Abstract
INTRODUCTION: Artificial intelligence (AI) is rapidly transforming cardiovascular diagnostics by enhancing early disease detection, risk stratification, and clinical decision-making. Recent studies have shown the effectiveness of AI in analyzing electrocardiograms (ECGs) and cardiac imaging, predicting adverse cardiovascular outcomes, and enabling personalized care. AI models have also demonstrated potential in community-based and population-specific applications, signaling a shift toward data-driven, precision cardiovascular medicine. STUDY OBJECTIVE: To systematically evaluate the clinical applications and diagnostic performance of AI in the detection and risk assessment of cardiovascular diseases. METHODS: A systematic search was conducted in PubMed, Google Scholar, and ScienceDirect for English-language articles published between January 2020 and June 2025. Eligible studies included randomized controlled trials and observational designs with free full-text availability. QUADAS-2 tool for diagnostic accuracy studies and the PROBAST for prognostic or risk-prediction models, were used for quality assessment. Of 30 eligible articles, 14 high-quality studies were included. RESULTS: Across the included studies, AI-based diagnostic tools demonstrated consistently high performance for cardiovascular disease detection. Reported area under the curve (AUC) values ranged from 0.804 to 0.991, with most ≥ 0.88, indicating robust discriminative accuracy across diverse modalities including ECG analysis, cardiac imaging, and predictive risk modeling. Although formal pooling was not conducted due to methodological heterogeneity, the descriptive synthesis highlighted strong and consistent performance in applications such as heart failure, coronary artery disease, and arrhythmia detection. Variability in study design and reporting limited direct comparison, but overall trends support the potential of AI systems to enhance diagnostic precision across cardiovascular contexts. CONCLUSION: AI-driven diagnostic tools demonstrate consistently high accuracy across cardiovascular applications, supporting their potential to complement clinical decision-making. However, variability in study design and limited external validation highlight the need for standardized evaluation and transparent reporting before widespread clinical integration.