Pappy George, Aczon Melissa, Wetzel Randall, Ledbetter David
The Laura P. and Leland K. Whittier Virtual PICU, Children's Hospital Los Angeles, Los Angeles, CA, United States.
JMIR Med Inform. 2022 Mar 3;10(3):e31760. doi: 10.2196/31760.
High flow nasal cannula (HFNC) provides noninvasive respiratory support for children who are critically ill who may tolerate it more readily than other noninvasive ventilation (NIV) techniques such as bilevel positive airway pressure and continuous positive airway pressure. Moreover, HFNC may preclude the need for mechanical ventilation (intubation). Nevertheless, NIV or intubation may ultimately be necessary for certain patients. Timely prediction of HFNC failure can provide an indication for increasing respiratory support.
The aim of this study is to develop and compare machine learning (ML) models to predict HFNC failure.
A retrospective study was conducted using the Virtual Pediatric Intensive Care Unit database of electronic medical records of patients admitted to a tertiary pediatric intensive care unit between January 2010 and February 2020. Patients aged <19 years, without apnea, and receiving HFNC treatment were included. A long short-term memory (LSTM) model using 517 variables (vital signs, laboratory data, and other clinical parameters) was trained to generate a continuous prediction of HFNC failure, defined as escalation to NIV or intubation within 24 hours of HFNC initiation. For comparison, 7 other models were trained: a logistic regression (LR) using the same 517 variables, another LR using only 14 variables, and 5 additional LSTM-based models using the same 517 variables as the first LSTM model and incorporating additional ML techniques (transfer learning, input perseveration, and ensembling). Performance was assessed using the area under the receiver operating characteristic (AUROC) curve at various times following HFNC initiation. The sensitivity, specificity, and positive and negative predictive values of predictions at 2 hours after HFNC initiation were also evaluated. These metrics were also computed for a cohort with primarily respiratory diagnoses.
A total of 834 HFNC trials (455 [54.6%] training, 173 [20.7%] validation, and 206 [24.7%] test) met the inclusion criteria, of which 175 (21%; training: 103/455, 22.6%; validation: 30/173, 17.3%; test: 42/206, 20.4%) escalated to NIV or intubation. The LSTM models trained with transfer learning generally performed better than the LR models, with the best LSTM model achieving an AUROC of 0.78 versus 0.66 for the 14-variable LR and 0.71 for the 517-variable LR 2 hours after initiation. All models except for the 14-variable LR achieved higher AUROCs in the respiratory cohort than in the general intensive care unit population.
ML models trained using electronic medical record data were able to identify children at risk of HFNC failure within 24 hours of initiation. LSTM models that incorporated transfer learning, input data perseveration, and ensembling showed improved performance compared with the LR and standard LSTM models.
高流量鼻导管（HFNC）为重症儿童提供无创呼吸支持，与其他无创通气（NIV）技术（如双水平气道正压通气和持续气道正压通气）相比，这些儿童可能更容易耐受。此外，HFNC可能无需进行机械通气（插管）。然而，对于某些患者，最终可能仍需要NIV或插管。及时预测HFNC失败可为增加呼吸支持提供依据。
本研究旨在开发并比较用于预测HFNC失败的机器学习（ML）模型。
使用2010年1月至2020年2月期间入住三级儿科重症监护病房患者的电子病历虚拟儿科重症监护病房数据库进行回顾性研究。纳入年龄<19岁、无呼吸暂停且接受HFNC治疗的患者。使用517个变量（生命体征、实验室数据和其他临床参数）训练长短期记忆（LSTM）模型，以生成对HFNC失败的连续预测，HFNC失败定义为在开始HFNC治疗后24小时内升级为NIV或插管。为作比较，还训练了7个其他模型：使用相同517个变量的逻辑回归（LR）模型、仅使用14个变量的另一个LR模型，以及另外5个基于LSTM的模型，这些模型使用与第一个LSTM模型相同的517个变量并结合了其他ML技术（迁移学习、输入保留和集成）。在开始HFNC治疗后的不同时间，使用受试者操作特征（AUROC）曲线下面积评估性能。还评估了开始HFNC治疗后2小时预测的敏感性、特异性以及阳性和阴性预测值。这些指标也针对主要为呼吸诊断的队列进行了计算。
共有834次HFNC试验（455次[54.6%]训练、173次[20.7%]验证和206次[24.7%]测试）符合纳入标准，其中175次（21%；训练：103/455，22.6%；验证：30/173，17.3%；测试：42/206，20.4%）升级为NIV或插管。采用迁移学习训练的LSTM模型通常比LR模型表现更好，最佳LSTM模型在开始治疗2小时后的AUROC为0.78，而14变量LR模型为0.66，517变量LR模型为0.71。除14变量LR模型外，所有模型在呼吸队列中的AUROC均高于普通重症监护病房人群。
使用电子病历数据训练的ML模型能够在开始治疗后24小时内识别有HFNC失败风险的儿童。与LR和标准LSTM模型相比，纳入迁移学习、输入数据保留和集成的LSTM模型表现更佳。
