文献速递细菌感染、耐药与抗菌药物

个性化药敏谱:多任务机器学习框架同时预测肠杆菌科细菌耐药谱并提升碳青霉烯耐药检测

Personalized Antibiogram: A Novel Multitask Machine Learning Framework for Simultaneous Prediction of Antimicrobial Resistance Profile With Enhanced Detection of Carbapenem Resistance in Enterobacteriaceae.
PubMed 文献 · Clin Infect Dis · 2026-01-01

本研究开发了多任务极端梯度提升(XGBoost)模型,利用电子健康记录(EHR)结构化数据同时预测大肠埃希菌和克雷伯菌属对8类抗菌药物的耐药性。回顾性多中心研究纳入127家医院2017年1月至2024年9月的分离株,多任务模型在测试集上总体AUROC达0.779(大肠埃希菌)和0.810(克雷伯菌属),优于传统医院药敏谱和单目标模型,并改善碳青霉烯耐药检测的校准和假阴性率。

要点

  • 多任务XGBoost可同时预测8类抗菌药物耐药概率,生成个体化药敏谱。
  • 测试集总体AUROC:大肠埃希菌0.779,克雷伯菌属0.810。
  • 多任务方法改善碳青霉烯耐药检测的校准并降低假阴性率。

核心结论

  • 多任务XGBoost框架能准确预测常见革兰阴性病原体的个体化耐药谱,优于传统药敏谱和单目标模型。
  • 个性化药敏谱可能改善经验性治疗选择,包括在低流行区检测碳青霉烯耐药。

研究设计与样本

  • 回顾性多中心研究,数据来自127家医院和>1400家诊所,2017年1月至2024年9月收集的大肠埃希菌和克雷伯菌属分离株。
  • 2017年1月至2023年9月数据用于模型开发,2023年10月至2024年9月数据用于模拟前瞻性测试。
  • 训练队列包括536 252株大肠埃希菌和246 898株克雷伯菌属;测试队列包括75 138株和38 015株。
  • 模型性能与传统医院药敏谱和单目标XGBoost模型比较。

主要发现

  • 测试数据上多任务模型总体AUROC为0.779(大肠埃希菌)和0.810(克雷伯菌属)。
  • 各类别性能良好至优秀,AUROC范围0.743-0.847。
  • 多任务方法改善校准并降低碳青霉烯耐药的假阴性率,同时预测所有目标抗菌药物的个体化耐药概率。

临床怎么用

  • 可利用EHR结构化数据生成个体化药敏谱,辅助经验性抗菌药物选择。
  • 在低流行区可借助模型提升碳青霉烯耐药的检测能力。

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: Conventional hospital antibiograms summarize aggregated resistance rates, limiting their utility for individualized antimicrobial selection. Existing statistical and machine learning models predict each phenotype separately, ignoring correlations among resistance profiles. We developed novel multitask extreme gradient boosting (XGBoost) models utilizing structured data in electronic health records (EHRs) to predict resistance to 8 antimicrobial classes simultaneously and evaluated their performance within the Veterans Health Administration (VHA). METHODS: We conducted a retrospective multicenter study of Escherichia coli and Klebsiella spp. isolates collected at 127 hospitals and >1400 clinics from January 2017 to September 2024. Data from January 2017 to September 2023 were used for model development, while data from October 2023 to September 2024 were used for simulated prospective testing. Model performances were compared to hospital antibiograms and single-target XGBoost models. RESULTS: The training cohort included 536 252 E. coli and 246 898 Klebsiella spp. isolates; the test cohort included 75 138 and 38 015 isolates, respectively. On the test data, the multitask model achieved overall areas under the receiver operating characteristic curve (AUROCs) of 0.779 (E. coli) and 0.810 (Klebsiella spp.), with good to excellent per-class performance (AUROC range, 0.743-0.847). A multitask approach improved calibration and decreased false-negative rates for carbapenem resistance while predicting individualized resistance probabilities for all target antimicrobials simultaneously ("personalized antibiograms"). CONCLUSIONS: A multitask XGBoost framework can accurately predict individualized resistance profiles for common Gram-negative pathogens, outperforming conventional antibiograms and single-target models. Personalized antibiograms may enhance the selection of empiric therapy, including the detection of carbapenem resistance in low-endemicity settings.

来源:Clin Infect Dis,查看原文。版权归原作者所有。

引用

  1. Goto M, Bandyopadhyay A, Shi Q, et al. Personalized Antibiogram: A Novel Multitask Machine Learning Framework for Simultaneous Prediction of Antimicrobial Resistance Profile With Enhanced Detection of Carbapenem Resistance in Enterobacteriaceae. Clin Infect Dis. 2026. PMID: 41546531. doi:10.1093/cid/ciag027

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。