English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multivariate biosignals are prevalent in many medical domains, such aselectroencephalography, polysomnography, and electrocardiography. Modelingspatiotemporal dependencies in multivariate biosignals is challenging due to(1) long-range temporal dependencies and (2) complex spatial correlationsbetween the electrodes. To address these challenges, we propose representingmultivariate biosignals as time-dependent graphs and introduce GraphS4mer, ageneral graph neural network (GNN) architecture that improves performance onbiosignal classification tasks by modeling spatiotemporal dependencies inbiosignals. Specifically, (1) we leverage the Structured State Spacearchitecture, a state-of-the-art deep sequence model, to capture long-rangetemporal dependencies in biosignals and (2) we propose a graph structurelearning layer in GraphS4mer to learn dynamically evolving graph structures inthe data. We evaluate our proposed model on three distinct biosignalclassification tasks and show that GraphS4mer consistently improves overexisting models, including (1) seizure detection from electroencephalographicsignals, outperforming a previous GNN with self-supervised pre-training by 3.1points in AUROC; (2) sleep staging from polysomnographic signals, a 4.1 pointsimprovement in macro-F1 score compared to existing sleep staging models; and(3) 12-lead electrocardiogram classification, outperforming previousstate-of-the-art models by 2.7 points in macro-F1 score.

Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models