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: Atrial fibrillation (AF) and congestive heart failure (CHF) remain major contributors to cardiovascular mortality in the United States. When accompanied by underlying ischemic heart disease (IHD), mortality risk is amplified. Although IHD mortality declined in the early 2000s, recent data suggest a resurgence. Methods: This population-based study used the CDC Wide-Ranging Online Data for Epidemiologic Research (CDC WONDER) database from 1999 to 2023. Deaths were identified using ICD-10 codes I48 (AF) and I50.0 (CHF) as multiple causes of death and I20–I25 (IHD) as the underlying cause. Adults aged ≥ 65 years were included. Crude mortality rates (CMRs) and age-adjusted mortality rates (AAMRs) were calculated. Temporal trends were analyzed using Joinpoint regression to estimate annual percent change (APC) and average annual percent change (AAPC). Future mortality trends were projected using autoregressive integrated moving average (ARIMA) model. Results: From 1999 to 2023, AF, CHF, and IHD accounted for 219,188 deaths among adults ≥ 65 years. The overall AAMR increased from 193.8 per million in 1999 to 220.1 per million in 2023, with a decline from 1999 to 2010 followed by a sustained rise. Males (108,732 deaths) showed the steepest increase (AAPC + 1.40%, p < 0.001), whereas females (110,456 deaths) experienced a modest decline (AAPC − 0.55%, p < 0.001). Non-Hispanic Black adults had the largest racial increase (AAPC + 1.21%, p < 0.001). Non-metropolitan areas showed the greatest geographic rise (AAPC + 1.67%, p < 0.001). Conclusion: Mortality involving AF and CHF with underlying IHD among U.S. adults ≥ 65 years declined only temporarily before reversing after 2010. Persistent racial and geographic disparities underscore gaps in prevention and acute cardiovascular care. Clinical Trial Registration: Not applicable.

Context: Obesity is a known risk factor for various cancers. Despite the growing prevalence of obesity in the United States, national-level trends in obesity-associated cancer mortality remain insufficiently quantified. Objective: To evaluate national trends in cancer mortality where obesity was listed as a contributing or underlying cause of death from 1999 to 2020. Methods: A retrospective cross-sectional study was conducted using publicly available mortality data from the CDC WONDER database. Adults aged 25 years and older were included if both obesity (ICD-10: E66) and cancer (ICD-10: C00–D9) were listed on their death certificates. Age-adjusted mortality rates (AAMRs) were calculated per 1 000 000 population, and Joinpoint regression was used to assess temporal trends through annual percent change (APC) and average annual percent change (AAPC). Results: A total of 33 572 obesity and cancer-related deaths were recorded. The overall AAMR rose from 3.73 in 1999 to 13.52 in 2020, with an AAPC of 5.92%. The highest mortality rates were observed in older adults, women, rural populations, and racial minorities, particularly Black and American Indian individuals. Breast, prostate, and lung cancers accounted for the greatest burden. A marked rise occurred between 2018 and 2020 across all subgroups. Conclusion: Obesity and cancer-related mortality in the United States has more than tripled over 2 decades, with notable disparities across demographic groups. These findings highlight the need for targeted public health efforts that integrate obesity prevention into cancer control strategies.

Anticoagulation in patients with atrial fibrillation (AF) and liver cirrhosis is challenging due to competing risks of thrombosis and bleeding. While direct oral anticoagulants (DOACs) have emerged as alternatives to warfarin, their comparative safety and effectiveness in cirrhosis remain incompletely defined. We conducted a retrospective cohort study using the TriNetX Global Collaborative Network. Adult patients (≥ 18 years) with AF and cirrhosis receiving DOACs or warfarin were identified. Propensity score matching (1:1) was performed to balance baseline characteristics. The primary outcomes were hepatic decompensation and ischemic stroke within 1 year. Secondary outcomes included all-cause mortality, major bleeding, intracranial hemorrhage, gastrointestinal bleeding, and all-cause hospitalization. Survival (Kaplan–Meier) analysis and hazard ratios were estimated. After propensity score matching, 2,522 matched pairs (5,044 patients) were included. Over 1-year follow-up, hepatic decompensation occurred in 8.8% of DOAC patients and 11.1% of warfarin patients, with a significantly lower risk observed in the DOAC group (HR 0.79, 95% CI 0.67–0.95; p = 0.010). Ischemic stroke occurred in 2.9% of DOAC patients and 2.4% of warfarin patients, with no statistically significant difference between groups (HR 1.22, 95% CI 0.85–1.75; p = 0.289). All-cause mortality was lower in the DOAC group (17.7% vs. 20.3%; HR 0.87, 95% CI 0.77–0.99; p = 0.035). No significant differences were observed in major bleeding (HR 0.84, 95% CI 0.70–1.02), intracranial hemorrhage (HR 0.98, 95% CI 0.59–1.62), gastrointestinal bleeding (HR 0.97, 95% CI 0.77–1.23), or all-cause hospitalization (HR 1.04, 95% CI 0.97–1.12). In patients with atrial fibrillation and cirrhosis, DOAC use was associated with lower risks of hepatic decompensation and all-cause mortality compared with warfarin, while no significant difference was observed in ischemic stroke or other safety outcomes. Given the observational design and modest absolute differences, these findings should be interpreted as associative and hypothesis-generating rather than causal or definitive. Graphical abstract