Impact of artificial intelligence on pathologists’ decisions: an experiment

Impact of artificial intelligence on pathologists’ decisions: an experiment

Abstract Objective The accuracy of artificial intelligence (AI) in medicine and in pathology in particular has made major progress but little is known on how much these algorithms will influence pathologists’ decisions in practice. The objective of this paper is to determine the reliance of patholog...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the American Medical Informatics Association : JAMIA 2022-09, Vol.29 (10), p.1688-1695
Hauptverfasser: Meyer, Julien, Khademi, April, Têtu, Bernard, Han, Wencui, Nippak, Pria, Remisch, David
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Artificial Intelligence
Humans
Male
Pathologists
Prospective Studies
Research and Applications
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1695
container_issue 10
container_start_page 1688
container_title Journal of the American Medical Informatics Association : JAMIA
container_volume 29
creator Meyer, Julien
Khademi, April
Têtu, Bernard
Han, Wencui
Nippak, Pria
Remisch, David
description Abstract Objective The accuracy of artificial intelligence (AI) in medicine and in pathology in particular has made major progress but little is known on how much these algorithms will influence pathologists’ decisions in practice. The objective of this paper is to determine the reliance of pathologists on AI and to investigate whether providing information on AI impacts this reliance. Materials and Methods The experiment using an online survey design. Under 3 conditions, 116 pathologists and pathology students were tasked with assessing the Gleason grade for a series of 12 prostate biopsies: (1) without AI recommendations, (2) with AI recommendations, and (3) with AI recommendations accompanied by information about the algorithm itself, specifically algorithm accuracy rate and algorithm decision-making process. Results Participant responses were significantly more accurate with the AI decision aids than without (92% vs 87%, odds ratio 13.30, P 
doi_str_mv 10.1093/jamia/ocac103
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9471707</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/jamia/ocac103</oup_id><sourcerecordid>2681044113</sourcerecordid><originalsourceid>FETCH-LOGICAL-c420t-cee74d8ec1a629a9f0228747c4ff2bdba89cdd19a1d4613c0e625b344ba4085d3</originalsourceid><addsrcrecordid>eNqFUctOwzAQtBCIlsKRK8qRS6hfiRMOSKjiUamIC0jcrI3ttK6SOMQJghu_we_xJQRaCpw47Uo7mpmdQeiQ4BOCUzZeQmlh7BQogtkWGpKIijAV_GG733EswghTMUB73i8xJjFl0S4asEhEhHMyRDfTsgbVBi4PoGltbpWFIrBVa4rCzk2lTOCqoIZ24Qo3t771769vgTbKeusqfxpAFZjn2jS2NFW7j3ZyKLw5WM8Rur-8uJtch7Pbq-nkfBYqTnEbKmME14lRBGKaQppjShPBheJ5TjOdQZIqrUkKRPOYMIVNTKOMcZ4Bx0mk2QidrXjrLiuNVr10A4WsexfQvEgHVv69VHYh5-5JplwQgUVPcLwmaNxjZ3wrS-tV_zNUxnVe0jghuA-IsB4arqCqcd43Jt_IECw_K5BfFch1BT3-6Le3Dfo78x9t19X_cH0A8C6VEQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2681044113</pqid></control><display><type>article</type><title>Impact of artificial intelligence on pathologists’ decisions: an experiment</title><source>Oxford University Press Journals All Titles (1996-Current)</source><source>MEDLINE</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><creator>Meyer, Julien ; Khademi, April ; Têtu, Bernard ; Han, Wencui ; Nippak, Pria ; Remisch, David</creator><creatorcontrib>Meyer, Julien ; Khademi, April ; Têtu, Bernard ; Han, Wencui ; Nippak, Pria ; Remisch, David</creatorcontrib><description>Abstract Objective The accuracy of artificial intelligence (AI) in medicine and in pathology in particular has made major progress but little is known on how much these algorithms will influence pathologists’ decisions in practice. The objective of this paper is to determine the reliance of pathologists on AI and to investigate whether providing information on AI impacts this reliance. Materials and Methods The experiment using an online survey design. Under 3 conditions, 116 pathologists and pathology students were tasked with assessing the Gleason grade for a series of 12 prostate biopsies: (1) without AI recommendations, (2) with AI recommendations, and (3) with AI recommendations accompanied by information about the algorithm itself, specifically algorithm accuracy rate and algorithm decision-making process. Results Participant responses were significantly more accurate with the AI decision aids than without (92% vs 87%, odds ratio 13.30, P &lt; .01). Unexpectedly, the provision of information on the algorithm made no significant difference compared to AI without information. The reliance on AI correlated with general beliefs on AI’s usefulness but not with particular assessments of the AI tool offered. Decisions were made faster when AI was provided. Discussion These results suggest that pathologists are willing to rely on AI regardless of accuracy or explanations. Generalization beyond the specific tasks and explanations provided will require further studies. Conclusion This study suggests that the factors that influence the reliance on AI differ in practice from beliefs expressed by clinicians in surveys. Implementation of AI in prospective settings should take individual behaviors into account.</description><identifier>ISSN: 1067-5027</identifier><identifier>EISSN: 1527-974X</identifier><identifier>DOI: 10.1093/jamia/ocac103</identifier><identifier>PMID: 35751441</identifier><language>eng</language><publisher>England: Oxford University Press</publisher><subject>Algorithms ; Artificial Intelligence ; Humans ; Male ; Pathologists ; Prospective Studies ; Research and Applications</subject><ispartof>Journal of the American Medical Informatics Association : JAMIA, 2022-09, Vol.29 (10), p.1688-1695</ispartof><rights>The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com 2022</rights><rights>The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c420t-cee74d8ec1a629a9f0228747c4ff2bdba89cdd19a1d4613c0e625b344ba4085d3</citedby><cites>FETCH-LOGICAL-c420t-cee74d8ec1a629a9f0228747c4ff2bdba89cdd19a1d4613c0e625b344ba4085d3</cites><orcidid>0000-0002-0581-4623</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9471707/pdf/$$EPDF$$P50$$Gpubmedcentral$$H</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9471707/$$EHTML$$P50$$Gpubmedcentral$$H</linktohtml><link.rule.ids>230,314,723,776,780,881,1578,27901,27902,53766,53768</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/35751441$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Meyer, Julien</creatorcontrib><creatorcontrib>Khademi, April</creatorcontrib><creatorcontrib>Têtu, Bernard</creatorcontrib><creatorcontrib>Han, Wencui</creatorcontrib><creatorcontrib>Nippak, Pria</creatorcontrib><creatorcontrib>Remisch, David</creatorcontrib><title>Impact of artificial intelligence on pathologists’ decisions: an experiment</title><title>Journal of the American Medical Informatics Association : JAMIA</title><addtitle>J Am Med Inform Assoc</addtitle><description>Abstract Objective The accuracy of artificial intelligence (AI) in medicine and in pathology in particular has made major progress but little is known on how much these algorithms will influence pathologists’ decisions in practice. The objective of this paper is to determine the reliance of pathologists on AI and to investigate whether providing information on AI impacts this reliance. Materials and Methods The experiment using an online survey design. Under 3 conditions, 116 pathologists and pathology students were tasked with assessing the Gleason grade for a series of 12 prostate biopsies: (1) without AI recommendations, (2) with AI recommendations, and (3) with AI recommendations accompanied by information about the algorithm itself, specifically algorithm accuracy rate and algorithm decision-making process. Results Participant responses were significantly more accurate with the AI decision aids than without (92% vs 87%, odds ratio 13.30, P &lt; .01). Unexpectedly, the provision of information on the algorithm made no significant difference compared to AI without information. The reliance on AI correlated with general beliefs on AI’s usefulness but not with particular assessments of the AI tool offered. Decisions were made faster when AI was provided. Discussion These results suggest that pathologists are willing to rely on AI regardless of accuracy or explanations. Generalization beyond the specific tasks and explanations provided will require further studies. Conclusion This study suggests that the factors that influence the reliance on AI differ in practice from beliefs expressed by clinicians in surveys. Implementation of AI in prospective settings should take individual behaviors into account.</description><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Humans</subject><subject>Male</subject><subject>Pathologists</subject><subject>Prospective Studies</subject><subject>Research and Applications</subject><issn>1067-5027</issn><issn>1527-974X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqFUctOwzAQtBCIlsKRK8qRS6hfiRMOSKjiUamIC0jcrI3ttK6SOMQJghu_we_xJQRaCpw47Uo7mpmdQeiQ4BOCUzZeQmlh7BQogtkWGpKIijAV_GG733EswghTMUB73i8xJjFl0S4asEhEhHMyRDfTsgbVBi4PoGltbpWFIrBVa4rCzk2lTOCqoIZ24Qo3t771769vgTbKeusqfxpAFZjn2jS2NFW7j3ZyKLw5WM8Rur-8uJtch7Pbq-nkfBYqTnEbKmME14lRBGKaQppjShPBheJ5TjOdQZIqrUkKRPOYMIVNTKOMcZ4Bx0mk2QidrXjrLiuNVr10A4WsexfQvEgHVv69VHYh5-5JplwQgUVPcLwmaNxjZ3wrS-tV_zNUxnVe0jghuA-IsB4arqCqcd43Jt_IECw_K5BfFch1BT3-6Le3Dfo78x9t19X_cH0A8C6VEQ</recordid><startdate>20220912</startdate><enddate>20220912</enddate><creator>Meyer, Julien</creator><creator>Khademi, April</creator><creator>Têtu, Bernard</creator><creator>Han, Wencui</creator><creator>Nippak, Pria</creator><creator>Remisch, David</creator><general>Oxford University Press</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-0581-4623</orcidid></search><sort><creationdate>20220912</creationdate><title>Impact of artificial intelligence on pathologists’ decisions: an experiment</title><author>Meyer, Julien ; Khademi, April ; Têtu, Bernard ; Han, Wencui ; Nippak, Pria ; Remisch, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c420t-cee74d8ec1a629a9f0228747c4ff2bdba89cdd19a1d4613c0e625b344ba4085d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Humans</topic><topic>Male</topic><topic>Pathologists</topic><topic>Prospective Studies</topic><topic>Research and Applications</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Meyer, Julien</creatorcontrib><creatorcontrib>Khademi, April</creatorcontrib><creatorcontrib>Têtu, Bernard</creatorcontrib><creatorcontrib>Han, Wencui</creatorcontrib><creatorcontrib>Nippak, Pria</creatorcontrib><creatorcontrib>Remisch, David</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Journal of the American Medical Informatics Association : JAMIA</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Meyer, Julien</au><au>Khademi, April</au><au>Têtu, Bernard</au><au>Han, Wencui</au><au>Nippak, Pria</au><au>Remisch, David</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Impact of artificial intelligence on pathologists’ decisions: an experiment</atitle><jtitle>Journal of the American Medical Informatics Association : JAMIA</jtitle><addtitle>J Am Med Inform Assoc</addtitle><date>2022-09-12</date><risdate>2022</risdate><volume>29</volume><issue>10</issue><spage>1688</spage><epage>1695</epage><pages>1688-1695</pages><issn>1067-5027</issn><eissn>1527-974X</eissn><abstract>Abstract Objective The accuracy of artificial intelligence (AI) in medicine and in pathology in particular has made major progress but little is known on how much these algorithms will influence pathologists’ decisions in practice. The objective of this paper is to determine the reliance of pathologists on AI and to investigate whether providing information on AI impacts this reliance. Materials and Methods The experiment using an online survey design. Under 3 conditions, 116 pathologists and pathology students were tasked with assessing the Gleason grade for a series of 12 prostate biopsies: (1) without AI recommendations, (2) with AI recommendations, and (3) with AI recommendations accompanied by information about the algorithm itself, specifically algorithm accuracy rate and algorithm decision-making process. Results Participant responses were significantly more accurate with the AI decision aids than without (92% vs 87%, odds ratio 13.30, P &lt; .01). Unexpectedly, the provision of information on the algorithm made no significant difference compared to AI without information. The reliance on AI correlated with general beliefs on AI’s usefulness but not with particular assessments of the AI tool offered. Decisions were made faster when AI was provided. Discussion These results suggest that pathologists are willing to rely on AI regardless of accuracy or explanations. Generalization beyond the specific tasks and explanations provided will require further studies. Conclusion This study suggests that the factors that influence the reliance on AI differ in practice from beliefs expressed by clinicians in surveys. Implementation of AI in prospective settings should take individual behaviors into account.</abstract><cop>England</cop><pub>Oxford University Press</pub><pmid>35751441</pmid><doi>10.1093/jamia/ocac103</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-0581-4623</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1067-5027
ispartof Journal of the American Medical Informatics Association : JAMIA, 2022-09, Vol.29 (10), p.1688-1695
issn 1067-5027
1527-974X
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9471707
source Oxford University Press Journals All Titles (1996-Current); MEDLINE; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central
subjects Algorithms
Artificial Intelligence
Humans
Male
Pathologists
Prospective Studies
Research and Applications
title Impact of artificial intelligence on pathologists’ decisions: an experiment
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T16%3A54%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Impact%20of%20artificial%20intelligence%20on%20pathologists%E2%80%99%20decisions:%20an%20experiment&rft.jtitle=Journal%20of%20the%20American%20Medical%20Informatics%20Association%20:%20JAMIA&rft.au=Meyer,%20Julien&rft.date=2022-09-12&rft.volume=29&rft.issue=10&rft.spage=1688&rft.epage=1695&rft.pages=1688-1695&rft.issn=1067-5027&rft.eissn=1527-974X&rft_id=info:doi/10.1093/jamia/ocac103&rft_dat=%3Cproquest_pubme%3E2681044113%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2681044113&rft_id=info:pmid/35751441&rft_oup_id=10.1093/jamia/ocac103&rfr_iscdi=true