论文部分内容阅读
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。
Objective To construct a risk prediction model of coronary heart disease based on Shandong province health management cohort. Methods Based on the internationally accepted coronary risk prediction model variables, a Cox proportional hazards regression model was used to perform univariate analysis. The competition risk model was used to establish the cardiovascular and cerebrovascular events prediction model. Ten-fold cross-validation Test model stability. Results A total of 73 386 people were enrolled in the cohort, including 41 968 males and 31 418 females. The median follow-up of the cohort was 3.10 years. A total of 1 545 coronary heart disease patients were followed up, 958 of them were male, with a prevalence of 5.95 / 1000 person-years and 587 women, with an incidence of 4.90 / 1000 person-years. The AUC of the established male model was 0.809 (95CI: 0.804-0.815), and the O / E value was 0.98. The AUC of the female model was 0.869 (95% CI: 0.863-0.874) and the O / E value was 1.02. After 10-fold cross-validation, male model AUC was 0.806 (95% CI: 0.801-0.812) and female was 0.866 (95% CI: 0.860-0.872). Conclusion The prediction model of coronary heart disease constructed has good predictive ability in the health management cohort.