12-LB: A Prediction Model on Incident End-Stage Kidney Disease (ESKD) among Individuals with Type 2 Diabetes (T2D) and Chronic Kidney Disease (CKD)

Abstract

Diabetes is the leading cause of ESKD, a costly and disabling condition that often results in premature death. This study aimed to predict incident ESKD among individuals with T2D comorbid with CKD. The ACCORD clinical trial data were split into a training set and a validation set by a ratio of 7:3. A dynamic time-varying Cox model was fit to predict the development of incident ESKD. Significant predictors were identified from a list of candidate variables, including demographic characteristics, physical exam results, laboratory results, medical history, drug information, and healthcare utilization. Model performance was evaluated by Brier score and C statistics. Confidence intervals (CI) were calculated using a bootstrap method. Decomposition analysis was conducted to assess the variable importance. Patient-level data of HARMONY Outcome clinical trial was used for external validation. A total of 6,982 diabetes patients with CKD at baseline were used for model development, with a median follow-up of 4 years and 312 ESKD events. The significant predictors for the ESKD risk model were female, race, smoking status, age at T2D diagnosis, SBP, HR, HbA1c, estimated glomerular filtration rate (eGFR) , urine albumin-creatinine ratio (UACR) , retinopathy event happened in last year, antihypertensive drug use, and an interaction term between SBP and female. The model demonstrated good performance in discrimination (C-statistics 0.764 [95% CI 0.763-0.811]) and calibration (Brier Score 0.0083 [95% CI 0.0063-0.0108]) . The top 3 most important predictors in the prediction model were eGFR, retinopathy event, and UACR. There were 2,954 patients with CKD extracted from HARMONY Outcome with 545 ESKD events and a median follow-up of 2 years. Acceptable discrimination (C-statistics: 0.701 [95% CI 0.665-0.716]) and calibration (Brier Score: 0.0794 [95% CI 0.0733-0.1022]) were demonstrated in the external data. The dynamic risk prediction of incident ESKD among individuals with T2D can be used to support better disease management to lower the risk of developing ESKD. 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.