DEVELOPMENT OF A HEART DISEASE RISK PREDICTION APPLICATION BASED ON THE RANDOM FOREST CLASSIFICATION MODEL USING THE STREAMLIT FRAMEWORK

Abstract

Coronary Heart Disease (CHD) is one of the leading causes of mortality worldwide, making early risk detection crucial. The advancement of machine learning technology offers significant potential in developing accurate and accessible prediction tools. This study aims to develop a web-based calculator application to predict the risk of CHD. The method used is a Random Forest classification model trained on the UCI Heart Disease dataset, which was chosen after being compared with several other algorithms. The model was then implemented into an interactive web application using the Streamlit framework. The research process included data preprocessing, model training, performance evaluation, and user interface development. The evaluation results showed that the Random Forest model achieved the best performance with an accuracy of 88.52%. The resulting application successfully provides a real-time risk percentage visualization via an intuitive gauge chart, making it easily understandable for lay users. This application is expected to serve as an effective preliminary screening tool to increase public awareness of CHD risk.