Objectives To develop a consensual definition for the term ‘early axial spondyloarthritis—axSpA’—and ‘early peripheral spondyloarthritis—pSpA’. Methods The ASAS (Assessment of SpondyloArthritis international Society-Spondyloarthritis EARly definition) steering committee convened an international working group (WG). Five consecutive steps were followed: (1) systematic literature review (SLR); (2) discussion of SLR results within the WG and ASAS community; (3) a three-round Delphi survey inviting all ASAS members to select the items that should be considered for the definition; (4) presentation of Delphi results to the WG and ASAS community and (5) ASAS voting and endorsement (2023 annual meeting). Results Following the SLR, consensus was to proceed with an expert-based definition for early axSpA (81% in favour) but not for pSpA (54% against). Importantly, early axSpA should be based on symptom duration taking solely axial symptoms into account. 151–164 ASAS members participated in the Delphi surveys. Consensus was achieved for considering the following items within early axSpA definition: duration of symptoms ≤2 years; axial symptoms defined as cervical/thoracic/back/buttock pain or morning stiffness; regardless of the presence/absence of radiographic damage. The WG agreed that in patients with a diagnosis of axSpA ‘early axSpA’ should be defined as a duration of ≤2 years of axial symptoms. Axial symptoms should include spinal/buttock pain or morning stiffness and should be considered by a rheumatologist as related to axSpA. The ASAS community endorsed this proposal (88% in favour). Conclusions Early axSpA has newly been defined, based on expert consensus. This ASAS definition should be adopted in research studies addressing early axSpA.

Background Since the publication of the 2011 European Alliance of Associations for Rheumatology (EULAR) recommendations for patient research partner (PRP) involvement in rheumatology research, the role of PRPs has evolved considerably. Therefore, an update of the 2011 recommendations was deemed necessary. Methods In accordance with the EULAR Standardised Operational Procedures, a task force comprising 13 researchers, 2 health professionals and 10 PRPs was convened. The process included an online task force meeting, a systematic literature review and an in-person second task force meeting to formulate overarching principles (OAPs) and recommendations. The level of agreement of task force members was assessed anonymously (0–10 scale). Results The task force developed five new OAPs, updated seven existing recommendations and formulated three new recommendations. The OAPs address the definition of a PRP, the contribution of PRPs, the role of informal caregivers, the added value of PRPs and the importance of trust and communication in collaborative research efforts. The recommendations address the research type and phases of PRP involvement, the recommended number of PRPs per project, the support necessary for PRPs, training of PRPs and acknowledgement of PRP contributions. New recommendations concern the benefits of support and guidance for researchers, the need for regular evaluation of the patient–researcher collaboration and the role of a designated coordinator to facilitate collaboration. Agreements within the task force were high and ranged between 9.16 and 9.96. Conclusion The updated EULAR recommendations for PRP involvement are more substantially based on evidence. Together with added OAPs, they should serve as a guide for researchers and PRPs and will ultimately strengthen the involvement of PRPs in rheumatology research.

Artificial intelligence (AI) is transforming rheumatology research, with a myriad of studies aiming to improve diagnosis, prognosis and treatment prediction, while also showing potential capability to optimise the research workflow, improve drug discovery and clinical trials. Machine learning, a key element of discriminative AI, has demonstrated the ability of accurately classifying rheumatic diseases and predicting therapeutic outcomes by using diverse data types, including structured databases, imaging and text. In parallel, generative AI, driven by large language models, is becoming a powerful tool for optimising the research workflow by supporting with content generation, literature review automation and clinical decision support. This review explores the current applications and future potential of both discriminative and generative AI in rheumatology. It also highlights the challenges posed by these technologies, such as ethical concerns and the need for rigorous validation and regulatory oversight. The integration of AI in rheumatology promises substantial advancements but requires a balanced approach to optimise benefits and minimise potential possible downsides.

To analyse the types and applications of artificial intelligence (AI) technologies to predict treatment response in rheumatoid arthritis (RA) and spondyloarthritis (SpA). A comprehensive search in Medline, Embase, and Cochrane databases (up to August 2024) identified studies using AI to predict treatment response in RA and SpA. Data on study design, AI methodologies, data sources, and outcomes were extracted and synthesized. Findings were summarized descriptively. Of the 4257 articles identified, 89 studies met the inclusion criteria (74 on RA, 7 on SpA, 4 on Psoriatic Arthritis and 4 a mix of them). AI models primarily employed supervised machine learning techniques (e.g., random forests, support vector machines), unsupervised clustering, and deep learning. Data sources included electronic medical records, clinical biomarkers, genetic and proteomic data, and imaging. Predictive performance varied by methodology, with accuracy ranging from 60 to 70% and AUC values between 0.63 and 0.92. Multi-omics approaches and imaging-based models showed promising results in predicting responses to biologic DMARDs and JAK inhibitors but methodological heterogeneity limited generalizability. AI technologies exhibit substantial potential in predicting treatment responses in RA and SpA, enhancing personalized medicine. However, challenges such as methodological variability, data integration, and external validation remain. Future research should focus on refining AI models, ensuring their robustness across diverse patient populations, and facilitating their integration into clinical practice to optimize therapeutic decision-making in rheumatology.

To summarize evidence on the relationship between early treatment (definition based on symptom/disease duration or radiographic damage) and treatment clinical response in patients with SpA. A systematic literature review was conducted in studies on SpA patients treated with NSAIDs or biological/targeted synthetic DMARDs addressing the impact of symptom/disease duration or presence of radiographic damage on treatment response assessed by any disease activity outcome. For categorical outcomes, relative risk, relative risk ratio and number needed to treat were calculated, and for continuous outcomes, differences in differences, to compare groups stratified based on symptom/disease duration or the presence of radiographic damage. From the 8769 articles retrieved, 25 were included and 2 added by hand-search, all in axial SpA (axSpA), most of them with low risk of bias. Twenty-one studies compared groups based on symptom duration (n = 6) or disease duration (n = 15) and seven studies based on absence/presence of radiographic damage (two studies used two comparisons). When early axSpA was defined by symptom duration (<5 years) in randomized controlled trials, early treatment was associated with better outcomes in patients with non-radiographic axSpA [n = 2, ASAS40 relative risk ratio 5.24 (95% CI 1.12, 24.41) and 1.52 (0.60, 3.87)] but not in radiographic axSpA (n = 1) [ASAS20 0.96 (0.53–1.73)]. When early axSpA was defined based on disease duration or radiographic damage, no differences were found between groups. Evidence towards better outcomes in early axSpA is very limited and restricted to non-radiographic axSpA and <5 years symptom duration. When early axSpA is defined based on disease duration or radiographic damage, no differences in response to treatment are found.

Objectives To investigate the influence of gender on disease outcomes in patients with spondyloarthritis (SpA), including across SpA subtypes. Methods Data from 4185 patients of 23 countries with a diagnosis of axial SpA (axSpA), peripheral SpA (pSpA) or psoriatic arthritis (PsA) from the Assessment of SpondyloArthritis International Society (ASAS)-perSpA study were analysed. Associations between gender and disease activity (Ankylosing Spondylitis Disease Activity Score (ASDAS), Bath Ankylosing Spondylitis Disease Activity Score (BASDAI), C-reactive protein (CRP)), function (Bath Ankylosing Spondylitis Functional Index (BASFI)) and overall health (ASAS Health Index (ASAS HI), European Quality of Life Five Dimension (EQ-5D)) outcomes were investigated. Multilevel multivariable linear mixed models adjusted for relevant confounders (and stratified by disease subtype in case of a relevant interaction) were used. Results In total, 65%, 10% and 25% of patients had axSpA, pSpA and PsA, respectively. axSpA was more frequent in males (68%), whereas pSpA and PsA were more frequent in females (53% and 52%, respectively). A significant interaction between gender and disease subtype was found for ASDAS, BASDAI and BASFI. While being female independently contributed to higher BASDAI across the three disease subtypes (with varying magnitude), female gender was only associated with higher ASDAS in pSpA (β (95% CI): 0.36 (0.15 to 0.58)) and PsA (0.25 (0.12 to 0.38)) but not in axSpA (0.016 (−0.07 to 0.11)). No associations were observed between gender and CRP levels. Female gender was associated with higher ASAS HI and EQ-5D, without differences across disease subtype. Conclusion Female gender is associated with less favourable outcome measures across the SpA spectrum. However, while female gender influences BASDAI across the three subtypes, ASDAS is associated with gender only in pSpA and PsA but not in axSpA. Therefore, ASDAS is an appropriate instrument both for females and males with axSpA.