Heart Disease Prediction Using Machine Learning

Heart disease prediction using ML

Problem Statement: Heart disease is a leading cause of death globally, yet many cases can be prevented through early detection and timely intervention. However, traditional diagnostic methods often require expensive tests and specialist consultations, delaying critical action. We asked ourselves: Can we predict heart disease risk early using basic health data and machine learning?

Our Approach: We gathered real-world patient data with health indicators like age, blood pressure, cholesterol levels, and lifestyle habits. Instead of simply feeding this into a model, we refined the dataset:

We calculated BMI (Body Mass Index) to capture obesity risks.

We derived Pulse Pressure to better understand cardiovascular stress.

We removed outliers (extreme or incorrect values) to ensure cleaner learning.

We trained a Random Forest Classifier, which could not only predict heart disease risk but also identify the most important factors influencing it.

Results: Our model achieved strong accuracy and balanced sensitivity, ensuring fewer missed detections. We also built a user-friendly system where users can input their health data and instantly receive their risk prediction.

Impact: This project demonstrates how accessible, affordable data and machine learning can make early heart disease screening faster, smarter, and more available to all — contributing toward preventive healthcare efforts.