摘要
目的建立一个关于闭合性重型颅脑损伤预后的简单、便于使用、变量可以在日常工作中快速获得的预测准确率高的预测模型。方法采用分类和回归树（classification and regression tree，CART）分析方法，选择8个预后因子，对579例闭合性重型颅脑损伤患者的预后进行分析，预后指标为外伤后6个月GOS。结果GCS是最好的预测因子，血糖、头颅CT表现、年龄、瞳孔情况是强有力的预测因子，白细胞计数也对预后产生有意义的影响。CART中的所有变量都与预后相关，预测准确率达87％。结论CART预测模型能较好地预测闭合性重型颅脑损伤患者的预后，是一种简单有效、准确率高的预测方法。
Objective To develop a simple and convenient predictive model with a high predictive accuracy, involving variables that can be rapidly and easily achieved in daily routine practice for the outcome of severe closed brain injury. Methods A classification and regression tree （CART） techniques were employed in the analysis of data from 579 cases with severe closed brain injury. A total of 8 prognostic indicators were selected, while Glasgow Outcome Scale（GOS） at 6 months ＂after severe closed brain injury was used as prognostic criterion. Results Our results indicated that GCS was the best predictor of outcome. Glucose level, computed tomographic findings, age and pupillary response were proved to be strong predictors. In the meantime, leukocytosis was found to correlate significantly with prognosis. The overall predictive aecuracy of the CART model for these data was 87%. All variables included in this tree were found to be related to the hinged external fixators outcome. Conclusion The CART proves to be a useful and accurate method in developing a simple and effective model for predicting outcome after severe closed brain injury.
出处
《中华创伤杂志》
CAS
CSCD
北大核心
2007年第3期167-170,共4页
Chinese Journal of Trauma
关键词
脑损伤
重型
预后
因素分析
统计学
Brain injuries, severe
Prognosis
Factor analysis
Statistics
