Successful blood test for autism

Posted Jul 10, 2018 by Tim Sandle
Researchers have declared success with a blood test for autism. This is the first physiological test for autism, and the results indicate that the test proves a high level of accuracy following its second trial.
Lee's autism may act as an advantage in golf competitions  when pressure can adversely affect p...
Lee's autism may act as an advantage in golf competitions, when pressure can adversely affect performance
The results of the second trial come one year after researchers published the initial findings into their physiological test for autism. The second study confirms the initial findings: that the test can accurately assess whether a child is on the autism spectrum.
Autism is a developmental disorder characterized by issues with social interaction. Issues are also manifest with communication and exhibited through repetitive behavior. Indications that a child is on the autism spectrum tend to come from parental observations. Here signs are noticed during the first two or three years of their child's life.
Autism spectrum disorder is the term for a set of similar conditions, such as Asperger syndrome, which affect, in different ways, a person's social interaction, communication, interests and behavior.
The new research is based on screening of blood samples for patterns in metabolites relevant to two connected cellular pathways (a series of interactions between molecules that control cell function) with suspected links to autism spectrum disorder. The analysis is based on big data techniques, using advanced computers.
The research also involved the use of a specially developed algorithm. By screening those already diagnosed with autism, the algorithm was able to learn and improve in its ability to detect children with autism ahead of observed behaviors appearing.
The new test comes from Rensselaer Polytechnic Institute. Summarizing the test outcomes, lead researcher Professor Juergen Hahn explains: “We looked at groups of children with ASD independent from our previous study and had similar success. We are able to predict with 88 percent accuracy whether children have autism.”
Given slow progress in areas with other similar attempts at developing a test, Professor Hahn adds: “This is extremely promising.”
The research is published in the journal Bioengineering & Translational Medicine. The research is titled “Multivariate techniques enable a biochemical classification of children with autism spectrum disorder versus typically-developing peers: A comparison and validation study.”