Query tool analyzes radiology report database

Article

Using a new query tool, researchers at the University of Pennsylvania have found that the use of comparison studies by radiologists increases with the availability of PACS. The tool probed a database of radiology report text using structured query language (SQL).

Using a new query tool, researchers at the University of Pennsylvania have found that the use of comparison studies by radiologists increases with the availability of PACS. The tool probed a database of radiology report text using structured query language (SQL).

"Our results show that SQL investigations of text reports can achieve greater than 95% accuracy in determining the utilization of prior images," said Dr. Curtis P. Langlotz, an associate professor of radiology at Penn. "We found a trend toward increasing utilization of priors over time, possibly because the adoption of PACS in our practice has made prior exams more accessible."

Langlotz said this topic is important because the use of prior exams in routine clinical practice is thought to improve the quality of image interpretations, yet data to support this view are limited. Absent this information, radiologists don't know how much effort and expense to put into obtaining comparison images.

"We found at our institution comparison exams were mentioned in radiology reports an average of 39% of the time over the past eight years," Langlotz said.

The study also found significant variability in the mention of comparisons, ranging from 77% to 4%. The highest rates appeared in mammography, distantly followed by PET and computed radiology. Among the lowest rates were fluoroscopy studies.

The SQL tool searched for common phrases in free text reports that indicated whether comparison studies were used, not available, or not mentioned.

The queries were used on a database of 1.8 million reports. They found that comparisons were made to prior images in 38.69% of the reports, were unavailable in 18.79%, and were not mentioned in 42.52%.

Langlotz said the queries can be used by other institutions to determine the impact of PACS on their utilization of priors and can be modified to mine other data.

"It is also possible they can be applied toward developing a research PACS, a search engine specifically geared for querying radiology reports that could provide relatively accurate answers to research questions," he said.

Recent Videos
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
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
Related Content
© 2025 MJH Life Sciences

All rights reserved.