Department of Emergency Medicine, Seoul National University Hospital, Seoul, Korea.
Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Korea.
Sci Rep. 2021 Jan 13;11(1):1263. doi: 10.1038/s41598-020-80474-z.
The aim of this study was to develop a predictive model of pediatric mortality in the early stages of intensive care unit (ICU) admission using machine learning. Patients less than 18 years old who were admitted to ICUs at four tertiary referral hospitals were enrolled. Three hospitals were designated as the derivation cohort for machine learning model development and internal validation, and the other hospital was designated as the validation cohort for external validation. We developed a random forest (RF) model that predicts pediatric mortality within 72 h of ICU admission, evaluated its performance, and compared it with the Pediatric Index of Mortality 3 (PIM 3). The area under the receiver operating characteristic curve (AUROC) of RF model was 0.942 (95% confidence interval [CI] = 0.912-0.972) in the derivation cohort and 0.906 (95% CI = 0.900-0.912) in the validation cohort. In contrast, the AUROC of PIM 3 was 0.892 (95% CI = 0.878-0.906) in the derivation cohort and 0.845 (95% CI = 0.817-0.873) in the validation cohort. The RF model in our study showed improved predictive performance in terms of both internal and external validation and was superior even when compared to PIM 3.
本研究旨在使用机器学习开发一种在重症监护病房（ICU）入院早期预测儿科死亡率的预测模型。我们招募了年龄小于 18 岁且在四家三级转诊医院 ICU 入院的患者。其中三家医院被指定为机器学习模型开发和内部验证的推导队列，另一家医院被指定为外部验证的验证队列。我们开发了一种预测 ICU 入院后 72 小时内儿科死亡率的随机森林（RF）模型，评估了其性能，并将其与儿科死亡率 3 指数（PIM 3）进行了比较。在推导队列中，RF 模型的受试者工作特征曲线下面积（AUROC）为 0.942（95%置信区间 [CI]：0.912-0.972），在验证队列中为 0.906（95%CI：0.900-0.912）。相比之下，在推导队列中，PIM 3 的 AUROC 为 0.892（95%CI：0.878-0.906），在验证队列中为 0.845（95%CI：0.817-0.873）。我们研究中的 RF 模型在内部和外部验证方面均显示出了改进的预测性能，甚至优于 PIM 3。
