BackgroundThirteen drugs with different mechanisms of action may be considered to treat patients with methotrexate (MTX) inadequate response in rheumatoid arthritis (RA). TNF inhibitors (TNFi) are frequently the first choice in this situation. Unfortunately, 30% to 40% of RA patients do not respond to TNFi, resulting in a delay for beginning the appropriate targeted DMARD (tDMARD). Predicting the patient response to TNFi before prescribing the treatment is therefore a major goal and could help physicians to prescribe a tDMARD suited to the patient.ObjectivesWe aimed to build machine learning models based on simple clinical and biological data to predict patient response to TNFi.MethodsWe used data from the ESPOIR early arthritis cohort (1) to train the models, and the ABIRISK cohort (2) to validate the results. We included patients that fulfilled the EULAR/ACR 2010 criteria and that were treated with a TNFi. The models take as inputs patient’s characteristics at treatment initiation and predicts the therapeutic response, defined as the EULAR response 12 months (+/- 6 months) after treatment initiation. We compared the performances of four models (Linear Regression, Random Forest, XGBoost, and Catboost) on the training set by cross-validated them using the Area Under the ROC Curve (AUCROC). The best model was then evaluated on the validation dataset (ABIRISK cohort). We conducted the methodology both on all TNFi together and on etanercept and monoclonal anti-TNF antibodies separated. We analyzed how clinical and biological variables impacted response to provide explainability of the prediction.ResultsWe included 164 patients from the ESPOIR cohort and 118 patients from the ABIRISK cohort. Better results were obtained when etanercept and monoclonal anti-TNF antibodies were analyzed separately.These models predict a probability for a patient to respond to TNFi. This probability is compared to a decision threshold to obtain the binary outcome. Two decision thresholds were tested. The first prioritizes a high confidence when identifying responders (Strategy 1) while the second prioritizes a high confidence when identifying non-responders (Strategy 2). The model’s results are presented in Table 1.Table 1.Sensitivity, Specificity, PPV and NPV are computed on the ABIRISK validation cohort for each strategyDrugAUC(ESPOIR)AUC(ABIRA)STRATEGY 1 (high confidence in response)STRATEGY 2 (high confidence in non-response)SensitivitYSpecificityPPVNPVSensitivitySpecificityPPVNPVOverall TNFi0.720.6518%91%76%42%90%30%67%67%(0.68-0.73)(0.54 - 0.75)(10%-27%)(82%-98%)(54%-95%)(32%-51%)(83%-96%)(18%-44%)(58%-76%(45%-86%Etanercept0.740.7060%73%78%53%95%15%64%67%(0.68-0.75)(0.57- 0.82)(44%-74%)(55%-89%)(63%-92%)(36%-69%)(88%-100%)(4%-30%)(52%-76%)(20%-100%)Monoclonal anti-TNF antibodies0.740.7137%95%92%50%90%40%69%73%(0.69-0.77)(0.55-0.86)(20%-55%)(83%-100%)(73%-100%)(35%-66%)(78%-100%)(19%-62%)(54%-84%)(44%-100%)Using SHAP, we were able to analyze how each variable impacted the predictions. In particular, a DAS28 around 5 had the highest positive impact on response. Higher and lower values of DAS28 had either less impact or even negative impact on the patient response to TNFi treatment (Figure 1). This allows to identify non-linear relations between variables and patient response.ConclusionThe machine learning models developed in this study can predict RA patients’ response to TNFi using exclusively data available in clinical routine. These models also allow to analyze how these variables are used to predict response. Along with similar models for other tDMARDs, such algorithms could lead to a personalized therapeutic strategy.References[1]Combe B, Benessiano J, Berenbaum F, Cantagrel A, Daurès J-P, Dougados M, et al. The ESPOIR cohort: A ten-year follow-up of early arthritis in France.[2]Anon. ABIRISK Anti-Biopharmaceutical Immunization: Prediction and Analysis of Clinical Relevance to Minimize the RISK. 2019.AcknowledgementsFor the first 5 years of the ESPOIR cohort, an unrestricted grant from Merck Sharp and Dohme (MSD) was allocated. Two additional grants from INSERM were obtained to support part of the biological database. The French Society of Rheumatology, Pfizer, AbbVie, Lilly, and more recently Fresenius and Biogen also supported the ESPOIR cohort study. We also wish to thank Nathalie Rincheval (Montpellier) who did expert monitoring and data management and all the investigators who recruited and followed the patients (F.Berenbaum, Paris-Saint Antoine, MC.Boissier, Paris-Bobigny, A.Cantagrel, Toulouse, B.Combe, Montpellier, M.Dougados, Paris-Cochin, P.Fardellone et P.Boumier Amiens, B.Fautrel, Paris-La Pitié, RM. Flipo, Lille, Ph. Goupille, Tours, F. Liote, Paris-Lariboisière, O.Vittecoq, Rouen, X.Mariette, Paris Bicetre, P.Dieude, Paris Bichat, A.Saraux, Brest, T.Schaeverbeke, Bordeaux, J.Sibilia, Strasbourg) as well as S.Martin (Paris Bichat) who did all the central dosages of CRP, IgA and IgM rheumatoid.SB was supported by FHU CARE.Disclosure of InterestsNone declared.
BackgroundMethotrexate (MTX) is the first line of treatment for rheumatoid arthritis (RA) patients. Unfortunately, 30% to 40% of RA patients do not respond to MTX, resulting in uncontrolled joint pain and potential joints destruction. At the same time, many efficient second-line treatments exist and can be given to the inadequate responder patients. Predicting patient response to MTX before prescribing the treatment is therefore a major goal and could enable physicians to directly prescribe second-line treatments if inadequate response to MTX is predicted.ObjectivesWe aimed to build machine learning models based on simple clinical and biological data to predict patient response to MTX.MethodsWe used data from the ESPOIR early arthritis (1) and Leiden cohorts (2) to train the models, and the tREACH cohort to validate the results. We included patients that fulfilled the EULAR/ACR 2010 criteria and that were treated with MTX in monotherapy as their first treatment for RA. The models take as inputs patient’s characteristics at treatment initiation and predict the therapeutic response, defined as the EULAR response 3 to 12 months after treatment initiation. We evaluated four missing data imputation methods (median, mean, MICE, KNN); we used the backward feature selection algorithm to select the most relevant variables; and compared the performances of four models (Linear Regression, Random Forest, XGBoost, and Catboost) on the training set by cross-validated them using the Area Under the ROC Curve (AUCROC). The best model was then evaluated on the validation dataset.ResultsWe included 435 patients from the ESPOIR cohort, 243 patients from the Leiden cohort and 143 patients from the t-REACH cohort. Results of the model are displayed in Table 1. The variables automatically selected to perform prediction were Sex, DAS28, White blood cells, AST, ALT and lymphocytes. Our model performs well on unseen data, this result comes from the fact that we included two different cohorts in our training set which reduces the overfitting of our model and helps him generalize.Table 1.Sensitivity, Specificity, PPV and NPV are computed on the T-REACH validation cohort for each strategyAUC(ESPOIR, LEIDEN)AUC(T-REACH)STRATEGY 1 (High confidence in responders)STRATEGY 2 (high confidence in non-responDeRS)SensitivitYSpecificityPPVNPVSensitivitySpecificityPPVNPV0.720.7320%98%95%40%91%33%71%68%(0.70-0.73)(0.64-0.81)(12%-28%)(83%-100%)(82%-100%)(32%-49%)(85%-97%)(20%-47%)(63%-79%)(48%-86%)Our model predicts a probability for a patient to respond to MTX. This probability is compared to a decision threshold to obtain the final binary outcome. Two decision thresholds were tested. The first prioritizes a high confidence when identifying responders (Strategy 1) while the second prioritizes a high confidence when identifying non-responders (Strategy 2). This second strategy would enable physicians to identify highly probable inadequate responders to methotrexate and propose them directly a targeted DMARD such as TNF inhibitors, while still treating more than 70% of patients with MTX as first-line treatment.ConclusionThe machine learning models developed in this study can predict RA patients’ response to methotrexate with a good accuracy exclusively using data available in clinical routine. It paves the way for personalized therapeutic strategies in rheumatoid arthritis.References[1]Combe B, Benessiano J, Berenbaum F, Cantagrel A, Daurès J-P, Dougados M, et al. The ESPOIR cohort: A ten-year follow-up of early arthritis in France. Joint Bone Spine 2007;74:440–445.[2]van Aken, J., van Bilsen, J. H., Allaart, C. F., Huizinga, T. W., & Breedveld, F. C. The Leiden Early Arthritis Clinic. Clinical and experimental rheumatology, 21(5 Suppl 31), S100–S105.Disclosure of InterestsNone declared.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.