Optimizing Random Forest using Genetic Algorithm for Heart Disease Classification

Heart disease is a leading cause of death worldwide, and the need for effective predictive systems major source to treat affected patients. This study aimed determine how improve accuracy Random Forest in predicting classifying heart disease. The experiments performed this were designed select most optimal parameters using an RF optimization technique GA. Genetic Algorithm (GA) used optimize predict classify Optimization parameter genetic algorithm carried out by as input initial population Algorithm. undergoes series processes from Algorithm: Selection, Crossover Rate, Mutation Rate. chromosome that has survived evolution best or Forest. are stored hall fame module DEAP library classification process optimized max_depth, max_features, n_estimator, min_sample_leaf, min_sample_leaf. experimental uses default parameters, random search, grid search. Overall, obtained each experiment 82.5%, search 82%, 83%. RF+GA performance 85.83%; result GA generations, population, crossover, mutation. shows can be Forest.