Lei Lei, Zhang Shuai, Yang Lin, Yang Cheng, Liu Zhangqin, Xu Hao, Su Shaoyu, Wan Xingli, Xu Min
Department of Pediatric Intensive Care Unit Nursing, West China Second University Hospital, Sichuan University/West China School of Nursing, Sichuan University, China; Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, Chengdu, Sichuan, China.
Key Laboratory of Birth Defects and Related Diseases of Women and Children (Sichuan University), Ministry of Education, Chengdu, Sichuan, China; Nursing Department, West China Second University Hospital, Sichuan University, China.
Int J Nurs Stud. 2023 Oct;146:104565. doi: 10.1016/j.ijnurstu.2023.104565. Epub 2023 Jul 16.
Accurately identifying patients at high risk of delirium is vital for timely preventive intervention measures. Approaches for identifying the risk of developing delirium among critically ill children are not well researched.
To develop and validate machine learning-based models for predicting delirium among critically ill children 24 h after pediatric intensive care unit (PICU) admission.
A prospective cohort study.
A large academic medical center with a 57-bed PICU in southwestern China from November 2019 to February 2022.
One thousand five hundred and seventy-six critically ill children requiring PICU stay over 24 h.
Five machine learning algorithms were employed. Delirium was screened by bedside nurses twice a day using the Cornell Assessment of Pediatric Delirium. Twenty-four clinical features from medical and nursing records during hospitalization were used to inform the models. Model performance was assessed according to numerous learning metrics, including the area under the receiver operating characteristic curve (AUC).
Of the 1576 enrolled patients, 929 (58.9 %) were boys, and the age ranged from 28 days to 15 years with a median age of 12 months (IQR 3 to 60 months). Among them, 1126 patients were assigned to the training cohort, and 450 were assigned to the validation cohort. The AUCs ranged from 0.763 to 0.805 for the five models, among which the eXtreme Gradient Boosting (XGB) model performed best, achieving an AUC of 0.805 (95 % CI, 0.759-0.851), with 0.798 (95 % CI, 0.758-0.834) accuracy, 0.902 sensitivity, 0.839 positive predictive value, 0.640 F1-score and a Brier score of 0.144. Almost all models showed lower predictive performance in children younger than 24 months than in older children. The logistic regression model also performed well, with an AUC of 0.789 (95 % CI, 0.739, 0.838), just under that of the XGB model, and was subsequently transformed into a nomogram.
Machine learning-based models can be established and potentially help identify critically ill children who are at high risk of delirium 24 h after PICU admission. The nomogram may be a beneficial management tool for delirium for PICU practitioners at present.
准确识别谵妄高危患者对于及时采取预防干预措施至关重要。关于识别危重症儿童发生谵妄风险的方法研究尚不充分。
开发并验证基于机器学习的模型，用于预测儿科重症监护病房（PICU）收治的危重症儿童入院24小时后发生谵妄的情况。
一项前瞻性队列研究。
中国西南部一家拥有57张床位PICU的大型学术医疗中心，研究时间为2019年11月至2022年2月。
1576名需要在PICU住院超过24小时的危重症儿童。
采用五种机器学习算法。床边护士每天使用康奈尔儿科谵妄评估量表对谵妄进行两次筛查。利用住院期间医疗和护理记录中的24项临床特征为模型提供信息。根据包括受试者操作特征曲线下面积（AUC）在内的多种学习指标评估模型性能。
在1576名入组患者中，929名（58.9%）为男性，年龄范围为28天至15岁，中位年龄为12个月（四分位间距3至60个月）。其中，1,126名患者被分配到训练队列，450名被分配到验证队列。五个模型的AUC范围为0.763至0.805，其中极端梯度提升（XGB）模型表现最佳，AUC为0.805（95%CI，0.759 - 0.851），准确率为0.798（95%CI，0.758 - 0.834），灵敏度为0.902, 阳性预测值为0.839，F1分数为0.640，布里尔评分为0.144。几乎所有模型在24个月以下儿童中的预测性能均低于年龄较大的儿童。逻辑回归模型表现也较好，AUC为0.789（95%CI，0.739, 0.838），略低于XGB模型，随后被转化为列线图。
可以建立基于机器学习的模型，可能有助于识别PICU入院24小时后发生谵妄高危的危重症儿童。目前，列线图可能是PICU从业者管理谵妄的有益工具。
