Can machine learning improve on the early prediction of upper limb recovery after stroke?
Our model provides significantly more accurate predictions of upper limb recovery, with a 69% error reduction compared to the mixed-effects model. Its ease of use, interpretability, and use of routinely collected clinical data make it suitable for digital clinical workflows. Future research could validate the model in larger, more recent cohorts and explore integrating neuroimaging and temporal features.
Authors
- Eleni‐Rosalina Andrinopoulou (ORCID: https://orcid.org/0000-0002-5372-4163)
- Carel G. M. Meskers (ORCID: https://orcid.org/0000-0002-5056-5611)
- Theo van Walsum (ORCID: https://orcid.org/0000-0001-8257-7759)
- Hester F. Lingsma (ORCID: https://orcid.org/0000-0003-2063-9533)
- Erwin E. H. van Wegen (ORCID: https://orcid.org/0000-0002-7920-9995)
- Sandra Sülz (ORCID: https://orcid.org/0000-0002-2354-1307)
- Lisa Hoogendam (ORCID: https://orcid.org/0000-0001-9542-5105)
- Sandra Cornelissen (ORCID: https://orcid.org/0000-0002-0332-2158)
- Ruisheng Su (ORCID: https://orcid.org/0000-0002-5013-1370)
- Gert Kwakkel (ORCID: https://orcid.org/0000-0002-4041-4043)
- Paul van der Hulst (ORCID: https://orcid.org/0000-0002-2635-833X)
- Ellen Hu (ORCID: https://orcid.org/0009-0009-6017-7119)
- Daniël Ruijters (ORCID: https://orcid.org/0000-0002-9931-4047)
- Ruud W. Selles (ORCID: https://orcid.org/0000-0002-2432-6756)
- Bob Roozenbeek (ORCID: https://orcid.org/0000-0002-8320-8303)
- Daniël Bos (ORCID: https://orcid.org/0000-0001-8979-2603)
- Xi Li (ORCID: https://orcid.org/0000-0003-3639-1907)
- Erik Grauwmeijer
- Frank G. te Nijenhuis (ORCID: https://orcid.org/0009-0003-1321-5836)
- Milou Silkens
- G. J. van der Gun
Institutions
- Codarts Rotterdam (NL)
- Erasmus MC (NL)
- Amsterdam Neuroscience (NL)
- Amsterdam University Medical Centers (NL)
- Vrije Universiteit Amsterdam (NL)
- Erasmus University Rotterdam (NL)
Publication Details
- Journal
- Journal of NeuroEngineering and Rehabilitation
- Published
- 2025-10-27
- DOI
- https://doi.org/10.1186/s12984-025-01743-4
- Citations
- 2
- Primary Topic
- Stroke Rehabilitation and Recovery
- Type
- article
- Field-Weighted Citation Impact
- 2.05
Funders
- European Commission
- ZonMw
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek
- Hersenstichting
- Ministerie van Economische Zaken en Klimaat