Objectives: Nailfold videocapillaroscopy (NVC) is the gold standard for diagnosing SSc and differentiating primary from secondary RP. The CAPI-Score algorithm, designed for simplicity, classifies capillaroscopy scleroderma patterns (CSPs) using a limited number of capillary variables. This study aims to develop a more advanced machine learning (ML) model to improve CSP identification by integrating a broader range of statistical variables while minimizing examiner-related bias. Methods: A total of 1780 capillaroscopies were randomly and blindly analysed by three to four trained observers. Consensus was defined as agreement among all but one observer (partial consensus) or unanimous agreement (full consensus). Capillaroscopies with at least partial consensus were used to train ML-based classification models using CatBoost software, incorporating 24 capillary architecture-related variables extracted via automated NVC analysis. Validation sets were employed to assess model performance. Results: Of the 1490 capillaroscopies classified with consensus, 515 achieved full consensus. The model, evaluated on partial and full consensus datasets, achieved 0.912, 0.812 and 0.746 accuracy for distinguishing SSc from non-SSc, among SSc patterns, and between normal and non-specific patterns, respectively. When evaluated on full consensus only, accuracy improved to 0.910, 0.925 and 0.933. CAPI-Detect outperformed CAPI-Score, revealing novel capillary variables critical to ML-based classification. Conclusions: CAPI-Detect, an ML-based model, provides an unbiased, quantitative analysis of capillary structure, shape, size and density, significantly improving capillaroscopic pattern identification.

Background: Systemic sclerosis (SSc) is a multisystem autoimmune disease characterised by fibrosis, vasculopathy, and immune dysfunction. Silica exposure has been associated with a more aggressive phenotype of the disease, including diffuse cutaneous involvement and interstitial lung disease. This study aims to identify proteomic differences between SSc patients exposed to silica and those not exposed to silica. Methods: An observational study of 32 SSc patients (11 silica-exposed and 21 non-exposed) was performed, with occupational history and quantitative proteomic analysis using SWATH-MS mass spectrometry. Differentially expressed proteins were analysed, and functional pathway enrichment was performed. Results: Eight proteins showed significant differences between groups, all with reduced levels in silica-exposed patients: adiponectin, immunoglobulins (IGLV3-19, IGLV2-18), complement C2, alpha-2-macroglobulin, vitronectin, cytoplasmic actin 2, and pigment epithelium-derived factor. Alterations in pathways related to fibrinolysis, complement activation, and inflammation were highlighted, suggesting that silica exposure may influence the pathogenesis of SSc and worsen its clinical course. Conclusions: This study supports the hypothesis that silica exposure is not only a triggering factor for SSc, but is also modulating its progression through inflammatory, procoagulant, and fibrotic pathways. The identification of proteomic biomarkers could contribute to the phenotypic classification of patients and the development of personalised therapies. Future studies should expand the cohort and further investigate the functional mechanisms of these proteins in SSc.