Related Experiment Video
Updated: Jul 2, 2026
Development of a Hepatitis B Virus Reporter System to Monitor the Early Stages of the Replication Cycle
Published on: February 1, 2017
Noninvasive Prediction of Significant Hepatic Injury in Treatment-Naïve Children with Chronic HBV Infection
Jiaying Wu1, Xiaorong Peng1, Yunan Chang1
1Department of Infectious Diseases, Children's Hospital of Chongqing Medical University, National Clinical Research Center for Children and Adolescents' Health and Diseases, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing Key Laboratory of Child Infection and Immunity, Chongqing, 401122, People's Republic of China.
Insights
Developing a non-invasive model for significant hepatic injury (SHI) in children with chronic hepatitis B virus (HBV) infection is crucial. This study created a predictive tool using routine data, showing moderate accuracy for identifying SHI without invasive procedures.
Area of Science:
- Pediatric Hepatology
- Viral Hepatitis Research
- Biostatistics and Machine Learning in Medicine
Background:
- Significant hepatic injury (SHI) in children with chronic hepatitis B virus (HBV) infection necessitates early detection.
- Liver biopsy, the current standard, is invasive and not always feasible for routine assessment.
- Developing non-invasive methods is critical for timely SHI identification in pediatric HBV cases.
Purpose of the Study:
- To develop and validate a non-invasive predictive model for significant hepatic injury (SHI) in treatment-naïve children with chronic HBV infection.
- To assess the model's performance against existing clinical markers like alanine aminotransferase (ALT).
- To provide a tool for easier and safer identification of liver injury in pediatric HBV patients.
Main Methods:
- Retrospective analysis of treatment-naïve children with chronic HBV infection undergoing liver biopsy.
- Data preprocessing, imputation, and feature selection using LASSO regression.
- Development and optimization of nine machine learning models, including logistic regression (LR), with nested cross-validation.
- Construction and validation of a predictive nomogram based on the optimal LR model.
Main Results:
- The study included 246 children; 59.8% had SHI.
- LASSO regression identified five key predictors for SHI.
- The optimal LR model achieved an AUC of 0.799 in training, 0.781 in validation, and 0.707 in the independent testing cohort.
- The developed nomogram demonstrated moderate calibration and improved clinical utility over ALT alone.
Conclusions:
- A non-invasive predictive model for SHI in pediatric chronic HBV infection was successfully developed using routine clinical data.
- The model exhibits moderate predictive power, offering a potential alternative to invasive liver biopsy.
- While showing marginal improvement over ALT alone, the model aids in identifying SHI in this vulnerable population.
Background:
Significant hepatic injury (SHI) in children with chronic hepatitis B virus (HBV) infection requires timely identification, yet liver biopsy is invasive and not routinely feasible. This study aimed to develop a non-invasive predictive model for SHI.
Methods:
This retrospective analysis included treatment-naïve children with chronic HBV infection undergoing liver biopsy. Participants were randomly split into 70% training and 30% independent testing cohorts prior to preprocessing. Missing data imputation and least absolute shrinkage and selection operator (LASSO)-based feature selection were performed, and nine machine learning (ML) models were developed and optimized using nested cross-validation (CV). The optimal logistic regression (LR) model was used to construct and validate a predictive nomogram.
Results:
A total of 246 eligible children were included, of whom 147 (59.8%) had SHI. LASSO regression identified five predictors for model development. Among the evaluated ML models, LR showed stable performance, achieving an area under the receiver operating characteristic curve (AUC) of 0.799 (95% CI: 0.740-0.858) in the training folds, 0.781 (95% CI: 0.585-0.972) in the validation folds, and 0.707 (95% CI: 0.562-0.851) in the independent testing cohort. The nomogram showed moderate calibration and better clinical utility compared with alanine aminotransferase (ALT) alone across a broad range of threshold probabilities.
Conclusion:
We developed a non-invasive predictive model based on routine clinical data to detect SHI in treatment-naïve children with chronic HBV infection, which exhibited moderate predictive power and marginal improvement over ALT alone.
