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

Recent efforts in Machine Learning (ML) interpretability have focused oncreating methods for explaining black-box ML models. However, these methodsrely on the assumption that simple approximations, such as linear models ordecision-trees, are inherently human-interpretable, which has not beenempirically tested. Additionally, past efforts have focused exclusively oncomprehension, neglecting to explore the trust component necessary to convincenon-technical experts, such as clinicians, to utilize ML models in practice. Inthis paper, we posit that reinforcement learning (RL) can be used to learn whatis interpretable to different users and, consequently, build their trust in MLmodels. To validate this idea, we first train a neural network to provide riskassessments for heart failure patients. We then design a RL-based clinicaldecision-support system (DSS) around the neural network model, which can learnfrom its interactions with users. We conduct an experiment involving a diverseset of clinicians from multiple institutions in three different countries. Ourresults demonstrate that ML experts cannot accurately predict which systemoutputs will maximize clinicians' confidence in the underlying neural networkmodel, and suggest additional findings that have broad implications to thefuture of research into ML interpretability and the use of ML in medicine.

What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems