WEB OF HEALTH
Topics in health and medicine are increasingly searched for and tracked online, and relevant content is often delivered via digital means. This dynamic offers new opportunities to improve our health and the delivery of medicine; for example, by learning about aspects of people’s health status that are otherwise difficult to track, by facilitating rapid collection and dissemination of time-critical epidemiological data, and by allowing novel interventions to improve health.
The Web of Health track at the Web Conference is strengthening the connection between healthcare and web research communities. Our goal is to exchange research paradigms among participants from different fields, ranging from medicine and public health, to ML and AI, and to general computer science. The event program will include distinguished invited talks and a keynote.
Organizers
Tim Althoff, University of Washington
Emre Kiciman, Microsoft Research
1:30-2:15 CEST – Stefano Tessaro
Exposure Notification: Barriers, Challenges, and a few Lessons Learned
Exposure Notification (EN) leverages BLE to alert users about a potential SARS-CoV-2 infection while protecting their privacy to the largest possible extent. It promises to supplement conventional contact tracing efforts by potentially detecting additional exposures that can otherwise remain unnoticed, and has been adopted by several countries, mostly thanks to its implementation by Google and Apple. EN offers an important case study in the development and deployment of privacy-sensitive digital health technologies, and teaches us important lessons about our (in)ability to induce trust in these tools when adopted at scale. This talk will survey some of the inherent barriers in the development of EN, and discuss how they have ultimately affected public perception and adoption. For example, I will explain how the goal of achieving best-possible privacy and security is inherently at odds with scalability needs and with desirable policies. I will also argue for better governance models and for more principled pre-deployment validation strategies to reason about effectiveness.
Stefano Tessaro is an associate professor in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. He received his PhD from ETH Zurich in 2010. Prior to joining UW, he was an assistant professor at the University of California, Santa Barbara, and held postdoctoral positions at UC San Diego and MIT. His research interests span a wide range of topics across cryptography and its applications. He has recently been involved in the development of exposure notification technologies as part of the PACT and CommonCircle teams at UW, which have supported the state of Washington in the development of a digital contact tracing response.
2:15-3:00 CEST – Jina Suh
Population-Scale Study of Human Needs and Disparities During the COVID-19 Pandemic
Most work to date on mitigating the COVID-19 pandemic is focused urgently on biomedicine and epidemiology. However, pandemic-related policy decisions cannot be made on health information alone but need to consider the broader impacts on people and their needs. In addition, understanding the disparate impacts of the pandemic and its policies on a full spectrum of human needs, especially for vulnerable populations, is critical for designing response and recovery efforts for major disruptions. Quantifying human needs across the population is challenging as it requires high geo-temporal granularity, high coverage across the population, and appropriate adjustment for seasonal and other external effects. Quantifying disparities across population groups require careful disentanglement of key factors that are ingrained in our societal structure. In this talk, I will present computational approaches to leveraging web search interactions as a unique lens through which to examine changes in human needs as well as disparities in the expression of those needs during the COVID-19 pandemic. Grounding our analyses on well-established frameworks of human needs and social determinants of health, I will demonstrate how web search interactions can be used to enhance and complement our understanding of human behaviors during global crises.
Jina Suh is a Principal Research Software Engineer in the Human Understanding and Empathy group at Microsoft Research at Redmond. She is also a third year PhD student at Paul G. Allen School of Computer Science and Engineering at the University of Washington advised under James Fogarty and Tim Althoff. She is a proud alumnus of the Machine Teaching group where she grew her interest and passion for HCI and ML. Her recent interests lie in designing and developing technologies for improving mental health and wellbeing where she leverages human-centered design and data-driven approach to gain holistic and contextual understanding of the target population’s wellbeing. She works with clinicians to design and deliver technology-enhanced evidence-based interventions in real clinical contexts, collaborates with product groups to improve workplace wellbeing and understand the future of work, and uses quantitative methods to look at population-level shifts in wellbeing.
3:00-4:00 CEST – Keynote: Gabriel Leung
Making Sense of Big (and Small) Data in Outbreak Control: Lessons from COVID-19
I will describe the science underpinning better, smarter and more efficient use of big (and small) data in epidemic response, drawing mostly on recent experiences with COVID-19. Topics to be covered include the mathematics of connectivity and transmissibility, how we called the pandemic back in mid-January 2020, forecasting pandemic trajectories using granular mobility data, working out the epidemiologic anatomy of the disease before it was even named COVID-19, and how matrix algebra could inform school closures.
Gabriel Leung is one of Asia’s leading epidemiologists and global health exponents. His research defined the epidemiology of three novel viral epidemics, namely SARS in 2003, H7N9 influenza in 2013 and most recently COVID-19. As under secretary, he led Hong Kong government’s response against the 2009 influenza pandemic. He was founding co-director of HKU’s WHO Collaborating Centre for Infectious Disease Epidemiology and Control and currently directs the Laboratory of Data Discovery for Health at the Hong Kong Science and Technology Park. He is Dean of Medicine at the University of Hong Kong.
17:00-17:45 CEST – Brenda Curtis
Artificial Intelligence-based Approaches in Behavioral Health
We are living in a very exciting era for addiction medicine. Advances in artificial intelligence (AI) have made it possible to build intelligent machines that enhance our ability to measure behaviors and deliver treatment. The goal of this seminar is to share some of the latest developments using language based digital phenotyping and to discuss important ethical considerations of using artificial intelligent tools in behavioral medicine.
Dr. Curtis earned both a bachelor’s degree in biology and a master’s degree in public health from the University of Illinois and subsequently obtained her doctorate in communication from the University of Pennsylvania, where she most recently held the appointment of Assistant Professor of Psychology in Psychiatry, Addictions at the Perelman School of Medicine. Dr. Curtis also completed a fellowship at the Fordham University HIV and Drug Abuse Prevention Research Ethics Training Institute. Before joining the National Institute on Drug Abuse Intramural Research Program, she was the PI of several grants including “Predicting AOD Relapse and Treatment Completion from Social Media Use” in which she used social media data to predict alcohol and other drug relapse and treatment completion among patients who have recently entered community outpatient treatment programs. Brenda’s recent work is translational, leveraging social media and big data methodology to form the development, evaluation, and implementation of technology-based tools that address substance use and related conditions such as HIV/AIDS. Her approach uses multiple methodologies to facilitate the flow of scientific discovery to practical application allowing her to not only reach under-served populations, but to design health monitoring and behavioral change interventions that are user-centered, inclusive, and evidence-based. Outside of NIDA, Brenda is a Board member of the Public Responsibility in Medicine and Research (PRIM&R).
17:45-18:30 CEST – Nuria Oliver
Data Science to fight against COVID-19
Nuria Oliver is a computer scientist. She holds a Ph.D. from the Media Lab at MIT. She is the first female computer scientist in Spain to be named an ACM Distinguished Scientist and an ACM Fellow. She is also a Fellow of the European Association of Artificial Intelligence and a IEEE Fellow. She is a member of the Academia Europaea and the fourth and youngest female member of the Spanish Royal Academy of Engineering. In 2018 she was named Engineer of the Year by the Professional Association of Telecommunication Engineers of Spain and she received an honorary doctorate from the University Miguel Hernandez
She is well known for her work in computational models of human behavior, human computer-interaction, intelligent user interfaces, mobile computing and big data for social good. She is the named inventor of 41 patents. She is a frequent keynote speaker both for technical and non-technical audiences. She regularly collaborates with and is featured by the media. She is very passionate about the power of technology to improve our quality of life, both individually and collectively (Wikipedia)
She invests significant effort in outreach efforts to make technology more accessible to non technical audiences and to inspire young people –and particularly girls– to pursue careers in technology
1:30-2:15 CEST – Munmun De Choudhury
Employing Social Media to Improve Mental Health: Harnessing the Potentials and Avoiding the Pitfalls
A popular form of web data — social media data — is being increasingly used to computationally learn about and infer the mental health states of individuals and populations. Despite being touted as a powerful means to shape interventions and impact mental health recovery, little do we understand about the theoretical, domain, and psychometric validity of this novel information source, or its underlying biases, when appropriated to augment conventionally gathered data, such as surveys and verbal self-reports. This talk presents a critical analytic perspective on the pitfalls of social media signals of mental health, especially when they are derived from “proxy” diagnostic indicators, often removed from the real-world context in which they are likely to be used. Then, to overcome these pitfalls, this talk presents two case studies, where computational algorithms to glean mental health insights from social media were developed in a context-sensitive and human-centered way. The first of these case studies, a collaboration with a health provider, focuses on the individual-perspective, and reveals the ability and implications of using social media data of consented schizophrenia patients to forecast relapse and support clinical decision-making. Scaling up to populations, in collaboration with a federal organization and towards influencing public health policy, the second case study seeks to forecast nationwide rates of suicide fatalities using social media signals, in conjunction with health services data. The talk concludes with discussions of the path forward, emphasizing the need for a collaborative, multi-disciplinary research agenda while realizing the potential of web data in health — one that incorporates methodological rigor, ethics, and accountability, all at once.
Munmun De Choudhury is an Associate Professor of Interactive Computing at Georgia Tech. Dr. De Choudhury is best known for laying the foundation of a line of research that develops computational techniques to responsibly and ethically employ social media in understanding and improving our mental health. To do this work, she adopts a highly interdisciplinary approach, combining social computing, machine learning, and natural language analysis with insights and theories from the social, behavioral, and health sciences. Dr. De Choudhury has been recognized with the 2021 ACM-W Rising Star Award, 2019 Complex Systems Society – Junior Scientific Award, over a dozen best paper and honorable mention awards from the ACM and AAAI, and extensive coverage in popular press like the New York Times, the NPR, and the BBC. Earlier, Dr. De Choudhury was a faculty associate with the Berkman Klein Center for Internet and Society at Harvard, a postdoc at Microsoft Research, and obtained her PhD in Computer Science from Arizona State University. When not working, she loves to cook, decorate, read history, and play armchair social scientist.
2:15-3:00 CEST – Luca Foschini
Person-generated Health Data (PGHD): A New Ally for Public Health
Person-Generated Health Data (PGHD) from smartphones, wearables and other sensors have the potential to transform the way health is measured, with broad-ranging applications from clinical research to public health and health care at large. This talk will survey examples of applications of PGHD across therapeutic areas, including post-op monitoring, screening for cognitive impairment, and a particular focus on public health applications for flu and COVID-19 detection and quantification. Finally, I will discuss lessons learned in translating PGHD research into benefits for the individual, with emphasis on the importance of evaluating analytics performance (e.g., AUROC, sensitivity, specificity, …) within a specific context of use of a real-world application.
Luca is the Co-founder and Chief Data Scientist at Evidation Health, responsible for data analytics and research and development. At Evidation he has driven research collaborations resulting in numerous publications in the fields of machine learning, behavioral economics, and medical informatics. Previously, Luca held research positions in industry and academic institutions, including Ask.com, Google, ETH Zurich, and UC Santa Barbara. He has co-authored several papers and patents on efficient algorithms for partitioning and detecting anomalies in massive networks. Luca holds MS and PhD degrees in Computer Science from UC Santa Barbara, and ME and BE degrees from the Sant’Anna School of Pisa, Italy.
