How machine learning led to a new discovery of blood biomarkers for autism diagnosis
A published article in the journal PLOS One led researchers at UT Southwestern Medical Center to the identification of biomarkers in the blood that may result in a quicker diagnosis of autism spectrum disorder (ASD) among children.
During their study, researchers uncovered nine serum proteins with the ability to predict the onset of autism.
“Serum samples from 76 boys with ASD and 78 typically developing (TD) boys, 18 months-8 years of age, were analyzed to identify possible early biological markers for ASD,” said Laura Hewitson, and her colleagues, in their findings.
“Proteomic analysis of serum was performed using SomaLogic’s SOMAScanTM assay 1.3K platform. A total of 1,125 proteins were analyzed. There were 86 downregulated proteins and 52 upregulated proteins in ASD.”
Using a form of artificial intelligence, known as machine learning, nine proteins were established to be significantly correlated with autism.
“Using machine learning methods, a panel of serum proteins was identified that may be useful as a blood biomarker for ASD in boys. Further verification of the protein biomarker panel with independent test sets is warranted,” concluded Hewitson in the study.
Other authors of the findings include Jeremy Mathews, Morgan Devlin, Claire Schutte, Jeon Lee, and Dwight German.