# MS-MDDNet: A Lightweight Deep Learning Framework for Interpretable EEG-Based Diagnosis of Major Depressive Disorder

## TL;DR

MS-MDDNet is a lightweight deep learning model that improves the diagnosis of Major Depressive Disorder using EEG data with high accuracy and interpretability.

## Contribution

MS-MDDNet introduces a lightweight CNN architecture with interpretability for EEG-based MDD detection, achieving high accuracy and robustness.

## Key findings

- MS-MDDNet achieved 99.33% accuracy on the MODMA dataset, a 9% improvement over existing methods.
- The model maintains high performance (98.59% and 96.61% accuracy) on MUMTAZ and PRED + CT datasets with lower computational complexity.
- Interpretability is achieved through correlation analysis between gamma energy and learned features.

## Abstract

Background: Major Depressive Disorder (MDD) is a pervasive psychiatric condition. Electroencephalography (EEG) is employed to detect MDD-specific neural patterns because it is non-invasive and temporally precise. However, manual interpretation of EEG signals is labor-intensive and subjective. This problem was addressed by proposing machine learning (ML) and deep learning (DL) methods. Although DL methods are promising for MDD detection, they face limitations, including high model complexity, overfitting due to subject-specific noise, excessive channel requirements, and limited interpretability. Methods: To address these challenges, we propose MS-MDDNet, a new lightweight CNN model specifically designed for EEG-based MDD detection, along with an ensemble-like method built on it. The architecture of MS-MDDNet incorporates spatial, temporal, and depth-wise separable convolutions, along with average pooling, to enhance discriminative feature extraction while maintaining computational efficiency with a small number of learnable parameters. Results: The method was evaluated using 10-fold Cross-Subjects Cross-Validation (CS-CV), which mitigates the risks of overfitting associated with subject-specific noise, thereby contributing to generalization robustness. Across three public datasets, the proposed method achieved performance comparable to state-of-the-art approaches while maintaining lower computational complexity. It achieved a 9% improvement on the MODMA dataset, with an accuracy of 99.33%, whereas on MUMTAZ and PRED + CT it achieved accuracies of 98.59% and 96.61%, respectively. Conclusions: The predictions of the proposed method are interpretable, with interpretability achieved through correlation analysis between gamma energy and learned features. This makes it a valuable tool for assisting clinicians and individuals in diagnosing MDD with confidence, thereby enhancing transparency in decision-making and promoting clinical credibility.