With a mix of social engineering and Web-based dashboard management, the radiology department at the University of Maryland Medical System has reduced overall report verification times for its radiologists.
With a mix of social engineering and Web-based dashboard management, the radiology department at the University of Maryland Medical System 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 Maryland.
After two weeks of implementation, the system had reduced 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, he said during a scientific session at the RSNA meeting. To reduce both verification time 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 on to 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 represent Big Brother watching over their every move, according to Nagy. But the group developed a metric that, when represented as a cumulative Pareto, 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 people," Nagy said.
After a few weeks, the physicians became reliant 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, according to Nagy.
The system has now been in place for over nine months. While there has been some drift in the verification time reduction, turnaround still averages about 16.4 hours, half of what it had been.
For more online information, visit Diagnostic Imaging's RSNA Webcast.
New Study Examines Short-Term Consistency of Large Language Models in Radiology
November 22nd 2024While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
FDA Grants Expanded 510(k) Clearance for Xenoview 3T MRI Chest Coil in GE HealthCare MRI Platforms
November 21st 2024Utilized in conjunction with hyperpolarized Xenon-129 for the assessment of lung ventilation, the chest coil can now be employed in the Signa Premier and Discovery MR750 3T MRI systems.
FDA Clears AI-Powered Ultrasound Software for Cardiac Amyloidosis Detection
November 20th 2024The AI-enabled EchoGo® Amyloidosis software for echocardiography has reportedly demonstrated an 84.5 percent sensitivity rate for diagnosing cardiac amyloidosis in heart failure patients 65 years of age and older.