Table_1_Machine Learning Model for Predicting Acute Respiratory Failure in Individuals With Moderate-to-Severe Traumatic Brain Injury.DOCX

Background: There is a high incidence of acute respiratory failure (ARF) in moderate or severe traumatic brain injury (M-STBI), worsening outcomes. This study aimed to design a predictive model for ARF.
Methods: Adult patients with M-STBI [3 ≤ Glasgow Coma Scale (GCS) ≤ 12] with a definite history of brain trauma and abnormal head on CT images, obtained from September 2015 to May 2017, were included. Patients with age >80 years or <18 years, multiple injuries with TBI upon admission, or pregnancy (in women) were excluded. Two models based on machine learning extreme gradient boosting (XGBoost) or logistic regression, respectively, were developed for predicting ARF within 48 h upon admission. These models were evaluated by out-of-sample validation. The samples were assigned to the training and test sets at a ratio of 3:1.
Results: In total, 312 patients were analyzed including 132 (42.3%) patients who had ARF. The GCS and the Marshall CT score, procalcitonin (PCT), and C-reactive protein (CRP) on admission significantly predicted ARF. The novel machine learning XGBoost model was superior to logistic regression model in predicting ARF [area under the receiver operating characteristic (AUROC) = 0.903, 95% CI, 0.834–0.966 vs. AUROC = 0.798, 95% CI, 0.697–0.899; p < 0.05].
Conclusion: The XGBoost model could better predict ARF in comparison with logistic regression-based model. Therefore, machine learning methods could help to develop and validate novel predictive models.

背景：中重度创伤性脑损伤（moderate or severe traumatic brain injury, M-STBI）患者的急性呼吸衰竭（acute respiratory failure, ARF）发病率较高，会恶化患者预后。本研究旨在构建用于预测ARF发生的预测模型。
方法：纳入2015年9月至2017年5月期间收治的成年中重度创伤性脑损伤（M-STBI）患者，需满足明确的颅脑创伤病史、头部CT影像异常，且格拉斯哥昏迷量表（Glasgow Coma Scale, GCS）评分介于3~12分之间。排除标准如下：年龄＞80岁或＜18岁、入院时合并多系统创伤性脑损伤（traumatic brain injury, TBI）、女性患者妊娠。分别基于机器学习的极端梯度提升（extreme gradient boosting, XGBoost）与逻辑回归（logistic regression）构建模型，用于预测患者入院后48小时内发生ARF的风险。采用样本外验证（out-of-sample validation）对两类模型进行性能评估，以3:1的比例将样本划分为训练集与测试集。
结果：本研究共纳入312例患者进行分析，其中132例（42.3%）发生ARF。入院时的GCS评分、马歇尔CT评分（Marshall CT score）、降钙素原（procalcitonin, PCT）与C反应蛋白（C-reactive protein, CRP）水平可显著预测ARF发生。新型机器学习XGBoost模型在预测ARF方面优于逻辑回归模型：受试者工作特征曲线下面积（area under the receiver operating characteristic, AUROC）分别为0.903（95%置信区间：0.834~0.966）与0.798（95%置信区间：0.697~0.899），组间比较差异具有统计学意义（p＜0.05）。
结论：相较于基于逻辑回归的模型，XGBoost模型可更精准地预测ARF发生。由此可见，机器学习方法有助于构建并验证新型临床预测模型。