Artificial intelligence and digital health platforms have the potential to support patient education, shared decision-making and engagement across rheumatic and musculoskeletal diseases, as research presented at the European Alliance of Associations for Rheumatology Congress 2026 highlights.

Health literacy remains a key determinant of outcomes in rheumatic and musculoskeletal diseases (RMDs), yet many patients continue to face challenges in accessing reliable, understandable information about their conditions and treatments.

Three patient-focused initiatives were presented at the European Alliance of Associations for Rheumatology (EULAR) Congress 2026 from teams in Germany and the US. They demonstrated how artificial intelligence (AI) and digital technologies can be used to address information gaps, support treatment decisions and improve patient engagement.

Guideline-based AI chatbots and patient acceptance

AI-powered chatbots are being increasingly explored as a scalable approach to patient education.

Dr Johannes Knitza, a rheumatologist and researcher at the University Hospital Giessen and Marburg and the Institute of Digital Medicine at Philipps University Marburg in Germany, presented data from the development and evaluation of 10 disease-specific rheumatology chatbots based on German clinical guidelines.

The chatbots were promoted by patient organisations and rheumatologists, enabling users to ask disease-related questions and provide immediate feedback on their responses.

During the first four months, 5,131 chatbot interactions were recorded across 1,312 individual sessions. Feedback was provided for 2,165 responses, with 92.9% giving a positive ‘like’ rating.

Among 520 users who completed an evaluation questionnaire, 94% reported having a diagnosed RMD – most commonly rheumatoid arthritis, axial spondyloarthritis or systemic lupus erythematosus (SLE).

Some 41% had previously used AI tools for health-related questions and most users reported positive experiences with the guideline-based platform. When asked whether the chatbot was easy to use and that its responses were easy to understand, 86% strongly agreed, while 58% said they preferred using the chatbot to general internet searches.

The findings suggested that disease-specific AI tools grounded in established guidelines may offer clinicians a practical adjunct to traditional patient education resources.

Reference: Wilhelmi T et al. Turning Guidelines to Answers: Patient Evaluation of AI-Based Guideline Chatbots in Rheumatology. Presented at EULAR 2026; OP0256-PARE. Ann Rheum Dis 2026; doi: 10.1136/annrheumdis-2026-eular.D.57.

Large language models and patient-centred measures

A separate study examined the ability of large language models (LLMs) to answer common patient questions about connective tissue diseases, comparing three general-purpose AI models with Google Search.

The analysis focused on the 20 most frequently asked questions from patients with SLE, idiopathic inflammatory myopathy, Sjögren’s disease and systemic sclerosis. Both patients and rheumatologists rated AI-generated responses favourably for empathy, trustworthiness and comprehensibility.

Importantly, physicians judged medical correctness to be consistently accurate across the disease areas evaluated. While Google Search generally provided medically accurate information, investigators found that LLMs offered additional benefits in the way information was communicated to patients.

Presenting the findings, Dr Phillip Kremer, medical doctor in the Division of Rheumatology and Systemic Inflammatory Diseases at University Medical Center Hamburg-Eppendorf III, Germany, said: ‘While Google-based information was largely medically correct, large-language models offered added value in terms of clarity and empathy.

‘When implemented with appropriate safeguards and physician oversight, these tools could complement established patient education strategies in rheumatology.’

Reference: Kremer P et al. Beyond “Dr Google”: Performance of Large Language Models in Patient Counselling for Connective Tissue Diseases. Presented at EULAR 2026; OP013-PARE. Ann Rheum Dis 2026; doi: 10.1136/annrheumdis-2026-eular.D.132.

Addressing steroid burden through digital education

Digital platforms may also help to address specific educational needs that are not routinely covered during consultations. One example presented at EULAR was ‘Steroids and Me (Sam)’ – a web-based platform designed to support people receiving glucocorticoid therapy.

Long-term glucocorticoid use is associated with multiple adverse effects, yet investigators noted a longstanding gap in patient education on how to recognise, prevent and manage steroid-related toxicity.

Developed in response to this unmet need, Sam was designed as a so-called ‘digital companion’ to empower patients to take a more active role in their care and support shared decision-making around glucocorticoid treatment.

The platform combines educational content with a patient journey tracker, allowing users to record steroid-related side effects in real time and share information with clinicians during their follow-up appointments.

Accessible via phone, tablet or computer, the platform was developed following consultation with patient advocacy groups and patient focus groups alongside physicians and scientists.

Content is presented in plain language and covers common and lesser-known adverse effects, practical management strategies and expert-led educational videos. Educational materials were developed by physician experts and align with validated clinical outcome assessments used to measure steroid toxicity.

The researchers reported that the platform has been implemented through collaborations with patient advocacy groups across multiple disease areas, including lupus, vasculitis, sarcoidosis, myasthenia gravis, immunoglobulin G4-related disease, asthma, and inflammatory bowel disease.

More than 25,000 users have accessed the Sam platform to date, spending an average of 5.4 minutes on the platform – around 10-times longer than reported for global health websites.

Following its launch in 2024, the platform experienced rapid growth, supported by patient advocacy partnerships and search optimisation strategies. According to the investigators, this level of engagement suggests that patients are actively seeking practical, accessible information about glucocorticoid toxicity and management.

Future development plans include integrating clinical outcome assessments of steroid toxicity into clinical trials to capture the patient experience alongside clinical measures, support steroid stewardship initiatives, strengthen clinical integration and expand partnerships across additional disease communities.

Reference: Stone M et al. Steroids and Me (Sam): Development and Validation of a Patient-Centered Digital Platform for Glucocorticoid Education and Shared Decision-Making. Presented at EULAR 2026; POS1388-PARE. Ann Rheum Dis 2026; doi: 10.1136/annrheumdis-2026-eular.D.42.

What might this mean for clinical practice?

These studies presented at EULAR 2026 illustrate how digital technologies are evolving from simple information resources into tools that may support education, shared decision-making and patient empowerment.

While clinician oversight remains important, guideline-based chatbots, LLMs and condition-specific digital platforms could help patients to access reliable information in a format that is understandable, engaging and tailored to their needs.

For healthcare professionals, these developments may offer new opportunities to reinforce education, improve health literacy and support more informed conversations in routine rheumatology care.