Background: Despite ongoing advancements in healthcare, acute coronary syndromes (ACS) remain a leading cause of morbidity and mortality. The 2023 European Society of Cardiology (ESC) guidelines have introduced significant improvements in ACS management. Concurrently, artificial intelligence (AI), particularly models like ChatGPT, is showing promise in supporting clinical decision-making and education. Methods: This study evaluates the performance of ChatGPT-v4 in adhering to ESC guidelines for ACS management over a 30-day interval. Based on ESC guidelines, a dataset of 100 questions was used to assess ChatGPT’s accuracy and consistency. The questions were divided into binary (true/false) and multiple-choice formats. The AI’s responses were initially evaluated and then re-evaluated after 30 days, using accuracy and consistency as primary metrics. Results: ChatGPT’s accuracy in answering ACS-related binary and multiple-choice questions was evaluated at baseline and after 30 days. For binary questions, accuracy was 84% initially and 86% after 30 days, with no significant change (p = 0.564). Cohen’s Kappa was 0.94, indicating excellent agreement. Multiple-choice question accuracy was 80% initially, improving to 84% after 30 days, also without significant change (p = 0.527). Cohen’s Kappa was 0.93, reflecting similarly high consistency. These results suggest stable AI performance with minor fluctuations. Conclusions: Despite variations in performance on binary and multiple-choice questions, ChatGPT shows significant promise as a clinical support tool in ACS management. However, it is crucial to consider limitations such as fluctuations and hallucinations, which could lead to severe issues in clinical applications.

Background: An exaggerated hypertensive response (EHR) during exercise is linked to increased cardiovascular risk and mortality. This study aims to assess structural and functional cardiac changes, along with subclinical myocardial damage, using transthoracic echocardiography (ECHO) and 2D longitudinal strain analysis in patients showing a hypertensive response to treadmill exercise. Methods: Patients without known chronic diseases, presenting to the Cardiology Department at Health Sciences University Gülhane Training and Research Hospital, were divided into 2 groups based on their blood pressure response during treadmill exercise: exaggerated hypertensive response (EHR, n = 42) and normal response (control, n = 44). Left ventricular longitudinal strain was assessed using transthoracic echocardiography, and global longitudinal strain (GLS) was calculated as the average from all segments. Data analysis was performed using SPSS 26. Results: No significant differences were found between the groups regarding baseline demographic and laboratory parameters (P > .05 for all). However, the EHR group exhibited significantly higher interventricular septum thickness, mitral A velocity, and mitral annulus velocity (a'), while mitral annulus velocity (e') was significantly lower (P < .05 for all). Additionally, left ventricular (LV) mass index, left atrial volume index, mitral E/e' ratio, deceleration time, and relative wall thickness (RWT) were higher in the EHR group, while the mitral E/A ratio was lower (P < .05 for all). The GLS was also significantly lower in the EHR group (P < .05). Conclusion: Left ventricular geometry parameters, such as LV mass index and RWT, and GLS findings indicating subclinical cardiac damage, were significantly altered in the EHR group, suggesting a higher risk of LV hypertrophy and myocardial dysfunction.

Background: Artificial intelligence (AI) tools, like ChatGPT, are gaining attention for their potential in supporting clinical decisions. This study evaluates the performance of ChatGPT-4o in acute cardiological cases compared to cardiologists and emergency physicians. Methods: Twenty acute cardiological scenarios were used to compare the responses of ChatGPT-4o, cardiologists, and emergency physicians in terms of accuracy, completeness, and response time. Statistical analyses included the Kruskal–Wallis H test and post hoc comparisons using the Mann–Whitney U test with Bonferroni correction. Results: ChatGPT-4o and cardiologists both achieved 100% correct response rates, while emergency physicians showed lower accuracy. ChatGPT-4o provided the fastest responses and obtained the highest accuracy and completeness scores. Statistically significant differences were found between ChatGPT-4o and emergency physicians (p < 0.001), and between cardiologists and emergency physicians (p < 0.001). A Cohen’s kappa value of 0.92 indicated a high level of inter-rater agreement. Conclusions: ChatGPT-4o outperformed human clinicians in accuracy, completeness, and response time, highlighting its potential as a clinical decision support tool. However, human oversight remains essential to ensure safe AI integration in healthcare settings.

This study aimed to investigate the relationship between exaggerated hypertensive response to exercise (EHRE), mobile phone screen time, and daily physical activity levels, with a focus on potential lifestyle-related factors that contribute to cardiovascular risk. This observational case-control study enrolled 85 participants, who were categorized into an Exaggerated Hypertensive Response to Exercise (EHRE) group (n = 33) and a normotensive control group (n = 52). Participants underwent a standardized treadmill exercise test to identify EHRE. Objective data on daily mobile phone screen time and step counts were collected directly from the smartphones' native tracking applications. Compared to controls, participants with EHRE exhibited significantly higher daily mobile phone screen time (6.1 ± 1.2 hours/day vs. 4.7 ± 0.9 hours/day; p < 0.001), greater weekly screen time in dim-light conditions (e.g., in bed at night) (14.5 ± 3.4 hours/week vs. 7.0 ± 2.1 hours/week; p < 0.001), a longer duration of mobile phone usage (19.7 ± 1.9 years vs. 17.7 ± 1.5 years; p = 0.002), and notably lower daily step counts (4120 ± 950 steps/day vs. 6830 ± 1120 steps/day; p < 0.001). Increased mobile phone screen time and reduced physical activity levels were significantly associated with EHRE, suggesting that these factors are relevant as modifiable behavioral risk factors. These findings support the integration of digital behavioral metrics into preventive cardiovascular risk management strategies.

Exercise-induced premature ventricular complexes (EI-PVCs) are key indicators of subclinical cardiac dysfunction and elevated cardiovascular risk. However, their clinical significance and prognostic value remain unclear, particularly in asymptomatic individuals without structural heart disease. This study uses advanced echocardiographic techniques to investigate the relationship between EI-PVCs and subclinical myocardial dysfunction. An observational case-control study was conducted with 141 participants (82 controls and 59 cases). Two-dimensional speckle tracking echocardiography (2D-STE) was utilized to assess myocardial function, including global longitudinal strain (GLS). Participants with exerciseinduced PVCs exhibited significantly greater left ventricular mass index (80.1 ± 15.7 vs. 74.3 ± 12.7 g/m²; p = 0.035), markedly reduced global longitudinal strain (–19.6 ± 2.0% vs. − 22.2 ± 1.4%; p < 0.001), and elevated myocardial performance index (0.42 ± 0.07 vs. 0.38 ± 0.06; p = 0.002) compared to controls, despite similar conventional systolic parameters. This study highlights EI-PVCs as early markers of subclinical myocardial dysfunction, warranting detailed echocardiographic evaluation in affected individuals. The findings. underscore the need for further research into the burden, morphology, and patterns of EI-PVCs to refine cardiovascular risk stratification and management strategies.