Measuring Repositioning in Home Care for Pressure Injury Prevention and Management
Bibliographic record
Abstract
Abstract A critical best practice for prevention and management of pressure injuries is regularly repositioning individuals who are at risk of these injuries are when they are in bed. However, despite the widespread agreement of the need for regular repositioning (typically every two hours), adherence to repositioning schedules remains poor in the clinical environment and there are some indications that the situation in home environment is even worse. Our team has recently developed a non-contact system that can continuously determine an individual’s position in bed (left-side lying, right-side lying or supine) using data from a set of inexpensive load cells placed under the bed frame. A proof of principle study showed that our system was able to detect whether healthy participants were supine, left-side lying or right-side lying with 94.2% accuracy in the lab environment. The objective of the present work was to deploy our system into the home environment to evaluate how well the system was able to detect the position of individuals sleeping in their own beds overnight by comparing to ground truth time-lapse camera images using eight machine learning classifiers. Nine participants were recruited for this study and we found our system was able to detect an individual’s position in bed with 98.1% accuracy and an F1 score of 0.982 using the XGBoost classifier. Future work will include using this system to evaluate interventions focused on improving adherence to 2-hour repositioning schedules for pressure injury prevention or management as well as incorporating this technology in a repositioning prompting system to alert caregiver when a patient has remained in the same position for too long.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.003 |
| Research integrity | 0.000 | 0.001 |
| 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".