Evaluating the Performance of Trauma Centers: Hierarchical Modeling Should be Used
Bibliographic record
Abstract
BACKGROUND: Comparing trauma centers in terms of patient survival is a key element of performance evaluation. The current standard in trauma center profiling is based on Ordinary Logistic Regression (OLR). However, OLR does not take account of the hierarchical structure of trauma systems. Hierarchical Logistic Regression (HLR) accounts for the clustering of patients within hospitals and is therefore more theoretically appropriate. The objective of this study was to evaluate whether HLR generates different profiling results than OLR. METHODS: The study was based on the Quebec Trauma Registry with mandatory participation of all 59 designated trauma centers in the province of Quebec, uniform inclusion criteria, and standardized data collection methods. Trauma profiling was based on adjusted odds ratios, which represent the odds that a patient will die in a specific hospital compared with an "average" hospital. Risk adjustment was performed with the Trauma Risk Adjustment Model score. Hospitals were ranked according to odds ratio, and outliers were identified by comparing each hospital with all other hospitals. Hospital ranks and statistical outliers generated by OLR and HLR were compared. RESULTS: The study population comprised 83,504 patients including 4,731 hospital deaths (5.7%). OLR identified 11 hospitals as statistical outliers whereas HLR flagged only four of these hospitals as outliers. In addition, 54 of 59 hospitals changed ranks and 24 hospitals changed by more than five ranks when HLR replaced OLR. CONCLUSIONS: This study shows that replacing OLR with HLR has an important impact on the results of hospital profiling. Along with the many theoretical advantages of HLR, these results support the adoption of hierarchical modeling as the standard method for trauma center profiling.
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 | 0.048 | 0.148 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".