New research points to a simple way to flag children at risk for autism that has the potential to cut the rate of false positives of traditional screening in half.

By analyzing the diagnostic codes present in a child’s existing medical records, researchers say they can reliably identify those most likely to qualify for a diagnosis on the spectrum.

“Using the information already being gathered and being able to harness it for this kind of exploration and clinical use is exciting, and it really has the potential to be a game changer,” said Dr. Peter J. Smith of the University of Chicago, an author of the study published this month in the journal Science Advances.

For the study, researchers developed a computer algorithm to assess the diagnostic codes in a child’s medical chart against comorbidities known to be associated with autism. Such codes are readily available since all doctors assign standardized codes from the International Classification of Diseases to each patient visit.

The algorithm known as the autism comorbid risk score, or ACoR, determines how likely it is that a child will receive an autism diagnosis.

The study found that ACoR was better at identifying which children were likely to have autism than the commonly used M-CHAT/F screening method. The algorithm was even more successful when used in tandem with the M-CHAT/F.

The ACoR was able to spot at-risk kids one year before their diagnosis and was consistently effective across racial and ethnic groups, the study found.

Those behind the study said that they hope the ACoR algorithm can be adopted widely to be used alongside traditional screening to limit false positives and thereby reduce wait times for children who need to see specialists.