Related Experiment Video
Updated: Sep 13, 2025
A Large Animal Model for Acute Kidney Injury by Temporary Bilateral Renal Artery Occlusion
Published on: February 2, 2021
Development and validation of a real-time risk prediction model for acute kidney injury in hospitalized pediatric
Chao Zhang1, Chen Wang1, Qin-Shi Hu2
1Department of Clinical Epidemiology and Evidence-Based Medicine, National Center for Children Health, Beijing Children's Hospital, Capital Medical University, No.56 Nanlishi Road, Xicheng District, Beijing, 100045, China.
Insights
This study developed a real-time acute kidney injury risk prediction model for hospitalized children. The model demonstrates excellent performance, aiding in timely prevention of acute kidney injury.
Area of Science:
- Pediatric Nephrology
- Clinical Informatics
- Machine Learning in Healthcare
Background:
- Acute kidney injury (AKI) in pediatric patients leads to longer hospital stays and increased mortality.
- Existing AKI prediction models often use fixed time windows, limiting real-world clinical application.
- There is a need for a dynamic, real-time AKI risk prediction tool for hospitalized children.
Purpose of the Study:
- To develop and validate a real-time machine learning model for predicting AKI in hospitalized pediatric patients.
- To overcome the limitations of pre-defined time windows in previous AKI prediction models.
- To provide a feasible tool for proactive AKI management in pediatric care.
Main Methods:
- A retrospective cohort of pediatric patients from two major hospitals was used.
- A stacking ensemble model combining XGBoost, LightGBM, and CatBoost was developed.
- Hyperparameters were optimized using a particle swarm optimization algorithm.
- Model performance was evaluated using Area Under the Receiver-Operating Curve (AUROC) and Area Under the Precision-Recall Curve (AUPR).
Main Results:
- The study included 26,671 patients (36,828 hospitalizations).
- The developed model showed excellent predictive performance for AKI within 24 hours.
- Internal validation yielded AUROC 0.851 and AUPR 0.322.
- External validation confirmed feasibility with AUROC 0.869 and AUPR 0.270.
Conclusions:
- A novel, real-time risk prediction model for pediatric AKI was successfully developed and validated.
- The model's strong performance in both internal and external validation supports its clinical utility.
- This tool can facilitate real-time prevention strategies for acute kidney injury in hospitalized children.
Background:
Acute kidney injury is associated with a prolonged hospital stay and high mortality for pediatric patients. The previous prediction models are based on a pre-defined time window which may affect its feasibility in clinical practice. This study aimed to develop and validate a real-time acute kidney injury risk prediction model for hospitalized pediatric patients.
Methods:
Based on a retrospective cohort composed of eligible pediatric patients hospitalized in Beijing Children's Hospital and Chongqing Children's Hospital, a machine learning model to predict acute kidney injury occurrence was developed and validated. The prediction model was established using a stacking technique to combine three base learners including XGBoost, LightGBM, and CatBoost. Particle swarm optimization algorithm was used to tune hyperparameters. Next, we assessed the performance of the prediction model using the area under the receiver-operating curve and the area under the precision-recall curve.
Results:
A total of 26,671 patients were included (20,967 in the derivation set, 5242 in the internal validation set, and 462 in the external validation set) contributing to 36,828 hospitalizations. The new proposed model had excellent performance for predicting any acute kidney injury within 24 hours. Both the internal [area under the receiver-operating curve (AUROC) was 0.851, area under the precision-recall curve (AUPR) was 0.322] and external validation set (AUROC was 0.869, AUPR was 0.270) approved the model's feasibility in predicting the risk of acute kidney injury.
Conclusion:
The established risk predicting model can be used for real-time prevention of acute kidney injury in hospitalized pediatric patients.
Related Concept Videos
01:30Acute Kidney Injury IV: Diagnostic Studies and Prevention
01:22Acute Kidney Injury I: Introduction
01:20Acute Kidney Injury V: Interprofessional Care
01:29Acute Kidney Injury II: Pathophysiology
01:29Acute Kidney Injury III: Clinical Manifestations
01:22Acute Kidney Injury VI: Nursing Management