Key result
A proposed CNN framework using EEG spectrogram images outperformed AlexNet and ResNet50 in classifying autism, epilepsy, Parkinson's disease, and schizophrenia from healthy subjects.
Why the study?
Neurological disorders carry a major global burden, but there is no unique automatic standard detection system to identify multiple neurological disorders within a single framework.
Does the proposed CNN model improve classification accuracy of neurological disorders from EEG signals compared to AlexNet and ResNet50?
Population
EEG data from subjects with autism, epilepsy, parkinson's disease, schizophrenia, and healthy subjects
Comparison
Proposed CNN framework vs AlexNet and ResNet50 models
Authors
Loading...
New multi-disorder EEG CAD system is preliminary; leaves open diagnostic utility pending rigorous validation.
Does the proposed CNN model improve classification accuracy of neurological disorders from EEG signals compared to AlexNet and ResNet50?
A novel CNN-based framework using EEG spectrograms efficiently and accurately classifies multiple neurological disorders.
Tawhid et al. (2023) studied Neurological disorders (autism, epilepsy, Parkinson's disease, schizophrenia). CNN model using spectrogram images of EEG signals vs. AlexNet and ResNet50 was evaluated on Classification of four neurological disorders from healthy subjects. A proposed CNN framework using EEG spectrogram images outperformed AlexNet and ResNet50 in classifying autism, epilepsy, Parkinson's disease, and schizophrenia from healthy subjects.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: