A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction

2026-07-02

AI Summary

This study addresses limitations in existing approaches to predicting dimensional psychopathological traits from electroencephalography (EEG), which often suffer from disorganized feature granularity and insufficient cross-paradigm consistency. The authors propose a granularity-aware, multi-scale EEG feature framework that hierarchically structures features at global, regional, and channel levels. Integrating tree-based models with a granularity-balanced feature selection strategy, the method effectively predicts four distinct psychopathological dimensions across multiple EEG paradigms. It reveals dimension-specific spatiotemporal-spectral patterns and demonstrates superior performance over conventional methods in cross-dataset validation. Notably, the approach identifies neurophysiological signals with small but informative effect sizes, underscoring its technical feasibility and potential clinical relevance.

Abstract

Electroencephalography (EEG) offers a noninvasive approach for examining neurophysiological correlates of dimensional psychopathology, yet systematic evidence across EEG paradigms and feature granularities remains limited. Here, we develop a granularity-aware EEG feature pipeline that organizes multi-scale descriptors into global, regional, and channel levels. Using the Healthy Brain Network (HBN) cohort, we evaluate the prediction of four psychopathology dimensions: p-factor, internalizing, externalizing, and attention problems, across four EEG paradigms. Given the heterogeneity of pediatric psychopathology and the moderate reliability of questionnaire-derived scores, this setting represents a challenging feasibility test rather than a clinical screening scenario. Tree-based models and granularity-balanced feature selection showed promising improvements over conventional approaches in selected conditions, although effect sizes remained modest. Visualization of selected markers revealed dimension-specific spatial and spectral patterns that were broadly aligned with existing neurophysiological knowledge. An exploratory cross-dataset sanity check on the independent PEARL cohort suggested that the proposed selection principle remains technically feasible under protocol shifts, without claiming cross-dataset generalizability. Overall, multi-scale EEG features contain weak but detectable signals related to dimensional psychopathology, and granularity-aware selection may serve as a useful feature-reduction strategy for future EEG-based phenotyping studies.

Problem

• EEG
• psychopathology dimensions
• feature granularity
• dimensional phenotyping
• neurophysiological correlates

Innovation

• granularity-aware
• multi-scale EEG features
• dimensional psychopathology
• feature selection
• tree-based models