Artificial Intelligence in the Early Detection of Heart Disease

Early identification of heart disease is essential, as it continues to be a major cause of global mortality. Recent progress in Artificial Intelligence (AI) has enabled faster and more reliable analysis of ECG signals, offering clinicians meaningful support in early diagnosis. Machine learning models, such as Random Forest and Support Vector Machines, have shown strong capability in classifying arrhythmias and coronary disease [4,12], while deeplearning approaches—particularly Convolutional Neural Networks—automatically extract complex cardiac features without manual input [5,6,9]. Explainable AI methods like SHAP further strengthen clinical confidence by clearly illustrating the factors behind each prediction [1], [10]. With the growing integration of multimodal data, AI systems are becoming more robust and clinically relevant [2,14]. Although still developing, these technologies are steadily moving toward practical, real-world deployment and have the potential to significantly enhance patient outcomes.