Predicting the Heart Disease of Machine Learning Techniques: A Comparative Study on LightGBM ,XGBoost and AdaBoost Model

Heart disease is one of the leading causes of death globally. With advancements intechnology and data availability, machine learning has emerged as an effective tool for predicting diseaseslike heart disease. This project focuses on the comparative study of three popular boosting algorithms:XGBoost, LightGBM, and AdaBoost, in the context of predicting heart disease. The project aims toleverage these algorithms to develop predictive models that can accurately diagnose heart disease based onvarious clinical features. Using the Cardiovascular Heart Disease dataset, we implement, train, andevaluate each algorithm. The performance is assessed using key metrics such as accuracy, precision,recall, F1-score, and AUC. Our findings indicate that XGBoost delivers superior performance, followed byLightGBM and then AdaBoost. The study concludes by highlighting the importance of model selection inhealthcare applications and suggests future work involving hybrid models and deep learning approaches.