外伤性颅内出血死亡率的预测因素：国家创伤数据库研究。,Frontiers in Neurology

当前位置： X-MOL 学术 › Front. Neurol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

外伤性颅内出血死亡率的预测因素：国家创伤数据库研究。
Frontiers in Neurology ( IF 2.7 ) Pub Date : 2020-11-17 , DOI: 10.3389/fneur.2020.587587
Esther Wu ₁ , Siddharth Marthi ₁ , Wael F Asaad _{1,

2,

3,

4,

5}

Affiliation

背景/目的：创伤性颅内出血（tICH）导致明显的创伤发病率和死亡率。一些研究已经开发了tICH结果的预后模型，但是以前的模型面临局限性，包括普遍性差和准确性有限。目的是使用美国最大的创伤数据库，开发出一种预后模型，并确定死亡率的预测指标，并采用严格的分析方法并进行真正的模型验证。方法：我们从2012年至2016年在国家创伤数据库（NTDB）中鉴定了248,536名患者，其诊断代码与tICH相关。对于每次入院，我们收集了人口统计学信息，收缩压，血液酒精水平（BAL），格拉斯哥昏迷评分（GCS），损伤严重程度评分（ISS），硬膜外/硬膜下/蛛网膜下腔/实质内出血的存在，合并症，并发症，创伤中心水平和创伤中心区域。在排除缺少数据的记录之后，我们的最终研究人群为212,666名患者。因变量是患者死亡。线性支持向量机（SVM）分类是通过递归特征选择进行的。使用保留的10倍交叉验证评估模型性能。结果：交叉验证显示平均准确度为0.792（95％CI 0.783-0.799）。准确性，准确性，召回率和AUC分别为0.827、0.309、0.750和0.791。在最终模型中，高ISS，高龄，硬脑膜下出血和蛛网膜下腔出血与死亡率增加相关，而GCS口头和运动评分高，当前吸烟者，BAL超出法律限制，和1级创伤中心与死亡率降低相关。结论：针对tICH建立了线性SVM模型，并选择了九种特征作为死亡率的预测因子。这些发现适用于多种出血亚型，并可能在入院时对高危患者进行分类。尽管许多研究试图创建模型来预测TBI的死亡率，但我们试图通过使用美国最大的TBI数据库，使用现代建模方法，机器学习和真正的保留测试集来确认那些预测因素。我们确定的预测变量与以前的报告一致，但如果进行更严格的评估，总体预测准确性会比先前的报告低。有九种特征被选作死亡率的预测因子。这些发现适用于多种出血亚型，并可能在入院时对高危患者进行分类。尽管许多研究试图创建模型来预测TBI的死亡率，但我们试图通过使用美国最大的TBI数据库，使用现代建模方法，机器学习和真正的保留测试集来确认那些预测因素。我们确定的预测变量与以前的报告一致，但如果进行更严格的评估，总体预测准确性会比先前的报告低。有九种特征被选作死亡率的预测因子。这些发现适用于多种出血亚型，并可能在入院时对高危患者进行分类。尽管许多研究试图创建模型来预测TBI的死亡率，但我们试图通过使用美国最大的TBI数据库，使用现代建模方法，机器学习和真正的保留测试集来确认那些预测因素。我们确定的预测变量与以前的报告一致，但如果进行更严格的评估，总体预测准确性会比先前的报告低。

"点击查看英文标题和摘要"

Predictors of Mortality in Traumatic Intracranial Hemorrhage: A National Trauma Data Bank Study.

Background/Objective: Traumatic intracranial hemorrhage (tICH) accounts for significant trauma morbidity and mortality. Several studies have developed prognostic models for tICH outcomes, but previous models face limitations, including poor generalizability and limited accuracy. The objective was to develop a prognostic model and determine predictors of mortality using the largest trauma database in the U.S., applying rigorous analytical methodology with true hold-out-set model validation. Methods: We identified 248,536 patients in the National Trauma Data Bank (NTDB) from 2012 to 2016 with a diagnosis code associated with tICH. For each admission, we collected demographic information, systolic blood pressure, blood alcohol level (BAL), Glasgow Coma Score (GCS), Injury Severity Score (ISS), presence of epidural/subdural/subarachnoid/intraparenchymal hemorrhage, comorbidities, complications, trauma center level, and trauma center region. Our final study population was 212,666 patients following exclusion of records with missing data. The dependent variable was patient death. Linear support vector machine (SVM) classification was carried out with recursive feature selection. Model performance was assessed using holdout 10-fold cross-validation. Results: Cross-validation demonstrated a mean accuracy of 0.792 (95% CI 0.783-0.799). Accuracy, precision, recall, and AUC were 0.827, 0.309, 0.750, and 0.791, respectively. In the final model, high ISS, advanced age, subdural hemorrhage, and subarachnoid hemorrhage were associated with increased mortality, while high GCS verbal and motor subscores, current smoker, BAL beyond the legal limit, and level 1 trauma center were associated with decreased mortality. Conclusions: A linear SVM model was developed for tICH, with nine features selected as predictors of mortality. These findings are applicable to multiple hemorrhage subtypes and may benefit the triage of high risk patients upon admission. While many studies have attempted to create models to predict mortality in TBI, we sought to confirm those predictors using modern modeling approaches, machine learning, and true hold-out test sets, using the largest available TBI database in the U.S. We find that while the predictors we identify are consistent with prior reports, overall prediction accuracy is somewhat lower than prior reports when assessed more rigorously.

更新日期：2020-11-17

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南