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

Predicting in-hospital mortality for intensive care unit (ICU) patients iskey to final clinical outcomes. AI has shown advantaged accuracy but suffersfrom the lack of explainability. To address this issue, this paper proposes aneXplainable Multimodal Mortality Predictor (X-MMP) approaching an efficient,explainable AI solution for predicting in-hospital mortality via multimodal ICUdata. We employ multimodal learning in our framework, which can receiveheterogeneous inputs from clinical data and make decisions. Furthermore, weintroduce an explainable method, namely Layer-Wise Propagation to Transformer,as a proper extension of the LRP method to Transformers, producing explanationsover multimodal inputs and revealing the salient features attributed toprediction. Moreover, the contribution of each modality to clinical outcomescan be visualized, assisting clinicians in understanding the reasoning behinddecision-making. We construct a multimodal dataset based on MIMIC-III andMIMIC-III Waveform Database Matched Subset. Comprehensive experiments onbenchmark datasets demonstrate that our proposed framework can achievereasonable interpretation with competitive prediction accuracy. In particular,our framework can be easily transferred to other clinical tasks, whichfacilitates the discovery of crucial factors in healthcare research.

XAI for In-hospital Mortality Prediction via Multimodal ICU Data