A prediction model on incident chronic kidney disease among individuals with type 2 diabetes in the United States.

Abstract

Early identification of incident chronic kidney disease (CKD) in individuals with diabetes may help improve patients' clinical outcomes. This study aimed to develop a prediction equation for incident CKD among people with type 2 diabetes (T2D). A time-varying Cox model was applied to data from the ACCORD trial to predict the risk of incident CKD. A list of candidate variables was chosen based on literature reviews and experts' consultations, including demographic characteristics, vitals, laboratory results, medical history, drug use and health care utilization. Model performance was evaluated. Decomposition analysis was conducted, and external validation was performed. In total, 6006 patients with diabetes free of CKD were included, with a median follow-up of 3 years and 2257 events. The risk model included age at T2D diagnosed, smoking status, body mass index, high-density lipoprotein, very-low-density lipoprotein, alanine aminotransferase, estimated glomerular filtration rate, urine albumin-creatinine ratio, hypoglycaemia, retinopathy, congestive heart failure, coronary heart disease history, antihyperlipidaemic drug use, antihypertensive drug use and hospitalization. The urine albumin-creatinine ratio, estimated glomerular filtration rate and congestive heart failure were the top three factors that contributed most to the incident CKD prediction. The model showed acceptable discrimination [C-statistic: 0.772 (95% CI 0.767-0.805)] and calibration [Brier Score: 0.0504 (95% CI 0.0477-0.0531)] in the Harmony Outcomes Trial. Incident CKD prediction among individuals with T2D was developed and validated for use in decision support of CKD prevention.