New research suggests that a simple, inexpensive test may be able to accurately identify whether or not children as young as 3 months will go on to have autism. A study published online this week in the journal Scientific Reports found that the developmental disorder can be flagged in infants by measuring electrical activity in the brain using an electroencephalogram, or EEG.

The test was able to pick up on autism in some babies by 3 months and had near-perfect accuracy by 9 months. EEGs are low-cost, non-invasive and relatively easy to incorporate into well-baby checkups. Their reliability in predicting whether a child will develop autism raises the possibility of intervening very early, well before clear behavioral symptoms emerge. This could lead to better outcomes and perhaps even prevent some of the behaviors associated with ASD.

The study looked at 99 children considered to be at high risk for autism because they had an older sibling with the condition as well as 89 low-risk kids. All of the participants had EEGs at ages 3, 6, 9, 12, 18, 24 and 36 months and they took part in a traditional behavioral evaluation for autism. Using computational algorithms, researchers assessed six different frequencies of the EEGs and were able to offer a “highly accurate” prediction of autism risk at just 3 months.