Discovery of Shared Latent Nonlinear Effective Connectivity for EEG-Based Depression Detection

• Published in: IEEE transaction on neural networks and learning systems Vol. 36; no. 6; pp. 10663 - 10677
• Main Authors: Yuan, Wenjie, Zhang, Xiaowei, Zhang, Xuejuan, Wang, Shuangyan, Wang, Tianzhi, Zhang, Tong, Zhao, Qinglin, Hu, Bin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2025
• Subjects: Algorithms; Brain modeling; Decoding; Depression; Depression - diagnosis; Depression - physiopathology; Depression detection; Electroencephalography; Electroencephalography - methods; Encoding; Feature extraction; Graph neural networks; graph neural networks (GNNs); Humans; Kernel; Mental disorders; Neural Networks, Computer; Nonlinear Dynamics; nonlinear effective connectivity (EC); shared dynamics; Signal Processing, Computer-Assisted; Time series analysis; variational autoencoders (VAEs)

Granger causality (GC) effective connectivity (EC) calculated from electroencephalogram (EEG) signals has been widely used in mental disorder detection. However, the existing methods only take into account linear dynamics or nonlinear dynamics within a single sample, ignoring the nonlinear dynamics...