13-LB: A Prediction Model of Chronic Kidney Disease Progression among Individuals with Type 2 Diabetes in the United States

Abstract

CKD progression among individuals with T2D is associated with poor outcomes and high costs. The risk factors for CKD progression in T2D have not been fully studied. This study aimed to predict CKD progression among individuals with T2D. Using the ACCORD clinical trial, a time-varying Cox model was developed to predict the risk of CKD progression among patients with CKD. CKD progression was defined as a 50% decline, or 25 mL/min/1.73 m2 decline in eGFR from baseline, doubling of the serum creatinine, or onset of ESKD. A list of candidate variables included demographic characteristics, physical exam, laboratory, medical history, drug use, and healthcare utilization. A stepwise algorithm was used for variable selection. Data was separated into training and validation set. Model performance was evaluated by Brier score (BS) and C statistics. Confidence intervals (CI) were calculated by bootstraping. Decomposition analysis was conducted to assess the predictor contribution. Generalizability was assessed on patient-level data of the HARMONY Outcome clinical trial. A total of 6,982 T2D patients with CKD were used for model development, with a median follow-up of 4 years and 3,346 CKD progression events. The predictors for CKD progression included female sex, age at T2D diagnosis, smoking status, BP, HR, HbA1c, ALT, eGFR, UACR, retinopathy event, hospitalization, interaction of SBP and smoking, and SBP and ALT. The model demonstrated good discrimination (C-statistics 0.745 [95% CI 0.723-0.763]) and calibration (BS 0.0923 [95% CI 0.0873-0.0965]) . The most contributing predictors for CKD progression were eGFR, HbA1c, and SBP. There were 2,954 patients with CKD extracted from HARMONY with 640 CKD progression events and median follow-up of 2 years. The model demonstrated acceptable discrimination (C-statistics: 0.742 [95% CI 0.721-0.7645]) and calibration (BS: 0.0988 [95% CI 0.0952-0.1022]) in the external data. For high-risk patients with both diabetes and CKD, the tool as a dynamic risk prediction of CKD progression may help develop novel strategies to lower the risk of CKD progression. Disclosure Y. Lin: None. H. Shao: Board Member; BRAVO4HEALTH, LLC. A. H. Anderson: None. V. Fonseca: Consultant; Abbott, Asahi Kasei Corporation, Bayer AG, Novo Nordisk, Sanofi, Research Support; Fractyl Health, Inc., Jaguar Gene Therapy, Stock/Shareholder; Abbott, Amgen Inc., BRAVO4Health, Mellitus Health. V. Batuman: None. L. Shi: None.