The business model of first come, first served works at fast food restaurants but not in medical care, a fact embraced by emergency but not many radiology departments, according to Dr. Mark J. Halsted. The exception is Cincinnati Children’s Hospital Medical Center, where Halsted is chief of the Informatics Core.
The business model of first come, first served works at fast food restaurants but not in medical care, a fact embraced by emergency but not many radiology departments, according to Dr. Mark J. Halsted. The exception is Cincinnati Children's Hospital Medical Center, where Halsted is chief of the Informatics Core.
There the radiology department has instituted an algorithm that prioritizes cases according to medical urgency. The radiological triage system has dramatically increased productivity, Halsted told DI SCAN at the Society of Imaging Informatics in Medicine conference last week. In the latter half of this year other radiologists will have access to the technology through a licensing deal with PACS developer Amicas (DI SCAN 4/28/06 Business briefs "Amicas licenses workflow manager"
).
Beginning in the second half of 2006, Amicas plans to make the improved workflow algorithm, with some minor modifications, available as a Web-based stand-alone application that will run with any company's RIS or PACS, said Amicas president Peter McClennen. By mid-2007 the rules-based engine will be seamlessly integrated into the Amicas Vision PACS.
Halsted and Cincinnati Children's shopped RadStream around the vendor community until Amicas picked up on it earlier this year. The hospital had neither the resources nor the inclination to productize their technology. It was developed to solve in-house problems. But the program was written so it could benefit any radiologist using any PACS, Halsted said.
The spur to its development was a workflow problem at Cincinnati Children's that may be common in radiology. Too many exams were arriving marked "STAT, call requested." The designation had lost its meaning.
"Our problem was that at especially busy times, we would have a stack of STAT requisitions that included the patient in a multiple-vehicle accident in need of urgent medical care as well as the patient who had belly pain for six months but whose physician wanted to go to lunch and couldn't until the patient was discharged," he said.
Radiologists teamed with the University of Cincinnati College of Business to develop a program that automatically prioritized cases according to medical need, then evolved the algorithm into a broad-based solution that covers paperless workflow, dynamic workflow balancing, communications, and documentation.
Last year the end product saved the hospital the equivalent of two full-time radiologists in a group of 29. The time savings was documented in a work study conducted by the business school. These savings in productivity will soon be available to other radiologists if Amicas follows through on its plans.
"We think the ability to prioritize and sift through work to put the right study at the right place at the right time, when combined with what we already have, will be a really differentiating application," McClennen said.
Comparative AI Study Shows Merits of RapidAI LVO Software in Stroke Detection
February 6th 2025The Rapid LVO AI software detected 33 percent more cases of large vessel occlusion (LVO) on computed tomography angiography (CTA) than Viz LVO AI software, according to a new comparative study presented at the International Stroke Conference (ISC).
Study: Mammography AI Leads to 29 Percent Increase in Breast Cancer Detection
February 5th 2025Use of the mammography AI software had a nearly equivalent false positive rate as unassisted radiologist interpretation and resulted in a 44 percent reduction in screen reading workload, according to findings from a randomized controlled trial involving over 105,000 women.