IMPROVED LIGHTGBM MODEL PERFORMANCE ANALYSIS AND COMPARISON FOR CORONARY HEART DISEASE PREDICTION

Abstract

Coronary heart disease (CHD) is a serious cardiovascular sickness with no therapy. Compelling patient treatment requires exact and early coronary course artery disease . Early distinguishing proof empowers early medicines and better persistent results. The "HY_OptGBM" model predicts CHD utilizing a superior LightGBM classifier. Gradient boosting framework LightGBM is proficient and exact in prescient demonstrating. Enhancements to the misfortune capability and hyperparameters streamline the LightGBM classifier. This streamlining approach further develops model preparation exactness and effectiveness. Model execution is surveyed utilizing Framingham Heart Institute coronary heart disease data. In light of this information, the model precisely predicts CHD, permitting early distinguishing proof and maybe lower treatment costs. Furthermore, presents a Voting Classifier (RF + AdaBoost) with
close to 100% accuracy to analyze Coronary Heart Disease. This Random Forest-AdaBoost ensemble model recognizes CHD designs well. An easy to use Flask framework with SQLite combination works on user testing enlistment and signin to really take a look at convenience. The CHD discovery partners might utilize ML moves toward all the more effectively with this worked on interface.