Ensemble Machine Learning Framework for Heart Disease Risk Prediction

This project presents an Ensemble Machine Learning Framework for Heart Disease Risk Prediction, aimed at improving early detection and classification of heart conditions. The system is built using a Raspberry Pi integrated with components such as a heartbeat sensor, USB web camera, LCD display, buzzer, memory card, power supply, and adapter. The heartbeat sensor is used to continuously monitor the heart rate and determine whether the condition is normal or abnormal. In addition, image processing techniques are applied using YOLOv8 to train and classify heart-related conditions based on visual data. The collected sensor data and image inputs are processed using Python-based ensemble machine learning models to improve prediction accuracy. Based on the analysis, the system classifies the risk level of heart disease and provides alerts through a buzzer while displaying results on the LCD. This approach enhances prediction reliability by combining multiple machine learning techniques and real-time monitoring. The system supports early diagnosis, improves healthcare decision-making, and can be effectively used in smart healthcare and remote patient monitoring applications.