A deep learning approach for diagnosing schizophrenic patients. Issue 6 (2nd November 2019)

• Record Type: Journal Article
• Authors: Srinivasagopalan, Srivathsan; Barry, Justin; Gurupur, Varadraj; Thankachan, Sharma
• Is Part Of: Journal of experimental & theoretical artificial intelligence. Volume 31:Issue 6(2019)
• Page Start: 803
• Page End: 816
• Publication Date: 2019-11-02
• Subjects: Schizophrenia -- fMRI -- deep learning -- random forest -- SVM; Artificial intelligence -- Periodicals; 006.3
• DOI: 10.1080/0952813X.2018.1563636
• Languages: English
• ISSNs: 0952-813X

Abstract

ABSTRACT: In this article, the investigators present a new method using a deep learning approach to diagnose schizophrenia. In the experiment presented, the investigators used a secondary dataset provided by The National Institute of Health. The experimentation involves analyzing this dataset for the existence of schizophrenia using traditional machine learning approaches such as logistic regression, support vector machine, and random forest. This is followed by the application of deep learning techniques using three hidden layers in the model. The results obtained indicate that the new deep learning technique formulated by the investigators provide a higher accuracy in diagnosing schizophrenia. These results suggest that deep learning may provide a paradigm shift in diagnosing schizophrenia.