Random Forest model using obesity indices predicts kidney stone risk in diabetic-hypertensive adults

A Random Forest model using obesity composite indices achieved an AUC of 0.895 (0.864–0.926) for identifying kidney stone history in patients with both diabetes and hypertension. Roundness fat mass and lipid accumulation product were the strongest predictors. Validation was on a…

• Cross-sectional NHANES analysis (2007–2018) of adults with diabetes and hypertension; 9 machine learning algorithms compared, Random Forest selected.
• SHAP analysis revealed roundness fat mass (RFM) and lipid accumulation product (LAP) had the strongest association with self-reported kidney stone disease.
• Single dataset, self-reported outcome, and no external clinical validation limit generalizability; the web-based app was not prospectively tested.

RadPigeon summaries are original and for information only. They are not clinical advice.