Digital dashboards track workflow, speed reporting

The digital era that has changed the face of radiology has brought with it a plethora of data to manage. Increasingly, departments are turning to custom digital dashboards to keep track of workflow and the many data systems that now pepper radiology departments.

With a mix of social engineering and Web-based dashboard management, the radiology department at the University of Maryland Medical Center in Baltimore has reduced overall report verification times for its radiologists.

Even before a report sign-off management system had been implemented, turnaround times decreased as news spread through the department that performance would be monitored, said Paul G. Nagy, Ph.D., an assistant professor of radiology at UMMC, at the 2005 RSNA meeting. Only two weeks after implementation, the system had already reduced radiology report verification times from 32.9 hours to 11.8 hours.

Speech recognition has been touted as a way to improve report turnaround, but it's not for everybody, Nagy said. Rather than wait for speech recognition to improve, the department chose to optimize its current report workflow. To reduce both verification times for report sign-off and fatigue levels in radiologists, the department developed an in-house system for workflow data management.

The program was developed in the Python programming language. It logs onto the department's RIS four times daily and twice during the weekends to pull all unsigned summary reports. The appropriate radiologists are then paged and e-mailed to notify them that a report is awaiting their sign-off.

When the system was first announced, some radiologists expressed concern that it would feel like Big Brother watching over their every move, according to Nagy. But the group developed a metric that, when represented as cumulative, would focus on the few laggards responsible for the bulk of the delays.

"It's the law of Pareto-80% of the problem comes from 20% of the people," Nagy said.

After a few weeks, the physicians started relying on the tool to alert them to reports that needed their attention. They admitted to liking the tool and noted that it was far less intrusive than speech recognition, Nagy said.

The system has now been in place for almost a year. While there has been some drift in the verification time reduction, turnaround still averages about 16.4 hours, half of what it had been.

At the University of Pittsburgh Medical Center, the radiology department has also turned to digital dashboard management. Dr. Matthew B. Morgan, a radiology resident at UPMC, published a description of the university's digital dashboard in the October online issue of the Journal of Digital Imaging.

"We started a couple of years ago with keeping a count of unsigned reports and integrating a 'ticker' into the user's PACS work list. It became apparent that, with the increasing complexity of digital radiology, there were many other ways in which a dashboard could help radiologists keep track of workflow and priority tasks," Morgan said.

The group currently uses its dashboard to track several workflow metrics. It divides the dashboard tasks into system-level alerts, division-level alerts, and user-level alerts, allowing the system to tailor the messages by user and helping to filter out the noise, according to Morgan.

As is the case for many large academic centers that use systems from multiple vendors and face needs not completely met by any vendor's PACS solution, UPMC developed its dashboard technology in-house.

"We have what our director of radiology informatics, Dr. Paul Chang, refers to as an 'appropriately idiosyncratic' workflow. Since no single vendor's product would allow us to view the state of our many systems, we realized we needed a metasystem to monitor all of the other systems," Morgan said.

To achieve the kind of functionality they needed, the researchers turned to a radiologist with a strong informatics background to direct a team of local developers. The group has used the dashboard to assure timely exam interpretation, reduce report turnaround time, and improve intradepartmental communication.

As an example, Morgan noted that the dashboard monitors the user's unsigned reports, alerts the user when the number exceeds a specified threshold, and then provides a direct link to the report signing application. The dashboard can also be used to alert the division if an exam falls through the cracks and does not get dictated, helping to eliminate unreported exams.

Morgan and colleagues are currently studying quantitatively how the dashboard improves the workflow processes. Research at UPMC was supported by a grant from the Society for Computer Applications in Radiology.

"The key to success was having the dashboard integrated into the PACS itself. This way, users are kept updated while they go about their normal routine," Morgan said.