{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T09:26:01Z","timestamp":1793179561103,"version":"4.5.0"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T00:00:00Z","timestamp":1613520000000},"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. Med."],"abstract":"<jats:p><jats:bold>Introduction:<\/jats:bold> The aim of this study was to find the best ordered combination of two FDG positive musculoskeletal sites with a machine learning algorithm to diagnose polymyalgia rheumatica (PMR) vs. other rheumatisms in a cohort of patients with inflammatory rheumatisms.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> This retrospective study included 140 patients who underwent [<jats:sup>18<\/jats:sup>F]FDG PET-CT and whose final diagnosis was inflammatory rheumatism. The cohort was randomized, stratified on the final diagnosis into a training and a validation cohort. FDG uptake of 17 musculoskeletal sites was evaluated visually and set positive if uptake was at least equal to that of the liver. A decision tree classifier was trained and validated to find the best combination of two positives sites to diagnose PMR. Diagnosis performances were measured first, for each musculoskeletal site, secondly for combination of two positive sites and thirdly using the decision tree created with machine learning.<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> 55 patients with PMR and 85 patients with other inflammatory rheumatisms were included. Musculoskeletal sites, used either individually or in combination of two, were highly imbalanced to diagnose PMR with a high specificity and a low sensitivity. The machine learning algorithm identified an optimal ordered combination of two sites to diagnose PMR. This required a positive interspinous bursa or, if negative, a positive trochanteric bursa. Following the decision tree, sensitivity and specificity to diagnose PMR were respectively 73.2 and 87.5% in the training cohort and 78.6 and 80.1% in the validation cohort.<\/jats:p><jats:p><jats:bold>Conclusion:<\/jats:bold> Ordered combination of two visually positive sites leads to PMR diagnosis with an accurate sensitivity and specificity vs. other rheumatisms in a large cohort of patients with inflammatory rheumatisms.<\/jats:p>","DOI":"10.3389\/fmed.2021.646974","type":"journal-article","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T07:29:08Z","timestamp":1613806148000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Decision Tree With Only Two Musculoskeletal Sites to Diagnose Polymyalgia Rheumatica Using [18F]FDG PET-CT"],"prefix":"10.3389","volume":"8","author":[{"given":"Anthime","family":"Flaus","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julie","family":"Amat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathalie","family":"Prevot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louis","family":"Olagne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucie","family":"Descamps","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cl\u00e9ment","family":"Bouvet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bertrand","family":"Barres","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cl\u00e9mence","family":"Valla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sylvain","family":"Mathieu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Andre","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Soubrier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles","family":"Merlin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antony","family":"Kelly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marion","family":"Chanchou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florent","family":"Cachin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,2,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1148\/rg.2020190047","article-title":"Fluorodeoxyglucose PET\/CT of arthritis in rheumatic diseases: a pictorial review","volume":"40","author":"Hotta","year":"2020","journal-title":"RadioGraphics"},{"key":"B2","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1053\/j.semnuclmed.2017.02.005","article-title":"Clinical value of FDG-PET\/CT for the evaluation of rheumatic diseases: rheumatoid arthritis, polymyalgia rheumatica, and relapsing polychondritis","volume":"47","author":"Kubota","year":"2017","journal-title":"Semin Nucl Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"705","DOI":"10.3109\/s10165-011-0581-x","article-title":"Whole-body fluorodeoxyglucose positron emission tomography\/computed tomography in patients with active polymyalgia rheumatica: evidence for distinctive bursitis and large-vessel vasculitis","volume":"22","author":"Yamashita","year":"2012","journal-title":"Mod Rheumatol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"546","DOI":"10.3109\/14397595.2014.978936","article-title":"Differences in fluorodeoxyglucose positron emission tomography\/computed tomography findings between elderly onset rheumatoid arthritis and polymyalgia rheumatica","volume":"25","author":"Takahashi","year":"2015","journal-title":"Mod Rheumatol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1093\/rheumatology\/kew202","article-title":"Utility of 18F-fluoro-dexoxyglucose positron emission tomography for the diagnosis of polymyalgia rheumatica: a controlled study","volume":"55","author":"Sondag","year":"2016","journal-title":"Rheumatology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.1007\/s00259-020-04731-z","article-title":"Abnormalities at three musculoskeletal sites on whole-body positron emission tomography\/computed tomography can diagnose polymyalgia rheumatica with high sensitivity and specificity","volume":"47","author":"Owen","year":"2020","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1908","DOI":"10.1093\/rheumatology\/kex376","article-title":"Use of 18F-fluorodeoxyglucose positron emission tomography in the diagnosis of polymyalgia rheumatica\u2014a prospective study of 99 patients","volume":"57","author":"Henckaerts","year":"2018","journal-title":"Rheumatology"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e0158509","DOI":"10.1371\/journal.pone.0158509","article-title":"Differentiation between Polymyalgia Rheumatica (PMR) and elderly-onset rheumatoid arthritis using 18F-fluorodeoxyglucose positron emission tomography\/computed tomography: is enthesitis a new pathological lesion in PMR?","volume":"11","author":"Wakura","year":"2016","journal-title":"PLoS ONE"},{"key":"B9","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3389\/fmed.2020.00394","article-title":"Utility of 18F-fluorodeoxyglucose positron emission tomography in inflammatory rheumatism, particularly polymyalgia rheumatica: a retrospective study of 222 PET\/CT","volume":"7","author":"Amat","year":"2020","journal-title":"Front Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"vi5","DOI":"10.1093\/rheumatology\/kes279","article-title":"ACR\/EULAR (2010) rheumatoid arthritis classification criteria","volume":"51","author":"Kay","year":"2012","journal-title":"Rheumatology"},{"key":"B11","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.ymed.2012.09.009","article-title":"Provisional classification criteria for polymyalgia rheumatica: a European League Against Rheumatism\/American College of Rheumatology collaborative initiative","volume":"71","author":"Dasgupta","year":"2012","journal-title":"Ann Rheum Dis"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1136\/ard.2009.110767","article-title":"Defining active sacroiliitis on magnetic resonance imaging (MRI) for classification of axial spondyloarthritis: a consensual approach by the ASAS\/OMERACT MRI group","volume":"68","author":"Rudwaleit","year":"2009","journal-title":"Ann Rheum Dis"},{"key":"B13","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1097\/MNM.0000000000000669","article-title":"Optimization of PET\/CT image quality using the GE \u2018Sharp IR' point-spread function reconstruction algorithm","volume":"38","author":"Vennart","year":"2017","journal-title":"Nucl Med Commun"},{"key":"B14","first-page":"1431","article-title":"Understanding the standardized uptake value, its methods, and implications for usage","volume":"45","author":"Thie","year":"2004","journal-title":"J Nucl Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1007\/s00259-018-3973-8","article-title":"FDG-PET\/CT(A) imaging in large vessel vasculitis and polymyalgia rheumatica: joint procedural recommendation of the EANM, SNMMI, and the PET Interest Group (PIG), and endorsed by the ASNC","volume":"45","year":"2018","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2387","DOI":"10.1007\/s00521-012-1196-7","article-title":"Decision tree classifiers for automated medical diagnosis","volume":"23","author":"Azar","year":"2013","journal-title":"Neural Comput Applic"},{"key":"B17","first-page":"2825","article-title":"Scikit-learn: machine learning in python. Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"B18","first-page":"98","article-title":"Machine learning basics","volume":"1","author":"Goodfellow","year":"2016","journal-title":"Deep Learn"},{"key":"B19","volume-title":"R: A Language and Environment for Statistical Computing (Version 3.5.2)","author":"Team","year":"2018"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e15791","DOI":"10.2196\/15791","article-title":"Improving clinical translation of machine learning approaches through clinician-tailored visual displays of black box algorithms: development and validation","volume":"8","author":"Wongvibulsin","year":"2020","journal-title":"JMIR Med Inform"},{"key":"B21","first-page":"526","article-title":"Lumbar interspinous bursitis in active polymyalgia rheumatica","volume":"31","author":"Salvarani","year":"2013","journal-title":"Clin Exp Rheumatol"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-020-05162-6","article-title":"Diagnostic value of [18F]FDG-PET\/CT in polymyalgia rheumatica: a systematic review and meta-analysis","author":"Van der Geest","year":"2020","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"B23","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1093\/rheumatology\/keq450","article-title":"Imaging of polymyalgia rheumatica: indications on its pathogenesis, diagnosis and prognosis","volume":"51","author":"Camellino","year":"2012","journal-title":"Rheumatology"},{"key":"B24","doi-asserted-by":"publisher","first-page":"310","DOI":"10.2214\/AJR.10.4923","article-title":"A systematic review of the factors affecting accuracy of SUV measurements","volume":"195","author":"Adams","year":"2010","journal-title":"AJR Am J Roentgenol"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.646974\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T07:29:15Z","timestamp":1613806155000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.646974\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,17]]},"references-count":24,"alternative-id":["10.3389\/fmed.2021.646974"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2021.646974","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,17]]},"article-number":"646974"}}