基于健康管理队列的冠心病风险预测模型

发布时间：2018-06-17 04:39

本文选题：冠心病 + 健康管理队列　；参考：《山东大学学报(医学版)》2017年06期

【摘要】：目的构建基于山东省健康管理队列的冠心病风险预测模型。方法构建山东省健康管理队列,基于国际上较为通用的冠心病风险预测模型变量,应用Cox比例风险回归模型进行单因素分析,利用竞争风险模型建立心脑血管事件预测模型,使用十折交叉验证法检验模型稳定性。结果共纳入队列73 386人,其中男41 968人,女31 418人。队列中位随访时间3.10年。经随访共有1 545人发生冠心病,其中男958人,发病密度为5.95/1 000人年;女587人,发病密度为4.90/1 000人年。建立的男性模型AUC为0.809(95CI:0.804~0.815),O/E值为0.98;女性模型AUC为0.869(95%CI:0.863~0.874),O/E值为1.02。经十折交叉内部验证,男性模型AUC为0.806(95%CI:0.801~0.812),女性为0.866(95%CI:0.860~0.872)。结论构建的冠心病预测模型在健康管理队列中有较好的预测能力。
[Abstract]:Objective to construct a risk prediction model of coronary heart disease based on health management cohort in Shandong province. Methods the health management cohort of Shandong Province was constructed. The Cox proportional risk regression model was used to analyze the single factor and the competitive risk model was used to establish the cardiovascular and cerebrovascular events prediction model. The stability of the model was tested by a ten-fold cross-validation method. Results A total of 73 386 persons were enrolled, including 41 968 males and 31 418 females. The median follow-up time was 3. 10 years. A total of 1 545 patients with coronary heart disease were followed up, of whom 958 were males with an incidence density of 5.95 / 1 000 person-years, and 587 females with an incidence density of 4.90 / 1 000 person-years. The AUC of male model was 0.809 / 95CI: 0.804 / 0.804 / 0. 15 / O / E = 0.98, and the value of female model AUC was 0.869 / 95 / 0. 863 / 0.874 / E = 1.02respectively. The results showed that the male model AUC was 0.806 / 95CI: 0.801 / 0.812, and the female's was 0.866 / 95CI / 0.860 / 0.887 / 2. Conclusion the predictive model of coronary heart disease has good predictive ability in health management cohort.
【作者单位】：济宁医学院附属医院健康管理中心;山东大学公共卫生学院生物统计学系;山东大学齐鲁生物医学大数据研究中心;山东大学齐鲁医院手术室;
【基金】：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)
【分类号】：R541.4

【相似文献】