Patient groups in Rheumatoid arthritis identified by deep learning respond differently to biologic or targeted synthetic DMARDs

Maria Kalweit, Andrea M Burden, Joschka Boedecker, Thomas Hügle and Theresa Burkard

PLOS Computational Biology, 2023, vol. 19, issue 6, 1-17

Abstract: Cycling of biologic or targeted synthetic disease modifying antirheumatic drugs (b/tsDMARDs) in rheumatoid arthritis (RA) patients due to non-response is a problem preventing and delaying disease control. We aimed to assess and validate treatment response of b/tsDMARDs among clusters of RA patients identified by deep learning. We clustered RA patients clusters at first-time b/tsDMARD (cohort entry) in the Swiss Clinical Quality Management in Rheumatic Diseases registry (SCQM) [1999–2018]. We performed comparative effectiveness analyses of b/tsDMARDs (ref. adalimumab) using Cox proportional hazard regression. Within 15 months, we assessed b/tsDMARD stop due to non-response, and separately a ≥20% reduction in DAS28-esr as a response proxy. We validated results through stratified analyses according to most distinctive patient characteristics of clusters. Clusters comprised between 362 and 1481 patients (3516 unique patients). Stratified (validation) analyses confirmed comparative effectiveness results among clusters: Patients with ≥2 conventional synthetic DMARDs and prednisone at b/tsDMARD initiation, male patients, as well as patients with a lower disease burden responded better to tocilizumab than to adalimumab (hazard ratio [HR] 5.46, 95% confidence interval [CI] [1.76–16.94], and HR 8.44 [3.43–20.74], and HR 3.64 [2.04–6.49], respectively). Furthermore, seronegative women without use of prednisone at b/tsDMARD initiation as well as seropositive women with a higher disease burden and longer disease duration had a higher risk of non-response with golimumab (HR 2.36 [1.03–5.40] and HR 5.27 [2.10–13.21], respectively) than with adalimumab. Our results suggest that RA patient clusters identified by deep learning may have different responses to first-line b/tsDMARD. Thus, it may suggest optimal first-line b/tsDMARD for certain RA patients, which is a step forward towards personalizing treatment. However, further research in other cohorts is needed to verify our results.Author summary: Rheumatoid arthritis (RA) is an auto-immune disease affecting the joints of the body. RA is subject to poor treatment response to advanced antirheumatic therapy. While previous studies have used machine learning techniques to identify different RA patient populations, no study has used these populations to evaluate potentially different treatment response of advanced RA treatments such as tumor necrosis factor inhibitors. Using machine learning, we identified five distinct RA patient groups which mainly differed by sex, disease burden/duration, and concomitant traditional RA treatment use (i.e. prednisone, methotrexate). Patients with high frequency of use of traditional RA treatment use at advanced RA treatment initiation, male patients, as well as patients with a lower disease burden responded better to tocilizumab than to adalimumab. Furthermore, seronegative women without use of prednisone at advanced RA treatment initiation as well as seropositive women with a higher disease burden and longer disease duration had a higher risk of non-response with golimumab than with adalimumab. The results are a step towards personalizing treatment and shall encourage other researchers to embrace machine learning techniques to improve treatment response in RA and other disease areas.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1011073 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 11073&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1011073

DOI: 10.1371/journal.pcbi.1011073

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().