Prediction of endotracheal tube size in pediatric patients: Development and validation of machine learning models.
Prediction of endotracheal tube size in pediatric patients: Development and validation of machine learning models.
复制标题
DOI：
10.3389/fped.2022.970646
复制
发表时间：
2022
影响因子：
2.6
通讯作者：
Zou, Zui
中科院分区：
文献类型：
--
作者：
Zhou, Miao;Xu, Wen Y.;Xu, Sheng;Zang, Qing L.;Li, Qi;Tan, Li;Hu, Yong C.;Ma, Ning;Xia, Jian H.;Liu, Kun;Ye, Min;Pu, Fei Y.;Chen, Liang;Song, Li J.;Liu, Yang;Jiang, Lai;Gu, Lin;Zou, Zui
我们旨在构建和验证用于儿科患者气管插管（ETT）大小预测的机器学习模型。回顾性收集2019年11月至2021年10月期间接受气管插管的990例儿科患者的数据，并将其分为带箍和未带箍气管插管亚组。选择支持向量回归（SVR）、逻辑回归（LR）、随机森林（RF）、梯度增强树（GBR）、决策树（DTR）和极端梯度增强树（XGBR）等6种机器学习算法，在训练集上进行十倍交叉验证，构建并验证模型。选择最优模型，并与传统预测公式和临床医生进行性能比较。此外，还收集了71例儿科患者的额外数据进行外部验证。通过特征选择筛选出最优的7个未套筒变量和5个套筒变量。RF模型对未折边ETT尺寸（MAE = 0.275 mm, RMSE = 0.349 mm）和折边ETT尺寸（MAE = 0.243 mm, RMSE = 0.310 mm）的预测误差均最小，表现最佳。RF模型的预测能力也优于未加箍和加箍的ETT大小预测公式。此外，RF模型的表现略好于高级临床医生，而他们明显优于初级临床医生。在SVR模型的基础上，我们分别提出了3个新的无袖带和有袖带ETT大小的线性公式。我们开发的机器学习模型在预测儿科患者带套和不带套气管插管的最佳气管插管大小方面表现优异，为临床医生选择合适的气管插管大小提供了强有力的决策支持。基于机器学习模型提出的新公式也具有相对较好的预测性能。这些模型和配方可以作为临床医生的重要临床参考，特别是对于经验稀少或偏远地区的表演者。
We aimed to construct and validate machine learning models for endotracheal tube (ETT) size prediction in pediatric patients. Data of 990 pediatric patients underwent endotracheal intubation were retrospectively collected between November 2019 and October 2021, and separated into cuffed and uncuffed endotracheal tube subgroups. Six machine learning algorithms, including support vector regression (SVR), logistic regression (LR), random forest (RF), gradient boosting tree (GBR), decision tree (DTR) and extreme gradient boosting tree (XGBR), were selected to construct and validate models using ten-fold cross validation in training set. The optimal models were selected, and the performance were compared with traditional predictive formulas and clinicians. Furthermore, additional data of 71 pediatric patients were collected to perform external validation. The optimal 7 uncuffed and 5 cuffed variables were screened out by feature selecting. The RF models had the best performance with minimizing prediction error for both uncuffed ETT size (MAE = 0.275 mm and RMSE = 0.349 mm) and cuffed ETT size (MAE = 0.243 mm and RMSE = 0.310 mm). The RF models were also superior in predicting power than formulas in both uncuffed and cuffed ETT size prediction. In addition, the RF models performed slightly better than senior clinicians, while they significantly outperformed junior clinicians. Based on SVR models, we proposed 3 novel linear formulas for uncuffed and cuffed ETT size respectively. We have developed machine learning models with excellent performance in predicting optimal ETT size in both cuffed and uncuffed endotracheal intubation in pediatric patients, which provides powerful decision support for clinicians to select proper ETT size. Novel formulas proposed based on machine learning models also have relatively better predictive performance. These models and formulas can serve as important clinical references for clinicians, especially for performers with rare experience or in remote areas.
登录
查看更多内容
影响因子：
4.6
作者：
Cuendet, Gabriel Louis;Schoettker, Patrick;Thiran, Jean-Philippe
通讯作者：
Thiran, Jean-Philippe
影响因子：
1.7
作者：
Altun, Demet;Orhan-Sungur, Mukadder;Camci, Emre
通讯作者：
Camci, Emre
影响因子：
28.1
作者：
Lundberg, Scott M.;Nair, Bala;Lee, Su-In
通讯作者：
Lee, Su-In
影响因子：
1.7
作者：
Trachsel, Daniel;Erb, Thomas O.;Hammer, Jurg;von Ungern-Sternberg, Britta S.
通讯作者：
von Ungern-Sternberg, Britta S.
影响因子：
1.7
作者：
Kohjitani, Atsushi;Iwase, Yoko;Sugiyama, Kazuna
通讯作者：
Sugiyama, Kazuna