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

Multi-modal fusion approaches aim to integrate information from differentdata sources. Unlike natural datasets, such as in audio-visual applications,where samples consist of "paired" modalities, data in healthcare is oftencollected asynchronously. Hence, requiring the presence of all modalities for agiven sample is not realistic for clinical tasks and significantly limits thesize of the dataset during training. In this paper, we propose MedFuse, aconceptually simple yet promising LSTM-based fusion module that can accommodateuni-modal as well as multi-modal input. We evaluate the fusion method andintroduce new benchmark results for in-hospital mortality prediction andphenotype classification, using clinical time-series data in the MIMIC-IVdataset and corresponding chest X-ray images in MIMIC-CXR. Compared to morecomplex multi-modal fusion strategies, MedFuse provides a performanceimprovement by a large margin on the fully paired test set. It also remainsrobust across the partially paired test set containing samples with missingchest X-ray images. We release our code for reproducibility and to enable theevaluation of competing models in the future.

MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray images