Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease.

Link: https://doi.org/10.1007/s00125-021-05444-0
Authors: Chan, Lili; Nadkarni, Girish N; Fleming, Fergus; McCullough, James R; Connolly, Patricia; Mosoyan, Gohar; El Salem, Fadi; Kattan, Michael W; Vassalotti, Joseph A; Murphy, Barbara; Donovan, Michael J; Coca, Steven G; Damrauer, Scott M

Abstract: Predicting progression in diabetic kidney disease (DKD) is critical to improving outcomes. We sought to develop/validate a machine-learned, prognostic risk score (KidneyIntelX™) combining electronic health records (EHR) and biomarkers. This is an observational cohort study of patients with prevalent DKD/banked plasma from two EHR-linked biobanks. A random forest model was trained, and performance (AUC, positive and negative predictive values [PPV/NPV], and net reclassification index [NRI]) was compared with that of a clinical model and Kidney Disease: Improving Global Outcomes (KDIGO) categories for predicting a composite outcome of eGFR decline of ≥5 ml/min per year, ≥40% sustained decline, or kidney failure within 5 years. KidneyIntelX improved prediction of kidney outcomes over KDIGO and clinical models in individuals with early stages of DKD.