Reference: October 2025 | Issue 10 | Vol 11 | Page 6
Highlights from EULAR 2025
EULAR 2025 featured a number of studies showing how artificial intelligence (AI) is influencing different areas in rheumatology – from diagnosis through to monitoring, risk prediction, and patient communication.
High-resolution CT is the standard to diagnose and assess progression in interstitial lung disease (ILD), a key feature in systemic sclerosis (SSc). AI-assisted interpretation has the potential to improve the quantification and characterisation of SSc-ILD, making it a powerful tool for monitoring.
Francesca Motta from the Humanitas University, Milan, Italy presented new data from an observational study pitting AI-assisted analysis against two radiologists with expertise in thoracic imaging. Results showed that the AI outperformed visual scoring in assessing the progression of fibrosis in patients with SSc-ILD, and showed more significant correlation with values from pulmonary function tests – enabling detection of subtle changes over time.
Seulkee Lee, from the Samsung Medical Center in Korea, also presented findings around AI in diagnosis, investigating a deep learning model that integrates inflammatory and structural changes in sacrum MRI to address the gap between detection of bone marrow oedema and clinical diagnosis of axSpA.
An end-to-end deep learning framework was developed using short tau inversion recovery and T1-weighted MRI sequences to reflect inflammatory and structural changes, respectively. Using data from 291 patients, the classification model demonstrated high sensitivity, specificity, and accuracy.
Of note, it was able to identify six out of nine patients who met clinical, but not ASAS-defined, positive MRI criteria – indicating its ability to detect features beyond conventional criteria. These findings highlight the potential of AI not only to detect specific imaging features, but also to predict clinical diagnoses.
Also in the field of imaging, an international team of researchers explored the role of a supervised deep learning model in ultrasound – specifically to assist in image classification for the presence or absence of lesions typical of giant cell arteritis. The developmental dataset included 3,800 images from 244 patients.
The model outperformed two comparators, with superior diagnostic performance for both the axillary and superficial common temporal arteries – with the exception of smaller branches of the superficial temporal artery that demonstrated lower performance, reflecting inherent diagnostic challenges. Future work will focus on expanding datasets and incorporating multi-centre validation to optimise detection in smaller arteries and enhance model generalisability.
Turning to risk factor identification, Antonio Tonutti, from Humanitas University, in Milan, Italy, presented results from two machine learning models that were developed and tuned to predict interceptable cancers (those diagnosed synchronously or after the first non-Raynaud symptom) in people with SSc using clinical, serological, and treatment data.
Breast cancer was the most common malignancy (32 per cent), followed by lung (16 per cent), gynaecological (8 per cent), colorectal (7.5 per cent), and haematological (7 per cent) cancers. The models demonstrated accuracy of 73-79 per cent, although there were differences in sensitivity, precision, and specificity between the two, with no one model winning out over the other in all parameters.
Key predictors identified included baseline ILD, digital ulcers, oesophageal involvement, telangiectasia, and high C-reactive protein, while taking mycophenolate mofetil was protective in both models. Finetuning and validation of these AI models could offer hope for personalised screening strategies to improve early cancer detection in SSc patients.
Another group shared work on using large language models for risk assessments. A team led by Pallavi Vij from the Royal Wolverhampton NHS Trust, UK, evaluated the effectiveness of these models and prompt engineering techniques in delivering osteoporosis care. They used case-based scenarios to assess capability in risk stratification, treatment recommendations, and referral decisions in accordance with national guidelines.
The findings suggest promising utility for risk stratification and referral triage – potentially reducing administrative burden. However, there was lower concordance in treatment recommendations, which highlights the necessity of clinical expertise for therapeutic decision-making. Further validation studies are needed.
Marco Capodiferro from the University of Bari Aldo Moro, Italy, presented a study on digital biomarkers on a multicentric European cohort (Lausanne, Bari, Bern). The research looked at how advances in deep learning and computer vision might provide opportunities to simplify hand-motion tracking via smartphones – offering significant potential for remote assessment of disease activity in rheumatoid arthritis.
Participants in the study performed five rapid finger flexions with their dominant hand while being recorded on a smartphone camera. The algorithm quantified joint angle changes and time to maximal flexion to analyse kinetic variables. Findings suggest significant associations between these kinetic features and clinical measures, and the model was able to robustly predict low disease activity and remission.
