All Issue

2026 Vol.22, Issue 3 Preview Page

Original Article

A Conceptual Model of CARS Digital Triage for CBRNe Disaster Decision Support: An Edge AI-Based Autonomous Triage Framework

CBRNe 재난 의사결정 지원을 위한 CARS Digital Triage 개념 모델 제안: 엣지 AI 기반 자율 트리아지 프레임워크

이종태1ㆍ김푸름2ㆍ송창영3*

Jongtae Lee1, Pureum Kim2, Changyoung Song3*

1Graduate student, Department of Disaster Prevention and Safety, Gwangju University, Gwangju,Republic of Korea
2Researcher, College of Medicine, Chonnam National University, Gwangju, Republic of Korea
3Professor, Department of Disaster Prevention and Safety, Gwangju University, Gwangju,Republic of Korea
30 September 2026. pp. 783-793
PDF Citation
Abstract
Purpose: This study proposes a conceptual model of the CARS (CBRNe Advanced Response System) Digital Triage system by integrating multi-dimensional sensor data fusion with edge AI. The model supports medical decision-making during the golden hour of CBRNe disaster response. Methods: We defined a data acquisition layer encompassing CBRNe hazardous agents, environmental parameters, vital signs, and location/exposure information. We also designed an edge preprocessing pipeline based on selective Kalman filtering and sensor health–driven robust data fusion. Introducing an MCU+NPU dual-core edge processing unit using lightweight DNN/LSTM models enabled on-device inference and continuous re-triage algorithms. Lastly, we examined the validity of the conceptual architecture through a review of prior research on disaster medicine, edge computing, and sensor fault detection. Results: Conceptual analysis and literature review suggest that the proposed model can autonomously perform on-device digital triage on the smart PPE endpoint even in the event of partial or complete communication infrastructure failure. Compared with conventional static triage protocols, it has the potential to reduce under-triage, improve the accuracy of severity classification, and enhance the efficiency of medical resource allocation. Conclusions: This study presents a novel digital triage framework for CBRNe disaster response that integrates sensor health monitoring, selective Kalman filter–based multi-sensor fusion, and edge AI, thereby offering academic and practical implications for disaster medicine decision support. Future work should include training and validating AI models with real CBRNe scenario data and implementing hardware prototypes to evaluate performance and safety in clinical and field environments.
Keywords
CBRNe Disaster
Digital Triage
Multi-sensor Data Fusion
Sensor Health Monitoring
Selective Kalman Filtering
MCU+NPU edge AI
On-device Inference
Dynamic re-triage
Smart PPE
Disaster Medicine Decision Support
연구목적: 본 연구는 CBRNe 재난 현장의 골든아워 내 의사결정 지원을 위해, 다차원 센서 데이터 융합과 엣지 AI를 결합한 CARS (CBRNe Advanced Response System) Digital Triage 의 개념 모델을 제안하는 것을 목적으로 한다. 연구방법: CBRNe 유해물질, 환경, 생체신호, 위치·노출 정보로 구성된 데이터 수집 계층을 정의하고, 선택적 칼만 필터와 센서 건강도 기반 로버스트 융합으로 구성된 엣지 전처리 파이프라인을 설계하였다. 또한 , MCU+NPU 듀얼 코어 구조의 엣지 프로세싱 유닛을 도입하여 온디바이스 추론이 가능한 경량 DNN/LSTM 모델과 연속 재분류(continuous re‑triage) 알고리즘을 설계하고, 기존 재난의학·엣지컴퓨팅·센서 결함 탐지 선행연구를 바탕으로 개념 모델의 타당성을 검토하였다. 연구결과: 개념적 분석과 선행연구 고찰 결과, 본 연구에서 제안한 모델은 통신 인프라 붕괴 상황에서도 스마트PPE 단말 수준에서 외부에 의존하지 않고 자체적으로 디지털 트리아지를 수행할 수 있는 구조적 가능성을 보여주었다. 또한 기존의 정적 프로토콜에 비해 under-triage 감소, 중증도 분류의 강건성 향상, 의료 자원 배분 효율 증대에 기여할 잠재력이 있는 것으로 판단된다. 결론: 본 연구는 CBRNe 재난 대응에서 센서 건강도 모니터링, 선택적 칼만 필터 기반 다중 센서 융합, 엣지AI를 통합한 새로운 디지털 트리아지 개념 모델을 제시하였다는 점에서 학술적·실무적 의의를 가진다. 향후에는 실제 CBRNe 상황 데이터를 활용한 모델 학습 및 검증, 하드웨어 프로토타입 구현, 그리고 임상 및 현장 환경에서의 성능·안전성 평가가 필요하다.
키워드
CBRNe 재난
디지털 트리아지
다중 센서 데이터 융합
센서 건강도 모니터링
선택적 칼만 필터
MCU+NPU 엣지 AI
온디바이스 추론
동적 재분류
스마트 PPE
재난의학 의사결정 지원
References
  1. Alnuaimi, M.K.(2025). “Integrating wearable sensor data with an AI-based, protocol-flexible triage platform to accelerate decision-making during the golden hour of combat casualty care.” Cureus, Vol. 17, No. 8. 10.7759/cureus.91121 41018348 PMC12467467
  2. Angelucci, A., Greco, M., Cecconi, M., Aliverti, A. (2025). “Wearable devices for patient monitoring in the intensive care unit.” Intensive Care Medicine Experimental, Vol .13 No. 1, pp. 26. 10.1186/s40635-025-00738-8 40016479 PMC11868008
  3. ASPR TRACIE (2019). Mass Casualty Trauma Triage: Paradigms And Pitfalls. U.S. Department of Health and Human Services, white paper.
  4. Chen, M., Li, W., Hao, Y., Qian, Y., Humar, I. (2018). “Edge cognitive computing based smart healthcare system.” Future Generation Computer Systems, Vol. 86, pp. 403-411. 10.1016/j.future.2018.03.054
  5. Cone, D.C., MacMillan, D.S. (2005). “Mass-casualty triage systems: a hint of science.” Annals of Emergency Medicine, Vol. 46, No. 3, pp. 239-241.
  6. Fang, H., Haile, M.A., Wang, Y. (2018). “Robustifying the Kalman filter against measurement outliers: An innovation saturation mechanism.” In 2018 IEEE Conference on Decision and Control (CDC), Miami, Florida, USA, pp. 6902-6907. 10.1109/CDC.2018.8619140
  7. Franc, J., Kirkland, S., Wisnesky, U., Campbell, S., Rowe, B.H. (2022). “METASTART: A systematic review and meta-analysis of the diagnostic accuracy of the simple triage and rapid treatment (START) algorithm for disaster triage.” Prehospital and Disaster Medicine, Vol. 37, No. 1, pp. 106-116. 10.1017/S1049023X2100131X
  8. Gaddam, A., Wilkin, T., Angelova, M., Gaddam, J. (2020). “Detecting sensor faults, anomalies and outliers in the Internet of Things: A survey on the challenges and solutions.” Sensors, Vol. 20, No. 18, pp. 5126. 10.3390/electronics9030511
  9. Gao, B., Chang, G., Wang, W., Zhang, S. (2021). “Multi-sensor data fusion based on adaptive Kalman filtering.” IEEE Access, Vol. 9, pp. 147370-147381.
  10. Hick, J.L., Barbera, J.A., Kelen, G.D. (2009). “Refining surge capacity: conventional, contingency, and crisis capacity.” Disaster Medicine and Public Health Preparedness, Vol. 3, Suppl 1, S59-S67. 10.1097/DMP.0b013e31819f1ae2
  11. Hogan, D.E., Waeckerle, J.F. (1999). “Emergency department impact of the Oklahoma City terrorist bombing.” Annals of Emergency Medicine, Vol. 34, No. 2, pp. 160-167. 10.1016/S0196-0644(99)70224-6
  12. Kahn, C.A., Schultz, C.H., Miller, K.T., Anderson, C.L. (2009). “Does START triage work? An outcomes assessment after a disaster.” Annals of Emergency Medicine, Vol.54, No.3, pp. 424-430. 10.1016/j.annemergmed.2008.12.035
  13. Keim, M.E., Kaufmann, A.F. (1999). “Principles for emergency response to bioterrorism.” Annals of Emergency Medicine, Vol. 34, No. 2, pp. 177-182. 10.1016/S0196-0644(99)70227-1
  14. Krylova, S., Schmidt, F., Vlassov, V. (2024). “Leveraging machine learning models to predict the outcome of digital medical triage interviews.” IEEE Access Vol. 12, pp. 117768-117781. 10.1109/ICMLA61862.2024.00028
  15. Lerner, E.B., Moscati, R.M. (2001). “The golden hour: scientific fact or medical ‘urban legend’?” Academic Emergency Medicine, Vol. 8, No. 7, pp. 758-760.
  16. Macintyre, A.G., Christopher, G.W., Eitzen, E., Jr, Gum, R., Person, S., Seitz, C., Weiner, A.S. (2000). “Weapons of mass destruction events with contaminated casualties: Effective planning for health care facilities.” JAMA, Vol. 283, No. 2, pp. 242-249. 10.1001/jama.283.2.242
  17. Okumura, T., Suzuki, K., Fukuda, A., Kohama, A., Takasu, N., Ishimatsu, S., Hinohara, S. (1998). “The Tokyo subway sarin attack: disaster management, Part 1: Community emergency response.” Academic Emergency Medicine, Vol. 5, No. 6, pp. 613-617. 10.1111/j.1553-2712.1998.tb02470.x
  18. Park, B., Cho, N. (2023). “Reinforcement learning model for mass casualty triage taking into account the medical capability.” Journal of the Society of Disaster Information, Vol 19, No. 1, pp. 44-59. 10.15683/KOSDI.2023.3.31.044
  19. Pourasghar, F., Daemi, A., Tabrizi, J.S., Ala, A. (2015). “Inter-rater reliability of triages performed by the electronic triage system.” Bulletin of Emergency and Trauma, Vol. 3 No. 4, pp. 134-137.
  20. Public Health England (2018). Chemical, Biological, Radiological and Nuclear Incidents: Clinical Management and Health Protection. GOV.UK.
  21. Ramesh, A.C., Kumar, S. (2010). “Triage, monitoring, and treatment of mass casualty events involving chemical, biological, radiological, or nuclear agents.” Journal of Pharmacy & Bioallied Sciences, Vol. 2, No. 3, pp. 239-247. 10.4103/0975-7406.68506 21829319 PMC3148628
  22. Salem, O., Guerassimov, A., Mehaoua, A., Marcus, A., Furht, B. (2013). “Anomaly detection in medical wireless sensor networks.” Journal of Computing Science and Engineering, Vol. 7, No. 4, pp. 272-284 10.5626/JCSE.2013.7.4.272
  23. Sena, J., Mostafiz, M.T., Zhang, J., Davidson, A.E., Bandyopadhyay, S., Nerella, S., Ren, Y., Ozrazgat-Baslanti, T., Shickel, B., Loftus, T., Schwartz, W.R., Bihorac, A., Rashidi, P. (2024). Wearable sensors in patient acuity assessment in critical care. Frontiers in Neurology, Vol. 15, pp. 1386728. 10.3389/fneur.2024.1386728 38784909 PMC11112699
  24. Shi, W., Cao, J., Zhang, Q., Li, Y., Xu, L. (2016). “Edge computing: vision and challenges.” IEEE Internet of Things Journal, Vol. 3 No. 5, pp. 637-646. 10.1109/JIOT.2016.2579198
  25. Song, M., Kim, J., Jang, E.C., Kwon, S. (2026). Interpretable machine learning for emergency department triage: clinical insights from 133,198 patients using the Korean triage and acuity scale (KTAS). Diagnostics, Vol. 16 No. 6, pp. 954. 10.3390/diagnostics16060954 41897687 PMC13025175
  26. Sung, S., Kang, C.Y., Lee, H., Lee, J.H., Kim, O.H., Youk, H., Lee, K.H. (2019). “Correlation between the pre-hospital triage scale and emergency department triage scale.” Hong Kong Journal of Emergency Medicine, Vol. 26, No. 5, pp. 281-287. 10.1177/1024907918793780
  27. Wang, H., Li, H., Fang, J., Wang, Y. (2018). “Robust gaussian kalman filter with outlier detection.” IEEE Signal Processing Letters, Vol. 25, No. 8, pp. 1236-1240. 10.1109/LSP.2018.2851156
  28. Wang, X., Han, Y., Wang, C., Zhao, Q., Chen, X., Chen, M. (2019). “In-Edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning.” IEEE Network, Vol. 33, No. 5, pp. 156-165. 10.1109/MNET.2019.1800286
  29. Ward, L.M., Lindskou, T.A., Mogensen, M.L., Christensen, E.F., Søvsø, M.B. (2025). “Machine learning to improve predictive performance of prehospital early warning scores.” Scientific Reports, Vol. 15 No.1, pp. 21459. 10.1038/s41598-025-08247-0 40594836 PMC12215262
  30. Wightman, J.M., Gladish, S.L. (2001). “Explosions and blast injuries.” Annals of Emergency Medicine, Vol 37, No. 6, pp. 664-678. 10.1067/mem.2001.114906
Information
  • Publisher :The Korean Society of Disaster Information
  • Publisher(Ko) :한국재난정보학회
  • Journal Title :Journal of the Society of Disaster Information
  • Journal Title(Ko) :한국재난정보학회논문집
  • Volume : 22
  • No :3
  • Pages :783-793
  • DOI :https://doi.org/10.15683/kosdi.2026.9.30.783
Journal Informaiton Journal of the Society of Disaster Information Journal of the Society of Disaster Information
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close