The frontiers of intelligent health services: cardiovascular disease prediction using novel machine learning methods and metaheuristic algorithm.

Abstract

Cardiovascular disease (CVD) significantly impacts global mortality and aging. Effective risk assessment relies on models like Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), which consider genetic, lifestyle, medical, and demographic factors. These models improve significantly when combined with optimization techniques like the Golf Optimization Algorithm (GOA) and Leader Harris Hawk's Optimization (LHHO), leading to more accurate predictions and better early intervention. According to empirical investigation, the LDGO model, obtained by integrating the LDA model with the GOA optimizer, is the most productive model, with accuracy values of 0.948 in the training phase and 0.946 in the test phase. According to empirical investigation, the LDGO model, obtained by integrating the LDA model with the GOA optimizer, is the most productive model, with accuracy values of 0.948 in the training phase and 0.946 in the test phase.