Researchers have used machine learning to identify patterns of maternal autoantibodies associated with autism, predicting a type of autism in offspring with 100% accuracy.
The team at the UC Davis MIND Institute have identified several patterns of maternal autoantibodies highly associated with the diagnosis and severity of autism. The team specifically focused on maternal autoantibody-related autism spectrum disorder (MAR ASD), a condition accounting for around 20% of all autism cases.
Autoantibodies are immune proteins that attack a person’s own tissues. Previously, the study’s lead author Judy Van de Water, found that a pregnant mother’s autoantibodies can react with her growing foetus’ brain and alter its development.
Using machine learning
Using plasma samples from mothers enrolled in the CHARGE study, the researchers analysed the samples from 450 mothers of children with autism and 342 mothers of typically developing children, to detect reactivity to eight different proteins that are abundant in the foetal brain.
The team then used a machine learning algorithm to determine which autoantibody patterns were specifically associated with a diagnosis of ASD, creating and validating a test to identify ASD-specific maternal autoantibody patterns of reactivity against eight proteins highly expressed in the developing brain. The algorithm crunched roughly 10,000 patterns and identified three top patterns associated with MAR ASD: CRMP1+GDA, CRMP1+CRMP2 and NSE+STIP1. Researchers also found that reactivity to CRMP1 in any of the top patterns significantly increases the odds of a child having more severe autism.
Judy Van de Water, a professor of rheumatology, allergy and clinical immunology at UC Davis and the lead author of the study, said: “The implications from this study are tremendous. It’s the first time that machine learning has been used to identify with 100% accuracy MAR ASD-specific patterns as potential biomarkers of ASD risk. The big deal about this particular study is that we created a new, very translatable test for future clinical use.
“For example, if the mother has autoantibodies to CRIMP1 and GDA (the most common pattern), her odds of having a child with autism is 31 times greater than the general population, based on this current dataset. That’s huge. There’s very little out there that is going to give you that type of risk assessment.”
The future of autism diagnosis
The maternal blood test uses an ELISA (Enzyme-Linked-ImmunoSorbent Assay) platform and, according to the researchers, these maternal biomarkers open possibilities for very early diagnosis of MAR autism and more effective behavioural intervention.
“We can envision that a woman could have a blood test for these antibodies prior to getting pregnant. If she had them, she’d know she would be at very high risk of having a child with autism. If not, she has a 43% lower chance of having a child with autism as MAR autism is ruled out,” Van de Water said.
Van de Water is currently researching the pathologic effects of maternal autoantibodies using animal models. “We will also use these animal models to develop therapeutic strategies to block the maternal autoantibodies from the foetus,” she said.
“This study is a big deal in terms of early risk assessment for autism, and we’re hoping that this technology will become something that will be clinically useful in the future.”