Machine learning aided classification of tremor in multiple sclerosis

Abdulnasir Hossen; Abdul Rauf Anwar; Nabin Koirala; Hao Ding; Dmitry Budker; Arne Wickenbrock; Ulrich Heute; Günther Deuschl; Sergiu Groppa; Muthuraman Muthuraman

doi:10.1016/j.ebiom.2022.104152

Machine learning aided classification of tremor in multiple sclerosis

EBioMedicine. 2022 Aug:82:104152. doi: 10.1016/j.ebiom.2022.104152. Epub 2022 Jul 11.

Authors

Affiliations

¹ Department of Electrical & Computer Engineering, Sultan Qaboos University, Al-Khoud, 123 Muscat, Oman.
² Department of Biomedical Engineering, University of Engineering & Technology, Lahore 54890, Pakistan.
³ Haskins Laboratories, Yale University, New Haven, CT 06511, USA.
⁴ Department of Neurology, Movement Disorders and Neurostimulation, Biomedical Statistics and Multimodal Signal Processing, University Medical Centre of Johannes Gutenberg University, 55131 Mainz, Germany.
⁵ Helmholtz-Institut Mainz, GSI Helmholtz Zentrum für Schwerionenforschung, Johannes Gutenberg University, 55128 Mainz, Germany.
⁶ Institute of Digital Signal Processing and System Theory, Faculty of Engineering, University of Kiel, 24143 Kiel, Germany.
⁷ Department of Neurology, University of Kiel, 24105 Kiel, Germany.
⁸ Department of Neurology, Movement Disorders and Neurostimulation, Biomedical Statistics and Multimodal Signal Processing, University Medical Centre of Johannes Gutenberg University, 55131 Mainz, Germany. Electronic address: mmuthura@uni-mainz.de.

Abstract

Background: Tremors are frequent and disabling in people with multiple sclerosis (MS). Characteristic tremor frequencies in MS have a broad distribution range (1-10 Hz), which confounds the diagnostic from other forms of tremors. In this study, we propose a classification method for distinguishing MS tremors from other forms of cerebellar tremors.

Methods: Electromyogram (EMG), accelerometer and clinical data were obtained from a total of 120 [40 MS, 41 essential tremor (ET) and 39 Parkinson's disease (PD)] subjects. The proposed method - Soft Decision Wavelet Decomposition (SDWD) - was used to compute power spectral densities and receiver operating characteristic (ROC) analysis was performed for the automatic classification of the tremors. Association between the spectral features and clinical features (FTM - Fahn-Tolosa-Marin scale, UPDRS - Unified Parkinson's Disease Rating Scale), was assessed using a support vector regression (SVR) model.

Findings: Our developed analytical framework achieved an accuracy of up to 91.67% using accelerometer data and up to 91.60% using EMG signals for the differentiation of MS tremors and the tremors from ET and PD. In addition, SVR further revealed strong significant correlations between the selected discriminators and the clinical scores.

Interpretation: The proposed method, with high classification accuracy and strong correlations of these features to clinical outcomes, has clearly demonstrated the potential to complement the existing tremor-diagnostic approach in MS patients.

Funding: This work was supported by the German Research Foundation (DFG): SFB-TR-128 (to SG, MM), MU 4354/1-1(to MM) and the Boehringer Ingelheim Fonds BIF-03 (to SG, MM).

Keywords: Accelerometer; Electromyogram; Essential tremor; Multiple sclerosis tremor; Parkinson's disease tremor.

MeSH terms

Essential Tremor* / diagnosis
Humans
Machine Learning
Multiple Sclerosis* / diagnosis
Parkinson Disease* / diagnosis
Tremor / diagnosis
Tremor / etiology