T-S Fuzzy Neural Networks with RCDPSO_DM Optimization for Variances Handling of Clinical Pathways

Abstract

Clinical pathways’ variances present complex, fuzzy, uncertain and high-risk characteristics. They could cause complicating diseases or even endanger patients’ life if not handled effectively. Takagi-Sugeno (T-S) fuzzy neural networks (FNNs) can be used for variances handling of clinical pathways (CPs). However, there are many drawbacks, such as slow training rate, easy to trap into local minimum point, and bad ability on global search. In order to improve the accuracy and efficiency of variances handling by T-S FNNs, a new variances handling method for CPs is proposed in this study, which is based on random cooperative decomposing particle swarm optimization with double mutation mechanism (RCDPSO_DM) for T-S FNNs. Moreover, the proposed hybrid learning algorithm combining the RCDPSO_DM algorithm and the kalman filtering algorithm is applied to optimize the antecedent and consequent parameters of constructed T-S FNNs. Finally, a case study on liver poisoning of osteosarcoma preoperative chemotherapy is used to validate the proposed method. The result demonstrates that T-S FNNs based on the RCDPSO_DM achieves superior performance in efficiency, precision, and generalization ability to standard T-S FNNs, standard Mamdani FNNs and T-S FNNs based on other algorithms (CPSO and PSO) for variances handling of CPs. Therefore, it makes variances handling of CPs more effective.