End-to-End Machine Learning for Depressive State Classification via EEG and fNIRS

2026-06-09

AI Summary

Traditional diagnosis of psychiatric disorders relies heavily on subjective assessments, making objective identification of depressive states particularly challenging—especially in older adults where depression frequently co-occurs with dementia and early differentiation is critical. This study proposes the first end-to-end multimodal machine learning framework that integrates electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) signals to automatically classify depressive states directly from raw neurophysiological data. By eliminating the need for manual feature engineering, the approach establishes a novel, quantifiable, and non-invasive paradigm for early screening. Initial validation on 11 healthy participants demonstrates technical feasibility, laying the groundwork for future large-scale clinical deployment.

Abstract

The escalating demand for mental healthcare, driven by rising societal stress, highlights the limitations of traditional psychiatric diagnostics. Conventional methods - relying primarily on clinical interviews and patient self-reports - are inherently vulnerable to subjective bias and the varying empirical judgment of practitioners. To address the need for quantitative evaluation, biological signal-based detection, including electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS), has emerged as a promising objective alternative. Such technology is particularly vital for identifying latent depressive states that may be unrecognized by the subjects themselves. Furthermore, in aging populations, the high comorbidity between depression and dementia necessitates early differentiation to prevent mutual symptom exacerbation and maintain Quality of Life (QoL). This pilot study of eleven healthy students establishes a framework for biological signal-based depression detection, serving as a foundational step toward automated, objective diagnostic tools for clinical use.

Problem

• depressive state classification
• EEG
• fNIRS
• objective diagnosis
• mental healthcare

Innovation

• end-to-end machine learning
• EEG
• fNIRS
• depressive state classification
• objective mental health assessment