健康管理人群2型糖尿病发病风险预测模型

Prediction models on the onset risks of type 2 diabetes among the health management population

目的构建健康管理人群2型糖尿病3年发病风险预测模型。方法依托山东多中心健康管理纵向观察大数据库,选择20~75岁的基线未患2型糖尿病者构建队列。采用Cox比例风险回归构建2型糖尿病预测模型,以受试者工作特征曲线下面积(AUC)评价模型的预测效能,以十折交叉验证法检验模型的稳定性。结果随访期间共新发糖尿病1 624例,男性和女性的发病密度分别为15.00‰、10.83‰。男性预测模型最终纳入的变量包括年龄、体质量指数、空腹血糖、甘油三酯、谷丙转氨酶、白细胞计数。纳入女性预测模型的变量包括年龄、空腹血糖、甘油三酯、高密度脂蛋白、谷丙转氨酶。男性和女性预测模型的AUC分别为0.795(95%CI:0.764~0.827)和0.707(95%CI:0.654~0.759)。结论分性别建立的2型糖尿病发病风险预测模型在健康管理人群中均具有较好预测能力。

Objective To construct prediction models to estimate the risks of developing type 2 diabetes mellitus （T2DM） in 3 years among the health management population in China's Mainland. Methods Non-diabetic people aged 20 to 75 years at the baseline were chosen from Shandong Multi-center Longitudinal Cohort for Health Management to compose our cohort. Cox＇s proportional hazards regression model was adopted to build T2DM prediction model. The ar- ea under the receiver operating characteristic （ROC） curve （ AUC ） was used to evaluate the predictability of the model. Ten-fold cross-validation was adopted to test the stability of the model. Results During the follow-up of 3.68 ± 2.8 years, 1,624 cases of new-onset diabetes occurred. The incidence density of male and female was 15. 00%0 and 10.83%0, respectively. The risk factors for the male model included age, body mass index （ BMI）, fasting plasma glucose （FPG）, triglyceride, alanine aminotransferase （ALT）, and white blood cell （WBC） count. The risk factorsfor the female model included age, FPG, triglyceride, high density lipoprotein cholesterol （HDL-C）, and ALT. The AUC of the male model and female model was 0.795 （95% CI： 0. 764-0.827） and 0. 707 （95% CI： 0. 654-0. 759）, respectively. Conclusion The male and female prediction models we constructed have high predictability and reliability among the health management population.