Evaluating Hierarchical Medical Workflows using Feature Importance

Pawar, Urja; Culbert, Christopher T; O’Reilly, Ruairi

doi:10.1109/cbms52027.2021.00075

Cited by 1 publication

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As detailed in Section IV, the comparison involves the average rank of k missing features and the average rank of topk present features ensuring that our focus remains on the most influential present features and avoiding dilution of the average rank from lower-ranked ones. In [31], we gathered the workflow information for the heart disease diagnosis based on the medical literature for demonstrating a specific utility of XAI. However, in this work, we used random multiple sets of present/missing features for the evaluation due to the lack of workflow information with respect to other datasets -Cervical Cancer, and Diabetes.…”

Section: ) Early Stoppingmentioning

confidence: 99%

Optimal Neighborhood Contexts in Explainable AI: An Explanandum-Based Evaluation

Pawar,

O'Shea,

O'Reilly

et al. 2024

IEEE Open J. Comput. Soc.

Self Cite

View full text Add to dashboard Cite

Over the years, several frameworks have been proposed in the domain of Explainable AI (XAI), however their practical applicability and utility need to be clarified. The neighbourhood contexts are shown to significantly impact the explanations generated by XAI frameworks, thus directly affecting their utility in addressing specific questions, or "explananda". This work introduces a methodology that use a comprehensive range of neighbourhood contexts to evaluate and enhance the utility of specific XAI techniques, particularly Feature Importance and CounterFactuals. In this evaluation, two explananda are targeted. The first one examines whether features' collection should be halted as per the AI model based on the sufficiency of the current set of information. Here, the information refers to the features present in the data used to train the AI-based system. The second one explores what is the most effective information (features) that should be collected next to ensure that the AI outputs the same classification as it would have generated with all the information present. These questions serve as a platform to demonstrate our methodology's ability to assess the impact of customised neighbourhood contexts on the utility of XAI.

show abstract

Section: ) Early Stoppingmentioning

confidence: 99%