Automatic burst detection for the EEG of the preterm infant
Related Experiment Video
Updated: May 29, 2026
Application of an Amplitude-integrated EEG Monitor (Cerebral Function Monitor) to Neonates
Published on: September 6, 2017
Ward Jennekens1, Loes S Ruijs, Charlotte M L Lommen
1Department of Clinical Physics, Máxima Medical Centre, Veldhoven, The Netherlands.
Insights
An automated electroencephalogram (EEG) analysis method accurately detects patterns in preterm infants, aiding clinical treatment and prognosis. This computer-assisted tool offers objective and reproducible analysis for neonatal care.
Area of Science:
- Neonatal Neurology
- Computational Neuroscience
- Medical Signal Processing
Background:
- Accurate electroencephalogram (EEG) analysis is crucial for predicting outcomes and guiding treatment in preterm infants.
- Current EEG interpretation can be subjective, necessitating objective and reproducible methods.
Purpose of the Study:
- To develop and evaluate an automated algorithm for detecting bursts, interburst-intervals (IBIs), and continuous patterns in preterm infant EEG.
- To assess the algorithm's performance using sensitivity and positive predictive values against expert annotations.
Main Methods:
- A MATLAB-based algorithm was developed, utilizing amplitude, time span, channel count, and active electrode number for pattern detection.
- Threshold values were determined using annotations from two neurophysiologists on EEG recordings from preterm infants (PMA 29-34 weeks).
- Algorithm performance was validated on an independent dataset, calculating sensitivity and positive predictive values.
Main Results:
- The algorithm achieved high sensitivity: 90% ± 6% for bursts, 80% ± 9% for IBIs, and 97% ± 5% for continuous patterns.
- Positive predictive values were also strong: 88% ± 8% for bursts, 96% ± 3% for IBIs, and 85% ± 15% for continuous patterns.
- The algorithm demonstrated excellent performance in identifying key EEG patterns in preterm neonates.
Conclusions:
- The developed automated EEG analysis algorithm exhibits high sensitivity and positive predictive values for bursts, IBIs, and continuous patterns in preterm infants.
- Computer-assisted EEG analysis offers a promising approach for objective and reproducible assessment in clinical neonatal care.
- This technology can aid in the prognosis and stratification of clinical treatment for preterm infants.
Abstract:
To aid with prognosis and stratification of clinical treatment for preterm infants, a method for automated detection of bursts, interburst-intervals (IBIs) and continuous patterns in the electroencephalogram (EEG) is developed. Results are evaluated for preterm infants with normal neurological follow-up at 2 years. The detection algorithm (MATLAB®) for burst, IBI and continuous pattern is based on selection by amplitude, time span, number of channels and numbers of active electrodes. Annotations of two neurophysiologists were used to determine threshold values. The training set consisted of EEG recordings of four preterm infants with postmenstrual age (PMA, gestational age + postnatal age) of 29-34 weeks. Optimal threshold values were based on overall highest sensitivity. For evaluation, both observers verified detections in an independent dataset of four EEG recordings with comparable PMA. Algorithm performance was assessed by calculation of sensitivity and positive predictive value. The results of algorithm evaluation are as follows: sensitivity values of 90% ± 6%, 80% ± 9% and 97% ± 5% for burst, IBI and continuous patterns, respectively. Corresponding positive predictive values were 88% ± 8%, 96% ± 3% and 85% ± 15%, respectively. In conclusion, the algorithm showed high sensitivity and positive predictive values for bursts, IBIs and continuous patterns in preterm EEG. Computer-assisted analysis of EEG may allow objective and reproducible analysis for clinical treatment.
