A “digital dashboard” helps radiologists quickly identify workflow trouble spots and could improve image management processes, according to researchers from the University of Pittsburgh Medical Center.
A "digital dashboard" helps radiologists quickly identify workflow trouble spots and could improve image management processes, according to researchers from the University of Pittsburgh Medical Center.
Managing workflow in a film environment was a simple process: It was fairly easy to look around a film room and find a stack of films that needed to be interpreted. In today's digital environment, however, the obvious cues for workflow have disappeared and have been replaced by a system that is more complex and more amorphous. It is not always clear in a digital setting which are stat reads from emergency rooms and which are less urgent, which reports have been interpreted and not signed, and which reading sites are overloaded and which are underused.
What's needed is a system that summarizes key metrics and optimizes the user's ability to make decisions. "Dashboards" that monitor systems - like the dashboard in a car - are common in other businesses but have not widely affected radiology workflow, said Dr. Matthew B. Morgan, lead researcher in the Thursday presentation.
The digital dashboards take over the task of monitoring operations using preset rules. Rather than having to frequently check the status of particular studies, radiologists can rely on a digital dashboard to alert them when action is needed.
Such a system has been under development at UPMC since January and continues to be refined, Morgan said. Although the experiment is still in an early stage, staff are already seeing results from the feature that monitors unsigned reports.
Among the other features the system could provide:
For more news from the Society for Computer Applications in Radiology meeting, go to the SCAR Webcast.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.