Radiologists may be able to decrease the time they spend looking away from images by funneling all of their reporting system interactions through a microphone rather than a separate report interface, according to researchers at the University of Florida School of Medicine.
Radiologists may be able to decrease the time they spend looking away from images by funneling all of their reporting system interactions through a microphone rather than a separate report interface, according to researchers at the University of Florida School of Medicine.
Speech recognition systems are expected to converge with point-and-click menu-driven interfaces in the near future to form advanced computerized transcription and reporting systems. This trend raises the red flag for some radiologists.
"Any complex reporting system generally requires the radiologist to look at a computer interface that is separate from the images themselves," said Dr. Christopher Lee Sistrom, an assistant professor of radiology at the university.
This so-called look-away time can amount to a major distraction.
"It is well known that radiologist efficiency is decreased with these systems by as much as a factor of two," Sistrom said.
Sistrom proposes instead a concept he calls the "talking template." Most, if not all, interaction between a report generating system and the radiologist would be conducted through the microphone. The template would free the radiologist to view and manipulate the image, supporting the primary goal of efficient, timely, and error-free clinical communication (J Digit Imaging 2005 Jun 2;[Epub ahead of print]).
Cognitive synergy is created in the process of looking at an image while describing it at the same time, according to Sistrom. This can be important in the search and synthesis of radiology findings.
"This synergy would be lost in computerized reporting, since one can only look at the image or the reporting interface at any one time," he said.
The essence of the talking template is for all feedback about navigation through the document to be in the form of spoken cues, with little need to look away to the reporting interface during primary dictation of the case.
Radiologists could complete entire cases and even batches of studies in a single sitting, while deferring editing, correcting, and signing reports to a later time, he said.
As a corollary effect, radiologists would dictate in familiar narrative text and transfer the task of assigning codes and/or categorical choices to natural language processing on the completed reports.
Sistrom said he is not inclined to develop or market a talking template product.
"My purpose in writing the paper was to stimulate interest in the concept," he said. "Anyone willing to implement it is welcome to take the idea and run."
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.