Semantic match: Debugging feature attribution methods in XAI for healthcare

Giovanni Cinà, Tabea E. Röber, Rob Goedhart, Ş. İlker Birbil

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

The recent spike in certified Artificial Intelligence tools for healthcare has renewed the debate around adoption of this technology. One thread of such debate concerns Explainable AI and its promise to render AI devices more transparent and trustworthy. A few voices active in the medical AI space have expressed concerns on the reliability of Explainable AI techniques and especially feature attribution methods, questioning their use and inclusion in guidelines and standards. We characterize the problem as a lack of semantic match between explanations and human understanding. To understand when feature importance can be used reliably, we introduce a distinction between feature importance of low- and high-level features. We argue that for data types where low-level features come endowed with a clear semantics, such as tabular data like Electronic Health Records, semantic match can be obtained, and thus feature attribution methods can still be employed in a meaningful and useful way. For high-level features, we sketch a procedure to test whether semantic match has been achieved.
Original languageEnglish
Title of host publicationProceedings of the Conference on Health, Inference, and Learning, CHIL 2023
EditorsTasmie Sarker, Andrew Beam, Joyce C. Ho, Bobak J. Mortazavi
PublisherML Research Press
Pages182-191
Number of pages10
Volume209
Publication statusPublished - 2023
Event2nd Conference on Health, Inference, and Learning, CHIL 2023 - Cambridge, United States
Duration: 22 Jun 202324 Jun 2023

Publication series

NameProceedings of Machine Learning Research

Conference

Conference2nd Conference on Health, Inference, and Learning, CHIL 2023
Country/TerritoryUnited States
CityCambridge
Period22/06/202324/06/2023

Cite this