The first objective of this study was to implement and assess the performance and reliability of a vision transformer (ViT)-based deep-learning model, an ‘off-the-shelf’ artificial intelligence solution, for identifying distinct signs of microangiopathy in nailfold capilloroscopy (NFC) images of patients with SSc. The second objective was to compare the ViT’s analysis performance with that of practising rheumatologists. NFC images of patients prospectively enrolled in our European Scleroderma Trials and Research group (EUSTAR) and Very Early Diagnosis of Systemic Sclerosis (VEDOSS) local registries were used. The primary outcome investigated was the ViT’s classification performance for identifying disease-associated changes (enlarged capillaries, giant capillaries, capillary loss, microhaemorrhages) and the presence of the scleroderma pattern in these images using a cross-fold validation setting. The secondary outcome involved a comparison of the ViT’s performance vs that of rheumatologists on a reliability set, consisting of a subset of 464 NFC images with majority vote–derived ground-truth labels. We analysed 17 126 NFC images derived from 234 EUSTAR and 55 VEDOSS patients. The ViT had good performance in identifying the various microangiopathic changes in capillaries by NFC [area under the curve (AUC) from 81.8% to 84.5%]. In the reliability set, the rheumatologists reached a higher average accuracy, as well as a better trade-off between sensitivity and specificity compared with the ViT. However, the annotators’ performance was variable, and one out of four rheumatologists showed equal or lower classification measures compared with the ViT. The ViT is a modern, well-performing and readily available tool for assessing patterns of microangiopathy on NFC images, and it may assist rheumatologists in generating consistent and high-quality NFC reports; however, the final diagnosis of a scleroderma pattern in any individual case needs the judgement of an experienced observer.

Objective.: To address the hypothesis that very early patients with systemic sclerosis (SSc) are a heterogeneous group with mild or early disease, we analyzed the extent of heterogeneity in clinical, epidemiological, and immunological characteristics of these patients.Methods.: We performed an analysis of very early SSc patients from the Zurich cohort, who fulfilled neither the 2013 American College of Rheumatology (ACR)/European League Against Rheumatism nor the 1980 ACR classification criteria, but had a clinical expert diagnosis of SSc with Raynaud phenomenon (RP) and additional features of SSc (puffy fingers, SSc-specific antibodies, SSc pattern on nailfold capillaroscopy, or any organ involvement characteristic for SSc). Disease duration was defined from first RP symptom.Results.: One hundred and two patients fulfilled the inclusion criteria and were analyzed. Their clinical presentation was heterogeneous with the large majority presenting with RP, antinuclear antibodies, and nailfold capillaroscopy changes, but with varying presentations of other features such as SSc-specific antibodies and early signs of organ involvement. While 54.1% (52/96) of patients had a disease duration of < 5 years, as many as 29.1% (28/96) of patients had a disease duration of > 10 years, indicating long-standing mild disease. Patients with very early, potentially progressive disease did not differ from patients with long-standing mild disease in terms of their clinical features at first presentation.Conclusion.: This study showed that patients with very early SSc are a mixture with mild or early disease. This needs to be considered in clinical practice for risk stratification and for the study design of patients considered as early SSc.

Clinical aspects; Authors: A. Garaiman, C. Mihai, R. Dobrota, S. Jordan, B. Maurer, J. Flemming, O. Distler, M.O. Becker

Objective: To develop and validate the prognostic prediction model DU-VASC to assist the clinicians in decision-making regarding the use of platelet inhibitors (PIs) for the management of digital ulcers in patients with systemic sclerosis. Secondly, to assess the incremental value of PIs as predictor. Methods: We analysed patient data from the European Scleroderma Trials and Research group registry (one time point assessed). Three sets of derivation/validation cohorts were obtained from the original cohort. Using logistic regression, we developed a model for prediction of digital ulcers (DUs). C-Statistics and calibration plots were calculated to evaluate the prediction performance. Variable importance plots and the decrease in C-statistics were used to address the importance of the predictors. Results: Of 3710 patients in the original cohort, 487 had DUs and 90 were exposed to PIs. For the DU-VASC model, which includes 27 predictors, we observed good calibration and discrimination in all cohorts (C-statistic = 81.1% [95% CI: 78.9%, 83.4%] for the derivation and 82.3% [95% CI: 779.3%, 85.3%] for the independent temporal validation cohort). Exposure to PIs was associated with absence of DUs and was the most important therapeutic predictor. Further important factors associated with absence of DUs were lower modified Rodnan skin score, anti-Scl-70 negativity and normal CRP. Conversely, the exposure to phosphodiesterase-5 inhibitor, prostacyclin analogues or endothelin receptor antagonists seemed to be associated with the occurrence of DUs. Nonetheless, previous DUs remains the most impactful predictor of DUs. Conclusion: The DU-VASC model, with good calibration and discrimination ability, revealed that PI treatment was the most important therapy-related predictor associated with reduced DU occurrence.

Objectives: Gastroesophageal reflux disease (GERD) is frequent in systemic sclerosis (SSc) and could predict progression of interstitial lung disease (ILD). We aimed to analyse (1) the prevalence of GERD among SSc-ILD patients, (2) its association with disease characteristics and (3) predictive factors for ILD progression in SSc-ILD patients with GERD. Methods: SSc patients from the EUSTAR database with ILD were included. GERD was labelled as present if reflux/dysphagia was reported at the baseline visit or before. Disease characteristics of patients with and without GERD were compared at baseline. ILD progression was defined as relative FVC decline ≥10% or relative FVC decline between 5–9% in association with relative DLCO decline of ≥15% over 12 ± 3 months of follow-up. Prognostic factors for ILD progression, overall survival and progression-free survival in SSc-ILD patients with GERD were tested by multivariable Cox regression. Results: A total of 5462 SSc-ILD patients were included, 4400 (80.6%) had GERD. Patients with GERD presented more frequently with diffuse cutaneous SSc (OR: 1.44 [1.22–1.69], P < 0.001) and more severe lung involvement with lower FVC (85.8 ± 22.1 vs 90.2 ± 20.1, P < 0.001), lower DLCO (60.8 ± 19.7 vs 65.3 ± 20.6, P < 0.001) and worse performance at the 6-min walking test. Female sex (HR: 1.39 [1.07–1.80], P = 0.012) and older age (HR: 1.02 [1.01–1.03], P < 0.001) independently predicted ILD progression in SSc-ILD patients with GERD. Conclusion: SSc-ILD patients with GERD appear to suffer from a more severe SSc disease. In this population, female sex may be considered a risk factor for ILD progression.