Automatic Discrimination of Abnormal Subjects Using the Visual Evoked Potential Spectral Components

Area of Science:

• Neuroscience
• Computational Biology
• Ophthalmology

Background:

• Visual evoked potential (VEP) analysis is crucial for diagnosing ophthalmological and neurological conditions.
• Automatic detection of VEP spectral components aids in assessing mental activity and identifying abnormalities.

Purpose of the Study:

• To present a novel computational approach for identifying abnormal subjects based on VEP spectral component changes.
• To develop and implement a feedforward neural network for real-time VEP analysis.

Main Methods:

• Utilized a feedforward neural network architecture.
• Developed software using the Matlab package for VEP spectral component analysis.
• Focused on identifying abnormalities from changes in VEP spectral components.

Main Results:

• The feedforward neural network successfully identified abnormal subjects based on VEP spectral components.
• The developed software enables accurate, real-time abnormality identification on personal computers.

Conclusions:

• The novel computational approach offers an effective tool for the automatic detection of VEP abnormalities.
• This method has the potential to enhance clinical diagnosis in neurology and ophthalmology through real-time analysis.