Table of Contents Author Guidelines Submit a Manuscript
Computational and Mathematical Methods in Medicine
Volume 10, Issue 1, Pages 39-47
Original Article

Computer-Aided Diagnosis of Multiple Sclerosis

1Institute of Medical Informatics, University of Lübeck, Lübeck, Germany
2Department of Neurology, University of Lübeck, Lübeck, Germany

Received 18 December 2007; Accepted 20 March 2008

Copyright © 2009 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


The study aims to develop a computer-assisted decision support based on cerebrospinal fluid (CSF) and blood findings to improve their value and ease the diagnostic procedure of chronic inflammatory diseases (CIDs) of central nervous system (CNS). Data were collected from patients suffering from multiple sclerosis (MS, n = 73), from another CID of the CNS (n = 22), or a psychiatric disease (control group, CTRL, n = 12). Univariate and multivariate analyses were performed using multiple logistic regression and artificial neural networks. Differentiating between MS and CID, no parameter could be disclosed that could provide a meaningful decision support. However, multivariate analysis obtained a statistically significant classification (sensitivity = 84.9%, specificity = 54.5%, p < 0.001). On the contrary, multivariate analysis based on the differentiation between MS vs. CTRL, gave good results (sensitivity = 95.9%, specificity = 83.3%, p < 0.001). It became evident from standard laboratory findings that there is a significant potential for computer-aided decision support.