Related Experiment Video
Updated: Dec 12, 2025
Application of an Amplitude-integrated EEG Monitor Cerebral Function Monitor to Neonates
Published on: September 6, 2017
Reliability and accuracy of EEG interpretation for estimating age in preterm infants
Nathan J Stevenson1, Maria-Luisa Tataranno2, Anna Kaminska3,4
1Brain Modelling Group, QIMR Berghofer Medical Research Institute, Brisbane, QLD, Australia.
Insights
Functional brain age (FBA) offers a more accurate measure of preterm infant maturity than visual EEG/aEEG assessments. FBA shows stable trajectories and potential as an early outcome biomarker, unlike expert estimates prone to errors.
Area of Science:
- Neonatal Neurology
- Computational Neuroscience
- Biomarkers
Background:
- Assessing neurodevelopmental maturity in preterm infants is crucial for clinical management.
- Electroencephalography (EEG) and amplitude-integrated EEG (aEEG) are used for visual maturity estimation.
- Limitations exist in the accuracy and inter-reader variability of visual assessments.
Purpose of the Study:
- To compare the accuracy of visual EEG/aEEG maturity estimation with a novel computational Functional Brain Age (FBA) measure.
- To evaluate inter-reader agreement among experts assessing postmenstrual age (PMA) from EEG/aEEG.
- To explore the potential of FBA as a biomarker for early neurodevelopmental outcomes.
Main Methods:
- Seven experts visually estimated postmenstrual age (PMA) from preterm infant EEG/aEEG recordings.
- A machine learning algorithm calculated Functional Brain Age (FBA) for comparison.
- Intraclass correlation (ICC) assessed inter-reader agreement; error analysis compared accuracy.
Main Results:
- Moderate agreement was found among human experts (aEEG ICC=0.724, EEG ICC=0.517).
- The computational FBA estimate demonstrated significantly lower random and systematic errors compared to visual PMA interpretation.
- FBA showed stable maturation trajectories, while expert estimates were more susceptible to random errors; visual assessment accuracy was compromised by neurodevelopmental outcome.
Conclusions:
- Visual assessment of infant maturity from EEG/aEEG is feasible, with expert averages yielding higher accuracy.
- Tracking individual infant maturation is hindered by errors in expert PMA estimates.
- Functional Brain Age (FBA) provides a more accurate maturity assessment and shows promise as an early outcome biomarker.
Objectives:
To determine the accuracy of, and agreement among, EEG and aEEG readers' estimation of maturity and a novel computational measure of functional brain age (FBA) in preterm infants.
Methods:
Seven experts estimated the postmenstrual ages (PMA) in a cohort of recordings from preterm infants using cloud-based review software. The FBA was calculated using a machine learning-based algorithm. Error analysis was used to determine the accuracy of PMA assessments and intraclass correlation (ICC) was used to assess agreement between experts.
Results:
EEG recordings from a PMA range 25 to 38 weeks were successfully interpreted. In 179 recordings from 62 infants interpreted by all human readers, there was moderate agreement between experts (aEEG ICC = 0.724; 95%CI:0.658-0.781 and EEG ICC = 0.517; 95%CI:0.311-0.664). In 149 recordings from 61 infants interpreted by all human readers and the FBA algorithm, random and systematic errors in visual interpretation of PMA were significantly higher than the computational FBA estimate. Tracking of maturation in individual infants showed stable FBA trajectories, but the trajectories of the experts' PMA estimate were more likely to be obscured by random errors. The accuracy of visual interpretation of PMA estimation was compromised by neurodevelopmental outcome for both aEEG and EEG review.
Interpretation:
Visual assessment of infant maturity is possible from the EEG or aEEG, with an average of human experts providing the highest accuracy. Tracking PMA of individual infants was hampered by errors in experts' estimates. FBA provided the most accurate maturity assessment and has potential as a biomarker of early outcome.
