Evaluating Deep Learning Models for Heart Disease Prediction in IoT-Enabled Healthcare Systems

Heart disease is one of the leading causes of death worldwide, creating a strong need for intelligent and real-time healthcare monitoring systems. This paper presents an IoT-enabled healthcare system for heart disease prediction using deep learning techniques. The proposed system integrates an Arduino microcontroller with heartbeat and temperature sensors to continuously monitor patient health conditions. A USB camera is used to capture heart-related medical images for disease analysis. The captured images are processed using a Convolutional Neural Network (CNN) model developed in Python to detect possible heart disease conditions with improved accuracy. The system also uses a NodeMCU module for IoT-based cloud uploading and remote monitoring of patient data. Serial communication between the Arduino and PC enables efficient data transfer and system coordination. By combining IoT technology with deep learning-based image analysis, the proposed system provides continuous health monitoring, accurate disease prediction, and early diagnosis support. This approach can improve patient safety, reduce manual healthcare efforts, and contribute to the development of smart healthcare applications.