Automated Extraction of Imaging and Pathology Data From Diverse Prostate Cancer Electronic Records
JCO Clinical Cancer Informatics · 2025
DOI: 10.1200/cci-25-00085 ↗Kurz gefasst
Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von John M Culnan und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Veterans Affairs Healthcare System, Massachusetts Veterans Epidemiology Research and Information Center, Boston, MA. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Electronic Health Records. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
PURPOSE To develop and validate an algorithm to extract clinically relevant data elements for prostate cancer (PCa) from prostate biopsy reports and magnetic resonance imaging (MRI) reports. PATIENTS AND METHODS MRI reports and biopsy pathology reports were extracted from a cohort of 1,360,866 patients with PCa in the VA Cancer Registry System or the VA Corporate Data Warehouse, with 155,570 patients having the relevant reports for inclusion. We hand-annotated a sample of these reports, which were used to develop a rule-based natural language processing (NLP) algorithm for extracting Gleason score, positive cores, and total cores taken during biopsy from biopsy pathology reports and Prostate Imaging Reporting and Data System (PI-RADS) score, prostate-specific antigen (PSA) density, prostate volume, and prostate dimensions from MRI reports. Our algorithm was validated on a set of 250 biopsy reports and 250 MRI reports representing 378 patients at 78 VA centers with procedures between 2004 and 2024. RESULTS Our algorithm performed well across all data elements, demonstrating high F1 scores: Gleason (96.9), PI-RADS (93.7), PSA density (99.5), prostate volume (95.7), and prostate dimensions (93.2), with the percentage of positive cores being greater than or less than 34% (88.4). Error analysis demonstrated that items missed by our algorithm were often explained by unusual or vague wording within the notes or especially complex language. CONCLUSION We developed an NLP algorithm and validated that it successfully captures salient information about data elements of interest in PCa research. Reliable extraction of these key data elements will have numerous uses for downstream research in this field.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Veterans Affairs Healthcare System, Massachusetts Veterans Epidemiology Research and Information Center, Boston, MA.
- San Francisco Veterans Affairs Medical Center, San Francisco, CA.
- Department of Urology, UCSF Helen Diller Family Comprehensive Cancer Center, San Francisco, CA.
- Department of Medicine, Boston University School of Medicine, Boston, MA.
- Department of Medicine, Johns Hopkins University, Baltimore, MD.
- Department of Epidemiology and Biostatistics, UCSF Helen Diller Family Comprehensive Cancer Center, San Francisco, CA.
ORCID-Profile: John R Bihn, Grace Lee, Robert Zwolinski, Karlynn N Dulberger, Nhan V Do, Channing J Paller, Matthew R Cooperberg, Nathanael R Fillmore
Zitieren
APA
Culnan, J. M., Goryachev, S. D., Bihn, J. R., Lee, G., Chen, D. C. R., Soloviev, O., Zwolinski, R., Dulberger, K. N., Do, N. V., Paller, C. J., Cooperberg, M. R., & Fillmore, N. R. (2025). Automated Extraction of Imaging and Pathology Data From Diverse Prostate Cancer Electronic Records. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-25-00085
Vancouver
Culnan JM, Goryachev SD, Bihn JR, Lee G, Chen DCR, Soloviev O, et al. Automated Extraction of Imaging and Pathology Data From Diverse Prostate Cancer Electronic Records. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-25-00085
BibTeX
@article{Culnan2025,
author = {Culnan, John M and Goryachev, Sergey D and Bihn, John R and Lee, Grace and Chen, Daniel C R and Soloviev, Oleg and Zwolinski, Robert and Dulberger, Karlynn N and Do, Nhan V and Paller, Channing J and Cooperberg, Matthew R and Fillmore, Nathanael R},
title = {Automated Extraction of Imaging and Pathology Data From Diverse Prostate Cancer Electronic Records},
journal = {JCO Clinical Cancer Informatics},
year = {2025},
doi = {10.1200/cci-25-00085}
}
EUVIMED