Voices of Recovery: Patients’ Experiences with AI-Assisted Stroke Rehabilitation
Bibliographic record
Abstract
Objective: This study aims to explore the lived experiences of stroke survivors engaging in AI-assisted rehabilitation. Methods and Materials: This qualitative study was conducted with 14 stroke survivors undergoing AI-assisted rehabilitation at the York Rehab Center in Richmond Hill, Canada. Participants were recruited using purposive sampling, and data collection was carried out through in-depth, semi-structured interviews. Interviews lasted 45–60 minutes and were audio-recorded, transcribed verbatim, and coded using NVivo 14 software. Thematic analysis was employed following Braun and Clarke’s six-phase framework. The study continued until theoretical saturation was achieved. Ethical considerations including informed consent and confidentiality were rigorously maintained throughout the research process. Findings: Analysis revealed four main themes: (1) Human–Technology Interaction, including trust in AI and interface usability; (2) Emotional and Psychological Response, encompassing motivation, emotional bonding with technology, and performance anxiety; (3) Perceived Effectiveness of Rehabilitation, including functional improvement, personalized feedback, and therapy comparison; and (4) Social and Institutional Context, focusing on relationships with therapists, digital equity, and cultural influences. Patients generally found the AI systems to be engaging and supportive of their physical recovery. However, emotional detachment, dependence, and accessibility challenges emerged as concerns. Participants emphasized the need for human involvement alongside AI systems to ensure emotional and motivational support. Conclusion: AI-assisted rehabilitation was perceived as a promising and effective complement to traditional therapy, enhancing functional outcomes and patient engagement. However, its full potential lies in hybrid models that integrate human empathy with technological precision.
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 | 0.007 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.007 | 0.010 |
| Scholarly communication | 0.008 | 0.006 |
| Open science | 0.002 | 0.010 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".