Application of Deep Neural Networks for Disease Diagnosis Through Medical Data Sets

Abstract

In this chapter, a novel classification methodology for medical disease diagnosis is proposed. The proposed classification operator comprises a stacked autoencoder network cascaded with a softmax layer. The classifier is trained by applying a special training approach, where each layer of the proposed classifier is trained individually and sequentially. The performance of the proposed classifier is compared with a number of representative classification methods from the literature. The experimental results on medical data sets show that the proposed classifier performs better than or at least competitive with classifiers used in this chapter. It is also seen that the proposed classifier can efficiently be used for the diagnosis of medical diseases provided that it is trained with a suitable data set with a sufficient number of medical features obtained from a sufficient number of patients. © 2019, Springer Nature Switzerland AG.