Volume 8, Issue 3 (Shenakht Journal of Psychology and Psychiatry 2021)
Shenakht Journal of Psychology and Psychiatry 2021, 8(3): 101-115 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Goshvarpour A, Goshvarpour A. Comparing the discrepancy between mutual information of electroencephalogram electrodes in schizophrenia: a classification problem. Shenakht Journal of Psychology and Psychiatry 2021; 8 (3) :101-115
URL: http://shenakht.muk.ac.ir/article-1-1137-en.html
URL: http://shenakht.muk.ac.ir/article-1-1137-en.html
1- Ph.D, Department of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran
2- Assistant Professor, Department of Biomedical Engineering, Imam Reza International University, Mashhad, Razavi Khorasan, Iran , ak_goshvarpour@imamreza.ac.ir
2- Assistant Professor, Department of Biomedical Engineering, Imam Reza International University, Mashhad, Razavi Khorasan, Iran , ak_goshvarpour@imamreza.ac.ir
Abstract: (1973 Views)
Introduction: Evaluation of the electroencephalogram of schizophrenic patients has been the subject of many recent studies. However, accurate diagnosis of schizophrenia using the electroencephalogram is still a challenging issue.
Aim: This paper was aimed to investigate the information discrepancy between one brain channel and other electrodes in two groups of schizophrenic patients and healthy individuals. Furthermore, the capability of the extracted features in the problem of classification of the two groups was investigated.
Method: In the present analytic observational study, 19 channels of the electroencephalogram of 14 patients with schizophrenia (7 males with an average age of 27.9 ± 3.3 years and 7 females with a mean age of 28.3 ± 4.1 years), who were hospitalized at the Institute of Psychiatry and Neurologists in Warsaw, Poland, were used. In addition, data from 14 healthy individuals (7 males and 7 females with an average age of 26.8 ± 2.9 and 28.7 ± 3.4 years, respectively) were analyzed as a control group. Cross information potential and Cauchy-Schwartz mutual information between each electroencephalogram electrode and all the other electrodes were calculated. Using two strategies, the performance of the support vector machine was evaluated: (1) the mutual information of an electroencephalogram channel with other channels, and (2) the combination of the mutual information of all brain channels.
Results: The results showed that using mutual information between electroencephalogram channels, the diagnosis accuracy increases up to 100%. For both indices, the mutual information between O2 and the other channels provided the highest classification performance.
Conclusion: These results nominated the proposed system as a superior one compared to the state-of-the-art electroencephalogram schizophrenia diagnosis tools.
Aim: This paper was aimed to investigate the information discrepancy between one brain channel and other electrodes in two groups of schizophrenic patients and healthy individuals. Furthermore, the capability of the extracted features in the problem of classification of the two groups was investigated.
Method: In the present analytic observational study, 19 channels of the electroencephalogram of 14 patients with schizophrenia (7 males with an average age of 27.9 ± 3.3 years and 7 females with a mean age of 28.3 ± 4.1 years), who were hospitalized at the Institute of Psychiatry and Neurologists in Warsaw, Poland, were used. In addition, data from 14 healthy individuals (7 males and 7 females with an average age of 26.8 ± 2.9 and 28.7 ± 3.4 years, respectively) were analyzed as a control group. Cross information potential and Cauchy-Schwartz mutual information between each electroencephalogram electrode and all the other electrodes were calculated. Using two strategies, the performance of the support vector machine was evaluated: (1) the mutual information of an electroencephalogram channel with other channels, and (2) the combination of the mutual information of all brain channels.
Results: The results showed that using mutual information between electroencephalogram channels, the diagnosis accuracy increases up to 100%. For both indices, the mutual information between O2 and the other channels provided the highest classification performance.
Conclusion: These results nominated the proposed system as a superior one compared to the state-of-the-art electroencephalogram schizophrenia diagnosis tools.
Type of Study: Research |
Subject:
Special
Received: 2021/04/9 | Accepted: 2021/06/13 | Published: 2021/07/31
Received: 2021/04/9 | Accepted: 2021/06/13 | Published: 2021/07/31
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
