Heart-disease diagnosis decision support employing fuzzy systems with genetically optimized accuracy-interpretability trade-off

The main objective of this paper is the application of our multi-objective-evolutionary-optimization-based fuzzy classification technique to the decision support in diagnosing (classifying) the presence or absence of heart disease in the patients. Two publicly available medical data sets, i.e., Heart Disease (Cleveland) and South African Heart Disease data sets are considered. First, main components of our approach are outlined. For the purpose of comparison, three multi-objective evolutionary optimization algorithms are used in our experiments, i.e., the well-known Strength Pareto Evolutionary Algorithm 2 (SPEA2), Nondominated Sorting Genetic Algorithm II (NSGA-II), and our SPEA2's generalization (referred to as SPEA3) characterized by a higher spread and a better-balanced distribution of solutions. Our results for both considered medical data sets are compared with the results of 16 alternative methods, demonstrating the advantages (in terms of the systems' accuracy-interpretability trade-off optimization) of our approach.