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: 2196

Machine Learning Defines the Relationship Between Structural Knee Osteoarthritis and Patient-Important Outcomes: An 8-year Study of 47,858 Knee MRIs from the Osteoarthritis Initiative (OAI)

Michael Bowes1, Katherine Kacena 2, Oras Alabas 3, Alan Brett 1, Bright Dube 4, Neil Bodick 5 and Philip G Conaghan 6, 1Imorphics, Manchester, England, United Kingdom, 2BioBridges, Wellesley Hills, 3Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, and NIHR Leeds Biomedical Research Centre, Leeds, United Kingdom, 4University of Leeds, LEEDS, England, United Kingdom, 5Flexion Therapeutics, Burlington, 6Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds & NIHR Leeds Biomedical Research Centre, Leeds, United Kingdom

Meeting: 2019 ACR/ARP Annual Meeting

Keywords: Bone, cartilage and pain, Magnetic resonance imaging (MRI), Osteoarthritis

  • Tweet
  • Email
  • Print
Session Information

Date: Tuesday, November 12, 2019

Session Title: Osteoarthritis – Clinical Poster II

Session Type: Poster Session (Tuesday)

Session Time: 9:00AM-11:00AM

Background/Purpose: Osteoarthritis (OA) is a slowly progressing disease which may be asymptomatic for many years. Therapy development has been hampered by poor understanding of both structural progression and outcomes, largely based on imprecise radiographic assessment. A statistical shape model (SSM), a form of machine learning, identified a characteristic 3D OA bone shape from MR images, enabling investigation of the relationship between structure and clinical outcomes in the largest musculoskeletal MRI study to date.

Methods: Construction of an SSM produces a “shape space,” spanned by principal components used to describe the training set of examples. Within this space, we constructed an “OA vector” passing through the mean shape of an “OA Group” (all knees KLG ≥2 at all 0, 1, 2, and 4 years), and the mean shape for a “Non-OA Group” (KLG = 0 at the same time points). Distances along the OA vector are normalized to a z-score (“B-score”), with the mean shape of the Non-OA Group for each sex represented as the OA vector origin; 1 unit represents 1 SD of the Non-OA Group along the OA vector (+ve values toward the OA Group). Each femur bone shape was projected orthogonally onto the OA vector to specify the corresponding B-score. Representative examples of the femur bone shape are shown in Fig. 1.

The B-score was automatically measured at multiple time points up to 8 years in the OAI (9,433 knees; 5,031 without OA; 47,858 MRI images). WOMAC-A (pain) on the 20-unit scale was dichotomized, first by presence of moderate or higher pain (score ≥4) and then again by presence of severe pain (score ≥8).  Knee Replacement Surgery (KRS) was defined as having either total or partial knee arthroplasty within the follow-up period, adjudicated using post-surgery radiographs. Logistic regression analysis was performed modeling any reporting of pain or KRS at any single timepoint over the follow-up period for an individual knee by baseline B-score. This logistic regression was then repeated using baseline age.

Results: B-score was strongly associated with current and future pain; Fig. 2 displays the enhanced predictive power of B-score compared to age. Males and females were analyzed separately. However, an additional model combining both sexes was produced: for baseline B‑scores of 0 and 6 (incipient and advanced disease), future risk of painful knee within an average follow-up of 5 years was 36.0% (95% CI: 34.9 to 37.1) and 75.1% (72.6 to 77.5), respectively. Males had 210 KRS, females had 318. Although both baseline B-score and baseline age were both statistically significant at P< 0.001, Fig. 3 displays the enhanced predictive power of B-score compared to age for KRS. Using a combined model, future risk of KRS at B-scores of 0 and 6 was 2.3% (2.0 to 2.7) and 36.7% (32.5 to 41.1), respectively. Age had minimal utility in predicting pain or KRS.

Conclusion: By providing a continuous metric for OA, machine learning applied to a large dataset has for the first time demonstrated simple and strong relationships between bone shape and the current and future clinical outcomes.  B-score provides accurate stratification for interventions and improved personalized assessment and is analogous to the T-score developed for osteoporosis.

Figure 1. Change in Bone Shape with Increasing B-Score. Figure shows change in shape for the anterior femur -top row- and posterior femur -bottom row-, for various B-scores. Red indicates where there is an increase in size, blue indicates decrease in size; scale shows percentage in local area size change.

Figure 2. Knee Pain by B-Score for A- Males and B- Females and by Age for C- Males and D- Females. Moderate or more pain was defined as WOMAC-A -pain- ≥4 on the 20-unit scale; severe pain was defined as WOMAC-A -pain- ≥8 on the 20-unit scale. The average follow-up was 5 years. Vertical lines on B-score axis display Non-OA Range.

Figure 3. Risk of Knee Replacement Surgery by B-Score for A- Males and B- Females and by Age for C- Males and D- Females. Vertical lines on B-score axis display Non-OA B-score range.


Disclosure: M. Bowes, Imorphics (Stryker), 3, OrthoTrophix, 9; K. Kacena, Flexion Therapeutics, 5; O. Alabas, None; A. Brett, OrthoTrophix, 9, OrthoTrophix, Inc, 9; B. Dube, None; N. Bodick, Flexion Therapeutics, 3, 4; P. Conaghan, Abbvie, 5, 8, AbbVie, 5, 8, AstraZeneca, 5, 8, BMS, 5, 8, Bristol Myers Squibb, 5, 8, Eli Lilly, 8, EMD, 5, EMD Serono, 5, EMD Serono Research and Development Institute, Inc., 5, 8, Flexion, 5, 8, Flexion Therapeutics, 5, 8, Galapagos, 5, 8, Glaxo Smith Kline, 5, GlaxoSmithKline, 5, 8, Lilly, 8, Medivir, 5, 8, Novartis, 5, 8, Pfizer, 5, 8, Roche, 5, 8, Samumed, 5, 8, Serono, 5, Stryker, 5, 8.

To cite this abstract in AMA style:

Bowes M, Kacena K, Alabas O, Brett A, Dube B, Bodick N, Conaghan P. Machine Learning Defines the Relationship Between Structural Knee Osteoarthritis and Patient-Important Outcomes: An 8-year Study of 47,858 Knee MRIs from the Osteoarthritis Initiative (OAI) [abstract]. Arthritis Rheumatol. 2019; 71 (suppl 10). https://acrabstracts.org/abstract/machine-learning-defines-the-relationship-between-structural-knee-osteoarthritis-and-patient-important-outcomes-an-8-year-study-of-47858-knee-mris-from-the-osteoarthritis-initiative-oai/. Accessed January 27, 2023.
  • Tweet
  • Email
  • Print

« Back to 2019 ACR/ARP Annual Meeting

ACR Meeting Abstracts - https://acrabstracts.org/abstract/machine-learning-defines-the-relationship-between-structural-knee-osteoarthritis-and-patient-important-outcomes-an-8-year-study-of-47858-knee-mris-from-the-osteoarthritis-initiative-oai/

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