An interesting piece of work on the diagnosis of autism has recently been published in the scientific journal PLOS Computational Biology. The authors work at the Rensselaer Polytechnic Institute in New York.
Autistic patients have limited social interaction skills and show restricted repetitive behaviors. Although important progress has been made in recent years to understand the underlying pathophysiology of this disorder, its causes remain largely unknown. This lack of biological knowledge restricts diagnoses to be made based on behavioral observations and psychometric tools.
This study tackles a new approach that uses biochemical measures taken from blood samples in the diagnosis of the disorder. The idea behind this method is that certain metabolic pathways are frequently altered in autism. The authors have developed an algorithm that combines data from a number of blood metabolites and is able to predict the outcome of the disorder with high accuracy at least in a subset of the cases. The authors, who are system biologists, have used big data analytical tools. According to one of them, Juergen Hahn, “instead of looking at individual metabolites, we investigated patterns of several metabolites and found significant differences between metabolites of children with ASD and those that are neurotypical“. And he added that “by measuring 24 metabolites from a blood sample, this algorithm can tell whether or not an individual is on the Autism spectrum, and even to some degree where on the spectrum they land.”
The model developed by this team seem to have much stronger predictability than any existing approaches from the scientific literature and paves the way towards a diagnosis based on biomarkers for the first time.
More information can be found at http://dx.doi.org/10.1371/journal.pcbi.1005385