Early Prediction of Multiple Organ Dysfunction in the Pediatric Intensive Care Unit.
Early Prediction of Multiple Organ Dysfunction in the Pediatric Intensive Care Unit.
复制标题
DOI：
10.3389/fped.2021.711104
复制
发表时间：
2021
影响因子：
2.6
通讯作者：
Bembea MM
中科院分区：
文献类型：
--
作者：
Bose SN;Greenstein JL;Fackler JC;Sarma SV;Winslow RL;Bembea MM
目的：本研究的目的是建立早期预测儿科重症监护病房（PICU）患者发生多器官功能障碍（MOD）风险的模型。设计：该研究的设计是一项回顾性观察队列研究。背景：本研究的背景是马里兰州巴尔的摩约翰·霍普金斯医院的一个学术 PICU。患者：研究中纳入的患者年龄 <18 岁，于 2014 年 7 月至 2015 年 10 月期间入住 PICU。测量和主要结果：使用国际儿科脓毒症共识会议 (IPSCC) 和 Proulx 等人，从之前的 24 小时时间窗口每分钟生成器官功能障碍标签。 MOD 标准。早期的 MOD 预测模型是使用四种机器学习方法构建的：随机森林、XGBoost、GLMBoost 和 Lasso-GLM。从训练数据中学习到的最佳阈值用于检测高风险警报事件 (HRA)。对于 IPSCC 和 Proulx 标准，所有方法的早期预测模型的受试者工作特征曲线下面积均≥0.91。对于 IPSCC 和 Proulx 标准，分别使用随机森林（灵敏度：0.72，阳性预测值：0.70，F1 分数：0.71）和 XGBoost（灵敏度：0.8，阳性预测值：0.81，F1 分数：0.81）实现了最大 F1 分数方面的最佳性能。对于 IPSCC 和 Proulx 标准，随机森林的中位预警时间为 22.7 小时，XGBoost 模型的中位预警时间为 37 小时。在早期预警后 24 小时内对风险评分轨迹应用谱聚类，提供了阳性预测值≥0.93 的高风险组。结论：基于风险的患者监测的早期预测可以为 MOD 发病提供超过 22 小时的提前时间，对于 MOD 前确定的高风险组，阳性预测值≥0.93。
Objective: The objective of the study is to build models for early prediction of risk for developing multiple organ dysfunction (MOD) in pediatric intensive care unit (PICU) patients. Design: The design of the study is a retrospective observational cohort study. Setting: The setting of the study is at a single academic PICU at the Johns Hopkins Hospital, Baltimore, MD. Patients: The patients included in the study were <18 years of age admitted to the PICU between July 2014 and October 2015. Measurements and main results: Organ dysfunction labels were generated every minute from preceding 24-h time windows using the International Pediatric Sepsis Consensus Conference (IPSCC) and Proulx et al. MOD criteria. Early MOD prediction models were built using four machine learning methods: random forest, XGBoost, GLMBoost, and Lasso-GLM. An optimal threshold learned from training data was used to detect high-risk alert events (HRAs). The early prediction models from all methods achieved an area under the receiver operating characteristics curve ≥0.91 for both IPSCC and Proulx criteria. The best performance in terms of maximum F1-score was achieved with random forest (sensitivity: 0.72, positive predictive value: 0.70, F1-score: 0.71) and XGBoost (sensitivity: 0.8, positive predictive value: 0.81, F1-score: 0.81) for IPSCC and Proulx criteria, respectively. The median early warning time was 22.7 h for random forest and 37 h for XGBoost models for IPSCC and Proulx criteria, respectively. Applying spectral clustering on risk-score trajectories over 24 h following early warning provided a high-risk group with ≥0.93 positive predictive value. Conclusions: Early predictions from risk-based patient monitoring could provide more than 22 h of lead time for MOD onset, with ≥0.93 positive predictive value for a high-risk group identified pre-MOD.
登录
查看更多内容
DOI：
10.1097/pcc.0000000000000978
发表时间：
2017-01
期刊：
Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies
影响因子：
--
作者：
Lin JC;Spinella PC;Fitzgerald JC;Tucci M;Bush JL;Nadkarni VM;Thomas NJ;Weiss SL;Sepsis Prevalence, Outcomes, and Therapy Study Investigators
通讯作者：
Sepsis Prevalence, Outcomes, and Therapy Study Investigators
影响因子：
2.4
作者：
Feudtner C;Feinstein JA;Zhong W;Hall M;Dai D
通讯作者：
Dai D
影响因子：
8
作者：
Odetola, Folafoluwa O.;Gebremariam, Achamyeleh;Freed, Gary L.
通讯作者：
Freed, Gary L.
影响因子：
4.6
作者：
Liu, Ran;Greenstein, Joseph L.;Winslow, Raimond L.
通讯作者：
Winslow, Raimond L.
影响因子：
8.8
作者：
Graciano, AL;Balko, JA;Giroir, BP
通讯作者：
Giroir, BP