From an organizational perspective, the early days of any new technology are often an exercise in venturing into uncharted territory, and AI in healthcare has certainly been no exception.
But enough time has gone by since the really early days that a body of best practices observations has begun to be compiled.
At HIMSS20 in March, in Orlando, FL, Dr. Wade L. Schulz, director of informatics at Yale School of Medicine, and Dr. Harlan Krumholz, a cardiologist and researcher at Yale University and Yale-New Haven Hospital, will give an overview of a range of approaches for AI and clinical decision support that, in their experience, offer good examples of how organizations can successfully implement predictive algorithms.
“It’s critical to make sure we have high-quality models when we’re looking at deploying algorithms or clinical decision support that’s provider or patient-facing," Schulz recently told our colleague Mike Milliard at HealthcareIT News.
A clinical pathologist specializing in transfusion medicine, Schulz said most of his time these days is spent researching the computational healthcare space, “the tools that we use to acquire data, data integration, all of that," including advanced analytics, predictive models, neural networks and more.
According to Schulz, his and Krumholz's presentation is aimed partly at CIOs and CMIOs: "the people who are often pitched these tools by outside companies.”
The problem for executives, he said, it that “if you have a vendor come in, how can you really evaluate what they’ve done to make sure that tool will be safe and effective in a clinical setting for you? What are the steps that you can do to help validate that algorithm?”
The talk is also aimed at an analytics and data science audience, said Schulz, with the goal of offering "details on those analytic steps, especially if you’re building your own algorithm rather than something off the shelf from a vendor – what can you build out so you have on file all of that data to support the validation, and if you wanted to you could move forward for regulatory submission."
Schulz emphasized that the point of the talk is to counsel overall caution, but not to dismiss any particular technologies out of hand.
"We don’t want to be a block to things that are new and exciting and can have good outcomes," he said. "We’ve just seen too many times things have gone badly because we haven’t looked closely at the things that go into it. We won’t necessarily catch every error but if we can think of efficient ways to catch the majority of errors, things will improve for patients fairly quickly.”
Dr. Wade L. Schulz and Dr. Harlan Krumholz will discuss these emerging technologies in their HIMSS20 session "Validation and Regulatory Oversight of Clinical AI Tools."