Related Experiment Video
Updated: May 12, 2026

Technical Refinement of a Bilateral Renal Ischemia-Reperfusion Mouse Model for Acute Kidney Injury Research
Published on: November 3, 2023
Development of a Clinical Prediction Model for Acute Kidney Injury Among In-Hospital Cardiac Arrest Patients During
Halidan Abudu1, Ziquan Liu1, Yanxiang Niu1
1School of Disaster and Emergency Medicine, Tianjin University, 300192 Tianjin, China.
This study developed a nomogram to predict acute kidney injury (AKI) in patients after in-hospital cardiac arrest (IHCA). The model uses clinical factors to identify high-risk patients, improving AKI prediction in intensive care units (ICUs).
Area of Science:
- Nephrology
- Critical Care Medicine
- Medical Informatics
Background:
- Acute kidney injury (AKI) is a critical complication and cause of mortality in patients following in-hospital cardiac arrest (IHCA).
- Existing clinical prediction models for AKI in IHCA patients are limited, highlighting a need for improved risk assessment tools.
- This study addresses the gap by developing a nomogram for predicting AKI in intensive care unit (ICU) patients post-cardiac arrest.
Purpose of the Study:
- To develop and validate a predictive model (nomogram) for acute kidney injury (AKI) in patients experiencing in-hospital cardiac arrest (IHCA).
- To utilize readily available clinical characteristics for predicting the likelihood of AKI during ICU hospitalization.
- To enhance clinical decision-making and patient management for IHCA survivors at risk of AKI.
Main Methods:
- A retrospective study utilizing the Medical Information Mart for Intensive Care IV (MIMIC-IV) database.
- Variable selection performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression.
- Model development through univariate and multivariate logistic regression, with performance evaluated using ROC curves, DCA, and CIC.
Main Results:
- A nomogram was constructed using 1427 cardiac arrest (CA) patients, divided into training (n=999) and validation (n=428) cohorts.
- Five independent predictors for post-cardiac arrest AKI were identified: weight, SpO2, sodium levels, SOFA score, and OASIS score.
- The model demonstrated strong predictive performance with AUCs of 0.920 (training) and 0.875 (validation), and good clinical utility.
Conclusions:
- The developed nomogram shows high predictive accuracy for AKI in patients following IHCA.
- The model effectively integrates key clinical variables for risk stratification.
- This tool can aid clinicians in identifying and managing AKI risk in critically ill cardiac arrest patients.
Related Concept Videos
Acute Kidney Injury IV: Diagnostic Studies and Prevention
Acute Kidney Injury I: Introduction
Acute Kidney Injury V: Interprofessional Care
Acute Kidney Injury III: Clinical Manifestations
Acute Kidney Injury II: Pathophysiology
Acute Kidney Injury VI: Nursing Management
