000151597 001__ 151597
000151597 005__ 20251017144608.0
000151597 0247_ $$2doi$$a10.1093/rheumatology/keaf073
000151597 0248_ $$2sideral$$a143329
000151597 037__ $$aART-2025-143329
000151597 041__ $$aeng
000151597 100__ $$aLledó-Ibáñez, Gema M.
000151597 245__ $$aCAPI-Detect: machine learning in capillaroscopy reveals new variables influencing diagnosis
000151597 260__ $$c2025
000151597 5060_ $$aAccess copy available to the general public$$fUnrestricted
000151597 5203_ $$aObjectives
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.
CAPI-Detect, an ML-based model, provides an unbiased, quantitative analysis of capillary structure, shape, size and density, significantly improving capillaroscopic pattern identification.
000151597 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000151597 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000151597 700__ $$0(orcid)0000-0002-9868-6498$$aSáez Comet, Luis$$uUniversidad de Zaragoza
000151597 700__ $$aFreire Dapena, Mayka
000151597 700__ $$aMesa Navas, Miguel
000151597 700__ $$aMartín Cascón, Miguel
000151597 700__ $$aGuillén del Castillo, Alfredo
000151597 700__ $$aSimeon, Carmen Pilar
000151597 700__ $$aMartínez Robles, Elena
000151597 700__ $$aTodolí Parra, José
000151597 700__ $$aVarela, Diana Cristina
000151597 700__ $$aMaldonado, Génesis
000151597 700__ $$0(orcid)0000-0002-7815-8356$$aMarín, Adela$$uUniversidad de Zaragoza
000151597 700__ $$aPérez Abad, Laura
000151597 700__ $$aAramburu, Jimena
000151597 700__ $$aVela, Laura
000151597 700__ $$aRamos Ibáñez, Eduardo
000151597 700__ $$aGracia Tello, Borja del Carmelo$$uUniversidad de Zaragoza
000151597 7102_ $$11007$$2610$$aUniversidad de Zaragoza$$bDpto. Medicina, Psiqu. y Derm.$$cArea Medicina
000151597 773__ $$g(2025), keaf073 [9 pp.]$$pRheumatology (Oxford)$$tRheumatology (Oxford)$$x1462-0324
000151597 8564_ $$s1757543$$uhttps://zaguan.unizar.es/record/151597/files/texto_completo.pdf$$yVersión publicada
000151597 8564_ $$s2638463$$uhttps://zaguan.unizar.es/record/151597/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000151597 909CO $$ooai:zaguan.unizar.es:151597$$particulos$$pdriver
000151597 951__ $$a2025-10-17-14:16:00
000151597 980__ $$aARTICLE