{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T00:49:36Z","timestamp":1794617376368,"version":"4.9.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100016156","name":"U.S. Army Medical Research and Development Command","doi-asserted-by":"crossref","award":["W81XWH20C0031 and HT942524F0170"],"award-info":[{"award-number":["W81XWH20C0031 and HT942524F0170"]}],"id":[{"id":"10.13039\/100016156","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100016156","name":"U.S. Army Medical Research and Development Command","doi-asserted-by":"crossref","award":["W81XWH20C0031 and HT942524F0170"],"award-info":[{"award-number":["W81XWH20C0031 and HT942524F0170"]}],"id":[{"id":"10.13039\/100016156","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100016156","name":"U.S. Army Medical Research and Development Command","doi-asserted-by":"crossref","award":["W81XWH20C0031 and HT942524F0170"],"award-info":[{"award-number":["W81XWH20C0031 and HT942524F0170"]}],"id":[{"id":"10.13039\/100016156","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100013132","name":"Combat Casualty Care Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Fluid resuscitation immediately following a hemorrhagic injury improves clinical outcome. However, future military conflicts are expected to result in mass-casualty incidents with limited availability of fluid-resuscitation resources. Here, we developed and assessed the performance of a reinforcement learning AI method that optimized clinical outcome and fluid allocation under constrained resources. We generated a large cohort of synthetic trauma casualties using a validated cardio-respiratory computational model, simulating vital-sign time-series data for realistic battlefield scenarios involving hemorrhage, tourniquet application, and fluid resuscitation. For each casualty, we simulated three intervention options\u2014infusion or no infusion of one fluid unit every 30\u00a0min over 90\u00a0min\u2014and assessed whether the interventions restored the vital signs to \u201chealthy\u201d levels. Using these data, we trained the reinforcement learning model to predict the optimal sequence of interventions that maximized the number of casualties restored while minimizing fluid utilization. Using independent simulated data, we found that the AI model was twice as efficient and restored more than twice as many casualties as the current standard of care across varying numbers of casualties and resource limitations. These results highlight the model\u2019s potential to enable personalized interventions, enhance treatment efficiency, and support automated medical decision-making in resource-constrained environments.<\/jats:p>","DOI":"10.1038\/s41598-025-28021-6","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T13:18:49Z","timestamp":1766582329000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A reinforcement learning algorithm to optimize resource utilization in combat casualty care"],"prefix":"10.1038","volume":"15","author":[{"given":"Manivannan","family":"Subramaniyan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sridevi","family":"Nagaraja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders","family":"Wallqvist","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaques","family":"Reifman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"28021_CR1","doi-asserted-by":"publisher","unstructured":"Umlauf, L., Remley, M., Colombo, C. & Pamplin, J. Artificial intelligence decision support systems in resource-limited environments to save lives and reduce moral injury. Mil. Med. usaf010 https:\/\/doi.org\/10.1093\/milmed\/usaf010 (2025).","DOI":"10.1093\/milmed\/usaf010"},{"key":"28021_CR2","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1097\/aco.0000000000000574","volume":"31","author":"JM Gurney","year":"2018","unstructured":"Gurney, J. M. & Spinella, P. C. Blood transfusion management in the severely bleeding military patient. Curr. Opin. Anaesthesiol. 31, 207\u2013214. https:\/\/doi.org\/10.1097\/aco.0000000000000574 (2018).","journal-title":"Curr. Opin. Anaesthesiol."},{"key":"28021_CR3","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1097\/ta.0000000000000292","volume":"77","author":"JS Davis","year":"2014","unstructured":"Davis, J. S. et al. An analysis of prehospital deaths: who can we save? J. Trauma. Acute Care Surg. 77, 213\u2013218. https:\/\/doi.org\/10.1097\/ta.0000000000000292 (2014).","journal-title":"J. Trauma. Acute Care Surg."},{"issue":"Suppl 5","key":"28021_CR4","doi-asserted-by":"publisher","first-page":"S431","DOI":"10.1097\/TA.0b013e3182755dcc","volume":"73","author":"BJ Eastridge","year":"2012","unstructured":"Eastridge, B. J. et al. Death on the battlefield (2001\u20132011): implications for the future of combat casualty care. J. Trauma. Acute Care Surg. 73(Suppl 5), S431\u2013S437. https:\/\/doi.org\/10.1097\/TA.0b013e3182755dcc (2012).","journal-title":"J. Trauma. Acute Care Surg."},{"issue":"Suppl 1","key":"28021_CR5","doi-asserted-by":"publisher","first-page":"S333","DOI":"10.1111\/trf.16454","volume":"61","author":"SA Shackelford","year":"2021","unstructured":"Shackelford, S. A. et al. Joint trauma system, defense committee on trauma, and armed services blood program consensus statement on whole blood. Transfusion 61(Suppl 1), S333\u2013S335. https:\/\/doi.org\/10.1111\/trf.16454 (2021).","journal-title":"Transfusion"},{"key":"28021_CR6","doi-asserted-by":"publisher","first-page":"11","DOI":"10.55460\/p685-l7r7","volume":"21","author":"J Voller","year":"2021","unstructured":"Voller, J. et al. Joint trauma system clinical practice guideline (JTS CPG): prehospital blood transfusion. 30 October 2020. J. Spec. Oper. Med. 21, 11\u201321. https:\/\/doi.org\/10.55460\/p685-l7r7 (2021).","journal-title":"J. Spec. Oper. Med."},{"key":"28021_CR7","doi-asserted-by":"publisher","first-page":"126","DOI":"10.55460\/jylu-4oz8","volume":"21","author":"TG Deaton","year":"2021","unstructured":"Deaton, T. G. et al. Fluid resuscitation in tactical combat casualty Care; TCCC guidelines change 21\u2009\u2013\u200901. 4 November 2021. J. Spec. Oper. Med. 21, 126\u2013137. https:\/\/doi.org\/10.55460\/jylu-4oz8 (2021).","journal-title":"J. Spec. Oper. Med."},{"key":"28021_CR8","doi-asserted-by":"publisher","first-page":"1327948","DOI":"10.3389\/fphys.2024.1327948","volume":"15","author":"X Jin","year":"2024","unstructured":"Jin, X., Frock, A., Nagaraja, S., Wallqvist, A. & Reifman, J. AI algorithm for personalized resource allocation and treatment of hemorrhage casualties. Front. Physiol. 15, 1327948. https:\/\/doi.org\/10.3389\/fphys.2024.1327948 (2024).","journal-title":"Front. Physiol."},{"key":"28021_CR9","doi-asserted-by":"publisher","first-page":"533e1","DOI":"10.1016\/j.jcrc.2012.01.006","volume":"27","author":"AT Reisner","year":"2012","unstructured":"Reisner, A. T., Chen, L. & Reifman, J. The association between vital signs and major hemorrhagic injury is significantly improved after controlling for sources of measurement variability. J. Crit. Care. 27, 533e1\u201353310. https:\/\/doi.org\/10.1016\/j.jcrc.2012.01.006 (2012).","journal-title":"J. Crit. Care"},{"key":"28021_CR10","doi-asserted-by":"publisher","first-page":"1716","DOI":"10.1038\/s41591-018-0213-5","volume":"24","author":"M Komorowski","year":"2018","unstructured":"Komorowski, M., Celi, L. A., Badawi, O., Gordon, A. C. & Faisal, A. A. The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nat. Med. 24, 1716\u20131720. https:\/\/doi.org\/10.1038\/s41591-018-0213-5 (2018).","journal-title":"Nat. Med."},{"key":"28021_CR11","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402\u20132410. https:\/\/doi.org\/10.1001\/jama.2016.17216 (2016).","journal-title":"JAMA"},{"key":"28021_CR12","unstructured":"Prasad, N., Cheng, L. F., Chivers, C., Draugelis, M. & Engelhardt, B. E. A reinforcement learning approach to weaning of mechanical ventilation in intensive care units. Preprint at https:\/\/arxiv.org\/abs\/1704.06300 (2017)."},{"key":"28021_CR13","doi-asserted-by":"publisher","first-page":"e18477","DOI":"10.2196\/18477","volume":"22","author":"S Liu","year":"2020","unstructured":"Liu, S. et al. Reinforcement learning for clinical decision support in critical care: comprehensive review. J. Med. Internet Res. 22, e18477. https:\/\/doi.org\/10.2196\/18477 (2020).","journal-title":"J. Med. Internet Res."},{"key":"28021_CR14","doi-asserted-by":"publisher","first-page":"101964","DOI":"10.1016\/j.artmed.2020.101964","volume":"109","author":"A Coronato","year":"2020","unstructured":"Coronato, A., Naeem, M., De Pietro, G. & Paragliola, G. Reinforcement learning for intelligent healthcare applications: a survey. Artif. Intell. Med. 109, 101964. https:\/\/doi.org\/10.1016\/j.artmed.2020.101964 (2020).","journal-title":"Artif. Intell. Med."},{"key":"28021_CR15","doi-asserted-by":"publisher","first-page":"e3662","DOI":"10.1002\/cnm.3662","volume":"39","author":"X Jin","year":"2023","unstructured":"Jin, X., Laxminariyan, S., Nagaraja, S., Wallqvist, A. & Reifman, J. Development and validation of a mathematical model to simulate human cardiovascular and respiratory responses to battlefield trauma. Int. J. Numer. Method Biomed. Eng. 39, e3662. https:\/\/doi.org\/10.1002\/cnm.3662 (2023).","journal-title":"Int. J. Numer. Method Biomed. Eng."},{"key":"28021_CR16","unstructured":"Schwartz, D. A. & Holcomb, J. Common Problems in Acute Care Surgery. (eds Moore, L. J. & Todd, S. R.) 3\u201315 (Springer International Publishing, 2017)."},{"key":"28021_CR17","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1097\/CCM.0b013e31818477f0","volume":"36","author":"H Herff","year":"2008","unstructured":"Herff, H. et al. Influence of ventilation strategies on survival in severe controlled hemorrhagic shock. Crit. Care Med. 36, 2613\u20132620. https:\/\/doi.org\/10.1097\/CCM.0b013e31818477f0 (2008).","journal-title":"Crit. Care Med."},{"key":"28021_CR18","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1097\/shk.0000000000000174","volume":"42","author":"B Soller","year":"2014","unstructured":"Soller, B. et al. Investigation of noninvasive muscle pH and oxygen saturation during uncontrolled hemorrhage and resuscitation in swine. Shock 42, 44\u201351. https:\/\/doi.org\/10.1097\/shk.0000000000000174 (2014).","journal-title":"Shock"},{"key":"28021_CR19","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1097\/TA.0000000000002439","volume":"87","author":"DS Kauvar","year":"2019","unstructured":"Kauvar, D. S. et al. Effect of partial and complete aortic balloon occlusion on survival and shock in a swine model of uncontrolled Splenic hemorrhage with delayed resuscitation. J. Trauma. Acute Care Surg. 87, 1026\u20131034. https:\/\/doi.org\/10.1097\/TA.0000000000002439 (2019).","journal-title":"J. Trauma. Acute Care Surg."},{"key":"28021_CR20","unstructured":"Sutton, R. S. & Barto, A. G. Reinforcement Learning: An Introduction 2nd edn (The MIT Press, 2018)."},{"key":"28021_CR21","unstructured":"Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning, Lille, France, vol. 37, 448\u2013456 (2015)."},{"key":"28021_CR22","doi-asserted-by":"crossref","unstructured":"Hasselt, H. V., Guez, A. & Silver, D. Deep reinforcement learning with double Q-Learning. In Proceedings of the 30th Association for the Advancement of Artificial Intelligence Conference, Phoneix, AZ, 2094\u20132100 (2016).","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"28021_CR23","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529\u2013533. https:\/\/doi.org\/10.1038\/nature14236 (2015).","journal-title":"Nature"},{"key":"28021_CR24","unstructured":"ZOLL Medical Corporation. Propaq M Operator\u2019s Guide (ZOLL Medical, 2016)."},{"key":"28021_CR25","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1136\/heartjnl-2017-312731","volume":"104","author":"D Nanchen","year":"2018","unstructured":"Nanchen, D. Resting heart rate: what is normal? Heart 104, 1048\u20131049. https:\/\/doi.org\/10.1136\/heartjnl-2017-312731 (2018).","journal-title":"Heart"},{"key":"28021_CR26","doi-asserted-by":"publisher","first-page":"108","DOI":"10.18773\/austprescr.2020.025","volume":"43","author":"G Gabb","year":"2020","unstructured":"Gabb, G. What is hypertension? Aust Prescr. 43, 108\u2013109. https:\/\/doi.org\/10.18773\/austprescr.2020.025 (2020).","journal-title":"Aust Prescr"},{"key":"28021_CR27","doi-asserted-by":"publisher","first-page":"S180","DOI":"10.1097\/ta.0000000000004063","volume":"95","author":"MH Remondelli","year":"2023","unstructured":"Remondelli, M. H. et al. Casualty care implications of large-scale combat operations. J. Trauma Acute Care Surg. 95, S180\u2013S184. https:\/\/doi.org\/10.1097\/ta.0000000000004063 (2023).","journal-title":"J. Trauma. Acute Care Surg."},{"key":"28021_CR28","doi-asserted-by":"publisher","first-page":"1613874","DOI":"10.3389\/fphys.2025.1613874","volume":"16","author":"V Kurian","year":"2025","unstructured":"Kurian, V., Jin, X., Nagaraja, S., Wallqvist, A. & Reifman, J. A model to simulate human cardio-respiratory responses to different fluid resuscitation treatments after hemorrhagic injury. Front. Physiol. 16, 1613874. https:\/\/doi.org\/10.3389\/fphys.2025.1613874 (2025).","journal-title":"Front. Physiol."},{"key":"28021_CR29","doi-asserted-by":"publisher","first-page":"S240","DOI":"10.1111\/trf.18213","volume":"65","author":"AE Pusateri","year":"2025","unstructured":"Pusateri, A. E. et al. Potential military applications for a new freeze-dried plasma. Transfusion 65, S240\u2013S249. https:\/\/doi.org\/10.1111\/trf.18213 (2025).","journal-title":"Transfusion"},{"key":"28021_CR30","doi-asserted-by":"publisher","first-page":"e195085","DOI":"10.1001\/jamasurg.2019.5085","volume":"155","author":"AE Pusateri","year":"2020","unstructured":"Pusateri, A. E. et al. Association of prehospital plasma transfusion with survival in trauma patients with hemorrhagic shock when transport times are longer than 20 minutes: a post hoc analysis of the pamper and COMBAT clinical trials. JAMA Surg. 155, e195085. https:\/\/doi.org\/10.1001\/jamasurg.2019.5085 (2020).","journal-title":"JAMA Surg."},{"key":"28021_CR31","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1186\/cc3526","volume":"9","author":"D Rixen","year":"2005","unstructured":"Rixen, D. & Siegel, J. H. Bench-to-bedside review: oxygen debt and its metabolic correlates as quantifiers of the severity of hemorrhagic and post-traumatic shock. Crit. Care. 9, 441\u2013453. https:\/\/doi.org\/10.1186\/cc3526 (2005).","journal-title":"Crit. Care"},{"key":"28021_CR32","unstructured":"Joint Trauma System. Damage Control Resuscitation: Joint Trauma System Clinical Practice Guideline (CPG ID: 18) (U.S. Department of Defense, 2019)."},{"key":"28021_CR33","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1016\/j.suc.2012.04.004","volume":"92","author":"JG Perkins","year":"2012","unstructured":"Perkins, J. G. et al. Research and analytics in combat trauma care: converting data and experience to practical guidelines. Surg. Clin. North Am. 92, 1041\u20131054. https:\/\/doi.org\/10.1016\/j.suc.2012.04.004 (2012).","journal-title":"Surg. Clin. North. Am."},{"key":"28021_CR34","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1111\/trf.15097","volume":"59","author":"R Miskimins","year":"2019","unstructured":"Miskimins, R., Pati, S. & Schreiber, M. Barriers to clinical research in trauma. Transfusion 59, 846\u2013853. https:\/\/doi.org\/10.1111\/trf.15097 (2019).","journal-title":"Transfusion"},{"key":"28021_CR35","doi-asserted-by":"publisher","unstructured":"Ahmad, Z., Rahim, S., Zubair, M. & Abdul-Ghafar, J. Artificial intelligence (AI) in medicine, current applications and future role with special emphasis on its potential and promise in pathology: present and future impact, obstacles including costs and acceptance among pathologists, practical and philosophical considerations. A comprehensive review. Diagn. Pathol. 16 https:\/\/doi.org\/10.1186\/s13000-021-01085-4 (2021).","DOI":"10.1186\/s13000-021-01085-4"},{"key":"28021_CR36","doi-asserted-by":"publisher","first-page":"143","DOI":"10.3399\/bjgp18X695213","volume":"68","author":"VH Buch","year":"2018","unstructured":"Buch, V. H., Ahmed, I. & Maruthappu, M. Artificial intelligence in medicine: current trends and future possibilities. Br. J. Gen. Pract. 68, 143\u2013144. https:\/\/doi.org\/10.3399\/bjgp18X695213 (2018).","journal-title":"Br. J. Gen. Pract."},{"key":"28021_CR37","doi-asserted-by":"publisher","unstructured":"Alowais, S. A. et al. Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med. Educ. 23, 689. https:\/\/doi.org\/10.1186\/s12909-023-04698-z (2023).","DOI":"10.1186\/s12909-023-04698-z"},{"key":"28021_CR38","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1097\/xcs.0000000000000707","volume":"237","author":"A Epstein","year":"2023","unstructured":"Epstein, A. et al. Putting medical boots on the ground: lessons from the war in Ukraine and applications for future conflict with near-peer adversaries. J. Am. Coll. Surg. 237, 364\u2013373. https:\/\/doi.org\/10.1097\/xcs.0000000000000707 (2023).","journal-title":"J. Am. Coll. Surg."},{"key":"28021_CR39","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1093\/milmed\/usaa352","volume":"186","author":"AB Cohen","year":"2021","unstructured":"Cohen, A. B., Davis, M. & Herman, S. E. M. Prolonged field care research approach and its relevance to civilian medicine. Mil Med. 186, 123\u2013128. https:\/\/doi.org\/10.1093\/milmed\/usaa352 (2021).","journal-title":"Mil Med."},{"key":"28021_CR40","doi-asserted-by":"publisher","first-page":"S135","DOI":"10.1016\/j.wem.2017.02.001","volume":"28","author":"S Keenan","year":"2017","unstructured":"Keenan, S. & Riesberg, J. C. Prolonged field care: beyond the golden hour. Wilderness Environ. Med. 28, S135\u2013S139. https:\/\/doi.org\/10.1016\/j.wem.2017.02.001 (2017).","journal-title":"Wilderness Environ. Med."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28021-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28021-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28021-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:43:47Z","timestamp":1781624627000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-28021-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["28021"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-28021-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]},"assertion":[{"value":"31 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"44534"}}