Heart disease is one of the leading causes of death in the world, so early diagnosis is very important. This research develops a web-based heart prediction system using Random Forest algorithm and Streamlit framework. The dataset used consists of 299 samples with 13 attributes, taken from Kaggle. The research stages include data collection, pre-processing, SMOTE technique to handle data imbalance, modeling, evaluation, and system implementation. The resulting model showed 86.58% accuracy on the test data, demonstrating effective working practices in classifying heart disease risk. The system is designed with an interactive interface that makes it easy for users to analyze data and derive predictions. This research provides a technological solution that can assist medical personnel in making an initial diagnosis quickly and accurately, thus accelerating clinical decision-making.
Copyrights © 2025