Cui Wenxing, Ge Shunnan, Shi Yingwu, Wu Xun, Luo Jianing, Lui Haixiao, Zhu Gang, Guo Hao, Feng Dayun, Qu Yan
Department of Neurosurgery, Tangdu Hospital, No. 569 Xin Si Road, Xi'an, 710038, Shaanxi Province, China.
Chin Neurosurg J. 2021 Apr 21;7(1):24. doi: 10.1186/s41016-021-00242-4.
Despite advances in decompressive craniectomy (DC) for the treatment of traumatic brain injury (TBI), these patients are at risk of having a poor long-term prognosis. The aim of this study was to predict 1-year mortality in TBI patients undergoing DC using logistic regression and random tree models.
This was a retrospective analysis of TBI patients undergoing DC from January 1, 2015, to April 25, 2019. Patient demographic characteristics, biochemical tests, and intraoperative factors were collected. One-year mortality prognostic models were developed using multivariate logistic regression and random tree algorithms. The overall accuracy, sensitivity, specificity, and area under the receiver operating characteristic curves (AUCs) were used to evaluate model performance.
Of the 230 patients, 70 (30.4%) died within 1 year. Older age (OR, 1.066; 95% CI, 1.045-1.087; P < 0.001), higher Glasgow Coma Score (GCS) (OR, 0.737; 95% CI, 0.660-0.824; P < 0.001), higher D-dimer (OR, 1.005; 95% CI, 1.001-1.009; P = 0.015), coagulopathy (OR, 2.965; 95% CI, 1.808-4.864; P < 0.001), hypotension (OR, 3.862; 95% CI, 2.176-6.855; P < 0.001), and completely effaced basal cisterns (OR, 3.766; 95% CI, 2.255-6.290; P < 0.001) were independent predictors of 1-year mortality. Random forest demonstrated better performance for 1-year mortality prediction, which achieved an overall accuracy of 0.810, sensitivity of 0.833, specificity of 0.800, and AUC of 0.830 on the testing data compared to the logistic regression model.
The random forest model showed relatively good predictive performance for 1-year mortality in TBI patients undergoing DC. Further external tests are required to verify our prognostic model.
尽管在用于治疗创伤性脑损伤（TBI）的减压性颅骨切除术（DC）方面取得了进展，但这些患者仍有长期预后不良的风险。本研究的目的是使用逻辑回归和随机树模型预测接受DC治疗的TBI患者的1年死亡率。
这是一项对2015年1月1日至2019年4月25日期间接受DC治疗的TBI患者的回顾性分析。收集了患者的人口统计学特征、生化检查结果和术中因素。使用多变量逻辑回归和随机树算法建立了1年死亡率预后模型。使用总体准确率、敏感性、特异性和受试者操作特征曲线下面积（AUC）来评估模型性能。
在230例患者中，70例（30.4%）在1年内死亡。年龄较大（OR，1.066；95%CI，1.045 - 1.087；P < 0.001）、格拉斯哥昏迷评分（GCS）较高（OR，0.737；95%CI，0.660 - 0.824；P < 0.001）、D - 二聚体水平较高（OR，1.005；95%CI，1.001 - 1.009；P = 0.015）、凝血病（OR，2.965；95%CI，1.808 - 4.864；P < 0.001）、低血压（OR，3.862；95%CI，2.176 - 6.855；P < 0.001）以及基底池完全消失（OR，3.766；95%CI，2.255 - 6.290；P <
