Search

Copyright of Der Ophthalmologe is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

PURPOSE: The aim of this study was to classifythe human IgG autoantibody repertoire of sera from patients suffering fromendocrine ophthalmopathy (EOP) and healthy subjects (CTRL) for diagnosticpurposes using the recently developed Megablot technique. This technique allowsfor the simultaneous and quantitative screening of a large set of antigensand uses multivariate statistical techniques and an artificial neural network.METHODS: Sera were tested against Western blots (WBs) of SDS-PAGE preparationsof proteins from human extraorbital eye muscle (EOP: n=16; CTRL: n=11). Digitalimage analysis was performed. The blots were subsequently analyzed by multivariatestatistical techniques (analysis of discriminance) and an artificial neuralnetwork (probalistic neural network). RESULTS: The sera of both the EOP andCTRL groups showed a complex staining pattern against WBs of SDS-PAGEs fromhuman eye muscle. Using the multivariate statistical technique for classification,all of the known samples and 85% of the unknown samples (not presented duringcalculation) were assigned to their correct clinical group. Using the artificialneural network as classifier, all of the samples presented during trainingand 96.3% of the unknown samples (not trained) were assigned correctly. CONCLUSIONS:The artificial neural network exceeds the ability of multivariate statisticaltechniques such as analysis of discriminance to assign unknown samples totheir correct predefined group. Thus, the neural network exceeds other methodsin generalizing some similarities of blots used for classification. This studyreveals that our new technique and its evaluation using a neural network canbe used as a helpful diagnostic tool in autoimmune diseases such as endocrineophthalmopathy. [ABSTRACT FROM AUTHOR]