Vollenhoven, Ronald van

Objective To test the ability of machine learning (ML) approaches with clinical and genomic biomarkers to predict methotrexate treatment response in patients with early rheumatoid arthritis (RA). Methods Demographic, clinical, and genomic data from 643 patients of European ancestry with early RA (mean age 54 years; 70% female) subdivided into a training (n = 336) and validation cohort (n = 307) were used. The genomic data comprised 160 single‐nucleotide polymorphisms (SNPs) previously associated with RA or methotrexate metabolism. Response to methotrexate monotherapy was defined as good or moderate by the European Alliance of Associations for Rheumatology (EULAR) response criteria at the 3‐month follow‐up. Supervised ML methods were trained with 5 repeats and 10‐fold cross‐validation using the training cohort. Prediction performance was validated in the independent validation cohort. Results Supervised ML methods combining age, sex, smoking, rheumatoid factor, baseline Disease Activity Score in 28 joints (DAS28) scores and 160 SNPs predicted EULAR response at 3 months with the area under the receiver operating curve of 0.84 ( P = 0.05) in the training cohort and achieved a prediction accuracy of 76% ( P = 0.05) in the validation cohort (sensitivity 72%, specificity 77%). Intergenic SNPs rs12446816, rs13385025, rs113798271, and ATIC (rs2372536) had variable importance above 60.0 and along with baseline DAS28 scores were among the top predictors of methotrexate response. Conclusion Pharmacogenomic biomarkers combined with baseline DAS28 scores can be useful in predicting response to methotrexate in patients with early RA. Applying ML to predict treatment response holds promise for guiding effective RA treatment choices, including timely escalation of RA therapies.

A European League Against Rheumatism–American College of Rheumatology working group consisting of practicing and academic rheumatologists, a rheumatology researcher, and a patient representative created a succinct general statement describing rheumatic and musculoskeletal diseases (RMDs) in adults and children in language that can be used in conversations with the lay public, media, healthcare providers, and other stakeholders. Based on the literature review, several elements were deemed important for inclusion in the description of RMDs. First, RMDs encompass many different diseases that can affect individuals at any age, including children. Second, there are various pathophysiological pathways underlying different RMDs. Third, the impact of RMDs on individuals and society should be emphasized. The working group agreed that the language should be comprehensible to the lay public. Thus, the following description of RMDs has been developed: “Rheumatic and musculoskeletal diseases (RMDs) are a diverse group of diseases that commonly affect the joints, but can affect any organ of the body. There are more than 200 different RMDs, affecting both children and adults. They are usually caused by problems of the immune system, inflammation, infections, or gradual deterioration of joints, muscles, and bones. Many of these diseases are long term and worsen over time. They are typically painful and limit function. In severe cases, RMDs can result in significant disability, having a major impact on both quality of life and life expectancy.” This description can be used by rheumatology groups, researchers, and those who work in advocacy and education related to RMDs.