Article

DyGraphTrans: A temporal graph representation learning framework for modeling disease progression from Electronic Health Records

2026-02-02

Abstract excerpt

<h4>Motivation</h4> Electronic Health Records (EHRs) contain vast amounts of longitudinal patient medical history data, making them highly informative for early disease prediction. Numerous computational methods have been developed to leverage EHR data; however, many process multiple patient records simultaneously, resulting in high memory consumption and computational cost. Moreover, these models also often lack...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 705316d8-1005-560f-a608-d8241612a868
DOI: 10.64898/2026.01.28.702347

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

DyGraphTrans: A temporal graph representation learning framework for modeling disease progression from Electronic Health RecordsDOI 10.64898/2026.01.28.702347Read

Graph-based Fusion Modeling and Explanation for Disease Trajectory PredictionSemantic proximity Read

A Novel Dynamic Graph Architecture for Staging Parkinson’s Disease Progression Using Cerebrospinal Fluids Longitudinal ProfilesSemantic proximity Read

A Heterogeneous Graph Neural Network Framework for Multi-Horizon Stroke Mortality PredictionSemantic proximity Read

Multimodal Electronic Health Record Foundation Models with Electrocardiogram for Cardiovascular Disease PredictionSemantic proximity Read

Time-Aware Contrastive Transformer for Longitudinal Patient Representation LearningSemantic proximity Read

Outcome-Oriented Deep Temporal Phenotyping of Disease Progression.Semantic proximity Read

Structure-Aware Temporal Modeling for Chronic Disease Progression PredictionSemantic proximity Read

High-throughput Phenotyping with Temporal SequencesSemantic proximity Read

Temporal Learning with Dynamic Range (TLDR) for Modeling Recurrent Exposure and Treatment OutcomesSemantic proximity Read

DEPOT: graph learning delineates the roles of cancers in the progression trajectories of chronic kidney disease using electronic medical recordsSemantic proximity Read

Characterization of Long Covid Temporal Sub-Phenotypes by Distributed Learning from Electronic Health Record DataSemantic proximity Read

Early Detection of Rare Disease Using Hierarchical Set-to-Sequence Modeling of Structured Electronic Health RecordsSemantic proximity Read