[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126264-en":3,"doc-seo-126264-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126264,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","CAPI-Detect: machine learning in capillaroscopy reveals new variables influencing diagnosis","Nailfold videocapillaroscopy (NVC) is used for diagnosing systemic sclerosis (SSc) and distinguishing primary from secondary Raynaud’s phenomenon. The CAPI-Score algorithm classifies capillaroscopic scleroderma patterns using a limited set of capillary variables, with potential examiner-related bias. This study develops CAPI-Detect, a CatBoost-based machine learning model trained on 1,780 blinded analyses with automated extraction of 24 quantitative variables, minimizing bias. Performance is validated on partial and full consensus datasets.","Rheumatology, 2025, 64, 3667–3675  \n[https://doi.org/10.1093/rheumatology/keaf073](https://doi.org/10.1093/rheumatology/keaf073)[ ](https://doi.org/10.1093/rheumatology/keaf073)Advance access publication 7 February 2025  \nOriginal Article  \nRheumatology  \nClinical science  \nCAPI-Detect: machine learning in capillaroscopy reveals new variables influencing diagnosis  \nGema M. Lled-Ib~nez 1,􀀃 , Luis Sez Comet2, Mayka Freire Dapena 3, Miguel Mesa Navas 4  \n,  \nMiguel Martn Cascn 5, Alfredo Guilln del Castillo 6, Carmen Pilar Simeon6,  \nElena Martinez Robles 7, Jos Todol  Parra8, Diana Cristina Varela 9, Gnesis Maldonado 10  \n,  \nAdela Marn 11, Laura Prez Abad11, Jimena Aramburu 11, Laura Vela2, Eduardo Ramos Ib~nez 12, Borja del Carmelo Gracia Tello 11  \n1 Department of Autoimmune Diseases, Institut Clinic de Medicina i Dermatologia, Hospital Cl de Barcelona, Barcelona, Spain 2 Department of Internal Medicine, Hospital Universitario Miguel Servet, Zaragoza, Spain  \n3 Department of Internal Medicine, Hospital Cl Universitario de SAntiago de Compostela, La Coru~na, Spain 4 Rheumatology Department, Cl Universitaria Bolivariana, Universidad Pontificia Bolivariana, Medell 􀀓ın, Colombia 5 Department of Internal Medicine, Hospital General Universitario Morales Meseguer, Murcia, Spain  \n6 Department of Internal Medicine, Hospital Universitario Vall d’Hebron, Barcelona, Spain 7 Department of Internal Medicine, Hospital Universitario La Paz, Madrid, Spain 8 Department of Internal Medicine, Hospital Universitario La F, Valencia, Spain 9 Rheumatology Department, Hospital General de Medell 􀀓ın, Medell 􀀓ın, Colombia 10Vanderbilt University, Nashville, Tennessee, USA  \n11 Department of Internal Medicine, Hospital Cl Universitario Lozano Blesa, Zaragoza, Spain 12 Ingeniero Informtico, Universidad de Zaragoza, Zaragoza, Spain  \n􀀃 Correspondence to: Gema M. Lled-Ib~nez, Department of Autoimmune Diseases, Hospital Cl de Barcelona, Carrer Villarroel 170, 08036 Barcelona,  \nSpain. E-mail: [gemma.lleiba@gmail.com](gemma.lleiba@gmail.com)  \nAbstract  \nObjectives: 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.  \nMethods: 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.  \nResults: 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.  \nConclusions: CAPI-Detect, an ML-based model, provides an unbiased, quantitative analysis of capillary structure, shape, size and density, significantly improving capillaroscopic pattern identification.  \nKeywords: nailfold capillaroscopy, systemic sclerosis, disease pattern, examiner consensus, software-based analysis, quantitative analysis, CatBoost algorithm, machine learning-based model.  \nRheumatology key messages  \n􀀏 M","cbCaigGWGhxEZlab","https://ap.wps.com/l/cbCaigGWGhxEZlab","pdf",1756683,5,1,9,"English","en",105,"# Abstract\n## Objectives\n## Methods\n## Results\n## Conclusions\n# Key messages\n# Introduction","[{\"question\":\"What is CAPI-Detect and what problem does it address?\",\"answer\":\"CAPI-Detect is a machine learning model for classifying capillaroscopic scleroderma patterns. It targets improved identification while reducing examiner-related bias compared with simpler scoring approaches.\"},{\"question\":\"How were the training data and labels created in this study?\",\"answer\":\"A total of 1,780 capillaroscopies were randomly and blindly analysed by three to four trained observers. Consensus labels were defined as partial agreement among all but one observer or full unanimous agreement.\"},{\"question\":\"What inputs does CAPI-Detect use for classification?\",\"answer\":\"It uses automated NVC analysis to extract 24 quantitative capillary architecture-related variables, which are then used within a CatBoost classification model.\"}]","CAPI-Detect: machine learning in capillaroscopy reveals new variables influencing diagnosis | PDF",1785904129,23,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"capi-detect-machine-learning-in-capillaroscopy-reveals-new-variables-influencing-diagnosis","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/capi-detect-machine-learning-in-capillaroscopy-reveals-new-variables-influencing-diagnosis/126264/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is CAPI-Detect and what problem does it address?","Question",{"text":77,"@type":78},"CAPI-Detect is a machine learning model for classifying capillaroscopic scleroderma patterns. It targets improved identification while reducing examiner-related bias compared with simpler scoring approaches.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How were the training data and labels created in this study?",{"text":82,"@type":78},"A total of 1,780 capillaroscopies were randomly and blindly analysed by three to four trained observers. Consensus labels were defined as partial agreement among all but one observer or full unanimous agreement.",{"name":84,"@type":75,"acceptedAnswer":85},"What inputs does CAPI-Detect use for classification?",{"text":86,"@type":78},"It uses automated NVC analysis to extract 24 quantitative capillary architecture-related variables, which are then used within a CatBoost classification model.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]