Related Experiment Video
Updated: Apr 5, 2026
Modeling Posthemorrhagic Hydrocephalus of Prematurity in Rats
Published on: March 28, 2025
Intraventricular hemorrhage in preterm infants: A systematic review of risk- and outcome-prediction models
Vivek V Shukla1, Junkai Wen1, Waldemar A Carlo1
1The University of Alabama at Birmingham, Division of Neonatology, 1700 6th Avenue South, WIC, Suite 9380, Birmingham, AL, 35233, USA.
Insights
Predicting intraventricular hemorrhage (IVH) in preterm infants is crucial. Current models show promise but need better validation and standardization for improved clinical use in neonatal care.
Area of Science:
- Neonatal Medicine
- Medical Informatics
- Biostatistics
Background:
- Intraventricular hemorrhage (IVH) is a significant cause of mortality and neurodevelopmental issues in premature infants.
- Effective prediction models are needed to identify infants at risk and forecast outcomes.
Purpose of the Study:
- To systematically review existing prediction models for IVH occurrence and outcomes in preterm infants.
- To assess the performance, generalizability, and clinical relevance of these models.
Main Methods:
- Systematic review of 40 studies from PubMed, Scopus, and Web of Science (1980-2025).
- Evaluation of regression and machine learning models using perinatal clinical variables, physiologic indices, and biomarkers.
- Analysis of model predictors, performance metrics, and validation strategies.
Main Results:
- Models incorporated diverse predictors; machine learning showed better discrimination in larger datasets.
- IVH severity was the most consistent outcome predictor.
- Limited generalizability due to heterogeneity, small sample sizes, and inconsistent measurements; clinical relevance hampered by poor reporting of calibration and validation.
Conclusions:
- Existing IVH prediction models show acceptable performance but face limitations in generalizability and clinical applicability.
- Future research should focus on standardizing definitions, using multicenter data, and rigorous validation to enhance clinical relevance and neonatal care.
Abstract:
Intraventricular hemorrhage (IVH) is a major complication of prematurity and one of the top causes of mortality and neurodevelopmental impairment. We conducted a systematic review of PubMed, Scopus, and Web of Science (From 1980 to 2025), identifying 40 studies evaluating prediction models (regression and machine learning) for risk of IVH occurrence and short- and long-term outcomes in preterm infants with IVH. Across these published studies, IVH risk prediction models included combinations of perinatal clinical variables, physiologic and hemodynamic indices, and serum biomarkers. Outcome-prediction models likewise varied. IVH grade was commonly included, with varying inclusion of comorbidities and neuroimaging-based injury markers. Most models performed acceptably, with machine-learning models showing better discrimination in larger datasets. However, the generalizability of the models is limited by heterogeneity in predictors, limited sample sizes, and inconsistent timing of predictor measurements. IVH severity remained the most consistent predictor across all outcome-prediction models. Despite promising performance assessments, clinical relevance is limited due to the infrequent reporting of model calibration, internal validation, and external validation. Future research that standardizes predictor definitions, leverages multicenter cohorts, and ensures thorough validation can advance early IVH risk and outcome-prediction models, thereby meaningfully improving clinical relevance and neonatal care.
