Test may detect autism before age 1

VIDEO: Link between vaccines, autism discredited

BOSTON, Feb. 23 (UPI) -- U.S. researchers have developed a test that uses standard electroencephalogram to detect autism with machine-learning algorithms.

William Bosl and Charles A. Nelson, both at Children's Hospital Boston, say in their pilot study, their system had 80 percent accuracy in distinguishing between 9-month-old infants known to be at high risk for autism from controls of the same age.

The early test would allow parents to begin behavioral interventions one to two years before autism can be diagnosed through traditional behavioral testing, the researchers say.

"Electrical activity produced by the brain has a lot more information than we realized," Bosl says in a statement. "Computer algorithms can pick out patterns in those squiggly lines that the eye can't see."

The babies watched a research assistant blowing bubbles, while recordings were made via a hairnet-like cap on their scalps studded with 64 electrodes and when possible, tests were repeated at 6, 9, 12, 18 and 24 months of age.

"Many neuroscientists believe that autism reflects a 'disconnection syndrome,' by which distributed populations of neurons fail to communicate efficiently with one another," Nelson says. "The current paper supports this hypothesis by suggesting that the brains of infants at high risk for developing autism exhibit different patterns of neural connectivity."

The work requires validation and refinement, the researchers add.

The findings are published online in BMC Medicine.