An AI-Based Telerehabilitation Solution to Improve Mobility in People With Multiple Sclerosis (the PLATINUMS Project): Protocol for an Implementation and Evaluation Study
Bibliographic record
Abstract
BACKGROUND: Multiple sclerosis (MS) is a chronic, progressive, and neurodegenerative disease affecting more than 2.8 million people globally. Mobility impairments are among the most significant challenges faced by people with MS, leading to physical inactivity, deconditioning, and disability progression (for some, even irreversible disability). This negatively impacts mental health, social participation, and quality of life while placing a considerable economic burden on society. Exercise can improve mobility and mitigate disability progression, but facility-based options are often inaccessible, especially for those in remote areas. Telerehabilitation offers a promising alternative, but current systems are limited by complexity and hardware requirements. OBJECTIVE: The PLATINUMS (Implementation of an Advanced Telerehabilitation Solution for People With Multiple Sclerosis) project proposes an AI-driven telerehabilitation system to deliver accessible, cost-effective, and home-based exercise therapy for people with MS. METHODS: The PLATINUMS project begins with working package (WP) 1, focusing on obtaining ethical approval and recruiting staff. Following this, WP2 involves a 4-week system feasibility and usability study (n=40) to assess and refine the digital platform. WP3 comprises a validity study (n=60) to evaluate remote mobility tests via the system, such as the Short Physical Performance Battery (SPPB), functional reach, and sit-to-stand tests, to ensure their reliability for use in WP4, the feasibility multicenter randomized controlled trial (RCT). The 10-week multicenter feasibility RCT will be conducted in MS centers across Denmark, Ireland, Israel, and Italy, with 96 participants varying in disability levels. The primary objective is to evaluate the efficacy of the AI-powered telerehabilitation system on mobility outcomes compared to usual care. Finally, WP5 will assess the cost-effectiveness of the telerehabilitation system by analyzing implementation costs, adherence, and use of health care. The PLATINUMS project aims to revolutionize exercise therapy for people with MS by demonstrating the feasibility, validity, and preliminary efficacy of the AI-driven telerehabilitation system. This approach addresses barriers such as accessibility, privacy, and standardization while promoting patient and therapist acceptance. RESULTS: Funding for the PLATINUMS project was obtained in February 2024. WP2 data collection began in April 2025 across 4 European sites. WP3 is scheduled to launch in July 2025, with WP4 (the feasibility RCT) planned for January 2026. Initial WP2 results are expected by October 2025, with first publications anticipated in mid-2026. CONCLUSIONS: The PLATINUMS project is expected to generate critical insights into the feasibility, usability, and preliminary efficacy of an AI-based telerehabilitation system for people with MS. By leveraging widely available technology and real-time feedback, the system addresses key barriers to traditional rehabilitation. Findings from this protocol may inform future large-scale trials and support the broader implementation of digital health solutions in neurological rehabilitation. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/75983.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.059 | 0.047 |
| Meta-epidemiology (narrow) | 0.004 | 0.003 |
| Meta-epidemiology (broad) | 0.004 | 0.005 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.005 | 0.003 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.005 | 0.008 |
| Insufficient payload (model declined to judge) | 0.072 | 0.015 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".