用分层专家模型融合影像与病历，提升间质性肺病诊断准确率。
Hierarchical MoE for Multi-Modal ILD Diagnosis
- 分两阶段路由：先选影像或病历，再细分病历特征组加权
- 在患者级交叉验证中平均AUC达0.875，优于纯影像模型
- 可解释性强，能看懂不同部位、模态及临床特征的贡献
混合专家（MoE）模型通过学习路由机制整合专用预测器，为利用医学数据异质性提供合理框架。本文提出一种分层多模态MoE用于间质性肺病（ILD）分类，将冻结的预训练影像专家与结构化电子健康记录（EHR）通过双阶段门控集成。模态级门控为影像与EHR预测分配患者特异性权重，子门控模块则将EHR分支分解为临床定义的特征组，并学习各组的专属贡献。该设计保持影像表征稳定的同时，实现输入依赖的临床加权和显式的EHR专业化。在严格的患者级交叉验证下，模型平均AUC达0.8750 ± 0.0443，高于仅影像的RENet（0.8646）和SwinUNETR（0.7685）。该框架扩展了对解剖区域、影像-病历利用及临床定义的EHR特征组的可解释性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。