Type 2 diabetes data classification using stacked autoencoders in deep neural networks

Abstract

ObjectiveThis paper aims to classify the Pima Indians diabetes dataset with better accuracy and other evaluation metrics. The Deep Neural Network (DNN) framework will help to diagnose the patient in an effective way with higher accuracy. MethodIn this approach, we proposed a Deep Neural Network framework for diabetes data classification using stacked autoencoders. Features are extracted from the dataset using stacked autoencoders and the dataset is classified using softmax layer. Also, fine tuning of the network is done using backpropagation in supervised fashion with the training dataset. However, the medical diagnosis involves the risk factors of wrong prediction; hence we have used evaluation metrics such as precision, recall, specificity and F1 - score for the evaluation of our model and have achieved better results. ResultsThe proposed framework is experimented on Pima Indians Diabetes data which has 768 patient records with 8 attributes for each record. We achieved classification accuracy of 86.26%. ConclusionA stacked autoencoders based Deep Learning framework for classification of Type 2 Diabetes data is proposed in this paper. This approach is experimented on UCI machine learning data and proved the outperformance over various existing classification methods.