文献速递神经创伤神经重症

XGBoost机器学习算法在预测中重度创伤性脑损伤死亡率方面优于回归模型

XGBoost Machine Learning Algorism Performed Better Than Regression Models in Predicting Mortality of Moderate-to-Severe Traumatic Brain Injury.
PubMed 文献 · World Neurosurg · 2022-04-14

本研究基于368例GCS低于13分的中重度创伤性脑损伤住院患者,按7:3分为训练集与测试集,构建XGBoost死亡预测模型并与逻辑回归比较。XGBoost的ROC曲线下面积(0.955 vs. 0.805)和准确率(0.955 vs. 0.70)均高于逻辑回归,结论认为XGBoost预测死亡更有效且精确。

要点

  • 368例中重度TBI患者中205例预后不良,死亡率为55.7%。
  • 死亡组GCS更低(5 vs. 7,P < 0.001)、ISS更高(25 vs. 16,P < 0.001)。
  • XGBoost的ROC曲线下面积(0.955 vs. 0.805)和准确率(0.955 vs. 0.70)均高于逻辑回归。

核心结论

  • 使用XGBoost算法预测中重度TBI患者死亡率比逻辑回归更有效且精确,有助于医生评估预后不良高风险的TBI患者。

研究设计与样本

  • 纳入368例在华西医院住院、GCS低于13分的TBI患者,按7:3比例分为训练集与测试集。
  • 构建XGBoost预测模型,并构建逻辑回归预测模型与之比较。
  • 计算ROC曲线下面积、准确率、敏感度和特异度以比较XGBoost与逻辑回归的预后价值。

主要发现

  • 205例患者预后不良,死亡率为55.7%。
  • 死亡组GCS为5 vs. 存活组7(P < 0.001),死亡组ISS为25 vs. 存活组16(P < 0.001)。
  • 死亡组血小板(P < 0.001)、白蛋白(P < 0.001)和血红蛋白(P < 0.001)显著更低,而血糖(P < 0.001)和凝血酶原时间(P < 0.001)显著更高。
  • XGBoost模型中GCS、凝血酶原时间和血糖的特征重要性最显著。
  • XGBoost的ROC曲线下面积为0.955 vs. 逻辑回归0.805,准确率为0.955 vs. 逻辑回归0.70,两者均高于逻辑回归。

临床怎么用

  • 作者认为XGBoost预测方法有助于医生评估预后不良高风险的TBI患者。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Traumatic brain injury (TBI) brings severe mortality and morbidity risk to patients. Predicting the outcome of these patients is necessary for physicians to make suitable treatments to improve prognosis. The aim of this study is to develop a mortality prediction approach using XGBoost (extreme gradient boosting) in moderate-to-severe TBI. METHODS: A total of 368 patients hospitalized in West China hospital for TBI with Glasgow Coma Scale (GCS) below 13 were identified. To construct the XGBoost prediction approach, patients were divided into training set and test set with a ratio of 7:3. A logistic regression prediction model was also constructed and compared with the XGBoost model. Area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were calculated to compare the prognostic value between XGBoost and logistic regression. RESULTS: A total of 205 patients suffered a poor outcome with a mortality of 55.7%. Nonsurvivors had a lower GCS (5 vs. 7, P < 0.001) and a higher Injury Severit Score (ISS) than survivors (25 vs. 16, P < 0.001). Platelet (P < 0.001), albumin (P < 0.001), and hemoglobin (P < 0.001) were significantly lower in nonsurvivors, whereas glucose (P < 0.001) and prothrombin time (P < 0.001) were significantly higher in nonsurvivors. Among the XGBoost approach, GCS, prothrombin time, and glucose had the most significant feature importance. The area under the receiver operating characteristic curve (0.955 vs. 0.805) and accuracy (0.955 vs. 0.70) of XGBoost were both higher than logistic regression. CONCLUSION: Predicting mortality of patients with moderate-to-severe TBI using the XGBoost algorism is more effective and precise than logistic regression. The XGBoost prediction approach is beneficial for physicians to evaluate patients with TBI at high risk of poor outcome.

来源:World Neurosurg,查看原文。版权归原作者所有。

引用

  1. Wang R, Wang L, Zhang J, et al. XGBoost Machine Learning Algorism Performed Better Than Regression Models in Predicting Mortality of Moderate-to-Severe Traumatic Brain Injury. World Neurosurg. 2022. PMID: 35430400. doi:10.1016/j.wneu.2022.04.044

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。