1342-P: A Predictive Model for Five-Year Early Diabetic Kidney Disease

Introduction & Objectives: Early identification of individuals at elevated risk of developing diabetic kidney disease (DKD) could improve clinical care and prognosis through enhanced cost-effective surveillance and better management of underlying health conditions. The aim of this study was to develop an effective and practical model for predicting early DKD risk in a community-based prospective cohort.

Methods: A prospective community-based cohort study was undertaken from 2013 to 2018. We analyzed data from 1545 people with diabetes and normal kidney function at baseline. The least absolute shrinkage and selection operator regression with cross-validation was used to identify potential predictive variables. A less complex DKD prediction model was derived from logistic regression and presented as a nomogram. The performance of the novel DKD prediction model was compared with that of the existing prediction model by assessing model discrimination.

Results: Six predictors of DKD were identified: diabetes duration, family history of diabetes, systolic blood pressure, urine albumin-to-creatinine ratio, estimated glomerular filtration rate, and glycated albumin (GA). The new DKD predictive model demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.797 and was internally validated with a corrected AUC of 0.786. There were no significant deviations between observed probability and predicted probability. The predictive performance of the existing DKD risk prediction model was significantly lower than our new DKD risk prediction model (AUC: 0.681 vs. 0.797, P <0.001). In addition, the predictive value of GA was higher than that of Hemoglobin A1c and fasting plasma glucose.

Conclusions: The 5-year early DKD predictive model, derived from a community-based cohort, demonstrates good performance. Additionally, GA holds more significant importance than other glucose indicators in predicting DKD.