The Use of AI in Diagnosing Diseases and Providing Management Plans: A Consultation on Cardiovascular Disorders With ChatGPT
Authors:
Open Access
- 7 August 2023
- journal article
- research article
- Published by Springer Nature in Cureus
- Vol. 15 (8) , e43106
Abstract
Background: Cardiovascular diseases (CVDs) have remained the leading causes of death worldwide and substantially contribute to loss of health and excess health system costs. According to WHO, cardiovascular diseases (CVDs) take an estimated 17.9 million lives each year. One of the reasons for an immensely high fatality in CVDs is lack of efficient diagnosis and prompt treatment. Timely recognition and management are crucial to minimize mortality. In the advancing world, AI (artificial intelligence) and machine learning technologies continue to progress, this advancement has opened new avenues for innovative approaches in the field of medicine. Despite the rapid development in the field of AI, there is a limited understanding of the potential benefits among clinicians and medical practitioners. Methods: In this study, we aimed to investigate the potential that the AI language model holds to assist health practitioners in the diagnosis and treatment of cardiovascular disorders. We asked Chat Generative Pre-trained Transformer (ChatGPT) 10 hypothetical questions simulating clinical consultation. The responses given by ChatGPT were accessed for its accuracy and accessibility by a team of medical specialists and cardiologists with extensive experience in managing cardiovascular disorders. Result: Out of the 10 clinical scenarios inserted in ChatGPT, eight were perfectly diagnosed, however, the other two answers given by ChatGPT were not entirely incorrect since those conditions were associated with the actual diagnosis. Furthermore, the management plans and the treatment protocols that were given by ChatGPT were in line with the literature and current medical knowledge. The exact drug names and regimens were not provided but a general guideline that was given by this AI tool is definitely beneficial for junior doctors in getting an idea on how to proceed or refresh their previous knowledge. Conclusion: ChatGPT is a valuable resource in the field of medicine. Its comprehensive and properly organized response in an understandable language has made it an effective and efficient tool to be used. However, it is crucial to note that its limitations, such as the need for all associated and typical signs, symptoms, and physical examination findings, and its inability to personalize treatments need to be acknowledged.Keywords
This publication has 11 references indexed in Scilit:
- ChatGPT-4 and the Global Burden of Disease Study: Advancing Personalized Healthcare Through Artificial Intelligence in Clinical and Translational MedicineCureus, 2023
- ChatGPT: Is this version good for healthcare and research?Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 2023
- Unilateral pulmonary edema and acute severe mitral regurgitation associated with operatively repaired aortic coarctationBaylor University Medical Center Proceedings, 2021
- The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategiesJournal of Biomedical Informatics, 2021
- Síndrome de Marfan revisitada – da genética à clínicaRevista Portuguesa de Cardiologia, 2020
- Pseudomonas aeruginosa infective endocarditis in patients who do not use intravenous drugs: Analysis of risk factors and treatment outcomesJournal of Microbiology, Immunology and Infection, 2016
- Population-Based Study of Incidence and Outcome of Acute Aortic Dissection and Premorbid Risk Factor ControlCirculation, 2013
- Race/ethnicity and the incidence of new-onset atrial fibrillation after isolated coronary artery bypass surgeryHeart Rhythm, 2010
- Mitral Annular Calcification and the Risk of Stroke in an Elderly CohortNew England Journal of Medicine, 1992
- Second and Third Degree Atrioventricular Block with Graves' Disease: A Case Report and Review of the LiteraturePacing and Clinical Electrophysiology, 1980