EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY-NC-ND 4.0

Machine Learning to Predict Remission Between 6 and 24 Months in Rheumatoid Arthritis: Insights From JAK, an International Registry Collaboration

Zubeyir Salis iD, Denis Mongin, Denis Choquette, Louis Coupal, Catalin Codreanu, Florenzo Iannone iD, Roberto Caporali, Tore K Kvien iD, Sella Provan iD, Ruth Fritsch-Stork, Dan Nordström, Nina Trokovic und 11 weitere

Arthritis & Rheumatology · 2026

DOI: 10.1002/art.70165 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Arthritis & Rheumatology, 2026. Verfasst von Zubeyir Salis und 22 weiteren Autor:innen. Beteiligte Einrichtung: University of Montpellier and Physiology and Experimental Medicine of the Heart and Muscles, Montpellier, France. Hauptthemen laut MEDLINE: Arthritis, Rheumatoid, Antirheumatic Agents, Machine Learning. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop, externally validate, and simplify a machine learning model to predict remission between 6 and 24 months in patients with rheumatoid arthritis (RA) initiating tumor necrosis factor inhibitors, JAK inhibitors, interleukin‐6 inhibitors, abatacept, or rituximab using data from 11 international registries in the JAK‐pot collaboration.

Methods

We analyzed 21,675 treatment courses for model training, 5,418 courses for internal validation, and 1,807 courses from Switzerland for external validation. Remission was defined as a Clinical Disease Activity Index score ≤2.8 within 6 to 24 months after treatment initiation or switching. An XGBoost model was trained on 63 baseline demographic and clinical variables. Model performance was evaluated using the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Predictor contributions were quantified using Shapley Additive Explanations values. A simplified model using the top 10 predictors and a logistic regression benchmark were also evaluated.

Results

In external validation, the full model achieved an AUC of 0.797 (95% confidence interval 0.774–0.821), sensitivity of 0.804, specificity of 0.650, PPV of 0.454, and NPV of 0.902. The simplified model performed comparably (AUC 0.802). Logistic regression using the same 10 predictors achieved an AUC of 0.809. Key predictors included patient global assessment, 28‐tender joint count, previous biologic/targeted synthetic disease‐modifying antirheumatic drug exposure, and Health Assessment Questionnaire Disability Index score.

Conclusion

Using routinely collected baseline data across 11 registries, prediction of remission showed limited discrimination and was best suited to ruling out remission. Performance was similar for a 10‐variable model and logistic regression, indicating limited incremental value of model complexity without richer predictors. image

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Arthritis, RheumatoidAntirheumatic AgentsMachine LearningHumansRegistriesFemaleRemission InductionMalePredictive Learning ModelsMiddle AgedRituximabBoosting Machine Learning AlgorithmsPredictive Value of TestsPrediction AlgorithmsAgedTumor Necrosis Factor InhibitorsAdultSensitivity and SpecificityLogistic Models

Substanzen

Antirheumatic AgentsRituximabTumor Necrosis Factor Inhibitors

Autor:innen und Institutionen

  • University of Montpellier and Physiology and Experimental Medicine of the Heart and Muscles, Montpellier, France.
  • Division of Rheumatology, Geneva University Hospital, Geneva, Switzerland.
  • Geneva Center for Inflammation Research, Faculty of Medicine, University of Geneva, Geneva, Switzerland.
  • Centre Hospitalier de l'Université de Montréal, Institut de Recherche en Rhumatologie, Montréal, Québec, Canada.
  • Center of Rheumatic Diseases, University of Medicine and Pharmacy, Bucharest, Romania.
  • Rheumatology Unit, Department of Precision and Regenerative Medicine and Ionian Area, University of Bari Aldo Moro, Bari, Italy.

ORCID-Profile: Zubeyir Salis, Florenzo Iannone, Tore K Kvien, Sella Provan, Michele Iudici

Zitieren

APA

Salis, Z., Mongin, D., Choquette, D., Coupal, L., Codreanu, C., Iannone, F., Caporali, R., Kvien, T. K., Provan, S., Fritsch-Stork, R., Nordström, D., Trokovic, N., Pavelka, K., Závada, J., Rodrigues, A., Rotar, Z., Sidiropoulos, P., Flouri, I., Lamacchia, C., …, & Finckh, A. (2026). Machine Learning to Predict Remission Between 6 and 24 Months in Rheumatoid Arthritis: Insights From JAK, an International Registry Collaboration. Arthritis & Rheumatology. https://doi.org/10.1002/art.70165

Vancouver

Salis Z, Mongin D, Choquette D, Coupal L, Codreanu C, Iannone F, et al. Machine Learning to Predict Remission Between 6 and 24 Months in Rheumatoid Arthritis: Insights From JAK, an International Registry Collaboration. Arthritis & Rheumatology. 2026. doi:10.1002/art.70165

BibTeX
@article{Salis2026,
  author = {Salis, Zubeyir and Mongin, Denis and Choquette, Denis and Coupal, Louis and Codreanu, Catalin and Iannone, Florenzo and Caporali, Roberto and Kvien, Tore K and Provan, Sella and Fritsch-Stork, Ruth and Nordström, Dan and Trokovic, Nina and Pavelka, Karel and Závada, Jakub and Rodrigues, Ana and Rotar, Ziga and Sidiropoulos, Prodromos and Flouri, Irini and Lamacchia, Céline and Iudici, Michele and Courvoisier, Delphine and Lauper, Kim and Finckh, Axel},
  title = {Machine Learning to Predict Remission Between 6 and 24 Months in Rheumatoid Arthritis: Insights From JAK, an International Registry Collaboration},
  journal = {Arthritis & Rheumatology},
  year = {2026},
  doi = {10.1002/art.70165}
}
Kostenlos starten →