基于体检信息的急性冠脉综合征logistic预测模型  

Logistic regression model of predictive factors for acute coronary syndrome based on physical examination data

作　　者：赵立坤[1] 李学强[1] 赵季平[2] 王玉霞[1] 张明[3] 郭建花[4] ZHAO Li-Kun LI Xue-Qiang ZHAO Ji-Ping WANG Yu-Xia ZHANG Ming GUO Jian-Hua(Department of Cardiology Cadre＇ s Ward Department of Gastroenterology, 4. Center of Physical Examination, Hospital No. 731 of China Aerospace Science and Industry Corporation, Beijing 100074, China)

机构地区：[1]中国航天科工集团七三一医院心血管内科,北京100074 [2]中国航天科工集团七三一医院干部病房,北京100074 [3]中国航天科工集团七三一医院消化内科,北京100074 [4]中国航天科工集团七三一医院体检中心,北京100074

出　　处：《中华老年多器官疾病杂志》2017年第1期28-32,共5页Chinese Journal of Multiple Organ Diseases in the Elderly

基　　金：中国航天科工集团公司医疗卫生科研项目(2014-JKBZ-006)~~

摘　　要：目的探讨体检信息中急性冠脉综合征(ACS)的预测因素,并建立logistic预测模型,评价其预测发生ACS的准确度、敏感度和特异度。方法选取2014年10月至2015年10月中国航天科工集团七三一医院门诊、急诊及心血管内科ACS患者100例,按照性别、年龄匹配同期体检者100例作为对照组,于体检中心数据库调取入选者体检资料进行单因素分析,取其中有统计学意义的变量作多因素logistic回归分析,并建立预测模型。结果单因素分析结果表明体质量指数(BMI)、尿酸(UA)、总胆固醇(TC)、低密度脂蛋白胆固醇(LDL-C)、高敏C反应蛋白(Hs-CRP)、同型半胱氨酸(Hcy)、高血压、吸烟、糖尿病、高脂血症、缺血性脑卒中、脉搏波传导速度(PWV)、颈动脉内膜中层厚度(IMT)增厚、是否接受抗血小板治疗、是否接受他汀类药物治疗与ACS发病有关,其中8个因素进入logistic回归方程,logistic预测模型为P=1/1+e^((-8.444+1.182X_1+1.174X_2+0.430X_3+0.323X_4+0.315X_5+0.257X_6-1.569X_7-0.1884X_8)),预测ACS发生的准确度为83.5%(167/200),敏感度为82%(82/100),特异度为85%(85/100)。结论 IMT、糖尿病、吸烟、Hcy、LDL-C、BMI、是否接受抗血小板治疗、是否接受他汀类药物治疗是ACS发生的主要危险因素,所建立的logistic回归模型能较好地预测ACS发生风险。Objective To investigate the predictive factors of acute coronary syndrome （ACS） based on the information extracted from physical examination data, and to establish a logistic regression model and evaluate its accuracy, sensitivity and specificity in the prediction of ACS. Methods Clinical data of 100 identified ACS patients admitted to the outpatient, emergency and cardiologic departments of our hospital from October 2014 to October 2015 were collected and retrospectively reviewed in this study. Another 100 sex- and age-matched individuals without ACS who took physical examination in our hospital during the same period served as control group. The physical examination data were extracted from the database of physical examination center, and then analyzed with univariate analysis. The factors with statistical significance were further analyzed with multivariate logistic regression analysis to establish a model for ACS prediction. Results Univariate analysis showed that there were 15 clinical variables, including body mass index （BMI）, uric acid （UA）, total cholesterol （TC）, low density lipoprotein-cholesterol （LDL-C）, high sensitivity C-reactive protein （Hs-CRP）, homocysteine （Hcy）, hypertension, smoking, diabetes, hyperlipidemia, ischemic stroke, pulse wave velocity （PWV）, thickening of intima-media thickness （IMT）, antiplatelet therapy, and statins treament were associated with the occurrence of ACS. Among them, there were 8 factors into the logistic regression model, and the logistic regression model was P=1/1＋e（-8.444＋1.182X1＋1.174X2＋0.430X3＋0.323X4＋0.315X5＋0.257X6-1.569X7-0.184X8）, with the accuracy, sensitivity and specificity of 83.5% （167/200）, 82% （82/100）, and 85% （85/100）, respectively, Conclusions IMT, diabetes, smoking, Hcy, LDL-C, BMI, antiplatelet therapy, and statins treatment are the main risk factors for ACS. Our established logistic regression model is of good predictive value for the risk of ACS.

关 键 词：健康体检 急性冠脉综合征 多因素分析 预测因子 风险模型 

分 类 号：R541.4[医药卫生—心血管疾病]