Comparative analysis of machine learning algorithms for schizophrenia detection
Year 2024,
Volume: 3 Issue: 2, 33 - 41
Halil İbrahim Coşar
,
Muhammet Emin Şahin
Abstract
As mental and neurological disorders continue to rise globally, research utilizing artificial intelligence to analyse and classify differences in EEG signals is growing rapidly. This study utilises six different machine learning algorithms for detecting schizophrenia (SZ) using multichannel EEG signals. In the initial phase of this study, pre-processing is carried out, followed by the application of 13 distinct feature extraction techniques. The extracted features are subsequently classified using various machine learning algorithms, leading to classification accuracies up to 1.00 in four algorithms which are Decision Tree, Random Forest, Support Vector Machines (SVM) and Gradient Boosting. In addition, 5-fold cross-validation is applied to increase the reliability of the study. The findings indicate that the study achieved remarkable success and demonstrates the potential for effectively detecting schizophrenia using EEG signals.
References
- A. P. A.-T. revision and undefined 2000, “Diagnostic and statistical manual of mental disorders,” cir.nii.ac.jp, Accessed: Jun. 10, 2024. [Online]. Available: https://cir.nii.ac.jp/crid/1573950399819987840
- WHO, “Schizophrenia.” Accessed: Jun. 10, 2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/schizophrenia
- A. Craik, Y. He, and J. L. Contreras-Vidal, “Deep learning for electroencephalogram (EEG) classification tasks: A review,” Journal of Neural Engineering. 2019. doi: 10.1088/1741-2552/ab0ab5.
- G. Sahu, M. Karnati, A. Gupta, and A. Seal, “SCZ-SCAN: An automated Schizophrenia detection system from electroencephalogram signals,” Biomed. Signal Process. Control, vol. 86, p. 105206, Sep. 2023, doi: 10.1016/J.BSPC.2023.105206.
- S. Bagherzadeh, M. S. Shahabi, and A. Shalbaf, “Detection of schizophrenia using hybrid of deep learning and brain effective connectivity image from electroencephalogram signal,” Comput. Biol. Med., vol. 146, p. 105570, Jul. 2022, doi: 10.1016/J.COMPBIOMED.2022.105570.
- P. T. Krishnan, A. N. Joseph Raj, P. Balasubramanian, and Y. Chen, “Schizophrenia detection using MultivariateEmpirical Mode Decomposition and entropy measures from multichannel EEG signal,” Biocybern. Biomed. Eng., vol. 40, no. 3, pp. 1124–1139, Jul. 2020, doi: 10.1016/J.BBE.2020.05.008.
- V. Jahmunah et al., “Automated detection of schizophrenia using nonlinear signal processing methods,” Artif. Intell. Med., vol. 100, p. 101698, Sep. 2019, doi: 10.1016/J.ARTMED.2019.07.006.
- T. S. Kumar, K. N. V. P. S. Rajesh, S. Maheswari, V. Kanhangad, and U. R. Acharya, “Automated Schizophrenia detection using local descriptors with EEG signals,” Eng. Appl. Artif. Intell., vol. 117, p. 105602, Jan. 2023, doi: 10.1016/J.ENGAPPAI.2022.105602.
- K. Das and R. B. Pachori, “Schizophrenia detection technique using multivariate iterative filtering and multichannel EEG signals,” Biomed. Signal Process. Control, vol. 67, p. 102525, May 2021, doi: 10.1016/J.BSPC.2021.102525.
- H. Akbari, S. Ghofrani, P. Zakalvand, and M. Tariq Sadiq, “Schizophrenia recognition based on the phase space dynamic of EEG signals and graphical features,” Biomed. Signal Process. Control, vol. 69, p. 102917, Aug. 2021, doi: 10.1016/J.BSPC.2021.102917.
- S. K. Prabhakar, H. Rajaguru, and S. W. Lee, “A Framework for Schizophrenia EEG Signal Classification with Nature Inspired Optimization Algorithms,” IEEE Access, vol. 8, pp. 39875–39897, 2020, doi: 10.1109/ACCESS.2020.2975848.
- A. Shoeibi et al., “Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models,” Front. Neuroinform., vol. 15, p. 777977, Nov. 2021, doi: 10.3389/FNINF.2021.777977/BIBTEX.
- E. Olejarczyk and W. Jernajczyk, “EEG in schizophrenia.” RepOD, 2017, doi: 10.18150/REPOD.0107441.
- E. Olejarczyk and W. Jernajczyk, “Graph-based analysis of brain connectivity in schizophrenia,” PLoS One, vol. 12, no. 11, p. e0188629, Nov. 2017, doi: 10.1371/JOURNAL.PONE.0188629
Şizofreni tespiti için makine öğrenmesi algoritmalarının karşılaştırmalı analizi
Year 2024,
Volume: 3 Issue: 2, 33 - 41
Halil İbrahim Coşar
,
Muhammet Emin Şahin
Abstract
Zihinsel ve nörolojik bozukluklar küresel olarak artmaya devam ederken, EEG sinyallerindeki farklılıkları analiz etmek ve sınıflandırmak için yapay zekadan yararlanan araştırmalar hızla artmaktadır. Bu çalışmada, çok kanallı EEG sinyallerini kullanarak şizofreniyi (SZ) tespit etmek için altı farklı makine öğrenimi algoritması kullanılmaktadır. Bu çalışmanın ilk aşamasında, ön işleme gerçekleştirilmekte ve ardından 13 farklı özellik çıkarma tekniği uygulanmaktadır. Çıkarılan özellikler daha sonra çeşitli makine öğrenimi algoritmaları kullanılarak sınıflandırılmış ve Karar Ağacı, Rastgele Orman, Destek Vektör Makineleri (DVM) ve Gradyan Güçlendirme olmak üzere dört algoritmada 1.00'e varan sınıflandırma doğrulukları elde edilmiştir. Ayrıca, çalışmanın güvenilirliğini artırmak için 5 kat çapraz doğrulama uygulanmıştır. Bulgular, çalışmanın kayda değer bir başarı elde ettiğini ve EEG sinyallerini kullanarak şizofreniyi etkili bir şekilde tespit etme potansiyelini ortaya koyduğunu göstermektedir.
Ethical Statement
There is no ethical problem in the publication of this article.
References
- A. P. A.-T. revision and undefined 2000, “Diagnostic and statistical manual of mental disorders,” cir.nii.ac.jp, Accessed: Jun. 10, 2024. [Online]. Available: https://cir.nii.ac.jp/crid/1573950399819987840
- WHO, “Schizophrenia.” Accessed: Jun. 10, 2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/schizophrenia
- A. Craik, Y. He, and J. L. Contreras-Vidal, “Deep learning for electroencephalogram (EEG) classification tasks: A review,” Journal of Neural Engineering. 2019. doi: 10.1088/1741-2552/ab0ab5.
- G. Sahu, M. Karnati, A. Gupta, and A. Seal, “SCZ-SCAN: An automated Schizophrenia detection system from electroencephalogram signals,” Biomed. Signal Process. Control, vol. 86, p. 105206, Sep. 2023, doi: 10.1016/J.BSPC.2023.105206.
- S. Bagherzadeh, M. S. Shahabi, and A. Shalbaf, “Detection of schizophrenia using hybrid of deep learning and brain effective connectivity image from electroencephalogram signal,” Comput. Biol. Med., vol. 146, p. 105570, Jul. 2022, doi: 10.1016/J.COMPBIOMED.2022.105570.
- P. T. Krishnan, A. N. Joseph Raj, P. Balasubramanian, and Y. Chen, “Schizophrenia detection using MultivariateEmpirical Mode Decomposition and entropy measures from multichannel EEG signal,” Biocybern. Biomed. Eng., vol. 40, no. 3, pp. 1124–1139, Jul. 2020, doi: 10.1016/J.BBE.2020.05.008.
- V. Jahmunah et al., “Automated detection of schizophrenia using nonlinear signal processing methods,” Artif. Intell. Med., vol. 100, p. 101698, Sep. 2019, doi: 10.1016/J.ARTMED.2019.07.006.
- T. S. Kumar, K. N. V. P. S. Rajesh, S. Maheswari, V. Kanhangad, and U. R. Acharya, “Automated Schizophrenia detection using local descriptors with EEG signals,” Eng. Appl. Artif. Intell., vol. 117, p. 105602, Jan. 2023, doi: 10.1016/J.ENGAPPAI.2022.105602.
- K. Das and R. B. Pachori, “Schizophrenia detection technique using multivariate iterative filtering and multichannel EEG signals,” Biomed. Signal Process. Control, vol. 67, p. 102525, May 2021, doi: 10.1016/J.BSPC.2021.102525.
- H. Akbari, S. Ghofrani, P. Zakalvand, and M. Tariq Sadiq, “Schizophrenia recognition based on the phase space dynamic of EEG signals and graphical features,” Biomed. Signal Process. Control, vol. 69, p. 102917, Aug. 2021, doi: 10.1016/J.BSPC.2021.102917.
- S. K. Prabhakar, H. Rajaguru, and S. W. Lee, “A Framework for Schizophrenia EEG Signal Classification with Nature Inspired Optimization Algorithms,” IEEE Access, vol. 8, pp. 39875–39897, 2020, doi: 10.1109/ACCESS.2020.2975848.
- A. Shoeibi et al., “Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models,” Front. Neuroinform., vol. 15, p. 777977, Nov. 2021, doi: 10.3389/FNINF.2021.777977/BIBTEX.
- E. Olejarczyk and W. Jernajczyk, “EEG in schizophrenia.” RepOD, 2017, doi: 10.18150/REPOD.0107441.
- E. Olejarczyk and W. Jernajczyk, “Graph-based analysis of brain connectivity in schizophrenia,” PLoS One, vol. 12, no. 11, p. e0188629, Nov. 2017, doi: 10.1371/JOURNAL.PONE.0188629