Diagnostic classification of autoantibody repertoires in endocrine ophthalmopathy using an artificial neural network

Abstract

Purpose: The aim of this study was to classify the human IgG autoantibody repertoire of sera from patients suffering from endocrine ophthalmopathy (EOP) and healthy subjects (CTRL) for diagnostic purposes using the recently developed Megablot technique. This technique allows for the simultaneous and quantitative screening of a large set of antigens and uses multivariate statistical techniques and an artificial neural network. Methods: Sera were tested against Western blots (WBs) of SDS-PAGE preparations of proteins from human extraorbital eye muscle (EOP: n=16; CTRL: n=11). Digital image analysis was performed. The blots were subsequently analyzed by multivariate statistical techniques (analysis of discriminance) and an artificial neural network (probalistic neural network). Results: The sera of both the EOP and CTRL groups showed a complex staining pattern against WBs of SDS-PAGEs from human eye muscle. Using the multivariate statistical technique for classification, all of the known samples and 85% of the unknown samples (not presented during calculation) were assigned to their correct clinical group. Using the artificial neural network as classifier, all of the samples presented during training and 96.3% of the unknown samples (not trained) were assigned correctly. Conclusions: The artificial neural network exceeds the ability of multivariate statistical techniques such as analysis of discriminance to assign unknown samples to their correct predefined group. Thus, the neural network exceeds other methods in generalizing some similarities of blots used for classification. This study reveals that our new technique and its evaluation using a neural network can be used as a helpful diagnostic tool in autoimmune diseases such as endocrine ophthalmopathy.