A Smart Healthcare Framework for Accurate Detection of Schizophrenia using Multi-Channel EEG

In recent years, advanced computing techniques have been investigated and employed for the computerized detection of brain disorders like schizophrenia. Schizophrenia is a neurological condition leading to hallucinations and disorganized speech in patients. Emerging deep-learning approaches can augm...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement 2023-07, p.1-1
Main Authors: Sharma, Geetanjali, Joshi, Amit M., Yadav, Deepshikha, Mohanty, Saraju P.
Format: Article
Language:English
Subjects:
A Wearable device
Brain modeling
CNN
Data models
EEG Measurement
Electrodes
Electroencephalography
Feature extraction
Medical services
Mental disorders
Schizophrenia Disorder
Smart Healthcare
TCN
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, advanced computing techniques have been investigated and employed for the computerized detection of brain disorders like schizophrenia. Schizophrenia is a neurological condition leading to hallucinations and disorganized speech in patients. Emerging deep-learning approaches can augment the computer-based diagnosis of this brain disorder by measuring and analyzing the Electroencephalography (EEG) signals. This paper proposes a novel concept of easy-to-wear cap, namely SczCap, integrating hardware and software for acquiring EEG signals from the scalp for accurate schizophrenia detection. In this research, A seven-layer model comprising of convolution neural network (CNN) and temporal convolution network (TCN) is designed and tested using raw EEG data (approach 1) and manually extracted features (approach 2). Three pre-trained models, VGG 16, AlexNet, and ResNet 50, along with the proposed model, have also been implemented in this work. A dataset consisting of EEG signals of 14 healthy and 14 schizophrenic patients is used in this work for the implementations. The performance of the proposed CNN-TCN model (approach 1 & 2) is also presented using non-subject-wise and subject-wise experiments. It is found that the proposed CNN-TCN model using approach 1 outperformed all other implemented models with 99.57% accuracy, 99.51% sensitivity, 99.64% specificity, and 99.63% precision in non-subject-wise experiments. The experimental results also exhibit the superiority of this model over other schizophrenia models in the state of art literature.
ISSN:0018-9456
DOI:10.1109/TIM.2023.3293544