Progressive Transition From Supervised to Unsupervised Robot-Assisted Therapy After Stroke: Protocol for a Single-Group, Interventional Feasibility Study
Bibliographic record
Abstract
BACKGROUND: Increasing the dose of therapy delivered to patients with stroke may improve functional outcomes and quality of life. Unsupervised technology-assisted rehabilitation is a promising way to increase the dose of therapy without dramatically increasing the burden on the health care system. Despite the many existing technologies for unsupervised rehabilitation, active rehabilitation robots have rarely been tested in a fully unsupervised way. Furthermore, the outcomes of unsupervised technology-assisted therapy (eg, feasibility, acceptance, and increase in therapy dose) vary widely. This might be due to the use of different technologies as well as to the broad range of methods applied to teach the patients how to independently train with a technology. OBJECTIVE: This paper describes the study design of a clinical study investigating the feasibility of unsupervised therapy with an active robot and of a systematic approach for the progressive transition from supervised to unsupervised use of a rehabilitation technology in a clinical setting. The effect of unsupervised therapy on achievable therapy dose, user experience in this therapy setting, and the usability of the rehabilitation technology are also evaluated. METHODS: Participants of the clinical study are inpatients of a rehabilitation clinic with subacute stroke undergoing a 4-week intervention where they train with a hand rehabilitation robot. The first week of the intervention is supervised by a therapist, who teaches participants how to interact and train with the device. The second week consists of minimally supervised therapy, where the therapist is present but intervenes only if needed as participants exercise with the device. If the participants properly learn how to train with the device, they proceed to the unsupervised phase and train without any supervision during the third and fourth weeks. Throughout the duration of the study, data on feasibility and therapy dose (ie, duration and repetitions) are collected. Usability and user experience are evaluated at the end of the second (ie, minimally supervised) and fourth (ie, unsupervised) weeks, allowing us to investigate the effect of therapist absence. RESULTS: As of April 2023, 13 patients were recruited and completed the protocol, with no reported adverse events. CONCLUSIONS: This study will inform on the feasibility of fully unsupervised rehabilitation with an active rehabilitation robot in a clinical setting and its effect on therapy dose. Furthermore, if successful, the proposed systematic approach for a progressive transition from supervised to unsupervised technology-assisted rehabilitation could serve as a benchmark to allow for easier comparisons between different technologies. This approach could also be extended to the application of such technologies in the home environment, as the supervised and minimally supervised sessions could be performed in the clinic, followed by unsupervised therapy at home after discharge. TRIAL REGISTRATION: ClinicalTrials.gov NCT04388891; https://clinicaltrials.gov/study/NCT04388891. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/48485.
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 | 0.038 | 0.027 |
| Meta-epidemiology (narrow) | 0.005 | 0.003 |
| Meta-epidemiology (broad) | 0.007 | 0.004 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.006 | 0.006 |
| Insufficient payload (model declined to judge) | 0.042 | 0.012 |
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".