Emergency severity index version 4 during the first year of implementation at an academic institution
Bibliographic record
Abstract
Background: The Emergency Severity Index (ESI) version 4 (v4) is a triage system based on vital signs, potential limb or organthreat, as well as expected resources needed in the emergency department (ED).Objective: The purpose of this study was to examine accuracy and misclassification rate of ESI triage over one year following implementation.Methods: This was a retrospective analysis of ED encounters from January 2011 to 2012. Charts were selected in one-week intervals every 12 weeks for one year (months 1, 3, 6, 9, and 12). Each encounter was reviewed to determine post hoc ESI level based on care in the ED. Descriptive statistics was used to compare the agreement between initial triage and post hoc ESI levels. Sensitivity and specificity for each level was determined. Kruskal Wallis test (KW) and Mann Whitney U (MWU) was used toassess differences in initial versus post hoc ESI levels by month to explore change in accuracy over time.Results: Five hundred and sixty separate ED encounters were included. Agreement was observed in 301 triage encounters (53.8%). Overestimation of the triage level occurred in 131 (23.4%) encounters, while the triage level was underestimated in 128 (22.9%) encounters. There was a significant decline in accuracy during the year (KW = 10.2; p = .037); with the greatest dropbetween month 1 and 9 months (MWU 4,859; p = .035). Sensitivity ranged from 24% to 76% and specificity ranged from 61% to 99%, based on ESI level.Conclusions: Enhanced education and quality improvement process is necessary to improve overall accuracy rates at this site.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.031 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".