Explainable machine learning for movement disorders - Classification of tremor and myoclonus

Aug 3, 2026

Explainable machine learning for movement disorders focuses on differentiating essential tremor (ET) from cortical myoclonus (CM), where clinical distinction remains difficult due to substantial inter- and intra-observer variability. Using accelerometry-based recordings from 19 ET and 19 CM patients across 21 tasks and eight sensors, the approach applies generalized matrix learning vector quantization (GMLVQ) to power-spectrum features. The model delivers near-perfect AUROC and provides interpretable decision context by highlighting frequency relevance (notably 5–7 Hz, and 3–4 and 9–10 Hz), supporting improved clinician diagnostic accuracy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Article information

Abstract

Background

Objectives

Methods

Results

Conclusion

Introduction

University of Groningen Explainable machine learning for movement disorders-Classification of tremor and myoclonus van den Brandhof, Elina L. ; Tuitert, Inge; van der Stouwe, A. M. Madelein; Elting, Jan W.J. ; Dalenberg, Jelle R. ; Svorenova, Tatiana; Klamer, Marrit R. ; Marapin, Ramesh S. ; Biehl, Michael; Tijssen, Marina A.J. Published in: Computers in biology and medicine DOI: 10.1016/j.compbiomed.2025.110180 IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below. Document Version Publisher's PDF, also known as Version of record Publication date: 2025 Link to publication in University of Groningen/UMCG research database Citation for published version (APA): van den Brandhof, E. L. , Tuitert, I. , van der Stouwe, A. M. M. , Elting, J. W. J. , Dalenberg, J. R. , Svorenova, T. , Klamer, M. R. , Marapin, R. S. , Biehl, M. , & Tijssen, M. A. J. (2025) . Explainable machine learning for movement disorders-Classification of tremor and myoclonus. Computers in biology and medicine, 192(Part B), Article 110180. [https://doi.org/10.1016/j.compbiomed.2025.110180](https://doi.org/10.1016/j.compbiomed.2025.110180) Copyright Other than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons) . The publication may also be distributed here under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license. More information can be found on the University of Groningen website: [https://www.rug.nl/library/open-access/self-archiving-pure/taverne](https://www.rug.nl/library/open-access/self-archiving-pure/taverne)amendment. Take-down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. Downloaded from the University of Groningen/U MCG research database (Pure): [http://www.rug. nl/research/portal. For technical reasons the](http://www.rug. nl/research/portal. For technical reasons the)[ ](http://www.rug. nl/research/portal. For technical reasons the)[number of authors shown on this cover page is limited to 10 maximum.](number of authors shown on this cover page is limited to 10 maximum.) Download date: 30-12-2025 Computers in Biology and Medicine 192 (2025) 110180 Contents lists available at ScienceDirect Computers in Biology and Medicine journal [homepage: www.elsevier.com/locate/compbiomed](homepage: www.elsevier.com/locate/compbiomed) | Explainable machine learning for movement disorders - Classification of tremor and myoclonus
Elina L. van den Brandhofa,b,c , Inge Tuiterta,b,d, A.M. Madelein van der Stouwea,b, Jan W.J. Eltinga,b, Jelle R. Dalenberg a,b, Tatiana Svorenova a,b,e,f, Marrit R. Klamer a,b, Ramesh S. Marapina,b , Michael Biehl c,g , Marina A.J. Tijssen a,b,*
a Expertise Center Movement Disorders Groningen, University Medical Center Groningen, Groningen, the Netherlands b Department of Neurology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands
c Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, the Netherlands
d NHL Stenden University of Applied Sciences, Leeuwarden, the Netherlands e Department of Neurology, P.J. Safarik University, Kosice, Slovak Republic f Department of Neurology, University Hospital of L. Pasteur, Kosice, Slovak Republic
g SMQB, Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, United Kingdom | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Keywords:
Machine learning
Hyperkinetic movement disorders Cortic

FAQs

What clinical problem does the study address for tremor and myoclonus?

It targets the difficulty of distinguishing essential tremor (ET) from cortical myoclonus (CM) because symptoms overlap and clinical assessments show large variability.

How does the proposed method use accelerometry data?

It records upper-body movements from ET and CM patients using multiple accelerometry sensors, transforms signals into power spectra, and feeds these features into an explainable machine learning model.

Why is interpretability important in this work?

GMLVQ not only classifies ET versus CM but also provides context for decisions by indicating which frequency ranges drive the model’s judgments, supporting clinical understanding.

Aug 3, 2026

Upload by Theodora