用脑电图评估抑郁严重程度，提升分类精度与公平性
Cross-Subject Depression Level Classification Using EEG Signals with a Sample Confidence Method
- 引入置信度模块和少数类惩罚模块，缓解主观评分偏差与类别不平衡
- 在两个公开数据集上达到81.13%和81.36%的多级分类准确率
- 适合临床辅助诊断、精神健康研究者及深度学习在医疗中的应用
脑电图（EEG）是一种非侵入式实时神经监测工具，广泛用于基于深度学习的抑郁症检测。然而，现有模型主要聚焦于二分类（抑郁/正常），缺乏对严重程度的精细划分。为此，本文提出基于图卷积网络的抑郁程度分类模型DepL-GCN，解决两大挑战：(1) 由于患者自评带来的抑郁程度标注主观性；(2) 不同严重等级间类别不平衡。受模型学习模式启发，我们引入两个新模块：样本置信度模块通过预测误差的L2范数逐步过滤训练中标签对齐弱的样本，降低主观偏差影响；少数类惩罚模块自动提高误分类少数类样本的权重，缓解类别不平衡。在两个公开EEG数据集上测试，DepL-GCN在多级严重程度识别中分别取得81.13%和81.36%的准确率，优于基线模型。消融实验验证了两个模块的有效性。本文还讨论了回归模型在抑郁程度识别中的优劣。
原文摘要 · Abstract (English)
Electroencephalogram (EEG) is a non-invasive tool for real-time neural monitoring,widely used in depression detection via deep learning. However, existing models primarily focus on binary classification (depression/normal), lacking granularity for severity assessment. To address this, we proposed the DepL-GCN, i.e., Depression Level classification based on GCN model. This model tackles two key challenges: (1) subjectivity in depres-sion-level labeling due to patient self-report biases, and (2) class imbalance across severity categories. Inspired by the model learning patterns, we introduced two novel modules: the sample confidence module and the minority sample penalty module. The former leverages the L2-norm of prediction errors to progressively filter EEG samples with weak label alignment during training, thereby reducing the impact of subjectivity; the latter automatically upweights misclassified minority-class samples to address imbalance issues. After testing on two public EEG datasets, DepL-GCN achieved accuracies of 81.13% and 81.36% for multi-class severity recognition, outperforming baseline models.Ablation studies confirmed both modules' contributions. We further discussed the strengths and limitations of regression-based models for depression-level recognition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。