0678 Contactless 3D Detection Of Leg Movements In Sleep
Bibliographic record
Abstract
Currently, the diagnosis of periodic leg movements during sleep (PLMS) is based on electromyography (EMG) of the tibialis anterior muscles. We analyzed leg movements by automatic 3D video analysis and compared it to detections by conventional EMG. Our video analysis system uses a novel 3D near-infrared time-of-flight sensor. The AIT software measures the height profile of the body lying in bed in high spatial and temporal resolution. Changes in this profile indicate motor events. The software assigns these events to the limbs using a dynamic human model and computes selected features in the spatial, temporal and frequency domain. In a multi-centric clinical study in Austria that was approved by ethical committees, we recorded time-synchronized video-PSG and 3D video sleep data of 41 patients presenting with nocturnal leg movements. Two experienced somnologists annotated the polysomnographic recordings by visual inspection using AASM Scoring Rules 2.4 and compared the results to leg movements automatically computed from 3D data. Out of a total of 1853 significant leg movements (sLM) seen in 3D and/or EMG, 1718 (92.7%) were detected in 3D, but only 798 (43.1%) by EMG. For the individual patient, this number varied between 9.4% and 90.7%. Overall, 135 (7.3%) sLM were missed in 3D, but detected by EMG. These did not correspond to visible movements. EMG-derived sLM qualifying for PLMS can indicate either clinically relevant movements or muscle contractions without visible movements. On the other hand, leg movements caused by other than the tibialis anterior muscles are missed in standard PSG recordings, but are visible in 3D. In such cases, 3D video somnography provides more complete and additional diagnostic data as compared to conventional EMG. Depending on the patient, counting sLM of tibialis anterior muscles poses a very unequal measure to individuals. A substantial advantage of the 3D technology is the no-touch approach: It avoids poor electrode contacts, enables undisturbed sleep and facilitates the procedure of mounting, (re)adjusting and removing electrodes. This study was sponsored in parts by Wirtschaftsagentur Wien, ZIT project ID 1035740.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".