ACR Meeting Abstracts

ACR Meeting Abstracts

  • Home
  • Meetings Archive
    • ACR Convergence 2022
    • ACR Convergence 2021
    • ACR Convergence 2020
    • 2020 ACR/ARP PRSYM
    • 2019 ACR/ARP Annual Meeting
    • 2018 ACR/ARHP Annual Meeting
    • 2017-2009 Meetings
    • Download Abstracts
  • Keyword Index
  • Advanced Search
  • Your Favorites
    • Favorites
    • Login
    • View and print all favorites
    • Clear all your favorites
  • Meeting Resource Center

Abstract Number: 0160

Identifying Erosive Disease from Radiology Reports of Veterans with Inflammatory Arthritis with Natural Language Processing

Gopi Penmetsa1, Jessica Walsh2, Shaobo Pei3, Brian Sauer4, Kevin Douglas5, Jodi Walker5, Jerry Clewell6 and Bingjian Feng1, 1Salt Lake City Veteran Affairs and University of Utah Medical Centers, Salt Lake City, UT, 2Salt Lake City Veteran Affairs Medical Center (VAMC)/University of Utah Hospital, Salt Lake City, UT, 3VAMC, Salt Lake City, SLC, 4Veterans Affairs Medical Center, Salt Lake City, UT, 5AbbVie Inc., North Chicago, IL, 6Abbvie Inc, North Chicago, IL

Meeting: ACR Convergence 2021

Keywords: Erosions, radiography

  • Tweet
  • Email
  • Print
Session Information

Date: Saturday, November 6, 2021

Session Title: Imaging of Rheumatic Diseases Poster (0149–0182)

Session Type: Poster Session A

Session Time: 8:30AM-10:30AM

Background/Purpose: The presence of erosive disease influences diagnosis, management, & prognosis in inflammatory arthritis (IA). Inflammatory arthritis research in large datasets is limited by a lack of methods for identifying erosions.

The aim of our project was to develop methods for identifying articular erosions in radiology reports from veterans with IA.

Methods: Included veterans had ≥2 ICD codes for ankylosing spondylitis (AS), psoriatic arthritis (PsA), or rheumatoid arthritis (RA) between 2005- 2019, in Veterans Affairs Corporate Data Warehouse. Chart review & annotation of radiology notes produced the reference standard, & identified erosion terms that informed classification rule development. A rule-based natural language processing (NLP) model was created & revised in training snippets. The NLP method was validated in an independent reference sample of IA patients at the snippet & patient levels.

Results: In 168,667 veterans with inflammatory arthritis, the mean age was 63.1 & 90.3% were male. Method development involved radiology note & erosion term selection, rule development, NLP model building, & method validation. The NLP model accuracy was more than 95% at the snippet level & 90.0% at the patient level, for all IA patients.

Conclusion: The methods accurately identify erosions from radiology reports of veterans with inflammatory arthritis. They may facilitate a broad range of research involving cohort identification & disease severity stratification.

pt= patient. ^Snippets include text containing 30 words before & after meaningful terms

Patient level classifications involve assigning rules for classifying patients with conflicting snippet classifications (in subset of patients with >1 snippet)
**Included 20 RA patients, 20 PsA patients, 20 AS patients.

Accuracy of the NLP methods


Disclosures: G. Penmetsa, None; J. Walsh, AbbVie, 2, 5, Merck, 2, 5, Pfizer, 2, 5, UCB, 2, 5, Eli Lilly, 1, 2, Novartis, 2, 5, Amgen, 2, 5; S. Pei, None; B. Sauer, Abbvie, 12, I have been an investigator on research contracts supported by Abbvie.; K. Douglas, AbbVie, 3, 11; J. Walker, Abbvie, 3; J. Clewell, Abbvie Inc, 3, 11; B. Feng, Ambry Genetics, 9, Pfizer, 5, Regeneron, 5, Astra Zeneca, 5.

To cite this abstract in AMA style:

Penmetsa G, Walsh J, Pei S, Sauer B, Douglas K, Walker J, Clewell J, Feng B. Identifying Erosive Disease from Radiology Reports of Veterans with Inflammatory Arthritis with Natural Language Processing [abstract]. Arthritis Rheumatol. 2021; 73 (suppl 9). https://acrabstracts.org/abstract/identifying-erosive-disease-from-radiology-reports-of-veterans-with-inflammatory-arthritis-with-natural-language-processing/. Accessed January 28, 2023.
  • Tweet
  • Email
  • Print

« Back to ACR Convergence 2021

ACR Meeting Abstracts - https://acrabstracts.org/abstract/identifying-erosive-disease-from-radiology-reports-of-veterans-with-inflammatory-arthritis-with-natural-language-processing/

Advanced Search

Your Favorites

You can save and print a list of your favorite abstracts during your browser session by clicking the “Favorite” button at the bottom of any abstract. View your favorites »

ACR Pediatric Rheumatology Symposium 2020

© COPYRIGHT 2023 AMERICAN COLLEGE OF RHEUMATOLOGY

Wiley

  • Home
  • Meetings Archive
  • Advanced Search
  • Meeting Resource Center
  • Online Journal
  • Privacy Policy
  • Permissions Policies
  • Cookie Preferences