Welcome and Introduction
Yulin Hswen - Faculty and Computational Epidemiologist - Harvard Computational Epidemiology Lab
Presentation: Digital Tracing for Identifying Geospatial Temporal Hotspots of COVID-19 Transmission
Yulin Hswen - Harvard Computational Epidemiology Lab
Digital Tracing for Identifying Geospatial Temporal Hotspots of COVID-19 Transmission
Emerging computational methods and digital data sources are changing the landscape of population health research. As COVID19 continues to spread across the US and globally, it is essential to leverage digital footprints to identify novel cases and areas of high risk of transmission. In this presentation, Dr. Hswen will cover three key objectives spanning the fields of computational epidemiology and population informatics in relation to COVID19. First, Dr. Hswen will provide an overview of the application of novel computational methods for uncovering patterns of disease and exploring the links between individual behaviors and illness trajectories. Second, Dr. Hswen will demonstrate how digital data can advance our understanding of COVID19 and citizen science methods that engage and inform the public on COVID19. Last, Dr. Hswen will consider how big data and computational methods can advance our understanding of the impact of social and environmental influences related to COVID19 on human health and well-being. Across each aim in this presentation, Dr. Hswen will draw from her work to highlight digital studies on COVID19. With access to myriad sources of unconventional digital data, Dr. Hswen will conclude by highlighting the opportunities afforded by these digital sources and platforms for discovering new insights about human behaviors and the spread of disease, and why this is now one of the most exciting times in modern history of medical research as there is potential to understand human health in ways that were previously not possible.
Dr. Yulin Hswen is a Computational Epidemiologist and Faculty in the Innovation Program at Boston Children's Hospital, Harvard Medical School. Dr. Hswen completed her doctoral training as a social and computational epidemiologist at the Harvard T.H. Chan School of Public Health, where her research focused on leveraging big data to uncover hidden social determinants and patterns of disease. Her current work within the Innovation Program seeks to develop and test new methods to capture informal online data sources towards generating population health insights that can be used to predict the onset and course of various diseases and public health threats. Dr. Hswen's research involves the design and development of digital surveillance methods, as well as novel tools that can transform public practice and influence health policies. Dr. Hswen has received awards and competitive funding from the Canadian Institutes of Health Research, The Embassy of France, Harvard University, the Weatherhead Center, and the National Institutes of Health for her work in the field of social and computational epidemiology. Her work has been published in the New England Journal of Medicine, the American Journal of Public Health, Preventive Medicine, and the Journal of Medical Internet Research, and has been featured in Nature, Fast Company, Kaiser Health News, Bloomberg.
Simon de Montigny - University of Montreal
Scaling Up Health Care and Public Health
The COVID-19 pandemic shows the need for increasing the intensive care capacity of hospitals as well as the responsiveness of public health services. Artificial intelligence could help health workers handle more patients and more data efficiently. In this webinar, I will present some of my research projects that have implications for pandemic preparedness and response.
Simon de Montigny holds a PhD in mathematics from Polytechnique Montreal. He is currently Assistant Research Professor at the Department of Social and Preventive Medicine at the University of Montreal's School of Public Health and Researcher at the CHU Sainte-Justine Research Center. His research program focuses on artificial intelligence and big data applied to precision medicine and precision public health.
Sébastien Giguère - InVivo AI
Data-efficient Deep Learning to Better Model Emerging Biology
The COVID-19 outbreak offers a solemn reminder of how little we know - and how little data we have - for emerging biology. Novel, data-efficient learning algorithms are needed for these types of data poor environments. InVivo AI is developing novel algorithms capable of learning from small and noisy biological datasets. In light of the COVID-19 outbreak, the startup is leveraging their platform to learn models for the discovery of novel drug and vaccine therapies. In this webinar, we will present some of the opportunities for AI to contribute to finding therapeutic solutions to the current and future pandemics.
Expert in machine learning and computational biology passionate about bridging the gap between the computational and life sciences. Before co-founding InVivo AI, Dr. Giguère has spent significant amounts of time working with research laboratories, pharmaceutical companies and hospital networks on projects including the use of machine learning for design of pharmaceutical compounds, the prediction of antigen recognition by the MHC pathway for vaccine and immunotherapy development, the prediction of protein-protein interactions and kinase phosphorylation for drug target identification, and the prediction of antimicrobial resistance for the treatment of multi-drug resistant infection.
Q&A with the Speakers
END OF WEBINAR