文献类型：期刊文献

英文题名：Large language models in emergency and critical care medicine: a comprehensive review of applications, challenges, and future directions

作者：Yang, Jie[1];Yang, Suibi;Shao, Ziyao[2];Chen, Tianqi[1];Shen, Hongjie[1];Zhou, Pengmin[1];Xia, Boming[1];Lei, Xiong[1];Wang, Lihui[3];Xue, Dong[2];Zheng, Shaojiang[4];Yu, Yuetian[3];Zhang, Zhongheng[1,5,6,7]

机构：[1]Zhejiang Univ, Sir Run Run Shaw Hosp, Sch Med, Dept Emergency Med, 3 Qingchun East Rd, Hangzhou 310016, Peoples R China;[2]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, 130 Meilong Rd, Shanghai 200237, Peoples R China;[3]Shanghai Jiao Tong Univ, Renji Hosp, Sch Med, Dept Crit Care Med, 160 Pujian Rd, Shanghai 200001, Peoples R China;[4]Hainan Med Univ, Engn Res Ctr Hainan Biol Sample Resources Major Di, Affiliated Hosp 1, Key Lab Emergency & Trauma,Minist Educ, 31 Longhua Rd, Haikou 570102, Peoples R China;[5]Zhejiang Univ, Sir Run Run Shaw Hosp, Sch Med, Key Lab Precis Med Diag & Monitoring Res Zhejiang, 3 Qingchun East Rd, Hangzhou 310016, Peoples R China;[6]Shaoxing Univ, Sch Med, 508 Huancheng West Rd, Shaoxing 312000, Peoples R China;[7]Longquan Ind Innovat Res Inst, 2 Ind Rd,Longyuan St, Longquan 323799, Lishui, Peoples R China

年份：2026

卷号：14

外文期刊名：BURNS & TRAUMA

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001785860800001)】；

基金：This study was supported by funding from the Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project (No. 2025ZD01902500, No. 2025ZD01902501, Z.Z.), the China National Key Research and Development Program (No. 2023YFC3603104, Z.Z.), the National Natural Science Foundation of China (82272180, 82472243, Z.Z.), the Fundamental Research Funds for the Central Universities (226-2025-00024, Z.Z.), the Huadong Medicine Joint Funds of the Zhejiang Provincial Natural Science Foundation of China under Grant No. LHDMD24H150001 (Z.Z.), the Key Research & Development Project of Zhejiang Province (2024C03240, Z.Z.), a collaborative scientific project co-established by the Science and Technology Department of the National Administration of Traditional Chinese Medicine and the Zhejiang Provincial Administration of Traditional Chinese Medicine (GZY-ZJ-KJ-24082, Z.Z.), General Health Science and Technology Program of Zhejiang Province (2024KY1099, Z.Z.), the Project of Zhejiang University Longquan Innovation Center (ZJDXLQCXZCJBGS2024016, Z.Z.), the Beijing Municipal Natural Science Foundation (No. 7252298, Z.Z.), Wu Jieping Medical Foundation Special Research Grant (320.6750.2024-23-07, Z.Z.), and the Zhejiang Provincial Science and Technology Program for Disease Control and Prevention (2026JKZ042, Z.Z.).

语种：英文

外文关键词：Large language models; Emergency and critical care medicine; Clinical decision support; Multimodal integration; Artificial intelligence; Precision medicine

摘要：Emergency and critical care medicine requires the rapid synthesis of heterogeneous clinical data under extreme time constraints. Early artificial intelligence tools lacked the flexibility to manage real-world patient heterogeneity. Large language models (LLMs) offer a paradigm shift by demonstrating advanced natural language understanding, cross-task generalization, and context-sensitive reasoning, thereby bridging the gap between fragmented algorithms and holistic clinical decision support. The effective deployment of these models is grounded in four methodological pillars: domain adaptation, knowledge integration, multimodal and temporal modeling, and transparency. Domain adaptation and knowledge integration specifically empower the context-sensitive reasoning required for high-stakes intensive care. This theoretical framework enables their application across clinical decision support, documentation optimization, medical education, and clinical research. Integrating continuous physiological waveforms with multi-omics data facilitates dynamic risk stratification for complex conditions like sepsis, while natural language-to-structured query language capabilities accelerate clinical data extraction and quality improvement. The transition of LLMs from experimental settings to routine clinical deployment remains constrained by model hallucinations, multimodal integration barriers, and unresolved ethical governance. Sustainable implementation requires a human-in-the-loop copilot design, rigorous multicenter prospective validation, and transparent regulatory frameworks. Addressing these challenges is essential to ensure that technological innovations safely translate into measurable improvements in patient survival and clinical outcomes.