{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T01:37:08Z","timestamp":1785893828610,"version":"3.56.0"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T00:00:00Z","timestamp":1649116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Inferential statistical methods failed in identifying reliable biomarkers and risk factors for relapsing giant cell arteritis (GCA) after glucocorticoids (GCs) tapering. A ML approach allows to handle complex non-linear relationships between patient attributes that are hard to model with traditional statistical methods, merging them to output a forecast or a probability for a given outcome.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>The objective of the study was to assess whether ML algorithms can predict GCA relapse after GCs tapering.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>GCA patients who underwent GCs therapy and regular follow-up visits for at least 12 months, were retrospectively analyzed and used for implementing 3 ML algorithms, namely, Logistic Regression (LR), Decision Tree (DT), and Random Forest (RF). The outcome of interest was disease relapse within 3 months during GCs tapering. After a ML variable selection method, based on a XGBoost wrapper, an attribute core set was used to train and test each algorithm using 5-fold cross-validation. The performance of each algorithm in both phases was assessed in terms of accuracy and area under receiver operating characteristic curve (AUROC).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The dataset consisted of 107 GCA patients (73 women, 68.2%) with mean age ( \u00b1 SD) 74.1 ( \u00b1 8.5) years at presentation. GCA flare occurred in 40\/107 patients (37.4%) within 3 months after GCs tapering. As a result of ML wrapper, the attribute core set with the least number of variables used for algorithm training included presence\/absence of diabetes mellitus and concomitant polymyalgia rheumatica as well as erythrocyte sedimentation rate level at GCs baseline. RF showed the best performance, being significantly superior to other algorithms in accuracy (RF 71.4% vs LR 70.4% vs DT 62.9%). Consistently, RF precision (72.1%) was significantly greater than those of LR (62.6%) and DT (50.8%). Conversely, LR was superior to RF and DT in recall (RF 60% vs LR 62.5% vs DT 47.5%). Moreover, RF AUROC (0.76) was more significant compared to LR (0.73) and DT (0.65).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>RF algorithm can predict GCA relapse after GCs tapering with sufficient accuracy. To date, this is one of the most accurate predictive modelings for such outcome. This ML method represents a reproducible tool, capable of supporting clinicians in GCA patient management.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fimmu.2022.860877","type":"journal-article","created":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T13:17:22Z","timestamp":1649164642000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Validity of Machine Learning in Predicting Giant Cell Arteritis Flare After Glucocorticoids Tapering"],"prefix":"10.3389","volume":"13","author":[{"given":"Vincenzo","family":"Venerito","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Emmi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Cantarini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pietro","family":"Leccese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Fornaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Fabiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nancy","family":"Lascaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Coladonato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irene","family":"Mattioli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giulia","family":"Righetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danilo","family":"Malandrino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabina","family":"Tangaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adalgisa","family":"Palermo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Letizia","family":"Urban","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edoardo","family":"Conticini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno","family":"Frediani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florenzo","family":"Iannone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Lopalco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,4,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra011913","article-title":"Polymyalgia Rheumatica and Giant-Cell Arteritis","volume":"347","author":"Salvarani","year":"2002","journal-title":"N Engl J Med"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1136\/ard.2008.088351","article-title":"EULAR Recommendations for the Management of Large Vessel Vasculitis","volume":"68","author":"Mukhtyar","year":"2009","journal-title":"Ann Rheumatic Dis"},{"key":"B3","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1136\/annrheumdis-2019-215672","article-title":"2018 Update of the EULAR Recommendations for the Management of Large Vessel Vasculitis","volume":"79","author":"Hellmich","year":"2020","journal-title":"Ann Rheum Dis"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1097\/RHU.0000000000001720","article-title":"A Machine Learning Approach for Predicting Sustained Remission in Rheumatoid Arthritis Patients on Biologic Agents","volume":"28","author":"Venerito","year":"2021","journal-title":"JCR: J Clin Rheumatol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"823","DOI":"10.3390\/app11020823","article-title":"A Machine Learning Tool to Predict the Response to Neoadjuvant Chemotherapy in Patients With Locally Advanced Cervical Cancer","volume":"11","author":"Arezzo","year":"2021","journal-title":"Appl Sci"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3390\/dermatopathology8030044","article-title":"Artificial Intelligence in Dermatopathology: New Insights and Perspectives","volume":"8","author":"Cazzato","year":"2021","journal-title":"Dermatopathology (Basel)"},{"key":"B7","doi-asserted-by":"publisher","first-page":"7833","DOI":"10.3390\/app11177833","article-title":"Radiomics Analysis in Ovarian Cancer: A Narrative Review","volume":"11","author":"Arezzo","year":"2021","journal-title":"Appl Sci"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1093\/infdis\/jiaa236","article-title":"Cohort-Derived Machine Learning Models for Individual Prediction of Chronic Kidney Disease in People Living With Human Immunodeficiency Virus: A Prospective Multicenter Cohort Study","volume":"224","author":"Roth","year":"2020","journal-title":"J Infect Dis"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s11739-020-02583-x","article-title":"A Convolutional Neural Network With Transfer Learning for Automatic Discrimination Between Low and High-Grade Synovitis: A Pilot Study","volume":"16","author":"Venerito","year":"2021","journal-title":"Intern Emerg Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330810","article-title":"The American College of Rheumatology 1990 Criteria for the Classification of Giant Cell Arteritis","volume":"33","author":"Hunder","year":"1990","journal-title":"Arthritis Rheumatol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.7861\/clinmedicine.10-4-381","article-title":"Concise Guidance: Diagnosis and Management of Giant Cell Arteritis","volume":"10","author":"Dasgupta","year":"2010","journal-title":"Clin Med (Lond)"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1309.0238","article-title":"API Design for Machine Learning Software: Experiences From the Scikit-Learn Project","author":"Buitinck","year":"2013","journal-title":"arXiv e-prints"},{"key":"B13","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learning"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3414\/ME14-04-0003","article-title":"Youden\u2019s Index and the Weight of Evidence","volume":"54","author":"Hughes","year":"2015","journal-title":"Methods Inf Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/nrrheum.2013.161","article-title":"Immune Mechanisms in Medium and Large-Vessel Vasculitis","volume":"9","author":"Weyand","year":"2013","journal-title":"Nat Rev Rheumatol"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/kev348","article-title":"Predictors of Relapse and Treatment Outcomes in Biopsy-Proven Giant Cell Arteritis: A Retrospective Cohort Study","volume":"55","author":"Labarca","year":"2016","journal-title":"Rheumatol (Oxford)"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e3524","DOI":"10.1097\/MD.0000000000003524","article-title":"Flares in Biopsy-Proven Giant Cell Arteritis in Northern Italy","volume":"95","author":"Restuccia","year":"2016","journal-title":"Med (Baltimore)"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1002\/acr.21569","article-title":"Incidence of Infections in Patients With Giant Cell Arteritis: A Cohort Study","volume":"64","author":"Durand","year":"2012","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/art.11388","article-title":"Glucocorticoid Therapy in Giant Cell Arteritis: Duration and Adverse Outcomes","volume":"49","author":"Proven","year":"2003","journal-title":"Arthritis Rheumatol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.674055","article-title":"Explainable Deep Learning for Personalized Age Prediction With Brain Morphology","volume":"15","author":"Lombardi","year":"2021","journal-title":"Front Neurosci"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3899\/jrheum.141347","article-title":"Disease Relapses Among Patients With Giant Cell Arteritis: A Prospective, Longitudinal Cohort Study","volume":"42","author":"Kermani","year":"2015","journal-title":"J Rheumatol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0b013e31821c4fad","article-title":"Relapses and Recurrences in Giant Cell Arteritis: A Population-Based Study of Patients With Biopsy-Proven Disease From Northwestern Spain","volume":"90","author":"Martinez-Lado","year":"2011","journal-title":"Med (Baltimore)"},{"key":"B23","article-title":"Prognostic Factors and Long-Term Evolution in a Cohort of 133 Patients With Giant Cell Arteritis","volume":"19","author":"Hachulla","year":"2001","journal-title":"Clin Exp Rheumatol"},{"key":"B24","article-title":"Giant Cell Arteritis: Intensity of the Initial Systemic Inflammatory Response and the Course of the Disease","volume":"26","author":"Nesher","year":"2008","journal-title":"Clin Exp Rheumatol"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2022.860877\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,5]],"date-time":"2022-04-05T13:17:29Z","timestamp":1649164649000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2022.860877\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,5]]},"references-count":24,"alternative-id":["10.3389\/fimmu.2022.860877"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2022.860877","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,5]]},"article-number":"860877"}}