Fifteen-minute consultation: Therapeutic hypothermia for infants with hypoxic ischaemic encephalopathy-translating jargon, prognosis and uncertainty for parents

Rule-based deep learning method for prognosis of neonatal hypoxic-ischemic encephalopathy by using susceptibility weighted image analysis

OBJECTIVE

Susceptibility weighted imaging (SWI) of neonatal hypoxic-ischemic brain injury can provide assistance in the prognosis of neonatal hypoxic-ischemic encephalopathy (HIE). We propose a convolutional neural network model to classify SWI images with HIE.

MATERIALS AND METHODS

Due to the lack of a large dataset, transfer learning method with fine-tuning a pre-trained ResNet 50 is introduced. We randomly select 11 datasets from patients with normal neurology outcomes (n = 31) and patients with abnormal neurology outcomes (n = 11) at 24 months of age to avoid bias in classification due to any imbalance in the data.

RESULTS

We develop a rule-based system to improve the classification performance, with an accuracy of 0.93 ± 0.09. We also compute heatmaps produced by the Grad-CAM technique to analyze which areas of SWI images contributed more to the classification patients with abnormal neurology outcome.

CONCLUSION

Such regions that are important in the classification accuracy can interpret the relationship between the brain regions affected by hypoxic-ischemic and neurodevelopmental outcomes of infants with HIE at the age of 2 years.

Neuroimaging to guide neuroprognostication in the neonatal intensive care unit

PURPOSE OF REVIEW

Neurological problems are common in infants admitted to the neonatal intensive care unit (NICU). Various neuroimaging modalities are available for neonatal brain imaging and are selected based on presenting problem, timing and patient stability.

RECENT FINDINGS

Neuroimaging findings, taken together with clinical factors and serial neurological examination can be used to predict future neurodevelopmental outcomes. In this narrative review, we discuss neonatal neuroimaging modalities, and how these can be optimally utilized to assess infants in the NICU. We will review common patterns of brain injury and neurodevelopmental outcomes in hypoxic-ischemic encephalopathy, perinatal arterial ischemic stroke and preterm brain injury.

SUMMARY

Timely and accurate neuroprognostication can identify infants at risk for neurodevelopmental impairment and allow for early intervention and targeted therapies to improve outcomes.

Neonatal Hypoxic-Ischemic Encephalopathy Spectrum: Severity-Stratified Analysis of Neuroimaging Modalities and Association with Neurodevelopmental Outcomes

OBJECTIVE

To compare hypoxic-ischemic injury on early cranial ultrasonography (cUS) and post-rewarming brain magnetic resonance imaging (MRI) in newborn infants with hypoxic-ischemic encephalopathy (HIE) and to correlate that neuroimaging with neurodevelopmental outcomes.

STUDY DESIGN

This was a retrospective cohort study of infants with mild, moderate, and severe HIE treated with therapeutic hypothermia and evaluated with early cUS and postrewarming MRI. Validated scoring systems were used to compare the severity of brain injury on cUS and MRI. Neurodevelopmental outcomes were assessed at 18 months of age.

RESULTS

Among the 149 included infants, abnormal white matter (WM) and deep gray matter (DGM) hyperechogenicity on cUS in the first 48 hours after birth were more common in the severe HIE group than the mild HIE group (81% vs 39% and 50% vs 0%, respectively; P < .001). In infants with a normal cUS, 95% had normal or mildly abnormal brain MRIs. In infants with severely abnormal cUS, none had normal and 83% had severely abnormal brain MRIs. Total abnormality scores on cUS were higher in neonates with near-total brain injury on MRI than in neonates with normal MRI or WM-predominant injury pattern (adjusted P < .001 for both). In the multivariable model, a severely abnormal MRI was the only independent risk factor for adverse outcomes (OR: 19.9, 95% CI: 4.0-98.1; P < .001).

CONCLUSION

The present study shows the complementary utility of cUS in the first 48 hours after birth as a predictive tool for the presence of hypoxic-ischemic injury on brain MRI.

Mild Hypoxic-Ischemic Encephalopathy: Can Neurophysiological Monitoring Predict Unfavorable Neurological Outcome? A Systematic Review and Meta-analysis

OBJECTIVE

 Hypoxic-ischemic encephalopathy (HIE) is the second cause of neonatal deaths and one of the main conditions responsible for long-term neurological disability. Contrary to past belief, children with mild HIE can also experience long-term neurological sequelae. The aim of this systematic review is to determine the predictive value of long-term neurological outcome of (electroencephalogram) EEG/amplitude-integrated electroencephalogram (aEEG) in children who complained mild HIE.

STUDY DESIGN

 From a first search on PubMed, Google Scholar, and clinicalTrials.gov databases, only five articles were considered suitable for this study review. A statistical meta-analysis with the evaluation of odds ratio was performed on three of these studies.

RESULTS

 No correlation was found between the characteristics of the electrical activity of the brain obtained through EEG/aEEG in infants with mild HIE and subsequent neurological involvement.

CONCLUSION

 EEG/aEEG monitoring in infants with mild HIE cannot be considered a useful tool in predicting their neurodevelopmental outcome, and its use for this purpose is reported as barely reliable.

KEY POINTS

· Hypoxic-Ischemic Encephalopathy is responsible for long-term neurological outcome, even in newborns with mild HIE.. · No correlation was found between EEG/aEEG trace in infants with mild HIE and neurological sequelae.. · Neurophysiological monitoring, in mild HIE, cannot predic neurodevelopmental outcome..