Proof-of-Concept Study: a Mobile Application to Derive Clinical Outcome Measures from Expression and Speech for Mental Health Status Evaluation
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
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.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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 it