Establishment and external validation of an online dynamic nomogram for predicting in-hospital death risk in sepsis-associated acute kidney disease

Abstract

Objectives Approximately one-third of patients with sepsis-associated acute kidney injury (AKI) will progress to acute kidney disease (AKD) with higher short-term mortality. We aimed to identify the clinical characteristics that influence in-hospital death in sepsis-associated AKD, and develop a nomogram to facilitate early warning. Methods Logical regression was applied to screen variables based on the clinical data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. A nomogram was established to predict in-hospital death risk in sepsis with AKD. Additionally, the eICU Collaborative Research Database (eICU-CRD) was utilized for external validation. The receiver operating characteristic curve and the calibration curve were used to determine the performance of the model. Results A total of 1779 patients with sepsis-associated AKD were included from MIMIC-IV, as well as 344 patients from eICU-CRD. Age, GCS score, systolic blood pressure (SBP), peripheral oxygen saturation (SpO2), platelets, white blood cells (WBC), and bicarbonate were significantly correlated with death. Moreover, the nomogram demonstrated high discrimination on both the training set (C-index, 0.829; 95%CI [0.807-0.852]) and the testing set (C-index, 0.760; 95%CI [0.706-0.814]). At the optimal cut-off value of 0.270, the sensitivity of the model in the training and validation dataset was 72.8% (95%CI [68.3%-76.9%]) and 64.5% (95%CI [54.9%-73.4%]), while the specificity was 79.2% (95%CI [76.9%-81.4%]) and 74.8% (95%CI [68.7%-80.2%]), respectively. Conclusion We identified seven predictors of in-hospital death in patients with sepsis-associated AKD and developed an online dynamic nomogram for accurately and conveniently predicting short-term outcomes, which performed well in the external dataset as well.