Details

Sang-Wong Bae, Ph.D.
Systems Faculty
Carnegie Mellon University

Abstract: Unnecessary hospitalizations and unexpected risky moments can be preventable. Inexpensive mobile sensors make it possible to monitor a stream of personal behavioral trajectories in order to help prevent risky behavior and hospitalizations.

In this talk, I will present how to examine the feasibility and acceptability of collecting continuously-sensed contextual information and active patient-reported symptom reports and how to use these types of information to develop algorithms to accurately predict behavior for use in health monitoring and treatment delivery. I will argue how digital marker-based algorithms can be used to trigger just-in-time harm reduction interventions. By collecting automated, continuous monitoring of at-risk populations and understanding people’s behaviors, engineers and scientists can create better interactions with future autonomous systems such as self-driving cars.