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

Explainability is key to enhancing artificial intelligence's trustworthinessin medicine. However, several issues remain concerning the actual benefit ofexplainable models for clinical decision-making. Firstly, there is a lack ofconsensus on an evaluation framework for quantitatively assessing the practicalbenefits that effective explainability should provide to practitioners.Secondly, physician-centered evaluations of explainability are limited.Thirdly, the utility of built-in attention mechanisms in transformer-basedmodels as an explainability technique is unclear. We hypothesize that superiorattention maps should align with the information that physicians focus on,potentially reducing prediction uncertainty and increasing model reliability.We employed a multimodal transformer to predict lymph node metastasis in rectalcancer using clinical data and magnetic resonance imaging, exploring how wellattention maps, visualized through a state-of-the-art technique, can achieveagreement with physician understanding. We estimated the model's uncertaintyusing meta-level information like prediction probability variance andquantified agreement. Our assessment of whether this agreement reducesuncertainty found no significant effect. In conclusion, this case study did notconfirm the anticipated benefit of attention maps in enhancing modelreliability. Superficial explanations could do more harm than good bymisleading physicians into relying on uncertain predictions, suggesting thatthe current state of attention mechanisms in explainability should not beoverestimated. Identifying explainability mechanisms truly beneficial forclinical decision-making remains essential.

Can Physician Judgment Enhance Model Trustworthiness? A Case Study on Predicting Pathological Lymph Nodes in Rectal Cancer