Accepted for/Published in: JMIR Research Protocols
Date Submitted: Jun 3, 2025
Date Accepted: Feb 9, 2026
Implementation and Evaluation of an AI-Assisted Telerehabilitation System (ATLAS) for Post-Discharge Continuation of Rehabilitative Care: Protocol for a Randomized Controlled Trial
ABSTRACT
Background:
The World Health Organization (WHO) launched a Rehabilitation 2030 initiative to call for action for global upscaling of rehabilitation efforts. Rehabilitation needs are growing, and efforts should be made to strengthen and integrate rehabilitation into all levels of health care, including building of research capacity and expanding of evidence for rehabilitation. Post-discharge rehabilitation is essential to reducing readmissions and keeping patients healthy within the community. However, locally, the shift towards community rehabilitation is often hampered by long waiting times for day rehabilitation centres (DRC), cost and logistical barriers, and the lack of a structured programme to onboard patients and caregivers to required digital solutions in Singapore. Telerehabilitation systems that incorporate wearables via a structured programme assists in inpatient rehabilitation and allows patients to continue with physical rehabilitation after discharge, while waiting for DRC.
Objective:
The aim of this randomized controlled trial (RCT) is to investigate the clinical and cost-effectiveness of ATLAS, an Artificial intelligence (AI)-assisted Telerehabilitation System, among patients admitted to community hospitals for rehabilitation.
Methods:
This is a two-arm pragmatic randomized controlled trial. Participants admitted to community hospitals for rehabilitation for hip fracture, musculoskeletal conditions or deconditioning will be enrolled and randomised to either intervention or control in a 1:1 ratio. The intervention group, in addition to usual care, will be enrolled into an ATLAS system. This ATLAS system consists of Rebee, an AI-assisted device, with an attached lightweight wireless motion-sensor that can be strapped on by patients for real-time feedback and logging of exercises via the Rebee application into an electronic platform, as well as a therapist-designed structured exercise programme to follow while inpatient and upon discharge. The control group will continue to receive usual rehabilitative care in the community hospitals and upon discharge but will not have access to this ATLAS system. Our primary outcome is functional status. Secondary outcomes include quality of life, length of stay in the community hospital, 30-day readmission rates, and cost-effectiveness.
Results:
A total of 407 participants have been recruited between January to September 2025 across three community hospitals. Data collection is scheduled for completion by December 2025. Data analysis is currently underway, and the results are expected to be submitted for publication in 2026.
Conclusions:
Our trial will provide valuable insights into the effectiveness and implementation of an AI-assisted telerehabilitation system for patients admitted to the community hospital for rehabilitation for hip fracture, musculoskeletal conditions, or deconditioning. This trial will also evaluate the sustainability and cost-effectiveness of such a system, with potential scaling to inpatients in the acute and community hospitals. Clinical Trial: This study was registered on clintrials.gov on 11/11/2024. Trial registration number: NCT06683963
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.