Machine learning for risk prediction of acute kidney injury in patients with diabetes mellitus combined with heart failure during hospitalization

Li et al. (2025) conducted an observational in Diabetes mellitus combined with heart failure (n=1,457). LightGBM machine learning model vs. Other machine learning algorithms (random forest, neural networks) was evaluated on Prediction of acute kidney injury (AKI) risk (AUC 0.804 (validation set)). The LightGBM machine learning model effectively predicted acute kidney injury risk in hospitalized diabetic patients with heart failure, achieving an AUC of 0.804 in the validation set.