Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Randomized Controlled Trial
. 2021 Feb 27;23(1):67.
doi: 10.1186/s13075-021-02439-5.

Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs

Asmir Vodencarevic #  1 , Koray Tascilar #  2   3 , Fabian Hartmann  2   3 , Michaela Reiser  2   3 , Axel J Hueber  2   3   4 , Judith Haschka  2   3   5 , Sara Bayat  2   3 , Timo Meinderink  2   3 , Johannes Knitza  2   3 , Larissa Mendez  2   3 , Melanie Hagen  2   3 , Gerhard Krönke  2   3 , Jürgen Rech  2   3 , Bernhard Manger  2   3 , Arnd Kleyer  2   3 , Marcus Zimmermann-Rittereiser  1 , Georg Schett  2   3 , David Simon  6   7 ; RETRO study group
Affiliations
Randomized Controlled Trial

Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs

Asmir Vodencarevic et al. Arthritis Res Ther. .

Abstract

Background: Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients tapering bDMARDs using machine learning methods.

Methods: Longitudinal clinical data of RA patients on bDMARDs from a randomized controlled trial of treatment withdrawal (RETRO) were used to build a predictive model to estimate the probability of a flare. Four basic machine learning models were trained, and their predictions were additionally combined to train an ensemble learning method, a stacking meta-classifier model to predict the individual flare probability within 14 weeks after each visit. Prediction performance was estimated using nested cross-validation as the area under the receiver operating curve (AUROC). Predictor importance was estimated using the permutation importance approach.

Results: Data of 135 visits from 41 patients were included. A model selection approach based on nested cross-validation was implemented to find the most suitable modeling formalism for the flare prediction task as well as the optimal model hyper-parameters. Moreover, an approach based on stacking different classifiers was successfully applied to create a powerful and flexible prediction model with the final measured AUROC of 0.81 (95%CI 0.73-0.89). The percent dose change of bDMARDs, clinical disease activity (DAS-28 ESR), disease duration, and inflammatory markers were the most important predictors of a flare.

Conclusion: Machine learning methods were deemed feasible to predict flares after tapering bDMARDs in RA patients in sustained remission.

Keywords: Flare prediction; Machine learning; Rheumatoid arthritis.

PubMed Disclaimer

Conflict of interest statement

None to declare.

Figures

Fig. 1
Fig. 1
(a) Logistic Regression, (b) k-Nearest Neighbors, (c) Naïve Bayes, (d) Random Forest, (e) Stacking-Meta Classifier
Fig. 2
Fig. 2
Model diagnostics. Algorithm learning curve is depicted in a, b shows influence of missing data on the algorithm performance, c shows relative importance of predictors, and d shows the calibration plot of the model
See this image and copyright information in PMC

References

    1. Aga AB, Lie E, Uhlig T, Olsen IC, Wierod A, Kalstad S, Rodevand E, Mikkelsen K, Kvien TK, Haavardsholm EA. Time trends in disease activity, response and remission rates in rheumatoid arthritis during the past decade: results from the NOR-DMARD study 2000–2010. Ann Rheum Dis. 2015;74(2):381–388. doi: 10.1136/annrheumdis-2013-204020. - DOI - PubMed
    1. Combe B, Rincheval N, Benessiano J, Berenbaum F, Cantagrel A, Daures JP, Dougados M, Fardellone P, Fautrel B, Flipo RM, et al. Five-year favorable outcome of patients with early rheumatoid arthritis in the 2000s: data from the ESPOIR cohort. J Rheumatol. 2013;40(10):1650–1657. doi: 10.3899/jrheum.121515. - DOI - PubMed
    1. Schett G, Emery P, Tanaka Y, Burmester G, Pisetsky DS, Naredo E, Fautrel B, van Vollenhoven R. Tapering biologic and conventional DMARD therapy in rheumatoid arthritis: current evidence and future directions. Ann Rheum Dis. 2016;75(8):1428–1437. doi: 10.1136/annrheumdis-2016-209201. - DOI - PubMed
    1. Haschka J, Englbrecht M, Hueber AJ, Manger B, Kleyer A, Reiser M, Finzel S, Tony HP, Kleinert S, Feuchtenberger M, et al. Relapse rates in patients with rheumatoid arthritis in stable remission tapering or stopping antirheumatic therapy: interim results from the prospective randomised controlled RETRO study. Ann Rheum Dis. 2016;75(1):45–51. doi: 10.1136/annrheumdis-2014-206439. - DOI - PubMed
    1. Tanaka Y, Hirata S, Kubo S, Fukuyo S, Hanami K, Sawamukai N, Nakano K, Nakayamada S, Yamaoka K, Sawamura F, et al. Discontinuation of adalimumab after achieving remission in patients with established rheumatoid arthritis: 1-year outcome of the HONOR study. Ann Rheum Dis. 2015;74(2):389–395. doi: 10.1136/annrheumdis-2013-204016. - DOI - PMC - PubMed

Publication types