Using a Fuzzy Neural Network in Clinical Decision Support for Patients with Advanced Heart Failure

Abstract

Determining the appropriate timing of mechanical circulatory support (MCS) or heart transplantation (HT) for patients with advanced heart failure is essential as there may be a mortality cost to delayed care. An automated decision-making system that can identify patients eligible for a HT/MCS would facilitate primary care physicians or general cardiologists referring those patients for consideration of advanced therapies. In this study, a novel fuzzy neural network was built by integrating fuzzy set theory, neural network, and genetic algorithm techniques. The overall architecture of the proposed fuzzy neural network was inspired by clinical practice guidelines. Clinical variables were encoded using fuzzy concepts and rules were calculated in a fully-connected layer with constraints in weights. From the experiments, the proposed fuzzy neural network achieved an average AUC of 0.838 and an F1 score of 0.462. The rules from the trained network were further analyzed. Our results show that the proposed fuzzy neural network can not only achieve good classification performance, but also provides transparency with respect to knowledge extraction and interpretation.