Researchers at Children's Hospital Boston, US, are developing a non-invasive test which analyses the electrical activity in the brain to evaluate an infant's autism risk.
The test combines the standard electroencephalogram (EEG), which records electrical activity in the brain, and machine-learning algorithms to calculate autism risk.
In a pilot study, the new test had 80% accuracy in identifying 9-month-old infants known to be at high risk of autism from controls of the same age.
According to researchers the test will allow parents to begin behavioral interventions one to two years before autism can be diagnosed through traditional behavioral testing.