Welcome to DASIO

 In spite of significant recent advances in molecular genetics and neuroscience, behavioral ratings based on clinical observations are still the gold standard for screening, diagnosing, and assessing outcomes in behavioral health and developmental disorders. Such behavioral ratings are still subjective, require significant clinician expertise and training, typically do not capture data from the children and adults in their natural environments, and are not scalable for large population screening, low resource settings, or longitudinal monitoring, all of which are critical for outcome evaluation in multi-site studies and for understanding and evaluating symptoms in the general population. The development of innovative and efficient approaches to behavioral screening, diagnosis, and monitoring is thus a significant unmet need in the area of healthcare. It is critical to develop validated, low cost and scalable tools for behavioral analysis of behavioral health and developmental conditions.   

Automatic digital behavioral coding in natural environments is possible. This is achieved by a unique integration of carefully designed stimuli, computer vision and machine learning tools, and mobile sensing capabilities.   We have developed, tested, refined, and begun to validate automatic, objective, and quantitative measurement of symptom-related behaviors, such as visual attention and affective facial expressions, that can serve as sensitive, objective, and quantitative measures for screening and assessment of outcomes, e.g., in clinical trials. Our goal is to reliably and efficiently capture dynamic behavioral data from individuals across a wide age range and functioning level in diverse settings (from the clinic to their natural environments), without the need for rater training or costly equipment. Our team has been developing and testing tools based on computer vision analysis and other techniques that automatically quantify a person’s behavior while s/he watches stimuli (on an iPad/iPhone/laptop/desktop), designed to elicit relevant behaviors relevant e.g., autism symptoms. The stimuli, video recording, and automatic analysis are all integrated in the ubiquitous devices, producing a software-only objective solution without need for specialized hardware, allowing us to assess in natural environments. We have tested this tool in the clinic and in the wild. This approach offers a scalable solution that addresses the challenges of reliable and quantitative behavioral assessment and phenotyping, and will move us from the standard, moment-in-time, single-visit-assessment paradigm toward continuous-observation-assessment.    

Our team combines leaders in behavioral health, developmental disorders, computer vision, machine learning, app design, and UI. We collaborate with the leading companies in the field and top academic institutions. Our team is uniquely positioned to address the great challenge of efficient, objective, quantification of dynamic behavior with the goal of improving outcomes.