A new study published at Science Translational Medicine AAAS shows that break-through AI could assess the risk of autism in 6-month-old infants using functional neuroimaging techniques.
Social deficiencies and repetitive behaviors usually show itself before the age of 2 and it is extremely important to identify early signs of autism spectrum disorder and develop effective treatments that could potentially improve the health of the child in the long-term.
26 scientists in different fields from 9 Universities trained an artificial intelligence using prospective imaging of 59 6-month-old infants with a high familial risk to autism spectrum disorder with the aim of accurately identifying which children would get a research clinical best-estimate diagnosis of ASD.
Study revealed that using functional connectivity magnetic resonance imaging, functioning neurons in the 6-month-old infant’s brain could be correlated with a 24-month child’s scores who has ASD and compare the scores of social behavior, language, motor development, and repetitive behavior, which are all early signs of autism spectrum disorder.
A highly trained and cross validated AI was successfully and clinically be able to identify high autism risk with a 96% accuracy, with a confidence level of 95%.