Feasibility Analysis of FaceADE: A Mobile Tool for Real-Time, Objective Assessment of Facial Paralysis (Preprint)
Bibliographic record
Abstract
BACKGROUND: Patients with facial paralysis require detailed clinical assessment and long-term follow-up to monitor facial function. The current standard of care for evaluating facial symmetry and movement uses validated clinician scoring tools such as the House-Brackmann facial paralysis score or the Electronic Clinician-Graded Facial Function Scale (eFACE). Existing tools are difficult to use in normal clinic workflows and do not provide real-time facial movement tracking, representing an unmet need. Therefore, we developed FaceADE, a novel iOS app leveraging native 3D image acquisition capabilities on the iPhone to rapidly quantify facial movement in patients with facial paralysis. OBJECTIVE: This study aimed to benchmark FaceADE against 2D image analysis and establish the feasibility of measuring oral commissure movement in patients with facial paralysis and healthy controls. METHODS: Patients were enrolled in a tertiary care clinic focused on facial paralysis treatment. Patients underwent image capture using the FaceADE app assisted by study team personnel. Measurements of lip commissure position and movement were obtained from 20 patients with facial paralysis and 10 healthy volunteers without facial paralysis. Measurements of lip movement and symmetry gathered from FaceADE were benchmarked against 2D measurements using open-source image analysis software (ImageJ). RESULTS: FaceADE measurements of lip commissure position and movement showed strong agreement with 2D measurements in both healthy volunteer and facial paralysis cohorts. The intraclass correlation coefficient was 0.96 (95% CI 0.90-0.98; P<.001) in the healthy volunteer cohort and 0.82 (95% CI 0.72-0.88; P<.001) in the facial paralysis cohort. Bland-Altman analysis found strong agreement between the 2 methods for these measurements. The 95% CI contained 97.5% (39/40) of data points in the healthy cohort and 91.2% (73/80) of data points in the facial paralysis cohort. CONCLUSIONS: Our proposed mobile method of measuring clinically important lip commissure position and movement is feasible for use at the time of care delivery. In the future, this technology may be useful for a quantitative assessment of facial paralysis severity.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.006 |
| Science and technology studies | 0.000 | 0.001 |
| 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".