Hierarchical MoE for Multi-Modal ILD Diagnosis

2026-08-25

AI Summary

本文提出了一种分层多模态混合专家模型，通过结合预训练的影像专家和电子健康记录来提高间质性肺病的诊断准确性。

Abstract

Mixture-of-experts (MoE) models combine specialized predictors under learned routing, offering a principled mechanism for leveraging heterogeneity in medical data. We present a hierarchical multimodal MoE for interstitial lung disease (ILD) classification that integrates a frozen, pre-trained imaging expert with structured electronic health records (EHR) via two-stage gating. A modality-level gate assigns patient-specific weights to imaging and EHR predictions, while a sub-gating module decomposes the EHR branch into clinically defined feature groups with learned, group-specific contributions. This design preserves stable imaging representations while enabling input-dependent clinical weighting and explicit EHR specialization. Under strict patient-level cross-validation, the model achieved the highest mean AUC among the evaluated methods (0.8750 +- 0.0443), compared with 0.8646 for imaging-only REN and 0.7685 for SwinUNETR. The framework extends interpretability across anatomical regions, imaging--EHR utilization, and clinically defined EHR feature groups.

Problem

• Interstitial Lung Disease
• Multimodal Data
• Mixture-of-Experts
• Electronic Health Records
• Medical Imaging

Innovation

• Hierarchical MoE
• Multi-Modal ILD Diagnosis
• Two-Stage Gating
• Modality-Level Gate
• Sub-Gating Module