Application of Neural Network Algorithm for Schizophrenia Diagnosis

Authors

  • J. E. Zaccheus Department of Biomedical Engineering, Afe Babalola University, Ado-Ekiti, Ekiti State, NIGERIA
  • Obinna P. Fidelis DEPT OF BIOMEDICAL TECHNOLOGY, FEDERAL UNIVERSITY OF TECHNOLOGY, AKURE, ONDO STATE, NIGERIA
  • E.O. Nwoye Department of Biomedical Engineering, University of Lagos, Lagos State, Nigeria

Keywords:

artificial intelligence;, medical records, mental health, python, schizophrenia

Abstract

Schizophrenia is a prolonged mental condition that affects functional impairment in work, interpersonal relationships, and self-care. This research is aimed at developing a neural network model to diagnose schizophrenia using text data acquired from patients’ records. The model was developed from datasets obtained from Neuropsychiatric Hospital in Yaba and the Lagos University Teaching Hospital, both in Lagos, Nigeria, using Python programming language and is provided with significant features from data sets to learn patterns within the training data and perform classification on the test data. The results show that the model produced a test accuracy of 85%, specificity of 95% and a precision of 93%. These results indicate that the model can be used for effective computer aided diagnosis of schizophrenia.

Downloads

Published

2021-11-01

Issue

Section

Agricultural, Bioresources, Biomedical, Food, Environmental & Water Resources Engineering