HEART DISEASE PREDICTION SYSTEM USING MACHINE LEARNING

Cardiovascular disease is one of the most prevalent causes of death worldwide, and early detection is crucial to prevent additional deaths and to increase survival rates. Conventional diagnosis by examining electrocardiograms (ECG), blood and clinical approach is time-consuming and expensive methods, which are prone to human error. A Heart Disease Prediction System leveraging various Machine Learning algorithms including Logistic Regression and Support Vector Machine predicts patient risk pretty accurately. The system is trained on the UCI Cleveland Heart Disease Dataset, comprising 10,000 patients with recorded ages, cholesterol, blood pressure, heart rate, and blood sugar values. Data preprocessing methods, including how to handle missing value, normalizing and feature selection, help improving the effectiveness of model. The system reaches the accuracy of 87.5% which is better than that of typical diagnosis.