Genetic-algorithm-based artificial neural network modeling for platelet transfusion requirements on acute myeloblastic leukemia patients

In this paper, an artificial neural network (ANN) model with the genetic algorithm (GA) is used to predict the platelet transfusion requirements for the acute myeloblastic leukemia (AML) patients. The hybrid Taguchi-genetic algorithm (HTGA) is applied in this ANN to find the optimal parameters (i.e., weights of links and biases govern the input–output relationship of an ANN) by directly maximizing the training accuracy performance criterion. Experimental results show that the HTGA-based ANN model outperforms the ANN model with backpropagation algorithm given in the Matlab toolbox in terms of prediction accuracy. Therefore, this study demonstrated the feasibility of applying the HTGA-based ANN as the mechanism of the decision support systems for the platelet transfusion requirements of the AML patients based on clinical databases.