How data sharing can drive innovation

Photo of Dr. Martin McKeown
Dr. Martin McKeown is a Parkinson’s researcher who wants to tailor new treatments and interventions to each person’s specific Parkinson’s journey. Through the Canadian Open Parkinson Network, you can give him and other researchers valuable information that they need to ultimately develop more personalized, targeted therapies.
By Krista Lamb

As the director of the Pacific Parkinson’s Research Centre at the University of British Columbia, Dr. Martin McKeown is investigating new treatments and interventions to help people with Parkinson’s and related disorders. With a background in engineering, much of his work looks at how to use technologies in this research, including through the use of artificial intelligence (AI).

McKeown is also playing a leading role in the Canadian Open Parkinson Network (C-OPN), a joint project with Parkinson Canada and Brain Canada aimed at accelerating the understanding of Parkinson’s.

For Mckeown, C-OPN is a way to formalize data sharing between research centres across Canada. “If we can pool information we may end up with more examples of Parkinson’s than any single clinician would ever see in their lifetime, and this will enable us to learn subtle things about the disease that we would not otherwise be able to do,” he says.

The first step for targeted therapies

For this process to be effective, there is a need for more individuals to share their information, especially in ways that are anonymous. McKeown hopes that knowing this will encourage people to register for C-OPN. “If you had enough examples, you might find there’s a subset of people with Parkinson’s who respond to a specific treatment very well. If you turned out to be part of that subset, that’s knowledge that would directly benefit you. Or you may find that there is a subset of people with certain characteristics that are at very high risk for falling. That might be useful information for you to know.”

With enough data to pull from, researchers could also potentially develop more targeted therapies or technologies that are geared to help with specific complications. “If we can take a heterogeneous condition like Parkinson’s and stratify it into different subgroups who respond similarly to different therapies, knowing what subgroup you were in may guide your clinician into how to tailor the therapy specifically for you,” says McKeown.

Currently, when McKeown starts a project, he reaches out to colleagues to learn what they have seen in clinic – it’s helpful to collect their examples to help frame his understanding. However, it’s a process that only reaches a small pool of people. C-OPN allows for this type of information sharing on a far larger, and more effective scale.

“Part of our research is starting to look at things like deep learning,” says McKeown, referencing a form of AI that uses algorithms to find patterns that might not otherwise be apparent. “For this, we need lots and lots of examples of a particular feature to be able to learn some of the subtle nuances. The amount of data that is useful to answer some of these more important questions is beyond what could be collected by a single individual or even a single centre.”

Technology breaks down research silos

Logo for Canadian Open Parkinson Network (C-OPN)

As an example, McKeown notes a project his team is working on that uses privacy-compliant video monitoring. The video camera has a built-in function that takes a picture and immediately converts it into a skeletal representation that allows the team to monitor changes in mobility. The pictures are never stored and never identifiable. Being able to input these deidentified images into a database like C-OPN allows increased access for researchers and more ability to study these changes in movement.

“It’s a sad reality that that many of us work in silos. I think setting up these structures where we pool data is a first step to larger collaborative projects, which will be absolutely essential for moving forward,” says McKeown. “In addition, there’s a lot of people who have great expertise in big data analysis, but don’t have access to data. In the past they would have to collaborate with an individual who did have data. But if we have a large pool of deidentified data and make it available to people who are experts in analysis, it rapidly and markedly expands the pool of people who are doing research on Parkinson’s disease. I think that will be extremely valuable.”

Your involvement is critical to helping Canadian Open Parkinson Network reach its goals. Visit to learn more and register today.

Leave a Reply

Your email address will not be published. Required fields are marked *