Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models.
Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models.
复制标题
DOI：
10.1371/journal.pone.0207192
复制
发表时间：
2018
期刊：
影响因子：
3.7
通讯作者：
Hsieh CH
中科院分区：
文献类型：
--
作者：
Rau CS;Kuo PJ;Chien PC;Huang CY;Hsieh HY;Hsieh CH
本研究的目的是建立一个机器学习（ML）模型，用于预测孤立性中度和重度创伤性脑损伤（TBI）患者的死亡率。 2009 年 1 月至 2015 年 12 月期间在创伤登记系统中登记的住院成年患者被纳入本研究。本研究仅纳入与头部损伤相关的简明损伤量表 (AIS) 评分≥ 3 分的患者。训练组和测试组分别包含 1734 名（1564 名存活者和 170 名死亡者）和 325 名（293 名存活者和 32 名死亡者）患者。利用人口统计和损伤特征以及患者实验室数据、预测工具（例如逻辑回归 [LR]、支持向量机 [SVM]、决策树 [DT]、朴素贝叶斯 [NB] 和人工神经网络 [ANN]）来确定个体患者的死亡率。通过准确性、敏感性和特异性以及受试者操作特征曲线的曲线下面积 (AUC) 测量来评估预测性能。在训练集中，所有五个 ML 模型的特异性均超过 90%，并且所有 ML 模型（除 NB 之外）的准确率均超过 90%。其中，ANN对死亡率的预测灵敏度最高（80.59%）。在性能方面，ANN 的 AUC 最高（0.968），其次是 LR（0.942）、SVM（0.935）、NB（0.908）和 DT（0.872）。在测试集中，ANN 对死亡率预测的敏感性最高（84.38%），其次是 SVM（65.63%）、LR（59.38%）、NB（59.38%）和 DT（43.75%）。 ANN 模型为孤立性中度和重度 TBI 患者的死亡率提供了最佳预测。
The purpose of this study was to build a model of machine learning (ML) for the prediction of mortality in patients with isolated moderate and severe traumatic brain injury (TBI). Hospitalized adult patients registered in the Trauma Registry System between January 2009 and December 2015 were enrolled in this study. Only patients with an Abbreviated Injury Scale (AIS) score ≥ 3 points related to head injuries were included in this study. A total of 1734 (1564 survival and 170 non-survival) and 325 (293 survival and 32 non-survival) patients were included in the training and test sets, respectively. Using demographics and injury characteristics, as well as patient laboratory data, predictive tools (e.g., logistic regression [LR], support vector machine [SVM], decision tree [DT], naive Bayes [NB], and artificial neural networks [ANN]) were used to determine the mortality of individual patients. The predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operator characteristic curves. In the training set, all five ML models had a specificity of more than 90% and all ML models (except the NB) achieved an accuracy of more than 90%. Among them, the ANN had the highest sensitivity (80.59%) in mortality prediction. Regarding performance, the ANN had the highest AUC (0.968), followed by the LR (0.942), SVM (0.935), NB (0.908), and DT (0.872). In the test set, the ANN had the highest sensitivity (84.38%) in mortality prediction, followed by the SVM (65.63%), LR (59.38%), NB (59.38%), and DT (43.75%). The ANN model provided the best prediction of mortality for patients with isolated moderate and severe TBI.