AUTHOR=Chen Fan , Xu Kedong , Han Yimin , Ding Jiachun , Ren Jiaqiang , Cao Fang , Wang Yaochun , Qian Weikun , Wang Zheng , Wu Zheng , Ma Zhenhua 

TITLE=Risk factors for acute kidney injury in patients with acute pancreatitis and construction of nomogram model: a single-center study and external validation

JOURNAL=Frontiers in Medicine

VOLUME=Volume 12 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2025.1626664

DOI=10.3389/fmed.2025.1626664

ISSN=2296-858X

ABSTRACT=ObjectiveThis study aims to utilize clinical data from patients with acute pancreatitis (AP) recorded in the MIMIC-IV database to analyze the risk factors associated with acute kidney injury (AKI) and to develop a nomogram prediction model.MethodsThis study included clinical data from 754 patients diagnosed with AP sourced from the MIMIC-IV database. They were randomly divided into a training set and an internal validation set. Another 202 patients from the First Affiliated Hospital of Xi’an Jiaotong University were used as an external validation set. Univariate and multivariate logistic regression analyses were conducted to identify the independent influencing factors associated with AKI in these patients. A nomogram model was developed to predict the incidence of AKI, and its performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA).ResultsSix independent risk factors were identified as predictors of AKI incidence in patients with AP and utilized to construct the nomogram model. The AUC values for the training set, internal validation set, and external validation set were 0.770 (95% CI, 0.719–0.821), 0.755 (95% CI, 0.676–0.834), and 0.628 (95% CI, 0.551–0.706), respectively. Furthermore, the calibration curve indicates that the predicted outcomes align well with the actual observations. Finally, the DCA demonstrates that the nomogram model possesses significant clinical applicability.ConclusionThe nomogram developed in this study for predicting the incidence of AKI in patients with AP demonstrates strong predictive value and clinical applicability, thereby offering clinicians a more accurate and practical tool for prediction.