Minimizing bias when using artificial intelligence in critical care medicine

•As artificial intelligence (AI) use in critical care increases, identifying and minimizing sources of bias is essential•Bias can be introduced (and be minimized) at all stages of the AI lifecycle•Reliance on AI in clinical practice without addressing bias may result in unfair and inequitable treatm...

Full description

Saved in:
Bibliographic Details
Published inJournal of critical care Vol. 82; p. 154796
Main Authors Ranard, Benjamin L., Park, Soojin, Jia, Yugang, Zhang, Yiye, Alwan, Fatima, Celi, Leo Anthony, Lusczek, Elizabeth R.
Format Journal Article
LanguageEnglish
Published United States Elsevier Inc 01.08.2024
Elsevier Limited
Subjects
Algorithms
Artificial Intelligence
Bias
COVID-19
Critical Care
Critical Care - methods
Decision making
Disparities
Electronic health records
Fairness
Health care access
Health care expenditures
Health equity
Humans
Intensive care
Machine learning
Missing data
Palliative care
Pandemics
Sepsis
Ventilators
United States > US
Bias
Machine learning
Health equity
Critical Care
Disparities
Artificial intelligence
Fairness
Online AccessGet full text
ISSN0883-9441
1557-8615
1557-8615
DOI10.1016/j.jcrc.2024.154796

Cover

More Information
Summary:•As artificial intelligence (AI) use in critical care increases, identifying and minimizing sources of bias is essential•Bias can be introduced (and be minimized) at all stages of the AI lifecycle•Reliance on AI in clinical practice without addressing bias may result in unfair and inequitable treatment of patients•Diverse, multidisciplinary teams that are attuned to sources of bias may have the best chance of minimizing bias in AI
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Editorial-2
ObjectType-Commentary-1
ISSN:0883-9441
1557-8615
1557-8615
DOI:10.1016/j.jcrc.2024.154796