Evaluating Mixed Reality Technology for Tracking Hand Motion for Shoulder Rehabilitation Assessment
Bibliographic record
Abstract
Shoulder injuries and conditions are common musculoskeletal complaints that can limit a patient's range of motion and daily activities. Recently, serious games and mixed reality technologies, such as the HoloLens, have been proposed for shoulder rehabilitation. However, it is unclear if this technology accurately tracks 3D hand movements for reporting therapy-related kinematic metrics. This paper presents accuracy and repeatability tests of the HoloLens 2 in tracking hand movements, and its potential for shoulder rehabilitation assessment. Comparisons were made between index fingertip, palm, and wrist movements captured by the HoloLens 2 and an Aurora electromagnetic system, which was used as the ground truth. A mixed-reality environment was developed to capture static hand positions, as well as dynamic hand movements performed during a shoulder physiotherapy-based exercise. The tracking data were used to calculate several kinematic metrics. The results show that the HoloLens 2 hand-tracking system is accurate to within a median of 10.2 mm and has repeatability comparable to the Aurora system, with the palm exhibiting the best results. The HoloLens 2 data are suitable for computing kinematic metrics for shoulder rehabilitation assessment, achieving accuracies above 86.9% for all of the tested metrics. Metrics such as time-to-speed peak and the$\log$dimensionless jerk were found to have significant differences between dynamic hand movements. These findings support the mixed reality technology potential to assist shoulder rehabilitation through immersive and interactive environments.
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 | 0.004 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".