Speakers: Mauricio Santillana and Jared Hawkins
These will be two 20 - 25 minute presentations.
Location: CGIS South S020
Abstract: (Launching the Next Generation of Digital Disease Surveillance Tools)
The aggregated activity patterns of Internet users have enabled the detection and tracking of multiple population-wide events such as disease outbreaks, financial markets performance, and preferences in online movie selections. As a consequence, a collection of mathematical models aiming at monitoring and predicting these events in real-time have been proposed in the past decade. As we discover new methods and data sources suitable to track these events, it is not clear whether more information will lead to improved predictions.
In the context of digital disease detection at the population level, I will present to you a collection of methodologies we have developed in the past two years capable of accurately tracking flu activity in the US. In addition, I will show you that it is advantageous to combine information from these multiple flu activity predictors rather than simply choosing the best performing method. In other words, our findings suggest that the information from multiple data sources (Google searches, Twitter microblogs, nearly real-time electronic health records, and data from a participatory surveillance system) complement one another and produce the most accurate and robust set of flu predictions when combined optimally.
Our work is particularly timely since the well-established Google Flu Trends website was discontinued worldwide last month. Our team at Boston Children’s Hospital was chosen as one of the exclusive partners that will receive raw data from Google to produce predictions for flu and dengue worldwide. This will enable us to launch the next generation of digital disease surveillance tools.
Speaker bio:
Mauricio Santillana is a physicist and applied mathematician with expertise in mathematical modeling and scientific computing. He has worked in multiple research areas frequently analyzing big data sets to understand and predict the behavior of complex systems. His research modeling population growth patterns has informed policy makers in Mexico and Texas. His research in numerical analysis and computational fluid dynamics has been used to improve models of coastal floods due to hurricanes, and to improve the performance of global atmospheric chemistry models. In recent years, his main interest has been to develop mathematical models to improve healthcare. Specifically, he has leveraged the information from big data sets from internet-based services (Google, Twitter, Flu Near You) to predict disease incidence in multiple locations worldwide.
Mauricio received a B.S. in physics with highest honors from the Universidad Nacional Autonoma de Mexico in Mexico City, and a master’s and PhD in computational and applied mathematics from the University of Texas at Austin. Mauricio first joined Harvard as a postdoctoral fellow at the Harvard Center for the Environment and has been a lecturer in applied mathematics at the Harvard SEAS, receiving two awards for excellence in teaching. He is a faculty member in the Health Informatics Program at Boston Children’s Hospital, and an associate at the Harvard Institute for Applied and Computational Sciences.
Abstract: (Exploring the Digital Phenotype)
Through social media, forums and online communities, wearable technologies and mobile devices, there is a growing body of health-related data that can shape our assessment of human illness. Collectively, this data comprises an individual’s ‘digital phenotype’ - unique, unsolicited and real-time information about a person’s health. As a corollary to traditional forms of disease expression, digital phenotypes can expand our ability to identify and diagnose health conditions. These phenotypes let us, for instance: 1) identify individual patients suffering from acute or chronic disease, and 2) monitor the health of a population by tracking the prevalence of infectious diseases (e.g., influenza). Importantly, the role of digital phenotypes in diagnosis extends beyond surveillance and early detection. Digital phenotypes redefine disease expression in terms of the lived experience of individuals, which expands our ability to classify and understand disease.
During this presentation, I will present some recently published work explaining how we use digital phenotypes to better understand health disorders as well as investigate how people perceive the quality of their health care. We explored whether it is possible to identify patients who suffer from sleep disorders, and if they differ from a control population, based on data from Twitter. Additionally, I will present methods for identifying tweets detailing patients’ perceptions of the quality of care they receive in U.S. hospitals and discuss the utility of this novel data stream. Finally, I will introduce some promising early results attempting to characterize autistic users based on their online behavior.
Speaker bio:
Jared Hawkins is a Research Associate in the Computational Epidemiology Lab in the Children’s Hospital Informatics Program, and the Director of Informatics in the Innovation Program at Boston Children’s Hospital. He received a PhD in Immunology from Tufts Medical School and a MMSc in Biomedical Informatics from Harvard Medical School. Jared works translationally bringing digital health projects from research into implementation and enterprise. Through social media, forums and online communities, wearable technologies and mobile devices, there is a growing body of health-related data that can shape our assessment of human illness. Collectively, this data comprises an individual’s ‘digital phenotype’ - unique, unsolicited and real-time information about a person’s health. Jared’s research focuses on using digital phenotypes for population health surveillance, specifically to identify and analyze specific sub-populations over space and time with the goal of better understanding patient behavior and disease dynamics. Some current research topics include foodborne illness, insomnia, autism, febrile illness, and patient experience.
no links
Files:
hawkins_promo_small3.png
