Iapascurta Victor, Fiodorov Ion, Belii Adrian, Bostan Viorel
Department of Software Engineering and Automatics, Technical University of Moldova, Chisinnu, Republic of Moldova.
Department of Anesthesia and Intensive Care, Nicolae Testemitanu State University of Medicine and Pharmacy, Chisinnu, Republic of Moldova.
Healthc Inform Res. 2025 Apr;31(2):209-214. doi: 10.4258/hir.2025.31.2.209. Epub 2025 Apr 30.
The high incidence of sepsis necessitates the development of practical decision-making tools for intensivists, especially during the early, critical phases of management. This study evaluates a multi-agent system intended to assist clinicians with antibiotic therapy and adherence to current sepsis management guidelines before diagnostic results become available.
A multi-agent system incorporating three specialized agents was developed: a sepsis management agent, an antibiotic recommendation agent, and a sepsis guidelines compliance agent. A sepsis case from the MIMIC IV database, organized as a clinical vignette, was used to integrate and test these agents for generating management recommendations. The system leverages retrieval-augmented generation to improve decision-making through the integration of current literature and guidelines.
The application produced management recommendations for a sepsis case associated with pneumonia, including early initiation of broad-spectrum antibiotics and close monitoring for clinical deterioration. Two expert intensivists evaluated these recommendations as "acceptable" and reported moderate interrater agreement (Cohen's kappa = 0.622, p = 0.003) across various aspects of recommendation usefulness.
The multi-agent system shows promise in enhancing decision-making for sepsis management by optimizing antibiotic therapy and ensuring guideline compliance. However, reliance on a single case study limits the generalizability of the findings, highlighting the need for broader validation in diverse clinical settings to improve patient outcomes.
脓毒症的高发病率使得有必要为重症监护医生开发实用的决策工具，尤其是在管理的早期关键阶段。本研究评估了一个多智能体系统，旨在在诊断结果出来之前协助临床医生进行抗生素治疗并遵守当前的脓毒症管理指南。
开发了一个包含三个专门智能体的多智能体系统：一个脓毒症管理智能体、一个抗生素推荐智能体和一个脓毒症指南合规智能体。使用来自MIMIC IV数据库的一个脓毒症病例，整理成临床案例，来整合和测试这些智能体以生成管理建议。该系统利用检索增强生成技术，通过整合当前文献和指南来改善决策。
该应用程序为一个与肺炎相关的脓毒症病例生成了管理建议，包括早期使用广谱抗生素以及密切监测临床恶化情况。两名专家重症监护医生将这些建议评为“可接受”，并报告在建议有用性的各个方面，评分者间的一致性为中等（科恩kappa系数 = 0.622，p = 0.003）。
该多智能体系统在通过优化抗生素治疗和确保指南合规性来增强脓毒症管理决策方面显示出前景。然而，依赖单一案例研究限制了研究结果的普遍性，这突出表明需要在不同临床环境中进行更广泛的验证以改善患者预后。
