{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T21:41:41Z","timestamp":1782510101578,"version":"3.54.5"},"reference-count":50,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2005,12,9]],"date-time":"2005-12-09T00:00:00Z","timestamp":1134086400000},"content-version":"vor","delay-in-days":4240,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Arthritis &amp; Rheumatism"],"published-print":{"date-parts":[[1994,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p><jats:italic>Objective<\/jats:italic>. Neural networks are a group of computer\u2010based pattern recognition methods that have recently been applied to clinical diagnosis and classification. In this study, we applied one type of neural network, the backpropagation network, to the diagnostic classification of giant cell arteritis (GCA).<\/jats:p><jats:p><jats:italic>Methods<\/jats:italic>. The analysis was performed on the 807 cases in the vasculitis database of the American College of Rheumatology. Classification was based on the 8 clinical criteria previously used for classification of this data set: 1) age \u226550 years, 2) new localized headache, 3) temporal artery tenderness or decrease in temporal artery pulse, 4) polymyalgia rheumatica, 5) abnormal result on artery biopsy, 6) erythrocyte sedimentation rate \u226550 mm\/hour, 7) scalp tenderness or nodules, and 8) claudication of the jaw, of the tongue, or on swallowing. To avoid overtraining, network training was terminated when the generalization error reached a minimum. True cross\u2010validation classification rates were obtained.<\/jats:p><jats:p><jats:italic>Results<\/jats:italic>. Neural networks correctly classified 94.4% of the GCA cases (n = 214) and 91.9% of the other vasculitis cases (n = 593). In comparison, classification trees correctly classified 91.6% of the GCA cases and 93.4% of the other vasculitis cases. Neural nets and classification trees were compared by receiver operating characteristic (ROC) analysis. The ROC curves for the two methods crossed, indicating that the better classification method depended on the choice of decision threshold. At a decision threshold that gave equal costs to percentage increases in false\u2010positive and false\u2010negative results, the methods were not significantly different in their performance (<jats:italic>P<\/jats:italic> = 0.45).<\/jats:p><jats:p><jats:italic>Conclusion<\/jats:italic>. Neural networks are a potentially useful method for developing diagnostic classification rules from clinical data.<\/jats:p>","DOI":"10.1002\/art.1780370522","type":"journal-article","created":{"date-parts":[[2007,2,15]],"date-time":"2007-02-15T01:15:04Z","timestamp":1171502104000},"page":"760-770","source":"Crossref","is-referenced-by-count":33,"title":["Application of neural networks to the classification of giant cell arteritis"],"prefix":"10.1002","volume":"37","author":[{"given":"Michael L.","family":"Astion","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark H.","family":"Wener","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronald G.","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gene G.","family":"Hunder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel A.","family":"Bloch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2005,12,9]]},"reference":[{"key":"e_1_2_1_2_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780251101"},{"key":"e_1_2_1_3_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780310302"},{"key":"e_1_2_1_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780240612"},{"key":"e_1_2_1_5_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780230510"},{"key":"e_1_2_1_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780290816"},{"key":"e_1_2_1_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780331101"},{"key":"e_1_2_1_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780340502"},{"key":"e_1_2_1_9_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330802"},{"key":"e_1_2_1_10_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330805"},{"key":"e_1_2_1_11_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330806"},{"key":"e_1_2_1_12_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330807"},{"key":"e_1_2_1_13_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330808"},{"key":"e_1_2_1_14_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330809"},{"key":"e_1_2_1_15_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330810"},{"key":"e_1_2_1_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330811"},{"key":"e_1_2_1_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330813"},{"key":"e_1_2_1_18_2","volume-title":"Learning internal representations by error propagation, Parallel Distributed Processing: Exploration in the Microstructure of Cognition","author":"Rumelhart DE","year":"1986"},{"key":"e_1_2_1_19_2","first-page":"995","article-title":"The application of backpropagation neural networks to problems in pathology and laboratory medicine","volume":"116","author":"Astion ML","year":"1992","journal-title":"Arch Pathol Lab Med"},{"key":"e_1_2_1_20_2","doi-asserted-by":"publisher","DOI":"10.1097\/00004424-199009000-00013"},{"key":"e_1_2_1_21_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.177.3.2244001"},{"key":"e_1_2_1_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/0002-9378(92)91621-G"},{"key":"e_1_2_1_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/0022-0736(92)90001-G"},{"key":"e_1_2_1_24_2","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-115-11-843"},{"key":"e_1_2_1_25_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.5.772"},{"key":"e_1_2_1_26_2","doi-asserted-by":"publisher","DOI":"10.1093\/ajcp\/96.1.134"},{"key":"e_1_2_1_27_2","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/S0030-5898(20)31655-2","article-title":"Artificial intelligence in the diagnosis of low back pain","volume":"22","author":"Mann NH","year":"1991","journal-title":"Orthop Clin North Am"},{"key":"e_1_2_1_28_2","first-page":"25","article-title":"A neural network as an approach to clinical diagnosis","volume":"7","author":"Mulsant BH","year":"1990","journal-title":"MD Comput"},{"key":"e_1_2_1_29_2","first-page":"314","article-title":"Computer\u2010aided diagnosis of breast aspirates via expert systems","volume":"12","author":"Wolberg WH","year":"1990","journal-title":"Anal Quant Cytol Histol"},{"key":"e_1_2_1_30_2","first-page":"S29","article-title":"Nuclear grading of breast carcinoma by image analysis","volume":"95","author":"Dawson AE","year":"1991","journal-title":"Am J Clin Pathol"},{"key":"e_1_2_1_31_2","first-page":"402","article-title":"Computer\u2010assisted image interpretation: use of a neural network to differentiate tubular carcinoma from sclerosing adenosis","volume":"5","author":"O'Leary TJ","year":"1992","journal-title":"Mod Pathol"},{"key":"e_1_2_1_32_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.88.24.11426"},{"key":"e_1_2_1_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/clinchem\/38.1.34"},{"key":"e_1_2_1_34_2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1093\/clinchem\/38.1.9","article-title":"Neural networks and diagnosis in the clinical laboratory: state of the art","volume":"38","author":"Cicchetti DV","year":"1992","journal-title":"Clin Chem"},{"key":"e_1_2_1_35_2","doi-asserted-by":"publisher","DOI":"10.1002\/art.1780330803"},{"key":"e_1_2_1_36_2","volume-title":"Statistical Aspects of Neural Networks","author":"Ripley BD","year":"1992"},{"key":"e_1_2_1_37_2","volume-title":"NETtalk: a parallel network that learns to read aloud, Neurocomputing: Foundations of Research","author":"Sejnowski TJ","year":"1988"},{"key":"e_1_2_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1989.118274"},{"key":"e_1_2_1_39_2","volume-title":"Generalization dynamics in LMS trained linear networks, Advances in Neural Information Processing Systems 3","author":"Chauvin Y","year":"1991"},{"key":"e_1_2_1_40_2","volume-title":"Can neural networks do better than the Vapnik\u2010Chervonenkis bounds? Advances in Neural Information Processing Systems 3","author":"Cohn D","year":"1991"},{"key":"e_1_2_1_41_2","doi-asserted-by":"crossref","first-page":"1998","DOI":"10.1093\/clinchem\/39.9.1998","article-title":"Overtraining in neural networks that interpret clinical data","volume":"39","author":"Astion ML","year":"1993","journal-title":"Clin Chem"},{"key":"e_1_2_1_42_2","volume-title":"CART","author":"California Statistical Software","year":"1984"},{"key":"e_1_2_1_43_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19980430)17:8<857::AID-SIM777>3.0.CO;2-E"},{"key":"e_1_2_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/0895-4356(91)90146-Z"},{"key":"e_1_2_1_45_2","unstructured":"BlochDA: Comparing diagnostic tests against the same \u201cgold standard\u201d in the same sample (technical report). Stanford CA Stanford University 1993"},{"key":"e_1_2_1_46_2","volume-title":"What size net gives valid generalization? Advances in Neural Information Processing Systems 1","author":"Baum EB","year":"1989"},{"key":"e_1_2_1_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90015-W"},{"key":"e_1_2_1_48_2","volume-title":"Back Propagation implementation on the adaptive solutions CNAPS neurocomputer chip. Advances in Neural Information Processing Systems 3","author":"McCartor H","year":"1991"},{"key":"e_1_2_1_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90023-8"},{"key":"e_1_2_1_50_2","volume-title":"Generalization by weight elimination with application to forecasting, Advances in Neural Information Processing Systems 3","author":"Weigend AS","year":"1991"},{"key":"e_1_2_1_51_2","first-page":"1465","article-title":"Neural networks as expert systems in rheumatic disease diagnosis: artificial intelligence or intelligent artifice","volume":"20","author":"Astion ML","year":"1993","journal-title":"J Rheumatol"}],"container-title":["Arthritis &amp; Rheumatism"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fart.1780370522","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/art.1780370522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T18:58:29Z","timestamp":1700765909000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/art.1780370522"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1994,5]]},"references-count":50,"journal-issue":{"issue":"5","published-print":{"date-parts":[[1994,5]]}},"alternative-id":["10.1002\/art.1780370522"],"URL":"https:\/\/doi.org\/10.1002\/art.1780370522","archive":["Portico"],"relation":{},"ISSN":["0004-3591","1529-0131"],"issn-type":[{"value":"0004-3591","type":"print"},{"value":"1529-0131","type":"electronic"}],"subject":[],"published":{"date-parts":[[1994,5]]}}}