文献速递医院感染防控

结合大语言模型与规则算法提升导管相关尿路感染监测效率

The Best of Both Worlds: How Combining a Large Language Model and a Rule-Based Algorithm Makes Catheter-Associated Urinary Tract Infection Surveillance More Efficient.
PubMed 文献 · Clin Infect Dis · 2026-01-01

该研究基于2021至2024年Barnes-Jewish医院电子监测算法标记的919例潜在CAUTI病例(其中291例CAUTI、628例非CAUTI),比较了不同应用NHSN CAUTI定义的方法。结果显示,规则逻辑联合CLEAR输入大语言模型达到最高灵敏度90.0%和特异度93.5%,经专家裁定调整假阴性和假阳性后灵敏度93.6%、特异度98.6%。结论认为大语言模型可显著提升CAUTI监测效率并减少人工病历审查时间。

要点

  • 规则逻辑联合CLEAR输入LLM的CAUTI监测灵敏度90.0%、特异度93.5%。
  • 专家裁定调整后灵敏度93.6%、特异度98.6%。
  • 假阴性主要因提供给模型的临床记录中缺少症状信息。

核心结论

  • 在现有算法基础上增加大语言模型能力可显著提升CAUTI监测效率,并可能减少感染防控人员人工病历审查的时间。

研究设计与样本

  • 研究分析了Barnes-Jewish医院2021至2024年由电子监测算法标记的919例潜在CAUTI病例,其中291例CAUTI、628例非CAUTI由 trained infection preventionists (IPs) 分类。
  • 比较了从电子病历提取临床数据后应用National Healthcare Safety Network (NHSN) CAUTI定义的不同方法。

主要发现

  • 多数患者为女性(61.6%),中位年龄68岁(IQR 58, 77)。
  • 规则逻辑联合Clinical Entity Augmented Retrieval (CLEAR)输入大语言模型达到最高灵敏度90.0%和特异度93.5%。
  • 经专家裁定调整假阴性和假阳性后,灵敏度为93.6%,特异度为98.6%。
  • 假阴性病历审查显示,与金标准不一致主要因提供给模型的临床记录中缺少症状信息。

关键数值与推荐

  • 规则逻辑联合CLEAR输入LLM:灵敏度90.0%,特异度93.5%。
  • 专家裁定调整后:灵敏度93.6%,特异度98.6%。

临床怎么用

  • 可将规则算法与大语言模型结合用于CAUTI监测,以减少感染防控人员人工病历审查时间。
  • 优化提供给模型的临床信息(如补充症状信息)可能进一步改善性能。

局限性

  • 假阴性与金标准不一致主要归因于提供给模型的临床记录中缺少症状信息。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Catheter-associated urinary tract infection (CAUTI) surveillance is critical for patient safety. Many healthcare systems use electronic algorithms to flag candidate infection events but still require manual chart review to confirm CAUTI cases. We evaluated the use of a large language model (LLM) to enhance CAUTI surveillance. METHODS: We analyzed 919 potential CAUTI cases flagged by the electronic surveillance algorithm at Barnes-Jewish Hospital from 2021 to 2024. These cases were previously classified as 291 CAUTIs and 628 non-CAUTIs by trained infection preventionists (IPs). Several approaches for applying the National Healthcare Safety Network (NHSN) CAUTI definition after extracting clinical data from the electronic medical record (EMR) were compared. RESULTS: Most patients were female (61.6%) with a median age 68 years (IQR 58, 77). Combining rule-based logic with Clinical Entity Augmented Retrieval (CLEAR) input into an LLM achieved the highest sensitivity (90.0%) and specificity (93.5%). Adjustment of false negatives and false positives after expert adjudication showed sensitivity of 93.6% and specificity of 98.6%. Chart review of false negatives revealed that disagreement with the gold standard mainly occurred due to missing symptom information in clinical documentation provided to the model. CONCLUSIONS: Augmenting the existing algorithmic approach with LLM capabilities significantly enhances CAUTI surveillance and may improve efficiency by reducing the amount of time IPs spend performing manual chart review. Further improvements could be made by optimizing the clinical information presented to the model.

来源:Clin Infect Dis,查看原文。版权归原作者所有。

引用

  1. Nordman J, Najjuuko C, Jeschke N, et al. The Best of Both Worlds: How Combining a Large Language Model and a Rule-Based Algorithm Makes Catheter-Associated Urinary Tract Infection Surveillance More Efficient. Clin Infect Dis. 2026. PMID: 42132396. doi:10.1093/cid/ciag301

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。