How custom worklists can lead to faster MRI interpretation times

Analytics-driven worklists can help entire groups of radiologists achieve faster MRI interpretation times, according to new research published in the American Journal of Roentgenology.

“Imaging interpretation is just one part of a radiologist's many responsibilities, which can include clinical consultations, resident education, and other tasks such as determining appropriate study protocols,” wrote Tony T. Wong, MD, department of radiology at New York-Presbyterian/Columbia University Medical Center in New York City, and colleagues. “Many efforts have been made to improve efficiency at various levels of the workflow from the initial referring physician order request to billing. However, strategies that decrease the time spent interpreting studies have been more limited.”

The authors first studied the interpretation times for all MRI studies performed by three musculoskeletal fellowship-trained radiologists in 2016. Specific worklists were then designed for each specialist, taking their 2016 interpretation times into account.

“In our practice, two readers are assigned to MRI each workday,” the authors explained. “Two worklists were therefore generated for each reader to account for all possible pairings (readers one and two, two and three, and one and three). They were structured so that each reader would interpret body parts in an order from their own fastest to slowest speed relative to their counterpart.”

The radiologists followed these worklists for a trial period lasting seven consecutive days. Overall, the total interpretation time for the three specialists decreased by a mean of 29.5 minutes per day during the seven-day trial. One reader interpreted wrist studies 10 minutes slower and another reader interpreted cervical spine studies 9 minutes faster, but no other significant changes in reading times were noted in the research.

“Our results show that worklists organized by relative individual interpretation times can decrease the overall group interpretation time in a multi-reader setting,” the authors noted.

Wong et al. also wrote that the study’s primary outcome was speed, not quality. This means more research is still required to fully grasp the impact of these worklists.

“Faster report turnaround time does not mean reports of better, or lesser, quality,” they wrote. “Readers in our study were instructed to interpret all studies as they normally would. Although this instruction theoretically should ensure that the quality of any individual report would not be altered, we did not specifically assess for changes in quality, which would be important to study before implementing sustained use of such worklists to ensure that quality is not being sacrificed.”