, Articles

Preprint: Toward Trustworthy Human-AI Collaboration in Neurorehabilitation: A Multimodal Data Registry for Clinical Decision Support

Articles
Published 03.11.2026
Kinga Quaaden
ZHAW Zurich University of Applied Sciences, School of Engineering, Institute of Applied Mathematics and Physics
Simone Bonato
FHNW University of Applied Sciences and Arts Northwestern Switzerland, School of Computer Science, Institute of Data Science, Brugg-Windisch, Switzerland
Rudolf Füchslin
ZHAW Zurich University of Applied Sciences, School of Engineering, Institute of Applied Mathematics and Physics, Winterthur, Switzerland
Martina Spiess
ZHAW Zurich University of Applied Sciences, School of Health Professions, Institute of Occupational Therapy, Winterthur, Switzerland
Anne Deblock-Bellamy
HES-SO University of Applied Sciences and Arts Western Switzerland, School of Health Sciences, Occupational Therapy Department, Lausanne, Switzerland
Susanne Suter
FHNW University of Applied Sciences and Arts Northwestern Switzerland, School of Computer Science, Institute of Data Science, Brugg-Windisch, Switzerland
Yara Peterko
ZHAW Zurich University of Applied Sciences, School of Health Professions, Institute of Occupational Therapy, Winterthur, Switzerland
Celina Schweizer-Chavez Panduro
ZHAW Zurich University of Applied Sciences, School of Health Professions, Institute of Occupational Therapy, Winterthur, Switzerland
Mathilde Berger
HES-SO University of Applied Sciences and Arts Western Switzerland, School of Health Sciences, Occupational Therapy Department, Lausanne, Switzerland
Lijin Aryananda Blatter
ZHAW Zurich University of Applied Sciences, School of Engineering, Institute of Applied Mathematics and Physics
Vera Kaelin
OST Eastern Switzerland University of Applied Sciences, School of Health Sciences, Institute of Health Sciences, St.Gallen, Switzerland
PDF

Keywords

Clinical decision support system
Human-in-the-loop
Neurorehabilitation
Gait rehabilitation
Data registry
Rehabilitation technology

Abstract

Regaining independent walking ability is a primary goal after stroke or spinal cord and brain injuries, yet selecting appropriate technological interventions remains a complex challenge. While a human-in-the-loop clinical decision support system (CDSS) can enhance clinical judgement, current real-world data is too fragmented to train trustworthy models. This paper presents a standardised, multimodal data registry prospectively capturing patient characteristics, clinical assessments, and device parameters, providing the foundational infrastructure to develop and validate a reliable, AI-based CDSS for gait neurorehabilitation.

PDF
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2026 Kinga Quaaden, Simone Bonato, Rudolf Füchslin, Martina Spiess, Anne Deblock-Bellamy, Susanne Suter, Yara Peterko, Celina Schweizer-Chavez Panduro, Mathilde Berger, Lijin Aryananda Blatter, Vera Kaelin