Related Experiment Video
Updated: May 2, 2026
Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
Published on: April 26, 2024
Line length as a robust method to detect high-activity events: automated burst detection in premature EEG recordings
Ninah Koolen1, Katrien Jansen2, Jan Vervisch2
1Department of Electrical Engineering (ESAT), Division SCD, KU Leuven, Leuven, Belgium; iMinds-KU Leuven Future Health Department, Leuven, Belgium.
Insights
We developed a new automated method to detect bursts in preterm EEG recordings, achieving high accuracy. This technique can improve brain maturation assessment in premature infants in the NICU.
Area of Science:
- Neonatal neurology
- Neurophysiology
- Medical instrumentation
Background:
- Electroencephalography (EEG) is crucial for assessing brain maturation in preterm infants.
- Preterm EEG displays characteristic burst activities and interburst intervals (IBIs) that evolve with development.
- Analyzing these background characteristics aids in predicting neurological outcomes.
Purpose of the Study:
- To develop an automated method for detecting burst activity in preterm EEG.
- To establish a reliable tool for objective analysis of brain maturation in neonates.
Main Methods:
- A novel burst detection algorithm was created using the line length feature.
- The algorithm was applied to 13 polysomnography recordings from preterm infants (postmenstrual age 31.4 weeks).
- Performance was evaluated against manual scoring by experts and existing methods.
Main Results:
- The line length-based algorithm demonstrated robust performance with 84.27% accuracy, 84.00% sensitivity, and 85.70% specificity.
- Accuracy remained high (82%) even with only two EEG channels.
- The algorithm accurately estimated key features like median IBI duration, maximum IBI duration, and burst percentage.
Conclusions:
- Automated analysis of long-term preterm EEG is feasible and can optimize interpretation in Neonatal Intensive Care Units (NICUs).
- This study represents a significant advancement towards fully automated preterm brain analysis.
Objective:
EEG is a valuable tool for evaluation of brain maturation in preterm babies. Preterm EEG constitutes of high voltage burst activities and more suppressed episodes, called interburst intervals (IBIs). Evolution of background characteristics provides information on brain maturation and helps in prediction of neurological outcome. The aim is to develop a method for automated burst detection.
Methods:
Thirteen polysomnography recordings were used, collected at preterm postmenstrual age of 31.4 (26.1-34.4)weeks. We developed a burst detection algorithm based on the feature line length and compared it with manual scorings of clinical experts and other published methods.
Results:
The line length-based algorithm is robust (84.27% accuracy, 84.00% sensitivity, 85.70% specificity). It is not critically dependent on the number of measurement channels, because two channels still provide 82% accuracy. Furthermore, it approximates well clinically relevant features, such as median IBI duration 5.45 (4.00-7.11)s, maximum IBI duration 14.02 (8.73-18.80)s and burst percentage 48.89 (35.45-60.12)%, with a median deviation of respectively 0.65s, 1.96s and 6.55%.
Conclusion:
Automated assessment of long-term preterm EEG is possible and its use will optimize EEG interpretation in the NICU.
Significance:
This study takes a first step towards fully automatic analysis of the preterm brain.
