AI Platforms for mHealth Behavior Medicine


Research question:

How can modern technology help guide us to live healthier lives?  We have many possible futures — some healthy, some not.  How can technology such as mobile phones and the internet of things (IoT) work in coordination to nudge our behavior to make healthy decisions and live healthier lifestyles?

Emergence of AI in Behavior Medicine:

Over the past several years, we have developed a variety of wearable, mobile, and non-contact sensor technologies that can be used to monitor our behavior, our physiology, and our mood.  Coupled with an online server and clinical doctor or therapist, these tools can be used in a feedback loop to enable adaptive  interventions in real time.

An important insight here is that we humans do not have as much conscious control over our behavior as we think we do.  Other “forces” are always at play which affect our behavior (how we sleep, eat, take drugs, etc.).  A simple analogy to the system we wish to create is the GPS system that helps us navigate in physical space.  However, building a navigation system for human behavior is much more challenging, which we call the “Self-Driving Brain AI system”

While we have been working in this field for some time, and have an early patent on this concept, there are many open challenges that still need to be resolved by the research community in order to make this practical.  Ongoing work includes: (1) developing better behavioral and physiological biomarkers; (2)  developing customizable, dynamic, and personalized software models of human behavior; (3) designing effective interventions, which include not just technology but also other people in the feedback loop.  Of course many practical challenges also remain, including things such as open APIs for integration of Internet of Things and also legal and privacy issues.

Past and current collaborators: Ed Boyer (UMass Medical School), Noelle Leonard, Marya Gwadz (NYU), Nicolas Orescovic (Mass General Hospital/Harvard)