Researchers analyzed a cohort of preterm infants (born before 28 weeks of gestation) at the Wilhelmina Children’s Hospital in the Netherlands, focusing on predicting neurodevelopmental outcomes using early postnatal amplitude-integrated electroencephalogram (aEEG) and raw EEG features.
The study analyzed data from 339 infants, including nine qualitative parameters and 330 quantitative metrics, and employed machine learning models to predict cognitive, motor, and behavioral outcomes at ages 2-3 and 5-7 years.
Results showed that classification models effectively identified infants with intellectual impairments at age 5-7 years, with balanced accuracies of 0.77 for full-scale and 0.81 for verbal IQ scores.
These findings suggest the potential of early postnatal aEEG–EEG features in automatically recognizing highly preterm infants at risk of poor outcomes, aiding in decision-making and therapy planning.
Ref: Wang X, Trabatti C, Weeke L, et al. Early qualitative and quantitative amplitude-integrated electroencephalogram and raw electroencephalogram for predicting long-term neurodevelopmental outcomes in extremely preterm infants in the Netherlands: a 10-year cohort study. Lancet Digit Health. 2023;5(12):e895-e904. doi:10.1016/S2589-7500(23)00198-X
You must be logged in to post a comment.