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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the emergence of multimodal electronic health records, the evidence foran outcome may be captured across multiple modalities ranging from clinical toimaging and genomic data. Predicting outcomes effectively requires fusionframeworks capable of modeling fine-grained and multi-faceted complexinteractions between modality features within and across patients. We developan innovative fusion approach called MaxCorr MGNN that models non-linearmodality correlations within and across patients throughHirschfeld-Gebelein-Renyi maximal correlation (MaxCorr) embeddings, resultingin a multi-layered graph that preserves the identities of the modalities andpatients. We then design, for the first time, a generalized multi-layered graphneural network (MGNN) for task-informed reasoning in multi-layered graphs, thatlearns the parameters defining patient-modality graph connectivity and messagepassing in an end-to-end fashion. We evaluate our model an outcome predictiontask on a Tuberculosis (TB) dataset consistently outperforming severalstate-of-the-art neural, graph-based and traditional fusion techniques.

MaxCorrMGNN: A Multi-Graph Neural Network Framework for Generalized Multimodal Fusion of Medical Data for Outcome Prediction