Development and validation of the prediction model for mortality in patients with diabetic kidney disease in intensive care unit: a study based on medical information Mart for intensive care

Abstract

We aimed to explore factors associated with mortality of diabetic kidney disease (DKD), and to establish a prediction model for predicting the mortality of DKD. This was a cohort study. In total, 1,357 DKD patients were identified from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, with 505 DKD patients being identified from the MIMIC-III as the testing set. The outcome of the study was 1-year mortality. COX proportional hazard models were applied to screen the predictive factors. The prediction model was conducted based on the predictive factors. A receiver operating characteristic (ROC) curve with the area under the curve (AUC) was calculated to evaluate the performance of the prediction model. The median follow-up time was 365.00 (54.50,365.00) days, and 586 patients (43.18%) died within 1 year. The predictive factors for 1-year mortality in DKD included age, weight, sepsis, heart rate, temperature, Charlson Comorbidity Index (CCI), Simplified Acute Physiology Score (SAPS) II, and Sequential Organ Failure Assessment (SOFA), lymphocytes, red cell distribution width (RDW), serum albumin, and metformin. The AUC of the prediction model for predicting 1-year mortality in the training set was 0.771 [95% confidence interval (CI): 0.746-0.795] and the AUC of the prediction model in the testing set was 0.795 (95% CI: 0.756-0.834). This study establishes a prediction model for predicting mortality of DKD, providing a basis for clinical intervention and decision-making in time.

Keywords

• Diabetic kidney disease
• mortality
• prediction model
• MIMIC database