Related Experiment Video
Updated: Aug 26, 2025
An Adoptive Transfer Model of Rheumatoid Arthritis in Mice
Published on: June 6, 2025
Predictive model to identify multiple failure to biological therapy in patients with rheumatoid arthritis
Marta Novella-Navarro1, Diego Benavent2, Virginia Ruiz-Esquide3
1Rheumatology, Hospital Universitario La Paz, Paseo de la Castellana, 28046, Madrid, Spain.
Background:
Despite advances in the treatment of rheumatoid arthritis (RA) and the wide range of therapies available, there is a percentage of patients whose treatment presents a challenge for clinicians due to lack of response to multiple biologic and target-specific disease-modifying antirheumatic drugs (b/tsDMARDs).
Objective:
To develop and validate an algorithm to predict multiple failure to biological therapy in patients with RA.
Design:
Observational retrospective study involving subjects from a cohort of patients with RA receiving b/tsDMARDs.
Methods:
Based on the number of prior failures to b/tsDMARDs, patients were classified as either multi-refractory (MR) or non-refractory (NR). Patient characteristics were considered in the statistical analysis to design the predictive model, selecting those variables with a predictive capability. A decision algorithm known as 'classification and regression tree' (CART) was developed to create a prediction model of multi-drug resistance. Performance of the prediction algorithm was evaluated in an external independent cohort using area under the curve (AUC).
Results:
A total of 136 patients were included: 51 MR and 85 NR. The CART model was able to predict multiple failures to b/tsDMARDs using disease activity score-28 (DAS-28) values at 6 months after the start time of the initial b/tsDMARD, as well as DAS-28 improvement in the first 6 months and baseline DAS-28. The CART model showed a capability to correctly classify 94.1% NR and 87.5% MR patients with a sensitivity = 0.88, a specificity = 0.94, and an AUC = 0.89 (95% CI: 0.74-1.00). In the external validation cohort, 35 MR and 47 NR patients were included. The AUC value for the CART model in this cohort was 0.82 (95% CI: 0.73-0.9).
Conclusion:
Our model correctly classified NR and MR patients based on simple measurements available in routine clinical practice, which provides the possibility to characterize and individualize patient treatments during early stages.
Insights
A new algorithm predicts rheumatoid arthritis patients likely to fail multiple biologic therapies. This tool uses early disease activity scores to identify non-responders, aiding personalized treatment strategies.
Area of Science:
- Rheumatology
- Clinical Prediction Modeling
- Pharmacogenomics
Background:
- Rheumatoid arthritis (RA) treatment faces challenges with patients resistant to multiple biologic and targeted synthetic disease-modifying antirheumatic drugs (b/tsDMARDs).
- Identifying patients likely to experience multiple treatment failures is crucial for optimizing RA management.
Purpose of the Study:
- To develop and validate a predictive algorithm for identifying patients with RA who will experience multiple failures to b/tsDMARDs.
- To enable early characterization and individualization of treatment strategies for RA patients.
Main Methods:
- A retrospective observational study classified RA patients as multi-refractory (MR) or non-refractory (NR) based on prior b/tsDMARD failures.
- A Classification and Regression Tree (CART) algorithm was developed using baseline and early (6-month) disease activity score-28 (DAS-28) metrics.
- The CART model's performance was validated in an independent external cohort, assessing predictive capability via Area Under the Curve (AUC).
Main Results:
- The CART model accurately predicted multiple b/tsDMARD failures using DAS-28 at 6 months, DAS-28 improvement, and baseline DAS-28.
- The model achieved high classification accuracy: 94.1% for NR and 87.5% for MR patients in the initial cohort (AUC=0.89).
- External validation demonstrated a robust AUC of 0.82, confirming the model's generalizability.
Conclusions:
- A validated CART model effectively predicts multiple b/tsDMARD failures in RA patients.
- The algorithm utilizes readily available clinical data (DAS-28) for early patient stratification.
- This tool supports individualized treatment decisions in early RA management, improving therapeutic outcomes.
More Related Videos
07:44Author Spotlight: Implementation of BIVA for Analyzing Disease Risk Factors in Patients with Low Body Cell Mass
Published on: July 14, 2023
04:50Preliminary Study on Acupuncture Combined with Grain-sized Moxibustion for Treating Rheumatoid Arthritis with Finger Joint Pain
Published on: May 16, 2025