A scoping review of artificial intelligence in acute care surgerypromise, pitfalls, and a path forward
Bibliographic record
Abstract
BACKGROUND: Acute care surgery (ACS) faces unique challenges due to time-sensitive decisions, high diagnostic variability, and complex patient data. Artificial Intelligence (AI) offers potential solutions, yet the breadth, focus, safety, and translational readiness of current AI applications in ACS remain unclear. METHODS: A scoping review was conducted in PubMed, Scopus, and IEEE Xplore databases for peer-reviewed articles published 2015-2025. Data extraction included model architecture, data source, temporal and functional classifications, performance metrics, external validation, explainability, and risk of bias among others. Descriptive statistics and thematic synthesis were performed. RESULTS: Forty-nine studies describing 341 AI models were included. Most models (69.5%) originated from North America and primarily targeted preoperative prognostic tasks (76.5%). Large-scale registries (46.6%) and single-center studies (33.4%) were the primary data sources, and structured electronic health record data were predominantly used (91.5%), with minimal multimodal data integration. All models underwent internal validation, whereas external validation (20.2%), fairness assessments (3.2%), regulatory approval (0.2%), and adherence to standard reporting guidelines (34.3%) were limited. Model performance varied, with mean±SD (range): sensitivity 71.3±24.2% (10-100%), specificity 81.5±18.7% (5-100%), and AUROC 0.83± 0.11 (0.45-0.99) across studies. CONCLUSION: While AI holds promise for enhancing ACS, current applications are narrowly focused on pre-operative risk prediction using limited data modalities. Future efforts must prioritize prospective validation, real-time dynamic predictions, clinician-centered design, and multimodal data integration to realize AI's potential for improving ACS patient outcomes in time-sensitive, high-acuity surgical settings.
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 | 0.000 |
| 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) | 0.000 | 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".