An ANFIS-based model for predicting adequacy of vancomycin regimen using improved genetic algorithm

In this paper, a model based on the adaptive network-based fuzzy inference system (ANFIS) with the improved genetic algorithm is used to predict the adequacy of vancomycin regimen. The improved genetic algorithm, i.e., hybrid Taguchi-genetic algorithm (HTGA), is applied in the ANFIS to simultaneously find the optimal premise and consequent parameters and a total output layer parameter by directly maximizing the training accuracy performance criterion. Experimental results show that the HTGA-based ANFIS model outperforms the logistic regression model in terms of prediction accuracy. Therefore, this study demonstrates the feasibility of applying the HTGA-based ANFIS as the mechanism of the decision support systems for the adequacy of vancomycin regimen for the patients based on clinical databases.