Evaluation of Policy Capturing to Model Judgements of Medical Experts for Triage Applications
Bibliographic record
Abstract
The possibility to automate medical triage is appealing as it could decrease the burden on humans. In instances of mass casualty events, this could allow for much faster triage as the process would occur in parallel instead of in sequence. The greatest efficacy could be achieved with a system that relies solely on remote sensors, which would necessitate an adaptation of existing triage algorithms that rely on human observations. A policy capturing method is proposed to demonstrate the possibility to mimic medical experts’ decision-making model of triage based only on observable parameters sampled by wearables: heart rate, respiration rate, heart rate variability, and blood oxygen saturation. Two medical experts classified simulated cases from these five parameters and sex in regards of four potential outcomes: Delayed green, Urgent yellow, Immediate red, or Expectant black. Seven model types were trained to replicate the decision pattern of the experts. Overall, the decision pattern was best captured by a decision tree (test set accuracy of 92% and 76% for Raters 1 and 2, respectively). Interestingly, common physiological differences were found across the four classifications for both experts. The model was optimized during a workshop with the experts. We discuss the implications of using such a model to support medical triage, especially for military contexts.
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 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) | 0.000 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".