健康管理人群高脂血症风险预测模型

doi:10.6040/j.issn.1671-7554.0.2017.402

山东大学学报（医学版） ›› 2017, Vol. 55 ›› Issue (6): 72-76.doi: 10.6040/j.issn.1671-7554.0.2017.402

健康管理人群高脂血症风险预测模型

张光¹,王广银²,吴红彦¹, 张红玉¹,王停停^3,4,李吉庆^3,4,李敏^3,4,康凤玲^3,4,刘言训^3,4,薛付忠^3,4

1.山东大学附属千佛山医院健康管理中心, 山东济南 250014;2.胜利石油管理局胜利医院健康管理科, 山东东营 257055;3.山东大学公共卫生学院生物统计学系, 山东济南 250012;4.山东大学齐鲁生物医学大数据研究中心, 山东济南 250012

收稿日期:2017-05-06 出版日期:2017-06-10 发布日期:2017-06-10
通讯作者: 王广银. E-mail:18605463543@163.com E-mail:18605463543@163.com
基金资助:
国家国际科技合作专项项目(2014DFA32830)

A prediction model of hyperlipidemia risk based on the health management population

ZHANG Guang¹, WANG Guangyin², WU Hongyan¹, ZHANG Hongyu¹, WANG Tingting^3,4, LI Jiqing^3,4, LI Min^3,4, KANG Fengling^3,4, LIU Yanxun^3,4, XUE Fuzhong^3,4

1. Health Management Center, Shandong Provincial Qianfoshan Hospital, Shandong University, Jinan 250014, Shandong, China;
2. Health Management Section, Shengli Hospital of Shandong Dongying Shengli Petroleum Administration Bureau, Dongying 257055, Shandong, China;
3. Department of Biostatistics, School of Public Health, Shandong University, Jinan 250012, Shandong, China;
4. Cheeloo Research Center for Biomedical Big Data, Shandong University, Jinan 250012, Shandong, China

Received:2017-05-06 Online:2017-06-10 Published:2017-06-10

摘要/Abstract

摘要： 目的建立20岁以上健康管理人群高脂血症风险预测模型并对其预测效果进行评价。方法依托山东多中心健康管理纵向观察队列共纳入30 056人,采用Cox比例风险回归建立高脂血症预测模型,利用ROC曲线下面积(AUC)进行模型评价,十折交叉验证法检验模型的预测效果和判别能力。结果随访期间共新发高脂血症5 063例,发病密度为47.78‰。预测模型纳入的变量为年龄、性别、吸烟、饮酒、总胆固醇、甘油三酯、总胆红素、高密度脂蛋白、糖尿病和高血压10个变量。预测模型的ROC曲线下面积AUC为0.741(95%CI: 0.731~0.752),经十折交叉验证平均AUC为0.741。结论构建的高脂血症风险预测模型在健康管理人群中具有较好预测能力。

关键词: 风险预测模型, 队列, 健康管理人群, 高脂血症

Abstract: Objective To construct a risk prediction model of hyperlipidemia for people aged 20 years and over. Methods A total of 30 056 people without hyperlipidemia at baseline were included based on the Shandong Multi-center Longitudinal Cohort for Health Management. The prediction model was built on Cox proportional hazards regression model. The predictability was evaluated with the area under the receiver operating characteristic(ROC)curve(AUC). The predictive effect and distinguishing ability were verified with ten-fold cross-validation. Results During the follow-up of 3.53±2.65 years, there were 5 063 new hyperlipidemia cases, and the incidence was 47.78‰. The risk factors of hyperlipidemia included age, sex, drinking, smoking, total cholesterol, triglyceride, total bilirubin, high-density lipoprotein cholesterol, diabetes and hypertension. The AUC was 0.741(95%CI:0.731-0.752). Ten-fold cross-validation verified that the AUC was 0.741. Conclusion The prediction model of hyperlipidemia has good prediction ability in the health management population.

Key words: Longitudinal cohort, Hyperlipidemia, Risk prediction model, Health management population

中图分类号:

R589.2

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.

ZHANG Guang, WANG Guangyin, WU Hongyan, ZHANG Hongyu, WANG Tingting, LI Jiqing, LI Min, KANG Fengling, LIU Yanxun, XUE Fuzhong. A prediction model of hyperlipidemia risk based on the health management population[J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2017, 55(6): 72-76.

参考文献

[1] Navar-Boggan AM, Peterson ED, Dagostino RB, et al. Hyperlipidemia in early adulthood increases long-term risk of coronary heart disease[J]. Circulation, 2015, 131(5): 451-458.
[2] Nelson RH. Hyperlipidemia as a risk factor for cardiovascular disease[J]. Prim Care, 2013, 40(1): 195-211.
[3] Gasparyan AY, Sandoo A, Stavropoulos-Kalinoglou A, et al. Mean platelet volume in patients with rheumatoid arthritis: the effect of anti-TNF-α therapy[J]. Rheumatol Int, 2010, 30(8): 1125-1129.
[4] Marschner IC, Colquboun D, Simes RJ, et al. Long-term risk stratification for survisors of acute coronary syndromes. Results from the long-term intervention with pravastatin in ischemic disease(LIPID)study[J]. J Am Coll Cardiol, 2001, 38(1): 56-63.
[5] Cholesterol Treatment Trialists’ Collaborators. Efficacy and safety of cholesterol-lowing treatment: prospective meta-analysis of data from 90056 participants in 14 randomised trials of statins[J]. Lancet, 2005, 366(9493): 1267-1278.
[6] 吴兆苏, 姚崇华, 赵冬, 等. 11省市队列人群心血管疾病前瞻性研究II, 个体危险因素聚集与心血管病发病的关系[J]. 中华心血管病杂志, 2001, 29(4): 246-250. WU Zhaosu, YAO Chonghua, ZHAO Dong, et al. A prospective cohort study on cardiovascular disease incidence in 11 provinces in China. Associations between individual risk factor aggregation and cardiovascular disease incidence[J]. Chin J Cardiol, 2001, 29(4): 246-250.
[7] Zhao WH, Zhang J, Zhai Y, et al. Blood lipid profile and prevalence of dyslipidemia in Chinese adults[J]. Biomed Environ Sci, 2007, 20(4): 329-335.
[8] Erem C, Hacihasanoglu A, Deger O, et al. Prevalence of dyslipidemia andassociated risk factors among Turkish adults: Trabzon lipid study[J]. Endocrine, 2008, 34(1-3):36-51.
[9] 赵文华, 张坚, 由悦, 等. 中国18岁及以上人群血脂异常流行特点研究[J]. 中华预防医学杂志, 2005, 39(5): 306-310. ZHAO Wenhua, ZHANG Jian, YOU Yue, et al. Epidemiologic characteristics of dyslipidemia in people aged 18 years and over in China[J]. Chine Pre Med, 2005, 39(5): 306-310.
[10] 周红,德吉央宗,余光华. 87例中老年高脂血症患病情况调查[J]. 西南民族大学学报, 2011, 37(2): 246-249. ZHOU Hong, DEJIYANGZONG, YU Guanghua. A survey on 87 cases of old hyperlipidermia[J]. Journal of Southwest University for Nationalities, 2011, 37(2): 246-249.
[11] He J, Gu D, Reynolds K, et al. Serum total and lipprotein cholesterol levels and awareness, treatment, and control of hypercholesterolemia in China[J]. Circulation, 2004, 110(4): 405-411.
[12] Cannon CP. Mixed dyslipidemia, metabolic syndrome, diabetes mellitus and cardiovascular disease: clinical implications[J]. Am J Cardiol, 2008, 102(12A): 5L-9L.
[13] Martin SS, Michos ED. Mapping hyperlipidemia in young adulthood to coronary risk: importance of cumulative exposure and how to stay young[J]. Circulation, 2015, 131(5): 445-447.
[14] Friedman JI, Tang CY, de Haas HJ, et al. Brain imaging changes associated with risk factors for cardiovascular and cerebrovascular disease in asymptomatic patients[J]. JACC Cardiovasc Imaging, 2014, 7(10): 1039-1053.
[15] 中国成人血脂异常防治指南修订联合委员会. 中国成人血脂异常防治指南(2016年修订版)[J]. 中华循环杂志, 2016, 31(10): 937-953.
[16] Tietge UJ. Hyperlipidemia and cardiovascular disease: inflammation, dyslipidemia, and atherosclerosis[J]. Curr Opin Lipidol, 2014, 25(1): 94-95.
[17] Hopkins AL, Lamm MG, Funk JL, et al. Hibiscus sabdariffa L. in the treatment of hypertension and hyperlipidemia: a comprehensive review of animal and human studies[J]. Fitoterapia, 2013, 85: 84-94.
[18] Erem C, Hacihasanoglu A, Deger O, et al. Prevalence of dyslipidemia and associated risk factor among Turkish adults: Trabzon lipid study[J]. Endocr, 2008, 34(1-3): 36-51.
[19] 谢娟, 来则民, 黄国伟, 等. 高脂血症危险因素研究[J]. 疾病控制杂志, 2004, 4(1): 64-66. XIE Juan, LAI Zemin, HUANG Guowei, et al. Study on risk factor of hyperlipidemia[J]. Chin J Dis Control Prev, 2004, 4(1): 64-66.
[20] SU M, FU C, LI S,et al. Prevalence of hyperlipidemia and possible risk factors in rural Chinese adults: cohort study of health population in Yuhuan rural[J].Wei Sheng Yan Jiu, 2013, 42(5): 724-729.
[21] Wu JY, Duan XY, Li L, et al. Dyslipidemia in Shanghai, China[J]. Prev Med, 2010, 51(5): 412-415.
[22] Li Z, Yang R, Xu G, et al. Serum lipid concentrations and prevalence of dyslipidemia in a large professional population in Beijing[J]. J Clin Chem,2005, 51(1): 144-150.
[23] 邵金凤,谭先娥.生活方式干预对血脂异常人群的影响[J]. 护理学杂志, 2006, 21(5): 66-67. SHAO Jinfeng, TAN Xiane. Effect of intervention about the cure of lifestyle in the blood fat abnormity crowd[J]. Journal of Nursing Science, 2006, 21(5): 66-67.
[24] Chen G, Wang H, Zhang X, et al. Nutraceuticals and functional foods in the management of hyperlipidemia[J]. Crit Rev Food Sci Nutr, 2014, 54(9): 1180-1201.
[25] Wang SH, Sun ZL, Ruan XZ, et al. Dyslipidaemia among diabetic patients with ischemic stroke in a Chinese hospital[J]. Chin Med J, 2009, 122(21): 2567-2572.
[26] Ascunce RR, Berger JS, Weintraub HS, et al. The role of statin therapy for primary prevention: what is the evidence?[J]. Curr Atheroscler Rep, 2012, 14(2): 167-174.
[27] Lauer MS, Fontanrosa PB. Updated guidelines for cholesterol management[J]. JAMA, 2001, 285(19): 2508-2509.

相关文章 15

[1]	王建民,李晓峰,由志涛,董圣杰,赵宇驰,李占菊,邹德鑫,张剑锋,孙涛,杜伟. 基于可解释机器学习的后路腰椎椎体间融合术后慢性疼痛风险预测模型构建[J]. 山东大学学报 (医学版), 2026, 64(2): 78-88.
[2]	逄锦宏,苏萍,乔俊鹏,陈巧巧,陈学禹,赵颖颖,施婕,孙晓茹,李秋春,何蕊言,范轶欧,迟蔚蔚. 老年人群可改变心血管危险因素聚集模式与脑卒中的关联[J]. 山东大学学报 (医学版), 2025, 63(9): 11-19.
[3]	王乐,罗清馨,吴思佳,吴雨桐,葛祎蕾,俞一凡,韦云,吉寒冰,刘铁梅,张紫妍,修佳伟,薛付忠,李洪凯. 虚弱和癫痫关联研究:前瞻性队列和孟德尔随机化分析[J]. 山东大学学报 (医学版), 2025, 63(9): 20-30.
[4]	薛付忠. AI语言表征的多模态大数据队列设计理论方法体系[J]. 山东大学学报 (医学版), 2025, 63(8): 1-16.
[5]	于晴晴,常开锋,李吉庆,张凯,付苹,刘晓雯,赵英淇,薛付忠. 中老年人群高血压在非甾体抗炎药暴露与心脑血管疾病风险关联中的中介分析[J]. 山东大学学报 (医学版), 2023, 61(8): 79-85.
[6]	钟璐,薛付忠. 基于贝叶斯网络不确定性推理的肺癌风险预测模型[J]. 山东大学学报 (医学版), 2023, 61(4): 86-94.
[7]	袁孟绮,霍凤蕾,任会萍,郭秋爽,蓝菁. Sdccag3通过Wnt通路对高脂血症大鼠种植体骨结合的影响[J]. 山东大学学报 (医学版), 2022, 60(7): 66-73.
[8]	龙宇晗,罗霞,姜洁. 妊娠期异常高脂血症2例报告并文献复习[J]. 山东大学学报 (医学版), 2021, 59(3): 103-106.
[9]	李源,王强,石晓蕾,张晓丽,徐欣. 卷曲受体蛋白4在高脂血症大鼠种植体周围组织中的早期表达[J]. 山东大学学报 (医学版), 2020, 58(2): 29-35.
[10]	李明卓,孙秀彬,王春霞,杨洋,刘新辉,刘言训,薛付忠,袁中尚. 血脂正常人群HDL-C纵向变化与冠心病的关联性分析:一项回顾性队列研究[J]. 山东大学学报 (医学版), 2019, 57(8): 110-116.
[11]	徐源佑,杨亚超,王春霞,马晓天,薛付忠,刘言训,王萍. 基于体检队列的胃炎风险预测模型[J]. 山东大学学报 (医学版), 2019, 57(6): 112-116.
[12]	林伟强,王春霞,李明卓,孙秀彬,刘言训,薛付忠,袁中尚. 中老年人血压变化轨迹与冠心病发病的关系[J]. 山东大学学报 (医学版), 2019, 57(4): 106-112.
[13]	周苗,卞伟玮,柳晓涓,康凤玲,薛付忠,刘静. 嗜碱性粒细胞百分比与慢性肾脏病关系的回顾性队列研究[J]. 山东大学学报 (医学版), 2018, 56(3): 85-90.
[14]	马晓天,顾建华,王丽,薛付忠,刘言训. 血小板计数与代谢综合征关联性的前瞻性队列研究[J]. 山东大学学报 (医学版), 2018, 56(12): 92-97.
[15]	曹瑾,季晓康,孙秀彬,蒋正,薛付忠. γ-谷氨酰转肽酶与高尿酸血症关系的队列分析[J]. 山东大学学报（医学版）, 2017, 55(6): 124-128.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

健康管理人群高脂血症风险预测模型

A prediction model of hyperlipidemia risk based on the health management population

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

多维度评价

本文评价

推荐阅读 0