Supporting dispatch decisions in interfacility medical transfers: Understanding the roles of uncertainty and reliability
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
Efficient transfer of patients between facilities is a key component of regionalized critical care systems, but interfacility transfers pose added risks to patients. We created a decision support tool for dispatchers in medical transportation systems which provides estimates of the time to definitive care, the time between receiving the transfer request and patient handoff, which is a key component of dispatch decisions. This tool provides point-estimates of transfer times that are more accurate than the dispatchers own estimates, to support resource allocation and medical triage decisions. However, additional information about the uncertainty of these estimates may further improve dispatcher decision making. This paper describes an observational study conducted with 2 expert and 2 novice dispatchers in a medical transportation service on usage of our prototype decision support tool. In particular, we focused on whether these dispatchers use uncertainty information in their decision process, and how this information should be presented in a tool. We found that uncertainty, as represented by of the spread of possible transfer times (i.e., variability of times), is not currently considered by dispatchers. However, our observations suggest that reliability information (i.e., the trustworthiness of the tool's estimates) would be used. Expert dispatchers would use information about the reliability of estimates to build their trust in the system, while novices should use reliability information to calibrate their trust.
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 | 0.001 |
| 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