急诊科分流决策:多智能体AI系统回顾性研究显示性能存在乐观偏倚
Safety-constrained multi-agent AI for emergency department disposition decisions
研究团队在以色列一家医院回顾了469例成人急诊就诊记录,开发并测试了结合角色专责语言模型与确定性规则的「SMARTriage AI」多智能体系统用于推荐入院或出院决策。
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
Emergency department disposition decisions integrate measurements, narratives and contextual risk. We developed SMARTriage AI, a multi-agent system combining role-specialized language-model agents with deterministic rules, intended as safety gates, to recommend admission or discharge. In a retrospective, single-center development study of 469 valid-label adult internal medicine and geriatric encounters from one 24-h period (468 analyzed; 154 admitted), prompts and rules were refined over about 30 cycles on the same cohort, without a held-out set. Apparent accuracy was 88.2% (95% CI, 85.0–90.9%) and admission recall 96.1%. Accuracy was 97.2% with physician summary or recommendations text (n = 248) and 78.2% without it (n = 220); with the text withheld it was 65.0%. After peer review, a redesigned system (v2), evaluated on all 469 encounters under a protocol locked before the runs, discriminated worse than a single language-model agent (Setting A AUC 0.794 vs. 0.821–0.823). At the pre-specified thresholds, accuracy was 76.3% for v2 versus 67.0% for discharging everyone. The multi-agent design did not outperform a single agent, and apparent performance was optimistically biased by development on the evaluation encounters and by disposition information in physician documentation. Evaluation on unseen encounters, and external and prospective validation, are required before any conclusion about clinical utility.
Author information
Authors and Affiliations
Department of Biomedical Engineering, Faculty of Engineering, Tel Aviv University, Tel Aviv, Israel
Lior Tsafrir & Liniv Arama
Sheba Medical Center, Ramat Gan, Israel
Gal Ben Haim
DataMED Lab, Gray Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel
Mor Saban
Authors
- Lior Tsafrir
- Liniv Arama
- Gal Ben Haim
- Mor Saban
Corresponding author
Correspondence to Mor Saban.
Ethics declarations
Funding
This research received no specific grant from any funding agency.
Competing interests
The authors declare no competing interests.
Ethics approval and consent to participate
This study was approved by the Institutional Review Board of Sheba Medical Center (SMC) (IRB no. 0799-23-MHS) and was conducted in accordance with the Declaration of Helsinki and applicable national regulations. Due to the retrospective nature of the study, the Institutional Review Board of SMC waived the need to obtain informed consent.
Consent for publication
Not applicable.
Use of AI tools
See “Methods” section, ‘Use of AI-assisted tools’.
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/.
About this article
Cite this article
Tsafrir, L., Arama, L., Ben Haim, G. et al. Safety-constrained multi-agent AI for emergency department disposition decisions. Sci Rep (2026). https://doi.org/10.1038/s41598-026-80974-4
Received: 24 July 2026
Accepted: 12 November 2026
Published: 18 November 2026
DOI: https://doi.org/10.1038/s41598-026-80974-4
Keywords
来源:Nature 健康护理主题 · nature.com