We are shaping how.

Faculty and students in Northeastern University’s Department of Public Health and Health Sciences are exploring how artificial intelligence and emerging technologies can strengthen public health research, education, communication, and practice, while asking critical questions about ethics, equity, and responsible use.

Dr. Aarti Sathyanarayana uses artificial intelligence, machine learning, and digital phenotyping to transform data from smartphones, wearables, and biomedical devices into meaningful information about human health. Her SATH Lab develops new approaches to digital biomarker discovery with applications ranging from sleep and mental health to maternal and neurological health.

Dr. Annika Schoene studies the safety, robustness, and security of artificial intelligence systems, including large language models. Her work examines how AI safeguards can fail in high-risk health contexts and develops approaches to identify and reduce harmful outputs, helping to advance the safe and responsible use of AI in public health and healthcare.

Dr. Matthew Goodwin pairs wearable biosensors with machine learning to support people with profound autism, who often can’t communicate distress. In a study published in JAMA Network Open, his team used commercial wristbands in four inpatient psychiatric hospitals to predict aggressive behavior three minutes before it happened, with 80% accuracy, giving caregivers time to step in.

Dr. Samuel Scarpino, director of AI + Life Sciences at Northeastern’s Institute for Experiential AI, builds AI and network science tools to track and forecast infectious disease. His work includes wastewater surveillance that can flag rising or newly emerging pathogens in a community, and he co-founded Global.health, a data science initiative backe

Dr. Stephen Intille develops and evaluates technologies that use data from smartphones, smartwatches, wearable devices, and in-home sensors to better understand health and behavior. His work combines artificial intelligence methods with behavioral science to develop new approaches to personal and preventative health.

Dr. Alessandro Vespignani develops computational models and forecasting tools to understand how infectious disease spreads through populations. His interdisciplinary work brings together network science, epidemiology, data, and computational modeling to help anticipate emerging health threats and inform public health decision making.

Dr. Herman Saksono investigates how digital health technologies can be designed to improve health while addressing disparities. His work combines human-computer interaction, health informatics, and user-centered design to create technologies that support health as both individual and collective experiences.

Dr. Robert Leeman’s team develops and tests digital health interventions to reduce alcohol and other substance use and prevent HIV among at-risk young adults. He recently received a new NIH R01 grant for implementation science research combining a web-based intervention with peer counseling and navigator services. Dr. Leeman is a member of the ASPPH AI Task Force.
The same innovation driving faculty research is shaping how PHHS prepares students for the future of public health and health science. Students have opportunities to develop AI literacy, critically evaluate emerging technologies, and explore how AI can be used responsibly to address real-world health challenges.
Senior Lecturer

HLTH 5820
This course explores the application of artificial intelligence in health through collaborative, project-based learning. Students develop and evaluate AI-driven health solutions while engaging with healthcare data, clinical problem framing, responsible AI, safety, and ethical considerations. The course integrates computational methods with clinical perspectives to prepare students to thoughtfully apply AI in evolving healthcare settings.
PHTH 5360
This course examines how AI tools could affect social determinants of health, which are conditions that influence health and well-being (e.g., poverty, education, work, place, as well as discrimination by gender and racial identities). Explores the principles of machine learning predictions, classification, causality, and fairness. Covers the techniques to mitigate such concerns, notably through human-centered AI, participatory design, and value-sensitive design.
PHTH 6130
Offers students an opportunity to develop an understanding of the multiple forms of technology that are deployed to advance both healthcare and public health and the broad range of ethical challenges and individual and community-level disparities associated with these technologies. Examines theoretical and conceptual frameworks to address disparities associated with public health technologies. Explores case studies to understand how a social justice framework can be applied to the development, implementation, and evaluation of public health technologies.
Through faculty-mentored research, experiential learning, co-op, and interdisciplinary collaboration, students can apply what they learn to real-world health challenges.


