Proposing New RadLex Terms by Analyzing Free-Text Mammography Reports

Journal Article · Mon Oct 15 04:00:00 EDT 2018 · Journal of Digital Imaging (Online)

DOI:https://doi.org/10.1007/S10278-018-0064-0· OSTI ID:22795588

Bulu, Hakan ^[1]; Lee, Janie M. ^[2]; Burnside, Elizabeth S. ^[3]; Rubin, Daniel L. ^[1]

---

1. Stanford University, Department of Radiology and Department of Biomedical Data Science, Medical School Office Building (MSOB) (United States)
2. University of Washington, Department of Radiology, Seattle Cancer Care Alliance (United States)
3. University of Wisconsin School of Medicine and Public Health, Department of Radiology, E3/311 Clinical Science Center (United States)

After years of development, the RadLex terminology contains a large set of controlled terms for the radiology domain, but gaps still exist. We developed a data-driven approach to discover new terms for RadLex by mining a large corpus of radiology reports using natural language processing (NLP) methods. Our system, developed for mammography, discovers new candidate terms by analyzing noun phrases in free-text reports to extend the mammography part of RadLex. Our NLP system extracts noun phrases from free-text mammography reports and classifies these noun phrases as “Has Candidate RadLex Term” or “Does Not Have Candidate RadLex Term.” We tested the performance of our algorithm using 100 free-text mammography reports. An expert radiologist determined the true positive and true negative RadLex candidate terms. We calculated precision/positive predictive value and recall/sensitivity metrics to judge the system’s performance. Finally, to identify new candidate terms for enhancing RadLex, we applied our NLP method to 270,540 free-text mammography reports obtained from three academic institutions. Our method demonstrated precision/positive predictive value of 0.77 (159/206 terms) and a recall/sensitivity of 0.94 (159/170 terms). The overall accuracy of the system is 0.80 (235/293 terms). When we ran our system on the set of 270,540 reports, it found 31,800 unique noun phrases that are potential candidates for RadLex. Our data-driven approach to mining radiology reports can identify new candidate terms for expanding the breast imaging lexicon portion of RadLex and may be a useful approach for discovering new candidate terms from other radiology domains.

• OSTI ID: 22795588
• Journal Information: Journal of Digital Imaging (Online), Journal Name: Journal of Digital Imaging (Online) Journal Issue: 5 Vol. 31; ISSN 1618-727X
• Country of Publication: United States
• Language: English

Related Subjects

62 RADIOLOGY AND NUCLEAR MEDICINE
ACCURACY
ALGORITHMS
BIOMEDICAL RADIOGRAPHY
MAMMARY GLANDS
PROGRAMMING LANGUAGES
SENSITIVITY