The Efficacy of a Named Entity Recognition AI Model for Identifying Incidental Pulmonary Nodules in CT Reports
Canadian Association of Radiologists Journal · 2025
DOI: 10.1177/08465371241266785 ↗Kurz gefasst
Fachartikel in der Zeitschrift Canadian Association of Radiologists Journal, 2025. Verfasst von Alireza Mojibian und 7 weiteren Autor:innen. Beteiligte Einrichtung: Sapien Machine Learning Corporation (SapienML), Vancouver, BC, Canada. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Lung Neoplasms, Solitary Pulmonary Nodule, Sensitivity and Specificity. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Purpose
This study evaluates the efficacy of a commercial medical Named Entity Recognition (NER) model combined with a post-processing protocol in identifying incidental pulmonary nodules from CT reports.
Methods
We analyzed 9165 anonymized CT reports and classified them into 3 categories: no nodules, nodules present, and nodules >6 mm. For each report, a generic medical NER model annotated entities and their relations, which were then filtered through inclusion/exclusion criteria selected to identify pulmonary nodules. Ground truth was established by manual review. To better understand the relationship between model performance and nodule prevalence, a subset of the data was programmatically balanced to equalize the number of reports in each class category.
Results
In the unbalanced subset of the data, the model achieved a sensitivity of 97%, specificity of 99%, and accuracy of 99% in detecting pulmonary nodules mentioned in the reports. For nodules >6 mm, sensitivity was 95%, specificity was 100%, and accuracy was 100%. In the balanced subset of the data, sensitivity was 99%, specificity 96%, and accuracy 97% for nodule detection; for larger nodules, sensitivity was 94%, specificity 99%, and accuracy 98%.
Conclusions
The NER model demonstrated high sensitivity and specificity in detecting pulmonary nodules reported in CT scans, including those >6 mm which are potentially clinically significant. The results were consistent across both unbalanced and balanced datasets indicating that the model performance is independent of nodule prevalence. Implementing this technology in hospital systems could automate the identification of at-risk patients, ensuring timely follow-up and potentially reducing missed or late-stage cancer diagnoses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Sapien Machine Learning Corporation (SapienML), Vancouver, BC, Canada.
- Radiology Department, Brampton Civic Hospital, Brampton, ON, Canada.
- Faculty of Medicine - Medical Imaging, University of Toronto, Toronto, ON, Canada.
- Schulich School of Medicine & Dentistry - University of Western Ontario, London, On, Canada.
- Faculty of Medicine, University of British Columbia, Vancouver, BC, Canada.
- BC Cancer Agency, Provincial Health Services Authority, Vancouver, BC, Canada.
ORCID-Profile: Jeff Jaskolka, William Parker
Zitieren
APA
Mojibian, A., Jaskolka, J., Ching, G., Lee, B., Myers, R., Devine, C., Nicolaou, S., & Parker, W. (2025). The Efficacy of a Named Entity Recognition AI Model for Identifying Incidental Pulmonary Nodules in CT Reports. Canadian Association of Radiologists Journal. https://doi.org/10.1177/08465371241266785
Vancouver
Mojibian A, Jaskolka J, Ching G, Lee B, Myers R, Devine C, et al. The Efficacy of a Named Entity Recognition AI Model for Identifying Incidental Pulmonary Nodules in CT Reports. Canadian Association of Radiologists Journal. 2025. doi:10.1177/08465371241266785
BibTeX
@article{Mojibian2025,
author = {Mojibian, Alireza and Jaskolka, Jeff and Ching, Geoffrey and Lee, Brian and Myers, Renelle and Devine, Chloe and Nicolaou, Savvas and Parker, William},
title = {The Efficacy of a Named Entity Recognition AI Model for Identifying Incidental Pulmonary Nodules in CT Reports},
journal = {Canadian Association of Radiologists Journal},
year = {2025},
doi = {10.1177/08465371241266785}
}
EUVIMED