Not much I can add to the article except to note that the findings suggest a metabolic aetiology : https://gizmodo.com/researchers-say-theyve-created-a-90-accurate-blood-tes-1823087752
Just for a little balance others have expressed some scepticism : Potential blood and urine test for autism greeted with skepticism https://newatlas.com/autism-blood-urine-test-biomarkers/53457/
Here's the paper : Advanced glycation endproducts, dityrosine and arginine transporter dysfunction in autism - a source of biomarkers for clinical diagnosis https://molecularautism.biomedcentral.com/articles/10.1186/s13229-017-0183-3
Seems interesting, but I think on balance I will remain skeptical until the rest of the work is done on a larger sample size etc.