Bipolar and Schizophrenia Disorders Diagnosis Using Artificial Neural Network

Abstract

Motivation: Bipolar disorder (BD) and schizophrenia (SZ) has a difficult diagnosis, so the main objective of this article is to propose the use of Artificial Neural Networks (ANNs) to classify (diagnose) groups of patients with BD or SZ from a control group using sociodemographic and biochemical variables. Methods: Artificial neural networks are used as classifying tool. The data from this study were obtained from the array collection from Stanley Neuropathology Consortium databank. Inflammatory markers and characteristics of the sampled population were the inputs variables. Results: Our findings suggest that an artificial neural network could be trained with more than 90% accuracy, aiming the classification and diagnosis of bipolar, schizophrenia and control healthy group. Conclusion: Trained ANNs could be used to improve diagnosis in Schizophrenia and Bipolar disorders. upon the activation function [1]. The ANN inputs are multiplied by different weights to generate a predictive response. So, these responses in ANN are widely used for several applications such as classification and pattern recognition [2].This tool is effective modeling non-linear relationships that may be a promising candidate for differentiation for several biological processes [3]. ANN are used in medical field to analysis of sleep disorders, cytopathology and histopathology

An Overview of Deep Learning Algorithms and Their Applications in Neuropsychiatry

“…Functional magnetic resonance imaging (fMRI) scans were also used for the same task by Jafri and Calhoun [ 16 ] achieving around 76% classification accuracy. In a different study [ 18 ], bipolar disorder (BP) and SZ were classified from normal controls using array collection data of Stanley Neuropathology Consortium databank. They excluded patients over 65 years old and achieved an accuracy of around 90%.…”

Untitled

“…The proposed model achieved an accuracy rate of 75.56%, which gave an improved performance of 62.22% over support-vector-machine (SVM) and the CNN method gave 66.67%. [44] developed a model for the diagnosis of Bipolar and Schizophrenia using the BPNN approach. This yielded an accuracy rate of 90% when tested with sociodemographic and biochemical data.…”

EEG based Major Depressive disorder and Bipolar disorder detection using Neural Networks: A review

“…It achieves 99.5% accuracy in the classification of unipolar vs healthy subjects and 85% in the discrimination of bipolar vs healthy subjects. In [174], bipolar and schizophrenia disorder diagnosis is achieved by using an artificial neural network. It achieves 90% classification accuracy among the bipolar, schizophrenia and healthy subjects.…”

“…Participants age varies from 20 to 50 years with no discrimination of gender. The classification of bipolar, schizophrenia and healthy subjects is performed in [174] in which 35 participants have schizophrenia, 35 are with bipolar illness and the remaining 35 are healthy subjects. From the available literature of bipolar disorder diagnosis, it is observed that there is no standard ratio of number of participants and it varies in different studies according to their resources and requirements of the experiment.…”

“…For all subjects, the inclusion criteria are history of epilepsy, head injury, psychiatric disorders and effect of illegal drugs as shown in Table 14. The Diagnostic and Statistical Manual of Mental Disorders (DSM-IV) and Back Depression Inventory (BDI-II) are the two major self-reported psychometric tests that are used in bipolar studies [115,116,175,174] for primary selection of the participants. Based on inclusion criteria and psychometric test, only those participants are considered for EEG study that have no psychotic disorder and their self-reported psychometric test score is above 14.…”