NORA: A Nephrology-Oriented Representation Learning Approach Towards Chronic Kidney Disease Classification
This work addresses CKD detection in outpatient settings where renal biomarkers are unavailable, though it is incremental as it applies existing methods to a specific medical domain.
The paper tackled early detection of Chronic Kidney Disease (CKD) using non-renal clinical variables from EHR data, introducing the NORA approach that improved classification performance, particularly enhancing the F1-score for early-stage CKD.
Chronic Kidney Disease (CKD) affects millions of people worldwide, yet its early detection remains challenging, especially in outpatient settings where laboratory-based renal biomarkers are often unavailable. In this work, we investigate the predictive potential of routinely collected non-renal clinical variables for CKD classification, including sociodemographic factors, comorbid conditions, and urinalysis findings. We introduce the Nephrology-Oriented Representation leArning (NORA) approach, which combines supervised contrastive learning with a nonlinear Random Forest classifier. NORA first derives discriminative patient representations from tabular EHR data, which are then used for downstream CKD classification. We evaluated NORA on a clinic-based EHR dataset from Riverside Nephrology Physicians. Our results demonstrated that NORA improves class separability and overall classification performance, particularly enhancing the F1-score for early-stage CKD. Additionally, we assessed the generalizability of NORA on the UCI CKD dataset, demonstrating its effectiveness for CKD risk stratification across distinct patient cohorts.