Search research articles

Search research articles

Related Experiment Videos

Detection of multiple sclerosis with visual evoked potentials--an unsupervised computational intelligence system.

T J Dasey¹, E Micheli-Tzanakou

¹Department of Biomedical Engineering, Rutgers University, Piscataway, NJ 08854, USA.

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society

|October 12, 2000

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Quantitative on-line analysis of physiological data for lesion placement in pallidotomy.

Stereotactic and functional neurosurgery·2001

Same author

Electrophysiological recordings in pallidotomy localized to 3D stereoscopic imaging.

Stereotactic and functional neurosurgery·2000

Same author

Speaker identification using neural networks and wavelets.

IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society·2000

Same author

Nonstationary speech analysis using neural prediction.

IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society·2000

Same author

Classification of retinal damage by a neural network based system.

Journal of medical systems·1998

Same author

A mobile automated mammography system.

Journal of medical systems·1998

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

A novel unsupervised pattern recognition system effectively classifies Visual Evoked Potentials (VEP) for multiple sclerosis (MS) detection. This method uses fuzzy clustering and a parallel neural network to distinguish MS patients from controls with high accuracy.

Area of Science:

Neuroscience
Biomedical Engineering
Artificial Intelligence

Background:

Multiple Sclerosis (MS) diagnosis relies on identifying neurological deficits.
Visual Evoked Potentials (VEP) are sensitive to MS-related optic nerve damage.
Current VEP analysis often requires expert interpretation and can be subjective.

Purpose of the Study:

To develop and apply a novel unsupervised pattern recognition system for classifying VEPs.
To differentiate between VEPs from normal subjects and those with multiple sclerosis.
To explore the potential of an AI-driven approach for MS detection using VEP data.

Main Methods:

Implemented an unsupervised pattern recognition system combining statistical feature extraction and fuzzy clustering.

Related Experiment Videos

Utilized a parallel neural network architecture trained with the ALOPEX optimization routine.

Employed a modified Fuzzy c-Means (FCM) algorithm for clustering VEP data, enhanced by ALOPEX for global optimization.

Main Results:

The system successfully classified VEPs from 13 normal and 12 MS subjects into two distinct groups.
Achieved classification without supervision, with a threshold set to ensure no false negatives.
Analysis of cluster prototypes revealed previously unused VEP portions relevant for MS detection.

Conclusions:

The developed unsupervised system demonstrates high efficacy in classifying VEPs for MS detection.
The approach offers an objective and potentially more reliable method for identifying MS patients.
The system's interpretable nature suggests its utility as a diagnostic aid and for VEP analysis research.