DEKYAS NEWS World Breaking News and Trusted Source
Related Articles
In a busy ward at St. Michael’s Hospital in downtown Toronto, one of Shirley Bell’s patients was suffering from a cat bite and a fever. He seemed fine otherwise, until an artificial intelligence-based warning system signaled that he was sicker than he seemed.
While the nursing team typically ran blood tests around noon, the technology would alert them to incoming results hours in advance. That warning indicated that the patient’s white blood cell count was “really, really high,” recalled Bell, the clinical nurse educator for the hospital’s general medicine program.
The cause turned out to be cellulitis, a bacterial skin infection. Without prompt treatment, it can lead to extensive tissue damage, amputation and even death. Bell said the patient was quickly given antibiotics to prevent those worst-case scenarios, thanks in large part to the team’s in-house AI technology, called Chartwatch.
“There are many, many other scenarios where patient conditions are identified earlier, the nurse is alerted earlier, and intervention occurs earlier,” she said. “It’s not replacing the bedside nurse; it’s actually improving your nursing care.”
A year and a half study on Chartwatch, published monday The Canadian Medical Association Journal found that use of the AI system led to a striking 26 percent reduction in unexpected deaths among hospitalized patients.
“We are happy to be saving lives,” said co-author Dr. Muhammad Mamdani, vice-president of data science and advanced analytics at Unity Health Toronto and director of the Centre for AI Research and Education in Medicine at the University of Toronto Temerty Faculty of Medicine.
‘A promising sign’
The research team looked at more than 13,000 admissions to St. Michael’s general internal medicine department, an 84-bed unit that cares for some of the hospital’s most complex patients. They compared the tool’s impact on that patient population with thousands of admissions to other subspecialty departments.
“Over the same period, in the other departments in our hospital that were not using Chartwatch, we saw no change in these unexpected deaths,” said lead researcher Dr. Amol Verma, a clinical scientist at St. Michael’s, one of Unity Health Toronto’s three network sites, and the Temerty Professor of AI Research and Education in Medicine at the University of Toronto.
“That was a promising sign.”
The Unity Health AI team began developing Chartwatch in 2017, based on suggestions from employees that predicting death or serious illness could be important areas where machine learning could make a positive difference.
The technology was intensively developed and tested for years before being implemented in October 2020, Verma said.
“Chartwatch measures approximately 100 inputs from [a patient’s] medical records that are routinely collected right now in the course of delivering care,” he explained. “So a patient’s vital signs, their heart rate, their blood pressure … all the lab test results that are done every day.”
The tool works in the background with clinical teams, monitoring any changes in a person’s medical record. “And every hour it makes a dynamic prediction about the likelihood that that patient’s condition will deteriorate in the future,” Verma told CBC News.
This could mean that someone is getting sicker, needs intensive care or is even on the brink of death. In that case, doctors and nurses are given the opportunity to intervene.
In some cases, these interventions involve escalating treatment to save a person’s life, or providing early palliative care in situations where the patient cannot be saved.
In both cases, Chartwatch appears to supplement clinicians’ own judgment, the researchers say, leading to better outcomes for vulnerable patients and helping to prevent sudden and potentially preventable deaths.
AI on the rise in healthcare
In addition to its applications in medicine, artificial intelligence has received a lot of attention in recent years, but also a lot of criticism.
There are plenty of reasons to be cautious about this emerging technology, from the controversy surrounding the use of machine learning software to write academic essays to concerns about AI’s ability to create realistic audio and video content that mimics real celebrities, politicians, or average citizens.
Verma himself said he has long been wary. But in health care, he stressed, these tools have enormous potential to address the workforce shortage plaguing Canada’s health care system by complementing traditional bedside care.
Often called the future of healthcare, artificial intelligence is already finding its way into Canadian hospitals. But AI is far from perfect, and some worry about the costs involved.
It’s just the beginning for many of those efforts. Several research teams, including private companies, are exploring ways to use AI for earlier cancer detection. Some studies suggest it has the potential for debilitating hypertension just by listening to someone’s voice; others show it can scan brain patterns to detect signs of a concussion.
Chartwatch is known for its success in keeping patients alive, Verma points out.
“There are very few AI technologies that have actually been implemented in clinical settings. This is, to our knowledge, one of the first in Canada that has actually been implemented to help us with the day-to-day care of patients in our hospital,” he said.
‘Real world’ look at AI’s impact on healthcare
The St. Michael’s study has limitations. It took place during the COVID-19 pandemic, at a time when the health care system was facing an unusual set of challenges. The urban hospital’s patient population is also unique, the team acknowledged, given its high number of complex patients, including those dealing with homelessness, addiction and overlapping health conditions.
“Our study was not a randomized controlled trial across multiple hospitals. It was within one organization, within one unit,” Verma said. “So before we say this tool can be used broadly everywhere, I think we need to do research on its use in multiple contexts.”
Dr. John-Jose Nunez, a psychiatrist and researcher at the University of British Columbia — who was not involved in the study — agreed that the research should be replicated elsewhere to get a better sense of how well Chartwatch might work in other settings. There are also considerations around patient privacy to consider when using emerging AI technologies, he added.
Still, he praised the research team for providing a “real-world” example of how machine learning can improve patient care.
“I really see AI tools as an additional team member to the clinical care team,” he said.
The Unity Health team hopes to see their technology rolled out more broadly in the future, within their own hospital network in Toronto and beyond.
Much of that work is done through TWINthe largest hospital data sharing network for research and analytics in Canada, said Mamdani, vice president of data science at Unity Health.
More than 30 hospitals in Ontario are working together, he said, creating opportunities to test Chartwatch and other AI tools in different clinical settings and hospitals.
“This lays the foundation for deploying these things outside our four walls,” said Mamdani.
