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 in:Journal of critical care 2024-08, Vol.82, p.154796, Article 154796
Main Authors: Ranard, Benjamin L., Park, Soojin, Jia, Yugang, Zhang, Yiye, Alwan, Fatima, Celi, Leo Anthony, Lusczek, Elizabeth R.
Format: Article
Language:English
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
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
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
ISSN:0883-9441
1557-8615
1557-8615
DOI:10.1016/j.jcrc.2024.154796