Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Yuezhe, Wang, Hao, Peng, Yige, Kim, Jinman, Bi, Lei
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.13919
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911387161198592
author Yang, Yuezhe
Wang, Hao
Peng, Yige
Kim, Jinman
Bi, Lei
author_facet Yang, Yuezhe
Wang, Hao
Peng, Yige
Kim, Jinman
Bi, Lei
contents Automated clinical diagnosis remains a core challenge in medical AI, which usually requires models to integrate multi-modal data and reason across complex, case-specific contexts. Although recent methods have advanced medical report generation (MRG) and visual question answering (VQA) with medical vision-language models (VLMs), these methods, however, predominantly operate under a sample-isolated inference paradigm, as such processing cases independently without access to longitudinal electronic health records (EHRs) or structurally related patient examples. This paradigm limits reasoning to image-derived information alone, which ignores external complementary medical evidence for potentially more accurate diagnosis. To overcome this limitation, we propose \textbf{HyperWalker}, a \textit{Deep Diagnosis} framework that reformulates clinical reasoning via dynamic hypergraphs and test-time training. First, we construct a dynamic hypergraph, termed \textbf{iBrochure}, to model the structural heterogeneity of EHR data and implicit high-order associations among multimodal clinical information. Within this hypergraph, a reinforcement learning agent, \textbf{Walker}, navigates to and identifies optimal diagnostic paths. To ensure comprehensive coverage of diverse clinical characteristics in test samples, we incorporate a \textit{linger mechanism}, a multi-hop orthogonal retrieval strategy that iteratively selects clinically complementary neighborhood cases reflecting distinct clinical attributes. Experiments on MRG with MIMIC and medical VQA on EHRXQA demonstrate that HyperWalker achieves state-of-the-art performance. Code is available at: https://github.com/Bean-Young/HyperWalker
format Preprint
id arxiv_https___arxiv_org_abs_2601_13919
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyperWalker: Dynamic Hypergraph-Based Deep Diagnosis for Multi-Hop Clinical Modeling across EHR and X-Ray in Medical VLMs
Yang, Yuezhe
Wang, Hao
Peng, Yige
Kim, Jinman
Bi, Lei
Computation and Language
Computer Vision and Pattern Recognition
Automated clinical diagnosis remains a core challenge in medical AI, which usually requires models to integrate multi-modal data and reason across complex, case-specific contexts. Although recent methods have advanced medical report generation (MRG) and visual question answering (VQA) with medical vision-language models (VLMs), these methods, however, predominantly operate under a sample-isolated inference paradigm, as such processing cases independently without access to longitudinal electronic health records (EHRs) or structurally related patient examples. This paradigm limits reasoning to image-derived information alone, which ignores external complementary medical evidence for potentially more accurate diagnosis. To overcome this limitation, we propose \textbf{HyperWalker}, a \textit{Deep Diagnosis} framework that reformulates clinical reasoning via dynamic hypergraphs and test-time training. First, we construct a dynamic hypergraph, termed \textbf{iBrochure}, to model the structural heterogeneity of EHR data and implicit high-order associations among multimodal clinical information. Within this hypergraph, a reinforcement learning agent, \textbf{Walker}, navigates to and identifies optimal diagnostic paths. To ensure comprehensive coverage of diverse clinical characteristics in test samples, we incorporate a \textit{linger mechanism}, a multi-hop orthogonal retrieval strategy that iteratively selects clinically complementary neighborhood cases reflecting distinct clinical attributes. Experiments on MRG with MIMIC and medical VQA on EHRXQA demonstrate that HyperWalker achieves state-of-the-art performance. Code is available at: https://github.com/Bean-Young/HyperWalker
title HyperWalker: Dynamic Hypergraph-Based Deep Diagnosis for Multi-Hop Clinical Modeling across EHR and X-Ray in Medical VLMs
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.13919