论文部分内容阅读
目的构建健康管理人群慢性肾脏病(CKD)发病风险预测模型。方法从山东多中心健康管理纵向观察队列中选取年龄20岁以上、至少有两次纵向观察结果、初次观察结果未患CKD的健康管理对象,共17 654人,随访观察结局为CKD。应用Cox比例风险回归模型建立风险预测模型,以受试者工作特征曲线下面积(AUC)评价模型的拟合效果,应用十折交叉验证法验证模型的稳定性。结果观察期间共有770例新发CKD病例,发病密度为17.69/1 000人年。最终纳入模型的预测因子有年龄、性别、高血压、糖尿病、血肌酐、血尿素氮、血尿酸、嗜碱性粒细胞百分比。模型AUC为0.685(95%CI:0.678~0.692),且稳定性较好。结论建立的CKD风险预测模型在健康管理人群中有较好的预测能力。
Objective To establish a risk management model of chronic kidney disease (CKD) in health management population. Methods A total of 17 654 healthy subjects who did not have CKD for the first time were selected from the longitudinal multinational health management longitudinal observation cohort in Shandong Province. Patients aged 20 years and older were selected and at least two longitudinal observations were performed. The follow-up observation was CKD. The Cox proportional hazards regression model was used to establish the risk prediction model. The area under the receiver operating characteristic curve (AUC) was used to evaluate the fitting effect of the model. Ten-fold cross-validation was used to verify the stability of the model. Results A total of 770 new cases of CKD were observed during the observation period, with an incidence of 17.69 per 1000 person-years. The predictors of inclusion in the model were age, sex, hypertension, diabetes, serum creatinine, blood urea nitrogen, serum uric acid, and basophil percentage. The model AUC was 0.685 (95% CI: 0.678 ~ 0.692) with good stability. Conclusion The established CKD risk prediction model has good predictive ability in health management population.