Data-mining tool helps to justify costly imaging tests

A new data-mining tool may justify the use of pricey imaging procedures.

The tool, RadLex Enhanced Automated Leximer Mining (REALM), used in conjunction with the clinical-decision support system at Massachusetts General Hospital, looks at radiology data in conjunction with an algorithm and reports similar patient characteristics, according to AuntMinnie. The hope is that such information will help to justify the use of costly imaging tests. REALM was presented at the Society for Imaging Informatics in Medicine's annual meeting last week.

The system's first test involved researchers inputting the term "subarachnoid hemorrhage" in looking at CT and MRI exams of the head. Out of more than 1,000 reports, REALM correctly identified that condition, or a related condition, roughly 96 percent of the time. According to AuntMinnie, "the positive predictive value...was 99.89 percent, and the negative predictive value was 63.6 percent." 

REALM co-researcher Thomas Schultz, chief engineer of enterprise medical imaging at Mass General, was enthusiastic about the tool's role in clinical-decision support. 

"When a patient is experiencing fatigue or has nonspecific symptoms, how do we evaluate them?" Schultz said, according to AuntMinnie. "Our hope is that REALM research will enable physicians to review the historic findings of patients with similar symptoms based on a specific diagnostic imaging exam or several different exams." 

For more information:
- read this AuntMinnie article