Everyone understands the concept of an individual person’s health, but what makes entire societies healthy?
Public health is a discipline that looks at this question, and it has major implications on evidence-based health policy. And using AI to find new patterns in data sets could break us out of traditional ways of thinking and uncover new ways to prevent disease, says Laura Rosella, associate professor at the University of Toronto’s Dalla Lana School of Public Health.
“A lot of people can relate to infectious disease: how diseases spread from one person to another, and that makes a lot of sense, and that’s still a very important area of public health,” says Rosella.
“But if you think about any other ailment of society, it also has those same patterns. There’s deep personal connections, there’s structural factors that influence it, there’s environmental factors, how we set up our health policies, or any policy for that matter. And that’s really what public health is about: trying to understand how we keep society and people healthy.”
Not only are we producing more medical data than ever, we are also creating other data that may seem unrelated, but that speak volumes about our well-being. Finding complex patterns in these rich data sources manually would be impossible, but machine learning is pushing the boundaries of what is possible in data analysis.
“I’m really excited about the discovery potential of AI,” says Rosella. “We have all this new data and all this new thinking, and analytically we didn’t really know what to do with it. We’re talking social media, GIS (geospatial data), all these emerging data sources that we actually didn’t have the ability to work with before.”
One exciting feature of AI is that, done well, researchers can strip away biases and predispositions to find patterns that have been overlooked.
“Some of the new technologies are really allowing us to look at the data in a new way that takes away our traditional thinking and unpack new patterns that are really areas of promise for disease prevention,” adds Rosella.
Rosella is also a scientist at the Institute for Clinical Evaluative Sciences and Public Health Ontario, and these active connections are helping her design more useful population risk tools and getting them into the hands of people who can actually use them to improve public health.
“I’m really proud of the work we’ve done in population risk tools because not only have we done something methodologically very interesting and scientifically very interesting, we’ve actually put those tools in the hands of people working in the public health system and they can actually use them,” says Rosella.
“I’m really proud of that work.”
