Smart Cardiac Monitoring: IoT and Vision Transformer for Early Heart Disease Detection

IoT advancements in healthcare enable continuous remote monitoring for early detection of fatal diseases, addressing the need for timely intervention in chronic conditions such as hypertension, kidney and heart disease. We propose an IoT-powered framework that streams real-time ECG from wearable sensors to the cloud and integrates patients’ EHRs, including ECG images; a transformer-based deep learning model analyses these multimodal inputs to predict cardiovascular disease in real time and triggers proactive notifications to clinicians and patients. The approach improves accuracy and precision over existing methods, achieving 99.8% accuracy for heart disease prediction while supporting timely, scalable, and continuous monitoring. Applications include continuous remote cardiac monitoring for high-risk patients, early warning alerts to inform rapid clinical decisions, integration with digital health records for precision cardiology, and population-scale monitoring in telemedicine and home care.