Combining magnetic resonance imaging and evoked potentials enhances machine learning prediction of multiple sclerosis disability worsening
This is the first study to integrate clinical, MRI radiomics, and motor EPTS features in an ML pipeline for MS prognosis. Combining structural and functional subclinical markers improves the prediction of disability worsening and supports multimodal monitoring for personalized care.
Authors
- Henry C. Woodruff (ORCID: https://orcid.org/0000-0001-7911-5123)
- Edward De Brouwer (ORCID: https://orcid.org/0000-0003-0608-0155)
- Veronica Popescu (ORCID: https://orcid.org/0000-0002-7156-5442)
- P. Lambin
- Jan Sijbers (ORCID: https://orcid.org/0000-0003-4225-2487)
- Dirk Deschrijver (ORCID: https://orcid.org/0000-0001-6600-1792)
- Diana L. Giraldo (ORCID: https://orcid.org/0000-0001-9778-1031)
- Liesbet M. Peeters
- Hamza Khan
- Lorin Werthen-Brabants
- Bart Van Wijmeersch
- Lotte Geys
- Tom Dhaene
- Sofie Aerts
Institutions
- University of Antwerp (BE)
- Wockhardt (United States) (US)
- Maastricht University Medical Centre (NL)
- Open Data Institute (GB)
- Ghent University (BE)
- Arctic Research Centre (SE)
- Biomed Research Institute (US)
- Precision for Medicine (United States) (US)
- National Rehabilitation Center (KR)
- KU Leuven (BE)
Publication Details
- Journal
- Frontiers in Immunology
- Published
- 2026-03-11
- DOI
- https://doi.org/10.3389/fimmu.2026.1625837
- Primary Topic
- Multiple Sclerosis Research Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Universiteit Hasselt
- Vlaamse regering
- Bijzonder Onderzoeksfonds UGent