Classification of traumatic brain injury severity using retrospective data
Bibliographic record
Abstract
Objective: Accurate classification of traumatic brain injury (TBI) severity is essential to brain injury research. TBI heterogeneity complicates classification of the injury; is a significant barrier in the design of therapeutic interventions; and results in retrospective data which is difficult to translate. The objective of this study is to describe the differences in two current tools used in the classification of TBI severity, the Glasgow Coma Scale (GCS) and the head Abbreviated Injury Score (AIS), using retrospective data to compare their performance.Methods: Using correlational and descriptive statistics, this study examined two TBI severity classification methods across a large sample of TBI patients (N = 56,131), who were treated at level I and level II trauma centers in the United States and were included in the 2010 National Sample Program (NSP) of the National Trauma Data Bank (NTDB®).Results: The study population was 67% male, 67% non-Hispanic white, treated most often in trauma centers in the South (38%), with blunt trauma (93%) and from non-motor vehicle collisions (MVC’s) (56%). Observation of the AIS classification system demonstrated that it tends to over-score TBI severity compared to the GCS classification. The methods (GCS & AIS) had a weak, inverse relationship with a correlation coefficient (Pearson’s r) of -0.3980, which was significant at p < .001.Conclusions: The current study addressed the difficulties associated with categorizing TBI severity when analyzing retrospective data. Although AIS is commonly used to classify severity in retrospective data when GCS is unavailable, the relationship between the two scales is relatively unknown. Results show that AIS and GCS are more closely related for severely brain injured patients but in cases of mild and moderate injury, AIS is less predictive of GCS. Since they are often used in conjunction in identifying brain injured severity in retrospective data, researchers cannot be certain that the tools are similarly classifying mild, moderate, and severe injuries. This study reinforces the need for additional TBI severity classification methods, such as neuroimaging techniques and biomarkers.
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 | 0.023 | 0.073 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".