ARE PATIENTS WITH ROTATOR CUFF INJURIES PERFORMING AT-HOME PHYSIOTHERAPY? SMART WATCH DATA VERSUS PATIENT-REPORTED DIARIES
Bibliographic record
Abstract
Physiotherapy is an essential component of upper extremity rehabilitation programs. At-home adherence to exercise prescriptions is a determining factor in the success of physiotherapy treatment, but participation is often poor in the home setting where patients are expected to perform the majority of their exercises. Objectively determining how well a patient is participating in at-home exercise has been an ongoing challenge. Patient diaries, commonly used in research to measure participation, have been shown to have low completion rates and be subject to biases. Wearable technology provides an alternative approach to measure at-home physiotherapy participation. Previously, our team developed a Smart Physiotherapy Activity Recognition System (SPARS) which uses inertial data collected from smart watches and machine learning (ML) to objectively measure at-home participation of shoulder physiotherapy exercises. The objective of this research was to evaluate the agreement of participation measures collected by self-reported patient diaries and SPARS. Inertial data (3-axis accelerometer/gyroscope) was collected by smart watches worn by 45 patients with rotator cuff pathology as they engaged in supervised clinic and unsupervised at-home physiotherapy exercise. A convolutional neural network (CNN) was trained on labelled inertial data collected during in-clinic physiotherapy sessions to predict periods in at-home recordings where patients were engaging in physiotherapy exercise. Self-reported adherence diaries tracking daily exercise sets completed were collected during the first two weeks of physiotherapy treatment. Participation for each measure was calculated as percentage of days exercised during that two-week period. Self reported participation was also predicated on patient indication that watch was worn while performing exercises. Analysis was performed on a sample size of 34 patients after filtering for data collection issues (watch technical issues n=5/diary non-completion n=6). Figure 1 illustrates self-reported diary (red) and SPARS (blue) participation by patient. Both the diaries and SPARS indicated a high degree of participation over the 2-week period (percentage of prescribed exercise sessions completed: diaries 74%±22% and SPARS 63%±21%) with significant agreement between measures (t=4.96, p=0.000021). The Bland Altman plot shown in Figure 2 suggests that the 11% lower participation as measured by SPARS was not dependent on the overall amount of physiotherapy participation. Significant agreement was found between ML predicted at-home physiotherapy participation measures generated by SPARS and self-reported patient diary participation, with a slightly lower rate of participation indicated by the smart watch data. Diary non-compliance was also noted in 13% of participants. Issues related to wearables (11%) must also be considered in acquiring robust at-home data. Overall, SPARS was shown to be an accurate measure of participation, and may be a suitable replacement for self-reporting, especially as patient engagement declines over lengthier periods of rehabilitation. For any figures or tables, please contact the authors directly.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".