At a time when CMS is pushing physicians to check appropriate use criteria before ordering advanced imaging exams, new research suggests some doctors often rely on a difference resource before placing an order: their instincts.
According to a new study by computer scientists at the Massachusetts Institute of Technology (MIT) in Cambridge, Massachusetts, intensive care unit (ICU) providers let their “gut feelings” about a patient’s condition influence the number of diagnostic imaging exams they order.
“There’s something about a doctor’s experience, and their years of training and practice, that allows them to know in a more comprehensive sense, beyond just the list of symptoms, whether you’re doing well or you’re not,” co-author Mohammad Ghassemi, a research affiliate at MIT’s Institute for Medical Engineering and Science (IMES), said in a MIT news release. “They’re tapping into something that the machine may not be seeing.”
Ghassemi and co-author Tuka Alhanai, a computer science graduate student at MIT, presented their findings at the IEEE Engineering in Medicine and Biology Society conference in Honolulu, Hawaii. In the same MIT news release, Ghassemi said he and his team were curious if “gut feelings” could influence the decision-making process.
“That gut feeling is probably informed by a history of experience that doctors have,” Ghassemi said. “It’s sort of like how when I was a kid, my mom could just look at me and tell that I had done something wrong. That’s not because of something mystical, but because she had so much experience dealing with me when I had done something wrong that a simple glance had some data in it.”
The researchers studied data from more than 60,000 ICU patients admitted to Boston’s Beth Israel Deaconess Medical Center from 2001-2012. Overall, they found “a statistically significant association between ICU provider sentiment and imaging utilization.” Positive sentiment was associated with ordering fewer exams, negative sentiment was associated with ordering more exams and “strongly positive” or “strongly negative” sentiment was associated with ordering fewer exams.
The team’s next step, according to the MIT news release, is seeing if artificial intelligence systems could somehow “learn” this perspective and use it when evaluating patients.
“It would be very interesting to teach the machine to approximate what the doctor encodes in their sentiment by using data not currently captured by electronic health systems, such as their speech,” Alhanai said.
Michael has more than 16 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.