Benita Hosseini: Stopping Asthma Before It Strikes
Asthma remains one of the most common chronic conditions affecting children worldwide. Despite the availability of effective treatments, preventing severe asthma attacks continues to be a major challenge in clinical care.
Through her participation in the HDRN Canada pragmatic trials training program, Dr. Benita Hosseini is developing a protocol to test how a new prediction tool performs in real-world clinical settings. The tool is designed to estimate whether a child may need emergency care or hospitalization within a defined period. “The goal is to give doctors and families a heads up so they can step in before things get serious,” she says.
Why prediction matters
Unpredictable asthma attacks place a significant burden on families and healthcare systems. Addressing this challenge requires approaches that move beyond treatment to better anticipate and prevent these episodes.
“You would be surprised to hear that each year, more than half of children with asthma actually experience asthma attacks,” she explains.
In Canada, many of these cases result in emergency visits or hospitalizations, placing additional strain on both families and the healthcare system.
For Dr. Hosseini, an assistant professor at the Department of Family and Community Medicine and the Dalla Lana School of Public Health at the University of Toronto, this underscores the need to focus on prevention. “Asthma attacks are really hard to predict,” she says. “Doctors would need a crystal ball to know when one might happen.”
A preventative approach
To address this, Dr. Hosseini has developed a machine-learning–based tool to identify which children are at risk of an asthma attack before it occurs. The aim is to provide clinicians and families with an early warning, what she describes as “a kind of crystal ball,” so they can intervene before symptoms escalate.
Her approach is distinct in that it integrates both clinical and environmental data. While most existing prediction models rely primarily on clinical information, such as medical history and medication use, her model also incorporates factors like air quality, weather changes, pollen levels, and other environmental triggers. “Most of the previous studies… focused on clinical data,” she explains, often overlooking the environmental conditions that can trigger asthma exacerbations.
By analyzing these combined data sources, the tool estimates a child’s risk of requiring emergency care or hospitalization, helping inform earlier and more targeted interventions.
Through her participation in the HDRN Canada pragmatic trials training program, Dr. Hosseini is designing a pragmatic trial to test this tool; she plans to implement the tool in pediatric asthma clinics and evaluate whether its use can reduce severe asthma exacerbations, emergency department visits, and hospitalizations compared to standard care.
“Once we develop this model, we will have to use it in a real-world setting to see if it’s useful,” she explains. The trial will compare outcomes between clinics using the tool and those providing usual care, helping determine whether access to these predictions can meaningfully improve patient outcomes.
The study will begin with a pilot phase to assess feasibility, usability, and integration into routine care. “We need to understand the landscape—can we recruit patients, and can we run this kind of trial smoothly within clinical settings?” she says. Feedback from clinicians and families will be used to refine the tool before expanding its use more broadly.
Ultimately, her work aims to shift asthma care from reactive to proactive, using data and real-world evidence to anticipate risk and enable earlier, more effective intervention.
** The HDRN Canada pragmatic trials training program is coordinated and hosted by the Schulich School of Medicine & Dentistry and is an initiative by Health Data Research Network (HDRN) Canada. It has been funded with $3.48 million from the Canadian Institutes of Health Research (CIHR). Read more.
You can also watch this video for a brief overview of Dr. Hosseini's work
