machine learning – ASF Weekly Science Podcasts

Last week in North Carolina, the Meeting on Language in Autism was held, with 3 days of amazing presentations and lots of productive discussions about how language and speech develops and how people with autism communicate. This podcast describes the origins of language development and how intervention during toddlerhood can promote lifelong language abilities. To learn more about the meeting go to www.mola.org and to see the Autism Navigator, go to www.autismnavigator.org.

The media has just called another biological marker a “diagnostic test”, when in this case, it was always intended to be an aid, not a test itself. It involves using baby hair strands to look a variation in metabolism of certain chemical elements across time. Remarkably, it showed similar results in autistic children in Japan, the US and Sweden. It’s not ready to be used as a diagnostic test, so what is it supposed to do? Listen to an interview with the inventor and researcher, Dr. Manish Arora from The Icahn School of Medicine at Mt. Sinai School here.

The full article (open access) can be found here: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9740182/

At this year’s International Society of Autism Research meeting in Austin, TX, there was a variety of themes explored. From early development and milestones, to intervention and supports, to different features like sensory issues, treatment, and how to solve the problem of heterogeneity. It comes down to this: Autism means different things to different people. This is just a small subset of everything that was presented at #INSAR2022 and I hope that if you want to see more, you advocate to have the presentations posted online or even have the program book made available publicly. In the meantime, enjoy the 30 minute summary.

www.autism-insar.org

This week’s podcast focuses on innovative methodologies to understand how to reach black families, understand why and when autistic people prefer not to look at faces and how interventions can improve conversation and social communication. They use culturally and racially matched mentors, old home video tapes (keep taking those!) and machine learning to look not just at novel methods but novel ways of studying a particular outcome.

https://pubmed.ncbi.nlm.nih.gov/35232271/

https://pubmed.ncbi.nlm.nih.gov/35228613/

https://pubmed.ncbi.nlm.nih.gov/35229983/