A Machine Learning Approach for Prediction of CDAI Remission with TNF Inhibitors: A Concept of Precision Medicine from the FIRST Registry.

INTRODUCTION: This study aimed to develop low-cost models using machine learning approaches predicting the achievement of Clinical Disease Activity Index (CDAI) remission 6 months after initiation of tumor necrosis factor inhibitors (TNFi) as primary biologic/targeted synthetic disease-modifying antirheumatic drugs (b/tsDMARDs) for rheumatoid arthritis (RA). METHODS: Data of patients with RA initiating TNFi as first b/tsDMARD after unsuccessful methotrexate treatment were collected from the FIRST registry (August 2003 to October 2022). Baseline characteristics and 6-month CDAI were collected. The analysis used various machine learning approaches including logistic regression with stepwise variable selection, decision tree, support vector machine, and lasso logistic regression (Lasso), with 48 factors accessible in routine clinical practice for the prediction model. Robustness was ensured by k-fold cross validation. RESULTS: Among the approaches tested, Lasso showed the advantages in predicting CDAI remission: with a mean area under the curve 0.704, sensitivity 61.7%, and specificity 69.9%. Predicted TNFi responders achieved CDAI remission at an average rate of 53.2%, while only 26.4% of predicted TNFi non-responders achieved remission. Encouragingly, the models generated relied solely on patient-reported outcomes and quantitative parameters, excluding subjective physician input. CONCLUSIONS: While external cohort validation is warranted for broader applicability, this study highlights the potential for a low-cost predictive model to predict CDAI remission following TNFi treatment. The approach of the study using only baseline data and 6-month CDAI measures, suggests the feasibility of establishing regional cohorts to generate low-cost models tailored to specific regions or institutions. This may facilitate the application of regional/in-house precision medicine strategies in RA management.

This study aims to enhance the management of rheumatoid arthritis by predicting the likelihood of achieving the treatment target­Clinical Disease Activity Index remission within 6 months of initiating tumor necrosis factor inhibitors. In rheumatoid arthritis, the goal is often Clinical Disease Activity Index remission, and the standard approach involves using medications like methotrexate and biologic/targeted synthetic disease-modifying antirheumatic drugs. However, not all patients respond to these treatments, leading to a trial-and-error process of changing medications. Tumor necrosis factor inhibitors are commonly used as the initial biologic/targeted synthetic disease-modifying antirheumatic drugs for patients who do not respond adequately to methotrexate; however, tumor necrosis factor inhibitor treatment may not achieve effective outcomes for all patients. The study, using a cohort of patients with rheumatoid arthritis treated with tumor necrosis factor inhibitor, has developed a model predicting Clinical Disease Activity Index remission with tumor necrosis factor inhibitors. The models use only standard clinical parameters, therefore no special examination or additional cost is required for the predictions. This approach holds the potential to improve rheumatoid arthritis management by reducing the need for trial-and-error approaches and facilitating more personalized and effective treatment strategies. While further validation is necessary, the study also suggests that creating cost-effective models tailored to specific regions or institutions is possible.

Efficacy and Safety of Biologics in Polymyalgia Rheumatica: A Retrospective Study.

INTRODUCTION: The study aimed to determine the efficacy and safety of biological disease-modifying antirheumatic drugs (bDMARDs) in the treatment of polymyalgia rheumatica (PMR) complicated by rheumatoid arthritis (RA). METHODS: Patients with PMR which could be classified as RA and who were treated with bDMARDs were included in the analysis. The primary endpoint was the clinical Polymyalgia Rheumatica Activity Score (Clin-PMR-AS) after 26 weeks of treatment, and the secondary endpoint was adverse events during the observation period. RESULTS: A total of 203 patients with PMR which was resistant or intolerant to glucocorticoids and could be classified as RA were receiving bDMARDs and were enrolled in the study. There were 83, 82, and 38 patients in the tumor necrosis factor inhibitor (TNFi), interleukin-6 receptor inhibitor (IL-6Ri), and cytotoxic T lymphocyte-associated antigen-4-immunoglobulin (CTLA4-Ig) groups, respectively. Twenty-six weeks after bDMARD initiation, Clin-PMR-AS levels were significantly lower in the IL-6Ri group as compared to other groups. Multiple regression analysis was performed with Clin-PMR-AS as the objective variable. Body mass index (BMI), history of bDMARDs, and IL-6Ri use were identified as factors involved in Clin-PMR-AS. After adjustment for group characteristics using inverse probability of treatment weighting with propensity scores, the Clin-PMR-AS score at 26 weeks was significantly lower in the IL-6Ri group (9.0) than in both the TNFi (12.4, p = 0.004) and CTLA4-Ig (15.9, p = 0.003) group. CONCLUSION: IL-6Ri may potentially improve the disease activity of PMR compared to other bDMARDs.