Artificial Intelligence Approach for CAD Detection Using ECG Images and Patient Biometrics

Coronary Artery Disease (CAD) remains one of the leading causes of death throughout the world, primary diagnosis essential for reducing patient risk with improving treatment outcomes[1-3]. Conventional CAD diagnosis generally depends on electrocardiogram (ECG) interpretation, clinical examination, or imaging modalities, each having certain limitations when used independently[5]. Recent advances in Artificial Intelligence (AI) have demonstrated significant potential in improving diagnostic accuracy through automated analysis of medical data. This article recommends an AI framework that integrates ECG images and patient biometric information to improve CAD classification. The study employed CNN for extracting deep features from ECG images, while ML Algorithms such as Random Forest and Naïve Bayes analyze biometric attributes including age of a person, glucose level, gender, cholesterol level, blood pressure, and body mass index[8-11]. The outputs of both models are fused to classify patients into three categories: first one is Normal, second is Abnormal, and third one is Myocardial Infarction (MI)[]. The proposed framework enhances diagnostic reliability by combining complementary information from multiple modalities. Furthermore, Grad-CAM and SHAP are incorporated to improve model transparency and clinician trust[12]. The proposed approach demonstrates the potential of multimodal AI systems in supporting early CAD diagnosis and clinical decision-making.