Background: As cardiovascular medicine advances rapidly, the integration of artificial intelligence (AI) has garnered increasing attention. Although AI has been widely adopted in diagnostics, risk prediction, and decision support, its application in exercise-based cardiovascular rehabilitation is still limited, representing a new and promising research frontier. Objective: This scoping review aimed to identify and analyze original studies that have applied AI to exercise-based interventions designed to improve cardiovascular outcomes. Methods: Following the PRISMA-ScR guidelines, PubMed, Scopus, Web of Science, Embase, and IEEE Xplore were searched for articles published between January 2015 and August 2025. Eligible studies were peer-reviewed by human research employing AI (machine learning or deep learning) to deliver, adapt, or monitor an exercise intervention with cardiovascular outcomes. Reviews, diagnostic-only studies, protocols without data, and animal studies were excluded. Non-original works (reviews, protocols), animal studies, and purely diagnostic applications were excluded, ensuring a strict focus on AI applied within exercise interventions. Data extraction focused on study design, AI method, exercise modality, outcomes, and findings. Results: From 2183 records, nine studies met the inclusion criteria (two RCTs, feasibility pilots, and validation studies). Designs included feasibility pilots, randomized controlled trials (RCTs), and validation studies. AI applications encompassed adaptive step goals, reinforcement learning for engagement, coaching apps, machine learning–based exercise prescription, and continuous monitoring (e.g., VO₂ estimation). These AI methods, such as machine learning and reinforcement learning, were used to personalize exercise interventions and improve cardiovascular outcomes. Reported outcomes included blood pressure reduction, improved adherence, increased daily steps, improvement in VO₂max, continuous physiological monitoring, and enhanced diagnostic accuracy. Conclusions: Findings demonstrate that AI has the potential to significantly enhance cardiovascular rehabilitation. It can personalize exercise prescriptions, enhance adherence, and facilitate safe monitoring in home settings. However, the evidence base remains preliminary, with very few RCTs and substantial methodological heterogeneity. Future research must prioritize large-scale clinical trials, explainable AI, and equitable implementation strategies to ensure clinical translation.

The present study examined the autonomic cardiac modulation of veteran athletes by the use of traditional and modern methods of heart rate variability (HRV) analysis. Twenty-nine healthy male master soccer players were divided into two groups; group A consisted of fourteen participants (age 48.9±5.8 years), who were engaged to regular aerobic exercise and group B of fifteen sedentary ones (age 50.8±5.7 years). Sixteen age-matched non-athletes formed control group C. All participants underwent ambulatory 24-h continuous electrocardiogram monitoring for the calculation of time and frequency domain HRV indices. Additionally, Poincaré analysis SD1 and SD2 as well as multiresolution wavelet analysis σwav(16) and σwav(32) markers were calculated. Time-domain indices were significantly increased in group A compared to groups B and C. Group A presented greater values of SD1 (by 43%, p<0.01 and 34.4%, p<0.05 than groups B and C respectively) and SD2 (by 26% compared to B and by 34.1% to C, p<0.05). Index σwav(16) was higher in group A than in B and C by 35.6% (p<0.01) and 23.5% (p<0.05) respectively and so did σwav(32) by 22% (p<0.05) and 24% (p<0.05). Strong correlations were reported among indices. In conclusion, physically active master athletes attain better cardiac autonomic activity than sedentary counterparts, as proved by the application of Poincaré and multiresolution wavelet analyses, which can be useful research tools of cardiac autonomic modulation in sports cardiology.

The tilt test is used for the diagnosis of reflex syncope (RS) and is characterized by low sensitivity, especially in athletes. The objective of the study was the implementation of a novel diagnostic strategy for the tilt test without pharmacologic provocation in athletes based on haemodynamic criteria. A passive tilt test for 30 min was performed in 132 athletes (53 with a history of RS, 79 without RS). Measurement of haemodynamic, heart rate variability (HRV) and baroreflex sensitivity parameters was performed. Tilt testing yielded 34% sensitivity and 94% specificity. Among negative tilt test responders, the ones with RS had increased heart rate (HR) (89 ± 11 vs 81 ± 10 bpm, p < 0.001), stroke index (SI) (40.2 ± 7.1 vs 35.5 ± 9.7 ml/m², p = 0.013), cardiac index (CI) (3.5 ± 0.6 vs 2.8 ± 0.8 l/(min·m²), p < 0.001) and decreased total peripheral resistance index (TPRI) (2230 ± 362 vs 2965 ± 725 dyne·s m²/cm⁵, p < 0.001), low frequency component of HRV (76.2% (49.0–88.4) vs 79.7% (10.2–91.1), p = 0.045) during head-up tilt, compared with those without RS. Receiver-operating characteristic (ROC) curve analysis showed that among athletes with a negative tilt test the area under the curve (AUC) values were 0.727 (0.626–0.828) for HR (p < 0.001), 0.707 (0.611–0.804) for SI (p = 0.001), 0.847 (0.774–0.920) for CI (p < 0.001), 0.830 (0.754–0.905) for TPRI (p < 0.001). Further stratification of negative tilt test responders, characterizing their results as positive when TPRI 3 l/(min·m²), resulted in 85% sensitivity and 76% specificity. Our results provide supportive evidence that a novel stratification based on haemodynamic criteria can improve the sensitivity of the tilt test for the diagnosis of RS in athletes.

Background: As cardiovascular medicine advances rapidly, the integration of artificial intelligence (AI) has garnered increasing attention. Despite its growing application across various domains, the role of AI in exercise-based interventions remains relatively underexplored, offering a novel and promising direction for future research. Objective: This scoping review aimed to identify and analyse original studies that have applied AI to exercise-based interventions designed to improve cardiovascular outcomes. Methods: Following the PRISMA-ScR guidelines, PubMed, Scopus, Web of Science, Embase, and IEEE Xplore were searched for articles published between January 2015 and August 2025. Eligible studies were peer-reviewed human research employing AI (machine learning or deep learning) to deliver, adapt, or monitor an exercise intervention with cardiovascular outcomes. Reviews, diagnostic-only studies, protocols without data, and animal studies were excluded. Data extraction focused on study design, AI method, exercise modality, outcomes, and findings. Results: From 2,183 records, 11 studies met the inclusion criteria. Designs included feasibility pilots, randomized controlled trials (RCTs), and validation studies. AI applications encompassed adaptive step goals, reinforcement learning for engagement, coaching apps, machine learning–based exercise prescription, and continuous monitoring (e.g., VO₂ estimation). These AI methods, such as machine learning and reinforcement learning, were used to personalize exercise interventions and improve cardiovascular outcomes. Reported outcomes included blood pressure reduction, improved adherence, increased daily steps, improvement in VO₂max, continuous physiological monitoring, and enhanced diagnostic accuracy. Conclusions: Although evidence remains limited, findings demonstrate AI’s potential to personal exercise interventions, enable continuous monitoring, and enhance adherence in cardiovascular care. These findings suggest that AI could be a valuable tool in the development of more effective and personalized exercise-based interventions. However, large-scale RCTs, methodological standardization, and explainable AI approaches are urgently needed to ensure reliability, equity, and clinical translation. These future research directions are crucial for the successful integration of AI in cardiovascular care.

Electrocardiographic characteristics of children and adolescents present differences compared to adults. The aim of our work was to study electrocardiograms (ECGs) of football male players from childhood to late adolescence and examine if the ECG parameters are influenced by systematic exercise. One thousand fifty-four football players participated and formed four groups. Group A included 89 players aged 5–7 years, group B 353 players aged 8–11 years, group C consisted of 355 football players 12-15 yearsold and group D of 257 players with 16–18 years of age. All participants underwent preparticipation screening, including 12-lead surface ECG. Heart rate (HR), PR, RR, QRS, QT, QTc intervals, QT dispersion (QTdisp) and QRS axis were calculated. All ECGs were evaluated according to the current preparticipation cardiac screening guidelines, that refer to athletes aged 12–35 years and do not include pediatric players. Eleven percent of the participants presented an ECG finding. Group D obtained the lowest values of HR, QTc and the highest of PR, RR, QRS, QT intervals and QTdisp, whereas no differences in QRS axis were reported. Incomplete Right Bandle Branch Block (RBBB) was the most frequent ECG peculiarity, detected in 7.3% of the participants. Years of training were statistically significantly correlated to HR, PR, RR, QRS and QT intervals. In conclusion, guidelines for ECG interpretation of athletes in childhood, early and late adolescence are needed.