An intelligible AI-driven decision support system for poststroke mobility assessment
The automated assessments agree well with those of the experts. Synergistic interactions between system, and experts via the computed key features may improve quality in diagnosis and objectify therapeutic targets.
Authors
- Dominik Raab (ORCID: https://orcid.org/0000-0003-4514-1053)
- Markus Jäger (ORCID: https://orcid.org/0000-0001-9516-1058)
- Jin Cheng Liaw
- Dörte Zietz (ORCID: https://orcid.org/0000-0002-3008-9400)
- Malte Weber (ORCID: https://orcid.org/0009-0006-3074-4205)
- Harald Hefter (ORCID: https://orcid.org/0000-0003-1069-7684)
- Francisco Geu Flores (ORCID: https://orcid.org/0000-0002-8106-0894)
- Andrés Kecskeméthy (ORCID: https://orcid.org/0000-0002-2044-7892)
- Mario Siebler
Institutions
- Düsseldorf University Hospital (DE)
- Ruhr West University of Applied Sciences (DE)
- Bochum University of Applied Sciences (DE)
- Heinrich Heine University Düsseldorf (DE)
- University of Duisburg-Essen (DE)
- Offenburg University of Applied Sciences (DE)
Publication Details
- Journal
- Journal of Rehabilitation Medicine – Clinical Communications
- Published
- 2025-07-20
- DOI
- https://doi.org/10.2340/jrm-cc.v8.42379
- Citations
- 1
- Primary Topic
- Stroke Rehabilitation and Recovery
- Type
- article
- Field-Weighted Citation Impact
- 1.03
Funders
- European Commission
- Universität Duisburg-Essen