Albu Elena, Gao Shan, Stijnen Pieter, Rademakers Frank E, Janssens Christel, Cossey Veerle, Debaveye Yves, Wynants Laure, Van Calster Ben
Department of Development & Regeneration, KU Leuven, Leuven, Belgium.
Management Information Reporting Department, University Hospitals Leuven, Leuven, Belgium.
Diagn Progn Res. 2025 Jul 21;9(1):21. doi: 10.1186/s41512-025-00194-8.
Prognostic outcomes related to hospital admissions typically do not suffer from censoring, and can be modeled either categorically or as time-to-event. Competing events are common but often ignored. We compared the performance of static and dynamic random forest (RF) models to predict the risk of central line-associated bloodstream infections (CLABSI) using different outcome operationalizations.
We included data from 27,478 admissions to the University Hospitals Leuven, covering 30,862 catheter episodes (970 CLABSI, 1466 deaths and 28,426 discharges) to build static and dynamic RF models for binary (CLABSI vs no CLABSI), multinomial (CLABSI, discharge, death or no event), survival (time to CLABSI) and competing risks (time to CLABSI, discharge or death) outcomes to predict the 7-day CLABSI risk. Static models used information at the onset of the catheter episode, while dynamic models updated predictions daily for 30 days (landmark 0-30). We evaluated model performance across 100 train/test splits.
Performance of binary, multinomial and competing risks models was similar: AUROC was 0.74 for predictions at catheter onset, rose to 0.77 for predictions at landmark 5, and decreased thereafter. Survival models overestimated the risk of CLABSI (E:O ratios between 1.2 and 1.6), and had AUROCs about 0.01 lower than other models. Binary and multinomial models had lowest computation times. Models including multiple outcome events (multinomial and competing risks) display a different internal structure compared to binary and survival models, choosing different variables for early splits in trees.
In the absence of censoring, complex modelling choices do not considerably improve the predictive performance compared to a binary model for CLABSI prediction in our studied settings. Survival models censoring the competing events at their time of occurrence should be avoided.
与住院相关的预后结果通常不存在删失问题，可以按类别建模或作为事件发生时间建模。竞争事件很常见，但常常被忽视。我们比较了静态和动态随机森林（RF）模型在使用不同结局操作化方法预测中心静脉导管相关血流感染（CLABSI）风险方面的性能。
我们纳入了鲁汶大学医院27478例住院病例的数据，涵盖30862次导管使用情况（970例CLABSI、1466例死亡和28426例出院），以构建用于二元（CLABSI与非CLABSI）、多项（CLABSI、出院、死亡或无事件）、生存（至CLABSI的时间）和竞争风险（至CLABSI、出院或死亡的时间）结局的静态和动态RF模型，以预测7天CLABSI风险。静态模型使用导管使用开始时的信息，而动态模型在30天内（时间点0 - 30）每日更新预测。我们在100次训练/测试分割中评估模型性能。
二元、多项和竞争风险模型的性能相似：导管开始时预测的曲线下面积（AUROC）为0.74，在时间点5时预测的AUROC升至0.77，并在之后下降。生存模型高估了CLABSI风险（估计值与观察值之比在1.2至1.6之间），且AUROC比其他模型低约0.01。二元和多项模型的计算时间最短。与二元和生存模型相比，包含多个结局事件（多项和竞争风险）的模型显示出不同的内部结构，在树的早期分割中选择不同的变量。
在不存在删失的情况下，与我们研究环境中用于CLABSI预测的二元模型相比，复杂的建模选择并不能显著提高预测性能。应避免在竞争事件发生时对其进行删失的生存模型。
