Physicians at Stanford University Medical Center actually enjoy hunting down appropriate teaching and research cases. The center has developed and implemented a data warehouse that has reduced the search time and increased the number of cases found.
Physicians at Stanford University Medical Center actually enjoy hunting down appropriate teaching and research cases. The center has developed and implemented a data warehouse that has reduced the search time and increased the number of cases found.
"There is immense value in clinical data repositories," said Dr. Daniel L. Rubin, informatics research scientist at the medical center.
The data warehouse, dubbed Radbank, was developed using open source tools. It brings together more than 1.8 million radiological reports and 270,000 pathology reports. Rubin described Radbank at the 2004 RSNA meeting.
To evaluate Radbank's effectiveness in retrieving teaching files, researchers compared the database with manual searches for such studies as porcelain gallbladder, nephrocalcinosis, and pathologically confirmed viral esophagitis cases.
Physicians accessing the Radbank database located 12 to 13 times as many teaching cases in a fraction of the time needed for manual searching, according to the investigators. In one instance, a radiologist manually searching for pathologically confirmed viral esophagitis found no cases compared with 55 cases discovered by Radbank.
Rubin and colleagues also evaluated the use Radbank in identifying cohorts for two research studies:
Regarding these research-related tasks, Radbank found four to five times as many cases as manual searching. Because researchers using Radbank had access to pathologic cases, they discovered that 75 of the RPOC cases had pathologic confirmation. The radiologists relegated to manual searching abandoned the attempt to correlate cases to pathology after only three cases.
Radiologists engaged in manual searches needed days to weeks to complete their searches, according to the study. Radbank queries took only minutes to write and seconds to run.
Further work is being done on making Radbank more user-friendly, by moving toward a Web-based interface and away from an SQL-query format, Rubin said.
For more information from the online Diagnostic Imaging archives:
Integrated implementation revamps information storage
PACS archive evolves to meet enterprise needs
New standards improve interhospital dialogue
Can MRI-Based AI Bolster Biopsy Decision-Making in PI-RADS 3 Cases?
December 9th 2024In patients with PI-RADS 3 lesion assessments, the combination of AI and prostate-specific antigen density (PSAD) level achieved a 78 percent sensitivity and 93 percent negative predictive value for clinically significant prostate cancer (csPCa), according to research presented at the Radiological Society of North American (RSNA) conference.