International Journal of Advanced Research in Computer and Communication Engineering

Abstract: Heart disease remains one of the leading causes of global mortality, often due to late diagnosis and the absence of early risk assessment. Traditional diagnostic methods require clinical visits, medical equipment, and expert interpretation, which may not always be accessible. This paper presents a Machine Learning (ML)–based heart disease prediction system designed to evaluate an individual’s likelihood of developing heart disease using key medical parameters. The model uses attributes such as age, cholesterol, blood pressure, fasting blood sugar, maximum heart rate, chest pain type, and other clinical indicators to generate accurate predictions. Several ML algorithms—Logistic Regression, Random Forest, KNN, and Support Vector Machine—were trained and evaluated, with Random Forest achieving the highest accuracy. A web-based interface built using Streamlit allows users to enter their health metrics and receive prediction results instantly, along with personalized health recommendations. This system is scalable, user-friendly, and promotes early prediction, ultimately supporting preventive healthcare.

Keywords: Heart Disease Prediction, Machine Learning, Random Forest, Health Monitoring System, Medical Diagnosis, Streamlit.

Downloads: | DOI: 10.17148/IJARCCE.2025.1411107