Meet researcher, Dr. JianLi Wang
Dr. JianLi Wang is a leading researcher and educator in the field of psychiatric epidemiology and health data science. He joined the Department of Community Health and Epidemiology (CH&E) at Dalhousie University on Sept. 1, 2021, where he serves as a full professor and holds a prestigious Tier 1 Canada Research Chair in Health Data Science and Innovation. With a career spanning decades, Dr. Wang has made significant contributions to understanding and improving mental health outcomes through data-driven approaches.
His research is rooted in the belief that mental health is a cornerstone of overall well-being. While treatment for mental illness is essential, Dr. Wang emphasizes the equal importance of prevention and early intervention—working to identify risks before they manifest into clinical conditions. His work integrates predictive analytics, machine learning, and population health data to develop tools that empower individuals and inform health systems.
Beyond research, Dr. Wang is deeply committed to graduate education and mentorship, teaching courses in population health and guiding students and postdoctoral fellows through hands-on research experiences. His collaborative approach spans partnerships with frontline clinicians, policy-makers, and people with lived experience, ensuring that his work remains ethical, actionable, and impactful.
Q: What inspired your career in psychiatric epidemiology and risk prediction?
My path into psychiatric epidemiology began during my PhD training at the University of Calgary. At the time, I didn’t anticipate that this would become my lifelong focus. But I was fortunate to work with a mentor who was both a psychiatrist and an epidemiologist—an exceptional educator whose passion for the field was truly inspiring. His mentorship sparked my initial interest, and over time, that interest evolved into a deep motivation to explore how data could be used to improve mental health outcomes. It was this early experience that laid the foundation for my career in psychiatric epidemiology and health data science.
Q: How did your early research in depression and suicide behaviors shape your current direction?
In the early stages of my career, I focused on estimating population health parameters—such as the prevalence of depression and suicidal behaviors—and understanding their distribution and determinants. While this work was essential for building a knowledge base, I began to reflect on how we could move beyond measurement to prevention. This led me to shift toward applied research, particularly in risk prediction and intervention. I wanted to use the insights we had gained to develop tools that could help individuals before they reached a crisis point. That transition marked a significant evolution in my research, from descriptive epidemiology to solution-oriented approaches that aim to reduce the burden of mental illness.
Q: What is the main focus of your current research, and how does it support mental health service delivery?
As a Tier 1 Canada Research Chair in Health Data Science and Innovation, my research focuses on psychiatric epidemiology, mental health services, and predictive analytics. A central theme is early prevention—developing tools that help individuals assess their mental health status and take proactive steps to manage risk. These tools are designed to support mental health promotion and prevention, aligning with the first tier of Nova Scotia’s mental health and addiction services model. In collaboration with Nova Scotia Health, my team is also working to improve continuity of care and service matching, ensuring that patients are connected to the appropriate level of care from their first point of contact. Ultimately, our goal is to enhance the efficiency and responsiveness of mental health services.
Q: How are predictive models and machine learning being used in your work?
We’ve developed sex-specific prediction models for major depression using nationally representative data from Statistics Canada. These models serve two key purposes: first, they inform individuals about their personal risk of developing depression; second, they motivate high-risk users to take evidence-based preventive actions. To ensure these tools are safe and effective, we conducted a national randomized controlled trial to confirm that sharing personalized risk information does not cause psychological harm. We’re currently running another trial to evaluate how risk communication can reduce the actual incidence of depression. Trained coaches are helping deliver this information and guide individuals through self-help strategies.
In addition, we’re exploring the use of machine learning (ML) to predict suicide risk and mental health service utilization. ML offers new possibilities for identifying patterns and forecasting outcomes, and we’re comparing its performance with traditional statistical methods. Our collaboration with the Mental Health and Addiction program includes developing models to assist with service matching, continuity of care, and identifying individuals who may require high levels of resources. We’re focused on finding approaches that are not only accurate but also interpretable and feasible for implementation in clinical settings.
Q: What are your hopes for the future of mental health prevention and early intervention in Canada?
There is increasing recognition among policy-makers that early intervention and prevention are critical to reducing the burden of mental illness. However, these areas still don’t receive the resources and attention they deserve. My hope is that we move from acknowledgment to action—investing in mental health education, promotion, and preventive strategies. As the saying goes, “an ounce of prevention is worth a pound of cure.” By prioritizing prevention, we can build a healthier, more resilient population and reduce the long-term costs and consequences of untreated mental health issues.