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. In this week’s podcast episode, 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.
Podcast: Machine Learning in Autism, Explained
Did you miss the ASF 2024 Day of Learning and can’t wait for the videos to be posted? This is a 17 minute brief summary of what was discussed, but unfortunately, with no visuals. Don’t just listen to the podcast, watch the videos when they are posted. Also included in this podcast is a shoutout to the Profound Autism Summit which brought together hundreds of advocates around those who need 24/7 care for their lives. The link to their advocacy page is here: https://www.votervoice.net/ProfoundAutism/campaigns/112917/respond
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.
This podcast episode 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
Restricted and repetitive behaviors (RRBs) range from hand flapping to debilitating self-injury. This student will investigate the biological basis for the broad range of RRBs by examining the development of the circuits in an area of the brain called the striatum. Pictures of the brain will be collected and analyzed at multiple time points in individuals from 1-4 years of age and matched with the presence and type of RRBs and later outcomes, like real-world function or adaptive behavior. The results will help identify critical windows for brain development when intervention can be most beneficial.
There is a critical need to understand how motor impairments drive development and predict outcomes in autism. Using an infant siblings research design, infants from 6 months of age will be tracked for 2 years to determine how specific motor impairments lead to social deficits that accompany an autism diagnosis. This study will utilize both home video observation and data gathered from activity sensors worn by the infant to examine specific motor abilities that are linked to later social skills in toddlers. The results of this study may identify potential areas of early intervention to improve developmental outcomes and possibly ameliorate autism symptoms.
Executive functioning is the ability to manage daily life, follow directions and handle emotions — and has been reported to be significantly impaired in individuals with ASD. This project will take advantage of an existing longitudinal study to examine the specific role and active ingredients of early intervention from ages 2-4 on executive functioning. The fellow will also examine whether demographic factors, including race and ethnicity, play a role in the effectiveness of the intervention.
In the last version of the Diagnostic and Statistical Manual, the different subtypes of autism were folded into one label: autism spectrum disorder. A similar revision is being made around the International Classification of Diseases, the system the WHO uses across the world to describe autism and provide appropriate reimbursements for services and supports. In this version, the ICD-11, a combination of 300 different presentations of autism are described. A diagnosis can be made if 1 feature of social-communication and 1 feature of repetitive behaviors are documented, with an onset of any time in life. This is causing a lot of confusion in the community, because since the presentations are not specific to autism, it is difficult to provide an accurate diagnosis using the ICD-11. On this week’s podcast episode we talk to German psychiatrist Inge Kamp-Becker, MD, who outlines what the changes are, and how misdiagnosis can be made and what those consequences might be. Her summary is linked below.
Abstract
Emerging evidence suggests that the higher prevalence of autism in individuals who are assigned male than assigned female at birth results from both biological factors and identification biases. Autistic individuals who are assigned female at birth (AFAB) and those who are gender diverse experience health disparities and clinical inequity, including late or missed diagnosis and inadequate support. In this Viewpoint, an international panel of clinicians, scientists, and community members with lived experiences of autism reviewed the challenges in identifying autism in individuals who are AFAB and proposed clinical and research directions to promote the health, development, and wellbeing of autistic AFAB individuals. The recognition challenges stem from the interplay between cognitive differences and nuanced or different presentations of autism in some AFAB individuals; expectancy, gender-related, and autism-related biases held by clinicians; and social determinants. We recommend that professional development for clinicians be supported by health-care systems, professional societies, and governing bodies to improve equitable access to assessment and earlier identification of autism in AFAB individuals. Autistic AFAB individuals should receive tailored support in education, identity development, health care, and social and professional sense of belonging
Abstract
Autism spectrum disorder (ASD), a neurodevelopmental disorder typified by differences in social communication as well as restricted and repetitive behaviors, is often responsive to early behavioral intervention. However, there is limited information on whether such intervention can be augmented with pharmacological approaches. We conducted a double-blinded, placebo-controlled feasibility trial to examine the effects of the β-adrenergic antagonist propranolol combined with early intensive behavioral intervention (EIBI) for children with ASD. Nine participants with ASD, ages three to ten, undergoing EIBI were enrolled and randomized to a 12-week course of propranolol or placebo. Blinded assessments were conducted at baseline, 6 weeks, and 12 weeks. The primary outcome measures focusing on social interaction were the General Social Outcome Measure-2 (GSOM-2) and Social Responsiveness Scale-Second Edition (SRS-2). Five participants completed the 12-week visit. The sample size was insufficient to evaluate the treatment efficacy. However, side effects were infrequent, and participants were largely able to fully participate in the procedures. Conducting a larger clinical trial to investigate propranolol’s effects on core ASD features within the context of behavioral therapy will be beneficial, as this will advance and individualize combined therapeutic approaches to ASD intervention. This initial study helps to understand feasibility constraints on performing such a study.
Keywords: autism; clinical trial; early intervention; propranolol.
Abstract
Background: Reporting retention data is critical to determining the soundness of a study’s conclusions (internal validity) and broader generalizability (external validity). Although selective attrition can lead to overestimates of effects, biased conclusions, or overly expansive generalizations, retention rates are not reported in many longitudinal studies.
Methods: We examined multiple child- and family-level factors potentially associated with retention in a longitudinal study of younger siblings of children with autism spectrum disorder (ASD; n = 304) or typical development (n = 163). The sample was followed from the first year of life to 36 months of age, for up to 7 visits.
Results: Of the 467 infant siblings who were consented and participated in at least one research visit, 397 (85.0%) were retained to study completion at 36 months. Retention rates did not differ by familial risk group (ASD-risk vs. Low-risk), sex, race, ethnicity, age at enrollment, number of children in the family, maternal employment, marital status, or parent concerns about the child at enrollment. A stepwise regression model identified 4 variables that, together, provided the most parsimonious predictive model of study retention: maternal education, maternal age at child’s birth, travel distance to the study site, and diagnostic outcome classification at the final study visit.
Conclusions: The retained and not-retained groups did not differ on most demographic and clinical variables, suggesting few threats to internal and external validity. The significantly higher rate of retention of children diagnosed with ASD (95%) than typically developing children (83%) may, however, present biases when studying recurrence risk. We conclude by describing engagement and tracking methods that can be used to maximize retention in longitudinal studies of children at risk of ASD.
Keywords: attrition; autism; external validity; internal validity; longitudinal study; retention.
Background: Differences in responding to sensory stimuli, including sensory hyperreactivity (HYPER), hyporeactivity (HYPO), and sensory seeking (SEEK) have been observed in autistic individuals across sensory modalities, but few studies have examined the structure of these “supra-modal” traits in the autistic population.
Methods: Leveraging a combined sample of 3868 autistic youth drawn from 12 distinct data sources (ages 3-18 years and representing the full range of cognitive ability), the current study used modern psychometric and meta-analytic techniques to interrogate the latent structure and correlates of caregiver-reported HYPER, HYPO, and SEEK within and across sensory modalities. Bifactor statistical indices were used to both evaluate the strength of a “general response pattern” factor for each supra-modal construct and determine the added value of “modality-specific response pattern” scores (e.g., Visual HYPER). Bayesian random-effects integrative data analysis models were used to examine the clinical and demographic correlates of all interpretable HYPER, HYPO, and SEEK (sub)constructs.
Results: All modality-specific HYPER subconstructs could be reliably and validly measured, whereas certain modality-specific HYPO and SEEK subconstructs were psychometrically inadequate when measured using existing items. Bifactor analyses supported the validity of a supra-modal HYPER construct (ωH = .800) but not a supra-modal HYPO construct (ωH = .653), and supra-modal SEEK models suggested a more limited version of the construct that excluded some sensory modalities (ωH = .800; 4/7 modalities). Modality-specific subscales demonstrated significant added value for all response patterns. Meta-analytic correlations varied by construct, although sensory features tended to correlate most with other domains of core autism features and co-occurring psychiatric symptoms (with general HYPER and speech HYPO demonstrating the largest numbers of practically significant correlations).
Limitations: Conclusions may not be generalizable beyond the specific pool of items used in the current study, which was limited to caregiver report of observable behaviors and excluded multisensory items that reflect many “real-world” sensory experiences.
Conclusion: Of the three sensory response patterns, only HYPER demonstrated sufficient evidence for valid interpretation at the supra-modal level, whereas supra-modal HYPO/SEEK constructs demonstrated substantial psychometric limitations. For clinicians and researchers seeking to characterize sensory reactivity in autism, modality-specific response pattern scores may represent viable alternatives that overcome many of these limitations.
Keywords: Autism; Hyperreactivity; Hyporeactivity; Integrative data analysis; Item response theory; Measurement; Meta-analysis; Responsiveness; Sensitivity; Sensory features; Sensory seeking.