检索结果-内蒙古大学图书馆

Correction: How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge Assessment

学校读者我要写书评

暂无评论

JMIR Medical Education 2024年 10卷 e57594页

作者： Gilson, Aidan Safranek, Conrad W. Huang, Thomas Socrates, Vimig Chi, Ling Taylor, Richard Andrew Chartash, David Section for Biomedical Informatics and Data Science Yale University School of Medicine New Haven CT United States Department of Emergency Medicine Yale University School of Medicine New Haven CT United States Program of Computational Biology and Bioinformatics Yale University New Haven CT United States School of Medicine University College Dublin National University of Ireland Dublin Dublin Ireland Section for Biomedical Informatics and Data Science Yale University School of Medicine 300 George Street Suite 501 New Haven 06511 CT United States

In “How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge” (MIR Med Educ 2023;9:e45312) three additions were made to enhance discoverability. The title originally appeared as: How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment And has been changed to: How Does ChatGPT Perform on the United States Medical Licensing Examination (USMLE)? The Implications of Large Language Models for Medical Education and Knowledge In the “Objective” section of the Abstract, the following sentence: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. Has been changed to read as: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination (USMLE) Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. Finally, the abbreviation “USMLE” has been added to the Keywords section. The correction will appear in the online version of the paper on the JMIR Publications website on February 27, 2024 together with the publication of this correction notice. Because this was made after submission to PubMed, PubMed Central, and other full-text repositories, the corrected article has also been resubmitted to those repositories. © 2024 JMIR Publications Inc.. All rights reserved.

关键词：

Analysis of time-to-event for observational studies: Guidance to the use of intensity models

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Andersen, Per Kragh Perme, Maja Pohar van Houwelingen, Hans C. Cook, Richard J. Joly, Pierre Martinussen, Torben Taylor, Jeremy M.G. Abrahamowicz, Michal Therneau, Terry M. Section of Biostatistics University of Copenhagen Denmark Department of Biostatistics and Medical Informatics Medical faculty University of Ljubljana Slovenia Department of Biomedical Data Sciences Leiden University Netherlands Department of Statistics and Actuarial Science University of Waterloo Canada Inserm ISPED Bordeaux Populations Health Research Center University of Bordeaux France Department of Biostatistics University of Michigan United States Department of Epidemiology Biostatistics and Occupational Health McGill University Montreal Canada Division of Biomedical Statistics and Informatics Mayo Clinic Rochester United States

This paper provides guidance for researchers with some mathematical background on the conduct of time-to-event analysis in observational studies based on intensity (hazard) models. Discussions of basic concepts like time axis, event definition and censoring are given. Hazard models are introduced, with special emphasis on the Cox proportional hazards regression model. We provide check lists that may be useful both when fitting the model and assessing its goodness of fit and when interpreting the results. Special attention is paid to how to avoid problems with immortal time bias by introducing time-dependent covariates. We discuss prediction based on hazard models and difficulties when attempting to draw proper causal conclusions from such models. Finally, we present a series of examples where the methods and check lists are exemplified. Computational details and implementation using the freely available R software are documented in Supplementary Material. The paper was prepared as part of the STRATOS initiative. Copyright © 2020, The Authors. All rights reserved.

关键词： Biographies

53914 Association between Atopic Dermatitis and Peripheral Vascular Disease: A Cross-sectional Study in the All of Us Research Program

学校读者我要写书评

暂无评论

Journal of the American Academy of Dermatology 2024年第3期91卷 AB19-AB19页

作者： Spaulding, Sarah, BS Chen, Gloria, BA Craver, Andrew, BA Cohen, Jeffrey, MD Yale School of Medicine Department of Dermatology Yale School of Medicine Section of Biomedical Informatics and Data Science Yale School of Medicine

Integration of Clinical, Biological, and Computational Perspectives to Support Cerebral Autoregulatory Informed Clinical Decision Making Decomposing Cerebral Autoregulation using Mechanistic Timescales to Support Clinical Decision-Making

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Briggs, Jennifer K. Stroh, J.N. Bennett, T.D. Park, S. Albers, D.J. Department of Bioengineering College of Engineering Design and Computing Aurora CO United States Section of Informatics and Data Science Department of Pediatrics University of Colorado School of Medicine AuroraCO United States Section of Critical Care Medicine Department of Pediatrics University of Colorado School of Medicine AuroraCO United States Department of Neurology Columbia University Irving Medical Center NewYork-Presbyterian Hospital New YorkNY10032 United States Department of Biomedical Informatics Columbia University Irving Medical Center NewYork-Presbyterian Hospital New YorkNY10032 United States

Adequate brain perfusion is required for proper brain function and life. Maintaining optimal brain perfusion to avoid secondary brain injury is one of the main concerns of neurocritical care. Cerebral autoregulation is responsible for maintaining optimal brain perfusion despite pressure derangements. Knowledge of cerebral autoregulatory function should be a key factor in clinical decision-making, yet it is often insufficiently and incorrectly applied. Multiple physiologic mechanisms impact cerebral autoregulation, each of which operate on potentially different and incompletely understood timescales confounding conclusions drawn from observations. Because of such complexities, clinical conceptualization of cerebral autoregulation has been distilled into practical indices defined by multimodal neuromonitoring, which removes mechanistic information and limits decision options. The next step towards cerebral autoregulatory-informed clinical decision-making is to quantify cerebral autoregulation mechanistically, which requires decomposing cerebral autoregulation into its fundamental processes and partitioning those processes into the timescales at which each operates. In this review, we scrutinize biologically, clinically, and computationally focused literature to build a timescales-based framework around cerebral autoregulation. We conclude that the myogenic mechanism acts on timescales faster than one second, the endothelial mechanism acts in one to two minutes, the metabolic mechanism will act on different timescales depending on the circumstance but will not be reflected in dynamic CA testing due to timescale constraints, and the neurologic mechanism acts within two seconds. These timescales have never been synthesized in the literature and lay the foundation for a new framework in which to view and test cerebral autoregulatory function. This new framework will allow us to quantify mechanistic interactions and directly infer which mechanism(s) are functioning based o

关键词： Decision making

Detecting potentially harmful and protective suicide-related content on twitter: A machine learning approach

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Metzler, Hannah Baginski, Hubert Niederkrotenthaler, Thomas Garcia, David Section for Science of Complex Systems Center for Medical Statistics Informatics and Intelligent Systems Medical University of Vienna Austria Unit Suicide Research & Mental Health Promotion Department of Social and Preventive Medicine Center for Public Health Medical University of Vienna Austria Complexity Science Hub Vienna Austria Institute of Interactive Systems and Data Science Department of Computer Science and Biomedical Engineering Graz University of Technology Graz Austria Institute of Globally Distributed Open Research and Education Austria Institute of Information Systems Engineering Vienna University of Technology Vienna Austria

Background Research has repeatedly shown that exposure to suicide-related news media content is associated with suicide rates, with some content characteristics likely having harmful and others potentially protective effects. Although good evidence exists for a few selected characteristics, systematic and large-scale investigations are missing. Moreover, the growing importance of social media, particularly among young adults, calls for studies on the effects of content posted on these platforms. Objective This study applies natural language processing and machine learning methods to classify large quantities of social media data according to characteristics identified as potentially harmful or beneficial in media effects research on suicide and prevention. Methods We manually labeled 3202 English tweets using a novel annotation scheme that classifies suicide-related tweets into 12 categories. Based on these categories, we trained a benchmark of machine learning models for a multi-class and a binary classification task. As models, we included a majority classifier, an approach based on word frequency (TF-IDF with a linear SVM) and two state-of-the-art deep learning models (BERT, XLNet). The first task classified postings into six main content categories, which are particularly relevant for suicide prevention based on previous evidence. These included personal stories of either (1) suicidal ideation and attempts or (2) coping and recovery, calls for action intending to spread either (3) problem awareness or (4) prevention-related information, (5) reporting of suicide cases, and (6) other tweets irrelevant to these five categories. The second classification task was binary, and separated postings in the 11 categories that refer to actual suicide, from postings in the off-topic category, which use suicide-related terms in another meaning or context. Results In both tasks, the performance of the two deep learning models was very similar and better than the majority or th

关键词： Learning algorithms

How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment

学校读者我要写书评

暂无评论

JMIR Medical Education 2023年 9卷 e45312页

Background: Chat Generative Pre-trained Transformer (ChatGPT) is a 175-billion-parameter natural language processing model that can generate conversation-style responses to user input. Objective: This study aimed to evaluate the performance of ChatGPT on questions within the scope of the United States Medical Licensing Examination Step 1 and Step 2 exams, as well as to analyze responses for user interpretability. Methods: We used 2 sets of multiple-choice questions to evaluate ChatGPT’s performance, each with questions pertaining to Step 1 and Step 2. The first set was derived from AMBOSS, a commonly used question bank for medical students, which also provides statistics on question difficulty and the performance on an exam relative to the user base. The second set was the National Board of Medical Examiners (NBME) free 120 questions. ChatGPT’s performance was compared to 2 other large language models, GPT-3 and InstructGPT. The text output of each ChatGPT response was evaluated across 3 qualitative metrics: logical justification of the answer selected, presence of information internal to the question, and presence of information external to the question. Results: Of the 4 data sets, AMBOSS-Step1, AMBOSS-Step2, NBME-Free-Step1, and NBME-Free-Step2, ChatGPT achieved accuracies of 44% (44/100), 42% (42/100), 64.4% (56/87), and 57.8% (59/102), respectively. ChatGPT outperformed InstructGPT by 8.15% on average across all data sets, and GPT-3 performed similarly to random chance. The model demonstrated a significant decrease in performance as question difficulty increased (P=.01) within the AMBOSS-Step1 data set. We found that logical justification for ChatGPT’s answer selection was present in 100% of outputs of the NBME data sets. Internal information to the question was present in 96.8% (183/189) of all questions. The presence of information external to the question was 44.5% and 27% lower for incorrect answers relative to correct answers on the NBME-Free-Step1 (P<.001

关键词： artificial intelligence chatbot ChatGPT conversational agent education technology generative pre-trained transformer GPT machine learning medical education MedQA natural language processing NLP

Leveraging Undecided Cases in Chart-Reviewed Phenotypes to Enhance Ehr-Based Association Studies

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Jian, Xinyao Zhang, Dazheng Yu, Zehao Xu, Hua Bian, Jiang Wu, Yonghui Tong, Jiayi Chen, Yong University of Pennsylvania Perelman School of Medicine PhiladelphiaPA United States Department of Biostatistics Epidemiology and Informatics Perelman School of Medicine The University of Pennsylvania PhiladelphiaPA United States Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida GainesvilleFL United States Section of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States Cancer Informatics Shared Resource University of Florida Health Cancer Center GainesvilleFL United States Department of Biostatistics Johns Hopkins Bloomberg School of Public Health BaltimoreMD United States The Graduate Group in Applied Mathematics and Computational Science School of Arts and Sciences University of Pennsylvania PhiladelphiaPA United States Leonard Davis Institute of Health Economics PhiladelphiaPA United States PhiladelphiaPA United States PhiladelphiaPA United States

Objectives: In electronic health record (EHR)-based association studies, phenotyping algorithms efficiently classify patient clinical outcomes into binary categories but are susceptible to misclassification errors. The gold standard, manual chart review, involves clinicians determining the true disease status based on their assessment of health records. These clinicians-labeled phenotypes are labor-intensive and typically limited to a small subset of patients, potentially introducing a third "undecided" category when phenotypes are indeterminate. We aim to effectively integrate the algorithm-derived and chart-reviewed outcomes when both are available in EHR-based association *** and Methods: We propose an augmented estimation method that combines the binary algorithm-derived phenotypes for the entire cohort with the trinary chart-reviewed phenotypes for a small, selected subset. Additionally, a cost-effective outcome-dependent sampling strategy is used to address the rare disease scenarios. The proposed trinary chart-reviewed phenotype integrated cost-effective augmented estimation (TriCA) was evaluated through a wide range of simulation settings and real-world applications in Alzheimer's disease and related dementias using EHR data from the OneFlorida+ Clinical Research ***: Compared to estimation based on random sampling, our augmented method improved mean square error by up to 43.5% in simulation studies;compared to estimation using trinary chart-reviewed phenotypes only, our method improved efficiency by up to 32.1% in the real-world data ***: Our simulation studies and real-world application demonstrate that, compared to existing methods, the proposed method provides unbiased estimates with higher statistical ***: The proposed method effectively combined binary algorithm-derived phenotypes for the whole cohort with trinary chart-reviewed outcomes for a limited validation set, making it applicable to

关键词： Electronic health record

Repurposing Drugs for Alzheimer's Diseases through Link Prediction on biomedical Literature

学校读者我要写书评

暂无评论

Repurposing Drugs for Alzheimer's Diseases through Link Pred...

IEEE International Conference on Healthcare informatics (ICHI)

作者： Yongkang Xiao Yu Hou Huixue Zhou Gayo Diallo Marcelo Fiszman Julian Wolfson Halil Kilicoglu You Chen Hua Xu William G. Mantyh Rui Zhang Institute for Health Informatics University of Minnesota Minneapolis MN USA Department of Surgery University of Minnesota Minneapolis MN USA INRIA SISTM Team AHeaD -INSERM 1219 Bordeaux Population Health University of Bordeaux France NITES - Núcleo de Inovação e Tecnologia Em Saúde Pontifical Catholic University of Rio de Janeiro Brazil Division of Biostatistics School of Public Health University of Minnesota Minneapolis MN USA School of Information Sciences University of Illinois Urbana-Champaign Champaign IL USA Department of Biomedical Informatics Vanderbilt University Medical Center Nashville TN USA Section of Biomedical Informatics and Data Science Yale University New Haven Connecticut USA Department of Neurology University of Minnesota Minneapolis MN USA

Recently, computational drug repurposing has emerged as a promising method for identifying new interventions for diseases. This study predicts novel drugs for Alzheimer's disease (AD) through link prediction on our developed biomedical knowledge graph. We constructed a comprehensive knowledge graph containing AD concepts and various potential interventions, called ADInt, by integrating a dietary supplement (DS) domain knowledge graph, SuppKG, with semantic triples from SemMedDB database. Four knowledge graph embedding models (TransE, RotatE, DistMult and ComplEX) and two graph convolutional network models (R-GCN and CompGCN) were compared to learn the representation of ADInt. R-GCN outperformed other models by evaluating on the time slice test set and the clinical trial test set, and was used to generate the score tables for the link prediction task. According to the results of link prediction, we proposed candidate drugs for AD. In conclusion, we presented a novel methodology to extend an existing knowledge graph and discover novel drugs for AD. Our method can potentially be applied to other clinical problems, such as discovering drug adverse reactions and drug-drug interactions.

关键词：

Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Zhiyuan Duan, Jinhao Yuan, Chenxi Chen, Qingyu Chen, Tianlong Zhang, Yue Wang, Ren Shi, Xiaoshuang Xu, Kaidi Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China Department of Computer Science Drexel University PhiladelphiaPA19104 United States Perelman School of Medicine University of Pennsylvania PhiladelphiaPA19104 United States Section of Biomedical Informatics & Data Science Yale School of Medicine Yale University New HavenCT06510 United States Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical and Computer Engineering Illinois Institute of Technology ChicagoIL60616 United States

Uncertainty estimation is crucial for the reliability of safety-critical human and artificial intelligence (AI) interaction systems, particularly in the domain of healthcare engineering. However, a robust and general uncertainty measure for free-form answers has not been well-established in open-ended medical question-answering (QA) tasks, where generative inequality introduces a large number of irrelevant words and sequences within the generated set for uncertainty quantification (UQ), which can lead to biases. This paper introduces Word-Sequence Entropy (WSE), a method that calibrates uncertainty at both the word and sequence levels, considering semantic relevance. WSE quantifies uncertainty in a way that is more closely aligned with the reliability of LLMs during uncertainty quantification (UQ). We compare WSE with six baseline methods on five free-form medical QA datasets, utilizing seven popular large language models (LLMs). Experimental results demonstrate that WSE exhibits superior performance in UQ under two standard criteria for correctness evaluation. Additionally, in terms of real-world medical QA applications, the performance of LLMs is significantly enhanced (e.g., a 6.36% improvement in model accuracy on the COVID-QA dataset) by employing responses with lower uncertainty that are identified by WSE as final answers, without any additional task-specific fine-tuning or architectural modifications. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics