Posted on

Machine Learning in Autism, Explained

Podcast: Play in new window | Download

Subscribe: RSS

Thank you to Dennis Wall from Stanford University for explaining what Machine Learning is, how it’s related to Artificial Intelligence (today’s four buzz words) and how these new technologies are helping families get a diagnosis. He talks about the overall goals of these techniques, highlighting Cognoa’s CanvasDx to provide remote diagnoses to potentially reduce the waiting lists for families.

Home
Posted on

How does autism prediction work?

Podcast: Play in new window | Download

Subscribe: RSS

This podcast provides updates on studies that help with prediction of an autism diagnosis – which is important for preparing for the future and for intervening early. First, a study that uses environmental factors to create an equation for the probability of a diagnosis following a combination of of non-genetic factors only which does a fairly good, but not perfect, job at predicting a diagnosis. Second, a study that looks at the accuracy of a machine that predicts autism from eye gaze as early as 9 months of age and with only a 2 minute test. This one wasn’t as accurate as the one that takes longer and tests older kids, but it’s a first step. No ONE thing does a perfect job at predicting a diagnosis – it’s going to be a combination of things, tested over time and multiple times that will be most helpful at predicting a diagnosis. Both studies are open access!

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10904522/pdf/fpsyt-15-1291356.pdf

https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/38429348/

Posted on

Learn about your infant’s development from your own home

Podcast: Play in new window | Download

Subscribe: RSS

Are you the parent of an infant? Are you wondering how you can get assessments on your child without having to struggle with your pediatrician’s time at a well- baby checkup? Are you interested in how your baby is thinking or communicating but your doctor says “it’s too early to tell?” A new study based out of Duke University is using remote computer based assessments to understand the very earliest markers of language and cognition to better predict later social development. The twist? It’s all done remotely. You can participate in research, get a gift card, and learn about your baby’s development all without leaving the house. This has been a struggle for many families and this may open the door for more video-based, but thorough, assessments.

Children Helping Science

sites.duke.edu/risebattery

Posted on

How to predict severe and dangerous behavior

Podcast: Play in new window | Download

Subscribe: RSS

On the first podcast of 2024, we describe a new paper in the Journal of the American Medical Association or JAMA which uses physiological measurements like heart rate and skin conductance to predict severe and dangerous behaviors, specifically aggression. If aggression can be predicted, it might be able to be prevented. It turns out aggression can be predicted up to 3 minutes before an episode occurs, in the future these measures can be used to possibly redirect aggression. In a separate study, the issue of stigma is addressed. There is an intense debate over “person first” vs. “identity first” language in autism, promoting recommendations of using one over the other because fear that person first language promotes stigma against autism. A new study shows that there is no added prejudice or fear using either person first or identity first language, but the stigma associated with schizophrenia is worse than it is for autism. What contributes to stigma? There is a wide range of experiences and perceptions of autism that need to be addressed. It’s not as simple as the language used.

https://pubmed.ncbi.nlm.nih.gov/38127348/

https://pubmed.ncbi.nlm.nih.gov/37965364/

Posted on

Waitlists for waitlists

Podcast: Play in new window | Download

Subscribe: RSS

Everyone who has looked for support for autism spectrum disorder is familiar with waitlists. Waitlists for evaluation, diagnosis, intervention, consultations and referrals. These waitlists prevent important opportunities for services and many groups developing technologies, policies, and approaches to reduce the waitlists or work around them. On this week’s podcast, we talk to Dr. Sharief Taraman from Cognoa to hear about their recent study on the scope of the problem on waitlists, what causes them, and how digital therapeutics may help them.

Waitlist Crisis Report
Posted on

Uncovering the digital underground

Podcast: Play in new window | Download

Subscribe: RSS

Digital therapeutics may very helpful in helping families and individuals on the spectrum. What are they? How can they be used? This week’s #ASFpodcast talks to Lani Hessen from the Digital Therapeutics Alliance who is holding a summit this week in Washington DC. There is technology that is already used to help those on the spectrum, and those that can be easily adapted or implemented in those with a diagnosis or their families. We want to hear about YOUR experience with digital technologies. Tell us more in the comments.

www.dtalliance.org

Posted on

Eye gaze and real-life early detection tools: An interview with researchers from Duke

Podcast: Play in new window | Download

Subscribe: RSS

What babies look at during development and how much time they spend looking at people vs things has received a lot of criticism from some advocates who feel scientists should be spending less time on differences and more on practical solutions. Those two concepts are getting closer and closer and our early understandings of early autism features are now turning into applications to help better and earlier identification of ASD. This week, we talk to Geri Dawson and George Chang at Duke University who used these findings to piloted an app on an iPad. This app shows early promise of being used in a pediatricians office to support faster referral of toddlers for services and intervention.

https://pubmed.ncbi.nlm.nih.gov/33900383/

Posted on

Managing autism practice from a distance: it’s called ECHO

Podcast: Play in new window | Download

Subscribe: RSS

Extension for Community Healthcare Outcomes (ECHO) pairs specialist centers with community providers to help them manage cases and empower them with knowledge to help their patients locally. It is done over the computer, which is especially relevant today. The goal is to help clinicians and physicians manage patients when local expertise is not available. Micah Mazurek of University of Virginia recently published a randomized study about the efficacy of this program, and is a special guest on the podcast to explain what it is and how it can be used to help doctors help each other and their families.

https://jamanetwork.com/journals/jamapediatrics/article-abstract/2762007