Eyeballing: the use of visual appearance to diagnose ‘sick’
Bibliographic record
Abstract
CONTEXT: Prior studies suggest that clinicians can categorise patients in an emergency room as 'sick' or 'not sick' using rapid visual assessment. The rapid nature of these decisions suggests clinicians are relying on pattern recognition or System 1 processing; however, this has not been studied experimentally. In this study, we explore the accuracy of these decisions using patient disposition (discharge, admission to ward or admission to critical care) as an objective outcome, and collect evidence to argue for the use of System 1 processing in the 'sick' or 'not sick' decision process. METHODS: Fourteen practising emergency physicians reviewed 25 videos of patients presenting to the emergency room. They were asked to predict patient disposition (discharge, admission to ward or admission to critical care) and estimate whether they were 'sick' or 'not sick' using a continuous slider on a 'sick' scale from 'not sick' (0) to 'sick' (100). We collected decision time and asked physicians to identify how they came to the decision using a continuous slider on a 'system processing' scale from 'knew immediately' (0) to 'deliberated intently' (1). RESULTS: Inter-rater reliability judging 'sick' was computed as an intraclass correlation coefficient (ICC) of 0.54. Agreement among physicians in predicting disposition was 68% with ICC of 0.44, and accuracy at predicting disposition was 55%. Physicians made their decision in an average of 10 - 11 seconds and rated 70% of their decisions as < 0.5 on the scale from 'knew immediately' (0) to 'deliberated intently' (1). CONCLUSIONS: Experienced emergency physicians are able to visually assess patients rapidly and predict disposition in a very short time, albeit with fair reliability and lower accuracy than reported previously. Subjectively, they reported that the majority of decisions were on the side of 'knew immediately', consistent with the application of System 1 processing.
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 | 0.000 | 0.307 |
| 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".