Krachman Joshua A, Patricoski Jessica A, Le Christopher T, Park Jina, Zhang Ruijing, Gong Kirby D, Gangan Indranuj, Winslow Raimond L, Greenstein Joseph L, Fackler James, Sochet Anthony A, Bergmann Jules P
Department of Biomedical Engineering, Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD, United States.
Division of Health Sciences Informatics, Johns Hopkins University School of Medicine, Baltimore, MD, United States.
Front Pediatr. 2021 Nov 8;9:734753. doi: 10.3389/fped.2021.734753. eCollection 2021.
High flow nasal cannula (HFNC) is commonly used as non-invasive respiratory support in critically ill children. There are limited data to inform consensus on optimal device parameters, determinants of successful patient response, and indications for escalation of support. Clinical scores, such as the respiratory rate-oxygenation (ROX) index, have been described as a means to predict HFNC non-response, but are limited to evaluating for escalations to invasive mechanical ventilation (MV). In the presence of apparent HFNC non-response, a clinician may choose to increase the HFNC flow rate to hypothetically prevent further respiratory deterioration, transition to an alternative non-invasive interface, or intubation for MV. To date, no models have been assessed to predict subsequent escalations of HFNC flow rates after HFNC initiation. To evaluate the abilities of tree-based machine learning algorithms to predict HFNC flow rate escalations. We performed a retrospective, cohort study assessing children admitted for acute respiratory failure under 24 months of age placed on HFNC in the Johns Hopkins Children's Center pediatric intensive care unit from January 2019 through January 2020. We excluded encounters with gaps in recorded clinical data, encounters in which MV treatment occurred prior to HFNC, and cases electively intubated in the operating room. The primary study outcome was discriminatory capacity of generated machine learning algorithms to predict HFNC flow rate escalations as compared to each other and ROX indices using area under the receiver operating characteristic (AUROC) analyses. In an exploratory fashion, model feature importance rankings were assessed by comparing Shapley values. Our gradient boosting model with a time window of 8 h and lead time of 1 h before HFNC flow rate escalation achieved an AUROC with a 95% confidence interval of 0.810 ± 0.003. In comparison, the ROX index achieved an AUROC of 0.525 ± 0.000. In this single-center, retrospective cohort study assessing children under 24 months of age receiving HFNC for acute respiratory failure, tree-based machine learning models outperformed the ROX index in predicting subsequent flow rate escalations. Further validation studies are needed to ensure generalizability for bedside application.
高流量鼻导管（HFNC）常用于危重症儿童的无创呼吸支持。关于最佳设备参数、患者成功反应的决定因素以及支持升级指征的共识，相关数据有限。临床评分，如呼吸频率 - 氧合（ROX）指数，已被描述为预测HFNC无反应的一种手段，但仅限于评估升级到有创机械通气（MV）的情况。在出现明显的HFNC无反应时，临床医生可能会选择增加HFNC流速，以假设性地防止呼吸进一步恶化，过渡到另一种无创接口，或进行MV插管。迄今为止，尚未评估任何模型来预测HFNC启动后HFNC流速的后续升级情况。为了评估基于树的机器学习算法预测HFNC流速升级的能力。我们进行了一项回顾性队列研究，评估2019年1月至2020年1月在约翰霍普金斯儿童中心儿科重症监护病房接受HFNC治疗的24个月以下急性呼吸衰竭患儿。我们排除了记录临床数据有缺失的病例、在HFNC之前进行MV治疗的病例以及在手术室择期插管的病例。主要研究结果是通过接受者操作特征曲线下面积（AUROC）分析，比较生成的机器学习算法与彼此以及ROX指数预测HFNC流速升级的辨别能力。以探索性方式，通过比较Shapley值评估模型特征重要性排名。我们的梯度提升模型在HFNC流速升级前8小时时间窗口和1小时提前期下，AUROC的置信区间为95%，即0.810±0.003。相比之下，ROX指数的AUROC为0.525±0.000。在这项评估24个月以下接受HFNC治疗急性呼吸衰竭患儿的单中心回顾性队列研究中，基于树的机器学习模型在预测后续流速升级方面优于ROX指数。需要进一步的验证研究以确保其在床边应用的普遍性。
