Clinical AI tools must convey predictive uncertainty for each individual patient

Clinical AI tools must convey predictive uncertainty for each individual patient

Artificial intelligence tools usually aim to maximize predictive accuracy, but personalized measures of uncertainty, using new techniques such as conformal prediction, are needed for clinical artificial intelligence to realize its potential and improve human health.

Saved in:
Bibliographic Details
Published in:Nature medicine Vol. 29; no. 12; pp. 2996 - 2998
Main Authors: Banerji, Christopher R. S., Chakraborti, Tapabrata, Harbron, Chris, MacArthur, Ben D.
Format: Journal Article
Language:English
Published: New York Nature Publishing Group US 01-12-2023
Nature Publishing Group
Subjects:
692/308
692/700/1538
Accuracy
Artificial intelligence
Bacterial infections
Biomedical and Life Sciences
Biomedicine
Cancer Research
Clinical decision making
Clinical outcomes
Comment
COVID-19
Epistemology
Headaches
Infectious Diseases
Ischemia
Knowledge
Medicine
Metabolic Diseases
Migraine
Molecular Medicine
Neurosciences
Patients
Stroke
Uncertainty
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial intelligence tools usually aim to maximize predictive accuracy, but personalized measures of uncertainty, using new techniques such as conformal prediction, are needed for clinical artificial intelligence to realize its potential and improve human health.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1078-8956
1546-170X
DOI:10.1038/s41591-023-02562-7