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 cohort

TL;DR

This study creates and validates a machine learning model to predict in-hospital mortality for ICU patients with diabetic kidney disease, using data from MIMIC and a Chinese hospital.

Contribution

The novel contribution is an interpretable machine learning model for predicting ICU mortality in diabetic kidney disease patients, validated in two cohorts.

Findings

XGBoost achieved an AUROC of 0.738 in internal validation and 0.746 in external validation.

Respiratory failure, lymphocyte count, and SOFA score were identified as key predictors of mortality.

The model provides satisfactory generalizability and interpretability for clinical use.

Abstract

Patients with diabetic kidney disease (DKD) admitted to the intensive care unit (ICU) face an exceptionally high risk of in-hospital mortality. Currently, effective tools for their early risk stratification are critically lacking. Therefore, this study aimed to develop and externally validate an interpretable machine learning (ML) model for predicting in-hospital mortality in this high-risk ICU-DKD patient population.

This retrospective cohort study involved developing and evaluating eight ML algorithms. Model performance was rigorously assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) provided model interpretability. Data from DKD patients with ≥24-hour ICU stays were extracted from the MIMIC-IV database (n=3,403) for model development. An independent external validation cohort (n=260) was collected from the First Affiliated Hospital of Yangtze University (YTU-ICU). The primary outcome was in-hospital mortality. Lasso regression identified key predictors. Model evaluation focused on the area under the ROC curve (AUROC), calibration, and net clinical benefit.

Ten features were selected for model development. Among the tested algorithms, XGBoost demonstrated superior predictive performance, achieving an AUROC of 0.738 (internal validation) and 0.746 (external validation), with corresponding accuracies of 72.18% and 72.69%. SHAP analysis highlighted respiratory failure, lymphocyte count, SOFA score, RDW, age, and SAPS II as the six most important predictors.

The developed XGBoost model demonstrates good predictive performance for in-hospital mortality in ICU-DKD patients, exhibiting satisfactory generalizability and interpretability. This tool supports early risk stratification and facilitates personalized treatment strategies in critical care settings.

Figures