Inexpensive EEGs, which measure brain activity, can either predict or rule out autism in infants as young as three months of age, says a new study from Boston Children's Hospital.

Autism Spectrum Disorder (ASD) is comprised of a wide range of problems, including difficulty in communicating, a lack of social skills, and repetitive behaviors.

"EEGs are low-cost, non-invasive and relatively easy to incorporate into well-baby checkups," says the study's co-author Charles Nelson, Ph.D. "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."

For the new study, researchers analyzed data from the Infant Sibling Project (now called the Infant Screening Project), a collaboration between Boston Children's Hospital and Boston University. The project attempts to map early development and identify infants at risk for developing ASD and/or language and communication difficulties.

William Bosl, Ph.D.has been working for more than a decade developing algorithms to interpret EEG signals. His research suggests that even an EEG that appears normal contains "deep" data that reflect brain function, connectivity patterns, and structure that can be found only with computer algorithms.

Bosl used EEG data from 99 infants considered at high risk for ASD because they had an older sibling who had been diagnosed with ASD, and 89 low-risk controls who didn't have an affected sibling.

EEGs were taken at 3, 6, 9, 12, 18, 24 and 36 months of age by fitting a net over the babies' scalps with 128 sensors as the babies sat in their mothers' laps. In addition, all of the babies also underwent extensive behavioral evaluations with the Autism Diagnostic Observation Schedule (ADOS), an established clinical diagnostic tool.

Bosl's algorithms analyzed six different frequencies of the EEG that can reflect differences in how the brain is wired, and how it processes and integrates information.

The algorithms predicted a clinical diagnosis of ASD that exceeded 95 percent at some ages.  

"The results were stunning," he says. Although autism could be predicted in some children as young as three months, "Our predictive accuracy by nine months of age was nearly 100 percent."

Autism experts believe that the earlier a child can be diagnosed, the earlier effective steps can be taken to deal with the condition to provide better outcomes.

According to the Centers for Disease Control and Prevention, one child in 68 had autism in 2010, a 119.4 percent increase from 2000.