Assessing chatbots ability to produce leaflets on cataract surgery: Bing AI, chatGPT 3.5, chatGPT 4o, ChatSonic, Google Bard, Perplexity, and Pi

To evaluate leaflets on cataract surgery produced by 7 common free chatbots. UK-based ophthalmologists carrying out online research. Data were collected from the responses of 7 freely available online chatbots. Analysis of answers given by 7 chatbots (Bing AI, chatGPT 3.5, chatGPT 4o, ChatSonic, Goo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of cataract and refractive surgery Ročník 51; číslo 5; s. 371
Hlavní autoři: Thompson, Polly, Thornton, Richard, Ramsden, Conor M
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 01.05.2025
Témata:
ISSN:1873-4502, 1873-4502
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract To evaluate leaflets on cataract surgery produced by 7 common free chatbots. UK-based ophthalmologists carrying out online research. Data were collected from the responses of 7 freely available online chatbots. Analysis of answers given by 7 chatbots (Bing AI, chatGPT 3.5, chatGPT 4o, ChatSonic, Google Bard, Perplexity, and Pi) was prompted to "make a patient information leaflet on cataract surgery." Answers were evaluated using the DISCERN instrument, Patient Education Materials Assessment Tool (PEMAT), presence of misinformation, the Flesch-Kincaid Grade level readability score, and material reliability. The highest overall scored response was from ChatSonic, followed by Bing AI and then Perplexity. The lowest scoring was ChatGPT 3.5. ChatSonic achieved the highest DISCERN and PEMAT scores, and had the highest Flesch-Kincaid Grade level. The lowest DISCERN and PEMAT scores were for Pi. Only ChatGPT 3.5 included some misinformation in its response. Bing AI, ChatSonic, and Perplexity included reliable references; the other chatbots provided no references. This study demonstrates a range of answers given by chatbots creating a cataract surgery leaflet, suggesting variation in their development and reliability. ChatGPT 3.5 scored the most poorly. However, ChatSonic indicated promise in how technology may be used to assist information giving in ophthalmology.
AbstractList To evaluate leaflets on cataract surgery produced by 7 common free chatbots. UK-based ophthalmologists carrying out online research. Data were collected from the responses of 7 freely available online chatbots. Analysis of answers given by 7 chatbots (Bing AI, chatGPT 3.5, chatGPT 4o, ChatSonic, Google Bard, Perplexity, and Pi) was prompted to "make a patient information leaflet on cataract surgery." Answers were evaluated using the DISCERN instrument, Patient Education Materials Assessment Tool (PEMAT), presence of misinformation, the Flesch-Kincaid Grade level readability score, and material reliability. The highest overall scored response was from ChatSonic, followed by Bing AI and then Perplexity. The lowest scoring was ChatGPT 3.5. ChatSonic achieved the highest DISCERN and PEMAT scores, and had the highest Flesch-Kincaid Grade level. The lowest DISCERN and PEMAT scores were for Pi. Only ChatGPT 3.5 included some misinformation in its response. Bing AI, ChatSonic, and Perplexity included reliable references; the other chatbots provided no references. This study demonstrates a range of answers given by chatbots creating a cataract surgery leaflet, suggesting variation in their development and reliability. ChatGPT 3.5 scored the most poorly. However, ChatSonic indicated promise in how technology may be used to assist information giving in ophthalmology.
This study aimed to evaluate leaflets on cataract surgery produced by seven common free chatbots.PURPOSEThis study aimed to evaluate leaflets on cataract surgery produced by seven common free chatbots.Usage of conversational artificial intelligence services (chatbots) is becoming more prevalent in all aspects of life, including healthcare. Cataract surgery is the most commonly performed operation in the world, with numbers set to increase. Possible applications for chatbots include information giving and education, allowing clinicians to allocate their time more efficiently.SETTINGUsage of conversational artificial intelligence services (chatbots) is becoming more prevalent in all aspects of life, including healthcare. Cataract surgery is the most commonly performed operation in the world, with numbers set to increase. Possible applications for chatbots include information giving and education, allowing clinicians to allocate their time more efficiently.Analysis of answers given by seven chatbots (Bing AI, chatGPT 3.5, chatGPT 4o, ChatSonic, Google Bard, Perplexity and Pi) were prompted to "make a patient information leaflet on cataract surgery".DESIGNAnalysis of answers given by seven chatbots (Bing AI, chatGPT 3.5, chatGPT 4o, ChatSonic, Google Bard, Perplexity and Pi) were prompted to "make a patient information leaflet on cataract surgery".Answers were evaluated using the DISCERN instrument, Patient Education Materials Assessment Tool (PEMAT), presence of misinformation, the Flesch-Kincaid Grade Level readability score and material reliability.METHODSAnswers were evaluated using the DISCERN instrument, Patient Education Materials Assessment Tool (PEMAT), presence of misinformation, the Flesch-Kincaid Grade Level readability score and material reliability.The highest overall scored response was from ChatSonic, followed by Bing AI and then Perplexity. The lowest scoring was ChatGPT 3.5.ChatSonic achieved the highest DISCERN and PEMAT scores, and had the highest Flesch-Kincaid Grade level. The lowest DISCERN and PEMAT scores were for Pi. Only ChatGPT 3.5 included some misinformation in its response. Bing AI, ChatSonic and Perplexity included reliable references; the other chatbots provided no references.RESULTSThe highest overall scored response was from ChatSonic, followed by Bing AI and then Perplexity. The lowest scoring was ChatGPT 3.5.ChatSonic achieved the highest DISCERN and PEMAT scores, and had the highest Flesch-Kincaid Grade level. The lowest DISCERN and PEMAT scores were for Pi. Only ChatGPT 3.5 included some misinformation in its response. Bing AI, ChatSonic and Perplexity included reliable references; the other chatbots provided no references.This study demonstrates a range of answers given by chatbots creating a cataract surgery leaflet, suggesting variation in their development and reliability. ChatGPT 3.5 scored the most poorly. However, ChatSonic indicated promise in how technology may be used to assist information giving in ophthalmology.CONCLUSIONSThis study demonstrates a range of answers given by chatbots creating a cataract surgery leaflet, suggesting variation in their development and reliability. ChatGPT 3.5 scored the most poorly. However, ChatSonic indicated promise in how technology may be used to assist information giving in ophthalmology.
Author Thompson, Polly
Thornton, Richard
Ramsden, Conor M
Author_xml – sequence: 1
  givenname: Polly
  orcidid: 0009-0003-0542-1090
  surname: Thompson
  fullname: Thompson, Polly
  organization: From the The West of England Eye Unit, Royal Devon University Hospital NHS Foundation Trust, Exeter, United Kingdom (Thompson, Ramsden); Royal Eye Infirmary, Derriford Hospital, University Hospitals Plymouth NHS Foundation Trust, Plymouth, United Kingdom (Thornton); The University of Exeter, Exeter, United Kingdom (Ramsden)
– sequence: 2
  givenname: Richard
  surname: Thornton
  fullname: Thornton, Richard
– sequence: 3
  givenname: Conor M
  orcidid: 0000-0002-4320-2994
  surname: Ramsden
  fullname: Ramsden, Conor M
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39885649$$D View this record in MEDLINE/PubMed
BookMark eNpNUMtOwzAQtFARfcAvgI8ckmDHsRNzaysolSpRid4jx96UVGlc7ESif8EnE6AI9rKz2tkZ7YzRoLENIHRDSUSJTO920U47H5F_RUUcn6ERzVIWJpzEg394iMbe73pSEjN-gYZMZhkXiRyhj6n34H3VbLF-VW1hW49VUdVVe8StxQdnTacB16DKGvqdbbBWrXJKt9h3bgvueI9nX-fTZfAtsVhvMIv435DYAM97_GKbSgd4Ye22BjxTzgR4De5Qw3vvFmDVGLyuLtF5qWoPV6c-QZvHh838KVw9L5bz6SrUTPA47FOgikFaMklIGSteatDElKXK0pRKpY1ICyHAkKRISUELqYXWRgueCiN5PEG3P7L9h28d-DbfV15DXasGbOdzRgWVlAspeur1idoVezD5wVV75Y75b4jxJ5fydzc
CitedBy_id crossref_primary_10_1016_j_acra_2025_08_056
crossref_primary_10_1177_11206721251367562
crossref_primary_10_1097_j_jcrs_0000000000001683
ContentType Journal Article
Copyright Copyright © 2025 Published by Wolters Kluwer on behalf of ASCRS and ESCRS.
Copyright_xml – notice: Copyright © 2025 Published by Wolters Kluwer on behalf of ASCRS and ESCRS.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1097/j.jcrs.0000000000001622
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
EISSN 1873-4502
ExternalDocumentID 39885649
Genre Journal Article
GroupedDBID ---
--K
.1-
.FO
0R~
1B1
1P~
1~5
4.4
457
4G.
5GY
7-5
AAAAV
AAEDT
AAGIX
AAHPQ
AAIQE
AALRI
AAQKA
AASCR
ABASU
ABDIG
ABIID
ABJNI
ABLJU
ABMAC
ABPXF
ABVCZ
ABZZY
ACGFO
ACGFS
ACILI
ACLDA
ACXJB
ACZKN
ADBBV
ADGGA
ADHPY
AENEX
AEVXI
AFBFQ
AFCTW
AFDTB
AFRHN
AFTJW
AHOMT
AHQNM
AINUH
AJCLO
AJIOK
AJNWD
AJUYK
AJZMW
AKCTQ
AKRWK
AKULP
ALKUP
ALMA_UNASSIGNED_HOLDINGS
ALMTX
AMJPA
AMKUR
AMNEI
AOQMC
BELOY
C45
C5W
CGR
CS3
CUY
CVF
DIWNM
DU5
EBS
ECM
EEVPB
EIF
ERAAH
F5P
FCALG
FDB
GBLVA
GNXGY
GQDEL
HLJTE
IHE
IKREB
IKYAY
J1W
KOM
L7B
MO0
NPM
O9-
OF-
OPF
OQ~
OVD
P2P
RLZ
RPZ
SEL
SES
SJN
SSZ
TEORI
TSPGW
UV1
XH2
Z5R
7X8
ACBKD
ADKSD
ADSXY
ID FETCH-LOGICAL-c3652-1091a3e7f3900f2a5fcec0dffa87719acd67b66ed04b70b1b9c6ccdc6576d952
IEDL.DBID 7X8
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001569141600013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1873-4502
IngestDate Sun Nov 09 14:06:09 EST 2025
Thu Jun 26 01:51:50 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
License Copyright © 2025 Published by Wolters Kluwer on behalf of ASCRS and ESCRS.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3652-1091a3e7f3900f2a5fcec0dffa87719acd67b66ed04b70b1b9c6ccdc6576d952
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0009-0003-0542-1090
0000-0002-4320-2994
PMID 39885649
PQID 3161915696
PQPubID 23479
ParticipantIDs proquest_miscellaneous_3161915696
pubmed_primary_39885649
PublicationCentury 2000
PublicationDate 2025-May
PublicationDateYYYYMMDD 2025-05-01
PublicationDate_xml – month: 05
  year: 2025
  text: 2025-May
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of cataract and refractive surgery
PublicationTitleAlternate J Cataract Refract Surg
PublicationYear 2025
SSID ssj0004235
Score 2.4743927
Snippet To evaluate leaflets on cataract surgery produced by 7 common free chatbots. UK-based ophthalmologists carrying out online research. Data were collected from...
This study aimed to evaluate leaflets on cataract surgery produced by seven common free chatbots.PURPOSEThis study aimed to evaluate leaflets on cataract...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 371
SubjectTerms Cataract Extraction
Comprehension
Generative Artificial Intelligence
Humans
Internet
Patient Education as Topic - methods
Title Assessing chatbots ability to produce leaflets on cataract surgery: Bing AI, chatGPT 3.5, chatGPT 4o, ChatSonic, Google Bard, Perplexity, and Pi
URI https://www.ncbi.nlm.nih.gov/pubmed/39885649
https://www.proquest.com/docview/3161915696
Volume 51
WOSCitedRecordID wos001569141600013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS-QwFA66I-LL6q7X1ZUI-zjRtmmTZl9EZdUFHQoOMm9DruowNON0dmF_hX95T9oO44sg2IfQC2lKcppzknPO9yH0g2sw2UCxEeVSRVJDFRE8yQkz0gkew906kfb-hvd6-WAginbDrWrDKudzYj1RG6_DHvkJBdNEwGJDsNPJMwmsUcG72lJoLKMOBVMmSDUfvEILT2qCzTjnlECbyTy-S_CT0fFIT6sGvbA9YhYYdN-yM2t9c7n-0S_dQJ9bSxOfNaLxBS3Z8itavW196ZvopfH3gurC-lHOlJ9VuAHt_odnHk9qKFiLxzbw-8IzX-Kw1xOyqnDVJFP_xOeh-tnvbv2Kq6KP6XG2uEh9F1_A-V3A3-3iK-8fxhafg1B2cWGnkwDGCa3J0uDiaQv1L3_1L65JS89ANGVZQgKkqKSWOyqiyCUyc9rqyDgnc85jIbVhXDFmTZQqHqlYCc20NprBEseILNlGn0pf2l2EcymzRFHupBRpZmC8MhMwTqkz1EK5h47mPT0E6Q8uDVla_6caLvp6D-00wzWcNDAdQyryPGOp-PaO2vtoLQnEvnUk4wHqOPj37Xe0ov_OnqrpYS1WUPaK2__3VtYR
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Assessing+chatbots+ability+to+produce+leaflets+on+cataract+surgery%3A+Bing+AI%2C+chatGPT+3.5%2C+chatGPT+4o%2C+ChatSonic%2C+Google+Bard%2C+Perplexity+and+Pi&rft.jtitle=Journal+of+cataract+and+refractive+surgery&rft.au=Thompson%2C+Dr+Polly&rft.au=Thornton%2C+Dr+Richard&rft.au=Ramsden%2C+Mr+Conor&rft.date=2025-05-01&rft.issn=1873-4502&rft.eissn=1873-4502&rft_id=info:doi/10.1097%2Fj.jcrs.0000000000001622&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1873-4502&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1873-4502&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1873-4502&client=summon