IMA-MoE: An Interpretable Modality-Aware Mixture-of-Experts Framework for Characterizing the Neurobiological Signatures of Binge Eating Disorder

2026-04-18

AI Summary

Binge Eating Disorder (BED) lacks objective, neurobiologically grounded diagnostic biomarkers, and current approaches—limited by single-modality data and hypothesis-driven models—struggle to enable early, precise identification. This study proposes an Interpretable Multimodal-aware Mixture-of-Experts framework (IMA-MoE), which uniquely integrates a modality-aware Mixture-of-Experts architecture with token-level importance mechanisms to jointly model neuroimaging, behavioral, hormonal, and demographic data. The framework preserves modality-specific characteristics while capturing cross-modal dependencies. Evaluated on the ABCD adolescent cohort, IMA-MoE significantly outperforms baseline models and uncovers sex-specific biomarkers: hormonal measures exhibit greater predictive relevance for BED in females, offering a novel pathway toward precision psychiatry.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Binge eating disorder (BED) is the most prevalent eating disorder. However, current diagnostic frameworks remain largely grounded in symptom-based criteria rather than underlying biological mechanisms, thereby limiting early detection and the development of biologically-informed interventions. Emerging studies have begun to investigate the neurobiological signatures of BED, yet their findings are often difficult to generalize due to the reliance on hypothesis-driven parametric models, single-modality analyses, and limited data diversity. Therefore, there is a critical need for advanced data-driven frameworks capable of modeling multimodal data to uncover generalizable and biologically meaningful signatures of BED. In this study, we propose the Interpretable Modality-Aware Mixture-of-Experts (IMA-MoE), a novel architecture designed to integrate heterogeneous neuroimaging, behavioral, hormonal, and demographic measures within a unified predictive framework. By encoding each measure as a distinct token, IMA-MoE enables flexible modeling of cross-modal dependencies while preserving modality-specific characteristics. We further introduce a token-importance mechanism to enhance interpretability by quantifying the contribution of each measure to model predictions. Evaluated on the large-scale Adolescent Brain Cognitive Development (ABCD) dataset, IMA-MoE demonstrates superior performance in differentiating BED from healthy controls compared with baseline methods, while revealing sex-specific predictive patterns, with hormonal measures contributing more prominently to prediction in females. Collectively, these findings highlight the promise of interpretable, data-driven multimodal modeling in advancing biologically-informed characterization of BED and facilitating more precise and personalized interventions in neuropsychiatric disorders.

Problem

• binge eating disorder
• neurobiological signatures
• multimodal data
• biologically-informed diagnosis
• generalizability

Innovation

• Mixture-of-Experts
• multimodal integration
• interpretable AI
• neurobiological signatures
• binge eating disorder