Enterprise Data and Analytics, University of Maryland Medical System, Linthicum Heights, MD, United States of America.
Rady Children's Hospital, San Diego, CA, United States of America.
PLoS One. 2023 Aug 4;18(8):e0289763. doi: 10.1371/journal.pone.0289763. eCollection 2023.
Acute respiratory failure is a life-threatening clinical outcome in critically ill pediatric patients. In severe cases, patients can require mechanical ventilation (MV) for survival. Early recognition of these patients can potentially help clinicians alter the clinical course and lead to improved outcomes.
To build a data-driven model for early prediction of the need for mechanical ventilation in pediatric intensive care unit (PICU) patients.
The study consists of a single-center retrospective observational study on a cohort of 13,651 PICU patients admitted between 1/01/2010 and 5/15/2018 with a prevalence of 8.06% for MV due to respiratory failure. XGBoost (extreme gradient boosting) and a convolutional neural network (CNN) using medication history were used to develop a prediction model that could yield a time-varying "risk-score"-a continuous probability of whether a patient will receive MV-and an ideal global threshold was calculated from the receiver operating characteristics (ROC) curve. The early prediction point (EPP) was the first time the risk-score surpassed the optimal threshold, and the interval between the EPP and the start of the MV was the early warning period (EWT). Spectral clustering identified patient groups based on risk-score trajectories after EPP.
A clinical and medication history-based model achieved a 0.89 area under the ROC curve (AUROC), 0.6 sensitivity, 0.95 specificity, 0.55 positive predictive value (PPV), and 0.95 negative predictive value (NPV). Early warning time (EWT) median [inter-quartile range] of this model was 9.9[4.2-69.2] hours. Clustering risk-score trajectories within a six-hour window after the early prediction point (EPP) established three patient groups, with the highest risk group's PPV being 0.92.
This study uses a unique method to extract and apply medication history information, such as time-varying variables, to identify patients who may need mechanical ventilation for respiratory failure and provide an early warning period to avert it.
急性呼吸衰竭是危重症儿科患者的一种危及生命的临床结局。在严重的情况下，患者可能需要机械通气（MV）才能存活。早期识别这些患者可能有助于临床医生改变临床过程，并导致更好的结果。
建立一个数据驱动的模型，用于预测儿科重症监护病房（PICU）患者需要机械通气的早期情况。
本研究包括一项单中心回顾性观察性研究，纳入了 2010 年 1 月 1 日至 2018 年 5 月 15 日期间入住 PICU 的 13651 例患者，MV 因呼吸衰竭的患病率为 8.06%。使用药物史的 XGBoost（极端梯度提升）和卷积神经网络（CNN）来开发一个预测模型，该模型可以产生一个时变的“风险评分”-患者接受 MV 的连续概率-并从接收者操作特征（ROC）曲线计算出理想的全局阈值。早期预测点（EPP）是风险评分首次超过最佳阈值的时间，EPP 与 MV 开始之间的间隔是早期预警期（EWT）。频谱聚类根据 EPP 后风险评分轨迹识别患者群体。
基于临床和药物史的模型获得了 0.89 的 ROC 曲线下面积（AUROC）、0.6 的灵敏度、0.95 的特异性、0.55 的阳性预测值（PPV）和 0.95 的阴性预测值（NPV）。该模型的早期预警时间（EWT）中位数[四分位间距]为 9.9[4.2-69.2]小时。在 EPP 后 6 小时的窗口内对风险评分轨迹进行聚类，确定了三个患者群体，其中最高风险群体的 PPV 为 0.92。
本研究使用一种独特的方法提取和应用药物史信息，如时变变量，以识别可能需要机械通气治疗呼吸衰竭的患者，并提供早期预警期以避免这种情况。
