Analytics is a staple of most Canadian industries. But it has yet to make a serious dent in one sector that is overflowing with data: Medicine.
That could be about to change, a Toronto conference on data analytics in health care was told Tuesday.
“A lot of good work is going on,” Dr. Richard Irving, conference co-chair and associate professor of operations management and information systems at Toronto’s York University Schulich School of Business, said at the end of the first day of presentations. “There’s reason for hope.”
During the day attendees heard how
–Cancer Care Ontario, a provincial agency for chronic diseases, has set up a data analytics centre of excellence;
–a Calgary hospital uses analytics to guide doctors to use better practices for patients with diabetes;
–Toronto’s Mount Sinai Hospital has started to use analytics in patient surveys to improve trust with clinicians;
–a children’s hospital gathers 90 million of points of real-time data a day for analysis in a neonatal intensive care unit.
This last project, at Toronto’s Hospital for Sick Children, is truly an example of big data in action in health care. The Artemis project hopes to be able to predict when babies in distress are about to fall prey to infections.
In fact, there’s a cloud version that connects to several hospitals around the world gathering data on sick babies.
“When you think about how much computing has changed and how much the backbone of network infrastructures have changed, we really are at a point now where big data solutions for health care make sense,” Dr. Carolyn McGregor, Canada research chair in health informatics at the University of Ontario institute of technology and an Artemis project leader told the conference. “We have the capacity.”
The conference heard that variations of patient outcomes across cities, provinces (or across countries) can’t be explained away. Some doctors’ patients do better than others and health care providers have to find out why.
“If we use analytics, we can determine what gives us the best outcome using the least resources – which is also the safest for the patient,” presenter Dr. Andrew Pattullo, senior medical director of analytics for Alberta Health Sciences for the Calgary area, said in an interview.
However, the conference also heard that the Canadian health care system suffers simultaneously from a surplus and a deficit of patient information. Some data is old and has to be treated carefully before being imporated into data warehouses.
Conference co-chair Irving started the day by reminding attendees that no matter how small the datasets they are looking at, the are never clean. Analysts have to make deal with that. Not only that, he said, they also have to scrutinize the context in which the data was gathered and the modelling.
As for the amount of data, speakers noted that in many Canadian hospitals today nurses still input patient data by hand into electronic health records systems (EHRs).
One speaker, Dr. Mathew Morgan, vice-president of patient experience and outcomes at Toronto’s Mount Sinai Hospital, even denounced Ontario ministry of health for not ordering hospitals to use one EHR for greater data collection efficiency.
“We in Ontario should not be permitting individual hospitals to be purchasing their own electronic medical records (systems),” he said. “It’s irresponsible and verges, in my opinion, on negligence. We will never be able to achieve our greater goal that we are all committed to if we continue along that journey.”
Finally, an Ontario official reminded the conference that all the analytics tools in the world means nothing without context.
Data analysts have to understand who the customers and stakeholders are and their expectations, said Vickie Welch, director of Cancer Care Ontario’s informatics centre of excellence. “It’s not just enough to manage data or have great tools and skill sets to crunch numbers,” she said.
“You can build the best data warehouse in the world, but if you haven’t built it and enabled the analytics to support a particular business strategy, then it’s of no use. Its not value-add.”
The conference is organized by the Strategy Institute.
Understanding how IBM Spectrum Protect enables hybrid data protection
Abdicating your company’s data protection responsibilities to the first cloud solution provider you encounter is just as unwise as doing nothing at all to leverage the cloud. On the other hand, it can be a wise decision to investigate what results you might achieve by choosing a backup technology that is capable of supporting a hybrid protection approach capable of covering both on-premises technology and offsite cloud capabilities.