Heart Disease Prediction Using Hybrid Model Integrating Artificial Neural Network, Decision Tree, and Logistic Regression

Heart disease, a leading cause of global mortality, necessitates accurate prediction for timely intervention. This study proposes a hybrid model amalgamating LR, DT and ANN algorithms to enhance heart disease prediction. Using a Kaggle dataset comprising 1025 patient records with 14 features, including age, sex, chest pain, and cholesterol levels, the hybrid model achieved an impressive 88% precision. This outperforms individual models, with DT achieving 99% accuracy, LR with 80%, and ANN with 86%. Evaluation metrics demonstrate competitive performance, affirming the hybrid model as a robust tool for cardiovascular ailment prediction. The study underscores the efficacy of combining diverse algorithms, leveraging their strengths for more effective predictive modeling in cardiovascular health assessment.