A unifying Bayesian approach for preterm brain-age prediction that models EEG sleep transitions over age
This addresses the challenge of early identification of learning problems in preterm infants by providing a more consistent and accurate brain-age prediction method, though it is incremental as it builds on existing EEG-based approaches.
The paper tackles the problem of predicting brain-age in preterm newborns from EEG sleep data to detect developmental deviations, introducing a Bayesian Network with Gaussian Mixture Models that directly estimates brain-age while modeling age and sleep dependencies, improving accuracy over a wider age range.
Preterm newborns undergo various stresses that may materialize as learning problems at school-age. Sleep staging of the Electroencephalogram (EEG), followed by prediction of their brain-age from these sleep states can quantify deviations from normal brain development early (when compared to the known age). Current automation of this approach relies on explicit sleep state classification, optimizing algorithms using clinician visually labelled sleep stages, which remains a subjective gold-standard. Such models fail to perform consistently over a wide age range and impacts the subsequent brain-age estimates that could prevent identification of subtler developmental deviations. We introduce a Bayesian Network utilizing multiple Gaussian Mixture Models, as a novel, unified approach for directly estimating brain-age, simultaneously modelling for both age and sleep dependencies on the EEG, to improve the accuracy of prediction over a wider age range.