Assessment of a biometric shirt for sleep body position identification in epilepsy
Bibliographic record
Abstract
Background: Patients with uncontrolled epilepsy are at increased risk of sudden unexpected death in epilepsy (SUDEP). Evidence suggests that sleeping prone or being in a prone position after a seizure may increase the risk of SUDEP. A few wearable devices have the potential to track sleeping habits. These devices could eventually be used to screen patients with epilepsy with a tendency to sleep in a prone position, allowing interventions such as sleep training to influence an ideal sleep position. Additionally, they could continuously monitor body positioning, allowing for responsive alarms and/or interventions when necessary. In this study, we prospectively assessed the accuracy of the Hexoskin biometric shirt algorithm in identifying sleep body positions. Methods: Patients were recruited at the University of Montreal Health Center (CHUM) epilepsy monitoring unit and were asked to wear the Hexoskin biometric shirt. A built-in algorithm identified prone, supine, right, left, or sitting/standing body positions using an accelerometer. Sleeping positions predicted by the algorithm were compared to "true" values collected via blind simultaneous video analysis. Results: Across 10 patients and 347 h of sleep analyzed, 65% of prone, 75% of supine, 94% of right lateral decubitus, 81% of left lateral decubitus, and 65% of sitting/standing positions were correctly classified by the Hexoskin algorithm. Balanced accuracy was 0.76 and weighted F1-score was 0.85. Conclusion: Our results show promise in the use of the Hexoskin shirt for detecting sleep positions. Optimizing performance in identifying prone sleep could enhance its clinical utility for monitoring patients with epilepsy.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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".