Picture an operating room where an artificial intelligence powered machine monitors a patient for imperceptible signs of trouble, warning doctors and nurses about adverse effects of a surgery before they become critical.
Or imagine AI trained to read diagnostic images so precisely that it could detect disease and injury earlier and more accurately than ever before.
Like antibiotics, X-rays and vaccines before them, AI and machine learning (ML) are poised to transform medicine, and the results are already starting to show up in our health care system.
“AI and machine learning represent the most promising technology that can transform the current medical practice and therapy designs,” says Bo Wang, Canadian Institute for Advanced Research (CIFAR) AI chair at the Vector Institute for Artificial Intelligence.
AI will relieve the workload on doctors by streamlining mundane tasks like image analysis, medication reconciliation, note-taking and so on, says Dr. Wang, who is also the lead scientist of the AI team at the Peter Munk Cardiac Centre at University Health Network (UHN). There is already abundant clinical data available and AI algorithms can be trained to make fast and accurate clinical predictions that will benefit doctors and patients, making diagnosis more straightforward. And last but not least, AI is enabling rapid drug discovery platforms.
No areas of medicine will be untouched by AI
The Royal College of Physicians and Surgeons of Canada predicts these sweeping changes will come soon.
“Many are predicting that specialty medicine may fundamentally change, and further, that no areas of medicine will remain untouched by the profound transformation these technologies are expected to bring,” says a report from the College’s Task Force Report on Artificial Intelligence and Emerging Digital Technologies published last year. “Applications of AI in health care are not a future consideration; they are here today,” it states.
Dr. Wang and his UHN lab are developing AI algorithms that integrate data from various sources such as electrocardiograms (ECGs), magnetic resonance imaging (MRI), clinical results, doctor’s notes, and demographic and genomic information to predict cardiac- related outcomes for patients.
“Early and accurate diagnosis of cardiac events can save people from catastrophic life-changing events,” Dr. Wang says. And as the role of AI in drug discovery accelerates, he adds that it’s important to establish guidelines on how ground-breaking algorithms are communicated to the general public.
“Not as a magical miracle cure, but with a nuanced, coherent explanation based in science,” Dr. Wang says.
Oversight of these new applications is an emerging consideration. The College task force report has 12 recommendations, including introducing a new discipline of clinical informatics and measures to ensure AI democratizes health care, rather than exacerbates the “digital divide” for marginalized populations.
“The ML algorithm learns patterns in the data even when such patterns originate from bias, noise, idiosyncrasies or other sources,” the report states. “Therefore, the data collection process requires significant care and some level of expertise and knowledge.”
Putting AI to better use
While there is a wealth of health data generated today, it’s not widely used, says Frank Rudzicz, a faculty member and CIFAR chair in AI at the Vector Institute and one of 14 task force members.
Yet there’s a wide array of applications for AI and ML in health care, Dr. Rudzicz adds, including genetics, patient-centred consumer apps that interact with patients like chatbots, workflow apps for practitioners, monitoring and data science.
He says the technology can save time and help avoid errors, for example, using AI to monitor surgeries for adverse events.
“So if during an operation there’s bleeding that’s more excessive than we might expect… if we can identify those cases in the first place and what caused them, we can structure surgeries much more effectively,” says Dr. Rudzicz, who is also an associate professor in the department of computer science at the University of Toronto.
AI and ML can offer insights that improve medicine and the health care system, he says. Patients may not even notice much of a difference in their interactions but the system as a whole will be made much more effective, he says.
Addressing AI’s challenges
Still, there are challenges to advancing the technology, Dr. Rudzicz notes. One is the long, expensive process of clinical trials and regulatory approval and another is the practicality of introducing new technology in the real world. Even the billing process will need to be revised to recognize these emerging technologies.
There’s also a natural hesitancy to change. “Sometimes you talk to clinicians and they’ve been practicing the same way for decades,” Dr. Rudzicz notes. “When it comes to some new technology that they don’t know about, it can cause a lot of concern.”
AI will not replace doctors, he says, but will improve patient outcomes and the quality of life for doctors and nurses. “It’s not going to be a robot doctor that’s going to come up to you and ask you how you’re feeling. It’s going to be more doctors getting insights from data that will improve things,” he says. “It’s a revolution, but it’s a revolution that won’t happen all at once.”
On Nov. 30, The Globe and Mail hosted a virtual event called Regenerative medicine: Where will stem cells take us? Presented by Bayer, the webinar explored the way researchers are working on stem cell advances that could change the future of medicine. Read more here.