Synergized Models for Enhanced Heart Disease Prediction

Abstract:- Abstract: Cardiovascular diseases, including coronary heart disease, re- main the main cause of loss of life globally, underscoring the urgent need for accurate prediction fashions. This paper provides a unique method for predicting cardiovascular disease using a hybrid learning version. This integration makes use of three variables (CatBoost, Random Forest, and Support Vector Machine (SVM)) as base newcomers and logistic regression as a meta-learner to improve the accuracy of predictions. All models are rapidly educated and evaluated the use of the Cleveland coronary heart disease data set, demonstrating the robustness of the ensemble for biomedical programs. The proposed model achieves 93% accuracy through metrics consisting of F1 rating, accuracy, remember, and ROC- AUC, even as also attaining high effects in terms of accuracy, don’t forget, and ROC-AUC. This look at demonstrates the ability of the system to gain knowledge of the gear to improve the accuracy of the diagnosis of heart disorders, leading to a higher analysis and diagnosis of affected people.