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

Explainable Artificial Intelligence (XAI) is a rising field in AI. It aims toproduce a demonstrative factor of trust, which for human subjects is achievedthrough communicative means, which Machine Learning (ML) algorithms cannotsolely produce, illustrating the necessity of an extra layer producing supportto the model output. When approaching the medical field, we can see challengesarise when dealing with the involvement of human-subjects, the ideology behindtrusting a machine to tend towards the livelihood of a human poses an ethicalconundrum - leaving trust as the basis of the human-expert in acceptance to themachines decision. The aim of this paper is to apply XAI methods to demonstratethe usability of explainable architectures as a tertiary layer for the medicaldomain supporting ML predictions and human-expert opinion, XAI methods producevisualization of the feature contribution towards a given models output on botha local and global level. The work in this paper uses XAI to determine featureimportance towards high-dimensional data-driven questions to informdomain-experts of identifiable trends with a comparison of model-agnosticmethods in application to ML algorithms. The performance metrics for aglass-box method is also provided as a comparison against black-box capabilityfor tabular data. Future work will aim to produce a user-study using metrics toevaluate human-expert usability and opinion of the given models.

A Comparative Approach to Explainable Artificial Intelligence Methods in  Application to High-Dimensional Electronic Health Records: Examining the  Usability of XAI