Development and validation of PainFace, a software platform that simplifies and standardizes mouse grimace analyses
Bibliographic record
Abstract
Abstract Facial grimaces are now commonly used to quantify spontaneous pain in mice and other mammalian species, but scoring remains subjective and relies on humans with very different levels of proficiency. Here, we developed a Mouse Grimace Scale (MGS) for black-coated (C57BL/6) mice consisting of four facial action units (orbitals, nose, ears, whiskers). We used this scale to generate ground truth data from over 70,000 images of black mice in different settings. With this large data set, we developed a deep neural network and cloud-based software platform called PainFace ( http://painface.net ) that accurately scores facial grimaces of black mice on a 0–8 scale. PainFace generates over two orders of magnitude more MGS data than humans can realistically achieve, and at superhuman speed. By analyzing the frequency distribution of grimace scores, we found that mice spent >7x more time in a high grimace state following laparotomy surgery relative to sham surgery controls. The analgesic carprofen reduced the amount of time animals spent in this high grimace state after surgery. Specific facial action unit score combinations were overrepresented following laparotomy surgery, suggesting that characteristic facial expressions are associated with a high grimace state. We performed validation experiments in two labs located in different countries to demonstrate reproducibility of the PainFace platform. To further enhance rigor and reproducibility, we will invite pain researchers to beta test PainFace and then incorporate their feedback into the software and manuscript prior to peer review. While this study is focused on mice, PainFace was designed to simplify, standardize, and scale up grimace analyses with many other mammalian species, including humans.
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 | 0.005 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".