London Trauma Conference December 2022: Abstracts
Bibliographic record
Abstract
Background: Multidisciplinary mortality and morbidity review (MoM) is the core of programs that aim to improve the quality of trauma care and is used to identify and address opportunities for improvement (OFI) [1].Case selection for MoM relies heavily on audit filters, a process associated with high frequencies of false positives.The use of trauma injury scores has been proposed as an alternative, but performance is also poor [2].Our aim was to develop, validate and compare the performance of different machine learning (ML) based models for predicting opportunities for improvement.Methods: We included all trauma patients from the Karolinska University Hospital trauma registry and trauma care quality database assessed between 2014 and 2021.OFI was defined as a binary variable representing a consensus decision from the Mortality and Morbidity Conference regarding the presence of at least one OFI.The data was split into a training (80%) and test set (20%).We developed seven ML models with 45 predictors and compared the performance between models.We also compared the performance of the models with currently used audit filters.Performance was measured using AUC, accuracy and Integrated Calibration Index.A resampling approach was used to estimate confidence intervals. Results:We included 6313 patients where OFI were present in 431 (6.83%) patients.The currently used audit filters (AUC: 0. 0.627, accuracy: 0.356) was outperformed by all developed models.Our best performing model was random forest (AUC: 0.794, accuracy: 0.933, ICI: 0.028) followed by light gradient-boosting machine (AUC: 0.790, accuracy: 0.932, ICI: 0.037).Conclusions: Machine learning models outperform audit filters based on established quality indicators and could prove to be valuable additions in the screening for OFI.Further research is needed on how to further increase performance as well as how to optimally apply developed models into trauma quality programs.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.002 | 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 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".