Related Experiment Video
Updated: Jun 10, 2025
Modeling Neonatal Intraventricular Hemorrhage Through Intraventricular Injection of Hemoglobin
Published on: August 25, 2022
Predicting Outcomes of Preterm Neonates Post Intraventricular Hemorrhage
Gabriel A Vignolle1, Priska Bauerstätter1, Silvia Schönthaler1
1Center for Health & Bioresources, Competence Unit Molecular Diagnostics, AIT Austrian Institute of Technology GmbH, 1210 Vienna, Austria.
Insights
This study uses explainable machine learning and proteomics to predict posthemorrhagic ventricular dilatation (PHVD) in preterm neonates with intraventricular hemorrhage (IVH). It identified 41 protein markers and gestational age as predictors, aiding early detection and parental counseling.
Area of Science:
- Neonatal Medicine
- Biomarker Discovery
- Machine Learning in Healthcare
Background:
- Intraventricular hemorrhage (IVH) in preterm neonates often leads to posthemorrhagic ventricular dilatation (PHVD), a serious complication impacting survival and long-term neurological outcomes.
- Early PHVD detection is critical for timely intervention and informed parental counseling.
- Current prediction methods for PHVD in preterm infants are limited, necessitating novel approaches.
Purpose of the Study:
- To investigate the efficacy of explainable machine learning (ML) models utilizing targeted liquid biopsy proteomics data for predicting PHVD development and survival in preterm neonates with IVH.
- To identify novel and known protein biomarkers associated with PHVD and survival.
- To enhance clinical decision-making and parental counseling through reliable predictive tools.
Main Methods:
- Prospective longitudinal cohort study analyzing 1109 liquid biopsy samples from 99 preterm neonates with IVH over 13 years.
- Application of diverse explainable ML techniques (statistical, regularization, deep learning, decision trees, Bayesian) to predict PHVD and survival.
- Targeted proteomic analysis of serum and urine samples using proximity extension assay to detect low-concentration proteins.
Main Results:
- Identified 41 significant independent protein markers and gestational age at birth as predictors of PHVD development and survival, surpassing rigorous performance thresholds (AUC-ROC ≥0.7, sensitivity ≥0.6, selectivity ≥0.6).
- Discovered both established biomarkers, such as neurofilament light chain (NEFL), and novel protein markers.
- Developed over 1600 ML models, demonstrating the potential of proteomics and ML in neonatal outcome prediction.
Conclusions:
- Targeted proteomics combined with explainable ML offers a promising avenue for early prediction of PHVD and survival in preterm neonates with IVH.
- The identified protein markers and ML models can potentially improve clinical decision-making and parental support.
- Further validation studies are necessary to translate these findings into routine clinical practice.
Abstract:
Intraventricular hemorrhage (IVH) in preterm neonates presents a high risk for developing posthemorrhagic ventricular dilatation (PHVD), a severe complication that can impact survival and long-term outcomes. Early detection of PHVD before clinical onset is crucial for optimizing therapeutic interventions and providing accurate parental counseling. This study explores the potential of explainable machine learning models based on targeted liquid biopsy proteomics data to predict outcomes in preterm neonates with IVH. In recent years, research has focused on leveraging advanced proteomic technologies and machine learning to improve prediction of neonatal complications, particularly in relation to neurological outcomes. Machine learning (ML) approaches, combined with proteomics, offer a powerful tool to identify biomarkers and predict patient-specific risks. However, challenges remain in integrating large-scale, multiomic datasets and translating these findings into actionable clinical tools. Identifying reliable, disease-specific biomarkers and developing explainable ML models that clinicians can trust and understand are key barriers to widespread clinical adoption. In this prospective longitudinal cohort study, we analyzed 1109 liquid biopsy samples from 99 preterm neonates with IVH, collected at up to six timepoints over 13 years. Various explainable ML techniques-including statistical, regularization, deep learning, decision trees, and Bayesian methods-were employed to predict PHVD development and survival and to discover disease-specific protein biomarkers. Targeted proteomic analyses were conducted using serum and urine samples through a proximity extension assay capable of detecting low-concentration proteins in complex biofluids. The study identified 41 significant independent protein markers in the 1600 calculated ML models that surpassed our rigorous threshold (AUC-ROC of ≥0.7, sensitivity ≥ 0.6, and selectivity ≥ 0.6), alongside gestational age at birth, as predictive of PHVD development and survival. Both known biomarkers, such as neurofilament light chain (NEFL), and novel biomarkers were revealed. These findings underscore the potential of targeted proteomics combined with ML to enhance clinical decision-making and parental counseling, though further validation is required before clinical implementation.
