Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-6th-edition.csl
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
An evaluation of contextual importance and utility for outcome explanation of black-box predictions for medical datasets
Aalto University, Helsinki, Finland; Bournemouth University, Poole, UK.
Umeå University, Faculty of Science and Technology, Department of Computing Science. Aalto University, Helsinki, Finland.ORCID iD: 0000-0002-8078-5172
2023 (English)In: Explainable artificial intelligence: First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part I / [ed] Luca Longo, Springer Nature, 2023, p. 544-557Conference paper, Published paper (Refereed)
Abstract [en]

Contextual Importance and Utility (CIU) is a model-agnostic method for producing situation- or instance-specific explanations of the outcome of so-called black-box systems. A major difference between CIU and other outcome explanation methods (also called post-hoc methods) is that CIU produces explanations without producing any intermediate interpretable model. CIU’s notion of importance is similar as in Decision Theory but differs from how importance is defined for other outcome explanation methods. Utility is also a well-known concept from Decision Theory that is largely ignored in current Explainable AI research. CIU is here validated by providing explanations for the two popular medical data sets - heart disease and breast cancer in order to show the applicability of CIU explanations on medical predictions and with different black-box models. The explanations are compared with corresponding ones produced by the Local Interpretable Model-agnostic Explanations (LIME) method [17], which is currently one of the most used post-hoc explanation methods. The paper’s main contribution is to provide new CIU results and insights on several benchmark data sets and showing in what way CIU differs from LIME-based explanations.

Place, publisher, year, edition, pages
Springer Nature, 2023. p. 544-557
Series
Communications in Computer and Information Science book series (CCIS), ISSN 1865-0929, E-ISSN 1865-0937 ; 1901
Keywords [en]
Explainable AI, Contextual Importance, Contextual Utility, Multiple Criteria Decision Making, Heart disease, Breast cancer data
National Category
Human Computer Interaction
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:umu:diva-217312DOI: 10.1007/978-3-031-44064-9_29Scopus ID: 2-s2.0-85176960967ISBN: 978-3-031-44063-2 (print)ISBN: 978-3-031-44064-9 (electronic)OAI: oai:DiVA.org:umu-217312DiVA, id: diva2:1815633
Conference
1st World Conference on Explainable Artificial Intelligence, xAI 2023, Lisbon, Portugal, July 26-28, 2023
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP), 570011220Available from: 2023-11-29 Created: 2023-11-29 Last updated: 2023-12-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Främling, Kary

Search in DiVA

By author/editor
Främling, Kary
By organisation
Department of Computing Science
Human Computer Interaction

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 141 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-6th-edition.csl
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf