By Nancy Fliesler / Boston Children’s Hospital.
The earlier autism can be diagnosed, the more effective interventions typically are. But the signs are often subtle or can be misinterpreted at young ages. As a result, many children aren’t diagnosed until age 2 or even older. Now, a study shows that electroencephalograms (EEGs), which measure the brain’s electrical activity, can accurately predict or rule out autism spectrum disorder (ASD) in babies as young as 3 months old. It appears today in Scientific Reports.
The beauty of EEG is that it’s already used in many pediatric neurology or developmental pediatric settings. “EEGs are low-cost, non-invasive and relatively easy to incorporate into well-baby checkups,” says study co-author Charles Nelson, PhD, director of the Laboratories of Cognitive Neuroscience at Boston Children’s Hospital. “Their reliability in predicting whether a child will develop autism raises the possibility of intervening very early, well before clear behavioral symptoms emerge.”
Mining “deep data” in EEG algorithms
The babies had EEGs taken at 3, 6, 9, 12, 18, 24 and 36 months of age, as part of the long-running Infant Screening Project, a collaboration between Nelson’s group and Boston University. As the babies sat in their mothers’ laps, the researchers slipped nets with 128 sensors over their scalps and blew bubbles to distract them while the EEGs were recorded. All babies also underwent extensive behavioral evaluations with the Autism Diagnostic Observation Schedule (ADOS), an established clinical diagnostic tool.
To interpret the EEG signals, Nelson tapped William Bosl, PhD, of the University of San Francisco and the Computational Health Informatics Program (CHIP) at Boston Children’s. Bosl’s research suggests that even a normal-appearing EEG contains “deep” data that reflect brain function, connectivity patterns and structure that can be found only with computer algorithms.
Predicting autism and its severity
In all, Bosl received EEG data from 99 infants considered at high risk for ASD (having an older sibling with the diagnosis) and 89 low-risk controls (without an affected sibling). His computational algorithms analyzed six components of the EEG signal (high gamma, gamma, beta, alpha, theta and delta waves), using measures of signal complexity. Bosl and Nelson believe these measures, which draw upon multiple aspects of brain activity, reflect differences in how the brain is wired and how it processes and integrates information.
Overall, the algorithms predicted a clinical diagnosis of ASD with high specificity, sensitivity and positive predictive value, exceeding 95 percent at some ages.
“The results were stunning,” Bosl says. “Our predictive accuracy by 9 months of age was nearly 100 percent. We were also able to predict ASD severity, as indicated by the ADOS Calibrated Severity Score, with quite high reliability, also by 9 months of age.” (Below, predicted ADOS severity scores for individual babies.)
Bosl believes that the early differences in signal complexity fit with the view that autism begins during the brain’s early development but can take different trajectories. In other words, an early predisposition to autism may be influenced by other factors along the way.
“We believe that infants who have an older sibling with autism may carry a genetic liability for developing autism,” he says. “This increased risk, perhaps interacting with another genetic or environmental factor, leads some infants to develop autism — although clearly not all, since we know that four of five ‘infant sibs’ do not develop autism.”
Helen Tager-Flusberg, PhD, of Boston University was the third co-author on the paper. The study was supported by National Institute of Mental Health, the National Institute on Deafness and Other Communication Disorders and the Simons Foundation.
Source: Boston Children’s Hospital.