Efficiency of convolutional neural networks of different architecture for the task of depression diagnosis from EEG data

Cover Page

Cite item

Full Text

Abstract

The purpose of this paper is to comparatively analyse the efficiency of using artificial neural networks with different convolutional and recurrent architectures in the task of depression diagnosis based on electroencephalogram (EEG) data. Open datasets were chosen as objects of the study and own EEG data of real patients with depression were collected. Methods. To solve the problem of identifying biomarkers of depressive disorder from EEG data, we used convolutional neural networks using two-dimensional or one-dimensional convolution operation, as well as hybrid models of convolutional and recurrent neural networks. To test the developed models of artificial neural networks, we selected open data sets, performed an experiment to collect our own data from real depressed patients, and merged the prepared data sets. The result of this work is analysis and comparison of the performance of different classifiers based on convolutional and recurrent neural network models. Conclusion. We show that the average accuracy of classification of depressive disorder in a test sample using cross-validation was 0.68. The results are consistent with the known results from the literature for small patient-disaggregated datasets. Although the accuracy obtained in this task is insufficient for practical application of the model, it can be argued that further research to improve the efficiency of the model is promising, as well as the need to create a sufficiently large representative dataset of depressed patients, which is an important scientific task for further construction of biophysical models of depressive disorders.

About the authors

Natalia Nikolaevna Shusharina

Immanuel Kant Baltic Federal University

ORCID iD: 0000-0002-3912-4639
Scopus Author ID: 55790267200
ResearcherId: A-6801-2014
14 A. Nevskogo ul., Kaliningrad, 236041

References

  1. Rajpurkar P., Chen E., Banerjee O., Topol E. J. AI in health and medicine // Nature medicine. 2022. Vol. 28, no. 1. P. 31–38. doi: 10.1038/s41591-021-01614-0.
  2. Abersek B., Flogie A., Pesek I. AI and Cognitive Modelling for Education. Springer Nature; 2023. 230 p. doi: 10.1007/978-3-031-35331-4.
  3. Karpov O. E., Pitsik E. N., Kurkin S. A., Maksimenko V. A., Gusev A. V., Shusharina N. N., Hramov A. E. Analysis of Publication Activity and Research Trends in the Field of AI Medical Applications: Network Approach // International Journal of Environmental Research and Public Health. 2023. Vol. 20, no. 7. P. 5335. doi: 10.3390/ijerph20075335.
  4. Карпов О. Э., Храмов А. Е. Информационные технологии, вычислительные системы и искусственный интеллект в медицине. М.: ДПК Пресс; 2022. 480 c.
  5. Tondo G., De Marchi F.. From biomarkers to precision medicine in neurodegenerative diseases: Where are we? // Journal of Clinical Medicine. 2022. Vol. 11, no. 15. P. 4515. DOI: 10.3390/ jcm11154515
  6. Strafella C., Caputo V., Galota M. R., Zampatti S., Marella G., Mauriello S., Cascella R., Giardina E.. Application of precision medicine in neurodegenerative diseases // Frontiers in neurology. 2018. Vol. 9. P. 701. doi: 10.3389/fneur.2018.00701.
  7. Chepurova A., Hramov A., Kurkin S. Motor Imagery: How to Assess, Improve Its Performance, and Apply It for Psychosis Diagnostics // Diagnostics. 2022. Vol. 12, no. 4. P. 949. doi: 10.3390/diagnostics1204094.
  8. Zhang Sh., Zhao H., Wang W., Wang Zh., Luo X., Hramov A., Kurths J. Edge-centric effective connection network based on muti-modal MRI for the diagnosis of Alzheimer’s disease // Neurocomputing. 2023. Vol. 552. P. 126512. doi: 10.1016/j.neucom.2023.126512.
  9. Andreev A. V., Kurkin S. A., Stoyanov D., Badarin A. A., Paunova R., Hramov A. E. Toward interpretability of machine learning methods for the classification of patients with major depressive disorder based on functional network measures // Chaos. 2023. Vol. 33, no. 6. P. 063140. doi: 10.1063/5.0155567.
  10. Sysoeva O., Maximenko V., Kuc A., Voinova V., Martynova O., Hramov A. Abnormal spectral and scale-free properties of resting-state EEG in girls with Rett syndrome // Scientific Reports. 2023. Vol. 13. P. 12932. doi: 10.1038/s41598-023-39398-7.
  11. Law Z. K., Todd C., Mehraram R., Schumacher J., Baker M. R., LeBeau F. E., Yarnall A., Onofrj M., Bonanni L., Thomas A., Taylor J. P. The role of EEG in the diagnosis, prognosis and clinical correlations of dementia with Lewy bodies—a systematic review // Diagnostics. 2020. Vol. 10, no. 9. P. 616. doi: 10.3390/diagnostics10090616.
  12. Schjønning Nielsen M., Simonsen A. H., Siersma V., Engedal K., Jelic V., Andersen B. B., Naik M., Hasselbalch S. G., Høgh P. Quantitative electroencephalography analyzed by statistical pattern recognition as a diagnostic and prognostic tool in mild cognitive impairment: results from a nordic multicenter cohort study // Dementia and Geriatric Cognitive Disorders Extra. 2019. Vol. 8, no. 3. P. 426–438. doi: 10.1159/000490788.
  13. Gouw A. A. Clinical appications of EEG/MEG in AD: diagnosis, prognosis and treatment monitoring // Alzheimer’s & Dementia. 2023. Vol. 19, no. S12. P. e073238. doi: 10.1002/alz.073238.
  14. Torres-Simon L., Doval S., Nebreda A., Llinas S. J., Marsh E. B., Maestu F. Understanding brain function in vascular cognitive impairment and dementia with EEG and MEG: A systematic review // NeuroImage: Clinical. 2019. Vol. 35. P. 103040. doi: 10.1016/j.nicl.2022.103040.
  15. Yahata N., Kasai K., Kawato M. Computational neuroscience approach to biomarkers and treatments for mental disorders // Psychiatry and clinical neurosciences. 2016. Vol. 71, no. 4. P. 215–237. doi: 10.1111/pcn.12502.
  16. Карпов О. Э., Храмов А. Е. Прогностическая медицина // Врач и информационные технологии. 2021. Т. 3. С. 20–37. doi: 10.25881/18110193_2021_3_20.
  17. Pitsik E. N., Maximenko V. A., Kurkin S. A., Sergeev A. P., Stoyanov D., Paunova R., Kandilarova S., Simeonova D., Hramov A. E. The topology of fMRI-based networks defines the performance of a graph neural network for the classification of patients with major depressive disorder // Chaos, Solitons & Fractals. 2023. Vol. 167. P. 113041. doi: 10.1016/j.chaos.2022.113041.
  18. Boronina A., Maksimenko V., Hramov A. E. Convolutional Neural Network Outperforms Graph Neural Network on the Spatially Variant Graph Data // Mathematics. 2023. Vol. 11, no. 11. P. 2515. doi: 10.3390/math11112515
  19. Mumtaz W. MDD Patients and Healthy Controls EEG Data (New) // figshare. 2016. Dataset. doi: 10.6084/m9.figshare.4244171.v2
  20. Cavanagh J. EEG: Depression rest // OpenNeuro. 2021. Dataset. doi: 10.18112/openneuro. ds003478.v1.1.0
  21. Cai H., Yuan Z., Gao Y., Sun S., Li N., Tian F., Xiao H., Li J., Yang Z., Li X., Zhao Q., Liu Z., Yao Z., Yang M., Peng H., Zhu J., Zhang X., Gao G., Zheng F., Li R., Guo Z., Ma R., Yang J., Zhang L., Hu X., Li Y., Hu B. MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis // arXiv:2002.09283. 2020. Dataset. doi: 10.48550/arXiv.2002.09283.
  22. MODMA Dataset. URL: http://modma.lzu.edu.cn/data/application/.
  23. Beck A. T., Ward C., Mendelson M., Mock J., Erbaugh J. An inventory for measuring depression // Archives of general psychiatry. 1961. Vol. 4, no. 6. P. 561–571. doi: 10.1001/archpsyc.1961. 01710120031004.
  24. Mumtaz W., Ali S. S. A., Yasin M. A. M., Malik A. S. A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD) // Medical & biological engineering & computing. 2018. Vol. 56, no. 2. P. 233–246. doi: 10.1007/s11517-017- 1685-z.
  25. Gramfort A., Luessi M., Larson E., Engemann D. A., Strohmeier D., Brodbeck C., Hamalainen M. MEG and EEG data analysis with MNE-Python // Frontiers in neuroscience. 2013. Vol. 7. P. 267. doi: 10.3389/fnins.2013.00267.
  26. Mumtaz W., Xia L., Ali S. S. A., Yasin M. A. M., Hussain M., Malik A. S. Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD) // Biomedical Signal Processing and Control. 2017. Vol. 31, P. 108–115. doi: 10.1016/j.bspc.2016.07.006.
  27. Stephan K. E., Schlagenhauf F., Huys Q. J., Raman S., Aponte E. A., Brodersen K. H., Rigoux L., Moran R. J., Daunizeau J., Dolan R. J., Friston K. J., Heinz A. Computational neuroimaging strategies for single patient predictions // Neuroimage. 2017. Vol. 145, Part B. P. 180–199. doi: 10.1016/j.neuroimage.2016.06.038.
  28. de Bardeci M., Ip C. T., Olbrich S. Deep learning applied to electroencephalogram data in mental disorders: A systematic review // Biological Psychology. 2021. Vol. 162. P. 108117. doi: 10.1016/j.biopsycho.2021.108117.
  29. Rivera M. J., Teruel M. A., Mate A., Trujillo J. Diagnosis and prognosis of mental disorders by means of EEG and deep learning: a systematic mapping study // Artificial Intelligence Review. 2022. Vol. 55. P. 1209–1251. doi: 10.1007/s10462-021-09986-y.
  30. Mumtaz W., Malik A. S., Ali S. S. A., Yasin M. A. M. P300 intensities and latencies for major depressive disorder detection // 2015 IEEE International Conference on Signal and Image Processing Applications (ICSIPA). 2015. P. 542–545. doi: 10.1109/ICSIPA.2015.7412250.
  31. Mumtaz W., Qayyum A. A deep learning framework for automatic diagnosis of unipolar depression // International journal of medical informatics. 2019. Vol. 132. P. 103983. doi: 10.1016/j.ijmedinf. 2019.103983.
  32. Acharya U. R., Oh S. L., Hagiwara Y., Tan J. H., Adeli H., Subha D. P. Automated EEG-based screening of depression using deep convolutional neural network // Computer methods and programs in biomedicine. 2018. Vol. 161. P. 103–113. doi: 10.1016/j.cmpb.2018.04.012.
  33. Ay B., Yildirim O., Talo M., Baloglu U. B., Aydin G., Puthankattil S. D., Acharya U. R. Automated depression detection using deep representation and sequence learning with EEG signals // Journal of medical systems. 2019. Vol. 43. P. 205. doi: 10.1007/s10916-019-1345-y.
  34. Sandheep P., Vineeth S., Poulose M., Subha D. P. Performance analysis of deep learning CNN in classification of depression EEG signals // 2019 IEEE Region 10 Conference (TENCON). 2019. P. 1339–1344. doi: 10.1109/TENCON.2019.8929254.
  35. Lawhern V. J., Solon A. J., Waytowich N. R., Gordon S. M., Hung C. P., Lance B. J. EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces // Journal of neural engineering. 2018. Vol. 15, no. 5. P. 056013. doi: 10.1088/1741-2552/aace8c.
  36. Cun Y. L., Bottou L., Orr G., Muller K. Efficient backprop. Neural networks: Tricks of the trade. Springer, Berlin, Heidelberg. 2012. P. 9–48. doi: 10.1007/978-3-642-35289-8_3.
  37. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Duchesnay E. Scikitlearn: Machine learning in Python // The Journal of Machine Learning Research. 2011. Vol. 12. P. 2825–2830.
  38. Abadi M., Agarwal A., Barham P., Brevdo E., Chen Z., Citro C., Zheng X. Tensorflow: Large-scale machine learning on heterogeneous distributed systems // arXiv:1603.04467. 2016. Dataset. doi: 10.48550/arXiv.1603.04467.
  39. Kingma D. P., Ba J. Adam: A method for stochastic optimization // arXiv:1412.6980. 2014. Dataset. doi: 10.48550/arXiv.1412.6980.
  40. Hutter F., Lucke J., Schmidt-Thieme L. Beyond manual tuning of hyperparameters // KI-Kunstliche Intelligenz. 2015. Vol. 29, no. 4. P. 329–337. doi: 10.1007/s13218-015-0381-0.
  41. Bergstra J., Bengio Y. Random search for hyper-parameter optimization // Journal of Machine Learning Research. 2012. Vol. 13. P. 281–305.
  42. KerasTuner. URL: https://github.com/keras-team/keras-tuner.
  43. Lashgari E., Liang D., Maoz U. Data augmentation for deep-learning-based electroencephalography // Journal of Neuroscience Methods. 2020. Vol. 346. P. 108885. doi: 10.1016/j.jneumeth. 2020.108885.
  44. Koppe G., Meyer-Lindenberg A., Durstewitz D. Deep learning for small and big data in psychiatry // Neuropsychopharmacology Reviews. 2021. Vol. 46. P. 176–190. DOI: doi.org/10.1038/s41386- 020-0767-z.
  45. Durstewitz D., Koppe G., Meyer-Lindenberg A. Deep neural networks in psychiatry // Molecular Psychiatry. 2019. Vol. 24. P. 1583–1598. DOI: doi.org/10.1038/s41380-019-0365-9.
  46. Zhang Z., Lin W., Liu M., Mahmoud M.. Multimodal Deep Learning Framework for Mental Disorder Recognition // 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), Buenos Aires, Argentina. 2020. P. 344–350. doi: 10.1109/FG47880.2020. 00033.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies