Published in: Journal of Computer Science and Engineering in Innovations and Research (ISSN No: 3049-1762 online)
Publication Date: June 15, 2025
Heart disease is one of the most critical global health challenges, responsible for millions of deaths annually. Early identification of individuals at risk plays a vital role in reducing mortality through preventive measures and timely medical intervention. This project presents a supervised machine learning–based Heart Disease Risk Prediction System using Logistic Regression. The model is trained on structured clinical data containing thirteen commonly used medical parameters. The trained model is integrated into a Flask-based web application that provides real-time predictions along with probability scores. The system emphasizes interpretability, reproducibility, and accessibility, making it suitable as an educational screening tool rather than a medical diagnostic system.
Heart Disease Prediction, Machine Learning, Logistic Regression, Flask Web Application, Medical Data Analytics, Risk Assessment
Cardiovascular diseases (CVDs) remain the leading cause of death worldwide, accounting for nearly one-third of global mortality. Lifestyle changes, aging populations, and increasing stress levels have contributed to the rising prevalence of heart-related illnesses. Early detection of heart disease risk can significantly reduce severe outcomes by enabling preventive care and lifestyle modification.
Traditional diagnostic methods rely on extensive clinical tests and expert interpretation, which may not always be accessible or affordable. Machine learning provides an efficient alternative by learning patterns from historical medical data and offering data-driven predictions. This project focuses on developing a reliable and interpretable machine learning model and deploying it through a web-based platform to improve public accessibility and awareness.