Machine Learning-Based Heart Disease Risk Prediction Using Clinical, Lifestyle, Genetic, and Biometric Features

Cardiovascular disease remains a major contributor to global mortality, creating a strong need for accurate and timely risk prediction methods.This study presents a machine learning-based framework for predicting heart disease risk using a healthcare dataset containing 2,000 patient records with clinical, lifestyle, genetic, and biometric features.Data preprocessing techniques were applied to prepare the dataset for model training and evaluation.Five machine learning algorithms-Decision Tree, Random Forest, Logistic Regression, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM)-were developed and compared.Model performance was evaluated using Accuracy, Precision, Recall, and F1-Score metrics.Experimental findings revealed that Logistic Regression achieved the best performance, attaining a classification accuracy of 97.6%, outperforming Random Forest (95.0%),Decision Tree (93.4%),SVM (85.8%), and KNN (82.4%).In addition, a 5-fold cross-validation procedure produced a mean accuracy of 98.44%, demonstrating the stability and reliability of the proposed approach.These findings indicate that machine-learning techniques can effectively support early heart disease risk assessment and assist healthcare professionals in clinical decision-making.