Development and validation of a nomogram for predicting in-hospital death in cirrhotic patients with acute kidney injury

Abstract

Background

The purpose of this study was to develop a nomogram for predicting in-hospital mortality in cirrhotic patients with acute kidney injury (AKI) in order to identify patients with a high risk of in-hospital death early.

Methods

This study collected data on cirrhotic patients with AKI from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. Multivariate logistic regression was used to identify confounding factors related to in-hospital mortality, which were then integrated into the nomogram. The concordance index (C-Index) was used to evaluate the accuracy of the model predictions. The area under the curve (AUC) and decision curve analysis (DCA) was used to assess the predictive performance and clinical utility of the nomogram.

Results

The final study population included 886 cirrhotic patients with AKI, and 264 (29.8%) died in the hospital. After multivariate logistic regression, age, gender, cerebrovascular disease, heart rate, respiration rate, temperature, oxygen saturation, hemoglobin, blood urea nitrogen, serum creatinine, international normalized ratio, bilirubin, urine volume, and sequential organ failure assessment score were predictive factors of in-hospital mortality. In addition, the nomogram showed good accuracy in estimating the in-hospital mortality of patients. The calibration plots showed the best agreement with the actual presence of in-hospital mortality in patients. In addition, the AUC and DCA curves showed that the nomogram has good prediction accuracy and clinical value.

Conclusions

We have created a prognostic nomogram for predicting in-hospital death in cirrhotic patients with AKI, which may facilitate timely intervention to improve prognosis in these patients.