The best way to maximize clinical adoption of a new enterprise viewer would be to get physicians involved in the selection process, IT officials said at SIIM 2013.
GRAPEVINE, Texas - What’s the best way to make sure physicians will embrace a new enterprise imaging system?
Get as many docs as possible to help select it. That’s the tactic officials at The Johns Hopkins Hospital took with a recent implementation.
“We wanted them to be a part of the decision making process, as many doctors as possible,” said Paul Nagy, PhD, FSIIM, director of quality in the Department of Radiology at Johns Hopkins. He was speaking Friday at a SIIM 2013 session on strategies for managing medical images. “We got 300 physicians.”
Nagy and his colleagues knew they wouldn’t have much luck asking physicians to come to vendor demo at 9 a.m. on a Tuesday. Physicians are busy, their schedules aren’t their own, and sitting through an hour-long passive demonstration was probably the last thing they wanted to do.
Instead, Nagy and his team brought the demo to the doctors. After identifying the technical and business requirements of the enterprise viewer, they rigorously evaluated a dozen solutions based on their criteria. Once the selections were narrowed to three, they presented the options to the doctors.
They developed a Web-based tool for the testing and evaluation of the options. Without a specific location or allotted time, Nagy said the physicians would be free to test the systems at their convenience. Further, they made the evaluations task-driven, rather than a passive demo, which would allow the physicians to really test drive the capabilities. They also added in a few incentives - raffling a few iPads - to entice participation.
They were also able to reach Johns Hopkins physicians as they were logging into the hospital system, giving them a notice to take part in the survey and be a part of the enterprise viewer selection process.
“This was a lot of fun,” Nagy said of the process.
Users evaluated the solutions and filled out short surveys. After about a month, they had more than 300 responses.
Nagy noted that had they asked 300 physicians to attend vendor demos, that would have eaten up more than 900 work hours. Instead, the Web-based evaluation system took only about 80 hours total, saving 10 times the physicians’ time.
It always seems that the number of physicians who show up to an in-person vendor demo is inversely proportionate to the number who complain about the system that’s selected, Nagy said. So few docs come to the demo, but they are lined up with gripes later. Nagy and his team wanted to avoid this, and giving physicians a direct and critical role in the selection was the solution, with the idea that they would have greater clinical adoption. He added, “We did a lot to get people involved.”
Deep Learning Detection of Mammography Abnormalities: What a New Study Reveals
June 19th 2023In multiple mammography datasets with the original radiologist-detected abnormality removed, deep learning detection of breast cancer had an average area under the curve (AUC) of 87 percent and an accuracy rate of 83 percent, according to research presented at the recent Society for Imaging Informatics in Medicine (SIIM) conference.
Detecting Intracranial Hemorrhages: Can an Emerging AI Advance Have an Impact?
June 9th 2022A 3D whole brain convolutional neural network could provide enhanced sensitivity and specificity for diagnosing intracranial hemorrhages on computed tomography, according to new research presented at the Society for Imaging Informatics in Medicine (SIIM) conference in Kissimmee, Fla.