Investigating anatomical bias in clinical machine learning algorithms

Jannik Skyttegaard Pedersen, Martin Sundahl Laursen, Pernille Just Vinholt, Anne Bryde Alnor, Thiusius Rajeeth Savarimuthu

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

31 Downloads (Pure)

Abstract

Clinical machine learning algorithms have shown promising results and could potentially be implemented in clinical practice to provide diagnosis support and improve patient treatment. Barriers for realisation of the algorithms’ full potential include bias which is systematic and unfair discrimination against certain individuals in favor of others. The objective of this work is to measure anatomical bias in clinical text algorithms. We define anatomical bias as unfair algorithmic outcomes against patients with medical conditions in specific anatomical locations. We measure the degree of anatomical bias across two machine learning models and two Danish clinical text classification tasks, and find that clinical text algorithms are highly prone to anatomical bias. We argue that datasets for creating clinical text algorithms should be curated carefully to isolate the effect of anatomical location in order to avoid bias against patient subgroups.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics: EACL 2023
PublisherAssociation for Computational Linguistics (ACL)
Publication date2023
Pages1368-1380
ISBN (Electronic)9781959429470
Publication statusPublished - 2023
Event17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023 - Dubrovnik, Croatia
Duration: 2. May 20236. May 2023

Conference

Conference17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023
Country/TerritoryCroatia
CityDubrovnik
Period02/05/202306/05/2023
SponsorAdobe, Babelscape, Bloomberg Engineering, Duolingo, LivePerson

Fingerprint

Dive into the research topics of 'Investigating anatomical bias in clinical machine learning algorithms'. Together they form a unique fingerprint.

Cite this