Related Experiment Video
Updated: Aug 20, 2025
11:50
EEG Mu Rhythm in Typical and Atypical Development
Published on: April 9, 2014
25.9K
Mental Disorder Diagnosis from EEG Signals Employing Automated Leaning Procedures Based on Radial Basis Functions
Miguel Ángel Luján1, Jorge Mateo Sotos2, Ana Torres2
1Departamento de Ingeniería Eléctrica, Automática y Comunicaciones, Universidad de Castilla-La Mancha, Electrónica, 02071 Albacete, Spain.
Journal of Medical and Biological Engineering
|November 21, 2022
Summary
A new deep learning method accurately diagnoses schizophrenia using electroencephalogram (EEG) signals. This automated tool achieves over 93% accuracy, outperforming existing machine learning approaches for early detection.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Medical Diagnostics
Background:
- Schizophrenia diagnosis relies on clinical observation, often leading to delayed treatment.
- Electroencephalogram (EEG) signals offer high temporal resolution for analyzing brain activity.
Purpose of the Study:
- To present a novel automated diagnostic procedure for schizophrenia using deep learning.
- To enhance the accuracy and efficiency of schizophrenia detection.
Main Methods:
- Utilized a 32-channel electroencephalogram (EEG) helmet to capture brain signals.
- Employed a neuronal network with radial basis functions and a fuzzy c-means algorithm for classification.
Main Results:
- Achieved classification accuracy exceeding 93% on real-world datasets.
- Demonstrated superior performance compared to established machine learning methods in schizophrenia detection.
- Effectively characterized EEG signal changes in schizophrenia patients.
Conclusions:
- The proposed deep learning method serves as a valuable tool for schizophrenia diagnosis.
- Facilitates earlier detection and intervention, potentially improving patient outcomes.
