Identification of a Rule to Predict Response to Sarilumab in Patients with Rheumatoid Arthritis Using Machine Learning and Clinical Trial Data
Markus Rehberg, Clemens Giegerich, Amy Praestgaard, Hubert van Hoogstraten, Melitza Iglesias-Rodriguez, Jeffrey R Curtis, Jacques-Eric Gottenberg, Andreas Schwarting, Santos Castañeda, Andrea Rubbert-Roth, Ernest H S Choy, MOBILITY, MONARCH, TARGET, and ASCERTAIN investigators, Markus Rehberg, Clemens Giegerich, Amy Praestgaard, Hubert van Hoogstraten, Melitza Iglesias-Rodriguez, Jeffrey R Curtis, Jacques-Eric Gottenberg, Andreas Schwarting, Santos Castañeda, Andrea Rubbert-Roth, Ernest H S Choy, MOBILITY, MONARCH, TARGET, and ASCERTAIN investigators
Abstract
Introduction: In rheumatoid arthritis, time spent using ineffective medications may lead to irreversible disease progression. Despite availability of targeted treatments, only a minority of patients achieve sustained remission, and little evidence exists to direct the choice of biologic disease-modifying antirheumatic drugs in individual patients. Machine learning was used to identify a rule to predict the response to sarilumab and discriminate between responses to sarilumab versus adalimumab, with a focus on clinically feasible blood biomarkers.
Methods: The decision tree model GUIDE was trained using a data subset from the sarilumab trial with the most biomarker data, MOBILITY, to identify a rule to predict disease activity after sarilumab 200 mg. The training set comprised 18 categorical and 24 continuous baseline variables; some data were omitted from training and used for validation by the algorithm (cross-validation). The rule was tested using full datasets from four trials (MOBILITY, MONARCH, TARGET, and ASCERTAIN), focusing on the recommended sarilumab dose of 200 mg.
Results: In the training set, the presence of anti-cyclic citrullinated peptide antibodies, combined with C-reactive protein > 12.3 mg/l, was identified as the "rule" that predicts American College of Rheumatology 20% response (ACR20) to sarilumab. In testing, the rule reliably predicted response to sarilumab in MOBILITY, MONARCH, and ASCERTAIN for many efficacy parameters (e.g., ACR70 and the 28-joint disease activity score using CRP [DAS28-CRP] remission). The rule applied less to TARGET, which recruited individuals refractory to tumor necrosis factor inhibitors. The potential clinical benefit of the rule was highlighted in a clinical scenario based on MONARCH data, which found that increased ACR70 rates could be achieved by treating either rule-positive patients with sarilumab or rule-negative patients with adalimumab.
Conclusions: Well-established and clinically feasible blood biomarkers can guide individual treatment choice. Real-world validation of the rule identified in this post hoc analysis is merited.
Clinical trial registration: NCT01061736, NCT02332590, NCT01709578, NCT01768572.
Keywords: Adalimumab; Clinical trial; Machine learning; Precision medicine; Rheumatoid arthritis; Sarilumab.
© 2021. The Author(s).
Figures
References
- Singh JA, Saag KG, Bridges SL, Jr, et al. 2015 American College of Rheumatology guideline for the treatment of rheumatoid arthritis. Arthritis Care Res. 2016;68(1):1–25. doi: 10.1002/acr.22783.
- Smolen JS, Landewe RBM, Bijlsma JWJ, et al. EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs: 2019 update. Ann Rheum Dis. 2020 doi: 10.1136/annrheumdis-2019-216655.
- Karsdal MA, Bay-Jensen AC, Henriksen K, et al. Rheumatoid arthritis: a case for personalized health care? Arthritis Care Res (Hoboken) 2014;66(9):1273–1280. doi: 10.1002/acr.22289.
- Hugle M, Omoumi P, van Laar JM, Boedecker J, Hugle T. Applied machine learning and artificial intelligence in rheumatology. Rheumatol Adv Pract. 2020;4(1):rkaa005. doi: 10.1093/rap/rkaa005.
- Venerito V, Lopalco G, Cacciapaglia F, Fornaro M, Iannone F. A Bayesian mixed treatment comparison of efficacy of biologics and small molecules in early rheumatoid arthritis. Clin Rheumatol. 2019;38(5):1309–1317. doi: 10.1007/s10067-018-04406-z.
- Migliore A, Bizzi E, Egan CG, Bernardi M, Petrella L. Efficacy of biological agents administered as monotherapy in rheumatoid arthritis: a Bayesian mixed-treatment comparison analysis. Ther Clin Risk Manag. 2015;11:1325–1335.
- Dennis G, Jr, Holweg CT, Kummerfeld SK, et al. Synovial phenotypes in rheumatoid arthritis correlate with response to biologic therapeutics. Arthritis Res Ther. 2014;16(2):R90. doi: 10.1186/ar4555.
- Johnson KJ, Sanchez HN, Schoenbrunner N. Defining response to TNF-inhibitors in rheumatoid arthritis: the negative impact of anti-TNF cycling and the need for a personalized medicine approach to identify primary non-responders. Clin Rheumatol. 2019;38(11):2967–2976. doi: 10.1007/s10067-019-04684-1.
- Plant D, Maciejewski M, Smith S, et al. Profiling of gene expression biomarkers as a classifier of methotrexate nonresponse in patients with rheumatoid arthritis. Arthritis Rheumatol. 2019;71(5):678–684. doi: 10.1002/art.40810.
- Mahler M, Martinez-Prat L, Sparks JA, Deane KD. Precision medicine in the care of rheumatoid arthritis: focus on prediction and prevention of future clinically-apparent disease. Autoimmun Rev. 2020;19(5):102506. doi: 10.1016/j.autrev.2020.102506.
- Aletaha D. Precision medicine and management of rheumatoid arthritis. J Autoimmun. 2020;110:102405. doi: 10.1016/j.jaut.2020.102405.
- Giacomelli R, Afeltra A, Alunno A, et al. Guidelines for biomarkers in autoimmune rheumatic diseases - evidence based analysis. Autoimmun Rev. 2019;18(1):93–106. doi: 10.1016/j.autrev.2018.08.003.
- Lequerré T, Rottenberg P, Derambure C, Cosette P, Vittecoq O. Predictors of treatment response in rheumatoid arthritis. Joint Bone Spine. 2019;86(2):151–158. doi: 10.1016/j.jbspin.2018.03.018.
- Norgeot B, Glicksberg BS, Trupin L, et al. Assessment of a deep learning model based on electronic health record data to forecast clinical outcomes in patients with rheumatoid arthritis. JAMA Netw Open. 2019;2(3):e190606. doi: 10.1001/jamanetworkopen.2019.0606.
- Guan Y, Zhang H, Quang D, et al. Machine learning to predict anti-tumor necrosis factor drug responses of rheumatoid arthritis patients by integrating clinical and genetic markers. Arthritis Rheumatol. 2019;71(12):1987–1996. doi: 10.1002/art.41056.
- Yoo J, Lim MK, Ihm C, Choi ES, Kang MS. A study on prediction of rheumatoid arthritis using machine learning. Int J Appl Engineering Res. 2017;12(20):9858–9862.
- Zhou SM, Fernandez-Gutierrez F, Kennedy J, et al. Defining disease phenotypes in primary care electronic health records by a machine learning approach: a case study in identifying rheumatoid arthritis. PLoS ONE. 2016;11(5):e0154515. doi: 10.1371/journal.pone.0154515.
- KEVZARA (sarilumab) [Prescribing Information] 2017. Available at: .
- KEVZARA (sarilumab) [Summary of Product Characteristics] 2017. Available at: .
- Genovese MC, Fleischmann R, Kivitz AJ, et al. Sarilumab plus methotrexate in patients with active rheumatoid arthritis and inadequate response to methotrexate: results of a phase III study. Arthritis Rheumatol. 2015;67(6):1424–1437. doi: 10.1002/art.39093.
- Burmester GR, Lin Y, Patel R, et al. Efficacy and safety of sarilumab monotherapy versus adalimumab monotherapy for the treatment of patients with active rheumatoid arthritis (MONARCH): a randomised, double-blind, parallel-group phase III trial. Ann Rheum Dis. 2017;76(5):840–847. doi: 10.1136/annrheumdis-2016-210310.
- Fleischmann R, van Adelsberg J, Lin Y, et al. Sarilumab and nonbiologic disease-modifying antirheumatic drugs in patients with active rheumatoid arthritis and inadequate response or intolerance to tumor necrosis factor inhibitors. Arthritis Rheumatol. 2017;69(2):277–290. doi: 10.1002/art.39944.
- Emery P, Rondon J, Parrino J, et al. Safety and tolerability of subcutaneous sarilumab and intravenous tocilizumab in patients with rheumatoid arthritis. Rheumatology (Oxford) 2019;58(5):849–858. doi: 10.1093/rheumatology/key361.
- Loh W-Y. Classification and regression trees. Wiley Interdiscip Rev Data Min Knowl Discov. 2011;1(1):14–23. doi: 10.1002/widm.8.
- Quinlan JR. Induction of decision trees. Mach Learn. 1986;1:81–106.
- Wijbrandts CA, Tak PP. Prediction of response to targeted treatment in rheumatoid arthritis. Mayo Clin Proc 2017;92(7):1129–43.
- Harrold LR, Litman HJ, Connolly SE, et al. Effect of anticitrullinated protein antibody status on response to abatacept or antitumor necrosis factor-α therapy in patients with rheumatoid arthritis: a US national observational study. J Rheumatol. 2018;45(1):32–39. doi: 10.3899/jrheum.170007.
- Pers YM, Fortunet C, Constant E, et al. Predictors of response and remission in a large cohort of rheumatoid arthritis patients treated with tocilizumab in clinical practice. Rheumatology (Oxford) 2014;53(1):76–84. doi: 10.1093/rheumatology/ket301.
- Harrold L, Wittstock K, Kelly S, et al. The comparative effectiveness of abatacept versus TNF inhibitors in patients who are ACPA positive and have the shared epitope: results from a US national observational study. Arthritis Rheumatol. 2020;72(suppl 10):0801.
- Boyapati A, Schwartzman S, Msihid J, et al. Association of high serum interleukin-6 levels with severe progression of rheumatoid arthritis and increased treatment response differentiating sarilumab from adalimumab or methotrexate in a post hoc analysis. Arthritis Rheumatol. 2020;72(9):1456–1466. doi: 10.1002/art.41299.
- Boss B, Neeck G. Correlation of IL-6 with the classical humoral disease activity parameters ESR and CRP and with serum cortisol, reflecting the activity of the HPA axis in active rheumatoid arthritis. Z Rheumatol 2000;59 Suppl 2:II/62–4.
- Cronstein BN. Interleukin-6–a key mediator of systemic and local symptoms in rheumatoid arthritis. Bull NYU Hosp Jt Dis. 2007;65(Suppl 1):S11–S15.
- van Leeuwen MA, Westra J, Limburg PC, van Riel PL, van Rijswijk MH. Clinical significance of interleukin-6 measurement in early rheumatoid arthritis: relation with laboratory and clinical variables and radiological progression in a three year prospective study. Ann Rheum Dis. 1995;54(8):674–677. doi: 10.1136/ard.54.8.674.
- Izawa S, Miki K, Liu X, Ogawa N. The diurnal patterns of salivary interleukin-6 and C-reactive protein in healthy young adults. Brain Behav Immun. 2013;27(1):38–41. doi: 10.1016/j.bbi.2012.07.001.
Source: PubMed