Article Text

Download PDFPDF

POS0543 MACHINE LEARNING PREDICTS RESPONSE TO METHOTREXATE IN RHEUMATOID ARTHRITIS: RESULTS ON THE ESPOIR, t-REACH AND LEIDEN COHORTS
Free
  1. V. Bouget1,
  2. J. Duquesne1,
  3. P. H. Cournède2,
  4. B. Fautrel3,
  5. F. Guillemin4,
  6. P. De Jong5,
  7. J. Heutz5,
  8. A. Van der Helm-van Mil6,
  9. M. Verstappen6,
  10. S. Bitoun7,
  11. X. Mariette7
  1. 1Scienta Lab, Research department, Paris, France
  2. 2Université Paris-Saclay, CentraleSupélec, Lab of mathematics and computer science (MICS), Gif-sur-Yvette, France
  3. 3Sorbonne Université – Assistance Publique Hôpitaux de Paris, Groupe Hospitalier Pitié Salpêtrière, Service de Rhumatologie, Paris, France
  4. 4Université de Lorraine, APEMAC, Nancy, France
  5. 5University Medical Center, Department of Rheumatology, Rotterdam, Netherlands
  6. 6Leiden University Medical Center, Department of Rheumatology, Leiden, Netherlands
  7. 7Université Paris Saclay, Assistance Publique-Hôpitaux de Paris, Hôpital Bicêtre, Service de Rhumatologie, Le Kremlin-Bicêtre, France

Abstract

Background Methotrexate (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.

Objectives We aimed to build machine learning models based on simple clinical and biological data to predict patient response to MTX.

Methods We 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.

Results We 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 strategy

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.

Conclusion The 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 Interests None declared.

Statistics from Altmetric.com

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.