Heart disease diagnosis: an efficient decision support system based on fuzzy logic and genetic algorithm

Abstract

Computerised clinical guidelines can provide benefits to health outcomes and costs; however, their effective implementation presents significant problems. One effective solution to achieve the optimal trade-off between data ambiguity and good decision-making would be to integrate data mining and artificial intelligence techniques. We devise an efficient clinical decision support system (CDSS) for heart disease diagnosis using data mining and AI techniques. The proposed algorithm makes use of the association pattern mining algorithm, apriori and genetic algorithm (GA) to formalise the treatment of vagueness in decision support architecture. The GA produces a set of high impact parameters and their respective optimal values essential for heart disease diagnosis. The fuzzy logic is employed as a decision-making tool in the proposed CDSS. Based on the fuzzy membership function, the system effectively diagnoses the clinical cases of heart disease. Experimental results demonstrate the effectiveness of the proposed CDSS in heart disease diagnosis.