An award-winning Montreal startup has developed a system that uses artificial intelligence technology to help doctors treat their patients struggling with depression by choosing personalized treatment plans for them in a bid to treat them more more effectively and more quickly.
Depression is the leading cause of disability worldwide, according to the World Health Organization. One person in nine will suffer an episode of depression at some point, said Dr. David Benrimoh, a co-founder of Aifred Health and its chief science officer. And the biggest problem in treating depression is it takes so long for people who seek help to improve, he said. For most, it will take four or five attempts over several months, said Benrimoh, a psychiatry resident who has a masters degree in neuroscience.
Treatments for depression can vary widely from person to person, explained co-founder Sonia Israel, director of business development for Aifred Health, in an interview on CBC Radio’s Spark in late 2017. “It’s essentially trial and error,” she said.
“Regular antidepressants normally take about three to four weeks to start taking effect. So the doctor has to prescribe it and then you go home, you wait and, if you have side effects you go back, or you go back if it doesn’t work and they say: ‘OK, let’s try something else.’ “
As the company website states: “The inability to predict any given individual’s unique response to psychiatric treatment is a huge bottleneck to recovery from mental-health conditions.”
The Aifred Health team is “focusing on helping physicians make better decisions in mental health,” Benrimoh told the Robotics Business Review in January.
In using artificial intelligence-based tools to personalize treatment of depression, the goal is to provide doctors with an evidence-based software tool they can use to match the best treatment to each individual by using that patient’s own health profile, Israel said.
The tool can be used on a desktop computer or a smartphone application; work has been under way nearly two years; a full version of the tool is still a while away but a light version was piloted in 2018, updates to the software are continuing and target date for the light version to be fully launched is toward the end of 2019, she said.
Clinical trials are being developed, some testing has been done and the team has had favourable comments from psychiatrists who have tested the treatment algorithm, Benrimoh said.
Aifred Health has had a good run the past couple of years. Last fall, it made it through a second elimination round to be one of 30 teams advancing in the IBM Watson AI Xprize, a four-year global competition that challenges teams to develop ways for humans to collaborate with artificial intelligence systems to tackle the world’s “grand challenges.” The prize purse is $5 million. Winners will be announced in 2020. And it has twice been recognized as a leader among the Xprize teams with bonus Milestone awards, placing second in 2017 and first in 2018.
“Standard therapies are roughly equally effective, but different people respond differently to different things,” he told the Robotics Business Review. “We may have no idea why they work, and classical statistics have not been able to figure it out. … With AI predictions from more complex mining of data, doctors can decide which treatment to start on, depending on an individual’s characteristics.”
The original idea for the tool came from Aifred Health co-founder and director of research Kelly Perlman, Benrimoh said. The system keeps track of how a patient is feeling, from day to day and week to week, he explained, so it’s possible to keep an eye on symptoms and see how treatment is progressing. “That alone will help a lot,” he said; the tool should be used in tandem with medical monitoring or psychotherapy.
Artificial intelligence “Is not just a thing that we use because it’s cool, because it’s sexy,” he said, but to address a problem that could not otherwise be solved to make predictions at the level of the individual.
The Aifred Health team has had support from Montreal’s entrepreneurial community, including the District 3 Innovation Centre at Concordia University, a joint initiative between Centech, which is the École de Technologie Supérieure’s startup incubator, and McGIll’s faculty of medicine, and the startup-in-residence program of Desjardins Lab, the credit union’s innovation team.
For now, they are focused on depression, Israel said, but they hope to expand to different areas in psychiatry and, eventually, beyond.
With files from The Canadian Press and the Montreal Gazette