基于TSP-1和APACHEⅡ评分构建老年重型颅脑损伤患者院内死亡的预测模型  

Construction of a predictive model for hospital mortality in elderly patients with severe head injury based on TSP-1 and APACHEⅡscore

作　　者：王成立 周林裕 梁哲勇 WANG Chengli;ZHOU Linyu;LIANG Zheyong(13201 Hospital/3201 Hospital Affiliated to Xi’an Jiaotong University School of Medicine,Hanzhong 723000,China;The First Affiliated Hospital of Xi’an Jiaotong University,Xi’an 710061,China)

机构地区：[1]三二〇一医院西安交通大学医学院附属三二〇一医院,陕西汉中723000 [2]西安交通大学第一附属医院,陕西西安710061

出　　处：《中国实用神经疾病杂志》2024年第7期816-820,共5页Chinese Journal of Practical Nervous Diseases

基　　金：陕西省自然科学基础研究计划项目(编号:2022JQ-957)。

摘　　要：目的基于血小板反应素-1(TSP-1)、急性生理与慢性健康评估Ⅱ(APACHEⅡ)评分构建老年重型颅脑损伤患者院内死亡的预测模型。方法回顾性收集2020-01—2022-12三二〇一医院收治的老年重型颅脑损伤患者192例,根据患者是否出现院内死亡分为死亡组(n=72)和对照组(n=120)。比较2组患者临床特征和TSP-1、APACHEⅡ评分,分析老年重型颅脑损伤患者院内死亡的危险因素,根据相关危险因素,构建老年重型颅脑损伤患者院内死亡的预测模型。结果与对照组比较,死亡组患者TSP-1显著增高[(141.95±32.85)μg/L比(116.20±29.39)μg/L,P<0.001];APACHEⅡ评分显著增高[(17.03±3.11)分比(13.14±3.24)分,P<0.001]。TSP-1>133.35μg/L、APACHEⅡ评分>15.5分、脑疝、多发伤、休克是老年重型颅脑损伤患者院内死亡的危险因素(P<0.05)。采用R 4.0.3统计软件将数据集随机分为训练集和验证集,训练集的样本量134,验证集的样本量58,构建预测模型,训练集的受试者工作特征(ROC)曲线下面积为0.872(95%可信区间0.814~0.930),验证集ROC曲线下面积为0.848(95%可信区间0.747~0.949)。在验证集里对模型进行Hosmer-Lemeshow Goodness-of-Fit检验,卡方值为6.105,P=0.636。结论基于TSP-1、APACHEⅡ评分构建的老年重型颅脑损伤患者院内死亡的预测模型具有良好的预测价值和可信度。Objective To construct a predictive model for hospital mortality in elderly patients with severe head injury based on thrombospondin-1(TSP-1)and acute physiology and chronic health evaluationⅡ(APACHEⅡ)score.Methods From January 2020 to December 2022,192 elderly patients with severe head injury admitted to the 3201 Hospital were retrospectively collected,and were divided into death group(n=72)and control group(n=120)according to whether they died in hospital.The clinical characteristics,and TSP-1 and APACHEⅡscore were compared between two groups,and the risk factors for hospital death in elderly patients with severe head injury were analyzed.Based on the relevant risk factors,we constructed a predictive model for hospital death in elderly patients with severe head injury.Results Compared with the control group,TSP-1 levels in the death group were significantly increased((141.95±32.85)μg/L vs(116.20±29.39)μg/L,P<0.001).The APACHEⅡscore significantly increased in the death group((17.03±3.11)pionts vs(13.14±3.24)pionts,P<0.001).TSP-1>133.35μg/L,APACHEⅡ>15.5 points,cerebral hernia,multiple injuries and shock were risk factors for hospital death in elderly patients with severe head injury(P<0.05).Using R 4.0.3 statistical software,the dataset was randomly divided into a training set and a validation set,with a sample size of 134 in the training set and 58 in the validation set.A prediction model was constructed,with an area under the receiver operating characteristic(ROC)curve of 0.872(95%confidence interval:0.814-0.930)for the training set and 0.848(95%confidence interval:0.747-0.949)for the validation set.In the validation set,the model was subjected to the Hosmer-Lemeshow Goodness-of-Fit test,with chi square value of 6.105 and P value of 0.636.Conclusion The predictive model for hospital death in elderly patients with severe head injury based on TSP-1 and APACHEⅡscore has good predictive value and reliability.

关 键 词：重型颅脑损伤 血小板反应素-1 急性生理与慢性健康评估Ⅱ评分 院内死亡 老年 

分 类 号：R651.15[医药卫生—外科学]