The reproducibility issues that haunt health-care AI

Health-care systems are rolling out artificial-intelligence tools for diagnosis and monitoring. But how reliable are the models? Health-care systems are rolling out artificial-intelligence tools for diagnosis and monitoring. But how reliable are the models? Credit: ktsimage/Getty Computer generated...

Full description

Saved in:
Bibliographic Details
Published in:Nature (London) 2023-01, Vol.613 (7943), p.402-403
Main Author: Sohn, Emily
Format: Article
Language:English
Subjects:
631/114
631/114/1305
639/705
706/648/697
Algorithms
Artificial intelligence
Artificial Intelligence - standards
Collaboration
Computed tomography
Coronaviruses
COVID-19
Data science
Datasets
Delivery of Health Care - methods
Delivery of Health Care - standards
Diagnosis
Digital data
Health care
Humanities and Social Sciences
Humans
Lung cancer
Lung diseases
Machine learning
Machine Learning - standards
Medical research
Medicine
multidisciplinary
Quality of Health Care
Reproducibility
Reproducibility of Results
Science
Scientists
Sepsis
Teams
Technology Feature
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:Health-care systems are rolling out artificial-intelligence tools for diagnosis and monitoring. But how reliable are the models? Health-care systems are rolling out artificial-intelligence tools for diagnosis and monitoring. But how reliable are the models? Credit: ktsimage/Getty Computer generated artwork illustrating points of a neural network on a background of binary.
ISSN:0028-0836
1476-4687
DOI:10.1038/d41586-023-00023-2