Our research brings together human-centered AI, mobile and wearable sensing, and computational methods to understand health and behavior in everyday life and develop new approaches to sensing, assessment, and intervention.
We integrate mobile and wearable sensing with computational models of behavior and context to understand social anxiety in everyday life and deliver personalized interventions in moments of need.
Develop novel multimodal biomarkers to characterize disease in children with pediatric-onset multiple sclerosis (POMS), spinal muscular atrophy (SMA), and Duchenne muscular dystrophy (DMD), including wearable-derived measures of real-world motor function, ultrasound measures of muscle structure, and neuroimaging measures of central nervous system injury.
Combine multimodal sensing and AI to characterize patient-clinician communication and design technologies that support high-quality, compassionate care.
Develop privacy-preserving wearable sensing methods to detect and characterize an individual's social environment in everyday life and better understand their relationship to mental health and well-being.
Develop personalized digital approaches to strengthen social connection and well-being by understanding how young people's behaviors, experiences, and social environments interact in everyday life.
Integrate longitudinal mobile, wearable, self-report, and medication-taking data to model the behavioral and contextual factors that shape adherence to endocrine therapy among breast cancer survivors.