Optimization for Cyclosporine Blood Concentration Prediction Based on Genetic Algorithm - BP Neural Network

Abstract

The paper proposes the new model of the genetic algorithm and BP neural networks to predict the blood concentration of Cyclosporine. The BP model was optimized by genetic algorithm to overcome the slower convergence speed, and the best result was found in the particular condition with the strong search function of genetic algorithm. The prediction precision of average blood concentration of Cyclosporine by using the GABP neural network model was 97.5%. It was found that the GABP model was superior to BP neural network in the prediction of Cyclosporine blood concentration. We conclude the GABP model can be used in the prediction of the Cyclosporine blood concentration and help clinicians provide better care for patients taking CsA.