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

Deep neural networks and other intricate Artificial Intelligence (AI) modelshave reached high levels of accuracy on many biomedical natural languageprocessing tasks. However, their applicability in real-world use cases may belimited due to their vague inner working and decision logic. A post-hocexplanation method can approximate the behavior of a black-box AI model byextracting relationships between feature values and outcomes. In this paper, weintroduce a post-hoc explanation method that utilizes confident itemsets toapproximate the behavior of black-box classifiers for medical informationextraction. Incorporating medical concepts and semantics into the explanationprocess, our explanator finds semantic relations between inputs and outputs indifferent parts of the decision space of a black-box classifier. Theexperimental results show that our explanation method can outperformperturbation and decision set based explanators in terms of fidelity andinterpretability of explanations produced for predictions on adisease-treatment information extraction task.

Explaining black-box text classifiers for disease-treatment information extraction