Cargando…

Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays

Artificial intelligence (AI)-generated clinical advice is becoming more prevalent in healthcare. However, the impact of AI-generated advice on physicians’ decision-making is underexplored. In this study, physicians received X-rays with correct diagnostic advice and were asked to make a diagnosis, ra...

Descripción completa

Detalles Bibliográficos
Autores principales: Gaube, Susanne, Suresh, Harini, Raue, Martina, Lermer, Eva, Koch, Timo K., Hudecek, Matthias F. C., Ackery, Alun D., Grover, Samir C., Coughlin, Joseph F., Frey, Dieter, Kitamura, Felipe C., Ghassemi, Marzyeh, Colak, Errol
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9876883/
https://www.ncbi.nlm.nih.gov/pubmed/36697450
http://dx.doi.org/10.1038/s41598-023-28633-w
_version_ 1784878261234302976
author Gaube, Susanne
Suresh, Harini
Raue, Martina
Lermer, Eva
Koch, Timo K.
Hudecek, Matthias F. C.
Ackery, Alun D.
Grover, Samir C.
Coughlin, Joseph F.
Frey, Dieter
Kitamura, Felipe C.
Ghassemi, Marzyeh
Colak, Errol
author_facet Gaube, Susanne
Suresh, Harini
Raue, Martina
Lermer, Eva
Koch, Timo K.
Hudecek, Matthias F. C.
Ackery, Alun D.
Grover, Samir C.
Coughlin, Joseph F.
Frey, Dieter
Kitamura, Felipe C.
Ghassemi, Marzyeh
Colak, Errol
author_sort Gaube, Susanne
collection PubMed
description Artificial intelligence (AI)-generated clinical advice is becoming more prevalent in healthcare. However, the impact of AI-generated advice on physicians’ decision-making is underexplored. In this study, physicians received X-rays with correct diagnostic advice and were asked to make a diagnosis, rate the advice’s quality, and judge their own confidence. We manipulated whether the advice came with or without a visual annotation on the X-rays, and whether it was labeled as coming from an AI or a human radiologist. Overall, receiving annotated advice from an AI resulted in the highest diagnostic accuracy. Physicians rated the quality of AI advice higher than human advice. We did not find a strong effect of either manipulation on participants’ confidence. The magnitude of the effects varied between task experts and non-task experts, with the latter benefiting considerably from correct explainable AI advice. These findings raise important considerations for the deployment of diagnostic advice in healthcare.
format Online
Article
Text
id pubmed-9876883
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-98768832023-01-27 Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays Gaube, Susanne Suresh, Harini Raue, Martina Lermer, Eva Koch, Timo K. Hudecek, Matthias F. C. Ackery, Alun D. Grover, Samir C. Coughlin, Joseph F. Frey, Dieter Kitamura, Felipe C. Ghassemi, Marzyeh Colak, Errol Sci Rep Article Artificial intelligence (AI)-generated clinical advice is becoming more prevalent in healthcare. However, the impact of AI-generated advice on physicians’ decision-making is underexplored. In this study, physicians received X-rays with correct diagnostic advice and were asked to make a diagnosis, rate the advice’s quality, and judge their own confidence. We manipulated whether the advice came with or without a visual annotation on the X-rays, and whether it was labeled as coming from an AI or a human radiologist. Overall, receiving annotated advice from an AI resulted in the highest diagnostic accuracy. Physicians rated the quality of AI advice higher than human advice. We did not find a strong effect of either manipulation on participants’ confidence. The magnitude of the effects varied between task experts and non-task experts, with the latter benefiting considerably from correct explainable AI advice. These findings raise important considerations for the deployment of diagnostic advice in healthcare. Nature Publishing Group UK 2023-01-25 /pmc/articles/PMC9876883/ /pubmed/36697450 http://dx.doi.org/10.1038/s41598-023-28633-w Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Gaube, Susanne
Suresh, Harini
Raue, Martina
Lermer, Eva
Koch, Timo K.
Hudecek, Matthias F. C.
Ackery, Alun D.
Grover, Samir C.
Coughlin, Joseph F.
Frey, Dieter
Kitamura, Felipe C.
Ghassemi, Marzyeh
Colak, Errol
Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays
title Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays
title_full Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays
title_fullStr Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays
title_full_unstemmed Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays
title_short Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays
title_sort non-task expert physicians benefit from correct explainable ai advice when reviewing x-rays
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9876883/
https://www.ncbi.nlm.nih.gov/pubmed/36697450
http://dx.doi.org/10.1038/s41598-023-28633-w
work_keys_str_mv AT gaubesusanne nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT sureshharini nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT rauemartina nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT lermereva nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT kochtimok nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT hudecekmatthiasfc nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT ackeryalund nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT groversamirc nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT coughlinjosephf nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT freydieter nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT kitamurafelipec nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT ghassemimarzyeh nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays
AT colakerrol nontaskexpertphysiciansbenefitfromcorrectexplainableaiadvicewhenreviewingxrays