, a study from Duke University, Durham, N.C., says.
“We can use the first 30 days of a child’s health care experience to say, ‘This child is really at risk,’ ” said David Mandell, DSc, a professor of psychiatry at the University of Pennsylvania, Philadelphia, in USA Today. He was not involved in the research.
Researchers analyzed electronic medical records of 45,000 children treated in the Duke University Health System as infants between 2006 and 2020. They created an algorithm that could predict which babies later developed autism. These babies were more likely to have been to an ophthalmologist or neurologist; had stomach or gastrointestinal issues; or received physical therapy.
“A huge number of factors across the infant’s entire health profile” went into the models, said study coauthor Matthew Engelhard, MD, an assistant professor of biostatistics and bioinformatics at Duke University. “Each one of those factors contributes incrementally.”
USA Today said the team “paid particular attention to how the model performed in groups of children who are often overlooked by traditional screening methods and, therefore, miss the advantages of early diagnosis, including girls, children of color, and children with combined diagnoses of autism and ADHD,” according to Dr. Engelhard.
The study could lead to the algorithm being used with other tools to diagnose and help children earlier, said study author Geraldine Dawson, PhD, who directs the Duke Center for Autism and Brain Development.
“We need to be thinking about autism as not only a behavioral health condition but also a condition that involves physical health,” she said. “This is one way to take advantage of that information: in doing a better job at early detection.”
Autism is a complicated condition that includes communication and behavior challenges involving a range of symptoms and skills. It can be minor or a disability that requires full-time care.
A version of this article first appeared on WebMD.com.