Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 13, 2026

A Detailed Protocol for Physiological Parameters Acquisition and Analysis in Neurosurgical Critical Patients
05:01

A Detailed Protocol for Physiological Parameters Acquisition and Analysis in Neurosurgical Critical Patients

Published on: October 17, 2017

7.4K

Prehospital real-time AI for trauma mortality prediction: a multi-institutional and multi-national validation study.

Na-Eun Oh1,2, Thomas Young-Chul Oh3, Jeremy Hsu3

  • 1Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin, Republic of Korea.

Nature Communications
|January 7, 2026
PubMed

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An Affordable Artificial Intelligence Solution for Intelligent Document Processing of Faxed Documents.

NEJM catalyst innovations in care delivery·2026
Same author

Sex-specific burden of osteoarthritis and rheumatoid arthritis across Asia, 1990-2023: a Global Burden of Disease Study 2023.

Clinical rheumatology·2026
Same author

Maternal Diabetes and Subsequent Risk of Asthma and Atopic Dermatitis in Offspring: A Binational Birth Cohort Study in South Korea and Japan.

Clinical and experimental allergy : journal of the British Society for Allergy and Clinical Immunology·2026
Same author

Global, Regional, and National Burden of Liver Cancer from 1990 to 2021 and Projections to 2050: A Global Burden of Disease Study 2021.

Gut and liver·2026
Same author

Prenatal Opioid Exposure and Subsequent Risk of Fractures in Children: An Emulated Target Trial Using a Nationwide Birth Cohort.

Indian pediatrics·2026
Same author

Author Correction: Global burden of amphetamine, cannabis, cocaine and opioid use in 204 countries, 1990-2023: a Global Burden of Disease Study.

Nature medicine·2026
Summary

A new AI model accurately predicts emergency room mortality in trauma patients using prehospital data. This advanced tool enhances trauma care efficiency and patient survival by enabling early risk assessment.

Area of Science:

  • Emergency Medicine
  • Artificial Intelligence
  • Data Science

Background:

  • Early identification of high-risk trauma patients pre-hospital is critical for resource allocation and survival.
  • Traditional triage tools often lack accuracy in predicting patient outcomes.

Purpose of the Study:

  • To develop and validate a real-time Artificial Intelligence (AI) model for predicting emergency room mortality in trauma patients.
  • To compare the AI model's performance against traditional triage methods.

Main Methods:

  • Developed an AI model using ensemble methods (XGBoost, LightGBM, random forest) with 21 prehospital variables.
  • Utilized the Korean Trauma Data Bank (KTDB) for model development and internal validation.
  • Externally validated the model across multiple South Korean and one Australian trauma centers.

More Related Videos

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K

Related Experiment Videos

Last Updated: Jan 13, 2026

A Detailed Protocol for Physiological Parameters Acquisition and Analysis in Neurosurgical Critical Patients
05:01

A Detailed Protocol for Physiological Parameters Acquisition and Analysis in Neurosurgical Critical Patients

Published on: October 17, 2017

7.4K
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K

Main Results:

  • The Prehospital-AI model achieved an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.923 on the test set.
  • The AI model significantly outperformed the shock index (AUROC: 0.712).
  • External validation demonstrated high AUROCs (0.895-0.956) across diverse international centers.

Conclusions:

  • The Prehospital-AI model provides accurate, real-time risk assessment in the prehospital setting.
  • This AI tool improves trauma system efficiency and outperforms existing triage methods.
  • Further multinational studies are recommended to confirm generalizability across varied trauma care systems.