Every year, thousands of people pass through the doors of the Cross Cancer Institute in Edmonton. Each one requires some form of care. With healthcare budgets strained and the demand for care growing, medical staff must use the resources they have as effectively as possible.

Dr. Naresh Jha thinks that artificial intelligence can help with that. A radiation oncologist, Dr. Jha leads a new program at the Cross Cancer Institute (CCI) to use AI to analyze how the Dept. of Radiation Oncology is allocating its resources and what changes might help allow them to improve patient care.

A decade of data

Just like any medical facility, CCI collects information about its patients: demographic info, type of cancer, number of patients treated and their outcomes. Over the past decade, the institute has collected a vast store of data. And while some of it gets used, Dr Jha believes there's enormous untapped potential.

"Data is a gold mine these days, and we have collected data for over ten years," he says. "This project is about the intelligent use of data, and that involves artificial intelligence and machine learning."

Dr Jha and his research team have started using artificial intelligence and data analytics to sift through that vast data reserve collected by the Department of Radiation Oncology, which uses radiation therapy to treat a patient's cancer.

By using AI to analyze patient data, Dr Jha hopes to better understand the costs and time that go into treating individual patients. A staggering amount of resources can be required when diagnosing and treating a person's cancer: everything from staffing costs, diagnostic tests, and expensive treatments. With a growing number of patients and limited budgets, Dr Jha and his research team believe in effectively using those resources is the only way to provide services to everyone who needs it.

"The need for healthcare resources [is] escalating. It is unsustainable the way we are. We have to make better decisions guided by the voluminous data that we have collected and continue to collect," he says.

To make those decisions, administrators need good quality information. Without it, areas of the clinic that require more resources might be left scrambling, while other sections might receive resources that could be more useful elsewhere.

A better understanding of how resources are used also means the work at the Cross Cancer Institute can be evaluated against other cancer clinics. If one centre can use resources more effectively, they can share those methods with other locations to improve patient care in Alberta.

A long road to AI

Dr Jha has seen the potential for using artificial intelligence to improve healthcare for a long time and has tried to develop similar projects in the past. However, he said it was nearly impossible to generate interest for the idea: at the time, agencies were reluctant to provide funding for AI projects.

As Alberta's AI ecosystem grew, interest in supporting artificial intelligence projects increased in turn. Dr Jha says a robust ecosystem is necessary for innovative new applications of AI and machine learning. Programs like Prairies Canada Regional Innovation Ecosystems (RIE) help fund the Cross Cancer Institute pilot and other health-based AI projects.

"​​I think we were ahead of our time years ago, but not right now," he says. "But all of a sudden, now it is in vogue, and everybody seems to go after data. And finally, we are funded."

Dr Jha says the project is now entering its second phase, where the data analysis will expand to other departments at the Cross Cancer Institute. He's hopeful that the program can later be used in other medical centres, both within Alberta and other parts of the world.

This project was part of the Western Economic Diversification Canada Regional Innovation Ecosystems (RIE) program. The initiative brought together nine organizations from non-profit, business and academia to establish viable uses for artificial intelligence and machine learning in health and data analytics.