跳到正文
原文
Nature 健康护理主题·· 14 天前AI 评分25

大型语言模型在创伤初步评估中的顺序一致性:一项自发xABCDE优先级排序的比较研究

Sequence fidelity of large language models in trauma primary survey: a comparative in silico study of spontaneous xABCDE-consistent prioritisation

AI 导读

研究评估了三种大型语言模型(GPT-4.1-mini、Gemini 2.5 Flash和Claude Haiku 4.5)在未提及xABCDE优先级的情况下,自发生成创伤管理动作的顺序一致性。在150个模型-案例-人物查询中,至少一次运行中出现顺序混乱的比例为72.7%(95% CI 65.0–79.2),表明这些模型在处理依赖顺序的紧急护理任务时,顺序一致性可能是一个有用的衡量指标。

正文

Scientific Reports (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

Large language models (LLMs) are increasingly evaluated for clinical decision support, but trauma care requires not only correct actions but also appropriate prioritisation. We assessed whether three LLMs spontaneously generated trauma-management actions in an xABCDE-consistent order and whether specialty-based system prompts affected prioritisation. Ten investigator-developed polytrauma cases were submitted to GPT-4.1-mini, Gemini 2.5 Flash and Claude Haiku 4.5 under five prompt conditions. The prompt requested six brief clinical actions without mentioning xABCDE or any predefined trauma algorithm. This generated 150 unique model-case-persona queries, each repeated once. Sequence disorder occurred in at least one run in 109/150 queries (72.7%; 95% CI 65.0–79.2) and in both runs in 101/150 (67.3%), with high inter-run agreement (Cohen’s κ = 0.873). At-least-one-run disorder occurred in 17/50 GPT-4.1-mini, 43/50 Gemini and 49/50 Claude queries. In both cases requiring immediate external haemorrhage control, no model placed haemorrhage control first in any condition or run. Persona-related advancement occurred in 3/90 eligible queries, whereas premature secondary-care recommendations occurred in 84/150. These findings suggest that sequence fidelity may provide a useful process-oriented safety measure when evaluating LLMs for sequence-dependent emergency-care tasks.

Abbreviations

AI:

Artificial intelligence

API:

Application programming interface

ATLS:

Advanced trauma life support

CT:

Computed tomography

FAST:

Focused assessment with sonography for trauma

GEE:

Generalized estimating equations

LLM:

Large language model

MI-CLAIM:

Minimum information about clinical artificial intelligence modeling

SaMD:

Software as a medical device

TRIPOD-LLM:

Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis using large language models

xABCDE:

External haemorrhage, airway, breathing, circulation, disability, exposure

Acknowledgements

Not applicable.

Funding

This research received no specific grant from any funding agency in the public, commercial or not-for-profit sectors.

Author information

Authors and Affiliations

  1. Department of Emergency Medicine, Faculty of Medicine, Kastamonu University, Kastamonu, Türkiye

    Miraç Koç, Hasan Burak Kaya & Fatma Mutlu Kukul Güven

  2. Department of Computer Engineering, Faculty of Engineering, Bozok University, Yozgat, Türkiye

    Ahmet Sertol Köksal

Authors

  1. Miraç Koç
  2. Hasan Burak Kaya
  3. Fatma Mutlu Kukul Güven
  4. Ahmet Sertol Köksal

Corresponding author

Correspondence to Miraç Koç.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

Not applicable. The study used only investigator-created simulated trauma cases and model-generated outputs. It did not involve human participants, identifiable or anonymised human data, human tissue, animals or biological samples. Therefore, ethics committee approval and informed consent were not required.

Consent for publication

Not applicable. The manuscript does not contain any individual person’s data, images or videos.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Koç, M., Kaya, H.B., Güven, F.M.K. et al. Sequence fidelity of large language models in trauma primary survey: a comparative in silico study of spontaneous xABCDE-consistent prioritisation. Sci Rep (2026). https://doi.org/10.1038/s41598-026-78435-z

Download citation

  • Received: 08 July 2026

  • Accepted: 26 October 2026

  • Published: 06 November 2026

  • DOI: https://doi.org/10.1038/s41598-026-78435-z

Keywords

来源:Nature 健康护理主题 · nature.com