مجله دانشگاه علوم پزشکی سبزوار

شماره جاری

بر اساس شماره‌های نشریه

بر اساس نویسندگان

بر اساس موضوعات

نمایه نویسندگان

نمایه کلیدواژه ها

درباره نشریه

اهداف و چشم انداز

اعضای هیات تحریریه

اصول اخلاقی انتشار مقاله

بانک ها و نمایه نامه ها

پیوندهای مفید

فرایند پذیرش مقالات

اخبار و اعلانات

فرم های ضروری نشریه

راهنمای تنظیم مقاله

راهنمای نگارش خلاصه سیاستی

فرم خلاصه سیاستی

نقش هوش مصنوعی در تریاژ مجروحان در شرایط جنگی: مرور سیستماتیک

نوع مقاله : مروری

نویسندگان

1 گروه آموزشی اتاق عمل، دانشکده پیراپزشکی، دانشگاه علوم پزشکی سبزوار، سبزوار، ایران

2 گروه آموزشی پرستاری داخلی جراحی، دانشکده پرستاری و مامایی، دانشگاه علوم پزشکی سبزوار، سبزوار، ایران

3 کمیته تحقیقات دانشجویی، دانشگاه علوم پزشکی و خدمات بهداشتی درمانی بیرجند، بیرجند، ایران.

چکیده

زمینه و هدف: در جنگ‌های مدرن با سلاح‌های پرسرعت، انفجاری و حملات موشکی، تعدد مجروحان ظرفیت سیستم‌های درمانی را تحت فشار قرار می‌دهد. باتوجه‌ به افزایش استفاده از فناوری‌های هوش مصنوعی در سال‌های اخیر، این مطالعه مروری با تحلیل شواهد موجود، اثربخشی، چالش‌ها و مسیرهای آینده هوش مصنوعی را در تریاژ مجروحان ارزیابی می‌کند
مواد و روش­ها: در این مطالعه، مقالات انگلیسی از پایگاه‌های PubMed، Scopus، Web of Science،  Embase و IEEE Xplore و با کلیدواژه‌های " Artificial Intelligence" و" Triage" ،” Armed Conflict و مترادف‌ها در بازه 2025-2015 جستجو شد. مطالعات مشاهده‌ای، کارآزمایی بالینی، مدل‌سازی و توسعه الگوریتم با کاربرد هوش مصنوعی در تریاژ نظامی وارد شدند. پس از حذف موارد تکراری با Rayyan.ai، از 189 مقاله، در نهایت 17 مقاله پس از غربالگری دو نفره مستقل تحلیل شدند. ارزیابی کیفیت مطالعات با ابزار CASP و گزارش‌دهی با PRISMA انجام شد.
یافته­ها: الگوریتم‌های یادگیری ماشین (مانند Random Forest و XGBoost) و یادگیری عمیق در تریاژ نظامی و محیط‌های مشابه بحران جنگی غالب بودند. مدل‌های مبتنی بر علائم حیاتی در پیش‌بینی انتقال خون گسترده (AUC 98/0– 987/0)، تشخیص شوک/هیپوولمی (حساسیت 94%) و مداخلات نجات‌بخش (AUC 81/0) دقت بالایی داشتند. در تصویربرداری، مدل‌های YOLOv3/v7 و U-Net تشخیص و تقسیم‌بندی ترکش/اجسام خارجی را با mIoU 73/0 بهبود دادند. مدل‌های زبان بزرگ (ChatGPT،Google Bard) در سناریوهای شبیه‌سازی‌شده دقت 64-60% مطابق پروتکل START داشتند، اما تکرارپذیری پایین و وابستگی به پرامپت نشان دادند. به‌طور کلی، هوش مصنوعی دقت و سرعت تریاژ را به‌طور قابل‌توجهی ارتقا می‌دهد، اما بیشتر مطالعات بر داده‌های آزمایشگاهی/شبیه‌سازی‌شده متکی بوده و نیاز به اعتبارسنجی میدانی دارند.
نتیجه‌گیری: اجرای مسئولانه و اخلاقی هوش مصنوعی، می‌تواند سرعت، عینیت و دقت تریاژ را به میزان قابل‌توجهی افزایش دهند. این امر به‌ویژه در جنگ‌های کوتاه‌مدت با هجوم گسترده مصدومان، که سیستم‌های پزشکی سنتی را تحت الشعاع قرار دهند، حیاتی است.

تازه های تحقیق

https://scholar.google.com/citations?user=LDrXrwEAAAAJ

https://pubmed.ncbi.nlm.nih.gov/?term=Fateme%20Borzoee

https://scholar.google.com/citations?user=UXLNSboAAAAJ

https://pubmed.ncbi.nlm.nih.gov/?term=narjes%20heshmatifar

https://scholar.google.com/citations?user=fHCx-hwAAAAJ&hl=fa

https://pubmed.ncbi.nlm.nih.gov/42091952/

 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

The role of artificial intelligence in the triage of the injured in war conditions: A systematic review

نویسندگان [English]

  • Fatemeh Borzoee 1
  • Narjes Heshmatifar 2
  • Yeganeh Salehi 3

1 PhD Candidate of nursing, Faculty Member, School of Paramedics, Sabzevar University of medical Sciences, Sabzevar, Iran

2 Assistant Professor of Nursing, Nursing and Midwifery School, Sabzevar University of Medical Sciences, Sabzevar, Iran

3 Student Research Committee, Birjand University of Medical Sciences, Birjand, Iran.

چکیده [English]

Background and Objective: In modern warfare characterized by high-velocity weapons, explosive devices, and missile attacks, the large number of casualties can overwhelm medical infrastructures far beyond their operational capacity. In recent years, there has been growing interest in the application of artificial intelligence (AI) to improve the efficiency and effectiveness of healthcare delivery. Therefore, this systematic review aims to evaluate the effectiveness, challenges, and future directions of AI in casualty triage by synthesizing the existing evidence.
Materials and Methods: In this systematic review, English-language articles were searched in PubMed, Scopus, Web of Science, Embase, IEEE Xplore, and the Cochrane Library using the keywords “Artificial Intelligence,” “Triage,” “Armed Conflict,” and their related terms, covering the period from 2015 to 2025. English-language observational studies, clinical trials, modeling studies, and algorithm-development research that examined the use of AI in military triage or analogous conflict-related settings were included. After duplicate removal using Rayyan.ai, a total of 189 articles were screened by title, abstract, and full text. Ultimately, 17 studies were included. Screening was performed independently by two reviewers, and discrepancies were resolved through consensus. Study quality was evaluated using CASP tools, and the selection process was reported according to the PRISMA flow diagram.
Results: Among the 17 included studies, AI was primarily applied through machine-learning algorithms (such as Random Forest and XGBoost) and deep-learning methods in military triage and war-related crisis environments. Models based on vital signs demonstrated high accuracy in predicting massive transfusion requirements (AUC 0.98–0.987), detecting shock/hypovolemia (sensitivity up to 94%), and identifying the need for life-saving interventions (AUC 0.81). In medical imaging, YOLOv3/v7 and U-Net models improved the detection and segmentation of shrapnel/foreign bodies, achieving an mIoU of 0.73 and high diagnostic precision. Large language models (LLMs) such as ChatGPT and Google Bard showed 60–64% accuracy when applying START protocols in simulated mass-casualty incidents (MCIs), although they exhibited limited reproducibility and strong dependence on prompting. Overall, AI substantially enhances the accuracy and speed of triage; however, most studies rely on laboratory or simulated datasets, highlighting the need for real-world field validation.
Conclusion: The responsible and ethical implementation of these technologies can significantly increase the speed, objectivity and accuracy of triage decisions. This is especially important in critical and short-term war situations, where large numbers of casualties can quickly overwhelm traditional medical systems.

کلیدواژه‌ها [English]

  • Artificial Intelligence
  • Triage War
  • Armed Conflict
مراجع
  1. Bazyar J, Farrokhi M, Salari A, Safarpour H, Khankeh HR. Accuracy of Triage Systems in Disasters and Mass Casualty Incidents; a Systematic Review. Arch Acad Emerg Med. 2022;10(1):e32. doi:10.22037/aaem.v10i1.1526
  2. Shin K, Lee T. Emergency medical service resource allocation in a mass casualty incident by integrating patient prioritization and hospital selection problems. IISE Transactions. 2020;52(10):1141-55. doi:https://doi.org/10.1080/24725854.2020.1727069
  3. Epstein A, Lim R, Johannigman J, Fox CJ, Inaba K, Vercruysse GA, et al. Putting Medical Boots on the Ground: Lessons from the War in Ukraine and Applications for Future Conflict with Near-Peer Adversaries. Journal of the American College of Surgeons. 2023;237(2):364-73. doi:10.1097/xcs.0000000000000707
  4. Lammers D, Williams J, Conner J, Francis A, Prey B, Marenco C, et al. Utilization of Machine Learning Approaches to Predict Mortality in Pediatric Warzone Casualties. Military Medicine. 2022;189(1-2):345-51. doi:10.1093/milmed/usac171
  5. April MD, Bridwell RE, Jones J, Oliver J, Long B, Schauer SG. Descriptive Analysis of Casualties Rapidly Returned to the Fight after Injury: Reverse Triage Implications for Large Scale Combat Operations. Med J (Ft Sam Houst Tex). 2022;Per 22-04-05-06(Per 22-04-05-06):3-9.
  6. Pikoulis E, Doucet J. Emergency medicine, trauma and disaster management: from prehospital to hospital care and beyond: Springer Nature; 2021.
  7. Franc JM, Kirkland SW, Wisnesky UD, Campbell S, Rowe BH. 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. 2022;37(1):106-16. doi:10.1017/S1049023X2100131X
  8. Kim GH, Kim JH, Kim H, Kim SH, Park SJ, Lee SB, et al. Assessment of the Suitability of Trauma Triage According to Physiological Criteria in Korea. Journal of Acute Care Surgery. 2022;12(3):120-4. doi:https://doi.org/10.17479/jacs.2022.12.3.120
  9. Montagner G, de Sousa KKI, dos Santos MVF. Acurácia do algoritmo Simple Triage and Rapid Treatment (START) na triagem de acidentes e desastres: uma revisão integrativa. Research, Society and Development. 2022;11(15):e314111537234-e. doi:https://doi.org/10.33448/rsd-v11i15.37234
  10. Remondelli MH, Remick KN, Shackelford SA, Gurney JM, Pamplin JC, Polk TM, et al. Casualty care implications of large-scale combat operations. Journal of Trauma and Acute Care Surgery. 2023;95(2S):S180-S4. doi: 10.1097/TA.0000000000004063
  11. Williamson A. Innovations in preoperative control of exsanguination in major trauma. Journal of Paramedic Practice. 2022;14(6):234-41. doi:https://doi.org/10.12968/jpar.2022.14.6.234
  12. Moghaddam PS, Jahangiri K, Sohrabizadeh S, Hassani N, Moghaddam MH, Tehrani GM. Challenges of emergency evacuation of residential areas caused by chemical release due to the earthquake: a Natech event scenario. Journal of injury and violence research. 2022;14(1):33. doi: 10.5249/jivr.v14i1.1698
  13. Achkoski J, Koceski S, Bogatinov D, Temelkovski B, Stevanovski G, Kocev I. Remote triage support algorithm based on fuzzy logic. Journal of the Royal Army Medical Corps. 2017;163(3):164-70. doi:10.1136/jramc-2015-000616
  14. Adebayo O, Bhuiyan ZA, Ahmed Z. Exploring the effectiveness of artificial intelligence, machine learning and deep learning in trauma triage: A systematic review and meta-analysis. DIGITAL HEALTH. 2023;920552076231205736. doi:10.1177/20552076231205736
  15. Rakhilin N, Morris HD, Pham DL, Hood MN, Ho VB. Opportunities for Artificial Intelligence in Operational Medicine: Lessons from the United States Military. Bioengineering. 2025;12(5):519. doi:https://doi.org/10.3390/bioengineering12050519
  16. Surman K, Lockey D. Unmanned aerial vehicles and pre-hospital emergency medicine. Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine. 2024;32(1):9. doi:10.1186/s13049-024-01180-7
  17. Liu Y, Gao J, Liu J, Walline JH, Liu X, Zhang T, et al. Development and validation of a practical machine-learning triage algorithm for the detection of patients in need of critical care in the emergency department. Scientific Reports. 2021;11(1):24044. doi:10.1038/s41598-021-03104-2
  18. Eastridge BJ, Butler F, Wade CE, Holcomb JB, Salinas J, Champion HR, et al. Field triage score (FTS) in battlefield casualties: validation of a novel triage technique in a combat environment. The American Journal of Surgery. 2010;200(6):724-7. doi:https://doi.org/10.1016/j.amjsurg.2010.08.006
  19. Jorma J, Heli L, Janne E, Ville H. Experiences of using a mobile RFID-based triage system. J Aeronaut Aerosp Eng. 2013;2117. doi: http://dx.doi.org/10.4172/2168-9792.1000117
  20. Franc JM, Hertelendy AJ, Cheng L, Hata R, Verde M. Accuracy of a commercial large language model (ChatGPT) to perform disaster triage of simulated patients using the simple triage and rapid treatment (START) protocol: gage repeatability and reproducibility study. Journal of Medical Internet Research. 2024;26e55648.
  21. Gan RK, Ogbodo JC, Wee YZ, Gan AZ, González PA. Performance of Google bard and ChatGPT in mass casualty incidents triage. The American Journal of Emergency Medicine. 2024;7572-8. doi:https://doi.org/10.1016/j.ajem.2023.10.034
  22. Nations U. UN chief 'gravely alarmed' by bombing of Iranian nuclear sites: UN News; 2025
  23. Eastridge BJ, Mabry RL, Seguin P, Cantrell J, Tops T, Uribe P, et al. Death on the battlefield (2001–2011): implications for the future of combat casualty care. Journal of trauma and acute care surgery. 2012;73(6):S431-S7. doi:10.1097/TA.0b013e3182755dcc
  24. Peng HT, Siddiqui MM, Rhind SG, Zhang J, da Luz LT, Beckett A. Artificial intelligence and machine learning for hemorrhagic trauma care. Military Medical Research. 2023;10(1):6. doi:10.1186/s40779-023-00444-0
  25. Rickards CA, Vyas N, Ryan KL, Ward KR, Andre D, Hurst GM, et al. Are you bleeding? Validation of a machine-learning algorithm for determination of blood volume status: application to remote triage. Journal of Applied Physiology. 2014;116(5):486-94. doi:10.1152/japplphysiol.00012.2013
  26. Nemeth C, Amos-Binks A, Burris C, Keeney N, Pinevich Y, Pickering BW, et al. Decision Support for Tactical Combat Casualty Care Using Machine Learning to Detect Shock. Military Medicine. 2021;186(Supplement_1):273-80. doi:10.1093/milmed/usaa275
  27. Lammers D, Marenco C, Morte K, Conner J, Williams J, Bax T, et al. Machine Learning for Military Trauma: Novel Massive Transfusion Predictive Models in Combat Zones. Journal of Surgical Research. 2022;270369-75. doi:https://doi.org/10.1016/j.jss.2021.09.017
  28. Stallings JD, Laxminarayan S, Yu C, Kapela A, Frock A, Cap AP, et al. APPRAISE-HRI: an artificial intelligence algorithm for triage of hemorrhage casualties. Shock. 2023;60(2):199-205.
  29. Joseph B, Pandit V, Zangbar B, Kulvatunyou N, Hashmi A, Green DJ, et al. Superiority of Frailty Over Age in Predicting Outcomes Among Geriatric Trauma Patients: A Prospective Analysis. JAMA Surgery. 2014;149(8):766-72. doi:10.1001/jamasurg.2014.296
  30. Ventura CAI, Denton EE, David JA. Artificial intelligence in emergency trauma care: a preliminary scoping review. Medical Devices: Evidence and Research. 2024191-211. doi:https://doi.org/10.2147/MDER.S467146
  31. Weidman AC, Malakouti S, Salcido DD, Zikmund C, Patel R, Weiss LS, et al. A Machine Learning Trauma Triage Model for Critical Care Transport. JAMA Network Open. 2025;8(6):e259639-e. doi:10.1001/jamanetworkopen.2025.9639
  32. Senda A, Endo A, Kinoshita T, Otomo Y. Development of practical triage methods for critical trauma patients: machine-learning algorithm for evaluating hybrid operation theatre entry of trauma patients (THETA). European Journal of Trauma and Emergency Surgery. 2022;48(6):4755-60. doi:10.1007/s00068-022-02002-0
  33. Snider EJ, Hernandez-Torres SI, Avital G, Boice EN. Evaluation of an Object Detection Algorithm for Shrapnel and Development of a Triage Tool to Determine Injury Severity. Journal of Imaging. 2022;8(9):252. doi: https://doi.org/10.3390/jimaging8090252
  34. Holland L, Hernandez Torres SI, Snider EJ. Using AI Segmentation Models to Improve Foreign Body Detection and Triage from Ultrasound Images. Bioengineering. 2024;11(2):128. doi:10.3390/bioengineering11020128
  35. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Medical Image Analysis. 2017;4260-88. doi:https://doi.org/10.1016/j.media.2017.07.005
  36. Zhou Z, Jin Y, Ye H, Zhang X, Liu J, Zhang W. Classification, detection, and segmentation performance of image-based AI in intracranial aneurysm: a systematic review. BMC Medical Imaging. 2024;24(1):164. doi:10.1186/s12880-024-01347-9
  37. Abramson HG, Curry EJ, Mess G, Thombre R, Kempski-Leadingham KM, Mistry S, et al. Automatic detection of foreign body objects in neurosurgery using a deep learning approach on intraoperative ultrasound images: From animal models to first in-human testing. Frontiers in Surgery. 2022;91040066. doi:10.3389/fsurg.2022.1040066
  38. Cross KP, Petry MJ, Cicero MX. A better START for low-acuity victims: data-driven refinement of mass casualty triage. Prehospital emergency care. 2015;19(2):272-8. doi:10.3109/10903127.2014.942481
  39. Cone DC, MacMillan DS. Mass-casualty triage systems: a hint of science: Acad Emerg Med. 2005 Aug;12(8):739-41. doi: 10.1197/j.aem.2005.04.001.
  40. Potter BK, Forsberg JA, Silvius E, Wagner M, Khatri V, Schobel SA, et al. Combat-Related Invasive Fungal Infections: Development of a Clinically Applicable Clinical Decision Support System for Early Risk Stratification. Military Medicine. 2018;184(1-2):e235-e42. doi:10.1093/milmed/usy182
  41. Bai S, Ye L, Liu L, Liang T, Qin C, Bu J, et al. Emergency triage based on deep ensemble learning and ICU physiological time series. Biomedical Signal Processing and Control. 2024;96106518. doi:https://doi.org/10.1016/j.bspc.2024.106518
  42. Xu Y, Malik N, Chernbumroong S, Vassallo J, Keene D, Foster M, et al. Triage in major incidents: development and external validation of novel machine learning-derived primary and secondary triage tools. Emerg Med J. 2024;41(3):176-83. doi:10.1136/emermed-2022-212440
  43. Seyedin H, Moslehi S, Tavan A, Narimani S. The role of artificial intelligence in protecting frontline forces in CBRNE incidents. Progress in Disaster Science. 2025;26100443. doi:https://doi.org/10.1016/j.pdisas.2025.100443
  44. Nanini S, Abid M, Mamouni Y, Wiedemann A, Jouvet P, Bourassa S. Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies. Diagnostics (Basel). 2024;14(23). doi:10.3390/diagnostics14232763
  45. Achkoski J, Stevanovski G. Remote triage support algorithm based on fuzzy logic. BMJ Military Health. 2017;163(3):164-70. doi:10.1136/jramc-2015-000616
  46. Salman OH, Aal-Nouman MI, Taha ZK. Reducing waiting time for remote patients in telemedicine with considering treated patients in emergency department based on body sensors technologies and hybrid computational algorithms: Toward scalable and efficient real time healthcare monitoring system. Journal of Biomedical Informatics. 2020;112103592. doi:https://doi.org/10.1016/j.jbi.2020.103592
  47. Abe D, Inaji M, Hase T, Takahashi S, Sakai R, Ayabe F, et al. A prehospital triage system to detect traumatic intracranial hemorrhage using machine learning algorithms. JAMA Network Open. 2022;5(6):e2216393-e. doi:10.1001/jamanetworkopen.2022.16393
  48. London AJ. Artificial intelligence and black‐box medical decisions: accuracy versus explainability. Hastings Center Report. 2019;49(1):15-21. doi: https://doi.org/10.1002/hast.973
  49. Cummings M. Artificial intelligence and the future of warfare: Chatham House for the Royal Institute of International Affairs London; 2017.
  50. Lin P, Bekey G, Abney K. Robots in war: issues of risk and ethics. 2009.
  51. Nguyen AT. Benefits and Challenges of Utilizing Artificial Intelligence in Decision Making for US Military Leaders: Alliant International University; 2022.
  52. Da'Costa A, Teke J, Origbo JE, Osonuga A, Egbon E, Olawade DB. AI-driven triage in emergency departments: A review of benefits, challenges, and future directions. Int J Med Inform. 2025;197105838. doi:10.1016/j.ijmedinf.2025.105838
  53. Bovet Emanuel P. Exploring Decision Advantages: Improving Speed, Precision and Efficiency inMilitary Targeting by Applying Artificial Intelligence: Försvarshögskolan (FHS); 2025.
مجله دانشگاه علوم پزشکی سبزوار
دوره 33، شماره 3
مرداد و شهریور 1405
صفحه 1052-1068
فایل ها
سابقه مقاله
  • تاریخ دریافت: 31 شهریور 1404
  • تاریخ بازنگری: 04 اسفند 1404
  • تاریخ پذیرش: 31 فروردین 1405
هم رسانی
ارجاع به این مقاله
آمار