Post Event Supplemental Material
We would like to thank everyone who presented and registered for this event, it was keenly attended and well received.
We have uploaded all conference materials that were presented during the conference, we encourage you to view them as part of our commitment to Knowledge Mobilization. They are listed under their respective agenda items below.
We are proud to offer a PDF of the ebook that this conference generated:
All the available videos from the conference maybe found on our YouTube channel here.
Please take a moment to read an article covering this event here.
Cybersecurity, Privacy, and Artificial Intelligence in Health Data: Advancements and Challenges Conference
May 5th, 2023.
This virtual conference will focus on the latest developments in cybersecurity and privacy research, gaps hindering the collection of informative data, and the potential of big data generated through mobile and other devices, along with the use of AI methods in healthcare. Additionally, discussions will touch on issues surrounding public trust and its impact on government policy. Representatives from Health Canada and Statistics Canada will also provide observations on research and public policy and how to effectively move forward with research partnerships.
- Conference format - Sessions start at 9 am and each presenter has 20 minutes. Each session will be moderated by a UW faculty member. There will be 20 minutes at the conclusion of presentations for Q and A from the audience and there will also be breaks in between sessions if in-person invitees would like to speak with the presenters.
- For any further questions, please email CPI
Conference Agenda: (subject to change)
8:30am – 9:00am
Welcome from President Vivek Goel, Deputy Minister Stephen Lucas (Health Canada) and Chief Statistician of Canada Anil Arora
9:00am – 10:30am: Cybersecurity and Health Data
This session will discuss the latest developments in cybersecurity and privacy research that have significant implications for health data.
An Introduction to Differential Privacy for Analysis of Sensitive Data
Gautam Kamath, Cheriton School of Computer Science - UWaterloo
Abstract: Sensitive data is increasingly ubiquitous in modern applications, and its protection is a critical concern for both individuals and organizations. For example, in the healthcare industry, vast amounts of sensitive data are collected and analyzed to improve patient outcomes, identify disease trends, and develop new treatments. However, any analyses run on this must be secured to prevent inadvertent disclosure of sensitive data. Best effort or heuristic approaches such as anonymization and data minimization have been repeatedly demonstrated to be ineffective. One promising solution to this challenge is differential privacy, a technique that provides a mathematically rigorous guarantee of privacy protection while still allowing for meaningful analysis of the underlying data. Differential privacy has already been implemented and deployed in practice in a number of settings. Some notable examples include by the US Census Bureau in the 2020 US Census, and by Apple and Google to gather and analyze aggregate user behaviour and telemetry. In this talk, we will provide an introduction to differential privacy and explore how it can be used to analyze sensitive data, simultaneously providing useful results and rigorous privacy guarantees for the individuals who provided their data. We will discuss the basic principles of data privacy, the failures of heuristic or best-effort approaches, the notion of differential privacy, and methods to make data analysis procedures differentially private.
Establishing A FAIR and CARE Synthetic Health Data Ecosystem for Canadian Learning Health Systems and Innovation
Helen Chen, School of Public Health Sciences - UWaterloo
Abstract: Accessing real world health data remains a daunting task, primarily due to privacy and security concerns. As a result, researchers, particularly those in the health data science and technology innovation space, are increasingly turning to synthetic health data to bridge the data gap. Synthetic health data can accelerate research and technology development. However, Canada lacks synthetic health datasets that meet the Findable, Accessible, Interoperable, and Reusable (FAIR) standards. Additionally, while federated machine learning has the advantage of protecting patient privacy by not requiring the exchange of source data across nodes, it has yet to be optimized in Canada's health research environment, and there is very limited use of federated learning with synthetic health data. This paper explores the ethical considerations and value proposition of generating and sharing synthetic health data. We propose an architecture and a data governance framework for establishing a pan-Canadian synthetic health data ecosystem that enables learning health systems and fosters health technology innovation. Our goal is to facilitate the development of a reliable and sustainable synthetic data infrastructure that supports ethical and responsible use of health data. We believe that this framework will pave the way for a more robust and secure synthetic data ecosystem, enabling the generation of valuable insights that can drive positive health outcomes for Canadians.
Blockchain Privacy and its Applications in Healthcare
Guang Gong, Department of Electrical & Computer Engineering - UWaterloo
Abstract: Blockchain, due to its decentralized, verifiable, and immutable data between untrusted entities, in addition of applications in cryptocurrency, is gaining interests to many different applications, such as decentralized identity management, supply chain management, private data management, digital healthcare data record, etc. However, those applications added more complex requirements for enforced privacy of blockchain. Currently, all existing blockchain privacy solutions employ advanced “cryptographic engines”, namely zero-knowledge proof verifiable computation schemes for which the zero-knowledge Succinct Non-interactive Argument of Knowledge (zkSNARK) approach is the most promising. In this talk, I will first present an overview for the current research on zkSNARK enabled blockchain privacy and how practical of those schemes. Then I will present some exploration of the application of blockchain in digital healthcare data record systems in different types of blockchain systems, such as public or permissionless blockchain, private and permissioned blockchain and consortium blockchain with privacy enforced.
10:30am – 11:00am: Networking Break
11:00am - 12:30pm: Health System Data Gaps, AI, Privacy, and Data Governance
The talks in this session will focus on current gaps that hinder the collection of informative data, the potential of big data generated through mobile and other devices, and the use of AI methods in healthcare.
Modernizing Canadian Health Data Systems to Improve Capacity for Evidence-informed Decision Making when the only Constant is Change
John Hirdes, School of Public Health Sciences - UWaterloo
Abstract: Decision-makers at all levels of the health care system face many complex choices in an ever-changing, ambiguous, and uncertain world. Major societal changes have been underway for prolonged periods with reasonably foreseeable consequences for the health system. Examples include population aging, female labour force participation, geographic mobility, and increased urbanization. However, the COVID-19 pandemic showed that other “unexpected” changes can occur with greater force and in shorter time frames to pose severe challenges to the health system’s function and effectiveness. Canada’s health data system is relatively robust and comprehensive compared to other countries, but the pandemic has highlighted urgent concerns that must be addressed to strengthen our capacity to mobilize evidence to inform decisions about future challenges. Some key concerns include: health system data gaps; inconsistent data standards; limited data literacy among some decision-makers; inertia in the mobilization of evidence; and constraints on use of data. While big data holdings and new machine learning tools are valuable, they are insufficient on their own to prepare Canadians for what lies ahead. Moving forward, we must implement practical solutions to address these short-comings while pursuing an on-going dialogue about the value-based choices Canadians must make to ensure sustainability of the health system.
Cyber Security and Privacy in the Digital Health Age – How Big Data Has Changed the Canadian Public Health Landscape
Plinio Morita's video presentation may be found here.
Plinio Morita, School of Public Health Sciences - UWaterloo
Abstract: The advancement of big data (e.g., wearables, social media data, mobile health) into mainstream public health and healthcare delivery has increased our ability to monitor population-level changes in near real-time, providing our society with advanced warnings for infectious diseases (GPHIN - Global Public Health Intelligence Network), channels for evaluating the impact of policy changes (Google Social Mobility), and mechanisms for controlling the progression of pandemics (COVID Alert). As a society, however, we are still not certain about the best practices on how to navigate the use of big data in public health, which consequently leads to public concerns about the privacy and security of their data. This paper presents a perspective on cybersecurity and privacy challenges and technologies supporting digital health and big data use in public health. Recent cloud technology and cybersecurity advancements can provide the necessary safeguards for digital health care. However, as a country, we still need a unified front guiding the implementation of such systems in Public Health. The authors will discuss the ideal approach for ensuring that Canada’s public health ecosystem is empowered big data while still ensuring that Canadians’ privacy and data security. Public Health is a complex and dynamic ecosystem that requires rapid surveillance programs, which was demonstrated by the COVID-19 pandemics and this article will seed the implementation of a Canada-wide strategy for using big data from digital health in Public Health initiatives.
Making Canadian Healthcare Systems "AI Ready": What do we need to build AI-powered Trustworthy Primary Healthcare Solutions?
Sirisha Rambhatla, School of Management Sciences - UWaterloo
Abstract: With the double whammy of aging population and healthcare worker shortage sending shockwaves throughout the healthcare systems in Canada, there is an urgent need to develop and deploy AI-powered healthcare solutions to assist and support our healthcare workers. While AI for healthcare solutions have made tremendous progress in recent years, translating these gains to improve quality of service (QoS) for real-world healthcare systems has been extremely slow despite a widespread interest from researchers, hospitals, policy-makers. This is primarily because our healthcare systems are not "Artificial Intelligence (AI) Ready". In this paper, we first outline various ways AI-powered solutions can revolutionize primary healthcare solutions based on our research in liver transplantation and burn surgical candidacy forecasting. Second, via an example of AI-based surgical skill assessment in radical proctectomy, we highlight how AI can play a key role in tooling and training our healthcare workforce in highly skilled tasks. Next, we delve into the data aspect of machine learning for trustworthy and fair AI modeling in healthcare systems and hospitals, followed by a discussion about the current challenges faced by hospitals in adoption of AI solutions. We then discuss some lessons learned from the COVID-19 pandemic, and its impact on policy, healthcare misinformation, calling attention to the need to tackle the new wave of large language model-driven misinformation. We end with a call to bring together hospitals, industry experts, academic researchers, and policy-makers to develop a unified healthcare strategy for building AI ready healthcare systems. This will lead to faster adoption of research results, data transparency initiatives for patients, and provide a blueprint for AI-centric data organization in the health systems in Canada and abroad.
12:30pm – 2:00pm: Networking and Lunch
2:00pm – 3:00pm: Trust, Data, and Data Literacy
This final session will explore issues relating to public trust and the corresponding impacts on government policy.
Trust in Canadian Government: What is it, (How) has it Changed, Can it be Measured, and Why does it Matter for Population Health?
Samantha B. Meyer, School of Public Health Sciences - UWaterloo
Abstract: The ability of governments and nations to protect the lives of citizens is heavily dependent on the public’s trust in their governments and related social institutions. Trust in government is indeed associated with increased social cohesion and interpersonal trust between citizens, public acceptance of government policy, and the acceptance of recommended health behaviours. Thus, trust in social institutions is critical for societal functioning and the health of the population. The COVID-19 pandemic brought the notion of trust, as it relates to health broadly, to centre stage. There is more interest than ever in research focused on understanding what trust is, if, how and why it has changed over time, and interventions that might be used to (re)build trust. This paper introduces the concept of institutional trust and speaks to the ways in which a decline in trust threatens the legitimacy of social institutions and thus, public support for policy and messaging designed to protect the health of the public. Literature focused on understanding and explaining declining trust are explored, including the proliferation of misinformation on social media, as well as broader social issues in Canada – e.g., levels of inequality in the population. The consequences of declining trust in terms of population health are also discussed. The paper concludes with a discussion of the importance of measuring citizens’ trust over time in an ever-changing political climate. Methods for researching the nature and extent of Canadian’s trust are presented, with specific mention of how research might focus on identifying populations of Canadians that would benefit from interventions to (re)build trust.
Estimating the Effects of COVID-19 Policies and using Mobility Data to Predict Daily Cases
Anindya Sen, School of Economics - UWaterloo
Abstract: This study reviews recent findings on the efficacy of different COVID-19 policies adapted by provinces. The paper also explores the usefulness of publicly available mobility data in predicting the spread of COVID-19. This is an important exercise given the controversy that occurred when the Public Health Agency of Canada (PHAC) explored the benefits of employing public mobility data from Telus to study trends in COVID-19. The findings reveal that mobility data were not particularly important in explaining future trends in the spread of the disease. However, data literacy is extremely important as the country moves forward in better data sharing arrangements that have the potential for significantly better population health outcomes.
3:15pm – 4:00pm
A panel of representatives from Health Canada, PHAC Statistics Canada and the Canadian Institute for Health Information discussing observations on research, use on public policy, and how can we move forward further on effective research partnerships.
Christopher Allison, PHAC Chief Data Officer, Public Health Agency of Canada
Steven Trites, Director of the Centre for Population Health Data, Health Canada
Deirdre Hennessy, Senior Research Analyst, Statistics Canada
Mario Francoeur, Acting Director of the Data Analytics as a Service Division, Statistics Canada
Brent Diverty, VP, Data Strategies and Statistics, Canadian Institute for Health Information
Dr. Helen Chen is an expert in health data analytics, health systems integration, and digital health. Her research focuses on creating interpretable machine learning models and explainable AI algorithms that generate real-world evidence in the healthcare and public health domain. Collaborating closely with health professionals, her research team develops cutting-edge natural language processing algorithms to extract key information from electronic medical records and constructs machine learning models to reveal patterns in population, disease and treatment while predicting outcomes. Dr. Chen is instrumental in fostering partnerships between academics, health professionals, and private industries to advance Canada's digital health transformation.
Dr. Guang Gong is a professor in the Department of Electrical and Computer Engineering at University of Waterloo, Canada since 2004. Currently, her research focuses on pseudorandom generation, lightweight cryptography (LWC), IoT security, blockchain privacy and privacy preserving machine learning. She has authored or coauthored more than 360 technical papers, two books, and three patents. She serves/served as an Associate Editor for several journals including an Associate Editor for the IEEE Transactions on Information Theory (2005-2008, 2017 - 2018, 2020-2022), the IEEE Transactions on Dependable and Secure Computing (Nov 2021 - ), and the Journal of Cryptography and Communications (2007 - ), and has served on numerous technical program committees and conferences as the co-chair/organizer or committee member. Dr. Gong has received several awards, including the Premier's Research Excellence Award (2001), Ontario, Canada, Ontario Research Fund - Research Excellence Award (2010), IEEE Fellow (2014) for her contributions to sequences and cryptography applied to communications and security, and the University Research Chair (2018-2024). Dr. Gong's research is supported by government grant agencies as well as industrial grants.
Dr. John Hirdes is a University Professor in the School of Public Health Sciences, University of Waterloo, a Fellow of the Canadian Academy of Health Sciences, and a Fellow of the Balsillie School of International Affairs. In addition, he is the Senior Canadian Fellow and a Board Member of interRAI (www.interRAI.org), an international consortium of researchers from over 40 countries. He chairs interRAI's Network for Mental Health and the interRAI Network of Canada.
Dr. Hirdes has 300+ publications in peer reviewed journals and academic book chapters. His primary areas of interest include assessment, mental health, aging, health services research, quality measurement, and quantitative research methods.
Dr. Gautam Kamath is an Assistant Professor at the David R. Cheriton School of Computer Science at the University of Waterloo, and a Faculty Member at the Vector Institute. He has a B.S. in Computer Science and Electrical and Computer Engineering from Cornell University, and an M.S. and Ph.D. in Computer Science from the Massachusetts Institute of Technology. He is interested in reliable and trustworthy statistics and machine learning, including considerations such as data privacy and robustness. He was a Microsoft Research Fellow, as a part of the Simons-Berkeley Research Fellowship Program at the Simons Institute for the Theory of Computing.
Dr. Samantha Meyer is an applied social scientist with expertise in social theory and a variety of methodological approaches used to inform research investigating critical and timely public health problems. Meyer’s specific research focus is understanding the complex social and structural factors that shape population health, and the health of vulnerable populations specifically. The concept of trust as it relates to health communication and acceptance of health promotion efforts is central to her work. Theoretically, she has identified and operationalised semantic distinctions between trust and the related concepts of dependence and obligation that are critical for research investigating and measuring trust. Her empirical research demonstrates the role of trust in the acceptance of health promotion efforts (e.g., vaccine uptake). She completed her graduate and early career research in Australia before returning to Canada as an Associate Professor in the School of Public Health Sciences, University of Waterloo.
Dr. Plinio Morita is an Associate Professor at the School of Public Health Sciences, Faculty of Health, University of Waterloo and a former J.W. Graham Information Technology Emerging Leader Chair in Applied Health Informatics (2016-2021). He also holds appointments as an affiliated scientist at eHealth Innovation, University Health Network, as a Research Scientist at the Research Institute for Aging, and as an Assistant Professor at the Institute of Health Policy, Management, and Evaluation, University of Toronto. He is a leading researcher in the use of AI and IoT for public health, global health, and technology for supporting independent living. At the UbiLab, his research team focuses on the use of IoT technologies, big data, and AI to improve current public health surveillance mechanisms and support countries in the monitoring of health indicators (e.g., physical activity, sleep, sedentary behavior), as well as environmental factors (e.g., heatwaves, extreme air pollution).
Professor Morita’s research team has developed large-scale data collection ecosystems for supporting local initiatives in Canada and low and middle income countries (LMIC) in their efforts to better understand the impact of the COVID-19 pandemic on health behaviours, the impact of extreme air pollution on child and maternal health in LMICs (in partnership with UNICEF Mongolia), the impact of heatwaves on seniors around the globe (in partnership with Health Canada and the Public Health Agency of Canada), and on the development IoT-based systems for supporting independent living in Canada (in partnerships with the Canadian Standards Association, Swidget, Smartone, Age-Well, and NRC).
Through the development of data ecosystems and AI solutions, the UbiLab has been pushing the envelope in the development of predictive models that can help public health officials around the world to better understand their data, as well as creating real-time indicators to support risk mitigation initiatives aimed at minimizing the impact of uncontrolled urbanization and climate change on health.
Dr. Sirisha Rambhatla is an Assistant Professor in the Management Sciences Department, Faculty of Engineering at the University of Waterloo (UW) where she leads the Critical ML Lab. Her research focusses on developing reliable machine learning (ML) and artificial intelligence (AI) models for critical real-world decision making in surgery, transplantation and healthcare, misinformation, and intelligent manufacturing using time-series and spatiotemporal modeling, representation learning, and explainable AI. Her inter-disciplinary work spanning both theory and practice of ML, has been published at top ML venues such as NeurIPS, ICLR, KDD, IJCAI, AAAI, and clinical venues such as AMIA, Urology Clinics North America, Surgery, and American Association for the Study of Liver Diseases. Recipient of the 2021 Merit Award for Excellence in Postdoctoral Research at the University of Southern California across science and engineering, Dr. Rambhatla recieved her Ph.D. and Masters in Electrical Engineering from the University of Minnesota -- Twin Cities in 2019 and 2012, respectively, where she was the recipient of the E. Bruce Lee Memorial Fellowship.
Dr. Anindya Sen is Professor of Economics and Associate Director of the Cybersecurity and Privacy Institute (CPI) at the University of Waterloo. He received his Ph.D. from the University of Toronto. Prior to working at the University of Waterloo, Professor Sen worked as an economist at the Competition Bureau, Industry Canada.
His research interests are the economics of public policy, with an emphasis on estimating the statistical effects of government intervention and imperfectly competitive market structures. He has published research on the relationship between market concentration and gasoline prices, the impacts of higher cigarette taxes on smoking, the effects of higher minimum wages on employment and poverty, the consequences of incentive programs on electricity usage, and the effects of government policies on daily COVID-19 cases. His work has extensively covered by The Globe and Mail, The Financial Post, CBC, and The Toronto Star.
Professor Sen’s currently studies: the use of AI tools to study issues of societal importance; the implications of being a digital and AI based society; understanding trends in cybercrime; and constructing efficient models of data governance.
He is passionate about improving population level data literacy and helping people acquire relevant skills to navigate an increasingly digital based society. With that in mind, and in partnership with WatSPEED, he has constructed a three-course certificate program which begins with a simplified introduction to the foundations of statistical analysis, and then goes to basic methods of coding and analysis in Python and R, enabling learners interpret data findings from complex statistical analysis and directly apply them to decision-making and policy development. The Data Analytics for Behavioural Insights Certificate Program is specifically designed for individuals who have a limited background in statistics and are interested in acquiring skills that will enable them to analyze data, extract insights, and apply them to decision-making.
Professor Sen is past recipient of the University of Waterloo’s Award for Distinguished Teaching.