Assessing the Performance of a Novel Bayesian Algorithm at Point of Care for Red Eye Complaints
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
The current diagnostic aids for red eye are static flowcharts that do not provide dynamic, stepwise workups. The diagnostic accuracy of a novel dynamic Bayesian algorithm for red eye was tested. Fifty-seven patients with red eye were evaluated by an emergency medicine physician who completed a questionnaire about symptoms/findings (without requiring extensive slit lamp findings). An ophthalmologist then attributed an independent “gold-standard diagnosis”. The algorithm used questionnaire data to suggest a differential diagnosis. The referrer’s diagnostic accuracy was 70.2%, while the algorithm’s accuracy was 68.4%, increasing to 75.4% with the algorithm’s top two diagnoses included and 80.7% with the top three included. In urgent cases of red eye (n = 26), the referrer diagnostic accuracy was 76.9%, while the algorithm’s top diagnosis was 73.1% accurate, increasing to 84.6% (top two included) and 88.5% (top three included). The algorithm’s sensitivity for urgent cases was 76.9% (95% CI: 56–91%) using its top diagnosis, with a specificity of 93.6% (95% CI: 79–99%). This novel algorithm provides dynamic workups using clinical symptoms, and may be used as an adjunct to clinical judgement for triaging the urgency of ocular causes of red eye.
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 | 0.000 | 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) | 0.000 | 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