发表机构
Indiana University Indianapolis（印第安纳大学印第安纳波利斯分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究利用12家医院13万余份培养数据，开发成本敏感XGBoost模型，在培养前预测ESBL表型，以指导经验性抗生素选择，实现高阴性预测值并减少不必要的碳青霉烯使用。
AI 中文摘要
对于疑似产ESBL肠杆菌科细菌感染的经验性抗生素治疗，必须在培养结果出来前48-72小时做出选择，这迫使临床医生在治疗不足（未能覆盖耐药菌感染）和过度使用碳青霉烯类药物（加剧耐药性）之间做出抉择。我们开发了一个成本敏感的XGBoost模型，在开具培养医嘱时，利用来自12家医院72,217名患者的132,955份培养（其中14.41%为ESBL表型）的45个培养前EHR特征，预测ESBL表型（对头孢曲松、头孢他啶、头孢吡肟或哌拉西林-他唑巴坦耐药）。培养样本按患者级别进行划分。在90%敏感性下，模型达到了95.8%的阴性预测值（NPV），将检测后ESBL概率降至4.2%，这一阈值可能支持在非ICU环境中安全地减少碳青霉烯使用，同时每1,000份培养中可避免307份不必要的广谱抗生素疗程，代价是每1,000份中漏诊14例ESBL病例。SHAP分析显示，既往ESBL定植是首要预测因子，其次为既往病原体负荷和社区贫困程度；移除贫困特征仅导致极小的性能损失（ΔAUROC = -0.020），从而支持在床旁公平部署。在严格的IDSA ESBL-E定义下，判别能力保持不变（AUROC 0.766），加入标本类型作为预测因子时AUROC为0.764，不进行任何类别不平衡校正时AUROC为0.762，且在不同菌株分层中AUROC介于0.71至0.78之间。
英文摘要
Empiric antibiotic therapy for suspected ESBL-producing Enterobacteriaceae must be selected 48-72 hours before culture results, forcing clinicians to choose between undertreating resistant infections and overusing carbapenems that drive further resistance. We developed a cost-sensitive XGBoost model predicting an ESBL phenotype (resistance to ceftriaxone, ceftazidime, cefepime or piperacillin-tazobactam) at culture ordering using 45 pre-culture EHR features across 132,955 cultures from 72,217 patients at 12 hospitals (14.41% with the ESBL phenotype). Cultures were partitioned at the patient level. At 90% sensitivity, the model achieved 95.8% NPV, reducing post-test ESBL probability to 4.2%, a threshold that may support safe carbapenem-sparing in non-ICU settings, while sparing 307 of every 1,000 cultures an unnecessary broad-spectrum course at the cost of 14 missed ESBL cases per 1,000. SHAP analysis identified prior ESBL colonization as the dominant predictor, ahead of prior organism burden and neighborhood deprivation; removing deprivation features caused minimal performance loss ($Δ\text{AUROC} = -0.020$), enabling equitable bedside deployment. Discrimination was unchanged under a strict IDSA ESBL-E definition (AUROC 0.766), with specimen type added as a predictor (0.764) and without any class-imbalance correction (0.762), and ranged from 0.71 to 0.78 across organism strata.
CommentsAccepted for presentation at American Medical Informatics Association (AMIA) Annual Symposium 2026
