机器学习模型基于入院特征无法理想预测全球肝硬化队列中的医院获得性感染
基于CLEARED联盟全球127中心8263例肝硬化住院患者的前瞻性数据,使用入院当日临床变量构建随机森林、极端梯度提升和神经网络模型预测医院获得性感染。随机森林模型AUC为0.69,优于其他模型(AUC 0.66,P=0.043),但无模型AUC≥0.80;在10%预测概率阈值下随机森林敏感度仅75.4%、特异度52.9%、阳性预测值15.9%。结论认为入院当日数据无法准确预测医院获得性感染,所有肝硬化住院患者均应接受规范化感染控制措施。
要点
- 随机森林模型AUC 0.69,优于极端梯度提升、神经网络和逻辑回归(AUC均0.66,P=0.043)。
- 无模型AUC≥0.80,10%阈值下随机森林敏感度75.4%、特异度52.9%、阳性预测值15.9%。
- 医院获得性感染发生率为10.5%,与住院死亡(31.9% vs 8.1%)和肝移植(4.8% vs 1.9%)相关。
核心结论
- 基于入院当日临床数据的机器学习模型无法准确预测肝硬化患者的医院获得性感染。
- 所有肝硬化住院患者均应接受规范化的感染控制措施。
研究设计与样本
- CLEARED联盟前瞻性纳入来自37个国家127个中心的肝硬化住院患者,共8263例。
- 使用入院当日临床数据,构建随机森林、极端梯度提升和神经网络三种机器学习模型预测医院获得性感染,并与逻辑回归比较。
- 数据按结局分层以80:20比例分为训练集和测试集,采用受试者工作特征曲线下面积(AUC)比较模型。
主要发现
- 8263例患者年龄55.90±13.34岁,男性占64.1%;869例(10.5%)发生医院获得性感染,中位发生时间为入院后6(4-11)天。
- 主要感染类型为呼吸道感染(29.6%)、尿路感染(15.7%)和自发性细菌性腹膜炎(13.5%)。
- 医院获得性感染更常见于低/中低收入国家患者、严重肝病、酒精病因及入院时存在感染的患者。
- 医院获得性感染与住院死亡(31.9% vs 8.1%,P<0.001)和肝移植(4.8% vs 1.9%,P<0.001)相关。
- 随机森林模型AUC 0.69,校准良好(Brier评分0.09),优于极端梯度提升、神经网络和逻辑回归(AUC均0.66,P=0.043);但无模型AUC≥0.80。
临床怎么用
- 不应依赖入院当日机器学习模型识别高风险患者,所有肝硬化住院患者均应执行规范化感染控制措施。
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
INTRODUCTION: Nosocomial infections (NIs) in cirrhosis are associated with high mortality but could be preventable. Logistic regression (LR) models have failed to identify high-risk patients. We aimed to develop machine learning (ML) models to predict NI. METHODS: The CLEARED consortium consists of prospectively enrolled cirrhosis inpatients from >120 centers. Using day-of-admission clinical data, 3 ML approaches (random forest [RF], extreme gradient boosting, and neural networks [NNs]) were used to predict NI. Data were split 80:20 for training and testing stratified by the outcome. Models were compared using area under the receiver operating characteristic curve (AUC). RESULTS: In total, 8,263 patients (55.90 ± 13.34 years; 64.1% men) from 127 centers in 37 countries were included. NI developed in 869 (10.5%), a median of 6 (4-11) days of postadmission. Major NIs were respiratory (29.6%) and urinary tract infection (15.7%), and spontaneous bacterial peritonitis (13.5%). NIs occurred more frequently in patients from low/low-middle income countries and those with severe liver disease, alcohol etiology, and admission infections. NIs were associated with inpatient mortality (31.9% vs 8.1%, P < 0.001) and liver transplantation (4.8% vs 1.9%, P < 0.001). Although the RF model (AUC 0.69) showed good calibration (Brier score 0.09), outperforming extreme gradient boosting, neural network, and LR models (AUC 0.66 for all; LR comparison P = 0.043), no model achieved AUC ≥0.80 for clinical utility. At 10% predicted probability threshold, the RF model demonstrated only 75.4% sensitivity, 52.9% specificity, and 15.9% positive predictive value (PPV). DISCUSSION: NIs cannot be accurately predicted from day-of-admission data using ML models, even in a large, prospective, global cirrhosis cohort. Every hospitalized patient with cirrhosis should receive protocolized infection control measures.
引用
- Silvey S, Choudhury AK, Kamath PS, et al. Machine Learning Models Using Hospital Admission Characteristics Do Not Optimally Predict Nosocomial Infection Development in a Global Cirrhosis Cohort. Am J Gastroenterol. 2026. PMID: 42043180. doi:10.14309/ajg.0000000000004031
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。