Development and external validation of a machine learning model for predicting in-hospital mortality in ICU patients with diabetic kidney disease: a study utilizing the MIMIC database and a Chinese co
6 hours ago
- #diabetic kidney disease
- #ICU mortality
- #machine learning
- Study aimed to develop and validate a machine learning model for predicting in-hospital mortality in ICU patients with diabetic kidney disease (DKD).
- Utilized data from the MIMIC-IV database (n=3,403) for model development and a Chinese cohort (n=260) for external validation.
- XGBoost algorithm showed superior performance with AUROC of 0.738 (internal) and 0.746 (external validation).
- Key predictors identified included respiratory failure, lymphocyte count, SOFA score, RDW, age, and SAPS II.
- Model demonstrated good predictive performance, generalizability, and interpretability for early risk stratification.