Scroll to top

Predicting Challenging Behavior in Individuals with Autism using Wearable Biosensors and Machine Learning Classifiers: A Computational Behavioral Science Approach


NOVEMBER 19, 2021

Matthew S. Goodwin, PhD
Interdisciplinary Associate Professor
Bouvé College of Health Sciences & Khoury College of Computer Sciences
Research Development Lead, The Roux Institute
Director, Computational Behavioral Science Lab
Northeastern University

About the Presentation: Unpredictable and potentially dangerous challenging behavior (aggression to others, self-injury, emotion dysregulation) can create barriers to accessing community, therapeutic, medical, and educational services for individuals with autism. The current line of research evaluates whether peripheral nervous system and physical activity data obtained from a wearable biosensor can be used to predict challenging behaviors before they occur. Iterative results in a sample of 70 psychiatric inpatients with autism suggest that aggression to others, self-injury, and tantrums can all be predicted 3 minutes in advance with 80% average accuracy using machine learning classifiers. These findings lay the groundwork for the future development of precursor behavior analysis and just-in-time adaptive intervention systems to prevent or mitigate the emergence, occurrence, and impact of challenging behavior in individuals with autism.

About the Presenter: Dr. Matthew S. Goodwin is an Interdisciplinary Associate Professor with tenure at Northeastern University jointly appointed in the Bouvé College of Health Sciences and the Khoury College of Computer Science, where he is a founding member of a new doctoral program in Personal Health Informatics and Directs the Computational Behavioral Science Laboratory. Goodwin has held appointments at Harvard Medical School as a Visiting Associate Professor in the Department of Biomedical Informatics (2018-2020), Brown University as an Adjunct Associate Professor of Psychiatry and Human Behavior (2008-2018), and the MIT Media Lab as Director of Clinical Research (2008-2011). He has also served on the Executive Board of the International Society for Autism Research (2005-2008) and the Scientific Advisory Board for Autism Speaks (2014-2017). He has over 25 years of research and clinical experience working with children and adults on the autism spectrum and developing and evaluating innovative technologies for behavioral assessment and intervention, including video and audio capture, telemetric physiological monitors, accelerometry sensors, and digital video/facial recognition systems. Goodwin has received several honors, including a dissertation award from the Society of Multivariate Experimental Psychology, Peter Merenda Prize in Statistics and Research Methodology, Hariri Award for Transformative Computational Science, a career contribution award from the Princeton Autism Lecture Series, and named an Aspen Ideas Scholar by the Aspen Institute and Matilda White Riley Early-Stage Investigator by the National Institutes of Health. He has obtained research funding from a variety of sources, including the National Institutes of Health, National Science Foundation, National Endowment for the Arts, Defense Advanced Research Project Agency, Department of Defense, Simons Foundation, Nancy Lurie Marks Family Foundation, and Autism Speaks. Goodwin received his B.A. in psychology from St. Clare’s in Oxford and Wheaton College and his MA and PhD, both in experimental psychology and behavioral science, from the University of Rhode Island. He completed a postdoctoral fellowship in Affective Computing in the MIT Media Lab in 2010.