Automated workstation auditing could improve interpretation workflow

Article

An auditing tool that tracks computer workstation workflow has been developed at the VA Medical Center in Baltimore. It could eventually be used to help radiologists improve their soft-copy reading skills. Workstation software has typically been

An auditing tool that tracks computer workstation workflow has been developed at the VA Medical Center in Baltimore. It could eventually be used to help radiologists improve their soft-copy reading skills.

Workstation software has typically been designed by engineers with relatively little clinical input from actual users, said Dr. Kahn Siddiqui, an imaging informatics fellow at the VA Maryland Healthcare System and one of the program's developers. Although observational sessions with radiologists can be helpful, it would be more effective to create software auditing tools that track radiologist image interpretation patterns.

"Previous attempts to understand the interpretation process were manual, subjective, and biased by the 'fish bowl' phenomenon, the tendency for human behavior to change when one is aware of being watched," Siddiqui said.

The tool can track several new variables such as interpretation timeline, workstation configuration, PACS user characteristics, work list preferences, user study preferences, and exam review characteristics, as well as study layout changes during review. Working with Siddiqui were Dr. Bruce Reiner and Dr. Eliot Siegel.

Research on precisely how radiologists read in a digital environment has been scarce, and current PACS and 3D workstation designs are based on what engineers think radiologists should be able to do and how they should do it, Siddiqui said. This explains why PACS workstation design has been static for the past decade.

Adding auditing software to soft-copy workstations may eventually improve image interpretation effectiveness. The information gathered from this type of auditing tool may also shape software development and graphical user interface designs in the future. The team is working with several vendors to develop this type of automated auditing and data mining system.

By incorporating the data gathered on the way radiologists use PACS workstations, designers can shift workstation design from an engineer-centric to a radiologist-centric process and empower radiologists to determine how they perform image interpretation, according to Siddiqui.

"This is an iterative, ongoing process, and radiologists must become proactive participants if they are to take control of their own destiny," he said.

Recent Videos
What New Research Reveals About the Impact of AI and DBT Screening: An Interview with Manisha Bahl, MD
Can AI Assessment of Longitudinal MRI Scans Improve Prediction for Pediatric Glioma Recurrence?
A Closer Look at MRI-Guided Adaptive Radiotherapy for Monitoring and Treating Glioblastomas
Incorporating CT Colonography into Radiology Practice
What New Research Reveals About Computed Tomography and Radiation-Induced Cancer Risk
What New Interventional Radiology Research Reveals About Treatment for Breast Cancer Liver Metastases
New Mammography Studies Assess Image-Based AI Risk Models and Breast Arterial Calcification Detection
Can Deep Learning Provide a CT-Less Alternative for Attenuation Compensation with SPECT MPI?
Employing AI in Detecting Subdural Hematomas on Head CTs: An Interview with Jeremy Heit, MD, PhD
Pertinent Insights into the Imaging of Patients with Marfan Syndrome
Related Content
© 2025 MJH Life Sciences

All rights reserved.