Key result
An appropriate combination of hyperparameters in a simple convolutional neural network model achieved high accuracy (>99%) in classifying major depressive disorder using resting-state EEG.
Why the study?
Objective diagnostic tools using biosignals are needed to monitor depression, but inappropriate input forms and network structures can degrade convolutional neural network performance.
Optimizing hyperparameters in simple CNN models using resting-state EEG can achieve >99% accuracy in classifying major depressive disorder.
Answers are grounded in this paper and cite their sources.
Simple CNN configs yield high MDD classification accuracy from EEG; leaves open clinical adoption pending larger validation.
To monitor patients with depression, objective diagnostic tools that apply biosignals and exhibit high repeatability and efficiency should be developed. Although different models can help automatically learn discriminative features, inappropriate adoption of input forms and network structures may cause performance degradation. Accordingly, the aim of this study was to systematically evaluate the effects of convolutional neural network (CNN) architectures when using two common electroencephalography (EEG) inputs on the classification of major depressive disorder (MDD). EEG data for 21 patients with MDD and 21 healthy controls were obtained from an open-source database. Five hyperparameters (i.e., number of convolutional layers, filter size, pooling type, hidden size, and batch size) were then evaluated. Finally, Grad-CAM and saliency map were applied to visualize the trained models. When raw EEG signals were employed, optimal performance and efficiency were achieved as more convolutional layers and max pooling were used. Furthermore, when mixed features were employed, a larger hidden layer and smaller batch size were optimal. Compared with other complex networks, this configuration involves a relatively small number of layers and less training time but a relatively high accuracy. Thus, high accuracy (>99%) can be achieved in MDD classification by using an appropriate combination in a simple model.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2023) studied Major depressive disorder (MDD) (n=42). Convolutional neural network (CNN) architectures with optimized hyperparameters vs. Other complex networks or inappropriate hyperparameter configurations was evaluated on MDD classification accuracy. An appropriate combination of hyperparameters in a simple convolutional neural network model achieved high accuracy (>99%) in classifying major depressive disorder using resting-state EEG.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: