Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 27 min ago
Peer-reviewedCC BY-NC-NDAnnals of Hepatology

Development and validation of a prediction model for acute kidney injury in cirrhosis with normal serum creatinine levels

  • Shenglong Lin1
  • Wenhai Ke2
  • Rong Wang3
  • Huaxi Ma1
  • Ziyuan Liao1
  • Jianyu Wang1
  • Minghua Lin1
  • Haibing Gao4
4 affiliations
  1. 1Department of Severe Hepatopathy, Mengchao Hepatobiliary Hospital of Fujian Medical University, No.66 Jintang Road, Jianxin Town, Cangshan District, Fuzhou, Fujian 350028, China
  2. 2Department of Infectious Disease, Pingtan Branch of Fujian Medical University Union Hospital, Pingtan, Fujian 350400, China; Department of Infectious Disease, Fujian Pingtan Comprehensive Experimental Zone Hospital, Pingtan, Fujian 350400, China
  3. 3Department of Severe Hepatopathy, Mengchao Hepatobiliary Hospital of Fujian Medical University, No.66 Jintang Road, Jianxin Town, Cangshan District, Fuzhou, Fujian 350028, China; The Clinical School of Fujian Medical University, Fuzhou, Fujian 350001, China
  4. 4Department of Severe Hepatopathy, Mengchao Hepatobiliary Hospital of Fujian Medical University, No.66 Jintang Road, Jianxin Town, Cangshan District, Fuzhou, Fujian 350028, China; Corresponding author.
Read full textDOICite

Abstract

Introduction and Objectives: Acute kidney injury (AKI) is a serious complication in decompensated cirrhosis (DC). Conventional kidney function markers, including serum creatinine (sCr) and estimated glomerular filtration rate (eGFR), are often inaccurate in these patients. We aimed to develop a predictive model for AKI using routine admission data. Patients and Methods: We retrospectively analyzed patients with DC and normal sCr admitted to a local tertiary hospital (Dec 2016-Dec 2022). AKI was defined per International Club of Ascites criteria. Predictors were selected using the least absolute shrinkage and selection operator regression and incorporated into a logistic model, internally validated via enhanced bootstrap and externally validated in the MIMIC-III cohort. Model performance was assessed using AUROC, calibration, and decision curve analysis (DCA). A user-friendly nomogram was constructed. Results: Of 1863 patients screened, 1091 met criteria; 122 (10.8%) developed AKI. AKI patients were older, had longer stays, worse liver function, more complications (hepatic encephalopathy, infections), and higher rates of hypertension (HT) and type 2 diabetes mellitus (DM2). sCr and eGFR had poor discrimination for AKI. The final model included age, neutrophil count, direct bilirubin, Child-Turcotte-Pugh score, DM2, and HT, achieving AUROC 0.755 (internal validation: AUROC 0.733, sensitivity 0.697, specificity 0.626). DCA showed greater clinical benefit than treat-all or treat-none strategies. External validation in 810 MIMIC-III patients yielded AUROC 0.729; bootstrap validation confirmed robustness (AUROC 0.752, sensitivity 0.748, specificity 0.677). Conclusions: We developed and validated a simple admission-based model for predicting AKI in DC, supporting its potential use for risk stratification and early intervention.

Related

  1. Development and external validation of prediction models for a trial-informed operational composite after stage 3 acute kidney injury
    Chao-Dong Chen, Peng-Chao Tian, Xin Chen +2
    Scientific ReportsPeer-reviewedCC BYFull textGeneral medicineDOAJ
  2. Development and validation of a prognostic prediction model for elderly patients with sepsis-associated acute kidney injury based on interpretable machine learning
    Nan Zhang, Jian-Zhong Wang, Qi Ma +2
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMCPMC
  3. Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
    Fengjie Guo, Shijie Zhong, Yang Tan +6
    Scientific ReportsPeer-reviewedCC BYFull text1 citedGeneral medicineDOAJ
  4. Creatinine increases have consistent and differential prognostic impact across kidney function
    Clinical kidney journalPeer-reviewedCC BY-NCFull textGeneral medicineEurope PMC
  5. Low Muscle Quality Predicts Creatinine-Based eGFR Overestimation Better than Skeletal Muscle Mass in Patients with Chronic Kidney Disease
    BiomedicinesPeer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{lin2026development,
  title = {{Development and validation of a prediction model for acute kidney injury in cirrhosis with normal serum creatinine levels}},
  author = {Shenglong Lin and Wenhai Ke and Rong Wang and Huaxi Ma and Ziyuan Liao and Jianyu Wang and Minghua Lin and Haibing Gao},
  journal = {Annals of Hepatology},
  year = {2026},
  month = jul,
  doi = {10.1016/j.aohep.2026.102223},
  url = {https://doi.org/10.1016/j.aohep.2026.102223},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Development and validation of a prediction model for acute kidney injury in cirrhosis with normal serum creatinine levels
AU  - Shenglong Lin
AU  - Wenhai Ke
AU  - Rong Wang
AU  - Huaxi Ma
AU  - Ziyuan Liao
AU  - Jianyu Wang
AU  - Minghua Lin
AU  - Haibing Gao
PY  - 2026
DA  - 2026/07/01
JO  - Annals of Hepatology
DO  - 10.1016/j.aohep.2026.102223
UR  - https://doi.org/10.1016/j.aohep.2026.102223
AB  - Introduction and Objectives: Acute kidney injury (AKI) is a serious complication in decompensated cirrhosis (DC). Conventional kidney function markers, including serum creatinine (sCr) and estimated glomerular filtration rate (eGFR), are often inaccurate in these patients. We aimed to develop a predictive model for AKI using routine admission data. Patients and Methods: We retrospectively analyzed patients with DC and normal sCr admitted to a local tertiary hospital (Dec 2016-Dec 2022). AKI was defined per International Club of Ascites criteria. Predictors were selected using the least absolute shrinkage and selection operator regression and incorporated into a logistic model, internally validated via enhanced bootstrap and externally validated in the MIMIC-III cohort. Model performance was assessed using AUROC, calibration, and decision curve analysis (DCA). A user-friendly nomogram was constructed. Results: Of 1863 patients screened, 1091 met criteria; 122 (10.8%) developed AKI. AKI patients were older, had longer stays, worse liver function, more complications (hepatic encephalopathy, infections), and higher rates of hypertension (HT) and type 2 diabetes mellitus (DM2). sCr and eGFR had poor discrimination for AKI. The final model included age, neutrophil count, direct bilirubin, Child-Turcotte-Pugh score, DM2, and HT, achieving AUROC 0.755 (internal validation: AUROC 0.733, sensitivity 0.697, specificity 0.626). DCA showed greater clinical benefit than treat-all or treat-none strategies. External validation in 810 MIMIC-III patients yielded AUROC 0.729; bootstrap validation confirmed robustness (AUROC 0.752, sensitivity 0.748, specificity 0.677). Conclusions: We developed and validated a simple admission-based model for predicting AKI in DC, supporting its potential use for risk stratification and early intervention.
SN  - 1665-2681
SN  - 2659-5982
ER  -