Intraventricular hemorrhage in preterm infants: A systematic review of risk- and outcome-prediction models

Clinical Snapshot

Key Findings

• P Value: Not applicable to this narrative systematic review format

• Effect Size: No pooled effect size reported. Narrative synthesis indicates most models performed 'acceptably'; machine learning models demonstrated better discrimination than regression models in larger datasets. IVH severity (grade) was the most consistent predictor across all outcome-prediction models.

• Primary Outcome: Performance of IVH risk-prediction and outcome-prediction models in preterm infants, assessed narratively across 40 included studies

• Nnt Or Sensitivity: Individual model discrimination statistics (AUC/C-statistic) are referenced narratively but not pooled. Calibration statistics were infrequently reported across included studies. Sensitivity and specificity values for individual models are not summarised in the abstract.

• Confidence Interval: Not reported; no meta-analytic pooling was performed

Clinical Application

No specific prediction model is currently recommended for routine clinical implementation based on this review. The review identifies that existing models require external validation and calibration assessment before clinical deployment. Feasibility of future models will depend on standardisation of predictor timing, accessibility of biomarker assays, and integration into electronic medical record systems. IVH remains a significant cause of neonatal mortality and neurodevelopmental disability in Australian NICUs. The Australian and New Zealand Neonatal Network (ANZNN) collects standardised data on IVH in preterm infants, providing an existing infrastructure for multicenter model development and validation — directly addressing the gaps identified by this review. The RACGP and RACP do not currently endorse specific IVH prediction tools for clinical use. No TGA-approved predictive diagnostic device for IVH risk currently exists in Australia. PBS-listed interventions targeting IVH prevention (e.g., antenatal corticosteroids, magnesium sulphate for neuroprotection) remain the standard of care. This review supports the case for ANZNN-leveraged Australian validation studies of promising international prediction models before local clinical adoption. Preterm infants admitted to neonatal intensive care units, particularly those at highest risk of IVH (gestational age <32 weeks, extremely low birthweight). Clinicians involved in antenatal counselling, delivery room management, and NICU prognostication for families of preterm infants with IVH.

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.

References

1. 1.Shukla, V. V., Wen, J., & Carlo, W. A. (2026). Intraventricular hemorrhage in preterm infants: A systematic review of risk- and outcome-prediction models. Seminars in Fetal & Neonatal Medicine, 101725. https://doi.org/10.1016/j.siny.2026.101725