University of Ottawa launches new applied AI centre for healthcare

The University of Ottawa has launched a new research institute to accelerate the development and adoption of AI-powered solutions in the healthcare system. The Ottawa Medical Artificial Intelligence Research Institute, or OMARI, is housed in the university’s Faculty of Medicine and has close ties with the city’s six hospitals and their research institutes.

OMARI is led by Dr. Khaled El Emam, a full professor in the university’s School of Epidemiology and Public Health. Dr. El Emam is also senior scientist at the Children’s Hospital of Eastern Ontario (CHEO) Research Institute and holds the Canada Research Chair in Medical Artificial Intelligence.

“We’re an applied institute, so we’re focused on innovations that can be applied in practice at the point of care in hospitals either directly by researchers or through commercialization by enabling researchers to create spinoffs, building teams and getting the funding so they can productize their innovations and deploy them at a much greater scale,” said Dr. El Emam.

OMARI differs from the three other AI research institutes in Canada – Toronto’s Vector Institute, Amii in Edmonton and Mila in Montreal – which do more basic research on AI and aren’t focused specifically on medicine.

While researchers in Ottawa have used artificial intelligence for many years, recent innovations have improved the capability and power of AI and its potential impact on medicine, creating a need for a more focused research institute to promote the use of the technology.

“We need to be able to produce impactful results faster and transition them into practice faster,” said Dr. El Emam. “We need to attract the best people domestically and internationally to work with us and we need to increase our computing capacity so we can apply AI at scale. These are the types of issues we are trying to address.”

Dr. El Emam cites the example of the ThinkRare AI algorithm developed at the CHEO Research Institute to speed rare disease diagnoses for children. The algorithm uses routinely collected clinical information and observations from 300,000 patient charts to flag children with potential undiagnosed rare genetic disorders, prompting clinicians to consider referring them for genetic testing.

“Historically, clinicians would notice some patterns over time when the children would come in and would eventually refer them for genetic testing,” said Dr. El Emam. “Now, we have an AI tool that runs in the background on top of the EMR looking at all the patterns in the data. This is an example of an AI tool that was developed by researchers, transitioned into practice and is now used on a regular basis. The plan now is to expand it more broadly across the country at other pediatric hospitals.”

The ThinkRare project was led by Dr. Ivan Terekhov, director of research informatics, AI and technology at the CHEO Research Institute.

Another example of AI’s potential impact is an AI model that estimates the chances of patients with advanced chronic kidney disease needing dialysis within the next six to 12 months. This work, led by Dr. Gregory Hundemer, a nephrologist and clinical researcher at the Ottawa Hospital, has the potential to reduce the number of unplanned dialysis starts linked to worse outcomes.

Roughly 40 percent of patients with advanced chronic kidney disease “crash” into dialysis after arriving in hospital very sick and needing urgent treatment. If AI can anticipate the need for dialysis, clinicians can ensure it’s planned rather than rushed.

“There’s a strong link between the research institutes at the hospitals and the university’s Faculty of Medicine,” said Dr. El Emam. “The clinicians have clinical appointments at their hospital and also have faculty appointments at the university where they’re teaching or supervising students.” Dr. Hundemer, for example, is also an assistant professor at the University of Ottawa.

OMARI will help researchers develop their AI-enabled solutions and bring them to market using the university’s entrepreneurship hub. Dr. El Emam is well aware of the challenges faced by entrepreneurs having founded or co-founded six companies himself over a career spanning more than 20 years at CHEO and the University of Ottawa.

“I know all about the pain of spinning off a company and raising money,” he said. “The university has some good support for entrepreneurs whether they’re students or faculty. I benefitted tremendously from the services the university offered when I spun off my first company 20 years ago.”

Help with matchmaking, seed funding and mentoring can be made available to medical students, faculty and researchers through OMARI and the university’s entrepreneurship hub. It’s also important that budding entrepreneurs hear from those who have successfully commercialized a product or spun off a company, he said.

“We want people to understand and appreciate that this happened before and that there are other clinicians and researchers at the University of Ottawa who have spun off companies that have been very successful. By telling our stories we’re hoping to encourage others to take the plunge. It’s not easy. It’s hard work, but it’s possible. It has been done. We have the knowledge and experience to make it happen, so if someone has a good idea, we can help them get started down this road.”

OMARI offers researchers several medical AI databases and resources, including the University of Ottawa Heart Institute’s ARCHIMEDES platform and the International Data Access Tools Repository.
The ARCHIMEDES platform is a national, digital health data platform that provides access to curated, multimodal brain-heart datasets, advanced analytics tools and high-performance computing. The platform supports secure, collaborative health research.

The International Data Access Tools Repository is a collection of tools and resources that support the discovery and access to population-level data across multiple countries. It brings together data catalogues, metadata tools, algorithm inventories and guidance on good practices for accessing and using health-related data. It helps researchers identify relevant data sources and understand access pathways, governance requirements and conditions for use.

OMARI also provides researchers with a systematic review tool, which gathers all the available evidence on a topic and provides an unbiased and reliable assessment of the current state of knowledge. Instead of relying on individual studies, systematic reviews gather information from multiple studies, ensuring a comprehensive overview of the current evidence.

Another resource available to researchers through OMARI is a regulatory playbook that educates researchers about Health Canada regulations for approving AI-enabled software as a medical device (SaMD). It provides information about Health Canada’s risk-based classification framework and educates researchers about Class 1 SaMD requirements.

OMARI also has a mandate to enhance AI education and help achieve better health equity using data-driven tools.

“One way to enhance medical education is to make sure that students learn how to use AI, how to collect, analyze and interpret data and synthesize evidence. We want our students to understand how to use these tools effectively so they can be competitive when they go out into the workforce,” said Dr. El Emam. Dr. El Emam encourages researchers across the country to learn more about OMARI by checking out its website and subscribing to its monthly newsletters.