A Neural Network Based Classifier for Acute Meningitis

Abstract

Differentiating bacterial from viral (aseptic) meningitis is still a difficult issue, compounded by factors such as age and time of presentation. Clinicians routinely rely on the results from blood and cerebrospinal fluid (CSF) to discriminate bacterial from viral meningitis. Tests such as the CSF Gram stain performed prior to broad-spectrum antibiotic treatment yield sensitivities between 60 and 92%. In this study, we wished to produce a learning vector quantisation network that could yielded a predictive accuracy approaching that of clinical assessment. The results from this study indicate that we can achieve a classification accuracy of over 97%. In addition, we wished to examine how data discretisation impacts the classification accuracy of the LVQ algorithm