Fri, Jan 30, 2026
| فارسی
Volume 27, Issue 2 (summer 2025)
Advances in Cognitive Sciences 2025, 27(2): 66-80 |
Back to browse issues page
Ethics code: IR.ISAAR.REC.1402.003
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Pourbaghi N, Pedram M M, Moradi A, Setarehdan S K. Diagnosing post-traumatic stress disorder using CANTAB test data and a machine learning model. Advances in Cognitive Sciences 2025; 27 (2) :66-80
URL: http://icssjournal.ir/article-1-1763-en.html
URL: http://icssjournal.ir/article-1-1763-en.html
1- PhD Candidate of Brain and Computation, Department of Cognitive Modelling & Brain and Computation (CM&BC), Institute for Cognitive Science Studies, Tehran, Iran
2- Associate Professor of Electrical Engineering, Department of Electrical and Computer Engineering, Faculty of Engineering, Kharazmi University, Tehran, Iran
3- Professor of Clinical Psychology, Department of Clinical Psychology, Kharazmi University, Tehran, Iran
4- Professor of Biomedical Engineering, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
2- Associate Professor of Electrical Engineering, Department of Electrical and Computer Engineering, Faculty of Engineering, Kharazmi University, Tehran, Iran
3- Professor of Clinical Psychology, Department of Clinical Psychology, Kharazmi University, Tehran, Iran
4- Professor of Biomedical Engineering, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
Abstract: (711 Views)
Introduction: Post-traumatic stress disorder (PTSD) is known as a severe psychological and emotional reaction to the experience of traumatic and adverse events such as war, life threats, natural disasters, and personal violence. This often leads to chronic mental and physical abnormalities. Studies have shown that executive function impairment is a characteristic of this disorder, and cognitive assessments can be an essential diagnostic criterion.
Methods: This study uses data from the CANTAB clinical SWM task to assess measures such as DTLR, CD, BE, WE, TF, and DD at different stages. After normalization, the data are standardized and amplified by adding Gaussian noise. Then, a support vector machine model with a Gaussian kernel, which has a strong ability to distinguish complex, nonlinear patterns due to its special characteristics, is trained.
Results: The extracted features were effective in identifying complex differences in cognitive performance that characterize PTSD symptoms. The information collected from these features demonstrated the model’s high ability to effectively simulate and analyze PTSD symptoms, as well as accurately distinguish between affected and non-affected groups.
Conclusion: The machine learning model used in this study has enabled the use of the CANTAB test as a neuropsychological tool for diagnosing PTSD. The model’s accuracy in this study reached 98%, indicating high power and confidence in correctly diagnosing individuals with this disorder.
Methods: This study uses data from the CANTAB clinical SWM task to assess measures such as DTLR, CD, BE, WE, TF, and DD at different stages. After normalization, the data are standardized and amplified by adding Gaussian noise. Then, a support vector machine model with a Gaussian kernel, which has a strong ability to distinguish complex, nonlinear patterns due to its special characteristics, is trained.
Results: The extracted features were effective in identifying complex differences in cognitive performance that characterize PTSD symptoms. The information collected from these features demonstrated the model’s high ability to effectively simulate and analyze PTSD symptoms, as well as accurately distinguish between affected and non-affected groups.
Conclusion: The machine learning model used in this study has enabled the use of the CANTAB test as a neuropsychological tool for diagnosing PTSD. The model’s accuracy in this study reached 98%, indicating high power and confidence in correctly diagnosing individuals with this disorder.
Type of Study: Research |
Received: 2025/02/25 | Accepted: 2025/09/11 | Published: 2025/10/5
Received: 2025/02/25 | Accepted: 2025/09/11 | Published: 2025/10/5
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
