As a second-year PhD student at the University of Toronto, Justin Boutilier spent four weeks in Dhaka, Bangladesh, investigating ways to curb ambulance response times in the bustling capital of a developing country.
He quickly got a firsthand look at the scope of the challenge: The roughly 10-mile trip from his hotel to meetings in the city took about three hours.
“You could walk faster,” he says, “but there’s no sidewalk, so it’s kind of dangerous.”
Boutilier, who has joined the Department of Industrial and Systems Engineering at the University of Wisconsin-Madison as an assistant professor, uses optimization and machine learning to improve healthcare access, delivery and quality, particularly in low- and middle-income settings.
He’s previously worked on projects to optimize emergency response times, such as the effort in Dhaka and drone delivery of automated external defibrillators in and around Toronto. But he arrives on the UW-Madison campus with an evolving research focus that’s shifted toward applying the same operations modeling to screen and manage chronic diseases in underserved populations around the world.
Boutilier has partnered with several healthcare startups, including Hyderabad, India-based NanoHealth—the creator of a successful disease management platform and a former winner of the prestigious Hult Prize, the so-called “Nobel Prize for students.”
Together, Boutilier and NanoHealth are building a diabetes risk assessment that’s tailored specifically to a lower-income Indian population. Whereas guidelines from the American Diabetes Association would encourage a patient to visit a doctor for cholesterol testing and lipids panels to inform a diagnosis, those aren’t feasible recommendations in the slums of India.
“Once we identify high-risk patients, then there are questions of how to manage them,” says Boutilier, who is using the risk data to optimize visitation schedules of community health workers in the area. “A lot of these people lack education about healthcare.”
He’s applying similar methods to try to improve the efficacy of tuberculosis treatment in Kenya.
As Boutilier puts it, he grew up around healthcare. His dad, a paramedic and firefighter, showed him how to use an automated external defibrillator when he was in elementary school, while his mother was a nurse. But he didn’t realize there was a way to connect his medical interests to his studies in math until late in his undergraduate schooling at Acadia University in Nova Scotia, where he was also a high-flying forward on the basketball team.
Now he’s thrilled to join a premier research institution where industrial engineers have already forged deep links with researchers in the School of Medicine and Public Health, the School of Nursing and the School of Pharmacy.
“Wisconsin has such a long history of healthcare work,” he says. “It’s a nice environment to come into. People in the medical sciences already know about us and what we do.”
In the classroom, Boutilier is adapting a course on machine learning—Machine Learning in Action—he taught as a postdoctoral researcher with the Center for Transportation and Logistics at Massachusetts Institute of Technology. The upper-level undergraduate course will take students through tangible applications of different machine learning methods, such as predicting decisions by Supreme Court justices.
“When you do research, the reward is typically far out. It’s a long process, whereas teaching, you can see students learning, almost in real time,” says Boutilier, who will also teach Healthcare Engineering. “That’s such a cool and rewarding experience. I love being in front of the class.”
He hopes to inspire students to follow his lead and take on global health challenges. “I very much want to send my future students to India, to Africa, to Bangladesh,” he says. “Go there, see it. It’s such a life-changing experience, both personally and professionally.”
Author: Tom Ziemer