NSSI-Net: A Multi-Concept GAN for Non-Suicidal Self-Injury Detection Using High-Dimensional EEG in a Semi-Supervised Framework

2024-10-16

AI Summary

Early identification of non-suicidal self-injury (NSSI) in adolescents remains a critical clinical challenge due to the scarcity of labeled neurophysiological data and the complexity of underlying neural dynamics. Method: We propose a semi-supervised EEG analysis framework integrating spatiotemporal dynamic modeling and heterogeneous multimodal information. Specifically: (i) a novel multi-concept discriminator jointly models EEG signals, gender, acquisition domain, and clinical status; (ii) a spatiotemporal-coupled feature extractor combines 2D-CNN and BiGRU to capture time-frequency and topographic dynamic patterns; and (iii) a semi-supervised generative adversarial strategy mitigates label scarcity. Contribution/Results: Evaluated on a newly collected dataset of 114 NSSI adolescents, our model outperforms state-of-the-art machine learning and deep learning methods by 5.44% in classification accuracy. It significantly enhances objective, early detection of NSSI in depressed adolescents and establishes a clinically actionable, interpretable, and robust paradigm for risk prediction.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Non-suicidal self-injury (NSSI) is a serious threat to the physical and mental health of adolescents, significantly increasing the risk of suicide and attracting widespread public concern. Electroencephalography (EEG), as an objective tool for identifying brain disorders, holds great promise. However, extracting meaningful and reliable features from high-dimensional EEG data, especially by integrating spatiotemporal brain dynamics into informative representations, remains a major challenge. In this study, we introduce an advanced semi-supervised adversarial network, NSSI-Net, to effectively model EEG features related to NSSI. NSSI-Net consists of two key modules: a spatial-temporal feature extraction module and a multi-concept discriminator. In the spatial-temporal feature extraction module, an integrated 2D convolutional neural network (2D-CNN) and a bi-directional Gated Recurrent Unit (BiGRU) are used to capture both spatial and temporal dynamics in EEG data. In the multi-concept discriminator, signal, gender, domain, and disease levels are fully explored to extract meaningful EEG features, considering individual, demographic, disease variations across a diverse population. Based on self-collected NSSI data (n=114), the model's effectiveness and reliability are demonstrated, with a 5.44% improvement in performance compared to existing machine learning and deep learning methods. This study advances the understanding and early diagnosis of NSSI in adolescents with depression, enabling timely intervention. The source code is available at https://github.com/Vesan-yws/NSSINet.

Problem

• Detecting Non-Suicidal Self-Injury via EEG
• Modeling high-dimensional EEG features
• Improving NSSI diagnosis in adolescents

Innovation

• Semi-supervised adversarial network
• Spatial-temporal feature extraction
• Multi-concept discriminator exploration