ESTIMATION OF EDSS FROM EEG SIGNALS OF MULTIPLE SCLEROSIS PATIENTS

Year 2023, Issue: 053, 169 - 188, 30.06.2023

Seda Şaşmaz Karacan , Hamdi Melih Saraoğlu , Sibel Canbaz Kabay

https://doi.org/10.59313/jsr-a.1253334

Abstract

Multiple sclerosis (MS) is an autoimmune, neurodegenerative, chronic disease that affects the central nervous system and manifests itself with attacks. Although there is no definite cure for the disease, it is possible to control these attacks. Follow-up of the disease has great importance in terms of disability. An Extended Disability Status Scale (EDSS) is used to show how much the disease affects. This score is determined by specialized clinicians. In this study, the EDSS score, previously determined by neurologists, was attempted to be estimated using the EEG signals. 32-channel EEG signals were recorded while 17 MS patients with EDSS 1.0, 1.5, and 2.0 were performing a working memory task. Using the band power of these 6-minute EEG signals, EDSS estimation was performed with the Decision Tree Regressor, resulting in a Mean Absolute Error (MAE) of 0.088. With the Leave One Out Cross-Validation, 17 trees were extracted and 12 were found to be identical. As a result, the band power features of F7 and CP2 EEG channels were found to be successful in predicting 3-level EDSS scores with a decision tree regressor with 0.0 MAE. Additionally, the relationship between the scores obtained in the working memory task and the EDSS scores of MS patients was statistically calculated with One-way ANOVA. There was no significant difference between the EDSS score and the task scores (p>.05).

Keywords

Multiple sclerosis (MS), EEG, EDSS, Working Memory, Decision Tree Regressor

References

• [1] Multiple sclerosis - Symptoms and causes - Mayo Clinic. (2022). Mayo Clinic. https://www.mayoclinic.org/diseases-conditions/multiple-sclerosis/symptoms-causes/syc-20350269 (accessed Feb. 17, 2023).
• [2] Goris, A., Vandebergh, M., McCauley, J. L., Saarela, J., and Cotsapas, C. (2022). Genetics of multiple sclerosis: lessons from polygenicity. Lancet. Neurol., 21(9), 830–842.
• [3] Mental Health and Substance Use. (2006). Neurological Disorders: Public Health Challenges. https://www.who.int/publications/i/item/9789241563369 (accessed Feb. 17, 2023).
• [4] Kurtzke, J. F. (1983). Rating neurologic impairment in multiple sclerosis: an expanded disability status scale (EDSS). Neurology, 33(11), 1444–1452.
• [5] Sharrack, B. and Hughes, R. A. C. (1996). Clinical scales for multiple sclerosis. J. Neurol. Sci., 135(1), 1–9.
• [6] Tombak, K. B, Armutlu, K. and Karabudak, R. (2010). The Effect of Walking Distance on EDSS Score in Patients with Multiple Sclerosis. Turkish Journal of Neurology, 16(2), 72–77.
• [7] McMillan, L. and Moore, K. A. (2006). The Development and Validation of the Impact of Multiple Sclerosis Scale and the Symptoms of Multiple Sclerosis Scale. Arch. Phys. Med. Rehabil., 87(6), 832–841.
• [8] Lynch, S., Baker, S., Nashatizadeh, M., Thuringer, A., Thelen, J., and Bruce, J. (2021). Disability measurement in Multiple Sclerosis patients 55 years and older: What is the Expanded Disability Status Scale really telling clinicians?. Mult. Scler. Relat. Disord., 49(102724).
• [9] Ellenberger, D. et al. (2020). Is benign MS really benign? What a meaningful classification beyond the EDSS must take into consideration. Mult. Scler. Relat. Disord., 46(102485).
• [10] Koziol, J. A., Lucero, A., Sipe, J. C., Romine, J. S. and Beutler, E. (1999). Responsiveness of the Scripps neurologic rating scale during a multiple sclerosis clinical trial. Can. J. Neurol. Sci., 26(4), 283–289.
• [11] Fischer, J. S., Rudick, R. A., Cutter, G. R., and Reingold, S. C. (1999). The Multiple Sclerosis Functional Composite Measure (MSFC): an integrated approach to MS clinical outcome assessment. National MS Society Clinical Outcomes Assessment Task Force. Mult. Scler., 5(4), 244–250.
• [12] Walz, L., Brooks, J. C., Shavelle, R. M., Robertson, N. and Harding, K. E. (2022). Life expectancy in multiple sclerosis by EDSS score. Mult. Scler. Relat. Disord., 68(104219).
• [13] Şen, S. (2018). Neurostatus and EDSS Calculation with Cases. Arch. Neuropsychiatry, 55(1), 80-83.
• [14] Alexandra, T., Kim, C., Estefania, B., Elaine, R., Pierre, D. and Isabelle, R. (2023). Cognitive reserve as a moderating factor between EDSS and cognition in multiple sclerosis. Mult. Scler. Relat. Disord., 70(104482).
• [15] Kaufmann, M. et al. (2020). Development and validation of the self-reported disability status scale (SRDSS) to estimate EDSS-categories. Mult. Scler. Relat. Disord., 42(102148).
• [16] Zurawski, J. et al. (2019). Time between expanded disability status scale (EDSS) scores. Mult. Scler. Relat. Disord., 30(2019), 98–103.
• [17] Song, X. et al. (2020). Correlation between EDSS scores and cervical spinal cord atrophy at 3T MRI in multiple sclerosis: A systematic review and meta-analysis. Mult. Scler. Relat. Disord., 37(101426).
• [18] Cao, H. et al. (2013). Expanded Disability Status Scale (EDSS) estimation in multiple sclerosis from posturographic data. Gait Posture, 37(2), 242–245.
• [19] Cao, H. et al. (2013). Automatic Assessment of Expanded Disability Status Scale (EDSS) in Multiple Sclerosis Using a Decision Tree. Engineering, 5(10), 566–569.
• [20] Alves, P. et al.(2022). Validation of a machine learning approach to estimate expanded disability status scale scores for multiple sclerosis. Mult. Scler. J. - Exp. Transl. Clin., 8(2).
• [21] Salim, A. A., Ali, S. H., Hussain, A. M., and Ibrahim, W. N. (2021). Electroencephalographic evidence of gray matter lesions among multiple sclerosis patients: A case-control study. Medicine (Baltimore), 100(33).
• [22] Gschwind, M. et al. (2016). Fluctuations of spontaneous EEG topographies predict disease state in relapsing-remitting multiple sclerosis. NeuroImage Clin., 12(2016), 466–477.
• [23] Vázquez-Marrufo, M. et al.(2019). Altered individual behavioral and EEG parameters are related to the EDSS score in relapsing-remitting multiple sclerosis patients. PLoS One, 14(7).
• [24] Karacan, S.S., Saraoglu, H. M., Kabay, S. C., Akdag, G., Keskinkilic, C., and Tosun, M.(2022). EEG Based Environment Classification During Cognitive Task of Multiple Sclerosis Patients. In 4th Int. Congr. Human-Computer Interact. Optim. Robot. Appl. Proc (HORA), 1-4.
• [25] Karacan, S.S., Saraoglu, H. M., Kabay, S. C., Akdag, G., Keskinkilic, C., and Tosun, M. (2023). EEG-based mental workload estimation of multiple sclerosis patients. Signal, Image Video Process., 1–9.
• [26] Della Sala, S., Gray, C., Baddeley, A., and Wilson, L. (1967). Visual patterns test: a test of short-term visual recall, Thames Valley Test Company, UK.
• [27] Gramfort, A. et al. (2013). MEG and EEG data analysis with MNE-Python. Front. Neurosci., 7(267), 1-13.
• [28] Welch, P. D. (1967). The Use of Fast Fourier Transform for the Estimation of Power Spectra: A Method Based on Time Averaging Over Short, Modified Periodograms. IEEE Trans. Audio Electroacoust., 15(2), 70–73.
• [29] Pedregosa, F. (2011). Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res., 12, 2825–2830.
• [30] J. Qi, J., Du, J., Siniscalchi, S. M., Ma, X., and Lee, C. H. (2020). On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression. IEEE Signal Process. Lett.,27, 1485–1489.
• [31] Gelman, A., Goodrich, B., Gabry, J., and Vehtari, A. (2019). R-squared for Bayesian Regression Models. The American Statistician, 73(3), 307-309.