← Back to all news
arXiv AI By Leo Y. Li-Han, Chris Varghese, Elizabeth B. Habermann, Mark J. Truty, William R. G. Perry, Cornelius A. Thiels, Hojjat Salehinejad

GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers

Read the original on arXiv AI →

GraphBEAT is a temporal graph representation learning framework that bucketizes clinical events from longitudinal electronic health records into time‑ordered graphs, enabling early risk stratification for gastrointestinal cancers. It uses a time‑decay message‑passing mechanism and multi‑head attention pooling to generate patient‑level representations, and was trained on multi‑site diagnosis codes and laboratory tests to predict pancreatic, liver, and intestinal cancer at 12, 24, and 36‑month lead times. Across all experiments, GraphBEAT outperformed baseline graph neural networks and sequence models while requiring far fewer floating‑point operations and parameters.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 4

EHR2Path: Comprehensive Pathway-Level Modeling of Longitudinal Patient Trajectories from Multimodal Electronic Health Records

arXiv:2506. 04831v3 Announce Type: replace Abstract: Forecasting how a patient's condition is likely to evolve, including possible deterioration, recovery, treatment needs, and care transitions, could support more proactive and personalized care, but requires modeling heterogeneous and longitudinal electronic health record (EHR) data.

By Chantal Pellegrini, Ege \"Ozsoy, David Bani-Harouni, Matthias Keicher, Nassir Navab
nlpmultimodal
More like this →
arXiv Machine Learning
4d ago

Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records

The study introduces a graph‑enhanced framework for discovering disease trajectories and forecasting temporal endpoints using longitudinal EHR data from MIMIC‑IV v3.1. It constructs patient‑specific motifs from consecutive admissions, applies a time‑aware Transformer to select up to 24 motifs per endpoint, and reports modest improvements in micro‑AUPRC and event‑time MAE, with larger gains for events occurring after 730 days. The authors also explore branching‑motif conditioning and GNN‑based edge repair, finding that motifs mainly provide long‑range timing support rather than superior endpoint discrimination or survival prediction.

By Jin-Jia Zheng, Vincent S. Tseng
llms
More like this →
arXiv Machine Learning
Aug 26

A Multimodal Foundation Model for Longitudinal Patient Representation and Scalable Insight Generation in Oncology

arXiv:2608.24688v1 Announce Type: new Abstract: Precision oncology necessitates a longitudinal model of patient state that captures cancer evolution and treatment over time, integrating multimodal ob...

By Eugene Vorontsov, Yi Kan Wang, Alican Bozkurt, Adam Casson, Ludmila Tydlitatova, Michal Zelechowski, Ezra E. W. Cohen, Jyoti D. Patel, Max Banaszak, Caitlin McWilliams, Shane Colley, Kate Sasser, Ryan Fukushima, Eric Lefkofsky, Razik Yousfi, Siqi Liu
ragmultimodalbenchmarks
More like this →