The use of artificial intelligence in rehabilitation of adults with chronic conditions in Canada: A scoping review
Bibliographic record
Abstract
This is a protocol for a scoping review. The aim of this scoping review is to understand the use of artificial intelligence (AI) in rehabilitation of adults with chronic conditions in a Canadian context. Artificial intelligence (AI) is a rapidly evolving field and AI technology is becoming increasingly integrated into healthcare. However, the use of AI in rehabilitation of individuals with chronic conditions in Canada has not been explored in the literature. This exploration is crucial to understand if AI is currently being used for the rehabilitation of individuals with chronic conditions, how it is being used, and to identify potential areas to integrate AI into treatment. AI is defined as computer systems or machines that perform tasks that normally require human intelligence1. This may include the creation of personalized rehabilitation protocols, predictive models that analyze patient data, or the control of robotic devices that support movement training3. The implementation of AI in healthcare in Canada is complex due to the various tiers of regulation from federal to private law. There are also vague surveillance and reporting requirements that may result in safety risks4. Other barriers include ethical challenges such as informed consent to use, safely, and data privacy5. The integration of AI technologies into current workflows can also pose a challenge, including the data quantity, the education of training of staff, and funding limitations. However, perceived benefit, usefulness, accuracy, and ease of use have been discussed as facilitators for the implementation of AI in healthcare6. Research Objective: Understand the use of artificial intelligence (AI) in rehabilitation of adults with chronic conditions in a Canadian context. Additionally, this review will explore where AI is currently being used, how AI is used, the characteristics and parameters of physical rehabilitation interventions using AI, identify potential gaps in use where AI could be integrated into treatment in the future, and the barriers and facilitators of implementing these interventions Research Question: What literature exists describing the use of artificial intelligence (AI) in the rehabilitation of adults with chronic conditions in Canada? How is AI used in rehabilitation for adults with chronic conditions in Canada? What are the characteristics and parameters of rehabilitation interventions using AI for adults with chronic conditions in Canada? What are the barriers and facilitators to rehabilitation interventions using AI for adults with chronic conditions in Canada? Contributions of authors: Conceptualization (JST, HE, EB, HC, JC, AC, SR, PS); Writing original draft (EB, HC, JC, AC, SR, PS); Writing – reviewing and editing (JST, HE, EB, HC, JC, AC, SR, PS); Supervision (JST, HE); Funding Acquisition (JST, HE) Author Affiliations: School of Rehabilitation Sciences, Faculty of Health Sciences, McMaster University, Hamilton, ON, Canada (JST, HE, );
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 | 0.054 | 0.138 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.008 | 0.009 |
| Bibliometrics | 0.031 | 0.035 |
| Science and technology studies | 0.006 | 0.003 |
| Scholarly communication | 0.010 | 0.006 |
| Open science | 0.005 | 0.006 |
| Research integrity | 0.005 | 0.003 |
| Insufficient payload (model declined to judge) | 0.015 | 0.002 |
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".