An exciting opportunity in AI to improve health is to leverage intensive longitudinal sensor data from mobile devices to develop and evaluate user-in-the-loop machine learning systems that support novel just-in-time interventions.

– Stephen Intille, Affiliate Faculty, Core Faculty, EAI

Stephen Intille is an associate professor in the Khoury College of Computer Sciences and the Bouvé College of Health Sciences. He helped establish and now directs the doctoral program in Personal Health Informatics.

Intille’s research explores how interventions based on data gathered from smartwatches, smartphones, wearable devices, and in-home sensors will pave the way for healthy aging and well-being. Using human-computer interfaces, Intille designs and evaluates interactive technologies and algorithms that measure and motivate behaviors backed by health and wellness research. Through real-time computational modeling, he’s attempting to accurately measure the time, duration, and intensity of physical activity, sedentary behavior, sleep, stress, and health-related habits using human and machine learning systems. That involves a combination of ubiquitous computing, user-interface design, applied machine learning, behavioral science, and preventive medicine.

Intille has been named principal investigator on sensor-enabled health technology grants from several foundations including, the National Science Foundation and the National Institutes of Health, and in industry. Before arriving at Northeastern, he was the technology director for the House_n Research Consortium at MIT. Intille earned a doctoral degree from MIT. He holds a Master of Science from MIT and a Bachelor of Science in Engineering from the University of Pennsylvania.