基于健康管理队列的心血管事件风险预测模型

doi:10.6040/j.issn.1671-7554.0.2017.356

山东大学学报（医学版） ›› 2017, Vol. 55 ›› Issue (6): 56-60.doi: 10.6040/j.issn.1671-7554.0.2017.356

基于健康管理队列的心血管事件风险预测模型

李吉庆^1,2,赵焕宗³,宋炳红³,张理纯³,李向一^1,2,陈亚飞^1,2,王萍⁴,薛付忠^1,2

1.山东大学公共卫生学院生物统计学系, 山东济南 250012;2.山东大学齐鲁生物医学大数据研究中心, 山东济南 250012;3.临沂市人民医院健康体检中心, 山东临沂 276000;4.山东大学齐鲁医院手术室, 山东济南 250012

收稿日期:2017-04-26 出版日期:2017-06-10 发布日期:2017-06-10
通讯作者: 赵焕宗. E-mail:zhaohuanzong@163.com E-mail:zhaohuanzong@163.com
基金资助:
国家国际科技合作专项项目(2014DFA32830);山东省医药卫生科技发展计划项目(2013WS0230)

Risk prediction model of cardiovascular disease based on health management cohort

LI Jiqing^1,2, ZHAO Huanzong³, SONG Binghong³, ZHANG Lichun³, LI Xiangyi^1,2, CHEN Yafei^1,2, WANG Ping⁴, XUE Fuzhong^1,2

1. Department of Biostatistics, School of Public Health, Shandong University, Jinan 250012, Shandong, China;
2. Cheeloo Research Center for Biomedical Big Data, Shandong University, Jinan 250012, Shandong, China;
3. Health Examination Center, Linyi Peoples Hospital, Linyi 276000, Shandong, China;
4. Operating Room of Qilu Hospital, Shandong University, Jinan 250012, Shandong, China

Received:2017-04-26 Online:2017-06-10 Published:2017-06-10

摘要/Abstract

摘要： 目的基于健康管理队列构建心血管事件风险预测模型。方法数据来源于山东多中心健康管理纵向观察队列,共72 843人纳入队列。随机抽取70%队列人群作为训练组,其余30%作为校验组,应用Cox比例风险回归模型对影响心血管事件发生的因素进行变量筛选,利用部分分布竞争风险模型建立心血管事件预测模型,并使用十折交叉验证法检验模型稳定性。结果队列随访期间共发生心血管事件2 463例,发病密度为88.79/1 000人年,死于非心血管事件164例。最终纳入模型的变量包括年龄、吸烟、体质量指数、高血压、糖尿病、血脂异常、ST-T改变、T波改变、异常Q波、心律失常及肾脏疾病。训练组ROC曲线下面积男性为0.837(95%CI:0.821~0.853),女性为0.897(95%CI:0.880~0.913);校验组ROC曲线下面积男性为0.838(95%CI:0.813~0.862),女性为0.893(95%CI:0.872~0.914)。结论构建的心脑血管事件预测模型在健康管理人群中有较好的预测能力。

关键词: 心血管事件, 健康管理, 风险预测模型

Abstract: Objective To establish a model to evaluate the risk of cardiovascular disease(CVD)among health management population. Methods The cohort consisted of 72 843 individuals who had physical check-up at Shandong Multi-center Longitudinal Cohort for Health Management. They were all free of CVD events. We randomly divided the cohort into the training group(70%)and testing group(30%). Cox proportional hazards regression model was applied to choose risk factors of CVD, competing risk prediction model was used to establish a prediction model for CVD, and ten-fold cross validation was used to test the stability of the model. Discriminatory ability was determined by the area under the receiver operating characteristic curve(AUC). Results There were 2 463 CVD cases during the study period and the incidence was 88.79/1 000 person-year, and 164 people died of other causes. The risk factors included age, 山东大学学报 (医学版)55卷6期 -李吉庆,等.基于健康管理队列的心血管事件风险预测模型 \=-smoke, BMI, hypertension, diabetes, dyslipidemia, ST-T segment changes, T wave change, abnormal Q wave, arrhythmia and chronic kidney diseases. The estimated AUC of the model in the training group was 0.837(95%CI: 0.821-0.854)for males and 0.897(95%CI:0.880-0.913)for females. The estimated AUC of the model in the testing group was 0.838(95%CI:0.813-0.862)for males and 0.893(95%CI:0.872-0.914)for females. Conclusion The risk prediction model can be used to screen high-risk subjects of CVD in health management population.

Key words: Cardiovascular event, Health management, Risk prediction model

中图分类号:

R541

李吉庆,赵焕宗,宋炳红,张理纯,李向一,陈亚飞,王萍,薛付忠. 基于健康管理队列的心血管事件风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 56-60.

LI Jiqing, ZHAO Huanzong, SONG Binghong, ZHANG Lichun, LI Xiangyi, CHEN Yafei, WANG Ping, XUE Fuzhong. Risk prediction model of cardiovascular disease based on health management cohort[J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2017, 55(6): 56-60.

参考文献

[1] 吴兆苏. 中国心血管病预防指南简介[J]. 岭南心血管病杂志, 2011(S1):36-37.
[2] 张啸飞, 胡大一, 丁荣晶, 等. 中国心脑血管疾病死亡现况及流行趋势[J]. 中华高血压杂志, 2012, 20(6):600.
[3] D'Agostino RB Sr, Vasan RS, Pencina MJ, et al. General cardiovascular risk profile for use in primary care: the Framingham Heart Study[J]. Circulation, 2008, 117(6): 743-753.
[4] 刘静, 赵冬, 秦兰萍, 等. 低密度脂蛋白胆固醇与心血管病发病关系的前瞻性研究[J]. 中华心血管病杂志, 2001, 29(9): 561-565. LIU Jing, ZHAO Dong, QIN Lanping, et al. Association of low density lipoprotein cholesterol with cardiovascular disease in a prospective study[J]. Chin J Cardiol, 2001, 29(9): 561-565.
[5] 吴兆苏, 姚崇华, 赵冬. 中国多省市心血管病趋势及决定因素的人群监测(中国MONICA方案)Ⅲ.危险因素水平与心血管病的联系[J]. 中华心血管病杂志, 1998, 26(2): 85-88. WU Zhaosu, YAO Chonghua, ZHAO Dong, et al. Multi-provincial monitoring of the trends and determinants of cardiovascular diseases(Sino-MONICA project)-III. Association between risk factor levels and cardiovascular disease[J]. Chin J Cardiol, 1998, 26(2): 85-88.
[6] 刘静, 赵冬, 王薇, 等.中国多省市心血管病危险因素队列研究与美国弗莱明翰心脏研究结果的比较[J]. 中华心血管病杂志, 2004, 32(2):167-172. LIU Jing, ZHAO Dong, WANG Wei, et al. Comparison between the results from the Chinese Multi-provincial Cohort Study and those from the Framingham Heart Study[J]. Chin J Cardiol, 2004, 32(2): 167-172.
[7] 王薇, 赵冬, 刘静, 等. 中国35~64岁人群心血管病危险因素与发病危险预测模型的前瞻性研究[J]. 中华心血管病杂志, 2003, 31(12): 902-908. WANG Wei, ZHAO Dong, LIU Jing, et al. Prospective study on the predictive model of cardiovascular disease risk in a Chinese population aged 35-64[J]. Chin J Cardiol, 2003, 31(12): 902-908.
[8] 何疆春,李田昌. 心血管疾病风险评估的现状与展望[J]. 心血管病学进展, 2013, 34(1): 50-55. HE Jiangchun, LI Tianchang. Current situation of and prospects for cardiovascular disease risk assessment[J]. Advance in Cardiovascular Disease, 2013, 34(1): 50-55.
[9] 中国高血压防治指南修订委员会. 中国高血压防治指南2010[J]. 中华心血管病杂志, 2011,39(7):579-616. Writing Group of 2010 Chinese Guidelines for the Management of Hypertension. 2010 Chinese guidelines for the management of hypertension[J]. Chin J Cardiol, 2011, 39(7):579-616.
[10] 范国洽, 郝慧斌, 杨昱, 等. 2013版《中国2型糖尿病防治指南》解读[J]. 中国临床医生杂志, 2015, 43(10): 92-94.
[11] 高秀芳, 李勇. 《中国成人血脂异常防治指南2016修订版》更新要点解析[J]. 中华高血压杂志, 2017, 25(1): 15-18.
[12] Jason P. Fine, Robert J. Gray. A proportional hazards model for the subdistribution of a competing risk[J]. J Am Stat Assoc, 1999, 94(446):496-509.
[13] Scrucca L, Santucci A, Aversa F. Competing risk analysis using R: an easy guide for clinicians[J]. Bone Marrow Transplantation, 2007, 40(4): 381-387.
[14] Robin X, Turck N, Hainard A, et al. pROC: an open-source package for R and S+ to analyze and compare ROC curves[J]. BMC Bioinformatics, 2011, 12(1): 77.
[15] Anderson KM, Wilson PW, Odell PM, et al. An updated coronary risk profile. A statement for health professionals[J]. Circulation, 1991, 83(1):356-362.
[16] 王薇, 赵冬. 中国心脑血管病流行特征转化规律、影响因素及预防策略研究与应用[J]. 中华心血管病杂志, 2013, 41(11): 992.
[17] 周北凡. 中国人群心血管病危险因素作用特点的前瞻性研究[J]. 中华流行病学杂志, 2005, 26(1): 58-61.
[18] Wilson PWF, Levy D, Belanger AM, et al. Prediction of coronary heart disease using risk factor categories[J]. Circulation, 1998, 97(18):1837-1847.
[19] Conroy RM, Pyörälä K, Fitzgerald AP, et al. Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project[J]. Eur Heart J, 2003, 24(11):987-1003.
[20] Nishimura K, Okamura T, Watanabe M, et al. Predicting coronary heart disease using risk factor categories for a Japanese urban population, and comparison with the Framingham risk score: the suita study[J]. J Atheroscler Thromb, 2014, 21(8):784.
[21] 饶栩栩, 陈百玲, 麦劲壮, 等. 队列人群心电图ST-T异常与死亡及心脑血管事件关系的前瞻性观察[J].中华心血管病杂志, 2004, 32(3):258-263. RAO Xuxu, CHEN Bailing, MAI Jinzhuang, et al. A prospective cohort study on the relationship of abnormal ST-T on electrocardiogram with death[J]. Chin J Cardiol, 2004, 32(3):258-263.
[22] 张义峰, 高晓丽, 郭忠则. 心电图ST-T异常改变与心脑血管事件的关系[J].江苏实用心电学杂志, 2005, 14(1):29-30.
[23] Verrier RL, Sroubek J. Quantitative T-wave alternans analysis for sudden cardiac death risk assessment and guiding therapy: answered and unanswered questions: For: proceedings of ICE2015 Comandatuba, Brazil, sudden death symposium[J]. J Electrocardiol, 2016, 49(3):429-438.
[24] Hanna EB, Glancy DL. ST-segment depression and T-wave inversion: classification, differential diagnosis and caveats[J]. Cleve Clin J Med, 2011, 78(6): 404-414.
[25] 刘龙, 汤哲, 李霞, 等. 基于竞争风险模型的北京市老年人群心血管疾病短期风险评估[J].首都医科大学学报, 2016, 37(2): 181-187. LIU Long, TANG Zhe, LI Xia, et al. A short-term risk assessment for cardiovascular diseases among the elderly in Beijing based on competing risk model[J]. Journal of Capital Medical University, 2016, 37(2): 181-187.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于健康管理队列的心血管事件风险预测模型

Risk prediction model of cardiovascular disease based on health management cohort

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

多维度评价

本文评价

推荐阅读 0

[1]	刘娅飞,邢娉,徐秀琴,杨淑芳,刘言训,袁中尚,薛付忠. 山东多中心健康管理纵向观察队列[J]. 山东大学学报（医学版）, 2017, 55(6): 30-36.
[2]	于涛,刘焕乐,冯新,徐付印,陈亚飞,薛付忠,张成琪. 基于健康管理队列的高血压风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 61-65.
[3]	王春霞,许艺博,杨宁,夏冰,王萍,薛付忠. 基于健康管理队列的冠心病风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 66-71.
[4]	张光,王广银,吴红彦, 张红玉,王停停,李吉庆,李敏,康凤玲,刘言训,薛付忠. 健康管理人群高脂血症风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 72-76.
[5]	李江冰,宋心红,林海燕,张冬芝,李向一,许艺博,王丽,薛付忠. 健康管理人群缺血性异常心电图的影响因素[J]. 山东大学学报（医学版）, 2017, 55(6): 77-81.
[6]	苏萍,杨亚超,杨洋,季加东,阿力木·达依木,李敏,薛付忠,刘言训. 健康管理人群2型糖尿病发病风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 82-86.
[7]	孙苑潆,杨亚超,曲明苓,陈雁敏,李敏,王淑康,薛付忠,刘云霞. 健康管理人群代谢综合征发病风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 87-92.
[8]	周苗,夏同耀,孙爱玲,李明,申振伟,卞伟玮,蒋正,康凤玲,柳晓涓,薛付忠,刘静. 健康管理人群慢性肾脏病风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 98-103.
[9]	李敏,王春霞,夏冰,朱茜,孙苑潆,王淑康,薛付忠,贾红英. 健康管理人群脑卒中风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 93-97.
[10]	于媛媛,王春霞,苏萍,孙苑潆,薛付忠,刘言训. 健康管理队列白内障发病风险预测模型[J]. 山东大学学报（医学版）, 2017, 55(6): 104-107.
[11]	柳晓涓,蒋正,康凤玲,周苗,林伟强,薛付忠. 中性粒细胞计数与非酒精性脂肪肝关联性的前瞻性队列研究[J]. 山东大学学报（医学版）, 2017, 55(6): 119-123.
[12]	杨洋,张光,张成琪,宋心红,薛付忠,王萍,王丽,刘言训. 基于体检队列的2型糖尿病风险预测模型[J]. 山东大学学报（医学版）, 2016, 54(9): 69-72.
[13]	王文文1，陈玉国2. GRACE与TIMI危险评分对急性冠脉综合征患者危险分层的对比研究[J]. 山东大学学报(医学版), 2013, 51(10): 54-57.