Using Artificial Intelligence and novel Internet-based data sources to anticipate disease outbreaks. Lessons learned during the COVID-19 pandemic

ABOUT THE SPEAKER
Mauricio Santillana, PhD, MSc is the director of the Machine Intelligence Group for the betterment of Health and the Environment (MIGHTE) at the Network Science Institute at Northeastern University, and the Harvard T.H. Chan School of Public Health. He is a Professor at both the Physics and Electrical and Computer Engineering Departments at Northeastern University, and an Adjunct Professor at the Department of Epidemiology, T.H. Chan Harvard School of Public Health. Dr. Santillana’s research areas include the modeling of geographic patterns of population growth, modeling fluid flow to inform coastal floods simulations and atmospheric global pollution transport models, and most recently, the design and implementation of disease outbreaks prediction platforms and mathematical solutions to healthcare. His research has shown that machine learning techniques can be used to effectively monitor and predict the dynamics of disease outbreaks using novel data sources not designed for these purposes such as: Internet search activity, social media posts, clinician’s searches, human mobility, weather, etc.

ABSTRACT
I will describe data-driven machine learning methodologies that leverage Internet-based information from search engines (clinicians and the general public), Twitter microblogs, crowd-sourced disease surveillance systems, news alerts, electronic medical records, waste water, and weather information to successfully monitor and forecast disease outbreaks in multiple locations around the globe in near real-time. I will present how these approaches can be used to build early warning systems to anticipate communicable disease outbreaks including COVID-19 outbreaks.