Loading…
Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice
Purpose Recently, there has been a growing interest in using ChatGPT for various applications in Medicine. We evaluated the interest of OpenAI chatbot (GPT 4.0) for drug information activities at Toulouse Pharmacovigilance Center. Methods Based on a series of 50 randomly selected questions sent to o...
Saved in:
| Published in: | European journal of clinical pharmacology 2023-10, Vol.79 (10), p.1375-1384 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| 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!
|
| cited_by | cdi_FETCH-LOGICAL-c375t-7af206172fd7286fa3cdc653c178141d9b59e2fd4079fc52f8019437593e5e773 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c375t-7af206172fd7286fa3cdc653c178141d9b59e2fd4079fc52f8019437593e5e773 |
| container_end_page | 1384 |
| container_issue | 10 |
| container_start_page | 1375 |
| container_title | European journal of clinical pharmacology |
| container_volume | 79 |
| creator | Montastruc, François Storck, Wilhelm de Canecaude, Claire Victor, Léa Li, Julien Cesbron, Candice Zelmat, Yoann Barus, Romain |
| description | Purpose
Recently, there has been a growing interest in using ChatGPT for various applications in Medicine. We evaluated the interest of OpenAI chatbot (GPT 4.0) for drug information activities at Toulouse Pharmacovigilance Center.
Methods
Based on a series of 50 randomly selected questions sent to our pharmacovigilance center by healthcare professionals or patients, we compared the level of responses from the chatbot GPT 4.0 with those provided by specialists in pharmacovigilance.
Results
Chatbot answers were globally not acceptable. Responses to inquiries regarding the assessment of drug causality were not consistently precise or clinically meaningful.
Conclusion
The interest of chatbot assistance needs to be confirmed or rejected through further studies conducted in other pharmacovigilance centers. |
| doi_str_mv | 10.1007/s00228-023-03547-8 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2850311706</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2850311706</sourcerecordid><originalsourceid>FETCH-LOGICAL-c375t-7af206172fd7286fa3cdc653c178141d9b59e2fd4079fc52f8019437593e5e773</originalsourceid><addsrcrecordid>eNp9kU1LAzEQhoMotlb_gAdZ8OJldZLsbnZPUopfUPCieAxpNtumpJttkgX7701t_cCDp4HM874zmRehcwzXGIDdeABCyhQITYHmGUvLAzTEGSUphgwfoiEAxWlRMRigE--XADivgB6jAWV5UWBKh2j9po1JhAu60VILk-g2KGP0XLVSJXIhwswGnzjVGbF9MLrVMmLdQriVkNbYufbB3ybjNlHvnbFOBOs2iQ99vYlmvxROyKClOkVHjTBene3rCL3e371MHtPp88PTZDxNZdwupEw0BArMSFMzUhaNoLKWRU4lZiXOcF3N8krFZgasamROmhJwlUVpRVWuGKMjdLXz7Zxd98oHvtJexr-JVtnec1Lm8TyYQRHRyz_o0vaujdtFqsjiBTGBSJEdJZ313qmGd06vhNtwDHwbCN8FwmMg_DMQXkbRxd66n61U_S35SiACdAf42Grnyv3M_sf2A-8plsg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2864697120</pqid></control><display><type>article</type><title>Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice</title><source>Springer Nature</source><creator>Montastruc, François ; Storck, Wilhelm ; de Canecaude, Claire ; Victor, Léa ; Li, Julien ; Cesbron, Candice ; Zelmat, Yoann ; Barus, Romain</creator><creatorcontrib>Montastruc, François ; Storck, Wilhelm ; de Canecaude, Claire ; Victor, Léa ; Li, Julien ; Cesbron, Candice ; Zelmat, Yoann ; Barus, Romain</creatorcontrib><description>Purpose
Recently, there has been a growing interest in using ChatGPT for various applications in Medicine. We evaluated the interest of OpenAI chatbot (GPT 4.0) for drug information activities at Toulouse Pharmacovigilance Center.
Methods
Based on a series of 50 randomly selected questions sent to our pharmacovigilance center by healthcare professionals or patients, we compared the level of responses from the chatbot GPT 4.0 with those provided by specialists in pharmacovigilance.
Results
Chatbot answers were globally not acceptable. Responses to inquiries regarding the assessment of drug causality were not consistently precise or clinically meaningful.
Conclusion
The interest of chatbot assistance needs to be confirmed or rejected through further studies conducted in other pharmacovigilance centers.</description><identifier>ISSN: 0031-6970</identifier><identifier>ISSN: 1432-1041</identifier><identifier>EISSN: 1432-1041</identifier><identifier>DOI: 10.1007/s00228-023-03547-8</identifier><identifier>PMID: 37566133</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Artificial intelligence ; Biomedical and Life Sciences ; Biomedicine ; Causality ; Chatbots ; Clinical medicine ; Drug interactions ; Information services ; Likert scale ; Medical personnel ; Patients ; Pharmacists ; Pharmacology ; Pharmacology/Toxicology ; Pharmacovigilance ; Social networks</subject><ispartof>European journal of clinical pharmacology, 2023-10, Vol.79 (10), p.1375-1384</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c375t-7af206172fd7286fa3cdc653c178141d9b59e2fd4079fc52f8019437593e5e773</citedby><cites>FETCH-LOGICAL-c375t-7af206172fd7286fa3cdc653c178141d9b59e2fd4079fc52f8019437593e5e773</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37566133$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Montastruc, François</creatorcontrib><creatorcontrib>Storck, Wilhelm</creatorcontrib><creatorcontrib>de Canecaude, Claire</creatorcontrib><creatorcontrib>Victor, Léa</creatorcontrib><creatorcontrib>Li, Julien</creatorcontrib><creatorcontrib>Cesbron, Candice</creatorcontrib><creatorcontrib>Zelmat, Yoann</creatorcontrib><creatorcontrib>Barus, Romain</creatorcontrib><title>Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice</title><title>European journal of clinical pharmacology</title><addtitle>Eur J Clin Pharmacol</addtitle><addtitle>Eur J Clin Pharmacol</addtitle><description>Purpose
Recently, there has been a growing interest in using ChatGPT for various applications in Medicine. We evaluated the interest of OpenAI chatbot (GPT 4.0) for drug information activities at Toulouse Pharmacovigilance Center.
Methods
Based on a series of 50 randomly selected questions sent to our pharmacovigilance center by healthcare professionals or patients, we compared the level of responses from the chatbot GPT 4.0 with those provided by specialists in pharmacovigilance.
Results
Chatbot answers were globally not acceptable. Responses to inquiries regarding the assessment of drug causality were not consistently precise or clinically meaningful.
Conclusion
The interest of chatbot assistance needs to be confirmed or rejected through further studies conducted in other pharmacovigilance centers.</description><subject>Artificial intelligence</subject><subject>Biomedical and Life Sciences</subject><subject>Biomedicine</subject><subject>Causality</subject><subject>Chatbots</subject><subject>Clinical medicine</subject><subject>Drug interactions</subject><subject>Information services</subject><subject>Likert scale</subject><subject>Medical personnel</subject><subject>Patients</subject><subject>Pharmacists</subject><subject>Pharmacology</subject><subject>Pharmacology/Toxicology</subject><subject>Pharmacovigilance</subject><subject>Social networks</subject><issn>0031-6970</issn><issn>1432-1041</issn><issn>1432-1041</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9kU1LAzEQhoMotlb_gAdZ8OJldZLsbnZPUopfUPCieAxpNtumpJttkgX7701t_cCDp4HM874zmRehcwzXGIDdeABCyhQITYHmGUvLAzTEGSUphgwfoiEAxWlRMRigE--XADivgB6jAWV5UWBKh2j9po1JhAu60VILk-g2KGP0XLVSJXIhwswGnzjVGbF9MLrVMmLdQriVkNbYufbB3ybjNlHvnbFOBOs2iQ99vYlmvxROyKClOkVHjTBene3rCL3e371MHtPp88PTZDxNZdwupEw0BArMSFMzUhaNoLKWRU4lZiXOcF3N8krFZgasamROmhJwlUVpRVWuGKMjdLXz7Zxd98oHvtJexr-JVtnec1Lm8TyYQRHRyz_o0vaujdtFqsjiBTGBSJEdJZ313qmGd06vhNtwDHwbCN8FwmMg_DMQXkbRxd66n61U_S35SiACdAf42Grnyv3M_sf2A-8plsg</recordid><startdate>20231001</startdate><enddate>20231001</enddate><creator>Montastruc, François</creator><creator>Storck, Wilhelm</creator><creator>de Canecaude, Claire</creator><creator>Victor, Léa</creator><creator>Li, Julien</creator><creator>Cesbron, Candice</creator><creator>Zelmat, Yoann</creator><creator>Barus, Romain</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7RV</scope><scope>7TK</scope><scope>7U9</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>H94</scope><scope>K9.</scope><scope>KB0</scope><scope>M0S</scope><scope>M1P</scope><scope>NAPCQ</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>7X8</scope></search><sort><creationdate>20231001</creationdate><title>Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice</title><author>Montastruc, François ; Storck, Wilhelm ; de Canecaude, Claire ; Victor, Léa ; Li, Julien ; Cesbron, Candice ; Zelmat, Yoann ; Barus, Romain</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c375t-7af206172fd7286fa3cdc653c178141d9b59e2fd4079fc52f8019437593e5e773</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>Biomedical and Life Sciences</topic><topic>Biomedicine</topic><topic>Causality</topic><topic>Chatbots</topic><topic>Clinical medicine</topic><topic>Drug interactions</topic><topic>Information services</topic><topic>Likert scale</topic><topic>Medical personnel</topic><topic>Patients</topic><topic>Pharmacists</topic><topic>Pharmacology</topic><topic>Pharmacology/Toxicology</topic><topic>Pharmacovigilance</topic><topic>Social networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Montastruc, François</creatorcontrib><creatorcontrib>Storck, Wilhelm</creatorcontrib><creatorcontrib>de Canecaude, Claire</creatorcontrib><creatorcontrib>Victor, Léa</creatorcontrib><creatorcontrib>Li, Julien</creatorcontrib><creatorcontrib>Cesbron, Candice</creatorcontrib><creatorcontrib>Zelmat, Yoann</creatorcontrib><creatorcontrib>Barus, Romain</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Nursing & Allied Health Database</collection><collection>Neurosciences Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>PML(ProQuest Medical Library)</collection><collection>Nursing & Allied Health Premium</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>MEDLINE - Academic</collection><jtitle>European journal of clinical pharmacology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Montastruc, François</au><au>Storck, Wilhelm</au><au>de Canecaude, Claire</au><au>Victor, Léa</au><au>Li, Julien</au><au>Cesbron, Candice</au><au>Zelmat, Yoann</au><au>Barus, Romain</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice</atitle><jtitle>European journal of clinical pharmacology</jtitle><stitle>Eur J Clin Pharmacol</stitle><addtitle>Eur J Clin Pharmacol</addtitle><date>2023-10-01</date><risdate>2023</risdate><volume>79</volume><issue>10</issue><spage>1375</spage><epage>1384</epage><pages>1375-1384</pages><issn>0031-6970</issn><issn>1432-1041</issn><eissn>1432-1041</eissn><abstract>Purpose
Recently, there has been a growing interest in using ChatGPT for various applications in Medicine. We evaluated the interest of OpenAI chatbot (GPT 4.0) for drug information activities at Toulouse Pharmacovigilance Center.
Methods
Based on a series of 50 randomly selected questions sent to our pharmacovigilance center by healthcare professionals or patients, we compared the level of responses from the chatbot GPT 4.0 with those provided by specialists in pharmacovigilance.
Results
Chatbot answers were globally not acceptable. Responses to inquiries regarding the assessment of drug causality were not consistently precise or clinically meaningful.
Conclusion
The interest of chatbot assistance needs to be confirmed or rejected through further studies conducted in other pharmacovigilance centers.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><pmid>37566133</pmid><doi>10.1007/s00228-023-03547-8</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0031-6970 |
| ispartof | European journal of clinical pharmacology, 2023-10, Vol.79 (10), p.1375-1384 |
| issn | 0031-6970 1432-1041 1432-1041 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2850311706 |
| source | Springer Nature |
| subjects | Artificial intelligence Biomedical and Life Sciences Biomedicine Causality Chatbots Clinical medicine Drug interactions Information services Likert scale Medical personnel Patients Pharmacists Pharmacology Pharmacology/Toxicology Pharmacovigilance Social networks |
| title | Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T03%3A28%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Will%20artificial%20intelligence%20chatbots%20replace%20clinical%20pharmacologists?%20An%20exploratory%20study%20in%20clinical%20practice&rft.jtitle=European%20journal%20of%20clinical%20pharmacology&rft.au=Montastruc,%20Fran%C3%A7ois&rft.date=2023-10-01&rft.volume=79&rft.issue=10&rft.spage=1375&rft.epage=1384&rft.pages=1375-1384&rft.issn=0031-6970&rft.eissn=1432-1041&rft_id=info:doi/10.1007/s00228-023-03547-8&rft_dat=%3Cproquest_cross%3E2850311706%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c375t-7af206172fd7286fa3cdc653c178141d9b59e2fd4079fc52f8019437593e5e773%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2864697120&rft_id=info:pmid/37566133&rfr_iscdi=true |