AI can successfully predict ESRD in diabetes patients, finds study

Netherlands: A machine-learning model can help in the successful prediction of end‐stage renal disease (ESRD) in patients with nephropathy and type 2 diabetes, suggests a recent study in the journal Diabetes, Obesity and Metabolism.

The prediction of long‐term renal risk in type 2 diabetes patients holds importance in clinical trials and clinical practice. Sunil Belur Nagaraj, University Medical Center Groningen, Groningen, The Netherlands, and colleagues hypothesized that machine learning models can accurately predict end‐stage renal disease by using multiple baseline demographic and clinical characteristics.

The study included a total of 11 789 patients (with type 2 diabetes and nephropathy) from three clinical trials: RENAAL (N = 1513), IDNT (N = 1715), and ALTITUDE (N = 8561). Eighteen baseline demographic and clinical characteristics were used as predictors to train machine learning models to predict ESRD (doubling of serum creatinine and/or end‐stage renal disease).

The area under the receiver operator curve (AUC) was used to assess the prediction performance of models and compared against traditional Cox proportional hazard regression and kidney failure risk equation models. 

"Nonlinear machine learning models can be used to predict long term ESRD, despite large inter‐patient variability, in patients with type 2 diabetes and nephropathy using baseline demographic and clinical characteristics. The proposed method offers the potential to create accurate and multiple outcome predictions automated models to identify high‐risk patients who could benefit from therapy in clinical practice," concluded the authors.

The study, "Machine Learning based Early Prediction of End‐stage Renal Disease in Patients with Diabetic Kidney Disease using Clinical Trials Data," is published in the journal Diabetes, Obesity and Metabolism.

DOI: https://doi.org/10.1111/dom.14178