Key result
A fused set of handcrafted and CNN-based EEG features predicted adolescent psychosis with a classification accuracy of 98%.
Why the study?
Feature extraction from EEG signals for psychiatric diagnosis has mostly relied on handcrafted features based on expert knowledge.
Does a fusion of handcrafted and CNN-based EEG features improve the prediction of adolescent psychosis compared to either feature set alone?
Does a fusion of handcrafted and CNN-based EEG features improve the prediction of adolescent psychosis compared to either feature set alone?
Combining handcrafted and CNN-based EEG features yields high accuracy (98%) for predicting adolescent psychosis.
Answers are grounded in this paper and cite their sources.
May support EEG-based psychosis screening in adolescents; hypothesis-generating and requires prospective validation before clinical use.
Schizophrenia is a psychiatric condition that affects a broad portion of the population and carries both health and economic consequences. EEG recordings, which involve the acquisition of brain waves non-invasively across the scalp of an individual, have been shown to be an effective means through which various neurodegenerative and psychiatric diseases can be diagnosed. The characterization and modelling of EEG signals involves the extraction of features, which in this area, have been mostly handcrafted based on expert knowledge. This work explores the comparison and performance of features extracted automatically via machine intelligence using convolutional neural networks (CNN), and a fusion of both handcrafted and CNN-based features towards yielding an enhanced feature set for enhanced prediction of schizophrenia in adolescents. The experimental results showed a greater ability to predict the adolescent psychosis for the fused set of features in the region of 98 % classification accuracy, and showcased a form of superior intelligence comprising of both handcrafted (expert intelligence) and CNN features (machine intelligence) for an enhanced prediction capability.
No takes yet. Share an insight, caveat, or question.
Nsugbe et al. (2022) studied Adolescent psychosis / Schizophrenia. Fusion of handcrafted and CNN-based features from EEG signals vs. Handcrafted features or CNN features alone was evaluated on Classification accuracy for predicting adolescent psychosis. A fused set of handcrafted and CNN-based EEG features predicted adolescent psychosis with a classification accuracy of 98%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: