RADEX: a rule-based clinical and radiology data extraction tool demonstrated on thyroid ultrasound reports
Question Radiology reports contain vital information that is buried in unstructured free-text fields. Can we extract this information effectively for research and audit applications? Findings A rule-based RAdiology Data Extraction tool (RADEX) is described and used to classify fourteen key findings from thyroid ultrasound reports with sensitivity and specificity > 0.95. Clinical relevance RADEX offers clinicians and researchers a time-saving tool to accelerate structured data collection. This practical approach prioritises transparency, repeatability, and usability, enabling new insights into improved patient care.
Authors
- James R. McLaughlan (ORCID: https://orcid.org/0000-0001-5795-4372)
- James H. Chandler (ORCID: https://orcid.org/0000-0001-9232-4966)
- Tze Min Wah (ORCID: https://orcid.org/0000-0001-5670-5454)
- Shishir Karthik
- Helen Ng (ORCID: https://orcid.org/0000-0002-7465-2090)
- L.N. Howell (ORCID: https://orcid.org/0000-0003-4807-4087)
- A. Zarei (ORCID: https://orcid.org/0000-0002-3364-5759)
- Zara Court
Institutions
- University of Leeds (GB)
- Leeds Teaching Hospitals NHS Trust (GB)
- St James's University Hospital (GB)
Publication Details
- Journal
- European Radiology
- Published
- 2025-02-13
- DOI
- https://doi.org/10.1007/s00330-025-11416-4
- Citations
- 5
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 12.40
Funders
- Engineering and Physical Sciences Research Council