An Integrated Machine Learning Model for Heart Disease Classification and Categorization

Abstract

Progressions in the coordination among the machine learning algorithms, helped to achieve high accuracy and reliability in decision-making systems. Due to the impact and importance of heart diseases in real life, designing the efficient heart disease prediction model become a pivotal aspect today. Former research scholars applied the popular supervised machine learning models like Decision Trees, Naïve Bayes, ANN's, and FNN's to implement the heart disease prediction systems. As the heart disease prediction process is a multi-layered operation, each layer is expecting the optimal machine learning algorithm and the coordination among the algorithms of different layers to minimize the errors in prediction results. In this study, we proposed a new fuzzy neural-genetic algorithm to design an efficient and accurate heart disease prediction system. In our prediction system, we integrated the genetic algorithm, neural networks, and fuzzy logic technologies for training, classification, and categorization processes respectively. Experimental evaluations of Cleveland's heart disease dataset proved that the proposed fuzzy neural-genetic algorithm-based prediction system achieved high accuracy and low error rate when compared with the other machine learning models.