Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Chat Generative Pretrained Transformer (ChatGPT) is a natural language processing tool created by OpenAI. Much of the discussion regarding artificial intelligence (AI) in medicine is the ability of the language to enhance medical practice, improve efficiency and decrease errors. The objective of this study was to analyze the ability of ChatGPT to answer board-style cardiovascular medicine questions by using the Medical Knowledge Self-Assessment Program (MKSAP).The study evaluated the performance of ChatGPT (versions 3.5 and 4), alongside internal medicine residents and internal medicine and cardiology attendings, in answering 98 multiple-choice questions (MCQs) from the Cardiovascular Medicine Chapter of MKSAP. ChatGPT-4 demonstrated an accuracy of 74.5 %, comparable to internal medicine (IM) intern (63.3 %), senior resident (63.3 %), internal medicine attending physician (62.2 %), and ChatGPT-3.5 (64.3 %) but significantly lower than cardiology attending physician (85.7 %). Subcategory analysis revealed no statistical difference between ChatGPT and physicians, except in valvular heart disease where cardiology attending outperformed ChatGPT (p = 0.031) for version 3.5, and for heart failure (p = 0.046) where ChatGPT-4 outperformed senior resident. While ChatGPT shows promise in certain subcategories, in order to establish AI as a reliable educational tool for medical professionals, performance of ChatGPT will likely need to surpass the accuracy of instructors, ideally achieving the near-perfect score on posed questions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ijcard.2024.132576 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Comparison of Navier-Stokes and lattice Boltzmann solvers for subject-specific modelling of intracranial aneurysms.
Comput Biol Med
September 2025
INSIGNEO Institute for in silico medicine, University of Sheffield, UK; School of Mechanical, Aerospace and Civil Engineering, University of Sheffield, UK. Electronic address:
Modelling cardiovascular disease is at the forefront of efforts to use computational tools to assist in the analysis and forecasting of an individual's state of health. To build trust in such tools, it is crucial to understand how different approaches perform when applied to a nominally identical scenario, both singularly and across a population. To examine such differences, we have studied the flow in aneurysms located on the internal carotid artery and middle cerebral artery using the commercial solver Ansys CFX and the open-source code HemeLB.
View Article and Find Full Text PDFIntracellular Galectin-3 as a Crucial Regulator of Foam Cell Formation and Apoptosis Progression through the Modulation of Membrane Lipid Rafts.
Arch Med Res
September 2025
Department and Graduate Institute of Microbiology and Immunology, National Defense Medical Center, Taipei, Taiwan. Electronic address:
Background: Atherosclerosis, a leading cause of cardiovascular disease (CVD) mortality worldwide, is characterized by dysregulated lipid metabolism and unresolved inflammation. Macrophage-derived foam cell formation and apoptosis contribute to plaque formation and vulnerability. Elevated serum galectin-3 (Gal-3) levels are associated with increased CVD risk, and Gal-3 in plaques is strongly associated with macrophages.
View Article and Find Full Text PDFCombined SHR and SIRI biomarkers predict increased coronary heart disease risk in type 2 diabetes.
Biomol Biomed
September 2025
Department of Cardiology, Renmin Hospital of Wuhan University, Wuhan, China.
Coronary heart disease (CHD) is a leading cause of morbidity and mortality; patients with type 2 diabetes mellitus (T2DM) are at particularly high risk, highlighting the need for reliable biomarkers for early detection and risk stratification. We investigated whether combining the stress hyperglycemia ratio (SHR) and systemic inflammation response index (SIRI) improves CHD detection in T2DM. In this retrospective cohort of 943 T2DM patients undergoing coronary angiography, associations of SHR and SIRI with CHD were evaluated using multivariable logistic regression and restricted cubic splines; robustness was examined with subgroup and sensitivity analyses.
View Article and Find Full Text PDFCorrection: Factors Affecting the Receptiveness of Chinese Internists and Surgeons Toward Artificial Intelligence-Driven Drug Prescription: Protocol for a Systematic Survey Study.
JMIR Res Protoc
September 2025
State Key Laboratory of Experimental Hematology, National Clinical Research Center for Blood Diseases, Haihe Laboratory of Cell Ecosystem, Institute of Hematology & Blood Diseases Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, China.
[This corrects the article DOI: .].
View Article and Find Full Text PDFUnderstanding and Addressing Challenges With Electronic Health Record Use in Gynecological Oncology: Cross-Sectional Survey of Multidisciplinary Professionals in the United Kingdom and Co-Design of an Integrated Informatics Platform to Support Clinical Decision-Making.
JMIR Cancer
September 2025
iCARE Secure Data Environment & Digital Collaboration Space, NIHR Imperial Biomedical Research Centre, London, United Kingdom.
Background: Electronic health records (EHRs) are a cornerstone of modern health care delivery, but their current configuration often fragments information across systems, impeding timely and effective clinical decision-making. In gynecological oncology, where care involves complex, multidisciplinary coordination, these limitations can significantly impact the quality and efficiency of patient management. Few studies have examined how EHR systems support clinical decision-making from the perspective of end users.
View Article and Find Full Text PDF