ACR Meeting Abstracts

ACR Meeting Abstracts

  • Meetings
    • ACR Convergence 2024
    • ACR Convergence 2023
    • 2023 ACR/ARP PRSYM
    • ACR Convergence 2022
    • ACR Convergence 2021
    • ACR Convergence 2020
    • 2020 ACR/ARP PRSYM
    • 2019 ACR/ARP Annual Meeting
    • 2018-2009 Meetings
    • Download Abstracts
  • Keyword Index
  • Advanced Search
  • Your Favorites
    • Favorites
    • Login
    • View and print all favorites
    • Clear all your favorites
  • ACR Meetings

Abstract Number: 2355

Efficacy of Risankizumab Across Distinct PsA Phenotypes Identified with Machine Learning Analytics Using Data from Biologic DMARD-Naive Patients in Two Phase 3 Clinical Trials

Laure Gossec1, Andra Balanescu2, Maria Antonietta D'Agostino3, Alexis Ogdie4, Philipp Sewerin5, Yu Deng6, Linyu Shi6, Yoshiyuki Sugimoto7, Sheng Zhong6, Yunzhao Xing6, Ralph Lippe6 and Mitsumasa Kishimoto8, 1Sorbonne Université, Paris, France, 2UNIVERSITY OF MEDICINE AND PHARMACY CAROL DAVILA, Bucharest, Romania, 3Versailles-Saint-Quentin University (INSERM U1173, Laboratoire d’Excellence INFLAMEX); University Hospital Ambroise Paré, Versailles, France, 4Department of Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, 5Rheumazentrum Ruhrgebiet, Ruhr University Bochum, Bochum, Germany, 6AbbVie Inc., North Chicago, IL, 7AbbVie GK, Tokyo, Tokyo, Japan, 8Department of Nephrology and Rheumatology, Kyorin University School of Medicine, Tokyo, Japan

Meeting: ACR Convergence 2024

Keywords: autoimmune diseases, clinical trial, Interleukins, Psoriatic arthritis, Randomized Trial

  • Tweet
  • Click to email a link to a friend (Opens in new window) Email
  • Click to print (Opens in new window) Print
Session Information

Date: Monday, November 18, 2024

Title: SpA Including PsA – Treatment Poster III

Session Type: Poster Session C

Session Time: 10:30AM-12:30PM

Background/Purpose: Risankizumab (RZB), an IL-23 p19 inhibitor, is well tolerated and provides long-term efficacy through 100 weeks in adults with PsA, demonstrated by the phase 3 KEEPsAKE 1 and KEEPsAKE 2 studies (Kristensen LE, et al. Rheumatol Ther. 2024 [Epub]; Östör A, et al. Rheumatol Ther. 2024 [Epub]). Cluster analysis is a data-driven hypothesis-free unsupervised machine learning approach that can potentially inform treatment decisions. This cluster analysis classified patients into PsA phenotype clusters using baseline characteristics. The probability of response to RZB was assessed by cluster at 24, 52, and 100 weeks of treatment.

Methods: This post hoc analysis of KEEPsAKE 1 and KEEPsAKE 2 evaluated data from bDMARD-naive adult patients with PsA. Patients in the 2 trials were required to have at least 5 tender and 5 swollen joints to be included. A finite mixture model was used to determine clusters; baseline demographic and clinical characteristics were input features. Variables with excess missing data/collinearity and patients with missing data were excluded. Optimal number of clusters and stability were assessed. Using descriptive statistics, baseline clinical and demographic characteristics were described for each cluster, as was efficacy by cluster at weeks 24, 52, and 100 for patients who received continuous RZB. Efficacy endpoints were response rates of minimal disease activity (MDA), Disease Activity in PsA low disease activity (DAPSA LDA), TJC improvement ≥ 50%, SJC improvement ≥ 50%, and clinically meaningful improvement in HAQ-Disability Index (score decrease of ≥ 0.35).

Results: Out of 1196 patients, 1119 (93.6%) were analyzed after excluding those with missing data. Five distinct phenotypic clusters were identified: patients with PsA that was (1) moderate disease activity across all domains (n [%] = 451 [40.3]), (2) hand dominant (154 [13.8]), (3) high disease activity across all domains (157 [14.0]), (4) dactylitis and feet dominant (124 [11.1]), and (5) enthesitis and large joints dominant (233 [20.8]; Figure 1). At baseline, clusters 1 and 4 were younger and had lower BMI; clusters 3 and 5 had a higher proportion of patients with BMI ≥ 30; cluster 4 had mainly male and cluster 5 had mainly female patients (Table). In patients receiving continuous RZB, the achievement of remission/low disease appeared higher in the more moderate disease activity clusters as expected, with 32.2%–57.0% of patients achieving MDA and 51.5%–79.2% DAPSA LDA at week 100; however, rates of response (change over time) appeared similar in all clusters, indicating consistent efficacy of RZB across the spectrum of PsA patients (Figure 2).

Conclusion: In this post hoc analysis, 5 distinct PsA phenotype clusters were identified based on the demographic and clinical features of PsA. RZB demonstrated efficacy across all 5 clusters through 100 weeks of treatment with notably highest achievement of remission/low disease in clusters 1 (moderate PsA activity) and 4 (dactylitis/feet dominant). These findings help to identify PsA phenotypes that may respond particularly well to RZB.

Supporting image 1

Table. Baseline Demographic and Clinical Characteristics

Supporting image 2

Figure 1. Identified PsA Phenotype Clusters Based on Frequency of Demographic and Clinical Features.

Supporting image 3

Figure 2. Response Across 5 Phenotype Clusters Among Bio-Naive Patients Receiving Continuous Risankizumab 150 mg for 24, 52, and 100 weeks. (A) MDA response, (B) LDA (DAPSA ≤ 14), (C) TJC (≥ 50% improvement), (D) SJC (≥ 50% improvement), and (E) HAQ-DI response (≥ 0.35).


Disclosures: L. Gossec: AbbVie, 2, 5, Amgen, 2, Biogen, 5, Bristol-Myers Squibb (BMS), 2, Celltrion, 2, Eli Lilly, 2, 5, Galapagos, 2, Janssen, 2, MSD, 2, Novartis, 2, 5, Pfizer, 2, Sandoz, 2, UCB, 2, 5; A. Balanescu: AbbVie, 2, 6, Akros, 12, Clinical trial investigator, AlphaSigma, 2, 6, Amgen, 2, 6, Angellini, 2, 6, AstraZeneca, 2, 6, 12, Clinical trial investigator, Berlin-Chemie, 2, 6, Biogen, 2, 6, Bristol Myers Squibb, 2, 6, 12, Clinical trial investigator, GlaxoSmithKline, 12, Clinical trial investigator, Janssen, 2, 6, Lilly, 2, 6, MSD, 2, 6, 12, Clinical trial investigator, Novartis, 2, 6, 12, Clinical trial investigator, Pfizer, 2, 6, 12, Clinical trial investigator, Roche, 2, 6, 12, Clinical trial investigator, Sandoz, 2, 6, 12, Clinical trial investigator, Sanofi, 12, Clinical trial investigator, Teva, 2, 6, UCB, 2, 6, 12, Clinical trial investigator, Zentiva, 2, 6; M. D'Agostino: AbbVie, 2, 6, AmGen, 2, 6, BMS, 2, 6, Galapagos, 2, 6, Janssen, 2, 6, Lilly, 2, 6, Novartis, 2, 6, Pfizer, 2, 6; A. Ogdie: AbbVie, 2, 5, Amgen, 2, 5, Bristol-Myers Squibb(BMS), 5, Celgene, 2, CorEvitas, 2, Eli Lilly, 2, Gilead, 2, GlaxoSmithKlein(GSK), 5, Happify Health, 2, Janssen, 2, 5, Novartis, 2, 5, Pfizer, 2, 5, UCB, 2; P. Sewerin: AbbVie, 2, 5, 6, Biogen, 2, 6, Bristol Myers Squibb, 2, 6, Celgene, 2, 5, 6, Chugai, 2, 5, 6, Hexal, 2, 6, Janssen-Cilag, 2, 5, 6, Lilly, 2, 5, 6, Novartis, 2, 5, 6, Pfizer, 2, 5, 6, Roche, 2, 6, Sanofi-Genzyme, 2, 5, Swedish Orphan Biovitrum, 2, 6, UCB, 2, 5, 6; Y. Deng: AbbVie, 3, 11; L. Shi: AbbVie, 3, 11; Y. Sugimoto: AbbVie, 3, 11; S. Zhong: AbbVie, 3, 11; Y. Xing: AbbVie, 3, 11; R. Lippe: AbbVie, 3, 11; M. Kishimoto: AbbVie, 2, 6, Amgen, 2, 6, Asahi-Kasei Pharma, 2, 6, Astellas, 2, 6, Ayumi Pharma, 2, 6, Bristol Myers Squibb, 2, 6, Chugai, 2, 6, Daiichi-Sankyo, 2, 6, Eisai, 2, 6, Eli Lilly, 2, 6, Gilead, 2, 6, Janssen, 2, 6, Novartis, 2, 6, Pfizer, 2, 6, Tanabe-Mitsubishi, 2, 6, UCB, 2, 6.

To cite this abstract in AMA style:

Gossec L, Balanescu A, D'Agostino M, Ogdie A, Sewerin P, Deng Y, Shi L, Sugimoto Y, Zhong S, Xing Y, Lippe R, Kishimoto M. Efficacy of Risankizumab Across Distinct PsA Phenotypes Identified with Machine Learning Analytics Using Data from Biologic DMARD-Naive Patients in Two Phase 3 Clinical Trials [abstract]. Arthritis Rheumatol. 2024; 76 (suppl 9). https://acrabstracts.org/abstract/efficacy-of-risankizumab-across-distinct-psa-phenotypes-identified-with-machine-learning-analytics-using-data-from-biologic-dmard-naive-patients-in-two-phase-3-clinical-trials/. Accessed .
  • Tweet
  • Click to email a link to a friend (Opens in new window) Email
  • Click to print (Opens in new window) Print

« Back to ACR Convergence 2024

ACR Meeting Abstracts - https://acrabstracts.org/abstract/efficacy-of-risankizumab-across-distinct-psa-phenotypes-identified-with-machine-learning-analytics-using-data-from-biologic-dmard-naive-patients-in-two-phase-3-clinical-trials/

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 »

All abstracts accepted to ACR Convergence are under media embargo once the ACR has notified presenters of their abstract’s acceptance. They may be presented at other meetings or published as manuscripts after this time but should not be discussed in non-scholarly venues or outlets. The following embargo policies are strictly enforced by the ACR.

Accepted abstracts are made available to the public online in advance of the meeting and are published in a special online supplement of our scientific journal, Arthritis & Rheumatology. Information contained in those abstracts may not be released until the abstracts appear online. In an exception to the media embargo, academic institutions, private organizations, and companies with products whose value may be influenced by information contained in an abstract may issue a press release to coincide with the availability of an ACR abstract on the ACR website. However, the ACR continues to require that information that goes beyond that contained in the abstract (e.g., discussion of the abstract done as part of editorial news coverage) is under media embargo until 10:00 AM ET on November 14, 2024. Journalists with access to embargoed information cannot release articles or editorial news coverage before this time. Editorial news coverage is considered original articles/videos developed by employed journalists to report facts, commentary, and subject matter expert quotes in a narrative form using a variety of sources (e.g., research, announcements, press releases, events, etc.).

Violation of this policy may result in the abstract being withdrawn from the meeting and other measures deemed appropriate. Authors are responsible for notifying colleagues, institutions, communications firms, and all other stakeholders related to the development or promotion of the abstract about this policy. If you have questions about the ACR abstract embargo policy, please contact ACR abstracts staff at [email protected].

Wiley

  • Online Journal
  • Privacy Policy
  • Permissions Policies
  • Cookie Preferences

© Copyright 2025 American College of Rheumatology