Using MRI and Machine Learning to Predict Cognitive Abilities in Infants

Magnetic Resonance Imaging (MRI) can now be used in conjunction with machine learning to predict cognitive development in infants, according to a study recently published in NeuroImage.

White matter is intrinsic to developing brain activity, and the white matter connectome at birth can be used as a neuroimaging biomarker to calculate cognitive development. The group of researchers led by Jessica B. Girault, PhD, from the Carolina Institute for Developmental Disabilities at the University of North Carolina Chapel Hill are searching for imaging biomarkers like white matter to determine risks for neuropsychiatric conditions, like autism and schizophrenia.

In their study, they used a deep learning model to examine white matter in a group of infants who had a median age of two. They found that white matter connectomes at birth had a 95 percent accuracy rate at determining cognitive development. They focused on the connections in the frontal lobe and areas between the frontal lobe for brain activity classification.

“This prediction could help identify children at risk for poor cognitive development shortly after birth with high accuracy,” said senior author John H. Gilmore, MD. “For these children, an early intervention in the first year or so of life – when cognitive development is happening – could help improve outcomes. For example, in premature infants who are at risk, one could use imaging to see who could have problems.”