오영철 (University of Sydney) | 한빛사논문 > 한빛사

한빛사논문

조회59

University of Sydney

Nat. Commun., Jan 07 2026, | https://doi.org/10.1038/s41467-025-68198-y Prehospital real-time AI for trauma mortality prediction: a multi-institutional and multi-national validation study

Na-eun Oh^1,†, Thomas Young-Chul Oh, MBBS, FRACS^2,†, Jeremy Hsu, BPharm, MBBS (Hons), DClinSurg, FRACS, FACS², Do Wan Kim, MD³, Byungchul Yu, MD⁴, Jayun Cho, MD⁵, Junepill Seok, MD^6,7, Jin Young Lee^8,9,10, Woocheol Jang¹, Jina Kim¹, Robert J. Femia, MD^11,12, Paul A. Testa, MD^11,12, Dong Keon Yon, MD, PhD, FAAAAI, FACAAI, ATSF^13,14, Daniel K Sodickson, MD, PhD^15,16, Wu Seong Kang, MD, PhD^{17,18 *}, and Jinseok Lee, PhD^{1, *}

¹Department of Biomedical Engineering, Kyung Hee University, Yongin, Republic of Korea
²Trauma Service, Westmead Hospital, University of Sydney, NSW, Australia
³Department of Thoracic and Cardiovascular Surgery, Chonnam National University Hospital and Chonnam National University Medical School, Gwangju, Republic of Korea
⁴Traumatology, Gachon University College of Medicine, Department of trauma surgery, Gachon University Gil Medical Center, Incheon, Republic of Korea
⁵Department of Trauma Surgery, Gachon University Gil Medical Center, Incheon, Republic of Korea
⁶Department of Thoracic and Cardiovascular Surgery, Chungbuk National University Hospital, Cheongju, Republic of Korea
⁷Department of Thoracic and Cardiovascular Surgery, Chungbuk National University, College of Medicine, Cheongju, Republic of Korea
⁸Department of Trauma Surgery, Chungbuk National University Hospital, Cheongju, Republic of Korea
⁹Present affiliation: Division of Acute Care Surgery, Department of Surgery, Korea University Guro Hospital, Seoul, Republic of Korea
¹⁰Present affiliation: Trauma Center, Armed Forces Capital Hospital, Seongnam, Republic of Korea
¹¹Department of Emergency Medicine, New York University Grossman School of Medicine, New York, New York, USA.
¹²Bellevue Hospital Center, Department of Emergency Medicine, New York, New York.
¹³Center for Digital Health, Medical Science Research Institute, Kyung Hee University College of Medicine, Seoul, South Korea
¹⁴Department of Pediatrics, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea.
¹⁵Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA.
¹⁶Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA.
¹⁷Department of Trauma Surgery, Jeju Regional Trauma Center, Cheju Halla General Hospital, Jeju, Republic of Korea
¹⁸Present affiliation: Department of Trauma Surgery, Gachon University Gil Medical Center, Incheon, Republic of Korea

^†These authors contributed equally to this work: Na-eun Oh, and Thomas Young-Chul Oh
^*These authors jointly supervised this work: Wu Seong Kang, and Jinseok Lee\
Corresponding authors: Wu Seong Kang, MD, PhD And, Jinseok Lee, PhD

Abstract

Early identification of high-risk trauma patients in the prehospital setting is crucial for optimizing resource allocation and improving survival. We developed and externally validated a real-time AI model predicting emergency room mortality using 21 prehospital variables. Model development and internal validation utilized the Korean Trauma Data Bank (KTDB; 204,189 patients), and external validation included four South Korean trauma centers (8,358 patients) and one Australian Level 1 center (3,578 patients). Our Prehospital-AI model, an ensemble of XGBoost, LightGBM, and random forest, achieved an AUROC of 0.923 (sensitivity: 0.780, specificity: 0.880) on the test set, outperforming the shock index (AUROC: 0.712). External validation yielded AUROCs of 0.925-0.956 across South Korean centers and 0.895 in the Australian center. Here we show that the Prehospital-AI model enables accurate, real-time risk assessment in the prehospital setting, outperforming traditional triage tools and improving trauma system efficiency. Nonetheless, additional multinational studies are warranted to further evaluate its generalizability across diverse trauma care systems.

논문정보