Study combines neuroimaging with machine learning to predict, with 96% accuracy, whether high-risk 6-month-old babies will develop autism spectrum disorder (ASD) by age 2

Researchers use brain imaging and machine learning to predict which high-risk infants will develop autism. Credit: Carolina Institute for Developmental Disabilities. — A Single Brain Scan Has Been Used to Accurately Predict Autism at Just 6 Months Old (Science alert) “Researchers have used brain scans and artificial intelligence to spot differences in how key areas of infant brains synchronise, allowing them to accurately predict which babies would develop autism spectrum disorder (ASD) as a toddler…The research, led by scientists from the University of Carolina and Washington University, comes hot on the heels of an earlier study that used two scans taken at 6 and 12 months to make a similar prediction. Not only has this new method reduced the number of scans required to make the judgement, they were able to predict with more than 96 percent accuracy which 6 month old infants would be diagnosed with autism by age 2, compared to 81 percent previously…The researchers used magnetic resonance imaging to analyse the neural activity of 230 regions across the brain in 59 infants who had at least one older sibling with a diagnosis of ASD… A larger sample size and more data will no doubt help determine just how accurate this method of diagnosis could be in the long term, which is what the researchers are planning next. It’s also unlikely that a single test will form the basis of any future diagnoses – more likely, it would form one piece in a risk profile informed by re...
Source: SharpBrains - Category: Neuroscience Authors: Tags: Cognitive Neuroscience Education & Lifelong Learning Health & Wellness Technology artificial intelligence ASD autism autism diagnosis autism spectrum disorder brain-function brain-scans high-risk machine-learning magnetic resonan Source Type: blogs