Yang Jianli, Zhang Zhen, Fu Zhiyu, Li Bing, Xiong Peng, Liu Xiuling
College of Electronic Information and Engineering, Hebei University, Baoding 071002, China; Key Laboratory of Digital Medical Engineering of Heibei Province, Baoding 071002, China.
College of Electronic Information and Engineering, Hebei University, Baoding 071002, China.
Comput Methods Programs Biomed. 2023 May;233:107360. doi: 10.1016/j.cmpb.2023.107360. Epub 2023 Jan 18.
The aim of this study is to solve the non-stationarity and complexity characteristics and huge individual differences in the electroencephalogram (EEG) signals for depression classification.
To address those problems, the Lempel-Ziv complexity feature matrices were extracted from the EEG signals under the two paradigms of eyes open and eyes closed in the resting state. Topographical map of brain and statistical analysis were introduced to investigate the significance of eyes open and eyes closed EEG for depression classification. To promote the classification accuracy, feature matrices from the two paradigms were fused. And linear combination and concatenation fusion methods were proposed to further reveal the underlying mechanism of improving classification accuracy. Support vector machine (SVM), K-nearest neighbor, and decision tree classifiers were employed and compared to classify depression under the eyes open, eyes closed and fused paradigm.
The classification results of 10-fold cross-validation showed that the highest average accuracy (86.58%) under a single paradigm was achieved in the eyes-open state. The multiparadigm fusion method of concatenation was better than the linear combination. The best classification result was obtained using multiparadigm feature concatenation under the SVM classifier, yielding an accuracy of 94.03%.
The multiparadigm feature fusion method proposed in this paper can effectively improve the accuracy of depression classification. It was proved that eyes open and eyes closed EEG have complementary information, which was benefit for the cross-subject classification of depression. It provides new ideas for depression classification in clinics.
本研究旨在解决脑电图（EEG）信号用于抑郁症分类时的非平稳性、复杂性特征以及巨大的个体差异问题。
为解决这些问题，在静息状态下的睁眼和闭眼两种范式下，从EEG信号中提取Lempel-Ziv复杂性特征矩阵。引入脑地形图和统计分析来研究睁眼和闭眼EEG对抑郁症分类的意义。为提高分类准确率，将两种范式下的特征矩阵进行融合。并提出线性组合和串联融合方法以进一步揭示提高分类准确率的潜在机制。采用支持向量机（SVM）、K近邻和决策树分类器，在睁眼、闭眼和融合范式下对抑郁症进行分类并比较。
10折交叉验证的分类结果表明，在单一范式下，睁眼状态获得了最高的平均准确率（86.58%）。串联的多范式融合方法优于线性组合。在SVM分类器下使用多范式特征串联获得了最佳分类结果，准确率为94.03%。
本文提出的多范式特征融合方法能有效提高抑郁症分类的准确率。证明了睁眼和闭眼EEG具有互补信息，这有利于抑郁症的跨个体分类。为临床抑郁症分类提供了新思路。
