A deep neural network to assess spontaneous pain from mouse facial expressions
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
Grimace scales quantify characteristic facial expressions associated with spontaneous pain in rodents and other mammals. However, these scales have not been widely adopted largely because of the time and effort required for highly trained humans to manually score the images. Convoluted neural networks were recently developed that distinguish individual humans and objects in images. Here, we trained one of these networks, the InceptionV3 convolutional neural net, with a large set of human-scored mouse images. Output consists of a binary pain/no-pain assessment and a confidence score. Our automated Mouse Grimace Scale integrates these two outputs and is highly accurate (94%) at assessing the presence of pain in mice across different experimental assays. In addition, we used a novel set of "pain" and "no pain" images to show that automated Mouse Grimace Scale scores are highly correlated with human scores (Pearson's r = 0.75). Moreover, the automated Mouse Grimace Scale classified a greater proportion of images as "pain" following laparotomy surgery when compared to animals receiving a sham surgery or a post-surgical analgesic. Together, these findings suggest that the automated Mouse Grimace Scale can eliminate the need for tedious human scoring of images and provide an objective and rapid way to quantify spontaneous pain and pain relief in mice.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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) | 0.001 | 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 it