Incomplete Depression Feature Selection with Missing EEG Channels

2025-11-10

AI Summary

Depression diagnosis using EEG faces critical challenges including feature redundancy, noise interference, and channel dropout-induced missing data. To address these issues, this paper proposes a robust feature selection method that innovatively embeds binary channel-missing indicators into an orthogonal regression framework. The method jointly integrates adaptive channel weighting with global redundancy minimization, thereby simultaneously mitigating the impact of data incompleteness and suppressing redundant features. Evaluated on the MODMA and PRED-d003 datasets under multiple channel-missing scenarios (3, 64, and 128 channels), the proposed approach consistently outperforms ten state-of-the-art feature selection methods, achieving average classification accuracy improvements of 3.2–5.7%. This work establishes a novel, interpretable, and highly robust feature selection paradigm for precise depression identification from incomplete EEG recordings.

Technology Category

• Machine Learning: Dimensionality Reduction/Feature Selection
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: State Estimation

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

As a critical mental health disorder, depression has severe effects on both human physical and mental well-being. Recent developments in EEG-based depression analysis have shown promise in improving depression detection accuracies. However, EEG features often contain redundant, irrelevant, and noisy information. Additionally, real-world EEG data acquisition frequently faces challenges, such as data loss from electrode detachment and heavy noise interference. To tackle the challenges, we propose a novel feature selection approach for robust depression analysis, called Incomplete Depression Feature Selection with Missing EEG Channels (IDFS-MEC). IDFS-MEC integrates missing-channel indicator information and adaptive channel weighting learning into orthogonal regression to lessen the effects of incomplete channels on model construction, and then utilizes global redundancy minimization learning to reduce redundant information among selected feature subsets. Extensive experiments conducted on MODMA and PRED-d003 datasets reveal that the EEG feature subsets chosen by IDFS-MEC have superior performance than 10 popular feature selection methods among 3-, 64-, and 128-channel settings.

Problem

• Selecting robust EEG features for depression detection with missing channels
• Reducing redundant and noisy information in EEG-based depression analysis
• Addressing incomplete EEG data from electrode detachment and noise interference

Innovation

• Integrates missing-channel indicators into orthogonal regression
• Uses adaptive channel weighting to handle incomplete EEG data
• Applies global redundancy minimization for feature selection