P.177 Artificial intelligence-based outcome prediction for moderate to severe traumatic brain injury: a systematic review and methodological appraisal
Bibliographic record
Abstract
Background: Artificial intelligence (AI) holds promise to predict outcomes for patients sustaining moderate to severe traumatic brain injury (msTBI). This systematic review sought to identify studies utilizing AI-based methods to predict mortality and functional outcomes after msTBI, where prognostic uncertainty is highest. Methods: The APPRAISE-AI quantitative evidence appraisal tool was used to evaluate methodological quality of included studies by determining overall scores and domain-specific scores. We constructed a multivariable linear regression model using study sample size, country of data collection, publication year and journal impact factor to quantify associations with overall APPRAISE-AI scores. Results: We identified 38 studies comprising 591,234 patients with msTBI. Median APPRAISE-AI score was 45.5 (/100 points), corresponding to moderate study quality. There were 13 low-quality studies (34%) and only 5 high-quality studies (13%). Weakest domains were methodological conduct, robustness of results and reproducibility. Multivariable linear regression highlighted that higher journal impact factor, larger sample size, more recent publication year and use of data that were collected in a high-income country were associated with higher APPRAISE-AI overall scores. Conclusions: We identified several study weaknesses of existing AI-based prediction models for msTBI; this work highlights methodological domains that require quality improvement to ultimately ensure safety and effiicacy of clinical AI models.
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 | 0.049 | 0.196 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.007 | 0.010 |
| Bibliometrics | 0.013 | 0.014 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.005 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
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".