Jan Páleník MD , Michal Soták PhD , Martin Černý MD , Martin Komarc PhD , Norbert Svoboda PhD , Daor Hayu , Tomáš Tyll PhD , David Netuka PhD , Václav Masopust PhD , Karel Roubík PhD , Martin Májovský PhD
{"title":"Conversational AI in tactical combat casualty care: Baseline GPT-4o improves medic decision-making","authors":"Jan Páleník MD , Michal Soták PhD , Martin Černý MD , Martin Komarc PhD , Norbert Svoboda PhD , Daor Hayu , Tomáš Tyll PhD , David Netuka PhD , Václav Masopust PhD , Karel Roubík PhD , Martin Májovský PhD","doi":"10.1016/j.ecns.2025.101803","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Mechanical ventilation is vital in Tactical Combat Casualty Care (TCCC), yet many combat medics lack sufficient training in ventilator management. Although artificial intelligence (AI) shows promise in emergency medicine, its use in combat scenarios remains largely unexplored. This study evaluated AI-assisted ventilator management under simulated battlefield conditions.</div></div><div><h3>Methods</h3><div>This prospective, simulation-based observational study using a within-subject design was conducted in February 2025 in the Czech Republic with 42 Czech Armed Forces combat medics from four units. Participants adjusted ventilator settings (Vt, RR, FiO₂, PEEP, I:E) across ten scenarios, five with GPT-4o AI assistance and five without. The AI was customized to TCCC protocols and Joint Trauma System guidelines. Performance was scored objectively and analyzed using two-way repeated-measures ANOVA.</div></div><div><h3>Results</h3><div>AI assistance significantly improved parameter accuracy (<em>p</em> < 0.001), with an overall performance increase of 79.7%. The greatest gains were observed in Vt selection (164.2%), followed by FiO₂ (105.9%) and PEEP (60.6%), while I:E ratio adjustments showed marginal improvement (19%). Less experienced and female medics benefited most. Notably, AI-generated recommendations outperformed AI-assisted human decisions.</div></div><div><h3>Conclusions</h3><div>AI-enhanced support significantly improved ventilator management in combat simulations, suggesting potential to optimize real-time decision-making in austere environments. However, this system is not ready for operational deployment, and results should be interpreted as exploratory pending further field validation. Human oversight and medic accountability remain essential.</div></div>","PeriodicalId":48753,"journal":{"name":"Clinical Simulation in Nursing","volume":"107 ","pages":"Article 101803"},"PeriodicalIF":2.5000,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Simulation in Nursing","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1876139925001203","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NURSING","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Mechanical ventilation is vital in Tactical Combat Casualty Care (TCCC), yet many combat medics lack sufficient training in ventilator management. Although artificial intelligence (AI) shows promise in emergency medicine, its use in combat scenarios remains largely unexplored. This study evaluated AI-assisted ventilator management under simulated battlefield conditions.
Methods
This prospective, simulation-based observational study using a within-subject design was conducted in February 2025 in the Czech Republic with 42 Czech Armed Forces combat medics from four units. Participants adjusted ventilator settings (Vt, RR, FiO₂, PEEP, I:E) across ten scenarios, five with GPT-4o AI assistance and five without. The AI was customized to TCCC protocols and Joint Trauma System guidelines. Performance was scored objectively and analyzed using two-way repeated-measures ANOVA.
Results
AI assistance significantly improved parameter accuracy (p < 0.001), with an overall performance increase of 79.7%. The greatest gains were observed in Vt selection (164.2%), followed by FiO₂ (105.9%) and PEEP (60.6%), while I:E ratio adjustments showed marginal improvement (19%). Less experienced and female medics benefited most. Notably, AI-generated recommendations outperformed AI-assisted human decisions.
Conclusions
AI-enhanced support significantly improved ventilator management in combat simulations, suggesting potential to optimize real-time decision-making in austere environments. However, this system is not ready for operational deployment, and results should be interpreted as exploratory pending further field validation. Human oversight and medic accountability remain essential.
期刊介绍:
Clinical Simulation in Nursing is an international, peer reviewed journal published online monthly. Clinical Simulation in Nursing is the official journal of the International Nursing Association for Clinical Simulation & Learning (INACSL) and reflects its mission to advance the science of healthcare simulation.
We will review and accept articles from other health provider disciplines, if they are determined to be of interest to our readership. The journal accepts manuscripts meeting one or more of the following criteria:
Research articles and literature reviews (e.g. systematic, scoping, umbrella, integrative, etc.) about simulation
Innovative teaching/learning strategies using simulation
Articles updating guidelines, regulations, and legislative policies that impact simulation
Leadership for simulation
Simulation operations
Clinical and academic uses of simulation.