A computer-aided diagnosis of multiple sclerosis based on mfVEP recordings

• Published in: PloS one Vol. 14; no. 4; p. e0214662
• Main Authors: de Santiago, Luis, Sánchez Morla, E. M., Ortiz, Miguel, López, Elena, Amo Usanos, Carlos, Alonso-Rodríguez, M. C., Barea, R., Cavaliere-Ballesta, Carlo, Fernández, Alfredo, Boquete, Luciano
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 04.04.2019; Public Library of Science (PLoS)
• Subjects: Adult; Algorithms; Autoimmune diseases; Biology and Life Sciences; Central nervous system; Classification; Classifiers; Computer and Information Sciences; Correlation coefficient; Correlation coefficients; Demyelinating Diseases; Demyelination; Development and progression; Developmental stages; Diagnosis; Diagnosis, Computer-Assisted - methods; Disability; Divergence; Electroencephalography; Evoked Potentials, Visual; Eye; Eye (anatomy); Female; Humans; Indexing; Latency; Male; Medical diagnosis; Medicine and Health Sciences; Multiple sclerosis; Multiple Sclerosis - diagnosis; Nervous system; Neuritis; NMR; Nuclear magnetic resonance; Optic neuritis; Optic Neuritis - diagnosis; Patients; Principal components analysis; Recording; Research and Analysis Methods; Software upgrading; Subgroups; Systematic review; Visual evoked potentials; Wavelet transforms; Spain
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0214662

The aim of this study is to develop a computer-aided diagnosis system to identify subjects at differing stages of development of multiple sclerosis (MS) using multifocal visual-evoked potentials (mfVEPs). Using an automatic classifier, diagnosis is performed first on the eyes and then on the subjects. MfVEP signals were obtained from patients with Radiologically Isolated Syndrome (RIS) (n = 30 eyes), patients with Clinically Isolated Syndrome (CIS) (n = 62 eyes), patients with definite MS (n = 56 eyes) and 22 control subjects (n = 44 eyes). The CIS and MS groups were divided into two subgroups: those with eyes affected by optic neuritis (ON) and those without (non-ON). For individual eye diagnosis, a feature vector was formed with information about the intensity, latency and singular values of the mfVEP signals. A flat multiclass classifier (FMC) and a hierarchical classifier (HC) were tested and both were implemented using the k-Nearest Neighbour (k-NN) algorithm. The output of the best eye classifier was used to classify the subjects. In the event of divergence, the eye with the best mfVEP recording was selected. In the eye classifier, the HC performed better than the FMC (accuracy = 0.74 and extended Matthew Correlation Coefficient (MCC) = 0.68). In the subject classification, accuracy = 0.95 and MCC = 0.93, confirming that it may be a promising tool for MS diagnosis. In addition to amplitude (axonal loss) and latency (demyelination), it has shown that the singular values of the mfVEP signals provide discriminatory information that may be used to identify subjects with differing degrees of the disease.