Editor’s Note: Each week, PolicyLab hosts our “Morning Speaker Series,” featuring experts who present their research and ongoing projects on a variety of topics including public health, policy, research methods, health equity, and population health, providing us with an opportunity to learn from our colleagues and partners. Now, we’re offering our blog readers a glimpse into these sessions through a blog post series in which we interview some of our speakers about their exciting work. For additional posts in the series, visit the landing page for PolicyLab’s blog.
Following her PolicyLab Morning Speaker Series presentation on the development and implementation of a machine learning-based risk model for enhancing care for individuals at risk of suicide, we sat down with Dr. Emily Haroz to ask her a few questions about her work:
Can you briefly describe your research on suicide prevention?
My research focuses on working in partnership with Indigenous and other communities to not only generate innovative approaches to suicide prevention, but to then think carefully about how to apply these approaches to improve suicide-related health disparities.
What’s one key takeaway everyone should know about this topic?
Despite generations of abuse and discrimination, Indigenous communities offer innovative solutions that have value for the world.
Can you describe why you chose a machine learning approach for your research?
Suicide is a complex phenomenon that is never driven by one factor. Machine learning approaches better account for this complexity.
What is the future of research in this field?
The field needs to focus on not only the development of new tools, but how to best implement multiple tools together and connect these to resources to help ensure people have a system of care that is responsive to their needs and backgrounds.
To learn more about Dr. Haroz’s work, click here, and read a recent study from her team here.