Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Background: Meta-analysis is a critical tool in evidence-based medicine, particularly in cardiology, where it synthesizes data from multiple studies to inform clinical decisions. This study explored the potential of using ChatGPT to streamline and enhance the meta-analysis process.
Aim: To investigate the potential of ChatGPT to conduct meta-analyses in interventional cardiology by comparing the results of ChatGPT-generated analyses with those of randomly selected, human-conducted meta-analyses on the same topic.
Methods: We systematically searched PubMed for meta-analyses on interventional cardiology published in 2024. Five meta-analyses were randomly chosen. ChatGPT 4.0 was used to perform meta-analyses on the extracted data. We compared the results from ChatGPT with the original meta-analyses, focusing on key effect sizes, such as risk ratios (RR), hazard ratios, and odds ratios, along with their confidence intervals (CI) and values.
Results: The ChatGPT results showed high concordance with those of the original meta-analyses. For most outcomes, the effect measures and values generated by ChatGPT closely matched those of the original studies, except for the RR of stent thrombosis in the Sreenivasan study, where ChatGPT reported a non-significant effect size, while the original study found it to be statistically significant. While minor discrepancies were observed in specific CI and values, these differences did not alter the overall conclusions drawn from the analyses.
Conclusion: Our findings suggest the potential of ChatGPT in conducting meta-analyses in interventional cardiology. However, further research is needed to address the limitations of transparency and potential data quality issues, ensuring that AI-generated analyses are robust and trustworthy for clinical decision-making.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12400340 | PMC |
| http://dx.doi.org/10.5662/wjm.v15.i4.102290 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
ChatGPT-4o is Not a Reliable Study Source for Orthopaedic Surgery Residents.
JB JS Open Access
September 2025
Department of Orthopaedic Surgery, St. Luke's University Health Network, Bethlehem, Pennsylvania.
Background: The use of artificial intelligence platforms by medical residents as an educational resource is increasing. Within orthopaedic surgery, older Chat Generative Pre-trained Transformer (ChatGPT) models performed worse than resident physicians on practice examinations and rarely answered questions with images correctly. The newer ChatGPT-4o was designed to improve these deficiencies but has not been evaluated.
View Article and Find Full Text PDFArtificial Intelligence in Cardiac Treatment Decision-Making: An Evaluation of the Performance of ChatGPT Versus the Heart Team in Coronary Revascularization.
Rev Cardiovasc Med
August 2025
Cardiovascular Surgery Department, Ankara Bilkent City Hospital, 06800 Ankara, Turkey.
Background: This study aimed to investigate the performance of two versions of ChatGPT (o1 and 4o) in making decisions about coronary revascularization and to compare the recommendations of these versions with those of a multidisciplinary Heart Team. Moreover, the study aimed to assess whether the decisions generated by ChatGPT, based on the internal knowledge base of the system and clinical guidelines, align with expert recommendations in real-world coronary artery disease management. Given the increasing prevalence and processing capabilities of large language models, such as ChatGPT, this comparison offers insights into the potential applicability of these systems in complex clinical decision-making.
View Article and Find Full Text PDFNon-invasive motor unit analysis reveals specific responses during maximal muscle contraction under normobaric hypoxia.
Pflugers Arch
September 2025
Department of Science, University "G. d'Annunzio" Chieti-Pescara, Chieti, Italy.
Hypoxia has been extensively studied as a stressor which pushes human bodily systems to responses and adaptations. Nevertheless, a few evidence exist onto constituent trains of motor unit action potential, despite recent advancements which allow to decompose surface electromyographic signals. This study aimed to investigate motor unit properties from noninvasive approaches during maximal isometric exercise in normobaric hypoxia.
View Article and Find Full Text PDF[The Dawn of Generative AI in Medicine: Empathy Through Emulation].
Dtsch Med Wochenschr
September 2025
Klinik für Kardiologie, Angiologie und Pneumologie, Institut für Cardiomyopathien Heidelberg, Universitätsklinikum Heidelberg, Heidelberg, Deutschland.
Rapid advancements in Artificial Intelligence (AI) have significantly impacted multiple sectors of our society, including healthcare. While conventional AI has been instrumental in solving mainly image recognition tasks and thereby adding in well-defined situations such as supporting diagnostic imaging, the emergence of generative AI is impacting on one of the main professional competences: doctor-patient interaction.A convergence of natural language processing (NLP) and generative AI is exemplified by intelligent chatbots like ChatGPT.
View Article and Find Full Text PDFChatGPT in Nursing: Applications, Advantages, and Challenges in Education, Research, and Clinical Practice.
Ann Biomed Eng
September 2025
Department of Midwifery, Faculty of Health Sciences, Sakarya University, 54100, Sakarya, Turkey.
The incorporation of AI-supported language models into the healthcare sector holds significant potential to revolutionize nursing education, research, and clinical practice. Within this framework, ChatGPT has emerged as a valuable tool for personalizing educational materials, enhancing academic productivity, expediting clinical decision-making processes, and optimizing research efficiency. In the realm of nursing education, ChatGPT offers numerous advantages, including the preparation of course content, facilitation of student assessments, and the development of simulation-based learning environments.
View Article and Find Full Text PDF