Mental trauma following disasters, military service, accidents, domestic violence and other traumatic events is a health issue costing multiple billion of dollars per year. Beyond its direct costs, there are indirect costs including a 45-150% greater use of medical and psychiatric care. While web-based support systems have been developed these are effectively a "one-size-fits all" approach lacking the personalization of regular treatment and the engagement and effectiveness associated with a tailored regimen. This project brings together a multi-disciplinary team of leading researchers in trauma treatment, facial analysis, computer vision and machine learning to develop a scalable, adaptive person-centered approach that uses vision and sensing to improve web-based trauma treatment. In particular, the effort measures specific personalized variables during treatment and then uses a model to adapt treatment to individuals in need.
The core treatment design builds on well-established social-cognitive theory, where self-efficacy and physiological response are critical elements of recovery. The project measures these as well as engagement that is critical in self-directed web-based treatment. The modeling requires advances in computer vision and facial analysis to develop individualized models that can be computed with just a standard laptop. This project is the first effort to approximate changes in self-efficacy from sensory data. The effort uses and advances machine learning and domain adaption to support this approximation as well as to support the rapid personalization of models. Building a smart system that empowers individuals by combining sensing and learning to improve web-based treatment offers a transformative approach to this national health need for cost-effective evidence-based treatment of trauma.