2020 Gatlinburg Conference Plenary Speakers
Kennedy Family Professor of Pediatrics and Medicine, and the Director of Clinical Research at the Simons Foundation
Date: Wednesday, April 15, 2020
Time: 8:30-9:30 AM
Title: SPARKing New Genetic Insights into Autism
Presentation Overview: Autism is a common condition, and there is significant heterogeneity among individuals in severity, symptoms, and associated co-morbidities. The causes of ASD and the cellular mechanisms leading to ASD are incompletely understood. Findings from clinical studies that have attempted to understand the brain and behavior in ASD are hampered by a lack of reproducibility. Major challenges for replication are the heterogeneity of ASD and the difficulty in recruiting large numbers of participants for initial and replication studies. These challenges have limited the development of effective diagnostic methods and treatments for this condition, and there are currently no approved medications that treat the core symptoms of ASD. Many of the research challenges in ASD are shared with other neurodevelopmental or neuropsychiatric disorders. Studies suggest an important role for genetic factors in ASD risk; however, the genetic architecture of ASD and underlying genes are only partially known. SPARK represents a new era of clinical research that combines online access to participants, ability to re-contact and recruit for new research studies, genomic, environmental, and longitudinal behavioral and medical information on all participants and support for participants through communication of meaningful genetic and other ASD-relevant information. Result from SPARK will be discussed along with the gene specific communities in Simons Searchlight.
Matthew Maenner, Ph.D.
Surveillance Team Lead, Developmental Disabilities Branch, National Center on Birth Defects and Developmental Disabilities, Centers for Disease Control and Prevention
Date: Wednesday, April 15, 2020
Time: 4:30-5:30 PM
Title: Algorithms and Impact: Modernizing an Autism Public Health Surveillance System
Presentation Overview: For nearly 20 years, the Centers for Disease Control and Prevention has operated the Autism and Developmental Disabilities Monitoring (ADDM) Network, a population-based surveillance system to track the number of children with autism and other developmental disabilities in multiple US communities. Traditionally, the ADDM Network approach has been labor-intensive and costly, requiring clinicians to manually review children’s medical and educational records for descriptions of autism symptoms. We considered several alternative approaches to potentially improve efficiency and timeliness, including training machine learning models to use the words in a child’s records to predict whether the ADDM Network clinician would have classified the child as meeting the autism criteria. We then assessed the algorithmic approaches (and alternatives) according to established guidelines for evaluating surveillance systems. This presentation will describe: 1) our work applying machine learning methods to population-based autism surveillance, 2) lessons learned and other real-world considerations for using statistical learning methods, and 3) the future of the ADDM Network.
Professor and Director, Center for Autism Research, Departments of Pediatrics and Psychiatry, Children’s Hospital of Philadelphia and University of Pennsylvania Perelman School of Medicine
Date: Thursday, April 16, 2020
Time: 8:00-9:00 AM
Title: Leveraging Technology for Computational Behavioral Analyses for Basic, Translational, and Clinical Research
Presentation Overview: Innovative technologies and advanced data analytics are increasingly used in research to digitize and analyze human behavior with impressive granularity. It seems probable that everything that an expert observes can one day be captured in the lab and in real world settings, with equal or better precision than current assessment techniques. In this presentation, I will review work in our autism center on computer vision based behavioral and language analyses. Ongoing studies are measuring speech based vocal biomarkers, nonverbal behavioral coordination, and gross motor coordination during walking and during imitation tasks. Current results on differences between individuals with autism and typical children and adults will be presented. This will include results from studies showing that automated video assessment of social coordination during a 3-5 minute conversation can detect who has autism with surprisingly high accuracy. Time efficient computational behavioral phenotyping will allow scaling of these methods to large samples (e.g., in genetic studies), and one day to routine clinical care, including video based telehealth encounters. These methods promise to set the foundation for a precision medicine approach to behavioral assessment of intellectual and developmental disabilities.
Professor and Director, Center for Mental Health, Department of Psychiatry, University of Pennsylvania Perelman School of Medicine
Date: Friday, April 17, 2020
Time: 11:30-12:30 PM
Title: Incorporating Digital Technology into Autism Intervention: What Doesn’t Work and What Might
Presentation Overview: The increasing number of children diagnosed with autism, combined with the high cost of treatment, has generated tremendous enthusiasm for leveraging digital technologies to augment or replace traditional intervention. While many technologies have been developed and disseminated, few have been rigorously tested. I will present the results of a large-scale randomized field trial of one computer-assisted intervention. The results were disappointing, and raise significant questions about the role of these technologies in autism intervention. I will present some possible directions and preliminary findings on how technology can support implementation of evidence-based practice in under-resourced communities, primarily by supporting the interventionist, rather than acting as a direct interface with the student.