Using Quantitative EEG to Stratify Epilepsy Risk After Neonatal Encephalopathy: A Comparison of Automatically...

Area of Science:

• Neuroscience
• Neonatal Medicine
• Epileptology

Background:

• Neonatal encephalopathy (NE) is a serious condition requiring accurate epilepsy prognostication.
• Therapeutic hypothermia (TH) is a standard treatment for NE.
• Predicting epilepsy after NE is crucial for long-term management.

Purpose of the Study:

• To evaluate automated electroencephalography (EEG) for predicting early-life epilepsy in NE infants treated with TH.
• To assess the accuracy of quantitative EEG (qEEG) features for epilepsy risk stratification.

Main Methods:

• Retrospective analysis of 144 neonates with moderate-to-severe NE undergoing TH.
• Automated artifact removal and qEEG analysis of the first 24 hours of EEG data.
• Evaluation of qEEG features at the 1st and 20th hour for epilepsy risk stratification.

Main Results:

• Of 67 eligible neonates, 23% had seizures and 9% developed epilepsy.
• Automatically extracted qEEG features predicted epilepsy risk as early as the first hour.
• Absolute spectral power in the 20th hour EEG showed high accuracy (AUC 76-83%) in stratifying epilepsy risk.
• Clinical examination was not a significant predictor of epilepsy development.

Conclusions:

• Quantitative EEG features significantly predict early-life epilepsy following NE.
• Automated qEEG offers a practical tool for improving epilepsy risk stratification in NE survivors.
• Further validation in larger cohorts is necessary to confirm the utility of automated EEG for epilepsy prediction.