Combining A Hybrid Genetic Algorithm with A Fuzzy Logic Classifier Enhances Heart Disease Diagnosis

Abstract

Because cardio illness has a significant impact on death rates worldwide, diagnosing heart disease is an essential field of healthcare. The study proposes a unique method, the HDD-GA-FL model, to enhance Heart Disease Diagnosis (HDD) that combines a hybrid genetic algorithm (GA) along with a fuzzy logic classifier (FL). The suggested hybrid system aims to overcome the difficulties brought on by the intricacy and ambiguity involved in diagnosing cardiac disease. Fuzzy logic classifiers are used to analyze ambiguous medical data, while genetic algorithms are used for choosing features and optimization. Combining these two methods provides a strong foundation for precise and effective diagnosis. Experiments on an extensive dataset with different clinical factors and cases of heart disease are conducted to assess the efficacy of the hybrid strategy. Compared to conventional diagnostic techniques, there have been significant improvements in diagnostic reliability and accuracy. When navigating the complex feature space involved in diagnosing heart illness, the combination of GA and FLC performs better than alone. It can capture minute associations and trends in the data. The suggested hybrid system has great potential for real-world application in clinical settings, providing doctors with an invaluable instrument for accurately diagnosing and detecting cardiac problems early on. This method advances the latest developments in cardiac healthcare by utilizing the complementary strengths of fuzzy logic classifiers and genetic algorithms, eventually improving patient outcomes and lowering healthcare costs.