ABSTRACT
Neural networks constitute a relatively new, radically different approach to the interpretation and recognition of subtle diagnostic patterns in multivariate data. In this study the use of neural networks with a single serum sample for rapid real-time recognition of recent toxoplasmic infection was investigated. A neural-network model was implemented on the basis of data obtained by four serological methods--dye test, indirect fluorescence assay, indirect hemagglutination assay, and IgM immunosorbent agglutination assay--and was "trained" to extract features of acute infection by application to an analysis of 65 immunocompetent patients, 10 of whom were in fact acutely infected. The trained model correctly classified all 10 cases of acute infection. On its application to 61 additional infected patients, this method correctly identified seven cases as potentially acute. Our study shows that neural networks can discern diagnostic patterns from variables that individually have limited utility in the diagnosis of acute toxoplasmosis.
