Scientists say they can predict with near perfect accuracy whether or not a child has autism from a blood sample.

Using an algorithm to assess metabolites in blood, researchers were able to identify samples that came from kids with autism in 97.6 percent of cases.

The findings published Thursday in the journal PLOS Computational Biology open the door to a possible biomarker for autism.

“The method presented in this work is the only one of its kind that can classify an individual as being on the autism spectrum or as being neurotypical,” said Juergen Hahn of the Rensselaer Polytechnic Institute in Troy, N.Y. and the lead author of the study. “We are not aware of any other method, using any type of biomarker that can do this, much less with the degree of accuracy that we see in our work.”

The study involved blood samples collected from 83 children with autism and 76 neurotypical children ages 3 to 10 at Arkansas Children’s Hospital. Rather than examining one particular gene or a single biomarker, researchers used big data techniques to take a broader look in order to find statistically significant patterns.

In kids with autism, substances produced by what are known as folate-dependent one-carbon metabolism and transulfuration pathways were altered, according to the findings.

“Instead of looking at individual metabolites, we investigated patterns of several metabolites and found significant differences between metabolites of children with ASD and those that are neurotypical. These differences allow us to categorize whether an individual is on the autism spectrum,” Hahn said. “By measuring 24 metabolites from a blood sample, this algorithm can tell whether or not an individual is on the autism spectrum, and even to some degree where on the spectrum they land.”

Hahn said that he’s looking to replicate the results, but indicated the findings could point to new ways to diagnose autism or potential treatments for the developmental disorder.