Data mining of structured radiology reports yields advantageous insights
Datapoints contained in structured radiology reports can be readily mined to guide decisions around long-term clinical, business and population-health aims, according to a study conducted in Germany and published in Abdominal Radiology [1].
The project examined the approach as applied to a cohort of patients with kidney stones, but the authors suggest their technique is likely generalizable to various other diagnoses.
Among the decisions and planning that such mined data might inform, the team names quality assurance, radiation protection, and scientific and economic investigations.
“These possibilities add to the long list of advantages of structured reporting over free-text reporting and underline the necessity of structured reporting usage,” the authors write before acknowledging one significant caveat:
Structured reporting in routine practice “may be elaborate since it requires radiologists to adapt to reporting templates that have to be filled using a mouse and keyboard” rather than a dictation system.
For the study, interventional radiologist Tobias Jorg and colleagues at Johannes Gutenberg University Mainz investigated numerous aspects of kidney stones by mining data from the structured radiology reports of 2,028 patients. All underwent abdominopelvic CT for suspected urolithiasis, a common condition in which stones move from the kidneys to the ureters, the bladder and, finally, the urethra.
Some 72% of the cohort proved positive for urolithiasis, a figure for which the authors credit the astuteness of the referring clinicians. The sex distribution was 2.3 men for each woman, the median age was 50, and the median stone count was one.
The researchers drew additional data from the structured reports on stone size and density, and they found these characteristics had no impact on the degree to which stones obstructed urine flow.
Jorg and co-authors remark that, by their study, structured report-based data mining has proven its utility—at least in one fairly common abdominopelvic diagnosis—as “a simple method with which to obtain important epidemiologic data and disease characteristics.”
What’s more, the method is adaptable ...
“without much expenditure of time or resources, provided a detailed structured reporting template has been consistently used for reporting beforehand. It adds a valuable overview of the patient population, including detailed information on the distribution and characteristics of renal and ureteral calculi, which is helpful for both radiologists and clinical referrers.”
The study is posted in full for free.
Mary joined TriMed Media in 2003. She was the founding editor and editorial director of Health Imaging, Cardiovascular Business, Molecular Imaging Insight and CMIO, now known as Clinical Innovation + Technology. Prior to TriMed, Mary was the editorial director of HealthTech Publishing Company, where she had worked since 1991. While there, she oversaw four magazines and related online media, and piloted the launch of two magazines and websites. Mary holds a master’s in journalism from Syracuse University. She lives in East Greenwich, R.I., and when not working, she is usually running around after her family, taking photos or cooking.