Related Experiment Video
Updated: Jun 25, 2025
06:48
Emergency Undocking in Robotic Surgery: A Simulation Curriculum
Published on: May 20, 2018
9.3K
Artificial Intelligence in Emergency Trauma Care: A Preliminary Scoping Review
Christian Angelo I Ventura1, Edward E Denton2, Jessica A David3
1Department of Health, Behavior and Society, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD USA; Department of Allied Health, Baltimore City Community College, Baltimore, MD, USA.
Medical Devices (Auckland, N.Z.)
|May 28, 2024
Summary
Generative AI shows promise in trauma care diagnostics, but requires more validation for widespread use. Gaps exist in injury scoring and real-time treatment guidance applications.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Medicine
- Trauma Surgery
Background:
- Generative Artificial Intelligence (AI) is increasingly explored for clinical applications.
- Emergency trauma care presents unique challenges requiring rapid and accurate decision-making.
- The integration of AI in trauma settings is an evolving area of research.
Purpose of the Study:
- To conduct a scoping review of generative AI applications in emergency trauma care.
- To analyze the current literature on AI's role in triage, diagnostics, and treatment.
- To identify research gaps and future directions for AI in trauma medicine.
Main Methods:
- Scoping review of literature from 2014-2024 using the NCBI repository.
- Search string utilizing selected keywords yielded 87 results; 28 articles met inclusion criteria.
- Analysis of heterogeneity using P < 0.10 or I² > 50%; categorization into triage, diagnostics, or treatment domains.
Main Results:
- Convolutional Neural Networks (CNNs) show strong diagnostic performance for traumatic injuries, needing multi-center validation.
- Injury scoring models exhibit calibration gaps in mortality prediction and lesion localization.
- Triage predictive models face barriers in transparency, explainability, and healthcare integration.
- A significant gap exists in treatment-oriented generative AI for real-time trauma intervention guidance.
Conclusions:
- Generative AI holds potential in trauma diagnostics, but clinical utility is limited by validation needs and model calibration.
- Current AI applications in triage and scoring require further development for reliable real-world translation.
- Future research should focus on developing generative AI for real-time treatment guidance in emergency trauma care.
