Can Artificial Intelligence Help Detect Osteoporosis early?

A Toronto-based startup is using a machine learning system trained to identify low bone mineral density for early detection of osteoporosis. A cloud version to be offered  virtually is also on the way.

Although one in three women and one in five men will suffer a fracture due to bone loss in their lifetime, only 22 percent of eligible at-risk patients are screened for osteoporosis — the underlying disease causing those preventable fractures.

A Toronto-based startup called 16 Bit wants to reverse that trend. With two Mitacs interns from the University of Toronto’s Master of Science in Applied Computing on board, the company has launched Rho™, a disruptive artificial intelligence (AI) “radiology assistant” that uses routine x-ray images to accurately screen and identify patients at risk of osteoporosis.

16 Bit was founded by two radiologists, Dr. Mark Cicero and Dr. Alex Bilbily. Focused on revolutionizing healthcare using AI, the startup is driven by a mission of significantly enhancing the quality and accessibility of healthcare for all.

Mitacs has been helpful in providing support as 16 Bit plans to scale up. Graduate students Abdur Rahman and Sarthak Narayan are using their expertise to design and implement a cloud version of Rho™ that can easily scale as the company starts to market the technology as a Health Canada-approved software-as-a-medical device (SaMD). Rho™ has also received De Novo marketing authorization from the U.S. Food and Drug Administration (FDA).

Early Detection of Osteoporosis 

The Canadian Task Force on Preventive Health Care currently recommends risk assessment-first screening only for women 65 years and up and recommends against screening men aged 40 and up.

But Dr. Cicero believes age and sex alone are poor predictors of developing osteoporosis and is therefore trying to close this gap. Rho™ is trained to identify low bone mineral density from up to 80 percent of X-ray images when patients go for routine tests for other medical reasons.

This technology works in the background of a typical radiology information system to alert radiologists whenever suspected low bone density is detected in a patient.

“The idea is to raise a flag so the referring clinician can follow up with that patient, talk to them about osteoporosis risk factors and, when applicable, recommend further testing such as a DXA scan,” said Dr. Bilbily. He also pointed out that early intervention leads to fewer fractures and lowers healthcare spending over the long term.

Capitalizing on Students’ Expertise 

Rahman and Narayan are both leveraging their advanced software engineering skills to transition Rho™ from a standalone system to a cloud where it can be centrally managed. Hospitals and clinics will have the option to choose between running the software in the cloud or on-premise.

With simpler and more scalable installation, it will be easier to onboard new customers as the company grows. This also means 16 Bit can offer their solutions directly to patients through online portals as they continue to market the product to hospitals and clinics.

For Rahman, the opportunity to learn the operational side of software development has been eye-opening. “Previously, I’ve had experience building quality software, but I’ve never had the chance to learn what happens after we have the software ready. At 16 Bit, I’ve had to make decisions about how to deliver it to customers and on-board them in a streamlined fashion,” he said.

Narayan also believes the internship has been an extremely valuable experience, and appreciates being part of a team to solve real-world challenges. “This product will have a positive impact on a lot of people as they age. It’s extremely fulfilling to know that I’m applying my software engineering skills to help people,” he said.

Dr. Cicero said that attracting top tech talent today is difficult since most students tend to work for bigger tech companies, but through Mitacs, 16 Bit was able to find the perfect match. Since 2018, the company has collaborated with five Mitacs interns on different projects.

“Working with Mitacs allows us to attract top talent while they’re still in school. We benefit from the students’ cutting-edge learning and they benefit from our entrepreneurial mentoring and guidance, so that together we can develop a very impactful product,” he explained. Both Rahman and Narayan have accepted full-time job offers at 16 Bit.

The company received Health Canada approval for Rho in July 2022 and has since clinically screened more than 150,000 Canadian patients, 45 percent of whom were identified by Rho as being at risk of bone loss.

“This is a new kind of tool,” said Dr. Bilbily. “There’s no population-level AI assistant sitting in a Canadian hospital or imaging clinic right now that discreetly analyzes patient images to provide clinical value. One of the biggest barriers we need to tackle is the social barrier. How will patients receive Rho? How will physicians receive Rho? This AI movement isn’t coming. It’s here.”

Mitacs’s programs receive funding from multiple partners across Canada. We thank the Government of Canada, the Government of Alberta, the Government of British Columbia, Research Manitoba, the Government of New Brunswick, the Government of Newfoundland and Labrador, the Government of Nova Scotia, the Government of Ontario, Innovation PEI, the Government of Quebec, the Government of Saskatchewan, and the Government of Yukon for supporting us to empower Canadian innovation. 

Do you have a business challenge that could benefit from a research solution? If so, contact Mitacs today to discuss partnership opportunities: BD@mitacs.ca.