Most radiologists believe report automation has a significant impact on the quality of their radiology reports, according to a new study published in Current Problems in Diagnostic Radiology. Automation has become more common, the authors explained, due to more radiology departments going “all-digital” and the integration of RIS, PACS and reporting systems.
Researchers surveyed 13 radiologists and nine radiology residents from the same facility about the effect of automatically populated reports. Respondents had experience using systems both with and without automation. Overall, 95 percent of respondents had a positive response when asked if report automation has an impact on time savings.
“Report automation allows the radiologist to spend more time per examination reviewing the images and synthesizing findings into a clinically relevant impression, rather than on dictating automatable noninterpretive but required fields,” wrote Mark D. Kovacs, MD, with the department of radiology at the Medical University of South Carolina in Charleston, and colleagues.
In addition, 91 percent of respondents had a positive response when asked if automation has an impact on dictation accuracy, and 82 percent had a positive response when asked if automation has an impact on fatigue. Three respondents did answer that automation “did not affect” fatigue.
The authors also conducted a “timing experiment,” asking six radiologists and three radiology residents to dictate reports for mock exams using voice recognition. Overall, the average time per day each radiologist saved from automation was found to be 68 minutes.
Kovacs and colleagues noted that their study did have limitations. The timing experiment “represented only a gross estimate of time spent dictating noninterpretive fields at sites without fully integrated reporting,” for example. The authors also noted that radiologists from only one institution were surveyed. “A questionnaire with broader outreach would also help improve on the qualitative assessment in the future,” they wrote.