Proof-of-Concept Study: a Mobile Application to Derive Clinical Outcome Measures from Expression and Speech for Mental Health Status Evaluation
Bibliographic record
Abstract
This proof-of-concept study aimed to assess the ability of a mobile application and cloud analytics software solution to extract facial expression information from participant selfie videos. This is one component of a solution aimed at extracting possible health outcome measures based on expression, voice acoustics and speech sentiment from video diary data provided by patients. Forty healthy volunteers viewed 21 validated images from the International Affective Picture System database through a mobile app which simultaneously captured video footage of their face using the selfie camera. Images were intended to be associated with the following emotional responses: anger, disgust, sadness, contempt, fear, surprise and happiness. Both valence and arousal scores estimated from the video footage associated with each image were adequate predictors of the IAPS image scores (p < 0.001 and p = 0.04 respectively). 12.2% of images were categorised as containing a positive expression response in line with the target expression; with happiness and sadness responses providing the greatest frequency of responders: 41.0% and 21.4% respectively. 71.2% of images were associated with no change in expression. This proof-of-concept study provides early encouraging findings that changes in facial expression can be detected when they exist. Combined with voice acoustical measures and speech sentiment analysis, this may lead to novel measures of health status in patients using a video diary in indications including depression, schizophrenia, autism spectrum disorder and PTSD amongst other conditions.
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 | 0.004 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".