Related Experiment Video
Updated: Aug 4, 2026
Modeling Neonatal Intraventricular Hemorrhage Through Intraventricular Injection of Hemoglobin
Published on: August 25, 2022
Prediction of post-hemorrhagic ventricular dilatation trajectory using a growth mixture model in preterm infants
Grace M Musiime1, Khorshid Mohammad1, Sarfaraz Momin1
1Department of Pediatrics, Section of Newborn Critical Care, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.
Insights
Predictive modeling of post-hemorrhagic ventricular dilatation (PHVD) using anterior horn width (AHW) shows promise for early identification of infants needing intervention. This approach aids in individualized risk-benefit assessments for preterm infants.
Area of Science:
- Neonatal Medicine
- Pediatric Neurology
- Medical Imaging Analysis
Background:
- Post-hemorrhagic ventricular dilatation (PHVD) in preterm infants requires careful management balancing intervention benefits against risks.
- Cranial ultrasound (cUS) measurements guide early intervention decisions for PHVD.
- Improved neurodevelopmental outcomes are linked to timely PHVD intervention.
Purpose of the Study:
- To evaluate the utility of growth mixture modeling (GMM) for identifying PHVD trajectories.
- To compare GMM-identified trajectories with neurosurgical intervention outcomes.
- To assess the potential of predictive modeling for early PHVD management.
Main Methods:
- Anterior horn width (AHW) and ventricular index (VI) were measured via cUS in preterm infants (<29 weeks) with intraventricular hemorrhage (2010-2018).
- PHVD was defined using AHW (>6 mm) or VI (>97th percentile).
- GMM was employed to identify latent trajectory classes and compare them to neurosurgical intervention status.
Main Results:
- Growth mixture modeling using AHW demonstrated high accuracy in classifying infants with and without PHVD, and those with or without intervention.
- VI-based GMM showed lower accuracy in distinguishing PHVD trajectories compared to AHW.
- The AHW GMM successfully identified a significant proportion of infants with severe PHVD.
Conclusions:
- Anterior horn width growth mixture modeling shows potential for early identification of severe PHVD trajectories.
- Refined predictive models can differentiate PHVD progression, aiding early intervention decisions.
- Individualized, data-driven risk-benefit assessments are crucial for managing PHVD in preterm infants.
Background:
Early intervention for post-hemorrhagic ventricular dilatation (PHVD), guided by ventricular size measurements from cranial ultrasound (cUS), is associated with improved neurodevelopmental outcomes in preterm infants but benefits must be balanced against intervention risks.
Methods:
Anterior horn width (AHW) and ventricular index (VI) were measured from cUS for preterm infants (<29 weeks) with intraventricular hemorrhage admitted from 2010-2018. PHVD was defined as AHW > 6 mm or VI >97th percentile for postmenstrual age. Individual ventricular size trajectories were plotted, and a growth mixture model (GMM) used to identify latent trajectory classes and compare these to predetermined outcome of neurosurgical intervention.
Results:
Measurements were obtained from 1543 cUS in 249 infants, of whom 39 had PHVD without and 17 PHVD with neurosurgical intervention based on signs of raised intracranial pressure. The GMM predicted trajectory identified: 93.3% of infants without PHVD, 88.2% and 30.8% of infants with PHVD with and without intervention using AHW; 100% of infants without PHVD, 52.9% and 59.0% of infants with PHVD with and without intervention using VI.
Conclusions:
The AHW GMM identified a significant proportion of infants with severe PHVD. Model refinement offers a promising approach for identifying differences in PHVD trajectory at an early stage to guide management.
Impact:
It is difficult to distinguish the trajectory of PHVD in the early stage of development, in particular PHVD that spontaneously arrests from slowly progressive PHVD which eventually requires intervention. We report the first modeling-based evaluation of PHVD trajectory for the prediction of short-term outcome of PHVD progression and neurosurgical intervention. With additional clinical validation and optimization to increase accuracy, predictive modeling has the potential to identify important differences in PHVD trajectory at an early stage in the clinical course, allowing for more individualized data-driven risk-benefit assessments to guide decisions on early intervention.
