Establishment Of A Risk Prediction Model For Type 2 Diabetes Mellitus Complicated With Diabetic Kidney Disease

Objective: To explore the risk factors of diabetic kidney disease in patients with type 2diabetes mellitus and to build a risk prediction model of diabetic kidney disease,so as to provide reference for clinical workers to identify high risk groups as early as possible and develop individualized intervention methods reasonably.Methods: Clinical data of type 2 diabetes mellitus(T2DM)patients admitted to the First Affiliated Hospital of Wannan Medical Colloge from November 2019 to September 2022 were continuously collected,after screening the inclusion criteria and exclusion criteria,data of 248 patients with T2 DM were analyzed retrospectively.The enrolled subjects were grouped according to urine trace albumin to creatinine ratio(UACR),UACR less than 30mg/g were included in simple diabetes mellitus(SDM)group,patients with UACR between 30 and 300mg/g were divided into diabetic kidney disease(DKD)group.Baseline data were compared between the two groups,variables with statistical differences were included in logistic regression analysis to screen independent risk factors for DKD in T2 DM patients.According to the results,a nomogram model was constructed to predict the risk of DKD in T2 DM patients.The model was internally verified by Bootstrap method(1000 times resamulation),concordance index(C-index)was calculated and receiver operating characteristic(ROC)curve was drawn to evaluate the predictive performance of the model,calibration plots were plotted for consistency test.Results: The occurrence of DKD in T2 DM patients was estimated with the duration of diabetes mellitus,glycosylated hemoglobin,hemoglobin,high density lipoprotein,serum uric acid,systolic blood pressure,free triiodothyronine,albumin,neutrophil/lymphocyte ratio,history of hypertension,coronary heart disease,cerebral infarction,diabetic retinopathy(P < 0.05).Uuric acid more than or equal to 420(male)/360(female)umol/L,systolic blood pressure more than or equal to130 mm Hg,high level of neutrophil/lymphocyte ratio and low level of free triiodothyronine and combined with hypertension and diabetic retinopathy were independent risk factors for DKD.The above risk factors were included in the prediction model of the nomogram,and the prediction efficiency of the model was better.The area under ROC curve of the model was 0.860(95%CI=0.810～0.911),and The optimal cut-off value was 0.562,and the specificity and sensitivity were 0.932 and0.670 respectively.Internal verification C index was 0.860.The correction curve showed that the prediction results of the nomogram model had a good consistency with the actual results.Conclusion:The DKD risk prediction model established in this study has a good differentiation degree,which has important guiding value for screening high risk groups of DKD and formulating individualized intervention measures.