Background: Artificial intelligence (AI) has significantly impacted health care, medicine, and radiology, offering personalized treatment plans, simplified workflows, and informed clinical decisions. ChatGPT (OpenAI), a conversational AI model, has revolutionized health care and medical education by simulating clinical scenarios and improving communication skills. However, inconsistent performance across medical licensing examinations and variability between countries and specialties highlight the need for further research on contextual factors influencing AI accuracy and exploring its potential to enhance technical proficiency and soft skills, making AI a reliable tool in patient care and medical education. Objective: This systematic review aims to evaluate and compare the accuracy and potential of ChatGPT-3.5 and 4.0 in medical licensing and in-training residency examinations across various countries and specialties. Methods: A systematic review and meta-analysis were conducted, adhering to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Data were collected from multiple reputable databases (Scopus, PubMed, JMIR Publications, Elsevier, BMJ, and Wiley Online Library), focusing on studies published from January 2023 to July 2024. Analysis specifically targeted research assessing ChatGPT’s efficacy in medical licensing exams, excluding studies not related to this focus or published in languages other than English. Ultimately, 53 studies were included, providing a robust dataset for comparing the accuracy rates of ChatGPT-3.5 and 4.0. Results: ChatGPT-4 outperformed ChatGPT-3.5 in medical licensing exams, achieving a pooled accuracy of 81.8%, compared to ChatGPT-3.5’s 60.8%. In in-training residency exams, ChatGPT-4 achieved an accuracy rate of 72.2%, compared to 57.7% for ChatGPT-3.5. The forest plot presented a risk ratio of 1.36 (95% CI 1.30-1.43), demonstrating that ChatGPT-4 was 36% more likely to provide correct answers than ChatGPT-3.5 across both medical licensing and residency exams. These results indicate that ChatGPT-4 significantly outperforms ChatGPT-3.5, but the performance advantage varies depending on the exam type. This highlights the importance of targeted improvements and further research to optimize ChatGPT-4’s performance in specific educational and clinical settings. Conclusions: ChatGPT-4.0 and 3.5 show promising results in enhancing medical education and supporting clinical decision-making, but they cannot replace the comprehensive skill set required for effective medical practice. Future research should focus on improving AI’s capabilities in interpreting complex clinical data and enhancing its reliability as an educational resource.

Background: Atherosclerotic heart disease (AHD) remains a leading cause of global mortality and a major driver of fatal cardiac syndromes. Ischemic myocardial injury from AHD can lead to ventricular remodeling and myocyte loss, progressing to heart failure (HF) and, in advanced stages, cardiogenic shock (CS). However, long-term national mortality trends for deaths involving the combined burden of AHD, HF, and CS remain insufficiently characterized. Methods: Mortality data from 1999 to 2023 were obtained from the CDC WONDER Multiple Cause of Death database. Deaths involving CS (ICD-10 R57.0), HF (I50, I50.1, I50.9), and AHD (I25.1) in adults were identified. Age-adjusted mortality rates (AAMRs) per 1,000,000 population were calculated and stratified by sex, race/ethnicity, and geographic region. Temporal trends were analyzed using Joinpoint regression to estimate annual percent changes (APCs) and average annual percent changes (AAPCs). Autoregressive integrated moving average (ARIMA) modeling was used to forecast mortality trends through 2035. Results: A total of 15,631 deaths were attributed to AHD-associated HF and CS during the study period. Overall AAMRs increased significantly (AAPC 3.75%; 95% CI 3.32–4.29; p < 0.01). Mortality rates declined between 1999 and 2006 (APC −7.55%; 95% CI −13.15 to −5.23; p < 0.01), increased modestly from 2006 to 2013 (APC 3.94%; 95% CI −1.47 to 8.91), and rose sharply from 2013 to 2023 (APC 12.33%; 95% CI 11.27–14.46; p < 0.01). Males had higher AAMRs than females in 2023 (9.26 vs. 3.39 per 1,000,000). Non-Hispanic White individuals accounted for the highest number of deaths (11,878), followed by non-Hispanic Black individuals (1708), while non-Hispanic American Indian populations had the lowest counts (39). Regionally, the West (7.31) and South (5.92) exhibited the highest final AAMRs. State-level AAMRs ranged from 2.49 in Minnesota to 8.27 in Nevada. Conclusions: Mortality involving AHD, HF, and CS has risen substantially in the United States since 2013, with marked demographic and geographic disparities. These findings highlight a growing burden of advanced ischemic heart disease and heart failure and underscore the need for earlier intervention and improved access to advanced HF therapies to prevent progression to cardiogenic shock and death.

Background: Cardiogenic shock (CS) and chronic ischemic heart disease (CIHD) remain major contributors to cardiovascular mortality in the United States. Although mortality related to ischemic disease declined in the early 2000s, recent trends suggest a resurgence. Methods: This population-based study utilized the Centers for Disease Control and Prevention’s Wide-Ranging OnLine Data for Epidemiologic Research (CDC WONDER) database from 1999 to 2023. Deaths were identified using ICD-10 codes R57.0 (CS) and I25 (CIHD). Adults aged ≥ 45 years were included. Crude mortality rates (CMRs) and age-adjusted mortality rates (AAMRs) were calculated, with temporal changes assessed using Joinpoint regression to estimate Annual Percent Change (APC) and Average Annual Percent Change (AAPC). Results: Between 1999 and 2023, deaths attributed to CS and CIHD accounted for 78,903 cases among adults ≥ 45 years. Overall AAMR ranged from 35.88 per million in 1999 to 37.44 per million in 2023, with a downward trend from 1999 to 2012 followed by an upward trend thereafter. Males (51,080 deaths) exhibited rising mortality (AAPC: +0.50, p < 0.001), while females (27,823 deaths) showed a decline (AAPC: − 0.91, p < 0.0004). Non-Hispanic Black adults demonstrated the steepest increase (AAPC: +1.85, p < 0.001). The burden was greatest in adults ≥ 65 years, but the 45–64 group showed the fastest rise (AAPC: +1.67, p < 0.001). Conclusion: Mortality from cardiogenic shock and chronic ischemic heart disease among U.S. adults ≥ 45 years declined initially but reversed after 2012. Rising mortality in middle-aged adults, persistent racial disparities, and geographic inequities highlight urgent gaps in prevention and acute care.

BACKGROUND Artificial intelligence (AI) has significantly impacted health care, medicine, and radiology, offering personalized treatment plans, simplified workflows, and informed clinical decisions. ChatGPT (OpenAI), a conversational AI model, has revolutionized health care and medical education by simulating clinical scenarios and improving communication skills. However, inconsistent performance across medical licensing examinations and variability between countries and specialties highlight the need for further research on contextual factors influencing AI accuracy and exploring its potential to enhance technical proficiency and soft skills, making AI a reliable tool in patient care and medical education. OBJECTIVE This systematic review aims to evaluate and compare the accuracy and potential of ChatGPT-3.5 and 4.0 in medical licensing and in-training residency examinations across various countries and specialties. METHODS A systematic review and meta-analysis were conducted, adhering to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Data were collected from multiple reputable databases (Scopus, PubMed, JMIR Publications, Elsevier, BMJ, and Wiley Online Library), focusing on studies published from January 2023 to July 2024. Analysis specifically targeted research assessing ChatGPT’s efficacy in medical licensing exams, excluding studies not related to this focus or published in languages other than English. Ultimately, 53 studies were included, providing a robust dataset for comparing the accuracy rates of ChatGPT-3.5 and 4.0. RESULTS ChatGPT-4 outperformed ChatGPT-3.5 in medical licensing exams, achieving a pooled accuracy of 81.8%, compared to ChatGPT-3.5’s 60.8%. In in-training residency exams, ChatGPT-4 achieved an accuracy rate of 72.2%, compared to 57.7% for ChatGPT-3.5. The forest plot presented a risk ratio of 1.36 (95% CI 1.30-1.43), demonstrating that ChatGPT-4 was 36% more likely to provide correct answers than ChatGPT-3.5 across both medical licensing and residency exams. These results indicate that ChatGPT-4 significantly outperforms ChatGPT-3.5, but the performance advantage varies depending on the exam type. This highlights the importance of targeted improvements and further research to optimize ChatGPT-4’s performance in specific educational and clinical settings. CONCLUSIONS ChatGPT-4.0 and 3.5 show promising results in enhancing medical education and supporting clinical decision-making, but they cannot replace the comprehensive skill set required for effective medical practice. Future research should focus on improving AI’s capabilities in interpreting complex clinical data and enhancing its reliability as an educational resource.