10th postoperative day. The overall time of observation was one year.\n\nResults and discussion\nThe Piezosurgery® Device is ideally sized for hand surgery. The cutting was very precise. The edges of the osteotomy were all sharp to the edge, there was no need to split the bone with a chisel, nor was there the danger of a break out. During the osteotomy there were no disturbing vibrations in the area of operation. This absence of vibration is very practical for operations using a magnifier. Vercellotti mentions that to overcome any problems during surgery, instead of increasing pressure on the hand piece, as in traditional techniques, it is necessary to find the correct pressure to achieve the desired result. With piezoelectric surgery, increasing the working pressure above a certain limit impedes the vibrations of the insert [4]. We have also experienced this in our study. The instrument can be moved in all directions comparable to a pen. The tip of the instrument is exchangeable. Using the fine tip enables multiplanar as well as curved cutting. Because of the automatic water cooling during the whole procedure, there is always a clear view onto the object. This is something oral surgeons found especially useful [6]. The authors mention that the downside of the device is the relative slow sawing process. We needed about 30 seconds for one cut of the relatively small bone. This is about 20 seconds longer than the time needed for cutting with the usual saw. Although the power can be regulated with the power box and the use of different scalpels, we agree with other authors that the optimal use of this device is in surgeries of small bones where precise and soft tissue friendly cutting is required [7]. As other literature has shown, the device selectively cuts bone while sparing nerves and other soft tissue [2,3]. This allows for minimal invasive surgeries with limited retraction of soft tissue and minimal stripping of the periosteum, saves time and might have a positive effect on the healing process. Our aim of the first time use of the Piezosurgery® Device in hand surgery was to check its usability in osteotomies of tubular bones. The preparation of the bone was done in the usual manner as is done when cutting with an oscillating saw. The reason for this was to fully visualize the cutting process using this new device, although in the future, it should be possible to minimize the bony exposure. In our patient the postoperative healing of the wound and the bone consolidation (Figure 4) were smooth. The duration of postoperative sick leave was four weeks which is more rapid than the usual recovery period. The patient regained full use of his finger according to the state before the fracture. At no point was there any loss of sensitivity. The patient as well as the surgeons were fully satisfied with the result.\n\nConclusion\nThe Piezosurgery® Device is a useful device for small long bone osteotomies. We feel that this device has great potential in the field of hand- and spinal surgery. As the device selectively cuts bone, considerable nerve lesions can be avoided and minimal invasive surgeries are possible. Using the fine tip enables curved cutting and provides an opportunity for new osteotomy techniques.\n\nCompeting interests\nThe author(s) declare that they have no competing interests.\n\nAuthors' contributions\nDJH initiated and coordinated the new application of Piezosurgery® device and wrote the publication.\nStSt lead the osteotomy as he was experienced with this tool from oral surgery. He played a major part in writing the technical aspects.\nOVK was the treating surgeon, performed the operation and evaluated the new tool.\nSS performed a literature review and wrote part of the publication.\nPH was the treating chief surgeon, evaluated the new tool and lead the treatment in all aspects.\n\nConsent\nWe obtained oral consent from the patient but could not obtain written consent.\n\nPre-publication history\nThe pre-publication history for this paper can be accessed here:",
"role": "user"
},
{
"content": "{\"Species\": [\"patient\"]}",
"role": "assistant"
}
] |
science.pubmedqa_qa
|
science.pubmedqa_qa.383
|
[
{
"content": "You will be shown an abstract from a research paper, and a corresponding research question. Determine the answer to the research question based on the context provided. Your answer should be one of: \"YES\", \"NO\", or \"MAYBE\".\n\nContext:\n(BACKGROUND) An increasingly significant public health issue in Canada, and elsewhere throughout the developed world, pertains to the provision of adequate palliative/end-of-life (P/EOL) care. Informal caregivers who take on the responsibility of providing P/EOL care often experience negative physical, mental, emotional, social and economic consequences. In this article, we specifically examine how Canada's Compassionate Care Benefit (CCB)--a contributory benefits social program aimed at informal P/EOL caregivers--operates as a public health response in sustaining informal caregivers providing P/EOL care, and whether or not it adequately addresses known aspects of caregiver burden that are addressed within the population health promotion (PHP) model.\n(METHODS) As part of a national evaluation of Canada's Compassionate Care Benefit, 57 telephone interviews were conducted with Canadian informal P/EOL caregivers in 5 different provinces, pertaining to the strengths and weaknesses of the CCB and the general caregiving experience. Interview data was coded with Nvivo software and emerging themes were identified by the research team, with such findings published elsewhere. The purpose of the present analysis was identified after comparing the findings to the literature specific to caregiver burden and public health, after which data was analyzed using the PHP model as a guiding framework.\n(RESULTS) Informal caregivers spoke to several of the determinants of health outlined in the PHP model that are implicated in their burden experience: gender, income and social status, working conditions, health and social services, social support network, and personal health practises and coping strategies. They recognized the need for improving the CCB to better address these determinants.\n\nQuestion:\nCanada's Compassionate Care Benefit: is it an adequate public health response to addressing the issue of caregiver burden in end-of-life care?\n\nAnswer:",
"role": "user"
},
{
"content": "NO",
"role": "assistant"
}
] |
science.bioasq_general_qa
|
science.bioasq_general_qa.1048
|
[
{
"content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is the function of a DEAD box protein?\n\nContext: DEAD-box helicase proteins perform ATP-dependent rearrangements of structured RNAs throughout RNA biology.\nDEAD-box proteins are ubiquitous in RNA-mediated processes and function by coupling cycles of ATP binding and hydrolysis to changes in affinity for single-stranded RNA. Many DEAD-box proteins use this basic mechanism as the foundation for a version of RNA helicase activity\nDEAD-box proteins as RNA helicases and chaperones.\nRNA helicases of the DEAD-box and related families have been found to be required for all processes involving RNA molecules\nDDX3 belongs to the DEAD-box proteins, a large family of ATP-dependent RNA helicases that participate in all aspects of RNA metabolism\nDEAD-box proteins catalyze the ATP-dependent unwinding of RNA duplexes and accompany RNA molecules throughout their cellular life.\nDEAD-box (DDX) proteins belong to the largest subfamily of RNA helicase SF2, which contributes to all biological processes of RNA metabolism\nDDX3Y (also known as DBY) is a member of the DEAD box protein family, which is involved in ATP-dependent RNA unwinding, needed in a variety of cellular processes including splicing, ribosome biogenesis and RNA degradation.\nVASA is a member of the DEAD-box protein family that plays an indispensable role in mammalian spermatogenesis, particularly during meiosis.\nBACKGROUND: Vasa is a member of the DEAD-box protein family that plays an indispensable role in mammalian spermatogenesis, particularly during meiosis.\nThe yeast DEAD box protein Mss116p is a general RNA chaperone that functions in mitochondrial group I and II intron splicing, translational activation, and RNA end processing.\nDEAD box proteins are putative RNA helicases that function in all aspects of RNA metabolism, including translation, ribosome biogenesis, and pre-mRNA splicing. B\nrom unwinding RNA duplexes, which established these proteins as RNA helicases, DEAD box proteins have been shown to also catalyse RNA annealing and to displace proteins from RNA. DEAD bo\nDDX3Y (also known as DBY) is a member of the DEAD box protein family, which is involved in ATP-dependent RNA unwinding, needed in a variety of cellular processes including splicing, ribosome biogenesis and RNA degradation. In\n'DEAD/H' family of putative RNA helicases may help regulate these processes by utilizing intrinsic RNA-dependent ATPase activity to catalyze conformational changes in RNA secondary structure. To\nDEAD-box helicases catalyze the ATP-dependent unwinding of RNA duplexes.\nA DEAD-box protein functions as an ATP-dependent RNA chaperone in group I intron splicing.\nDEAD-box proteins are nonprocessive RNA helicases that play diverse roles in cellular processes.\nA DEAD-box protein alone promotes group II intron splicing and reverse splicing by acting as an RNA chaperone.\nDEAD/H-box proteins are involved in various aspects of RNA metabolism.\nOur results demonstrate that a DExH/D-box protein has a specific, physiologically relevant chaperone function in the folding of a natural RNA substrate.\nDEAD-box proteins are the largest family of nucleic acid helicases, and are crucial to RNA metabolism throughout all domains of life.\nHere, structural, biochemical and genetic analyses of the yeast DEAD-box protein Mss116p indicate that the helicase core domains have modular functions that enable a novel mechanism for RNA-duplex recognition and unwinding.\nThe DEAD-box RNA helicase family comprise enzymes that participate in every aspect of RNA metabolism, associated with a diverse range of cellular functions including response to abiotic stress.\nThe Thermus thermophilus DEAD-box protein Hera is a general RNA binding protein and plays a key role in tRNA metabolism.\nDEAD-box proteins, a large class of RNA-dependent ATPases, regulate all aspects of gene expression and RNA metabolism.\nDEAD box proteins are putative RNA helicases that have been implicated in cellular processes involving alteration of RNA secondary structure, such as translation initiation and splicing.\nDEAD box proteins catalyze the ATP-dependent unwinding of double-stranded RNA (dsRNA).\nDEAD-box proteins are ATP-dependent RNA helicases that function in various stages of RNA processing and in RNP remodeling.\nDEAD-box proteins are ubiquitous in RNA-mediated processes and function by coupling cycles of ATP binding and hydrolysis to changes in affinity for single-stranded RNA.\nDEAD-box proteins ordinarily function as constituents of enormous multi-protein complexes and it is believed that interactions with other components in the complexes might be answerable for the various capacities ascribed to these proteins.\nThere is emerging evidence that DEAD-box family of RNA helicases play pivotal functions in various cellular processes and in numerous cases have been embroiled in cellular proliferation and/or neoplastic transformation.\nThis activity, coupled with mechanisms to direct different DEAD-box proteins to their physiological substrates, allows them to promote RNA folding steps and rearrangements and to accelerate remodeling of RNA–protein complexes.\nMany DEAD-box proteins use this basic mechanism as the foundation for a version of RNA helicase activity, efficiently separating the strands of short RNA duplexes in a process that involves little or no translocation.",
"role": "user"
},
{
"content": "DEAD-box helicases are ubiquitous in RNA-mediated processes and function by coupling cycles of ATP binding and hydrolysis to changes in affinity for single-stranded RNA. DEAD-box helicase proteins perform ATP-dependent rearrangements of structured RNAs DEAD-box (DDX) proteins belong to the largest subfamily of RNA helicase SF2, which contributes to all biological processes of RNA metabolism DEAD-box proteins catalyze the ATP-dependent unwinding of RNA duplexes and accompany RNA molecules throughout their cellular life.",
"role": "assistant"
}
] |
science.qasper_extractive_qa
|
science.qasper_extractive_qa.248.0
|
[
{
"content": "You will be shown sections from a scientific research paper, together with a question about the paper. Your task is to answer the question based on the contents of the paper. Your response should be a `json` object with two fields:\n\n\"answer\": An array of strings extracted directly from the paper which, collectively, answer the question.\n\"evidence\": An array of strings. Each should be an excerpt from the paper, in which one or more of the extracted answers can be found.\n\nFor instance, for the question \"What baselines did the authors compare against?\", a sample response might be:\n\n{\n \"answer\": [\"BERT\", \"RoBERTa\"],\n \"evidence\": [\"In our experiments, we compare the performance of our model against BERT and RoBERTa.\"]\n}\n\nDo not include any text in your response other than the json.\n\nIf the question is unanswerable given the provided excerpts, respond with the single word \"null\".\n\nPaper: Recognizing Musical Entities in User-generated Content\n\nRecognizing Musical Entities is important for Music Information Retrieval (MIR) since it can improve the performance of several tasks such as music recommendation, genre classification or artist similarity. However, most entity recognition systems in the music domain have concentrated on formal texts (e.g. artists' biographies, encyclopedic articles, etc.), ignoring rich and noisy user-generated content. In this work, we present a novel method to recognize musical entities in Twitter content generated by users following a classical music radio channel. Our approach takes advantage of both formal radio schedule and users' tweets to improve entity recognition. We instantiate several machine learning algorithms to perform entity recognition combining task-specific and corpus-based features. We also show how to improve recognition results by jointly considering formal and user-generated content\n\nIntroduction\nThe increasing use of social media and microblogging services has broken new ground in the field of Information Extraction (IE) from user-generated content (UGC). Understanding the information contained in users' content has become one of the main goal for many applications, due to the uniqueness and the variety of this data BIBREF0 . However, the highly informal and noisy status of these sources makes it difficult to apply techniques proposed by the NLP community for dealing with formal and structured content BIBREF1 .\nIn this work, we analyze a set of tweets related to a specific classical music radio channel, BBC Radio 3, interested in detecting two types of musical named entities, Contributor and Musical Work.\nThe method proposed makes use of the information extracted from the radio schedule for creating links between users' tweets and tracks broadcasted. Thanks to this linking, we aim to detect when users refer to entities included into the schedule. Apart from that, we consider a series of linguistic features, partly taken from the NLP literature and partly specifically designed for this task, for building statistical models able to recognize the musical entities. To that aim, we perform several experiments with a supervised learning model, Support Vector Machine (SVM), and a recurrent neural network architecture, a bidirectional LSTM with a CRF layer (biLSTM-CRF).\nThe contributions in this work are summarized as follows:\nThe paper is structured as follows. In Section 2, we present a review of the previous works related to Named Entity Recognition, focusing on its application on UGC and MIR. Afterwards, in Section 3 it is presented the methodology of this work, describing the dataset and the method proposed. In Section 4, the results obtained are shown. Finally, in Section 5 conclusions are discussed.\n\nRelated Work\nNamed Entity Recognition (NER), or alternatively Named Entity Recognition and Classification (NERC), is the task of detecting entities in an input text and to assign them to a specific class. It starts to be defined in the early '80, and over the years several approaches have been proposed BIBREF2 . Early systems were based on handcrafted rule-based algorithms, while recently several contributions by Machine Learning scientists have helped in integrating probabilistic models into NER systems.\nIn particular, new developments in neural architectures have become an important resource for this task. Their main advantages are that they do not need language-specific knowledge resources BIBREF3 , and they are robust to the noisy and short nature of social media messages BIBREF4 . Indeed, according to a performance analysis of several Named Entity Recognition and Linking systems presented in BIBREF5 , it has been found that poor capitalization is one of the main issues when dealing with microblog content. Apart from that, typographic errors and the ubiquitous occurrence of out-of-vocabulary (OOV) words also cause drops in NER recall and precision, together with shortenings and slang, particularly pronounced in tweets.\nMusic Information Retrieval (MIR) is an interdisciplinary field which borrows tools of several disciplines, such as signal processing, musicology, machine learning, psychology and many others, for extracting knowledge from musical objects (be them audio, texts, etc.) BIBREF6 . In the last decade, several MIR tasks have benefited from NLP, such as sound and music recommendation BIBREF7 , automatic summary of song review BIBREF8 , artist similarity BIBREF9 and genre classification BIBREF10 .\nIn the field of IE, a first approach for detecting musical named entities from raw text, based on Hidden Markov Models, has been proposed in BIBREF11 . In BIBREF12 , the authors combine state-of-the-art Entity Linking (EL) systems to tackle the problem of detecting musical entities from raw texts. The method proposed relies on the argumentum ad populum intuition, so if two or more different EL systems perform the same prediction in linking a named entity mention, the more likely this prediction is to be correct. In detail, the off-the-shelf systems used are: DBpedia Spotlight BIBREF13 , TagMe BIBREF14 , Babelfy BIBREF15 . Moreover, a first Musical Entity Linking, MEL has been presented in BIBREF16 which combines different state-of-the-art NLP libraries and SimpleBrainz, an RDF knowledge base created from MusicBrainz after a simplification process.\nFurthermore, Twitter has also been at the center of many studies done by the MIR community. As example, for building a music recommender system BIBREF17 analyzes tweets containing keywords like nowplaying or listeningto. In BIBREF9 , a similar dataset it is used for discovering cultural listening patterns. Publicly available Twitter corpora built for MIR investigations have been created, among others the Million Musical Tweets dataset BIBREF18 and the #nowplaying dataset BIBREF19 .\n\nMethodology\nWe propose a hybrid method which recognizes musical entities in UGC using both contextual and linguistic information. We focus on detecting two types of entities: Contributor: person who is related to a musical work (composer, performer, conductor, etc). Musical Work: musical composition or recording (symphony, concerto, overture, etc).\nAs case study, we have chosen to analyze tweets extracted from the channel of a classical music radio, BBC Radio 3. The choice to focus on classical music has been mostly motivated by the particular discrepancy between the informal language used in the social platform and the formal nomenclature of contributors and musical works. Indeed, users when referring to a musician or to a classical piece in a tweet, rarely use the full name of the person or of the work, as shown in Table 2.\nWe extract information from the radio schedule for recreating the musical context to analyze user-generated tweets, detecting when they are referring to a specific work or contributor recently played. We manage to associate to every track broadcasted a list of entities, thanks to the tweets automatically posted by the BBC Radio3 Music Bot, where it is described the track actually on air in the radio. In Table 3, examples of bot-generated tweets are shown.\nAfterwards, we detect the entities on the user-generated content by means of two methods: on one side, we use the entities extracted from the radio schedule for generating candidates entities in the user-generated tweets, thanks to a matching algorithm based on time proximity and string similarity. On the other side, we create a statistical model capable of detecting entities directly from the UGC, aimed to model the informal language of the raw texts. In Figure 1, an overview of the system proposed is presented.\n\nNER system\nAccording to the literature reviewed, state-of-the-art NER systems proposed by the NLP community are not tailored to detect musical entities in user-generated content. Consequently, our first objective has been to understand how to adapt existing systems for achieving significant results in this task.\nIn the following sections, we describe separately the features, the word embeddings and the models considered. All the resources used are publicy available.\nWe define a set of features for characterizing the text at the token level. We mix standard linguistic features, such as Part-Of-Speech (POS) and chunk tag, together with several gazetteers specifically built for classical music, and a series of features representing tokens' left and right context. For extracting the POS and the chunk tag we use the Python library twitter_nlp, presented in BIBREF1 .\nIn total, we define 26 features for describing each token: 1)POS tag; 2)Chunk tag; 3)Position of the token within the text, normalized between 0 and 1; 4)If the token starts with a capital letter; 5)If the token is a digit. Gazetteers: 6)Contributor first names; 7)Contributor last names; 8)Contributor types (\"soprano\", \"violinist\", etc.); 9)Classical work types (\"symphony\", \"overture\", etc.); 10)Musical instruments; 11)Opus forms (\"op\", \"opus\"); 12)Work number forms (\"no\", \"number\"); 13)Work keys (\"C\", \"D\", \"E\", \"F\" , \"G\" , \"A\", \"B\", \"flat\", \"sharp\"); 14)Work Modes (\"major\", \"minor\", \"m\"). Finally, we complete the tokens' description including as token's features the surface form, the POS and the chunk tag of the previous and the following two tokens (12 features).\nWe consider two sets of GloVe word embeddings BIBREF20 for training the neural architecture, one pre-trained with 2B of tweets, publicy downloadable, one trained with a corpora of 300K tweets collected during the 2014-2017 BBC Proms Festivals and disjoint from the data used in our experiments.\nThe first model considered for this task has been the John Platt's sequential minimal optimization algorithm for training a support vector classifier BIBREF21 , implemented in WEKA BIBREF22 . Indeed, in BIBREF23 results shown that SVM outperforms other machine learning models, such as Decision Trees and Naive Bayes, obtaining the best accuracy when detecting named entities from the user-generated tweets.\nHowever, recent advances in Deep Learning techniques have shown that the NER task can benefit from the use of neural architectures, such as biLSTM-networks BIBREF3 , BIBREF4 . We use the implementation proposed in BIBREF24 for conducting three different experiments. In the first, we train the model using only the word embeddings as feature. In the second, together with the word embeddings we use the POS and chunk tag. In the third, all the features previously defined are included, in addition to the word embeddings. For every experiment, we use both the pre-trained embeddings and the ones that we created with our Twitter corpora. In section 4, results obtained from the several experiments are reported.\n\nResults\nThe performances of the NER experiments are reported separately for three different parts of the system proposed.\nTable 6 presents the comparison of the various methods while performing NER on the bot-generated corpora and the user-generated corpora. Results shown that, in the first case, in the training set the F1 score is always greater than 97%, with a maximum of 99.65%. With both test sets performances decrease, varying between 94-97%. In the case of UGC, comparing the F1 score we can observe how performances significantly decrease. It can be considered a natural consequence of the complex nature of the users' informal language in comparison to the structured message created by the bot.\nIn Table 7, results of the schedule matching are reported. We can observe how the quality of the linking performed by the algorithm is correlated to the choice of the three thresholds. Indeed, the Precision score increase when the time threshold decrease, admitting less candidates as entities during the matching, and when the string similarity thresholds increase, accepting only candidates with an higher degree of similarity. The behaviour of the Recall score is inverted.\nFinally, we test the impact of using the schedule matching together with a biLSTM-CRF network. In this experiment, we consider the network trained using all the features proposed, and the embeddings not pre-trained. Table 8 reports the results obtained. We can observe how generally the system benefits from the use of the schedule information. Especially in the testing part, where the neural network recognizes with less accuracy, the explicit information contained in the schedule can be exploited for identifying the entities at which users are referring while listening to the radio and posting the tweets.\n\nConclusion\nWe have presented in this work a novel method for detecting musical entities from user-generated content, modelling linguistic features with statistical models and extracting contextual information from a radio schedule. We analyzed tweets related to a classical music radio station, integrating its schedule to connect users' messages to tracks broadcasted. We focus on the recognition of two kinds of entities related to the music field, Contributor and Musical Work.\nAccording to the results obtained, we have seen a pronounced difference between the system performances when dealing with the Contributor instead of the Musical Work entities. Indeed, the former type of entity has been shown to be more easily detected in comparison to the latter, and we identify several reasons behind this fact. Firstly, Contributor entities are less prone to be shorten or modified, while due to their longness, Musical Work entities often represent only a part of the complete title of a musical piece. Furthermore, Musical Work titles are typically composed by more tokens, including common words which can be easily misclassified. The low performances obtained in the case of Musical Work entities can be a consequences of these observations. On the other hand, when referring to a Contributor users often use only the surname, but in most of the cases it is enough for the system to recognizing the entities.\nFrom the experiments we have seen that generally the biLSTM-CRF architecture outperforms the SVM model. The benefit of using the whole set of features is evident in the training part, but while testing the inclusion of the features not always leads to better results. In addition, some of the features designed in our experiments are tailored to the case of classical music, hence they might not be representative if applied to other fields. We do not exclude that our method can be adapted for detecting other kinds of entity, but it might be needed to redefine the features according to the case considered. Similarly, it has not been found a particular advantage of using the pre-trained embeddings instead of the one trained with our corpora. Furthermore, we verified the statistical significance of our experiment by using Wilcoxon Rank-Sum Test, obtaining that there have been not significant difference between the various model considered while testing.\nThe information extracted from the schedule also present several limitations. In fact, the hypothesis that a tweet is referring to a track broadcasted is not always verified. Even if it is common that radios listeners do comments about tracks played, or give suggestion to the radio host about what they would like to listen, it is also true that they might refer to a Contributor or Musical Work unrelated to the radio schedule.\n\nTable 2. Example of entities annotated and corresponding formal forms, from the user-generated tweet (1) in Table 1.\n\nTable 3. Examples of bot-generated tweets.\n\nTable 4. Tokens’ distributions within the two datasets: user-generated tweets (top) and bot-generated tweets (bottom)\n\nFig. 2. Example of the workflow for recognizing entities in UGC using the information from the radio schedule\n\nTable 6. F1 score for Contributor(C) and Musical Work(MW) entities recognized from bot-generated tweets (top) and user-generated tweets (bottom)\n\nTable 8. Precision (P), Recall (R) and F1 score for Contributor (C) and Musical Work (MW) entities recognized from user-generated tweets using the biLSTM-CRF network together with the schedule matching. The thresholds used for the matching are t=1200, w=0.5, c=0.5.\n\nQuestion: What are their results on the entity recognition task?",
"role": "user"
},
{
"content": "{\"answer\": [\"With both test sets performances decrease, varying between 94-97%\"], \"evidence\": [\"The performances of the NER experiments are reported separately for three different parts of the system proposed.\", \"Table 6 presents the comparison of the various methods while performing NER on the bot-generated corpora and the user-generated corpora. Results shown that, in the first case, in the training set the F1 score is always greater than 97%, with a maximum of 99.65%. With both test sets performances decrease, varying between 94-97%. In the case of UGC, comparing the F1 score we can observe how performances significantly decrease. It can be considered a natural consequence of the complex nature of the users\\u0027 informal language in comparison to the structured message created by the bot.\"]}",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.1729
|
[
{
"content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nThe UK Resilience Programme: a school-based universal nonrandomized pragmatic controlled trial.\nAbstract 1:\nOBJECTIVE The study aim ed to assess the effectiveness of an 18-hr cognitive behavioral group intervention in reducing depressive symptoms ( and associated outcomes ) in a universal sample of students in mainstream schools in Engl and . The intervention , the UK Resilience Programme ( UKRP ) , was based on the Penn Resiliency Program for Children and Adolescents . METHOD Students ( N = 2,844 ; 49 % female ; 67 % White ) were ages 11 - 12 at 16 schools . Classes of students were assigned arbitrarily into intervention ( UKRP ) or control ( usual school provision ) conditions based on class timetables . Outcome measures were the Children 's Depression Inventory ( Kovacs , 1992 ) ( depressive symptoms , primary outcome ) ; Revised Children 's Manifest Anxiety Scale ( C. R. Reynolds & Richmond , 1985 ) ( anxiety ) ; and child-reported Goodman ( 1997 ) Strengths and Difficulties Question naire ( behavior ) . Students were surveyed at baseline , postintervention , 1-year follow-up , and 2-year follow-up . RESULTS At postintervention , UKRP students reported lower levels of depressive symptoms than control group students , but the effect was small ( d = 0.093 , 95 % CI [ -0.178 , -0.007 ] , p = .034 ) and did not persist to 1-year or 2-year follow-ups . There was no significant impact on symptoms of anxiety or behavior at any point . CONCLUSIONS UKRP produced small , short-term impacts on depression symptoms and did not reduce anxiety or behavioral problems . These findings suggest that interventions may produce reduced impacts when rolled out and taught by regular school staff . We discuss the implication s of these findings for policy and for future dissemination efforts\n\n\nTitle 2:\nClassroom-based cognitive behaviour therapy (FRIENDS): a cluster randomised controlled trial to Prevent Anxiety in Children through Education in Schools (PACES).\nAbstract 2:\nBACKGROUND Anxiety in children is common , impairs everyday functioning , and increases the risk of severe mental health disorders in adulthood . We investigated the effect of a classroom-based cognitive behaviour therapy prevention programme ( FRIENDS ) on anxiety symptoms in children . METHODS Preventing Anxiety in Children though Education in Schools ( PACES ) is a three-group parallel cluster r and omised controlled trial . Interventions were given between September , 2011 , and July , 2012 , with schools as the unit of allocation and individual participants as the unit of analysis . We enrolled state-funded junior schools in southwest Engl and . We sent information to all eligible schools ( state-funded junior schools in southwest Engl and ) inviting them to enrol in the study . School year groups were assigned by computer-generated r and omisation ( 1:1:1 ) to receive either school-led FRIENDS ( led by teacher or school staff member ) , health-led FRIENDS ( led by two trained health facilitators ) , or usual school provision . Children were not masked to treatment allocation . The allocated programme was given to all students ( aged 9 - 10 years ) in the school year ( ie , universal delivery ) as part of the school curriculum as nine , 60 min weekly sessions . Outcomes were collected by self-completed question naire administered by research ers masked to allocation . Primary outcome was symptoms of anxiety and low mood at 12 months assessed by the Revised Child Anxiety and Depression Scale ( RCADS 30 ) . Analyses were intention to treat and accounted for the clustered nature of the design . The study is registered , number IS RCT N23563048 . FINDINGS 45 schools were enrolled : 14 ( n=497 children ) were r and omly assigned to school-led FRIENDS , 14 ( n=509 ) to health-led FRIENDS , and 12 ( n=442 ) to usual school provision . 1257 ( 92 % ) children completed 12 month assessment s ( 449 in health-led FRIENDS , 436 in school-led FRIENDS , and 372 in usual school provision ) . We recorded a difference at 12 months in adjusted mean child-reported RCADS scores for health-led versus school-led FRIENDS ( 19·49 [ SD 14·81 ] vs 22·86 [ 15·24 ] ; adjusted difference -3·91 , 95 % CI -6·48 to -1·35 ; p=0·0004 ) and health-led FRIENDS versus usual school provision ( 19·49 [ 14·81 ] vs 22·48 [ 15·74 ] ; -2·66 , -5·22 to -0·09 ; p=0·043 ) . We noted no differences in parent or teacher ratings . Training teachers to deliver mental health programmes was not as effective as delivery by health professionals . INTERPRETATION Universally delivered anxiety prevention programmes can be effective when used in schools . However , programme effectiveness varies depending on who delivers them . FUNDING National Institute for Health Research Public Health Research Programme\n\n\nTitle 3:\nImpact of contact on adolescents’ mental health literacy and stigma: the SchoolSpace cluster randomised controlled trial\nAbstract 3:\nObjectives To investigate whether intergroup contact in addition to education is more effective than education alone in reducing stigma of mental illness in adolescents . Design A pragmatic cluster r and omised controlled trial compared education alone with education plus contact . Blocking was used to r and omly stratify classes within schools to condition . R and om allocation was concealed , generated by a computer algorithm , and undertaken after pretest . Data was collected at pretest and 2-week follow-up . Analyses use an intention-to-treat basis . Setting Secondary schools in Birmingham , UK . Participants The parents and guardians of all students in year 8 ( age 12–13 years ) were approached to take part . Interventions A 1-day educational programme in each school led by mental health professional staff . Students in the ‘ contact ’ condition received an interactive session with a young person with lived experience of mental illness . Outcomes The primary outcome was students ’ attitudinal stigma of mental illness . Secondary outcomes included knowledge-based stigma , mental health literacy , emotional well-being and resilience , and help-seeking attitudes . Results Participants were recruited between 1 May 2011 and 30 April 2012 . 769 participants completed the pretest and were r and omised to condition . 657 ( 85 % ) provided follow-up data . At 2-week follow-up , attitudinal stigma improved in both conditions with no significant effect of condition ( 95 % CI −0.40 to 0.22 , p=0.5 , d=0.01 ) . Significant improvements were found in the education-alone condition compared with the contact and education condition for the secondary outcomes of knowledge-based stigma , mental health literacy , emotional well-being and resilience , and help-seeking attitudes . Conclusions Contact was found to reduce the impact of the intervention for a number of outcomes . Caution is advised before employing intergroup contact with younger student age groups . The education intervention appeared to be successful in reducing stigma , promoting mental health knowledge , and increasing mental health literacy , as well as improving emotional well-being and resilience . A larger trial is needed to confirm these results . Trial registration number IS RCT N07406026 ; Results\n\n\nTitle 4:\nEffectiveness of the Mindfulness in Schools Programme: non-randomised controlled feasibility study.\nAbstract 4:\nBACKGROUND Mindfulness-based approaches for adults are effective at enhancing mental health , but few controlled trials have evaluated their effectiveness among young people . AIMS To assess the acceptability and efficacy of a schools-based universal mindfulness intervention to enhance mental health and well-being . METHOD A total of 522 young people aged 12 - 16 in 12 secondary schools either participated in the Mindfulness in Schools Programme ( intervention ) or took part in the usual school curriculum ( control ) . RESULTS Rates of acceptability were high . Relative to the controls , and after adjusting for baseline imbalances , children who participated in the intervention reported fewer depressive symptoms post-treatment ( P = 0.004 ) and at follow-up ( P = 0.005 ) and lower stress ( P = 0.05 ) and greater well-being ( P = 0.05 ) at follow-up . The degree to which students in the intervention group practised the mindfulness skills was associated with better well-being ( P<0.001 ) and less stress ( P = 0.03 ) at 3-month follow-up . CONCLUSIONS The findings provide promising evidence of the programme 's acceptability and efficacy\n\n\nTitle 5:\nExamining reward-seeking, negative self-beliefs and over-general autobiographical memory as mechanisms of change in classroom prevention programs for adolescent depression\nAbstract 5:\nBackground Effective methods to prevent adolescent depressive symptoms could reduce suffering and burden across the lifespan . However , psychological interventions delivered to adolescents show efficacy only in symptomatic or high-risk youth . Targeting causal risk factors and assessing mechanistic change can help devise efficacious universal or classroom based prevention programs . Methods A non-r and omized longitudinal design was used to compare three classroom-based prevention programs for adolescent depression ( Behavioral Activation with Reward Processing , “ Thinking about Reward in Young People ” ( TRY ) ; Cognitive Behavioral Therapy ( CBT ) and Mindfulness Based Cognitive Therapy ( MBCT ) ) , and determine cognitive mechanisms of change in these programs . Cognitive mechanisms examined were reward-seeking , negative self-beliefs ( assessed with behavioral tasks ) and over-general autobiographical memory . 256 healthy adolescents aged 13–14 participated with 236 ( 92 % ) and 227 ( 89 % ) completing the pre- and post- assessment s. Results TRY was the only intervention associated with a reduction in depressive symptoms at follow-up . Reward-seeking increased following TRY . In the other programs there were non-significant changes in cognitive mechanisms , with more reflective negative self-beliefs in CBT and fewer over-general autobiographical memories in MBCT In the TRY program , which focused on increasing sensitivity to rewarding activities , reward seeking increased and this was associated with decreased depressive symptoms . Limitations Due to the infeasibility of a cluster r and omized controlled trial , a non-r and omized design was used . Conclusions Increased reward-seeking was associated with decreased depressive symptoms and may be a mechanism of depressive symptom change in the intervention with a focus on enhancing sensitivity and awareness of reward . This study provides preliminary evidence to suggest that incorporating activities to enhance reward sensitivity may be fruitful in r and omized controlled trials of universal prevention programs for depression\n\n\nTitle 6:\nThe feasibility of creating a checklist for the assessment of the methodological quality both of randomised and non-randomised studies of health care interventions.\nAbstract 6:\nOBJECTIVE : To test the feasibility of creating a valid and reliable checklist with the following features : appropriate for assessing both r and omised and non-r and omised studies ; provision of both an overall score for study quality and a profile of scores not only for the quality of reporting , internal validity ( bias and confounding ) and power , but also for external validity . DESIGN : A pilot version was first developed , based on epidemiological principles , review s , and existing checklists for r and omised studies . Face and content validity were assessed by three experienced review ers and reliability was determined using two raters assessing 10 r and omised and 10 non-r and omised studies . Using different raters , the checklist was revised and tested for internal consistency ( Kuder-Richardson 20 ) , test-retest and inter-rater reliability ( Spearman correlation coefficient and sign rank test ; kappa statistics ) , criterion validity , and respondent burden . MAIN RESULTS : The performance of the checklist improved considerably after revision of a pilot version . The Quality Index had high internal consistency ( KR-20 : 0.89 ) as did the subscales apart from external validity ( KR-20 : 0.54 ) . Test-retest ( r 0.88 ) and inter-rater ( r 0.75 ) reliability of the Quality Index were good . Reliability of the subscales varied from good ( bias ) to poor ( external validity ) . The Quality Index correlated highly with an existing , established instrument for assessing r and omised studies ( r 0.90 ) . There was little difference between its performance with non-r and omised and with r and omised studies . Raters took about 20 minutes to assess each paper ( range 10 to 45 minutes ) . CONCLUSIONS : This study has shown that it is feasible to develop a checklist that can be used to assess the method ological quality not only of r and omised controlled trials but also non-r and omised studies . It has also shown that it is possible to produce a checklist that provides a profile of the paper , alerting review ers to its particular method ological strengths and weaknesses . Further work is required to improve the checklist and the training of raters in the assessment of external validity\n\n\nTitle 7:\nChild anxiety treatment: outcomes in adolescence and impact on substance use and depression at 7.4-year follow-up.\nAbstract 7:\nResearch suggests that the sequelae of childhood anxiety disorders , if left untreated , can include chronic anxiety , depression , and substance abuse . The current study evaluated the maintenance of outcomes of children who received a 16-week cognitive-behavioral treatment for primary anxiety disorders ( generalized , separation , and social anxiety disorders ) an average of 7.4 years earlier . The 86 participants ( ages 15 to 22 years ; 91 % of the original sample ) and their parents completed diagnostic interviews and self- and parent-report measures . According to the diagnostic interviews , a meaningful percentage of participants maintained significant improvements in anxiety at long-term follow-up . With regard to sequelae , positive responders to anxiety treatment , as compared with less positive responders , had a reduced amount of substance use involvement and related problems at long-term follow-up . The findings are discussed with regard to child anxiety and some of its sequelae",
"role": "user"
},
{
"content": "1 RESULTS : Effectiveness of school-based universal interventions was found to be neutral or small with more positive effects found for poorer quality studies and those based in primary schools ( pupils aged 9 - 12 years ) .\nOverall , results suggested a trend whereby higher quality studies reported less positive effects .\nThe current evidence suggests there are neutral to small effects of universal , school-based interventions in the UK that aim to promote emotional or mental well-being or the prevention of mental health difficulties .",
"role": "assistant"
}
] |
science.genia_ner
|
science.genia_ner.1086
|
[
{
"content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"RNA\", \"CellLine\", \"Protein\", \"DNA\", \"CellType\"].\n\nPlease return the output as a JSON object of the format: {\"DNA\" : [\"TAL1\", ...], \"RNA\": [\"mRNAs\", ...], \"CellLine\": [\"T cells\", ...], \"CellType\": [\"monocytes\", ...], \"Protein\": [\"IL-2\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nComparison of the transactivation domains of Stat5 and Stat6 in lymphoid cells and mammary epithelial cells. Stat (signal transducers and activators of transcription) and Jak (Janus kinases) proteins are central components in the signal transduction events in hematopoietic and epithelial cells. They are rapidly activated by various cytokines, hormones, and growth factors. Upon ligand binding and cytokine receptor dimerization, Stat proteins are phosphorylated on tyrosine residues by Jak kinases. Activated Stat proteins form homo-or heterodimers, translocate to the nucleus, and induce transcription from responsive genes. Stat5 and Stat6 are transcription factors active in mammary epithelial cells and immune cells. Prolactin activates Stat5, and interleukin-4 (IL-4) activates Stat6. Both cytokines are able to stimulate cell proliferation, differentiation, and survival. We investigated the transactivation potential of Stat6 and found that it is not restricted to lymphocytes. IL-4-dependent activation of Stat6 was also observed in HC11 mammary epithelial cells. In these cells, Stat6 activation led to the induction of the beta-casein gene promoter. The induction of this promoter was confirmed in COS7 cells. The glucocorticoid receptor was able to further enhance IL-4-induced gene transcription through the action of Stat6. Deletion analysis of the carboxyl-terminal region of Stat6 and recombination of this region with a heterologous DNA binding domain allowed the delimitation and characterization of the transactivation domain of Stat6. The potencies of the transactivation domains of Stat5, Stat6, and viral protein VP16 were compared. Stat6 had a transactivation domain which was about 10-fold stronger than that of Stat5. In pre-B cells (Ba / F3), the transactivation domain of Stat6 was IL-4 regulated, independently from its DNA binding function.",
"role": "user"
},
{
"content": "{\"CellLine\": [\"mammary epithelial cells\", \"COS7 cells\", \"these cells\", \"HC11 mammary epithelial cells\"], \"CellType\": [\"pre - B cells\", \"mammary epithelial cells\", \"hematopoietic and epithelial cells\", \"lymphoid cells\", \"epithelial cells\"], \"DNA\": [\"beta - casein gene promoter\"], \"Protein\": [\"signal transducers and activators of transcription\", \"IL - 4\", \"Stat6\", \"viral protein VP16\", \"Stat\", \"glucocorticoid receptor\", \"Jak\", \"interleukin - 4\", \"cytokine receptor\", \"Stat5\", \"transactivation domains\", \"carboxyl - terminal region\", \"Jak kinases\", \"Stat proteins\", \"cytokines\", \"heterologous DNA binding domain\", \"Janus kinases\", \"transcription factors\"], \"RNA\": []}",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.5552
|
[
{
"content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nOxygen improves maximal exercise performance in interstitial lung disease.\nAbstract 1:\nWe examined whether arterial hypoxemia impairs incremental exercise performance in subjects with interstitial lung disease ( ILD ) . Seven subjects underwent two incremental exercise tests on a bicycle ergometer in r and om order ; one while breathing room air ( RA ) , and the other while breathing 60 % O2 . Maximal exercise performance was impaired in all subjects : maximal oxygen uptake ( peak VO2 ) was 56 + /- 4 % predicted ( + /- SEM ) ; and all subjects demonstrated significant arterial oxygen desaturation during exercise breathing RA ( mean 11 + /- 1 % ) . Breathing 60 % O2 during exercise result ed in a significant increase in peak VO2 ( RA : 1.32 + /- 0.05 L/min ; O2 : 1.58 + /- 0.08 L/min ; p < 0.05 ) , exercise duration ( RA : 390 + /- 21 s ; O2 : 458 + /- 24 s ; p < 0.01 ) and maximal work load ( RA : 112 + /- 6 watts ; O2 : 129 + /- 6 watts ; p < 0.005 ) . There was no significant difference in maximal minute ventilation ( VI ) achieved at the end of both tests . At matched ventilation ( 90 % peak VI from the RA test ) , respiratory frequency ( f ) was significantly higher ( RA : 33 + /- 2 breaths/min ; O2 : 35 + /- 2 breaths/min ; p < 0.05 ) , and tidal volume ( VT ) significantly lower ( RA : 1.72 + /- 0.15 L ; O2 : 1.64 + /- 0.12 ; p < 0.05 ) when subjects exercised breathing oxygen . We conclude that arterial hypoxemia significantly impairs incremental exercise performance in subjects with ILD , but that mechanisms other than arterial oxygen desaturation are responsible for the rapid , shallow breathing pattern these subjects adopt during exercise\n\n\nTitle 2:\nClinically important differences in the intensity of chronic refractory breathlessness.\nAbstract 2:\nCONTEXT Clinical ly important differences in chronic refractory breathlessness are ill defined but important in clinical practice and trial design . OBJECTIVES To estimate the clinical relevance of differences in breathlessness intensity using distribution and patient anchor methods . METHODS This was a retrospective data analysis from 213 data sets from four clinical trials for refractory breathlessness . Linear regression was used to explore the relationship between study effect size and change in breathlessness score ( 0 - 100 mm visual analogue scale ) and to estimate the change in score equivalent to small , moderate , and large effect sizes . Pooled individual blinded patient preference data from three r and omized controlled trials were analyzed . The difference between the mean change in Day 4 minus baseline scores between preferred and non-preferred arms was calculated . RESULTS There was a strong relationship between change in score and effect size ( P = 0.001 ; R(2 ) = 0.98 ) . Values for small , moderate , and large effects were -5.5 , -11.3 , and -18.2 mm . The participant preference change in score was -9 mm ( 95 % CI , -15.8 , -2.1 ) ( P = 0.008 ) . CONCLUSION This larger data set supports a clinical ly important difference of 10 mm . Studies should be powered to detect this difference\n\n\nTitle 3:\nEffects of oxygen on exercise-induced increase of pulmonary arterial pressure in idiopathic pulmonary fibrosis.\nAbstract 3:\nINTRODUCTION Idiopathic pulmonary fibrosis ( IPF ) is a severe disease with no known effective therapy . Patients with IPF may develop severe increase of pulmonary arterial pressure ( PAP ) on exercise , the mechanisms of which is not clearly identified . OBJECTIVES To determine whether oxygen may correct the increase of PAP developed during exercise in patients with IPF . PATIENTS AND METHODS We performed a prospect i ve study on patients with IPF and no hypoxaemia at rest . The absence of pulmonary hypertension ( PH ) at rest was confirmed by echocardiography ( systolic PAP < 35 mmHg ) . Eight patients underwent echocardiography during exercise in air and with oxygen ( to maintain saturation of at least 94 % ) . Right ventricle-right atrium gradient and cardiac output were measured at rest , after each increment and at peak . We then compared the echocardiographic results obtained for air and oxygen . RESULTS All patients developed significant increase of SPAP on exercise ( 73 + /- 14 mmHg in air ) . Oxygen did not significantly improve SPAP on exercise ( SPAP : 76 + /- 15 mmHg ) . Echocardiographic characteristics were similar between air and oxygen except for exercise tolerance in term of workload ( p=0.045 ) and endurance ( p=0.017 ) . Resting pulmonary function tests did not predict the occurrence of increase of PAP on exercise . CONCLUSION Our results demonstrate that oxygen does not improve exercise-induced increase of PAP in patients with IPF and support the hypothesis that hypoxic vaso-constriction is not the main mechanism of acute increase of PAP during exercise\n\n\nTitle 4:\nLONG TERM DOMICILIARY OXYGEN THERAPY IN CHRONIC HYPOXIC COR PULMONALE COMPLICATING CHRONIC BRONCHITIS AND EMPHYSEMA: Report of the Medical Research Council Working Party\nAbstract 4:\nA controlled trial of long term domiciliary oxygen therapy has been carried out in three centres in the U.K. The 87 patients , all under 70 years of age , who took part had chronic bronchitis or emphysema with irreversible airways obstruction , severe arterial hypoxaemia , carbon dioxide retention , and a history of congestive heart failure . The patients were r and omised to oxygen therapy ( treated ) or no oxygen ( controls ) . Oxygen was given by nasal prongs for at least 15 h daily , usually at 2 1/min . The two groups were well matched , both clinical ly and in terms of lung function and other laboratory findings . 19 of the 42 oxygen treated patients died in the five years of survival follow-up compared with 30 out of 45 controls : in the 66 men in this trial the survival advantage of oxygen did not emerge until 500 days had elapsed . Survival for the 12 female controls was surprisingly poor , 8 of them being dead at 3 years . Mortality was not easy to predict , though a summation of arterial carbon dioxide tension and red cell mass was helpful . Neither time spent in hospital because of exacerbations of respiratory failure nor work attendance were affected by oxygen therapy , but these patients were very ill at the start of the trial and many had already retired on grounds of age or ill-health . Physiological measurements suggested that oxygen did not slow the progress of respiratory failure in those who died early . However , in longer term survivors on oxygen , arterial oxygenation did seem to stop deterioration\n\n\nTitle 5:\nContinuous or nocturnal oxygen therapy in hypoxemic chronic obstructive lung disease: a clinical trial. Nocturnal Oxygen Therapy Trial Group.\nAbstract 5:\nAt six centers , 203 patients with hypoxemic chronic obstructive lung disease were r and omly allocated to either continuous oxygen ( O2 ) therapy or 12-hour nocturnal O2 therapy and followed for at least 12 months ( mean , 19.3 months ) . The two groups were initially well matched in terms of physiological and neuropsychological function . Compliance with each oxygen regimen was good . Overall mortality in the nocturnal O2 therapy group was 1.94 times that in the continuous O2 therapy group ( P = 0.01 ) . This trend was striking in patients with carbon dioxide retention and also present in patients with relatively poor lung function , low mean nocturnal oxygen saturation , more severe brain dysfunction , and prominent mood disturbances . Continuous O2 therapy also appeared to benefit patients with low mean pulmonary artery pressure and pulmonary vascular resistance and those with relatively well-preserved exercise capacity . We conclude that in hypoxemic chronic obstructive lung disease , continuous O2 therapy is associated with a lower mortality than is nocturnal O2 therapy . The reason for this difference is not clear\n\n\nTitle 6:\nSymptomatic benefit of supplemental oxygen in hypoxemic patients with chronic lung disease.\nAbstract 6:\nWe have compared the symptomatic benefit of air and oxygen at rest in hypoxemic patients with chronic obstructive airway disease ( COAD ) or interstitial lung disease ( ILD ) . A total of 12 severely disabled patients with COAD ( mean + /- SEM , PaO2 , 50.3 + /- 3.7 mm Hg ) and 10 with ILD ( PaO2 , 48.0 + /- 3.1 mm Hg ) received 28 % oxygen and air by Venturi face mask , each gas on two occasions , in a double-blind r and omized fashion . SaO2 increased ( p less than 0.01 ) in both groups during oxygen breathing : COAD , 85.1 + /- 2.3 % versus 93.1 + /- 1.4 % ; ILD , 85.5 + /- 1.7 % versus 94.7 + /- 0.9 % . The patients with COAD stated that air helped their breathing on 15 of 24 occasions and that oxygen helped on 22 of 24 occasions ( p less than 0.05 ) . In the patients with ILD the values were 6 of 20 and 13 of 20 occasions , respectively ( p less than 0.05 ) . In both groups of patients the severity of breathlessness recorded on a 100-mm visual analog scale was significantly ( p less than 0.05 ) lower during oxygen breathing : COAD , 29.6 + /- 4.5 versus 45.6 + /- 6.0 ; ILD , 30.2 + /- 5.1 versus 48.1 + /- 4.4 . Ventilation measured by magnetometers was significantly lower during oxygen breathing in the patients with COAD ( 8.2 + /- 1.0 versus 9.3 + /- 1.1 L/min ; p less than 0.05 ) , but the difference between oxygen and air in patients with ILD was not statistically significant ( 9.3 + /- 1.3 versus 11.2 + /- 1.6 L/min ; p greater than 0.05 ) . ( ABSTRACT TRUNCATED AT 250 WORDS\n\n\nTitle 7:\nEffect of ambulatory oxygen on exertional dyspnea in IPF patients without resting hypoxemia.\nAbstract 7:\nBACKGROUND AND OBJECTIVE The effects of ambulatory oxygen for idiopathic pulmonary fibrosis ( IPF ) patients without resting hypoxemia have not been eluci date d. The purpose of this study was to assess the effect of ambulatory oxygen on dyspnea in IPF patients without resting hypoxemia but with desaturation on exertion . METHODS This was a double-blind , placebo-controlled , r and omized crossover trial of ambulatory oxygen versus ambulatory air . Patients with IPF who had a partial pressure of arterial oxygen ( PaO2 ) between 60 mm Hg and 80 mm Hg at rest , and desaturation of 88 % or less in a room-air 6-min walk test were eligible . Patients underwent a st and ardized 6-min walk test and a 6-min free walk test under each ambulatory gas . Oxygen and air were provided at 4 L/min intranasally . Dyspnea was evaluated immediately , 1 , and 2 min after the tests . RESULTS Twenty patients ( 16 men ) , with a mean age of 73.5 ( SD 4.1 ) years , % predicted forced vital capacity ( FVC ) of 71.0 ( 13.3 ) % , % predicted diffusion capacity for carbon monoxide ( DLco ) of 57.0 ( 13.3 ) % , and PaO2 of 72.5 ( 5.4 ) mm Hg were recruited . No significant differences in dyspnea were observed between ambulatory oxygen and air at each time point . However , some patients showed improvement in dyspnea with oxygen on an individual basis . CONCLUSIONS Since oxygen provides no additional benefit over air in terms of exertional dyspnea for IPF patients without resting hypoxemia , routine prescription of ambulatory oxygen is not recommended . However , assessment on an individual basis is necessary . Trial registration . UMIN Clinical Trial Registry ; No.:UMIN000005098 ; URL :",
"role": "user"
},
{
"content": "This systematic review showed no effects of oxygen therapy on dyspnoea during exercise in ILD , although exercise capacity was increased .",
"role": "assistant"
}
] |
science.bioasq_general_qa
|
science.bioasq_general_qa.523
|
[
{
"content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is the function of mTOR?\n\nContext: Protein synthesis regulation via mammalian target of rapamycin complex 1 (mTORC1) signaling pathway has key roles in neural development and function,\nmTOR regulates assembly of the translation initiation machinery by interacting with the eukaryotic initiation factor eIF3 complex and by controlling phosphorylation of key translational regulators\nMammalian target of rapamycin (mTOR) complexes, mTORC1 and mTORC2, are master regulators of cellular survival, growth and metabolism\n(mTOR) is a serine-threonine kinase that controls several important aspects of mammalian cell function. mTOR activity is modulated by various intra- and extracellular factors; in turn, mTOR changes rates of translation, transcription, protein degradation, cell signaling, metabolism, and cytoskeleton dynamics. mTOR has been repeatedly shown to participate in neuronal development and the proper functioning of mature neurons.\nmammalian target of rapamycin (mTOR), a member of the phosphoinositide 3-kinase related kinase (PIKK) family, plays a central role in the regulation of cell growth\n(mTOR) is a serine/threonine kinase and that forms two multiprotein complexes known as the mTOR complex 1 (mTORC1) and mTOR complex 2 (mTORC2). mTOR regulates cell growth, proliferation and survival\n(mTOR), a downstream effector of the phosphatidylinositol 3-kinase (PI3K)/Akt (protein kinase B) signaling pathway that mediates cell survival and proliferation,",
"role": "user"
},
{
"content": "The mTOR protein regulates assembly of the translation initiation machinery and are master regulators of cellular survival, growth and metabolism.",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.11455
|
[
{
"content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nSize is everything – large amounts of information are needed to overcome random effects in estimating direction and magnitude of treatment effects\nAbstract 1:\nAbstract Variability in patients ' response to interventions in pain and other clinical setting s is large . Many explanations such as trial methods , environment or culture have been proposed , but this paper sets out to show that the main cause of the variability may be r and om chance , and that if trials are small their estimate of magnitude of effect may be incorrect , simply because of the r and om play of chance . This is highly relevant to the questions of ‘ How large do trials have to be for statistical accuracy ? ’ and ‘ How large do trials have to be for their results to be clinical ly valid ? ’ The true underlying control event rate ( CER ) and experimental event rate ( EER ) were determined from single‐dose acute pain analgesic trials in over 5000 patients . Trial group size required to obtain statistically significant and clinical ly relevant ( 0.95 probability of number‐needed‐to‐treat within ±0.5 of its true value ) results were computed using these values . Ten thous and trials using these CER and EER values were simulated using varying group sizes to investigate the variation due to r and om chance alone . Most common analgesics have EERs in the range 0.4–0.6 and CER of about 0.19 . With such efficacy , to have a 90 % chance of obtaining a statistically significant result in the correct direction requires group sizes in the range 30–60 . For clinical relevance nearly 500 patients are required in each group . Only with an extremely effective drug ( EER>0.8 ) will we be reasonably sure of obtaining a clinical ly relevant NNT with commonly used group sizes of around 40 patients per treatment arm . The simulated trials showed substantial variation in CER and EER , with the probability of obtaining the correct values improving as group size increased . We contend that much of the variability in control and experimental event rates is due to r and om chance alone . Single small trials are unlikely to be correct . If we want to be sure of getting correct ( clinical ly relevant ) results in clinical trials we must study more patients . Credible estimates of clinical efficacy are only likely to come from large trials or from pooling multiple trials of conventional ( small ) size\n\n\nTitle 2:\nDifluoromethylornithine Plus Sulindac for the Prevention of Sporadic Colorectal Adenomas: A Randomized Placebo-Controlled, Double-Blind Trial\nAbstract 2:\nAbstract Pre clinical studies of chemoprevention drugs given in combination at low doses show remarkable efficacy in preventing adenomas with little additional toxicities , suggesting a strategy to improve risk to benefit ratios for preventing recurrent adenomas . Three hundred seventy-five patients with history of resected ( ≥3 mm ) adenomas were r and omly assigned to receive oral difluoromethylornithine ( DFMO ) 500 mg and sulindac 150 mg once daily or matched placebos for 36 months , stratified by use of low-dose aspirin ( 81 mg ) at baseline and clinical site . Follow-up colonoscopy was done 3 years after r and omization or off- study . Colorectal adenoma recurrence was compared among the groups with log-binomial regression . Comparing the outcome in patients receiving placebos to those receiving active intervention , ( a ) the recurrence of one or more adenomas was 41.1 % and 12.3 % ( risk ratio , 0.30 ; 95 % confidence interval , 0.18 - 0.49 ; P < 0.001 ) ; ( b ) 8.5 % had one or more advanced adenomas , compared with 0.7 % of patients ( risk ratio , 0.085 ; 95 % confidence interval , 0.011 - 0.65 ; P < 0.001 ) ; and ( c ) 17 ( 13.2 % ) patients had multiple adenomas ( > 1 ) at the final colonoscopy , compared with 1 ( 0.7 % ; risk ratio , 0.055 ; 0.0074 - 0.41 ; P < 0.001 ) . Serious adverse events ( grade ≥3 ) occurred in 8.2 % of patients in the placebo group , compared with 11 % in the active intervention group ( P = 0.35 ) . There was no significant difference in the proportion of patients reporting hearing changes from baseline . Recurrent adenomatous polyps can be markedly reduced by a combination of low oral doses of DFMO and sulindac and with few side effects\n\n\nTitle 3:\nDeriving dichotomous outcome measures from continuous data in randomised controlled trials of analgesics: verification from independent data\nAbstract 3:\nAbstract A previously established relationship for deriving dichotomous from continuous information in r and omised controlled trials ( RCTs ) of analgesics has been tested using an independent data set . Individual patient information from 18 RCTs of parallel‐group design in acute postoperative pain ( after abdominal , gynaecological and oral surgery ) was used to calculate the percentage of the maximum possible pain relief score ( % maxTOTPAR ) and the proportion of patients with > 50%maxTOTPAR for the different treatments . The relationship between the measures was investigated in 85 treatments with over 3400 patients . In 80 of 85 treatments ( 94 % ) agreement between calculated and actual number of patients with > 50%maxTOTPAR was within four patients per treatment and in 72 ( 85 % ) was within three ( average of 40 patients per treatment , range 21–58 patients ) . Summing the positive and negative differences between actual and calculated numbers of patients with > 50%maxTOTPAR gave an average difference of 0.30 patients per treatment arm . Reports of RCTs of analgesics frequently describe results of studies in the form of mean derived indices , rather than using discontinuous events , such as number or proportion of patients with 50 % pain relief . Because mean data inadequately describe information with a non‐normal distribution , combining mean data in systematic review s may compromise the results . Showing that dichotomous data can reliably be derived from mean data in acute pain studies enables data published as means to be used for quantitative systematic review s which require data in dichotomous form\n\n\nTitle 4:\nDeriving dichotomous outcome measures from continuous data in randomised controlled trials of analgesics\nAbstract 4:\n& NA ; Reports of RCTs of analgesics frequently describe results of studies in the form of mean derived indices , rather than using discontinuous events — such as number or proportion of patients with 50 % pain relief . Because mean data inadequately describe information with a non‐normal distribution , combining mean data in systematic review s may compromise the results . Showing that dichotomous data can reliably be derived from mean data , at least in acute pain models , indicates that more meaningful overviews or meta‐ analysis may be possible . This study investigated the relationship between continuous and dichotomous analgesic measures in a set of individual patient data , and then used that relationship to derive dichotomous from continuous information in r and omised controlled trials ( RCTs ) of analgesics . Individual patient information from 13 RCTs of parallel‐group and crossover design in acute postoperative pain was used to calculate the percentage of the maximum possible pain relief score ( % maxTOTPAR ) and the proportion of patients with greater than 50 % pain relief ( > 50%maxTOTPAR ) for the different treatments . The relationship between the measures was investigated in 45 actual treatments and 10 000 treatments simulated using the underlying actual distribution ; 1283 patients had 45 separate treatments . Mean % maxTOTPAR correlated with the proportion of patients with > 50%maxTOTPAR ( r2 = 0.90 ) . The relationship calculated from all the 45 treatments predicted to within three patients the number of patients with more than 50 % pain relief in 42 of 45 treatments , and 98.8 % of 10 000 simulated treatments . For seven effective treatments , actual numbers‐needed‐to‐treat ( NNT ) to achieve > 50%maxTOTPAR compared with placebo were very similar to those derived from calculated data\n\n\nTitle 5:\nA double-blind randomized study of fetal side effects during and after the short-term maternal administration of indomethacin, sulindac, and nimesulide for the treatment of preterm labor.\nAbstract 5:\nOBJECTIVE The purpose of this study was to establish whether nimesulide causes fewer fetal side effects than indomethacin or sulindac after short-term maternal exposure for tocolysis . STUDY DESIGN This was a double-blind , double-dummy prospect i ve r and omized study with three drug treatment groups ( n = 10 per group ) that were comprised of subjects who were at 28 to 32 weeks of gestation with preterm contractions . The subjects were treated in the delivery suites of two busy inner-city teaching hospitals ; the intervention consisted of 48 hours of treatment and with 72 hours of follow-up observation with indomethacin 100 mg ( twice daily ) , sulindac 200 mg ( twice daily ) , or nimesulide 200 mg ( twice daily ) . The amniotic fluid index , hourly fetal urine production , and ductal Doppler pulsatility index observations were monitored before the treatment and at 4 , 24 , 48 , 72 , and 120 hours after the treatment was started . The statistical analysis used repeated measures analysis of variance , Bonferroni test , and Bl and -Altman agreement . Significance assumed when the probability value was < .05 . RESULTS Each drug caused a significant reduction in all three observations over the 48-hour treatment period , which recovered to pretreatment levels by 72 hours after treatment . There were no significant differences among drugs for any of these effects . CONCLUSION Nimesulide causes similar short-term fetal side effects to indomethacin and sulindac\n\n\nTitle 6:\nThe effect of long-term treatment with sulindac on the progression of diabetic retinopathy*\nAbstract 6:\nABSTRACT Objective : To evaluate the effects of long-term treatment with sulindac on the progression of diabetic retinopathy ( DR ) . Research design and methods : 40 Japanese patients with type 2 diabetes were enrolled in a r and omized , single-blind controlled trial in which the effects of sulindac ( 200 mg/day , 100 mg twice a day ; n = 16 patients ) on the progression of DR were compared to controls ( 24 patients ) for 3 years . All patients were comparable in their age , gender , duration of disease , body mass index , dipstick proteinuria , insulin therapy , glycemic control , and clinical stages of DR . Outcome was determined by comparing parameters of retinopathy in fundus photographs that were taken at time 0 to those taken 1 , 2 , and 3 years after the initiation of treatment . Results : Patients in the sulindac group did not develop DR during the course of treatment nor was there progression of pathology in those who began the study with mild non-proliferative DR ( NPDR ) . On the other h and , six patients progressed to mild NPDR in the control group – three at year 1 and three at year 3 – and an additional patient progressed to severe NPDR from mild NPDR by year 1 and to proliferative DR by year 2 . The findings at year 3 in the sulindac group were significantly ( p < 0.05 ) different from the control group . None of the patients experienced any adverse effects of treatment . Conclusions : Long-term treatment with sulindac was clinical ly effective in decreasing the progression of mild DR in type 2 diabetic patients in this pilot study\n\n\nTitle 7:\nDeveloping a database of published reports of randomised clinical trials in pain research \nAbstract 7:\n& NA ; A data base of r and omised clinical trials ( RCTs ) in pain research published from 1950 to 1990 was created following an extensive literature search . By applying a refined MEDLINE search strategy from 1966 to 1990 and by h and ‐ search ing more than 1 000 000 pages of a total of 40 biomedical journals published during the period 1950–1990 , more than 8000 RCTs were identified . The RCTs were published in more than 800 journals and over 85 % appeared between 1976 and 1990 . If the trend of the last 15 years persists , a total of more than 15 000 RCTs will be published in pain relief by the year 2000 . A detailed description of methods to ensure efficient use of re sources during the identification , retrieval and management of the information in pain relief and other fields is given . Emphasis is made on the importance of refining MEDLINE search strategies , on the use of volunteers to h and ‐ search journals and on careful monitoring of each of the steps of the process . The potential uses of the data base to guide clinical and research decisions are discussed\n\n\nTitle 8:\nThe visual analogue pain intensity scale: what is moderate pain in millimetres?\nAbstract 8:\nAbstract One way to ensure adequate sensitivity for analgesic trials is to test the intervention on patients who have established pain of moderate to severe intensity . The usual criterion is at least moderate pain on a categorical pain intensity scale . When visual analogue scales ( VAS ) are the only pain measure in trials we need to know what point on a VAS represents moderate pain , so that these trials can be included in meta‐ analysis when baseline pain of at least moderate intensity is an inclusion criterion . To investigate this we used individual patient data from 1080 patients from r and omised controlled trials of various analgesics . Baseline pain was measured using a 4‐point categorical pain intensity scale and a pain intensity VAS under identical conditions . The distribution of the VAS scores was examined for 736 patients reporting moderate pain and for 344 reporting severe pain . The VAS scores corresponding to moderate or severe pain were also examined by gender . Baseline VAS scores recorded by patients reporting moderate pain were significantly different from those of patients reporting severe pain . Of the patients reporting moderate pain 85 % scored over 30 mm on the corresponding VAS , with a mean score of 49 mm . For those reporting severe pain 85 % scored over 54 mm with a mean score of 75 mm . There was no difference between the corresponding VAS scores of men and women . Our results indicate that if a patient records a baseline VAS score in excess of 30 mm they would probably have recorded at least moderate pain on a 4‐point categorical scale\n\n\nTitle 9:\nA comparison of ketoprofen SR and sulindac in the elderly with rheumatoid arthritis.\nAbstract 9:\nThe elderly ( age > 65 years ) are more vulnerable to side-effects induced by non-steroidal anti-inflammatory drugs ( NSAIDs ) . We therefore performed a double-blind comparative study of ketoprofen SR and sulindac in patients with active rheumatoid arthritis , 65 years of age or older . Sulindac was chosen because of its possible renal sparing effects , and ketoprofen SR because of its short half life and sustained release delivery system . Eighty patients were entered . More patients withdrew from the study due to side-effects in the sulindac group ; both treatment groups had a high incidence of side-effects during this study and during previous exposure to other NSAIDs , demonstrating that the elderly are susceptible to side-effects from NSAIDs",
"role": "user"
},
{
"content": "AUTHORS ' CONCLUSIONS In the absence of evidence of efficacy , at present , for oral sulindac in acute postoperative pain , its use in this indication is not justified .",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.752
|
[
{
"content": "Given a short query with keyphrases about a research idea in 2019 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from options provided. A short description of the datasets is also provided to help you.\n\nQuery: I want to find a method for object classification from point clouds.\n\nKeyphrases: 3d object classification point clouds\n\nDataset description:\nScanObjectNN: ScanObjectNN is a newly published real-world dataset comprising of 2902 3D objects in 15 categories. It is a challenging point cloud classification datasets due to the background, missing parts and deformations.\nCompletion3D: The Completion3D benchmark is a dataset for evaluating state-of-the-art 3D Object Point Cloud Completion methods. Ggiven a partial 3D object point cloud the goal is to infer a complete 3D point cloud for the object.\nSNIPS: The SNIPS Natural Language Understanding benchmark is a dataset of over 16,000 crowdsourced queries distributed among 7 user intents of various complexity: SearchCreativeWork (e.g. Find me the I, Robot television show), GetWeather (e.g.\nShapeNet: ShapeNet is a large scale repository for 3D CAD models developed by researchers from Stanford University, Princeton University and the Toyota Technological Institute at Chicago, USA. The repository contains over 300M models with 220,000 classified into 3,135 classes arranged using WordNet hypernym-hyponym relationships.\n\nOptions:- A: ScanObjectNN B: Completion3D C: SNIPS D: ShapeNet",
"role": "user"
},
{
"content": "ShapeNet",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.4413
|
[
{
"content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nNondestructive, in vitro quantification of crown margins.\nAbstract 1:\nSTATEMENT OF PROBLEM It is important that artificial crowns fit the prepared tooth accurately , as marginal deficiencies are predisposed to plaque accumulation and lead to increased risk of periodontal disease . Various methods of evaluation for marginal fit are described in the literature , but most approaches are limited by destructive methods of assessment and /or small points of measurement . PURPOSE This study compared , in vitro , the marginal fit of 4 types of complete crowns on human premolar teeth with the use of nondestructive profilometry . This method determined whether fit was influenced by type of crown or surface morphology of the tooth , namely , grooved or ungrooved surfaces . MATERIAL AND METHODS Four groups of specimens were prepared for complete crowns : group BA , bonding alloy with chamfer finish line ; group G , gold alloy with chamfer finish line ; group PC , porcelain with a chamfer finish line ; and group PS , porcelain with a shoulder finish line . Two profiles of grooved mesial and ungrooved distal surfaces of the teeth were performed : ( 1 ) teeth prepared for each type of crown and ( 2 ) teeth with crowns seated but not cemented . Marginal fit ( absolute marginal discrepancy ) from the finish line edge of the tooth preparations to crown edges ( CE ) and leading edges ( LE ) of crowns were measured . RESULTS A 2-way analysis of variance for crown type and tooth surface morphology revealed significant differences between crown types for all measurement parameters , except vertical LE . The effect of surface morphology was not significant , except for vertical LE ( P<.05 ) . For all parameters , except vertical LE , the ranking of marginal fit discrepancies from greatest to least was as follows : group PC , G , BA , and PS . For vertical LE distances , the ranking was PS , BA , G , and PC ( P<.05 ) . CONCLUSION Profilometry was used as a nondestructive , accurate method of evaluating the absolute marginal fit of different types of crowns . Marginal fits varied continuously around the circumference of each crown and made clinical assessment of fit accuracy subjective and arduous\n\n\nTitle 2:\nMisfit and microleakage of implant-supported crown copings obtained by laser sintering and casting techniques, luted with glass-ionomer, resin cements and acrylic/urethane-based agents.\nAbstract 2:\nOBJECTIVES This study evaluated the marginal misfit and microleakage of cement-retained implant-supported crown copings . METHODS Single crown structures were constructed with : ( 1 ) laser-sintered Co-Cr ( LS ) ; ( 2 ) vacuum-cast Co-Cr ( CC ) and ( 3 ) vacuum-cast Ni-Cr-Ti ( CN ) . Sample s of each alloy group were r and omly luted in st and ard fashion onto machined titanium abutments using : ( 1 ) GC Fuji PLUS ( FP ) ; ( 2 ) Clearfil Esthetic Cement ( CEC ) ; ( 3 ) RelyX Unicem 2 Automix ( RXU ) and ( 4 ) DentoTemp ( DT ) ( n=15 each ) . After 60 days of water ageing , vertical discrepancy was SEM-measured and cement microleakage was scored using a digital microscope . Misfit data were subjected to two-way ANOVA and Student-Newman-Keuls multiple comparisons tests . Kruskal-Wallis and Dunn 's tests were run for microleakage analysis ( α=0.05 ) . RESULTS Regardless of the cement type , LS sample s exhibited the best fit , whilst CC and CN performed equally well . Despite the framework alloy and manufacturing technique , FP and DT provide comparably better fit and greater microleakage scores than did CEC and RXU , which showed no differences . CONCLUSIONS DMLS of Co-Cr may be a reliable alternative to the casting of base metal alloys to obtain well-fitted implant-supported crowns , although all the groups tested were within the clinical ly acceptable range of vertical discrepancy . No strong correlations were found between misfit and microleakage . Notwithst and ing the framework alloy , definitive resin-modified glass-ionomer ( FP ) and temporary acrylic/urethane-based ( DT ) cements demonstrated comparably better marginal fit and greater microleakage scores than did 10-methacryloxydecyl-dihydrogen phosphate-based ( CEC ) and self-adhesive ( RXU ) dual-cure resin agents\n\n\nTitle 3:\nEffect of in vivo crown margin discrepancies on periodontal health.\nAbstract 3:\nNumerous reports have suggested a relationship between marginal adaptation of dental castings and periodontal tissue health , and this study examined this relationship quantitatively . Forty-two crown restorations in 29 r and omly selected patients were selected for this study using three criteria . ( 1 ) The crowns were placed at the University of North Carolina School of Dentistry ; ( 2 ) the crowns were in service for a minimum of 4 years ; and ( 3 ) the crown margins were within the intracrevicular crevice ( subgingival ) . Replica impressions of the facial margins of specific crowns were made with a vinyl polysiloxane impression material , and poured casts were prepared for scanning electron micrograph evaluation . Marginal discrepancy measurements were identified on each micrograph at 10 equally spaced locations along the margin and averaged for each specimen . Periodontal indices of pocket depths , crevicular fluid volume , and gingival index were accumulated for clinical measurements . Pearson correlation and Bonferroni adjusted probability tests were performed , but no significant correlation was found between marginal discrepancy ( 0.16 + /- 0.13 mm ) and pocket depth ( 2.4 + /- 0.9 mm ) . However , a strong correlation ( p less than 0.001 ) existed between marginal discrepancy and gingival index ( 2 + /- 0.8 ) and between marginal discrepancies and crevicular fluid volume ( 49.9 + /- 31.1 ) . These results established that a significant quantitative relationship existed between the marginal discrepancy and periodontal tissue inflammation for subgingivally located crown margins\n\n\nTitle 4:\nMarginal adaptation of fixed prosthodontics: a new in vitro 360-degree external examination procedure.\nAbstract 4:\nPURPOSE This study evaluated the marginal fit of experimental and custom-made fixed prosthetic restorations through a new 360-degree external examination . The minimum number of gap measurements required to produce relevant results for gap analysis was also investigated . MATERIAL S AND METHODS The marginal fit of six experimental and eight custom-made crowns was observed microscopically by means of a mechanical device , and software was employed to measure the gap . Two crowns , chosen from among the 14 previously evaluated , were reanalyzed to determine the minimum number of gap measurements required to produce significant results for gap analysis . RESULTS The precision obtained with the custom-made crowns differed from that of the experimental specimens . The minimum number of measurements required to produce a sample mean value within + /- 5 microm of the mean , calculated over 360 measurements , taking st and ard error of the means < or = 4 microm , was 18 for experimental and 90 for custom-made crowns , for both equidistant measurement spacing and r and omly selected points . CONCLUSION Differences in fit between experimental specimens and custom-made ones showed that experimental results might not always be obtained in clinical practice . Within the limitations of the protocol of this study , the minimum number of measurements required to ensure relevant results for gap analysis was 18 for experimental and 90 for custom-made crowns\n\n\nTitle 5:\nEvaluation of the marginal precision of one-piece complete arch titanium frameworks fabricated using five different methods for implant-supported restorations.\nAbstract 5:\nOBJECTIVE The aim of the present work was to compare the marginal precision of titanium frameworks for a complete arch-fixed prosthesis fabricated using five different methods . METHODS A prospect i ve study was design ed . Fifteen titanium frameworks for totally edentulous upper or lower jaws , each supported by five to nine implants , were assigned to five study groups , so as to have three frameworks in each group for each technique : ( 1 ) lost wax technique frameworks , ( 2 ) cast titanium sovrastructures laser welded to prefabricated titanium copings , ( 3 ) Procera Implant Bridge , ( 4 ) Cresco Ti System and ( 5 ) CAM StructSURE Precision Milled Bar . The microgap between the framework and the shoulders of implant analogues was measured on the master cast with a stereomicroscope at a magnification of 100 x at four different locations , yielding a total of 364 data points on 91 implants . Data were analyzed using an ANOVA and a Tukey post hoc test ( P=<0.05 ) . RESULTS The mean values for the microgap were 78 microm ( SD+/-48 ) for lost wax technique frameworks , 33 microm ( SD+/-19 ) for cast titanium sovrastructures laser welded to titanium copyings , 21 microm ( SD+/-10 ) for the Procera implant bridge , 18 microm ( SD+/-8 ) for the Cresco Ti System and 27 microm ( SD+/-15 ) for the CAM StructSURE . The differences among the mean values were statistically significant ( P<0.01 or P<0.05 ) . The comparisons among groups 3 , 4 , and 5 and between groups 2 and 5 were not significant ( P>0.05 ) . CONCLUSION The computer-aided procedures analyzed in the present study were able to produce a precision-fitting framework , with no significant differences among them and , at the same time , showed a greater precision compared with the traditional casting methods or with the use of prefabricated titanium copings . However , it should be noted that , even if group 2 frameworks were not as accurate as groups 3 and 4 , cast titanium sovrastructures laser welded to prefabricated titanium copings showed significantly better marginal precision than the frameworks produced with the lost wax technique\n\n\nTitle 6:\nClinical Marginal and Internal Adaptation of Maxillary Anterior Single All-Ceramic Crowns and 2-year Randomized Controlled Clinical Trial.\nAbstract 6:\nPURPOSE The aims of this r and omized-controlled clinical trial were to compare marginal and internal adaptation of all-ceramic crowns fabricated with CAD/CAM and heat-pressed ( HP ) techniques before luting and to evaluate the clinical outcomes at baseline and at 6 , 12 , and 24 months after luting . MATERIAL S AND METHODS Fifteen CAD/CAM ( CC ) and 15 HP all-ceramic crowns were placed in 15 patients . A silicone replica was obtained to measure marginal and internal adaptation of each all-ceramic crown before luting , and they were sectioned buccolingually and mesiodistally . Marginal and internal adaptations were measured using computerized light microscope at 40 × magnification . Clinical evaluations took place at baseline ( 2 days after luting ) and at 6 , 12 , and 24 months after luting . Replica scores were analyzed with Mann-Whitney U and Student 's t-test ( α = 0.05 ) . Survival rate of crowns was determined using Kaplan-Meier statistical analysis . RESULTS The median marginal gap for the CC group was 132.2 μm and was 130.2 μm for the HP group . The mean internal adaptation for the CC group was 220.3 ± 51.3 μm and 210.5 ± 31 μm for the HP group . There were no statistically significant differences with respect to marginal opening ( Mann-Whitney U test ; p = 0.95 ) and internal adaptation ( Student 's t-test ; p = 0.535 ) between the 2 groups . Based on modified Ryge criteria , 100 % of the crowns were rated satisfactory during the 2-year period . CONCLUSION In this in vivo study , CAD/CAM and HP all-ceramic crowns exhibited similar marginal and internal adaptations . A 100 % success rate was recorded for the 15 CAD/CAM and for the 15 HP all-ceramic crowns during the 2-year period\n\n\nTitle 7:\nMarginal fit of castable ceramic crowns.\nAbstract 7:\nThe objective of this study was to measure marginal fit of castable ceramic versus gold crowns . Full veneer gold and ceramic crowns were made on Ivorine dies . Crowns were cemented , embedded , sectioned faciolingually and mesiodistally , and photographed for measurement of absolute marginal discrepancies ( cavosurface angle to casting margin ) to evaluate fit . Results revealed no statistically significant differences in fit among four locations around the margins of either ceramic or gold crowns . There was no statistically significant difference in the combined absolute marginal discrepancy ( fit ) between ceramic and gold crowns . The variance of the combined absolute marginal discrepancy ( fit ) of the ceramic crowns was significantly different than that of the gold crowns ( p = 0.01 level ) . The st and ard deviation ( variability ) of the gold crowns was more than twice that of the ceramic crowns . R and omized block ANOVA demonstrated statistically significant differences among individual gold crown specimens , but none among individual ceramic crown specimens",
"role": "user"
},
{
"content": "Results : Of the 55 included comparative studies , 28 compared CAD‐CAM technology with conventional fabrication techniques , 12 contrasted CAD‐CAM technology and copy milling , 4 compared CAD‐CAM milling with direct metal laser sintering ( DMLS ) , and 22 investigated the performance of a CAD‐CAM system regarding marginal adaptation in restorations/infrastructures produced with different restorative material s. Conclusions : Most of the CAD‐CAM restorations/infrastructures were within the clinical ly acceptable marginal discrepancy ( MD ) range .\nThe performance of a CAD‐CAM system relative to marginal adaptation is influenced by the restorative material .\nCompared with CAD‐CAM , most of the heat‐pressed lithium disilicate crowns displayed equal or smaller MD values .\nSlip‐casting crowns exhibited similar or better marginal accuracy than those fabricated with CAD‐CAM .\nCobalt‐chromium and titanium implant infrastructures produced using a CAD‐CAM system elicited smaller MD values than zirconia .\nThe majority of cobalt‐chromium restorations/infrastructures produced by DMLS displayed better marginal accuracy than those fabricated with the casting technique .\nCompared with copy milling , the majority of zirconia restorations/infrastructures produced by CAD‐CAM milling exhibited better marginal adaptation .\nNo clear conclusions can be drawn about the superiority of CAD‐CAM milling over the casting technique and DMLS regarding marginal adaptation",
"role": "assistant"
}
] |
science.mslr2022_cochrane_multidoc_summarization
|
science.mslr2022_cochrane_multidoc_summarization.2871
|
[
{
"content": "You will be provided with the titles and abstracts of a collection of medical RCT reports studying a clinical question -- for instance, the efficacy of an intervention on some medical outcome. Please write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article. Your response should not include any other text. The RCT reports are below.\n\n\n\nTitle 1:\nAuthor contacts for retrieval of data for a meta-analysis on exercise and diet restriction.\nAbstract 1:\nThe mode of contact and response levels of authors who had been asked to provide missing or incomplete data for a systematic review on diet and exercise interventions for weight loss was examined.\n We contacted authors by electronic mail, letter, or both. Survival analyses were performed with the Kaplan-Meier method to determine differences in the proportion of responders over time among the different modes of contact and to determine whether response rates differed between authors from the United States and those from other countries. Logistic regression was used to determine whether the number of items requested and publication date influenced the likelihood of response.\n Two hundred forty-one (39.9 percent) studies had missing or incomplete data (e.g., sample size, age, caloric restriction, exercise amount, and so on). We were unable to locate ninety-five authors (39.4 percent). Of the remaining authors, forty-six authors (31.5 percent) responded to information requests. Time to respond differed by contact method (p < .05): e-mail (3 +/- 3 days), letter (27 +/- 30 days), and both (13 +/-12 days). Response rates from U.S. authors did not differ from those of other countries.\n Our study suggests poor success in the acquisition of essential information. Given considerable time and resources, weight loss studies require improved reporting standards to minimize the relatively unsuccessful attempt to contact authors for important and necessary information.",
"role": "user"
},
{
"content": "Those carrying out systematic reviews should continue to contact authors for missing data, recognising that this might not always be successful, particularly for older studies. Contacting authors by e-mail results in the greatest response rate with the fewest number of attempts and the shortest time to respond.",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.4869
|
[
{
"content": "Given a short query with keyphrases about a research idea in 2019 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from options provided. A short description of the datasets is also provided to help you.\n\nQuery: A simple yet effective method for accurate crowd counting and precise person localization.\n\nKeyphrases: crowd counting images\n\nDataset description:\nIMDB-BINARY: IMDB-BINARY is a movie collaboration dataset that consists of the ego-networks of 1,000 actors/actresses who played roles in movies in IMDB. In each graph, nodes represent actors/actress, and there is an edge between them if they appear in the same movie.\nMinneApple: MinneApple is a benchmark dataset for apple detection and segmentation. The fruits are labelled using polygonal masks for each object instance to aid in precise object detection, localization, and segmentation.\nREDDIT-BINARY: REDDIT-BINARY consists of graphs corresponding to online discussions on Reddit. In each graph, nodes represent users, and there is an edge between them if at least one of them respond to the other’s comment.\nShanghaiTech: The Shanghaitech dataset is a large-scale crowd counting dataset. It consists of 1198 annotated crowd images.\n\nOptions:- A: IMDB-BINARY B: MinneApple C: REDDIT-BINARY D: ShanghaiTech",
"role": "user"
},
{
"content": "ShanghaiTech",
"role": "assistant"
}
] |
science.mltables_te
|
science.mltables_te.6
|
[
{
"content": "\\section{Introduction}\nLarge datasets have made the phenomenal performance of Transformer-based \\citep{attention-is-all-you-need} pre-trained language models (PLMs) possible \\citep{devlin-etal-2019-bert, sanh2019distilbert, liu-2019-roberta, clark2020electra, bommasani2021fm}. \nHowever, recent studies show that a significant fraction of examples in a training dataset can be omitted without sacrificing test accuracy. \nTo this end, many metrics have been introduced for ranking the examples in a dataset based on their importance. \nOne of these metrics is \\emph{Forgetting Score} \\citep{toneva2018empirical-forgetting, yaghoobzadeh-etal-2021-increasing} which recognizes the examples that are misclassified after being correctly classified during training or are always misclassifed. \n\\emph{Datamap} \\citep{swayamdipta-2020-dataset-cartography} is another technique for diagnosing datasets which uses \\emph{confidence} and \\emph{variability} metrics. \n\n\\section{Background}\nIn this section, we describe the two metrics introduced by \\citet{NEURIPS2021_ac56f8fe_datadiet} for pruning the training data: \\textbf{GraNd} and its estimated variant, \\textbf{EL2N}. \n\\subsection{GraNd}\nConsider $\\mathbf{X} = \\{x_i, y_i\\}_{i=1}^N$ to be a training dataset for a given classification task with $K$ classes, where $x_i$ is the input (i.e. a sequence of tokens) and $y_i$ is its corresponding label. \nTo estimate the importance of each training sample $(x_i, y_i)$, \\citet{NEURIPS2021_ac56f8fe_datadiet} propose utilizing the expected value of the loss gradient norm denoted as GraNd:\n\n\\subsection{EL2N}\nBy defining $\\psi^{(k)}(x_i) = \\nabla_{\\boldsymbol{w}}f^{(k)}(x_i)$ for the $k^\\text{th}$ logit,\nthe loss gradient ($\\boldsymbol{g}$) can be written as:\n\nSince the $\\mathcal{L}(f(x_i), y_i)$ is a cross entropy loss, $\\nabla_{f^{(k)}}\\mathcal{L}(f(x_i), y_i)^T=p(x_i)^{(k)} - y^{(k)}_i$ , where $p(x_i)$ is the output probability vector of the model. By assuming orthogonality and uniform sizes across logits for $\\psi$ over the training examples, the norm in Eq. \\ref{eq:grand} is approximately equal to $\\left\\|p(x_i) - \\boldsymbol{y}_i\\right\\|_2$ ($\\boldsymbol{y}_i$ is the one-hot vector of the true label). As a result, an estimate of GraND is \\textbf{EL2N}, which is defined as follows:\n\n\\begin{equation}\n\\label{eq:el2n}\n \\text{EL2N}(x_i, y_i) = \\mathbb{E}_{\\boldsymbol{w}}\\left\\|p(x_i) - \\boldsymbol{y}_i\\right\\|_2\n\\end{equation}\n\n\\section{Experiments}\nIn this section, we verify the effectiveness of GraNd and EL2N \\citep{NEURIPS2021_ac56f8fe_datadiet} in the NLP domain. \nOur experimental setup is similar to \\citet{NEURIPS2021_ac56f8fe_datadiet} for the followings:\n(1) models are trained on the subsets of the data with higher GraNd and EL2N scores;\n(2) based on the expectation over multiple weight initializations mentioned in Eq.~\\ref{eq:grand} and Eq.~\\ref{eq:el2n}, we average the scores over five independent training runs.\\footnote{It is ten independent training runs in \\citet{NEURIPS2021_ac56f8fe_datadiet}}; and,\n(3) for putting our results in context, we utilized random pruning as the baseline\\footnote{Random selection with the same proportion} and the accuracy of training on the whole dataset with no pruning as the target performance.\n\nTwo major differences between these two setups are mentioned here:\n(1) we used a pre-trained model, i.e., BERT \\citep{devlin-etal-2019-bert}, standard in the NLP domain, whereas \\citet{NEURIPS2021_ac56f8fe_datadiet} uses vision models initialized with random weights; and\n(2) as fine-tuning requires few epochs of training, we computed the metrics over fine-grained steps rather than epochs.\n\n\\section{Appendix}\n\\subsection{Dataset samples and their scores}\nExamples with the highest and lowest EL2N scores are provided in Table~\\ref{tab:examples-agnews} and Table~\\ref{tab:examples-mnli} for AG News and MNLI datasets. \n\n\\begin{table*}[h]\n\\centering\n\\small\n\\begin{tabular}{lp{7.2cm}ccc}\n\\toprule \n & \\textbf{Instance} & \\textbf{EL2N} & \\textbf{Gold Label} & \\textbf{Prediction}\\\\\n\\midrule \n\\multirow{15}{*}{\\rotatebox{90}{Noise / Hard}}\n& Tom Hauck/Getty Images 1. Rapper Snoop Dogg attended practice Tuesday with No. 1 USC as a guest wide receiver. The Trojans were delighted by the star \\#39;s presence, as were a group of pee-wee football players watching practice that day.\n& 1.413128\n& Business (2)\n& Sports (1)\n\\\\\\cmidrule[0.01em](lr){2-5}\n& Palestinian gunmen kidnap CNN producer GAZA CITY, Gaza Strip -- Palestinian gunmen abducted a CNN producer in Gaza City on Monday, the network said. The network said Riyadh Ali was taken away at gunpoint from a CNN van.\n& 1.412653\n& Sports (1)\n& World (0)\n\\\\\\cmidrule[0.01em](lr){2-5}\n& Names in the Game Dressed in jeans and a white shirt, the men \\#39;s all-around champion in Athens appeared relaxed as he helped promote a 14-city gymnastics exhibition tour that kicks off at the Mohegan Sun Casino on Tuesday.\n& 1.412590\n& Business (2)\n& Sports (1)\n\\\\\\midrule[0.03em]\n\\multirow{14}{*}{\\rotatebox{90}{Easy}}\n& Vikings \\#39; Moss practices despite hamstring injury Eden Prairie, MN (Sports Network) - Minnesota Vikings wide receiver Randy Moss practiced on Wednesday despite nursing a strained right hamstring and is listed as questionable for this Sunday \\#39;s game against the New York Giants.\n& 0.000665\n& Sports (1)\n& Sports (1)\n\\\\\\cmidrule[0.01em](lr){2-5}\n& Cassell a no-show; Wolves sign Griffin Minneapolis, MN (Sports Network) - Minnesota Timberwolves guard Sam Cassell did not show up Tuesday for the first day of training camp.\n& 0.000653\n& Sports (1)\n& Sports (1)\n\\\\\\cmidrule[0.01em](lr){2-5}\n& Rockets activate Lue from injured list Houston, TX (Sports Network) - The Houston Rockets activated guard Tyronn Lue from the injured list prior to Wednesday \\#39;s game against the Hawks.\t\n& 0.000649\n& Sports (1)\n& Sports (1)\n \\\\\n\\bottomrule\n\\end{tabular}\n\\caption{\nExamples from AG News belonging to different score regions of EL2N. The highest scoring instances are mostly noisy samples, while the least scoring instances are very easy to learn.\n} \n\\label{tab:examples-agnews}\n\\end{table*}\n\nYou are provided with a table and supplementary text from a machine learning paper. Here are JSON templates for four types of numeric cells: \"Other\", \"Data Stat.\", \"Hyper-parameter/Architecture\", and \"Result\":\n{\"value\": \"xx\", \"type\": \"Other\"}\n{\"value\": \"xx\", \"type\": \"Data Stat.\", \"dataset\": \"xx\", \"attribute name\": \"xx\", \"sub-set/group name\": \"xx\", \"dataset features\": {\"xx\": \"yy\"}}\n{\"value\": \"xx\", \"type\": \"Hyper-parameter/Architecture\", \"model\": \"xx\", \"parameter/architecture name\": \"xx\", \"dataset\": \"xx\"}\n{\"value\": \"xx\", \"type\": \"Result\", \"task\": \"xx\", \"metric\": \"xx\", \"training data/set\": \"xx\", \"test data/set\": \"xx\", \"model\": \"xx\", \"model settings\": {\"xx\": \"yy\"}, \"experimental settings\": {\"xx\": \"yy\"}}\n\nPlease describe all numeric cells in the above latex table following the JSON templates (proceeding by row in a left-right, top-down direction). For each cell, output one JSON description per line. For any unanswerable attributes in the templates, set their value to the placeholder \"xx\" if it is of string type and {\"xx\": \"yy\"} if it is of dictionary type. Numeric cells, which describe performance/error analysis, should be labeled as \"Other\".\n\nCell Description:",
"role": "user"
},
{
"content": "{\"value\": \"1.413128\", \"type\": \"Other\"}\n{\"value\": \"1.412653\", \"type\": \"Other\"}\n{\"value\": \"1.412590\", \"type\": \"Other\"}\n{\"value\": \"0.000665\", \"type\": \"Other\"}\n{\"value\": \"0.000653\", \"type\": \"Other\"}\n{\"value\": \"0.000649\", \"type\": \"Other\"}",
"role": "assistant"
}
] |
science.mslr2022_cochrane_multidoc_summarization
|
science.mslr2022_cochrane_multidoc_summarization.1051
|
[
{
"content": "You will be provided with the titles and abstracts of a collection of medical RCT reports studying a clinical question -- for instance, the efficacy of an intervention on some medical outcome. Please write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article. Your response should not include any other text. The RCT reports are below.\n\n\n\nTitle 1:\nRandomized efficacy trial of early preconception counseling for diabetic teens (READY-girls).\nAbstract 1:\nTo develop and assess the feasibility of an early preconception counseling program for adolescents called READY-Girls (Reproductive-health Education and Awareness of Diabetes in Youth for Girls).\n A total of 53 adolescent females with type 1 diabetes between 16 and 19.9 years of age were randomized into groups receiving a CD-ROM, a book, or standard care (control) and given one comprehensive session. Outcomes were assessed at baseline, immediately after, and at 3 months.\n Teens who received the CD and those who received the book demonstrated significant (P < or = 0.05) sustained improvement (over 3 months) in knowledge, perceived benefits of both receiving preconception counseling and using effective family planning, and perceived more support with reproductive health issues.\n Clinical feasibility of the program was demonstrated. Both the CD and the book appeared to be efficacious formats for the short term. Future studies should examine repeated boosters of a CD and a book, which are not meant to replace but rather to reinforce and supplement health professional education.",
"role": "user"
},
{
"content": "Little evidence is available to recommend for or against preconception care for women with pre-existing diabetes. Further large, high-quality randomised controlled trials are needed to evaluate the effect of different protocols of preconception care for women with pre-existing diabetes.",
"role": "assistant"
}
] |
science.qasa_abstractive_qa
|
science.qasa_abstractive_qa.302
|
[
{
"content": "You will be shown an excerpt from a computer science scientific research paper, followed by a question about the paper. Please answer the question. Do not include any text in your response other than the answer.\n\nContext: We examine different attention models (global, local-m, local-p) and differentalignment functions (location, dot, general, concat) as described inSection 3. Due to limitedresources, we cannot run all the possible combinations.However, results in Table 4 do give us some idea aboutdifferent choices.The location-based function does not learn goodalignments: the global (location) model can only obtain a smallgain when performing unknown word replacement compared to using other alignmentfunctions.141414There is a subtle difference in how we retrieve alignmentsfor the different alignment functions. At time step t in which we receivey_{t-1} as input and then compute \\mbox{\\boldmath{$h$}}_{t},\\mbox{\\boldmath{$a$}}_{t},\\mbox{\\boldmath{$c$}}_{t}, and \\mbox{\\boldmath{$\\tilde{h}$}}_{t} beforepredicting y_{t}, the alignment vector \\mbox{\\boldmath{$a$}}_{t} is used as alignmentweights for (a) the predicted word y_{t} in the location-basedalignment functions and (b) the input word y_{t-1} in the content-basedfunctions.For content-based functions, our implementation concat does not yield good performancesand more analysis should be done to understand thereason.151515With concat, the perplexities achieved by different models are 6.7 (global), 7.1(local-m), and 7.1 (local-p). Such high perplexities could be due to the factthat we simplify the matrix W_{a} to set the part that corresponds to \\mbox{\\boldmath{$\\bar{h}$}}_{s}to identity. It is interesting to observe that dot workswell for the global attention and general is better for the localattention.Among the different models, the local attention model with predictive alignments (local-p) is best, both in terms of perplexities and BLEU.\n\nQuestion: What kinds of alignment functions are used for their attention-based models?",
"role": "user"
},
{
"content": "Authors used location, dot, general and concat alignment functions in their experiments.",
"role": "assistant"
}
] |
science.bioasq_yesno_qa
|
science.bioasq_yesno_qa.704
|
[
{
"content": "You have to answer a biomedical question in binary format, i.e. only yes and no are the only acceptable answer formats. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Can CD55 deficiency cause thrombosis?\n\nContext: The loss of CD55 and CD59 renders PNH erythrocytes susceptible to intravascular haemolysis, which can lead to thrombosis and to much of the morbidity and mortality of PNH.\nCD55 Deficiency, Early-Onset Protein-Losing Enteropathy, and Thrombosis.\nCONCLUSIONS: CD55 deficiency with hyperactivation of complement, angiopathic thrombosis, and protein-losing enteropathy (the CHAPLE syndrome) is caused by abnormal complement activation due to biallelic loss-of-function mutations in CD55.\nIt is caused by the expansion of a hematopoietic progenitor cell that has acquired a mutation in the X-linked phosphatidylinositol glycan class A (PIGA) gene that results in deficiency of the glycosylphosphatidylinositol anchor structure responsible for fixing a wide spectrum of proteins particularly CD55 and CD59. The clinical features of this disease arise as a result of complement-mediated hemolysis in unprotected red cells, leukocytes, and platelets as well as the release of free hemoglobin. Patients may present with a variety of clinical manifestations, such as anemia, thrombosis, kidney disease, smooth muscle dystonias, abdominal pain, dyspnea, and extreme fatigue.\nThe lack of one of the GPI-AP complement regulatory proteins (CD55, CD59) leads to hemolysis. The disease is diagnosed with hemolytic anemia, marrow failure and thrombosis.\nParoxysmal nocturnal hemoglobinuria (PNH) is a rare bone marrow failure disorder that manifests with hemolytic anemia, thrombosis, and peripheral blood cytopenias. The absence of two glycosylphosphatidylinositol (GPI)-anchored proteins, CD55 and CD59, leads to uncontrolled complement activation that accounts for hemolysis and other PNH manifestations.\nRESULTS: CD55 and/or CD59 deficiencies were found in 1.6% (2/127) of patients with primary BCS, 1.0% (1/100) of non-malignant and non-cirrhotic patients with PVT, and 4.7% (4/85) of cirrhotic patients with PVT.\nData of this study indicate that the PNH defect as detected with CD55, CD59, and CD16 is not an important cause of intra-abdominal thrombosis in northwestern India.\nPNH testing of red blood cells revealed a CD55 and CD59 deficiency consistent with PNH in both cases. The systemic complications typically associated with thrombosis were not observed for the following several months with early conservative treatments including eculizumab.\nDeficiency of the GPI-anchored complement inhibitors CD55 and CD59 on erythrocytes leads to intravascular hemolysis upon complement activation. Apart from hemolysis, another prominent feature is a highly increased risk of thrombosis.\nGenetic reconstitution of CD55 or treatment with a complement-inhibitory therapeutic antibody reversed abnormal complement activation.<br><b>CONCLUSIONS</b>: CD55 deficiency with hyperactivation of complement, angiopathic thrombosis, and protein-losing enteropathy (the CHAPLE syndrome) is caused by abnormal complement activation due to biallelic loss-of-function mutations in CD55.\nParoxysmal nocturnal hemoglobinuria (PNH) is an acquired clonal disorder characterized by a decrease or absence of glycosylphosphatidylinositol (GPI)-anchored molecules such as CD55 and CD59 from the surface of affected cells, resulting in intravascular hemolysis, cytopenia, and venous thrombosis.\nCONCLUSIONS CD55 deficiency with hyperactivation of complement, angiopathic thrombosis, and protein-losing enteropathy (the CHAPLE syndrome) is caused by abnormal complement activation due to biallelic loss-of-function mutations in CD55.\nCD55 deficiency with hyperactivation of complement, angiopathic thrombosis, and protein-losing enteropathy (the CHAPLE syndrome) is caused by abnormal complement activation due to biallelic loss-of-function mutations in CD55.\nCD55 Deficiency, Early-Onset Protein-Losing Enteropathy, and Thrombosis.",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
] |
science.mslr2022_cochrane_multidoc_summarization
|
science.mslr2022_cochrane_multidoc_summarization.2992
|
[
{
"content": "You will be provided with the titles and abstracts of a collection of medical RCT reports studying a clinical question -- for instance, the efficacy of an intervention on some medical outcome. Please write a few sentences synthesizing the findings of these reports, which could serve as a conclusion section for a systematic review article. Your response should not include any other text. The RCT reports are below.\n\n\n\nTitle 1:\n[Intra-umbilical administration of oxytocin in the treatment of retained placenta].\nAbstract 1:\nnan\n\n\nTitle 2:\nThe effect of oxytocin injection into the umbilical vein for the management of the retained placenta.\nAbstract 2:\nIn a single-blind study 51 patients with retention of the placenta were randomized into one of three groups: Group 1 was given 10 IU of oxytocin in 10 ml of sodium chloride into the umbilical vein; group 2 was given 10 ml of sodium chloride; group 3 was treated with manual removal of the placenta. No significant differences were recorded in groups 1 and 2, and no advantages were found in comparison with the procedure normally used.\n\n\nTitle 3:\nAvoiding manual removal of placenta: evaluation of intra-umbilical injection of uterotonics using the Pipingas technique for management of adherent placenta.\nAbstract 3:\nManual removal of placenta is performed in 1-3% of cases, and whilst a well established and relatively safe procedure, it is not without complications, which include infection, hemorrhage, uterine rupture, and occasional maternal death.\n A three-arm randomized controlled trial of 50 IU Syntocinon (in 30 ml N saline) versus 800 mcg misoprostol (in 30 ml N saline) versus 30 ml N saline alone (control), injected into the placental bed via the umbilical vein using the Pipingas method. A group sequential research model (triangular test: PEST4) was adopted to minimize the sample size, as retained placenta is a relatively uncommon condition.\n No significant difference in the rate of manual removal was observed between the control and Syntocinon groups. On triggering the automatic stopping rule for this arm of the trial all subsequent cases recruited were allocated to receive either Syntocinon or misoprostol. After a total of 54 cases a significant reduction in manual removal of placenta was observed in the misoprostol group, triggering the automatic stopping rule and terminating the trial.\n Misoprostol (800 mcg) dissolved in 30 ml N saline and administered by intraumbilical injection using the Pipingas technique significantly reduces the need for manual removal for retained adherent placenta, whereas Syntocinon has similar effectiveness to injection of N saline alone.\n\n\nTitle 4:\nIntraumbilical oxytocin for the management of retained placenta: a randomized controlled trial.\nAbstract 4:\nTo evaluate the ability of intraumbilical oxytocin injection as a treatment for retained placenta after vaginal delivery to reduce the incidence of manual removal and postpartum hemorrhage.\n A randomized controlled trial was set up in a university and a district general hospital. We recruited 81 women with singleton pregnancies who underwent vaginal delivery and who failed to deliver the placenta after 20 minutes of active management of the third stage of labor. Study subjects were randomized to receive either 1) an intraumbilical injection of oxytocin (20 IU in 20 mL of saline); 2) an intraumbilical injection of saline (20 mL); or 3) no treatment. Outcome measures were expulsion of the placenta within 45 minutes of delivery, need for manual removal of the placenta under anesthesia, and postpartum hemorrhage (defined as a blood loss greater than 500 mL).\n Women given an intraumbilical injection of oxytocin had a significant increase in spontaneous expulsion of the placenta within 45 minutes of delivery and fewer manual removals of the placenta, compared with women without treatment (odds ratio [OR] 11.6, 99% confidence interval [CI] 1.4, 272.8; and OR 7.4, 99% CI 1.1, 86.5; respectively). When women given intraumbilical oxytocin were compared with women given only intraumbilical saline, the difference was not statistically significant (OR 6.6, 99% CI 0.9, 77.2 for spontaneous expulsion of the placenta; and OR 4.7, 99% CI 0.8, 39.5 for manual removal). There was no significant difference in the incidence of spontaneous expulsion and manual removal of the placenta between women given intraumbilical saline injection and women without treatment (OR 1.8, 99% CI 0.1, 53.9; and OR 1.6, 99% CI 0.1, 22.4; respectively).\n The results of our study suggest a clinically important beneficial effect of intraumbilical oxytocin injection in the management of retained placenta.\n\n\nTitle 5:\nIntraumbilical vein injection of prostaglandin F2 alpha in retained placenta.\nAbstract 5:\nA randomized protocol was used to study the effect of intraumbilical prostaglandin F2 alpha (Hembate, Upjohn) and oxytocin injection in women with retained placenta. Prostaglandin F2 alpha, 20 mg, diluted to 20 ml in normal saline solution (10 women, group 1), 30 IU of oxytocin, diluted to 20 ml in normal saline solution (11 women, group 2), or 20 ml of normal saline solution alone (7 women, group 3), were injected into the umbilical vein 1 h after delivery. Nine women (group 4, controls) underwent manual removal of the retained placenta. In group 1, placental expulsion occurred in all patients and the duration of the placental expulsion after prostaglandin F2 alpha injection was 6.8 +/- 1.36 (mean +/- SE) min: in group 2, six placental expulsions occurred after 13.3 +/- 1.97 min (mean +/- SE); and in group 3, no effect was recorded after intraumbilical saline injection. We suggest that intraumbilical vein injection of prostaglandin F2 alpha might be a beneficial, non-surgical method for treating retained placenta. Oxytocin might reduce the incidence of manual lysis of the placenta and achieve partial success.\n\n\nTitle 6:\nIntra-umbilical vein injection and retained placenta: evidence from a collaborative large randomised controlled trial. Grupo Argentino de Estudio de Placenta Retenida.\nAbstract 6:\nTo determine whether intra-umbilical vein injection with saline solution, with or without oxytocin, reduces the need for manual removal of placenta compared with expectant management.\n Multicenter, randomised controlled trial.\n Eleven hospitals in four cities of Argentina: Buenos Aires, Corrientes, Rosario, and Salta.\n Two hundred and ninety-one women showing no evidence of placental separation thirty minutes after vaginal delivery.\n Three different management strategies: 1. intra-umbilical vein injection of saline solution plus oxytocin; 2. intra-umbilical vein injection of saline solution alone; and 3. expectant management.\n Primary: manual removal of the placenta. Secondary: blood loss after trial entry, haemoglobin level at 24 to 48 hours and at 40 to 45 days after delivery, blood transfusion, curettage, infection, and days of hospital stay.\n Rates of subsequent manual removal were similar: intra-umbilical vein injection of saline solution plus oxytocin (58%; RR 0.92; 95% CI 0.73-1.15), or saline alone (63%; RR 1.00; 95% CI 0.80-1.24), compared with expectant management (63%). There were also no detectable effects of the active managements on any of the secondary measures of outcome.\n Based on evidence available from randomised controlled trials, including this trial, it is unlikely that intra-umbilical injection with or without oxytocin, is clinically useful. We recommend that this intervention should not be used in third stage management of labour.\n\n\nTitle 7:\nIs there a place for intra-umbilical oxytocin for the management of retained placenta?\nAbstract 7:\nIntra-umbilical injection of oxytocin has been used to hasten placental separation in retained placenta. A randomised controlled trial was done on 35 consequent women who fulfilled the criteria for retained placenta at the Department of Obstetrics & Gynaecology Ipoh Hospital. Nineteen patients who were recruited into the study group received intraumbilical injection of 301U oxytocin in 27mls saline. Another 16 patients who were in the control group received 30mls of 0.9% sodium chloride (placebo). The primary outcome measured was the need for manual removal of placenta (MRP). Nine out of the 19 patients in the oxytocin group required MRP while 10/16 in the control group required MRP. There was a 24% reduction (95% C.I. 0.41 to 1.39) in the need for MRP in the study group compared to the saline group. our results indicate that intra-umbilical vein injection of oxytocin is not clinically useful for the removal of a retained placenta.\n\n\nTitle 8:\nRemoving a retained placenta by oxytocin--a controlled study.\nAbstract 8:\nNo increase in maternal plasma oxytocin concentration was detected after administration of 100 IU oxytocin into the umbilical veins of seven women immediately after delivery. The delivery of the placenta was accelerated after umbilical vein injection of 100 IU oxytocin in a placebo-controlled study of 40 women: 12 minutes (4 to 40) in the oxytocin group versus 40 minutes (29 to 40) in the placebo group (median and interquartile ranges), p less than 0.05.\n\n\nTitle 9:\nIntraumbilical oxytocin for management of retained placenta.\nAbstract 9:\nThe purpose of the study was to investigate the removal of a retained placenta.\n Oxytocin was injected into the vein of the umbilical cord. A total of 109 patients with retention of the placenta were randomized into two groups. Active management of the third stage of labor was carried out by giving oxytocin 5 IU intravenously and ergometrine maleate 0.2 mg intramuscularly after delivery of the fetus. Group 1, which comprised 68 patients, was allocated to receive 50 IU oxytocin diluted in 10 ml 0.9% sodium chloride solution, and the 41 patients in group 2 were given 20 ml plasma expander (dextran 70) into the umbilical vein.\n Forty-nine cases (72%) in the oxytocin group and 22 cases (54%) in the dextran 70 group required manual removal of the retained placenta. No significant differences were found between group 1 (oxytocin) and group 2 (dextran 70).\n Our results indicate that intraumbilical vein injection of oxytocin is not effective for removal of a retained placenta.\n\n\nTitle 10:\nUmbilical vein administration of oxytocin for the management of retained placenta: is it effective?\nAbstract 10:\nIn a multicenter randomized controlled trial involving 220 women with retained placenta no beneficial effects could be established of intraumbilical vein administration of 10 IU of oxytocin in 20 ml of saline solution. A reduction was not gained in the rate of manual removal of the placenta and there was no decrease in the amount of blood loss. Oxytocin only induced a minor shortening of the median time interval from administration to the spontaneous expulsion of the placenta as compared with a placebo injection. Maternal serum alpha-fetoprotein levels before and after intraumbilical vein injection did not show evidence of fetomaternal transfusion.",
"role": "user"
},
{
"content": "UVI of oxytocin solution is an inexpensive and simple intervention that could be performed while placental delivery is awaited. However, high-quality randomized trials show that the use of oxytocin has little or no effect. Further research into the optimal timing of manual removal and into UVI of prostaglandins or plasma expander is warranted.",
"role": "assistant"
}
] |
science.scitldr_aic
|
science.scitldr_aic.952
|
[
{
"content": "Below are the abstract, introduction, and conclusion of a computer science research paper. Please summarize the main contribution of the work in a single sentence. Your response should include the summary and no additional text.\n\nPaper text:\n\nDuring the last years, a remarkable breakthrough has been made in AI domain\n\nthanks to artificial deep neural networks that achieved a great success in many\n\nmachine learning tasks in computer vision, natural language processing, speech\n\nrecognition, malware detection and so on.\nHowever, they are highly vulnerable\n\nto easily crafted adversarial examples.\nMany investigations have pointed out this\n\nfact and different approaches have been proposed to generate attacks while adding\n\na limited perturbation to the original data.\nThe most robust known method so far\n\nis the so called C&W attack [1].\nNonetheless, a countermeasure known as fea-\n\nture squeezing coupled with ensemble defense showed that most of these attacks\n\ncan be destroyed [6].\nIn this paper, we present a new method we call Centered\n\nInitial Attack (CIA) whose advantage is twofold : first, it insures by construc-\n\ntion the maximum perturbation to be smaller than a threshold fixed beforehand,\n\nwithout the clipping process that degrades the quality of attacks.\nSecond, it is\n\nrobust against recently introduced defenses such as feature squeezing, JPEG en-\n\ncoding and even against a voting ensemble of defenses.\nWhile its application is\n\nnot limited to images, we illustrate this using five of the current best classifiers\n\non ImageNet dataset among which two are adversarialy retrained on purpose to\n\nbe robust against attacks.\nWith a fixed maximum perturbation of only 1.5% on\n\nany pixel, around 80% of attacks (targeted) fool the voting ensemble defense and\n\nnearly 100% when the perturbation is only 6%.\nWhile this shows how it is difficult\n\nto defend against CIA attacks, the last section of the paper gives some guidelines\n\nto limit their impact.\nSince the skyrocketing of data volumes and parallel computation capacities with GPUs during the last years, deep neural networks (DNN) have become the most effective approaches in solving many machine learning problems in several domains like computer vision, speech recognition, games playing etc.\nThey are even intended to be used in critical systems like autonomous vehicle BID17 , BID18 .\nHowever, DNN as they are currently built and trained using gradient based methods, are very vulnerable to attacks a.k.a. adversarial examples BID1 .\nThese examples aim to fool a classifier to make it predict the class of an input as another one, different from the real class, after bringing only a very limited perturbation to this input.\nThis can obviously be very dangerous when it comes to systems where human life is in stake like in self driven vehicles.\nCompanies IT networks and plants are also vulnerable if DNN based intrusion detection systems were to be deployed BID20 .Many\napproaches have been proposed to craft adversarial examples since the publication by Szegedy et al. of the first paper pointing out DNN vulnerability issue BID4 . In their\nwork, they generated adversarial examples using box-constrained L-BFGS. Later in\nBID1 , a fast gradient sign method (FGSM) that uses gradients of a loss function to determine in which direction the pixels intensity should be changed is presented. It is designed\nto be fast not optimize the loss function. Kurakin et al.\nintroduced in BID13 a straightforward simple improvement of this method where instead of taking a single step of size in the direction of the gradient-sign, multiple smaller steps are taken, and the result is clipped in the end. Papernot et al.\nintroduced in BID3 an attack, optimized under L0 distance, known as the Jacobian-based Saliency Map Attack (JSMA). Another simple\nattack known as Deepfool is provided in [34] . It is an untargeted\nattack technique optimized for the L2 distance metric. It is efficient and\nproduces closer adversarial examples than the L-BFGS approach discussed earlier. Evolutionary algorithms\nare also used by authors in BID14 to find adversarial example while maintaining the attack close to the initial data. More recently, Carlini\nand Wagner introduced in BID0 the most robust attack known to date as pointed out in BID5 . They consider different\noptimization functions and several metrics for the maximum perturbation. Their L2-attack defeated\nthe most powerful defense known as distillation BID7 . However, authors in BID6\nshowed that feature squeezing managed to destroy most of the C&W attacks. Many other defenses have\nbeen published, like adversarial training BID3 , gradient masking BID9 , defenses based on uncertainty using dropout BID10 as done with Bayesian networks, based on statistics BID11 , BID12 , or principal components BID22 , BID23 . Later, while we were carrying\nout our investigation, paper BID16 showed that not less than ten defense approaches, among which are the previously enumerated defenses, can be defeated by C&W attacks. It also pointed out that feature\nsqueezing also can be defeated but no thorough investigation actually was presented. Another possible defense but not\ninvestigated is based on JPEG encoding when dealing with images. It has never been explicitly attacked\neven after it is shown in BID13 that most attacks are countered by this defense. Also, to our knowledge, no investigation\nhas been conducted when dealing with ensemble defenses. Actually, attacks transferability between\nmodels that is well investigated and demonstrated in BID19 in the presence of an oracle (requesting defense to get labels to train a substitute model) is not guaranteed at all when it is absent. Finally, when the maximum perturbation added\nto the original data is strictly limited, clipping is needed at the end of training (adversarial crafting) even if C&W attacks are used. The quality of crafted attacks is therefore\ndegraded as the brought perturbation during the training is brutally clipped. We tackle all these points in our work while\nintroducing a new attack we call Centered Initial Attack (CIA). This approach considers the perturbation limits\nby construction and consequently no alteration is done on the CIA resulting examples.To make it clearer for the reader, an example is given below to illustrate the clipping issue. FIG0 shows a comparison between CIA and C&W L2\nattack before and after clipping on an example, a guitar targeted as a potpie with max perturbation equal to 4.0 (around 1.5%). The same number of iterations FORMULA4 is considered\nfor both methods. As can be seen on FIG0 , CIA generates the best attack\nwith 96% confidence. C&W is almost as good with a score of 95% but it is degraded\nto 88% after applying the clipping to respect the imposed max perturbation. Avoiding this degradation due to clipping is the core motivation\nof our investigation.The remaining of this paper is organized as follows. Section I presents some mathematical formulations and the principle\nof CIA strategy. Then Section II investigates the application of CIA against ensemble\ndefense, feature squeezing and JPEG encoding defenses. Then Section III provides some guidelines to limit the impact of CIA\nattacks. Finally, we give some possible future investigations in the conclusion\n.\nIn this paper we presented a new strategy called CIA for crafting adversarial examples while insuring the maximum perturbation added to the original data to be smaller than a fixed threshold.\nWe demonstrated also its robustness against some defenses, feature squeezing, ensemble defenses and even JPEG encoding.\nFor future work, it would be interesting to investigate the transferability of CIA attacks to the physical world as it is shown in BID13 that only a very limited amount of FGDM attacks, around 20%, survive this transfer.\nAnother interesting perspective is to consider partial crafting attacks while selecting regions taking into account the content of the data.\nWith regard to images for instance, this would be interesting to hide attacks with big but imperceptible perturbations.",
"role": "user"
},
{
"content": "In this paper, a new method we call Centered Initial Attack (CIA) is provided. It insures by construction the maximum perturbation to be smaller than a threshold fixed beforehand, without the clipping process.",
"role": "assistant"
}
] |
science.chia_ner
|
science.chia_ner.910
|
[
{
"content": "You will be shown inclusion or exclusion criteria for a clinical trial. Given these criteria, your task is to extract all unique entities of the following types: [\"Observation\", \"Condition\", \"Procedure\", \"Drug\", \"Temporal\", \"Multiplier\", \"Qualifier\", \"Negation\", \"ReferencePoint\", \"Scope\", \"Value\", \"Mood\", \"Device\", \"Visit\", \"Measurement\", \"Person\"].\n\nPlease return the output as a JSON object of the format: {\"Condition\" : [\"breast cancer\", ...], \"Device\" : [\"ports\", ...], \"Drug\" : [\"Atenolol\", ...], \"Measurement\" : [\"blood pressure\", ...], \"Mood\" : [\"suspected\", ...], \"Multiplier\" : [\"more than two\", ...], \"Negation\" : [\"no\", ...], \"Observation\" : [\"history\", ...], \"Person\" : [\"male\", ...], \"Procedure\" : [\"surgery\", ...], \"Qualifier\" : [\"severe\", ...], \"ReferencePoint\" : [\"enrollment\", ...], \"Scope\" : [\"infection\", ...], \"Temporal\" : [\"one day\", ...], \"Value\" : [\"50%\", ...], \"Visit\" : [\"ICU\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nNA",
"role": "user"
},
{
"content": "{\"Condition\": [], \"Device\": [], \"Drug\": [], \"Measurement\": [], \"Mood\": [], \"Multiplier\": [], \"Negation\": [], \"Observation\": [], \"Person\": [], \"Procedure\": [], \"Qualifier\": [], \"ReferencePoint\": [], \"Scope\": [], \"Temporal\": [], \"Value\": [], \"Visit\": []}",
"role": "assistant"
}
] |
science.genia_ner
|
science.genia_ner.1396
|
[
{
"content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"RNA\", \"CellLine\", \"Protein\", \"DNA\", \"CellType\"].\n\nPlease return the output as a JSON object of the format: {\"DNA\" : [\"TAL1\", ...], \"RNA\": [\"mRNAs\", ...], \"CellLine\": [\"T cells\", ...], \"CellType\": [\"monocytes\", ...], \"Protein\": [\"IL-2\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nInterferon-gamma-induced factor binding to the interleukin-4-responsive element of CD23b promoter in human tonsillar mononuclear cells: role in transient up-regulation of the interleukin-4-induced CD23b mRNA. Stimulation of human tonsillar mononuclear cells with interleukin-4 (IL-4) and interferon-gamma (IFN-gamma) rapidly induced the activation of distinct nuclear factors with different mobilities, both of which bind the IL-4 response element (IL-4RE) of CD23b promoter as examined by electrophoretic mobility shift assays (EMSA). Co-treatment of IL-4 and IFN-gamma induced, in addition to the two distinct complexes, a new complex with an intermediate mobility. The IL-4-induced complex reacted with anti-STAT (signal transducers and activators of transcription) 6, resulting in a supershift whereas the formation of the IFN-gamma-induced complex was inhibited by anti-STAT 1. The intermediate complex appeared to react with both anti-STAT 6 and anti-STAT 1. Although IFN-gamma alone did not induce CD23 mRNA transcription, Northern blot analysis revealed a transient up-regulation of the IL-4-induced CD23 mRNA by IFN-gamma within 2 h of IFN-gamma treatment in these tonsillar cells. The results suggest that the IL-4RE of the IL-4-inducible gene can accommodate both IL-4-and IFN-gamma-activated factors, such as STAT 6 and STAT 1, either in homodimeric or heterodimeric forms and the binding of these different proteins to the respective promoter may play a potential regulatory role in the IL-4-inducible gene expression.",
"role": "user"
},
{
"content": "{\"CellLine\": [], \"CellType\": [\"tonsillar cells\", \"these tonsillar cells\", \"human tonsillar mononuclear cells\"], \"DNA\": [\"CD23b promoter\", \"interleukin - 4 - responsive element\", \"IL - 4 - inducible gene\", \"IL - 4 response element\", \"IL - 4RE\"], \"Protein\": [\"nuclear factors\", \"IL - 4\", \"interferon - gamma\", \"STAT 6\", \"STAT 1\", \"anti - STAT 6\", \"IFN - gamma\", \"IL - 4 - induced complex\", \"Interferon - gamma - induced factor\", \"interleukin - 4\", \"STAT (signal transducers and activators of transcription) 6\", \"anti - STAT (signal transducers and activators of transcription) 6\", \"anti - STAT 1\", \"homodimeric or heterodimeric forms\", \"IL - 4 - and IFN - gamma - activated factors\", \"IFN - gamma - induced complex\"], \"RNA\": [\"interleukin - 4 - induced CD23b mRNA\", \"CD23b mRNA\", \"CD23 mRNA\", \"IL - 4 - induced CD23 mRNA\"]}",
"role": "assistant"
}
] |
science.data_reco_mcq_mc
|
science.data_reco_mcq_mc.1862
|
[
{
"content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: CODA is a novel adversarial learning approach for crowd counting adaptation. We first use a multi-scale\n\nKeyphrases: crowd counting images\n\nDataset description:\nMulti Task Crowd: Multi Task Crowd is a new 100 image dataset fully annotated for crowd counting, violent behaviour detection and density level classification.\nShanghaiTech: The Shanghaitech dataset is a large-scale crowd counting dataset. It consists of 1198 annotated crowd images.\nCell: The CELL benchmark is made of fluorescence microscopy images of cell.\nMall: The Mall is a dataset for crowd counting and profiling research. Its images are collected from publicly accessible webcam.\nWinoGrande: WinoGrande is a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. The key steps of the dataset construction consist of (1) a carefully designed crowdsourcing procedure, followed by (2) systematic bias reduction using a novel AfLite algorithm that generalizes human-detectable word associations to machine-detectable embedding associations.\n\nOptions:- A: Multi Task Crowd B: ShanghaiTech C: Cell D: Mall E: WinoGrande",
"role": "user"
},
{
"content": "[\"ShanghaiTech\", \"Mall\"]",
"role": "assistant"
}
] |
science.covid_deepset_qa
|
science.covid_deepset_qa.549
|
[
{
"content": "You will be shown a paragraph from a biomedical research paper, followed by a question about the paper. Please extract text from the paragraph to answer the question. Do not include any text in your repsonse other than the answer.\n\nParagraph: Since the emergence of the new A(H7N9) virus, more than 400 human cases were reported to the WHO with a mortality rate of more than 35% . Most patients with A(H7N9) infections had contact with poultry or visited live animal markets. However, some sporadic cases seemed to be a result of human to human transmissions [1, 2] . In contrast to pandemic viruses which fulminantly enter the human population and cause high mortality rates, seasonal influenza viruses generally cause uncomplicated and transient infections in humans, with virus replication localized to the upper respiratory tract [3, 4] . However, in its fully developed form influenza is an acute respiratory disease resulting in hospitalizations and deaths mainly among high-risk groups. Worldwide, annual epidemics result in about three to five million cases of severe illness, and about 250,000 to 500,000 deaths [5] . For this reason WHO [6] and CDC [7] recommend antiviral treatment for any patient with suspected influenza who is at risk for influenza complications without previous laboratory confirmation. It is known that influenza virus infections are often accompanied by other viral pathogens [8] . Depending on the detection method (qRT-PCR or immunofluorescence) different ratios of co-infections have been found. Analysis by qRT-PCR revealed that 54.5-83.3% of influenza A or B positive patients were found to have at least one concomitant respiratory viral infection [9] [10] [11] [12] . The detection frequency with immunofluorescence was found to be even higher (90-100%) [13, 14] . Potential concomitant viral pathogens of influenza virus infections include human rhinovirus (hRV), respiratory syncytial virus, adenovirus, human coronavirus, human metapneumovirus and parainfluenza virus [14, 15] . As a result of the multiple infections, a specific anti-influenza mono-therapy treats the influenza virus infection only, but not the infection with the concomitant viral pathogen. Hence, the therapy often fails to sufficiently resolve symptoms. This is also reflected by the fact that neuraminidase inhibitors (NI) are highly efficacious in animal models investigating influenza mono-infections [16, 17] but show lower efficacy against influenza symptoms in clinical trials in adults with natural infections [18] . Therefore, there is a high medical need for a broadly acting antiviral therapy in combination with a specific anti-influenza therapy for treatment of patients suffering from upper respiratory tract symptoms. Ideally, the substances present in the combination complement each other by different modes of action, leading to a treatment that provides full protection against a broad range of different respiratory viruses as well as different influenza strains with a low probability to induce escape mutations. One approach for a broad antiviral therapy is the creation of a protective physical barrier in the nasal cavity using carrageenan. Carrageenan is a high molecular weight sulfated polymer derived from red seaweed (Rhodophyceae) that has been extensively used in food, cosmetic and pharmaceutical industry and is generally recognized as safe by the FDA (GRAS) (reviewed in [19] ). Three main forms of carrageenans are commercially used: kappa, iota and lambda. They differ from each other in the degree of sulfation, solubility and gelling properties [20] . The antiviral mechanism of carrageenan is based on the interference with viral attachment; as a consequence, viral entry is inhibited [21, 22] . Its antiviral activity is dependent on the type of polymer as well as the virus and the host cells [23] [24] [25] [26] [27] [28] [29] [30] [31] [32] and has been reviewed in [33] [34] [35] . We published that iota-carrageenan is a potent inhibitor of hRV [36] and influenza A [37] replication and demonstrated the antiviral efficacy of iota-carrageenan against common cold viruses by intranasal application in several randomized, double-blind, parallel group, placebo-controlled clinical trials [38] [39] [40] . The pooled analysis of two studies conducted in 153 children and 203 adults revealed that patients infected with any respiratory virus, who were intranasally treated with iota-carrageenan showed a 1.9 day faster recovery from common cold symptoms than placebo treated patients in the intention-to-treat population [41, 42] . The anti-influenza activity was shown by subgroup analysis of 49 influenza infected patients who benefited from a 3.3 days faster recovery from symptoms. The use of carrageenan nasal spray was associated with a significant reduction of the influenza viral load in nasal fluids and a significant increase in the number of virus free patients within the treatment period of 7 days. In good accordance Prieschl-Grassauer are co-founders of Marinomed Biotechnologie GmbH. Marinomed Biotechnologie GmbH had a role in study design, data collection and analysis, decision to publish, preparation of the manuscript and is financing the processing charge of the manuscript. with the literature [9] [10] [11] [12] [13] [14] we observed that the majority of influenza virus infected patients suffered from a concomitant respiratory viral infection (66%) as determined by real-time PCR. Carrageenan containing nasal sprays are already marketed for the treatment of respiratory viral infections under different brand names in 18 countries. At present the only available effective drugs for treatment and post exposure prevention of influenza are the NI (Oseltamivir and Zanamivir worldwide; Peramivir in Japan and South Korea). Since the large-scale use of M2 blockers for prophylaxis and treatment in humans [43] and farming [44] , the currently circulating influenza viruses already lack sensitivity to this drug group [45] . We have already shown an additive therapeutic effect of a combination therapy with intranasally applied iota-carrageenan and orally administered Oseltamivir in lethally H1N1 A/PR/ 8/34 infected mice and a treatment start 48 hours post infection (hpi) [37] . Due to these very promising results we further developed the concept of combining carrageenan with an NI therapy. In contrast to Oseltamivir, which needs to be activated by metabolic conversion, Zanamivir is directly applied as active drug and can also be administered intranasally [46] [47] [48] [49] [50] [51] [52] . The potential of an intranasal administration of Zanamivir was investigated by GlaxoSmithKline. In seven clinical challenge trials 66 volunteers were infected with influenza B/Yamagata/16/88 and 213 with influenza A/Texas/36/91 (H1N1). 156 of these participants got intranasally applied Zanamivir at different doses (daily dose levels from 6.4 mg to 96 mg) for prophylaxis or therapy [46, 47, 53, 54] . These challenge trials showed that treatment starting before and up to 36 hours post virus inoculation was associated with prevention of laboratory confirmed influenza and febrile illness as well as a reduction in viral titers, duration of shedding and symptoms. In total, safety data from 1092 patients after intranasal application of Zanamivir were published and no evidence for Zanamivir induced adverse events or increased frequencies of local nasal intolerance in comparison to placebo groups was found [46, 49, 52] . Taken together, the combination of a carrageenan nasal spray that provides broad antiviral activity against upper respiratory infections-including influenza-with Zanamivir, a specific anti-influenza drug, meets the existing medical need to treat multiple viral infections. In the present work we investigate the therapeutic effect of a combination of carrageenan and Zanamivir in-vitro and in an animal model. Kappa-carrageenan and iota-carrageenan were purchased from FMC Biopolymers (Philadelphia, PA). The identity, purity (>95%) of carrageenan subtypes and the molecular weight (>100,000) was confirmed by NMR analysis as described elsewhere [55] and the presence of lambda-carrageenan was below the detection limit of 3%. The dry polymer powders were dissolved in aqua bidest (Fresenius Kabi, Austria) to a final concentration of 2.4 mg/ml iota-and 0.8 mg/ml kappa-carrageenan. This 2x stock solution was sterile filtered through a 0.22 μm filter (PAA, Switzerland) and stored at room temperature until use. For further testing the stock solution was diluted to a mixture containing 1.2 mg/ml iota-carrageenan and 0.4 mg/ml kappa-carrageenan (hereinafter referred to as \"carrageenan\"). Zanamivir was purchased as powder (Haosun Pharma, China) and the identity and purity was confirmed by NMR analysis. Zanamivir was either dissolved in carrageenan or placebo solutions, followed by sterile filtration through a 0.22 μm filter (Sarstedt, Germany). For in-vivo studies all Zanamivir containing solutions were freshly prepared. Madin-Darby canine kidney (MDCK) cells were obtained from the American Type Culture Collection (ATCC, Manassas, VA) and cultivated in a 37°C incubator (Sanyo, Japan; CO 2 : 5%, relative humidity: >95%). MDCK cells were grown in Dulbecco's minimal essential (DMEM) high glucose medium (PAA, Austria) supplemented with 10% fetal bovine serum (FBS; PAA, Austria; heat inactivated). Influenza virus A/Hansa Hamburg/01/09 (H1N1(09)pdm) was kindly provided by Peter Staeheli Department of Virology, University of Freiburg, Germany and previously described in [56] ; A/Teal/Germany/Wv632/05 (H5N1) previously published in [57] (accession numbers CY061882-9) and A/Turkey/Germany/R11/01 (H7N7) (taxonomy ID 278191, accession number AEZ68716) were supplied by courtesy of Martin Beer, Institute of Diagnostic Virology, Friedrich-Loeffler-Institute, Riems, Germany; A/Aichi/2/68 (H3N2) was purchased from the ATCC. All influenza viruses were propagated in MDCK cells at 37°C and 5% CO 2 in influenza medium [Opti-Pro serum free medium (Gibco, Austria) supplemented with 4 mM L-glutamine (PAA, Austria), 1% antibiotic-antimycotic mix (PAA, Austria) and 5 μg/ml trypsin (Sigma Aldrich, Austria)]. To determine the 50% inhibitory concentration (IC 50 ) and the combination effect of carrageenan and Zanamivir, a semi-liquid plaque assay was developed. Into 96 well tissue culture plates 1.7x10 4 MDCK cells/well were seeded and infected at 90% confluence (24-28 hours later). Serial dilutions of carrageenan and Zanamivir were prepared in assay medium (influenza medium without trypsin). For infection, viruses were diluted to an MOI of 0.003 (H1N1(09)pdm and H3N2 Aichi), 0.015 (H5N1) or 0.004 (H7N7), respectively, in assay medium and incubated at room temperature (RT) for 10 min with the serial dilutions of carrageenan and/or Zanamivir, respectively. For evaluation of the combination effect of carrageenan and Zanamivir, viruses were diluted in assay medium containing constant concentrations of either carrageenan or Zanamivir. The other substance was serially diluted and used for virus incubation. Cells were infected in 6 replicates/compound dilution, respectively, and incubated at RT for 45 min before inoculum removal. Cells were further incubated with the respective concentration of the investigated substances present in the overlay [influenza medium with 2.25% Carboxymethylcellulose (CMC, Fluka, Austria)] for 30-42 hours at 37°C. Evolving plaques were evaluated after methanol/acetone cell fixation by immune staining with antibodies either directed against the influenza A nucleoprotein (AbD Serotec, Germany) (for H1N1(09)pdm, H5N1 and H7N7) or the hemagglutinin (AbD Serotec, Germany) (for H3N2). Analysis was done with a HRP labeled detection antibody (Thermo Scientific, Germany) using TMB (Biolegend, Germany) as substrate and a microplate reader at 450 nm. The reduction of detected signal represents a reduction in the number and size of plaques and indicates suppression of viral replication during infection and cultivation. After the immunostaining cells were stained with 0.005% crystal violet solution to assess the condition of the cell layer and the toxicity of the compounds. IC 50 values and standard deviations were calculated for a sigmoidal dose response model using XLfit Excel add-in version 5.3.1.3. All animal experiments were carried out according to the guidelines of the \"European Convention for the Protection of Vertebrate Animals used for Experimental and other Scientific Purposes\" and the Austrian law for animal experiments. All animal experiments were approved by the Veterinary University of Vienna institutional ethics committee and performed under the Austrian Federal Ministry of Science and Research experimental animal license numbers BMWF-68.205/0262-II/3b/2011 and BMWF-68.205/0142-II/3b2012. C57BL/6 mice were purchased from Janvier Labs, France and maintained under standard laboratory conditions in the animal facilities of the Veterinary University of Vienna. For euthanasia and anesthesia asphyxiation through CO 2 was used and all efforts were made to minimize suffering. For infection experiments, 3-5 weeks old female mice were intranasally inoculated with 50 μl influenza virus solution (25 μl/nostril) containing 2.27x10 3 or 1.65x10 3 plaque-forming unit of H1N1(09)pdm or H7N7, respectively. Subsequently, treatment started 24, 48 or 72 hpi, as indicated for the different experiments. Treatment was performed intranasally either with 50 μl therapeutic solution or placebo twice per day for 5 days.\n\nQuestion: What was the mortality rate of influenza a virus subtype h7n9 (avian or bird flu)?",
"role": "user"
},
{
"content": "more than 35%",
"role": "assistant"
}
] |
science.mslr2022_ms2_multidoc_summarization
|
science.mslr2022_ms2_multidoc_summarization.10896
|
[
{
"content": "You will be presented with a collection of medical randomized controlled trial (RCT) reports addressing a shared clinical question -- for instance, the efficacy of a medical intervention on a disease or condition. Given the titles and abstracts of these reports, your task is to generate the conclusion of the systematic review article synthesizing the key findings. Your conclusion should be a few sentences long. In your response, include only the conclusion and no other text. The RCT reports are below.\n\n\n\nTitle 1:\nExpressive writing, self-criticism, and self-reassurance.\nAbstract 1:\nOBJECTIVES Self-criticism and reassurance are important mechanisms for regulating negative emotions but relatively little attention has been paid to interventions aim ed at improving them . DESIGN This study explored the use of an expressive writing task to increase self-reassurance and reduce self-criticism using a r and omized controlled design . METHOD A total of 46 participants wrote either about life goals ( the expressive writing task , n= 23 ) or a control topic ( a review of a recent book or film , n= 23 ) for 15 min , three times within an hour . Measures of self-criticism/self-reassurance , stress , and positive affect were completed at baseline and at 2-week follow-up . The Linguistic Inquiry and Word Count ( LIWC ) was used to analyse the writing of participants in the ' life goals ' condition to identify psychological processes that might differentiate those who improved and those who did not . RESULTS While there were no significant changes in self-reported stress or positive affect , participants writing about life goals decreased in their levels of self-criticism at 2-week follow-up relative to participants writing about control topics . Text analysis showed that experimental participants using words that imply the possibility of doubt or failure , including use of the subjunctive tense ( e.g. , could , would , should ) , were least likely to decrease their self-criticism . CONCLUSION . Expressive writing shows promise as a means by which people may decrease in their self-criticism . Future research should determine whether such experimentally induced changes in self-criticism lead to the improvements in psychological health that is implied by previous cross-sectional research\n\n\nTitle 2:\nA longitudinal experimental study comparing the effectiveness of happiness-enhancing strategies in Anglo Americans and Asian Americans\nAbstract 2:\nGrowing evidence suggests that well-being interventions can be effective . However , it is unclear whether happiness-increasing practice s are equally effective for individuals from different cultural background s. To investigate this question , Anglo Americans and predominantly foreign-born Asian Americans were r and omly assigned to express optimism , convey gratitude , or list their past experiences ( control group ) . Multilevel analyses indicated that participants in the optimism and gratitude conditions reported enhanced life satisfaction relative to those in the control condition . However , Anglo Americans in the treatment conditions demonstrated larger increases in life satisfaction relative to Asian Americans , while both cultural groups in the control condition showed the least improvement . These results are consistent with the idea that the value individualist cultures place on self-improvement and personal agency bolsters the efforts of Anglo Americans to become more satisfied , whereas collectivist cultures ’ de-emphasis of self-focus and individual goals interferes with the efforts of Asian Americans to pursue enhanced well-being\n\n\nTitle 3:\nWorking memory capacity can be improved by expressive writing: a randomized experiment in a Japanese sample.\nAbstract 3:\nThis study examined the influence of expressive writing on working memory capacity ( WMC ) , a component of executive function . Japanese undergraduates ( N=104 ) were individually tested across six separate experimental sessions ( baseline , three writing , and two follow-up sessions at 1 and 5 weeks ) . Participants were r and omly assigned to write about a traumatic experience , their best possible future selves ( BPS ) , or a trivial topic for 20 minutes . WMC tests were completed at baseline and follow-ups . Results indicate that expressive writing about traumatic experience can improve WMC at 5 weeks after writing , but that writing about BPS or trivial topics has no effect on WMC\n\n\nTitle 4:\nThe Delphi list: a criteria list for quality assessment of randomized clinical trials for conducting systematic reviews developed by Delphi consensus.\nAbstract 4:\nMost systematic review s rely substantially on the assessment of the method ological quality of the individual trials . The aim of this study was to obtain consensus among experts about a set of generic core items for quality assessment of r and omized clinical trials ( RCTs ) . The invited participants were experts in the field of quality assessment of RCTs . The initial item pool contained all items from existing criteria lists . Subsequently , we reduced the number of items by using the Delphi consensus technique . Each Delphi round comprised a question naire , an analysis , and a feedback report . The feedback report included staff team decisions made on the basis of the analysis and their justification . A total of 33 international experts agreed to participate , of whom 21 completed all question naires . The initial item pool of 206 items was reduced to 9 items in three Delphi rounds . The final criteria list ( the Delphi list ) was satisfactory to all participants . It is a starting point on the way to a minimum reference st and ard for RCTs on many different research topics . This list is not intended to replace , but rather to be used alongside , existing criteria lists",
"role": "user"
},
{
"content": "These results indicate that the BPS can be considered a valuable Positive Psychology Intervention to improve clients ' wellbeing , and it seems that it might be more effective for older participants and with shorter practice s ( measured as total minutes of practice )",
"role": "assistant"
}
] |
science.data_reco_mcq_sc
|
science.data_reco_mcq_sc.10392
|
[
{
"content": "Given a short query with keyphrases about a research idea in 2018 in the domain of artificial intelligence, recommend the relevant datasets to validate the research idea from options provided. A short description of the datasets is also provided to help you.\n\nQuery: In this paper, we propose an improved FCM algorithm based on morphological reconstruction and membership filtering (FRF\n\nKeyphrases: image segmentation\n\nDataset description:\nTHEODORE: Recent work about synthetic indoor datasets from perspective views has shown significant improvements of object detection results with Convolutional Neural Networks(CNNs). In this paper, we introduce THEODORE: a novel, large-scale indoor dataset containing 100,000 high- resolution diversified fisheye images with 14 classes.\nVOT2018: VOT2018 is a dataset for visual object tracking. It consists of 60 challenging videos collected from real-life datasets.\nBSDS500: Berkeley Segmentation Data Set 500 (BSDS500) is a standard benchmark for contour detection. This dataset is designed for evaluating natural edge detection that includes not only object contours but also object interior boundaries and background boundaries.\nHyperLex: A dataset and evaluation resource that quantifies the extent of of the semantic category membership, that is, type-of relation also known as hyponymy-hypernymy or lexical entailment (LE) relation between 2,616 concept pairs.\n\nOptions:- A: THEODORE B: VOT2018 C: BSDS500 D: HyperLex",
"role": "user"
},
{
"content": "BSDS500",
"role": "assistant"
}
] |
science.bioasq_factoid_qa
|
science.bioasq_factoid_qa.1049
|
[
{
"content": "You will be shown biomedical passages and your task is to the answer the provided question. Provide a concise and accurate response and do not include any additional text in the response other than the answer.\n\nQuestion: Which algorithm has been developed for finding conserved non-coding elements (CNEs)?\n\nContext: CNEFinder: finding conserved non-coding elements in genomes.\nTowards this direction, identifying sets of CNEs in a wide range of organisms is an important first step. Currently, there are no tools published in the literature for systematically identifying CNEs in genomes.Results: We fill this gap by presenting CNEFinder; a tool for identifying CNEs between two given DNA sequences with user-defined criteria.\nResults We fill this gap by presenting CNEFinder; a tool for identifying CNEs between two given DNA sequences with user-defined criteria.",
"role": "user"
},
{
"content": "CNEFinder",
"role": "assistant"
}
] |
science.data_reco_mcq_mc
|
science.data_reco_mcq_mc.979
|
[
{
"content": "You are provided with a research question, keyphrases about the question, a description of candidate datasets and dataset options. Read the description of popular datasets provided below and select the ones that can be used to validate the following research question. Use your knowledge of machine learning datasets to make the best judgement.\nYour response should be formatted as a `json` array. For instance, for the query \"Semi supervised image classification\", a sample response might be: [\"CIFAR-10\", \"CIFAR-100\"]. Do not include any extra text in the response other than the answer array.\n\nQuery: I'm going to train a model to perform a set of 12 tasks\n\nKeyphrases: dodecadialogue text\n\nDataset description:\nMegaFace: MegaFace was a publicly available dataset which is used for evaluating the performance of face recognition algorithms with up to a million distractors (i.e., up to a million people who are not in the test set). MegaFace contains 1M images from 690K individuals with unconstrained pose, expression, lighting, and exposure.\nMSRC-12: The Microsoft Research Cambridge-12 Kinect gesture data set consists of sequences of human movements, represented as body-part locations, and the associated gesture to be recognized by the system. The data set includes 594 sequences and 719,359 frames—approximately six hours and 40 minutes—collected from 30 people performing 12 gestures.\nMECCANO: The MECCANO dataset is the first dataset of egocentric videos to study human-object interactions in industrial-like settings. The MECCANO dataset has been acquired in an industrial-like scenario in which subjects built a toy model of a motorbike.\nConvAI2: The ConvAI2 NeurIPS competition aimed at finding approaches to creating high-quality dialogue agents capable of meaningful open domain conversation. The ConvAI2 dataset for training models is based on the PERSONA-CHAT dataset.\nDailyDialog: DailyDialog is a high-quality multi-turn open-domain English dialog dataset. It contains 13,118 dialogues split into a training set with 11,118 dialogues and validation and test sets with 1000 dialogues each.\nBDD100K: Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities.\n\nOptions:- A: MegaFace B: MSRC-12 C: MECCANO D: ConvAI2 E: DailyDialog F: BDD100K",
"role": "user"
},
{
"content": "[\"ConvAI2\", \"DailyDialog\"]",
"role": "assistant"
}
] |
science.medmentions_ner
|
science.medmentions_ner.1384
|
[
{
"content": "You will be shown an abstract from a biomedical research paper. Given this abstract, your task is to extract all unique entities of the following types: [\"HealthCareActivity\", \"InjuryOrPoisoning\", \"BodySubstance\", \"IntellectualProduct\", \"AnatomicalStructure\", \"SpatialConcept\", \"Chemical\", \"Bacterium\", \"MedicalDevice\", \"Organization\", \"BiomedicalOccupationOrDiscipline\", \"Finding\", \"BiologicFunction\", \"Virus\", \"ResearchActivity\", \"ClinicalAttribute\", \"PopulationGroup\", \"Eukaryote\", \"BodySystem\", \"Food\", \"ProfessionalOrOccupationalGroup\"].\n\nPlease return the output as a JSON object of the format: {\"Virus\": [\"HIV\", ...], \"Bacterium\": [\"MRSA\", ...], \"AnatomicalStructure\": [\"Lung\", ...], \"BodySystem\": [\"CNS\", ...], \"BodySubstance\": [\"Serum\", ...], \"Finding\": [\"Headache\", ...], \"InjuryOrPoisoning\": [\"Fracture\", ...], \"BiologicFunction\": [\"Death\", ...], \"HealthCareActivity\": [\"Biopsy\", ...], \"ResearchActivity\": [\"Clinical trial\", ...], \"MedicalDevice\": [\"Lenses\", ...], \"SpatialConcept\": [\"Camps\", ...], \"BiomedicalOccupationOrDiscipline\": [\"Forensic medicine\", ...], \"Organization\": [\"WHO\", ...], \"ProfessionalOrOccupationalGroup\": [\"Provider\", ...], \"PopulationGroup\": [\"Swimmers\", ...], \"Chemical\": [\"Gold\", ...], \"Food\": [\"Rice\", ...], \"IntellectualProduct\": [\"RPAM\", ...], \"ClinicalAttribute\": [\"Biomarker\", ...], \"Eukaryote\": [\"Dogs\", ...]}. The keys should be entity types and values should be lists of extracted entities belonging to the corresponding type. If you cannot find entities belonging to a specific type, the value should be [].\n\nOnly output the JSON object and do not include any additional text.\n\nAbstract:\n\nThe mechanism and application of the protein -stabilized gold nanocluster sensing system Protein -stabilized gold nanoclusters (protein - Au NCs) have been an attractive frontier of nanoparticle research. Due to their unique fluorescence properties, high stability, environmentally friendly synthetic routes and nontoxicity, protein - Au NCs could find applications in highly sensitive and selective detection of metal ions, inorganic ions and biomolecules in food, soil, water and biological samples. The past few years have witnessed the development of many successful strategies for the preparation of numerous protein - Au NC -based sensing systems. In this review, we focus on a number of sensing systems based on protein - Au NCs for the detection of various analytes of interest with a special emphasis on their corresponding sensing mechanisms.",
"role": "user"
},
{
"content": "{\"AnatomicalStructure\": [], \"Bacterium\": [], \"BiologicFunction\": [], \"BiomedicalOccupationOrDiscipline\": [], \"BodySubstance\": [], \"BodySystem\": [], \"Chemical\": [\"gold\", \"Au\", \"protein\", \"water\", \"metal ions\", \"inorganic ions\", \"Protein\"], \"ClinicalAttribute\": [], \"Eukaryote\": [], \"Finding\": [\"detection\", \"sensing\"], \"Food\": [\"food\"], \"HealthCareActivity\": [], \"InjuryOrPoisoning\": [], \"IntellectualProduct\": [], \"MedicalDevice\": [], \"Organization\": [], \"PopulationGroup\": [], \"ProfessionalOrOccupationalGroup\": [], \"ResearchActivity\": [\"nanoparticle research\"], \"SpatialConcept\": [], \"Virus\": []}",
"role": "assistant"
}
] |
science.bioasq_yesno_qa
|
science.bioasq_yesno_qa.415
|
[
{
"content": "You have to answer a biomedical question in binary format, i.e. only yes and no are the only acceptable answer formats. A list of paragraphs is provided as context to help you answer the question.\n\nQuestion: Is thrombophilia related to increased risk of miscarriage?\n\nContext: Thrombophilia does hardly increase the risk of IUGR/PMPC or if so, it can be prevented by LMWH\nfor illustrative purposes, a patient presenting with combined thrombophilia--both genetic and acquired--will be discussed. This patient had suffered severe gestational complications that led to devastating obstetrical outcome\nThrombophilias have been implicated in complications related to ischemic placental disease including recurrent pregnancy loss, intrauterine fetal demise, preeclampsia, fetal growth restriction, placental abruption, and preterm delivery\nFurther information about the combined risk of aPC resistance and pregnancy is needed before guidance on the management of affected women can be formulated.\nThrombotic risk during pregnancy and the puerperium is higher in asymptomatic women with than without thrombophilia\nFurther studies are required to assess the thrombotic risk in women with preeclampsia as well as early or late recurrent pregnancy loss.\nRisk of pregnancy-related venous thrombosis in carriers of severe inherited thrombophilia\nIn conclusion, homozygous carriers of factor V Leiden and, to a lesser extent, double heterozygous carriers of factor V Leiden and of the prothrombin mutation have an increased risk of venous thrombosis during pregnancy, particularly high during the postpartum period\nCareful diagnosis, observation and monitoring can add significant benefit to LMWH therapy during pregnancy\nPregnancy in healthy women is accompanied by hypercoagulable changes that may interact with thrombophilia risk factors and threaten pregnancy.\nFifty-three (13 %) women had antiphospholipid antibodies (lupus anticoagulant and/or anti-beta2-glycoprotein 1 antibodies) mainly associated with the risk of spontaneous abortion during the first trimester\nthrombophilia was found to be considerably more common in women with pregnancy-associated complications in comparison with the general population, and most frequently in conjunction with venous thromboembolism during pregnancy and the postpartum period\nWhen counseling white women with a history of preeclampsia, screening for thrombophilia can be useful for preconceptional counseling and pregnancy management.\nknowledge combined with the appropriate use of thromboprophylaxis and treatment in women who have objectively confirmed VTE continue to improve maternal and perinatal outcomes\nThe risk of having thrombophilia is doubled in men who have fathered pregnancies which ended in perinatal death as well as in the mothers of such pregnancies.\nThe prevalence of thrombophilic variants is of possible public health significance for other morbidity; but perhaps not in relation to preeclampsia\nThis study suggests that thrombophilia \"mediates\" in lowering of cardiovascular risk factors in women with a history of preeclampsia",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
] |
science.bioasq_general_qa
|
science.bioasq_general_qa.826
|
[
{
"content": "You will be shown a question, followed by excerpts from biomedical research papers. Please answer the question based on the provided context. Do not include any text in your response other than the answer.\n\nQuestion: What is Heterochromia Iridis?\n\nContext: The purpose of this study is to report a new and promising method for changing iris color in a sectorial heterochromia iridis patient. A 22-year-old man with a complaint of innate color disparity between his eyes presented to our clinic to seek medical advice.\nTo present a case of iatrogenic Horner's syndrome seen together with the heterochromia in the post-thyroidectomy period.METHODS: A 23-year-old female patient was admitted to our clinic with complaints of low vision in the eye and difference in eye color that developed over the past two years.\nHeterochromia iridis, asymmetry of iris pigmentation, has been well described with congenital Horner syndrome.\nBACKGROUND Heterochromia iridis, asymmetry of iris pigmentation, has been well described with congenital Horner syndrome.\nBACKGROUND Heterochromia iridis, asymmetry of iris pigmentation, has been well described with congenital Horner syndrome.",
"role": "user"
},
{
"content": "Heterochromia Iridis is a condition where the affected person has differences in the color of the iris. Heterochromia iridis is a rare autosomal recessive disorder of the iris, characterized by a heterochromatic pattern of inheritance, variable expressivity, and partial or total absence of iris and/or blonde hair. Heterochromia Iridis is a rare autosomal dominant disorder of melanocyte development characterized by heterochromatosis of the coronal, sagittal, and lambdoid sutures.",
"role": "assistant"
}
] |
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 27