Glaucoma Detection and Feature Identification via GPT-4V Fundus Image Analysis

The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations. Evaluation of multimodal large language models for reviewing fundus images in glaucoma. A total of 300 fundus images from 3 public datasets (ACRIMA...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Ophthalmology science (Online) Ročník 5; číslo 2; s. 100667
Hlavní autoři: Jalili, Jalil, Jiravarnsirikul, Anuwat, Bowd, Christopher, Chuter, Benton, Belghith, Akram, Goldbaum, Michael H., Baxter, Sally L., Weinreb, Robert N., Zangwill, Linda M., Christopher, Mark
Médium: Journal Article
Jazyk:angličtina
Vydáno: Netherlands Elsevier Inc 01.03.2025
Elsevier
Témata:
ISSN:2666-9145, 2666-9145
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations. Evaluation of multimodal large language models for reviewing fundus images in glaucoma. A total of 300 fundus images from 3 public datasets (ACRIMA, ORIGA, and RIM-One v3) that included 139 glaucomatous and 161 nonglaucomatous cases were analyzed. Preprocessing ensured each image was centered on the optic disc. GPT-4's vision-preview model (GPT-4V) assessed each image for various glaucoma-related criteria: image quality, image gradability, cup-to-disc ratio, peripapillary atrophy, disc hemorrhages, rim thinning (by quadrant and clock hour), glaucoma status, and estimated probability of glaucoma. Each image was analyzed twice by GPT-4V to evaluate consistency in its predictions. Two expert graders independently evaluated the same images using identical criteria. Comparisons between GPT-4V's assessments, expert evaluations, and dataset labels were made to determine accuracy, sensitivity, specificity, and Cohen kappa. The main parameters measured were the accuracy, sensitivity, specificity, and Cohen kappa of GPT-4V in detecting glaucoma compared with expert evaluations. GPT-4V successfully provided glaucoma assessments for all 300 fundus images across the datasets, although approximately 35% required multiple prompt submissions. GPT-4V's overall accuracy in glaucoma detection was slightly lower (0.68, 0.70, and 0.81, respectively) than that of expert graders (0.78, 0.80, and 0.88, for expert grader 1 and 0.72, 0.78, and 0.87, for expert grader 2, respectively), across the ACRIMA, ORIGA, and RIM-ONE datasets. In Glaucoma detection, GPT-4V showed variable agreement by dataset and expert graders, with Cohen kappa values ranging from 0.08 to 0.72. In terms of feature detection, GPT-4V demonstrated high consistency (repeatability) in image gradability, with an agreement accuracy of ≥89% and substantial agreement in rim thinning and cup-to-disc ratio assessments, although kappas were generally lower than expert-to-expert agreement. GPT-4V shows promise as a tool in glaucoma screening and detection through fundus image analysis, demonstrating generally high agreement with expert evaluations of key diagnostic features, although agreement did vary substantially across datasets. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
AbstractList Purpose: The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations. Design: Evaluation of multimodal large language models for reviewing fundus images in glaucoma. Subjects: A total of 300 fundus images from 3 public datasets (ACRIMA, ORIGA, and RIM-One v3) that included 139 glaucomatous and 161 nonglaucomatous cases were analyzed. Methods: Preprocessing ensured each image was centered on the optic disc. GPT-4's vision-preview model (GPT-4V) assessed each image for various glaucoma-related criteria: image quality, image gradability, cup-to-disc ratio, peripapillary atrophy, disc hemorrhages, rim thinning (by quadrant and clock hour), glaucoma status, and estimated probability of glaucoma. Each image was analyzed twice by GPT-4V to evaluate consistency in its predictions. Two expert graders independently evaluated the same images using identical criteria. Comparisons between GPT-4V's assessments, expert evaluations, and dataset labels were made to determine accuracy, sensitivity, specificity, and Cohen kappa. Main Outcome Measures: The main parameters measured were the accuracy, sensitivity, specificity, and Cohen kappa of GPT-4V in detecting glaucoma compared with expert evaluations. Results: GPT-4V successfully provided glaucoma assessments for all 300 fundus images across the datasets, although approximately 35% required multiple prompt submissions. GPT-4V's overall accuracy in glaucoma detection was slightly lower (0.68, 0.70, and 0.81, respectively) than that of expert graders (0.78, 0.80, and 0.88, for expert grader 1 and 0.72, 0.78, and 0.87, for expert grader 2, respectively), across the ACRIMA, ORIGA, and RIM-ONE datasets. In Glaucoma detection, GPT-4V showed variable agreement by dataset and expert graders, with Cohen kappa values ranging from 0.08 to 0.72. In terms of feature detection, GPT-4V demonstrated high consistency (repeatability) in image gradability, with an agreement accuracy of ≥89% and substantial agreement in rim thinning and cup-to-disc ratio assessments, although kappas were generally lower than expert-to-expert agreement. Conclusions: GPT-4V shows promise as a tool in glaucoma screening and detection through fundus image analysis, demonstrating generally high agreement with expert evaluations of key diagnostic features, although agreement did vary substantially across datasets. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations.PurposeThe aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations.Evaluation of multimodal large language models for reviewing fundus images in glaucoma.DesignEvaluation of multimodal large language models for reviewing fundus images in glaucoma.A total of 300 fundus images from 3 public datasets (ACRIMA, ORIGA, and RIM-One v3) that included 139 glaucomatous and 161 nonglaucomatous cases were analyzed.SubjectsA total of 300 fundus images from 3 public datasets (ACRIMA, ORIGA, and RIM-One v3) that included 139 glaucomatous and 161 nonglaucomatous cases were analyzed.Preprocessing ensured each image was centered on the optic disc. GPT-4's vision-preview model (GPT-4V) assessed each image for various glaucoma-related criteria: image quality, image gradability, cup-to-disc ratio, peripapillary atrophy, disc hemorrhages, rim thinning (by quadrant and clock hour), glaucoma status, and estimated probability of glaucoma. Each image was analyzed twice by GPT-4V to evaluate consistency in its predictions. Two expert graders independently evaluated the same images using identical criteria. Comparisons between GPT-4V's assessments, expert evaluations, and dataset labels were made to determine accuracy, sensitivity, specificity, and Cohen kappa.MethodsPreprocessing ensured each image was centered on the optic disc. GPT-4's vision-preview model (GPT-4V) assessed each image for various glaucoma-related criteria: image quality, image gradability, cup-to-disc ratio, peripapillary atrophy, disc hemorrhages, rim thinning (by quadrant and clock hour), glaucoma status, and estimated probability of glaucoma. Each image was analyzed twice by GPT-4V to evaluate consistency in its predictions. Two expert graders independently evaluated the same images using identical criteria. Comparisons between GPT-4V's assessments, expert evaluations, and dataset labels were made to determine accuracy, sensitivity, specificity, and Cohen kappa.The main parameters measured were the accuracy, sensitivity, specificity, and Cohen kappa of GPT-4V in detecting glaucoma compared with expert evaluations.Main Outcome MeasuresThe main parameters measured were the accuracy, sensitivity, specificity, and Cohen kappa of GPT-4V in detecting glaucoma compared with expert evaluations.GPT-4V successfully provided glaucoma assessments for all 300 fundus images across the datasets, although approximately 35% required multiple prompt submissions. GPT-4V's overall accuracy in glaucoma detection was slightly lower (0.68, 0.70, and 0.81, respectively) than that of expert graders (0.78, 0.80, and 0.88, for expert grader 1 and 0.72, 0.78, and 0.87, for expert grader 2, respectively), across the ACRIMA, ORIGA, and RIM-ONE datasets. In Glaucoma detection, GPT-4V showed variable agreement by dataset and expert graders, with Cohen kappa values ranging from 0.08 to 0.72. In terms of feature detection, GPT-4V demonstrated high consistency (repeatability) in image gradability, with an agreement accuracy of ≥89% and substantial agreement in rim thinning and cup-to-disc ratio assessments, although kappas were generally lower than expert-to-expert agreement.ResultsGPT-4V successfully provided glaucoma assessments for all 300 fundus images across the datasets, although approximately 35% required multiple prompt submissions. GPT-4V's overall accuracy in glaucoma detection was slightly lower (0.68, 0.70, and 0.81, respectively) than that of expert graders (0.78, 0.80, and 0.88, for expert grader 1 and 0.72, 0.78, and 0.87, for expert grader 2, respectively), across the ACRIMA, ORIGA, and RIM-ONE datasets. In Glaucoma detection, GPT-4V showed variable agreement by dataset and expert graders, with Cohen kappa values ranging from 0.08 to 0.72. In terms of feature detection, GPT-4V demonstrated high consistency (repeatability) in image gradability, with an agreement accuracy of ≥89% and substantial agreement in rim thinning and cup-to-disc ratio assessments, although kappas were generally lower than expert-to-expert agreement.GPT-4V shows promise as a tool in glaucoma screening and detection through fundus image analysis, demonstrating generally high agreement with expert evaluations of key diagnostic features, although agreement did vary substantially across datasets.ConclusionsGPT-4V shows promise as a tool in glaucoma screening and detection through fundus image analysis, demonstrating generally high agreement with expert evaluations of key diagnostic features, although agreement did vary substantially across datasets.Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.Financial DisclosuresProprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations. Evaluation of multimodal large language models for reviewing fundus images in glaucoma. A total of 300 fundus images from 3 public datasets (ACRIMA, ORIGA, and RIM-One v3) that included 139 glaucomatous and 161 nonglaucomatous cases were analyzed. Preprocessing ensured each image was centered on the optic disc. GPT-4's vision-preview model (GPT-4V) assessed each image for various glaucoma-related criteria: image quality, image gradability, cup-to-disc ratio, peripapillary atrophy, disc hemorrhages, rim thinning (by quadrant and clock hour), glaucoma status, and estimated probability of glaucoma. Each image was analyzed twice by GPT-4V to evaluate consistency in its predictions. Two expert graders independently evaluated the same images using identical criteria. Comparisons between GPT-4V's assessments, expert evaluations, and dataset labels were made to determine accuracy, sensitivity, specificity, and Cohen kappa. The main parameters measured were the accuracy, sensitivity, specificity, and Cohen kappa of GPT-4V in detecting glaucoma compared with expert evaluations. GPT-4V successfully provided glaucoma assessments for all 300 fundus images across the datasets, although approximately 35% required multiple prompt submissions. GPT-4V's overall accuracy in glaucoma detection was slightly lower (0.68, 0.70, and 0.81, respectively) than that of expert graders (0.78, 0.80, and 0.88, for expert grader 1 and 0.72, 0.78, and 0.87, for expert grader 2, respectively), across the ACRIMA, ORIGA, and RIM-ONE datasets. In Glaucoma detection, GPT-4V showed variable agreement by dataset and expert graders, with Cohen kappa values ranging from 0.08 to 0.72. In terms of feature detection, GPT-4V demonstrated high consistency (repeatability) in image gradability, with an agreement accuracy of ≥89% and substantial agreement in rim thinning and cup-to-disc ratio assessments, although kappas were generally lower than expert-to-expert agreement. GPT-4V shows promise as a tool in glaucoma screening and detection through fundus image analysis, demonstrating generally high agreement with expert evaluations of key diagnostic features, although agreement did vary substantially across datasets. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
PurposeThe aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations. DesignEvaluation of multimodal large language models for reviewing fundus images in glaucoma. SubjectsA total of 300 fundus images from 3 public datasets (ACRIMA, ORIGA, and RIM-One v3) that included 139 glaucomatous and 161 nonglaucomatous cases were analyzed. MethodsPreprocessing ensured each image was centered on the optic disc. GPT-4's vision-preview model (GPT-4V) assessed each image for various glaucoma-related criteria: image quality, image gradability, cup-to-disc ratio, peripapillary atrophy, disc hemorrhages, rim thinning (by quadrant and clock hour), glaucoma status, and estimated probability of glaucoma. Each image was analyzed twice by GPT-4V to evaluate consistency in its predictions. Two expert graders independently evaluated the same images using identical criteria. Comparisons between GPT-4V's assessments, expert evaluations, and dataset labels were made to determine accuracy, sensitivity, specificity, and Cohen kappa. Main Outcome MeasuresThe main parameters measured were the accuracy, sensitivity, specificity, and Cohen kappa of GPT-4V in detecting glaucoma compared with expert evaluations. ResultsGPT-4V successfully provided glaucoma assessments for all 300 fundus images across the datasets, although approximately 35% required multiple prompt submissions. GPT-4V's overall accuracy in glaucoma detection was slightly lower (0.68, 0.70, and 0.81, respectively) than that of expert graders (0.78, 0.80, and 0.88, for expert grader 1 and 0.72, 0.78, and 0.87, for expert grader 2, respectively), across the ACRIMA, ORIGA, and RIM-ONE datasets. In Glaucoma detection, GPT-4V showed variable agreement by dataset and expert graders, with Cohen kappa values ranging from 0.08 to 0.72. In terms of feature detection, GPT-4V demonstrated high consistency (repeatability) in image gradability, with an agreement accuracy of ≥89% and substantial agreement in rim thinning and cup-to-disc ratio assessments, although kappas were generally lower than expert-to-expert agreement. ConclusionsGPT-4V shows promise as a tool in glaucoma screening and detection through fundus image analysis, demonstrating generally high agreement with expert evaluations of key diagnostic features, although agreement did vary substantially across datasets. Financial Disclosure(s)Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
ArticleNumber 100667
Author Jalili, Jalil
Baxter, Sally L.
Bowd, Christopher
Weinreb, Robert N.
Chuter, Benton
Jiravarnsirikul, Anuwat
Belghith, Akram
Christopher, Mark
Goldbaum, Michael H.
Zangwill, Linda M.
Author_xml – sequence: 1
  givenname: Jalil
  surname: Jalili
  fullname: Jalili, Jalil
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 2
  givenname: Anuwat
  surname: Jiravarnsirikul
  fullname: Jiravarnsirikul, Anuwat
  organization: Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 3
  givenname: Christopher
  surname: Bowd
  fullname: Bowd, Christopher
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 4
  givenname: Benton
  surname: Chuter
  fullname: Chuter, Benton
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 5
  givenname: Akram
  surname: Belghith
  fullname: Belghith, Akram
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 6
  givenname: Michael H.
  surname: Goldbaum
  fullname: Goldbaum, Michael H.
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 7
  givenname: Sally L.
  surname: Baxter
  fullname: Baxter, Sally L.
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 8
  givenname: Robert N.
  surname: Weinreb
  fullname: Weinreb, Robert N.
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 9
  givenname: Linda M.
  surname: Zangwill
  fullname: Zangwill, Linda M.
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
– sequence: 10
  givenname: Mark
  orcidid: 0000-0001-6165-6175
  surname: Christopher
  fullname: Christopher, Mark
  email: mark.allen.christopher@gmail.com
  organization: Division of Ophthalmology Informatics and Data Science, Viterbi Family Department of Ophthalmology, Shiley Eye Institute, University of California, San Diego, La Jolla, California
BackLink https://www.ncbi.nlm.nih.gov/pubmed/39877464$$D View this record in MEDLINE/PubMed
BookMark eNqFkl9v0zAUxSM0xMbYF-AB5ZGXFP-LkyAEmgYtlSZAYvBq3dg3xSW1i51U9NvjthvaJjGebPne87vyPedpduS8wyx7TsmEEipfLSe__TpOGGEiPRApq0fZCZNSFg0V5dGt-3F2FuOSEMJKypmgT7Jj3tRVJaQ4yT7Nehi1X0H-HgfUg_UuB2fyKcIwBsznBt1gO6thX9pYyGdfrgrxPZ-Ozowxn69ggfm5g34bbXyWPe6gj3h2fZ5m36Yfri4-FpefZ_OL88tCS1YPRUfa1tRCYs1aqQUvgVScMwbY0q7WDUWDIAUD2dUVcFq2hkEDHcGukrJh_DSbH7jGw1Ktg11B2CoPVu0ffFgoCIPVPSquadcQjqVuQHS6asFoQUjNTVsbUpnEendgrcd2hUanDwfo70DvVpz9oRZ-oyitKk5knQgvrwnB_xoxDmplo8a-B4d-jIpTSRreNLRMrS9uD_s75caR1FAfGnTwMQbslLbDfvlptu0VJWrnv1qqnf9q5786-J-k7J70hv6g6M1BhMmujcWgorboNBobUh7SPu3D8rf35Lq3LsWl_4lbjEs_hhSNqKiKTBH1dZfKXShZsoARzhPg9b8B_5v-B7eT8b4
CitedBy_id crossref_primary_10_1016_j_xops_2025_100911
crossref_primary_10_3390_jcm14186519
Cites_doi 10.1038/s41598-021-99605-1
10.1016/j.xops.2023.100324
10.3389/fopht.2024.1387190
10.1186/s12938-019-0649-y
10.1167/tvst.9.2.27
10.1046/j.1475-1313.2000.00528.x
10.1007/s00417-023-06363-z
10.1016/j.ophtha.2014.05.013
10.1016/j.ophtha.2020.07.045
10.1016/j.xops.2022.100233
10.1038/s41598-018-35044-9
10.1038/s41746-023-00857-0
10.1016/j.ajo.2023.05.024
10.1001/jama.2014.3192
10.1007/s40123-023-00805-x
10.1109/ACCESS.2024.3359698
10.1001/jama.2016.17216
10.5566/ias.2346
10.1007/s40123-023-00789-8
10.1038/s41433-023-02564-2
10.1001/jamaophthalmol.2014.96
10.1001/jamaophthalmol.2023.6917
ContentType Journal Article
Copyright 2024 American Academy of Ophthalmology
American Academy of Ophthalmology
2024 by the American Academy of Ophthalmologyé.
2024 by the American Academy of Ophthalmologyé. 2024 American Academy of Ophthalmology
Copyright_xml – notice: 2024 American Academy of Ophthalmology
– notice: American Academy of Ophthalmology
– notice: 2024 by the American Academy of Ophthalmologyé.
– notice: 2024 by the American Academy of Ophthalmologyé. 2024 American Academy of Ophthalmology
DBID 6I.
AAFTH
AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.1016/j.xops.2024.100667
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
PubMed



Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals (ODIN)
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2666-9145
EndPage 100667
ExternalDocumentID oai_doaj_org_article_3c1f903e5c9a4fc7badc40083db8d07d
PMC11773068
39877464
10_1016_j_xops_2024_100667
S2666914524002033
1_s2_0_S2666914524002033
Genre Journal Article
GrantInformation_xml – fundername: National Institutes of Health
  grantid: OT2OD032644
  funderid: https://doi.org/10.13039/100000002
– fundername: National Eye Institute
  grantid: R01EY11008; R01EY19869; R01Y026574; R01EY034146; R01EY029058; R01EY027510; P30EY022589; R01EY023704; K12EY024225; R01MD014850; R00EY030942; R01EY026574; DP5OD029610
  funderid: https://doi.org/10.13039/100000053
– fundername: NEI NIH HHS
  grantid: R01 EY019869
– fundername: NEI NIH HHS
  grantid: R01 EY029058
– fundername: NEI NIH HHS
  grantid: R01 EY034146
– fundername: NEI NIH HHS
  grantid: R01 EY023704
– fundername: NEI NIH HHS
  grantid: R00 EY030942
– fundername: NEI NIH HHS
  grantid: P30 EY022589
– fundername: NIH HHS
  grantid: OT2 OD032644
– fundername: NEI NIH HHS
  grantid: R01 EY027510
– fundername: NIMHD NIH HHS
  grantid: R01 MD014850
– fundername: NEI NIH HHS
  grantid: K12 EY024225
GroupedDBID .1-
.FO
0R~
AAEDW
AALRI
AAXUO
AAYWO
ACVFH
ADCNI
ADVLN
AEUPX
AFJKZ
AFPUW
AFRHN
AIGII
AITUG
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
APXCP
EBS
FDB
GROUPED_DOAJ
M~E
OK1
ROL
RPM
Z5R
6I.
AAFTH
AAYXX
CITATION
NPM
7X8
5PM
ID FETCH-LOGICAL-c628t-f0bbd846e82b6c435a073322aeb1f8c91edea642a6f87a315bd2a9af0ef766923
IEDL.DBID DOA
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001398692700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2666-9145
IngestDate Fri Oct 03 12:22:06 EDT 2025
Thu Aug 21 18:40:20 EDT 2025
Fri Jul 11 09:11:57 EDT 2025
Mon Jul 21 06:08:02 EDT 2025
Wed Nov 12 01:47:09 EST 2025
Tue Nov 18 22:24:46 EST 2025
Sat Mar 22 15:54:40 EDT 2025
Thu Apr 03 20:56:38 EDT 2025
Tue Aug 26 16:33:12 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords CDR
Fundus image analysis
GPT-4V
MM-LLM
AI
UCSD
API
GPT
Large multimodal models
LLM
Artificial intelligence
Glaucoma detection
large language model
application programmer interface
generative pretrained transformer
cup-to-disc ratio
multimodal large language model
University of California, San Diego
Language English
License This is an open access article under the CC BY license.
2024 by the American Academy of Ophthalmologyé.
This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c628t-f0bbd846e82b6c435a073322aeb1f8c91edea642a6f87a315bd2a9af0ef766923
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0001-6165-6175
OpenAccessLink https://doaj.org/article/3c1f903e5c9a4fc7badc40083db8d07d
PMID 39877464
PQID 3160939915
PQPubID 23479
PageCount 1
ParticipantIDs doaj_primary_oai_doaj_org_article_3c1f903e5c9a4fc7badc40083db8d07d
pubmedcentral_primary_oai_pubmedcentral_nih_gov_11773068
proquest_miscellaneous_3160939915
pubmed_primary_39877464
crossref_citationtrail_10_1016_j_xops_2024_100667
crossref_primary_10_1016_j_xops_2024_100667
elsevier_sciencedirect_doi_10_1016_j_xops_2024_100667
elsevier_clinicalkeyesjournals_1_s2_0_S2666914524002033
elsevier_clinicalkey_doi_10_1016_j_xops_2024_100667
PublicationCentury 2000
PublicationDate 2025-03-01
PublicationDateYYYYMMDD 2025-03-01
PublicationDate_xml – month: 03
  year: 2025
  text: 2025-03-01
  day: 01
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle Ophthalmology science (Online)
PublicationTitleAlternate Ophthalmol Sci
PublicationYear 2025
Publisher Elsevier Inc
Elsevier
Publisher_xml – name: Elsevier Inc
– name: Elsevier
References Medeiros, Jammal, Mariottoni (bib7) 2021; 128
Hemelings, Elen, Barbosa-Breda (bib9) 2021; 11
Tomita, Nishida, Kitaguchi (bib24) 2024
Zhang, Yu, Dong (bib14) 2024
Huang, Pasquale, Hirabayashi, Barna (bib25) 2024; 142
Gulshan, Peng, Coram (bib6) 2016; 316
bib37
Carolan, Fennelly, Smeaton (bib15) 2024
Hu, Ran, Nguyen (bib22) 2023; 12
Shyamalee, Meedeniya (bib12) 2022
Li, Wong, Zhang, Usuyama (bib34) 2024
Fan, Alipour, Bowd (bib10) 2023; 3
Antaki, Touma, Milad (bib17) 2023; 3
Hemelings, Elen, Schuster (bib8) 2023; 6
Zhou, Ong, Kennedy (bib33) 2024; 311
He, Li, Liu (bib36) 2024
Christopher, Belghith, Bowd (bib31) 2018; 8
Shemer, Cohen, Altarescu (bib19) 2024; 262
Achiam, Adler, Agarwal, Ahmad (bib16) 2023
Zhang, Yin, Liu (bib28) 2010; 2010
Weinreb, Aung, Medeiros (bib2) 2014; 311
Shyamalee, Meedeniya, Lim, Karunarathne (bib11) 2024; 12
Fumero Batista, Diaz-Aleman, Sigut (bib29) 2020; 39
Christopher, Nakahara, Bowd (bib32) 2020; 9
Diaz-Pinto, Morales, Naranjo (bib27) 2019; 18
Tham, Li, Wong (bib1) 2014; 121
Yang, Xu, Sellergren, Kohlberger (bib35) 2024
Harper, Reeves, Smith (bib3) 2000; 20
O'Neill, Gurria, Pandav (bib5) 2014; 132
Cai, Shaheenx, Jin (bib21) 2023; 254
Fumero, Alayon, Sanchez, Gonzalez-Hernandez (bib30) 2011
Lin, Younessi, Kurapati (bib20) 2023; 37
Chen, Zhao, Zhang (bib18) 2024
AlRyalat, Musleh, Kahook (bib23) 2024; 4
bib38
Shyamalee, Meedeniya (bib13) 2022
Delsoz, Raja, Madadi (bib26) 2023; 12
Weinreb, Bowd, Moghimi (bib4) 2019
Shyamalee (10.1016/j.xops.2024.100667_bib12) 2022
Antaki (10.1016/j.xops.2024.100667_bib17) 2023; 3
Hu (10.1016/j.xops.2024.100667_bib22) 2023; 12
Shemer (10.1016/j.xops.2024.100667_bib19) 2024; 262
Tomita (10.1016/j.xops.2024.100667_bib24) 2024
Diaz-Pinto (10.1016/j.xops.2024.100667_bib27) 2019; 18
AlRyalat (10.1016/j.xops.2024.100667_bib23) 2024; 4
Achiam (10.1016/j.xops.2024.100667_bib16) 2023
Chen (10.1016/j.xops.2024.100667_bib18) 2024
Delsoz (10.1016/j.xops.2024.100667_bib26) 2023; 12
Christopher (10.1016/j.xops.2024.100667_bib32) 2020; 9
Carolan (10.1016/j.xops.2024.100667_bib15) 2024
O'Neill (10.1016/j.xops.2024.100667_bib5) 2014; 132
Harper (10.1016/j.xops.2024.100667_bib3) 2000; 20
Lin (10.1016/j.xops.2024.100667_bib20) 2023; 37
Cai (10.1016/j.xops.2024.100667_bib21) 2023; 254
Fumero Batista (10.1016/j.xops.2024.100667_bib29) 2020; 39
Zhou (10.1016/j.xops.2024.100667_bib33) 2024; 311
Fumero (10.1016/j.xops.2024.100667_bib30) 2011
Yang (10.1016/j.xops.2024.100667_bib35) 2024
Tham (10.1016/j.xops.2024.100667_bib1) 2014; 121
Christopher (10.1016/j.xops.2024.100667_bib31) 2018; 8
Shyamalee (10.1016/j.xops.2024.100667_bib11) 2024; 12
Zhang (10.1016/j.xops.2024.100667_bib28) 2010; 2010
Weinreb (10.1016/j.xops.2024.100667_bib2) 2014; 311
Shyamalee (10.1016/j.xops.2024.100667_bib13) 2022
Medeiros (10.1016/j.xops.2024.100667_bib7) 2021; 128
Li (10.1016/j.xops.2024.100667_bib34) 2024
Fan (10.1016/j.xops.2024.100667_bib10) 2023; 3
Huang (10.1016/j.xops.2024.100667_bib25) 2024; 142
Hemelings (10.1016/j.xops.2024.100667_bib8) 2023; 6
Weinreb (10.1016/j.xops.2024.100667_bib4) 2019
Hemelings (10.1016/j.xops.2024.100667_bib9) 2021; 11
Zhang (10.1016/j.xops.2024.100667_bib14) 2024
He (10.1016/j.xops.2024.100667_bib36) 2024
Gulshan (10.1016/j.xops.2024.100667_bib6) 2016; 316
References_xml – volume: 3
  year: 2023
  ident: bib10
  article-title: Detecting glaucoma from fundus photographs using deep learning without convolutions: transformer for improved generalization
  publication-title: Ophthalmol Sci
– volume: 39
  start-page: 161
  year: 2020
  end-page: 167
  ident: bib29
  article-title: RIM-ONE dl: a unified retinal image database for assessing glaucoma using deep learning
  publication-title: Image Anal Stereol
– year: 2024
  ident: bib36
  article-title: Pefomed: parameter efficient fine-tuning on multimodal large language models for medical visual question answering
  publication-title: arXiv
– volume: 9
  start-page: 27
  year: 2020
  ident: bib32
  article-title: Effects of study population, labeling and training on glaucoma detection using deep learning algorithms
  publication-title: Transl Vis Sci Technol
– year: 2024
  ident: bib15
  article-title: A review of multi-modal large language and vision models
  publication-title: arXiv
– year: 2024
  ident: bib34
  article-title: Llava-med: training a large language-and-vision assistant for biomedicine in one day. Advances
– start-page: 1
  year: 2011
  end-page: 6
  ident: bib30
  article-title: RIM-ONE: an open retinal image database for optic nerve evaluation. in 2011 24th International Symposium on Computer-Based Medical Systems (CBMS)
– volume: 254
  start-page: 141
  year: 2023
  end-page: 149
  ident: bib21
  article-title: Performance of generative large language models on ophthalmology board-style questions
  publication-title: Am J Ophthalmol
– volume: 18
  start-page: 29
  year: 2019
  ident: bib27
  article-title: CNNs for automatic glaucoma assessment using fundus images: an extensive validation
  publication-title: Biomed Eng Online
– volume: 132
  start-page: 560
  year: 2014
  end-page: 566
  ident: bib5
  article-title: Glaucomatous optic neuropathy evaluation project: factors associated with underestimation of glaucoma likelihood
  publication-title: JAMA Ophthalmol
– year: 2024
  ident: bib35
  article-title: Advancing multimodal medical capabilities of Gemini
  publication-title: arXiv
– ident: bib38
  article-title: OpenAI enterprise privacy
– start-page: 200
  year: 2022
  end-page: 205
  ident: bib13
  article-title: CNN based fundus images classification for glaucoma identification. in 2022 2nd International Conference on Advanced Research in Computing (ICARC)
– volume: 142
  start-page: 371
  year: 2024
  end-page: 375
  ident: bib25
  article-title: Assessment of a large language model's responses to questions and cases about glaucoma and retina management
  publication-title: JAMA Ophthalmol
– year: 2024
  ident: bib18
  article-title: EyeGPT: ophthalmic assistant with large language models
  publication-title: arXiv
– volume: 311
  year: 2024
  ident: bib33
  article-title: Evaluating GPT-V4 (GPT-4 with vision) on detection of radiologic findings on chest radiographs
  publication-title: Radiology
– year: 2023
  ident: bib16
  article-title: Gpt-4 technical report
  publication-title: arXiv
– year: 2024
  ident: bib24
  article-title: Performance of GPT-4V(ision) in ophthalmology: use of images in clinical questions
  publication-title: medRxiv
– volume: 128
  start-page: 383
  year: 2021
  end-page: 392
  ident: bib7
  article-title: Detection of progressive glaucomatous optic nerve damage on fundus photographs with deep learning
  publication-title: Ophthalmology
– volume: 12
  start-page: 17290
  year: 2024
  end-page: 17307
  ident: bib11
  article-title: Automated tool support for glaucoma identification with explainability using fundus images
  publication-title: IEEE Access
– start-page: 6
  year: 2022
  end-page: 10
  ident: bib12
  article-title: Attention U-net for glaucoma identification using fundus image segmentation. In 2022 international conference on decision aid sciences and applications (DASA)
– volume: 11
  year: 2021
  ident: bib9
  article-title: Deep learning on fundus images detects glaucoma beyond the optic disc
  publication-title: Sci Rep
– volume: 311
  start-page: 1901
  year: 2014
  end-page: 1911
  ident: bib2
  article-title: The pathophysiology and treatment of glaucoma: a review
  publication-title: JAMA
– volume: 262
  start-page: 2345
  year: 2024
  end-page: 2352
  ident: bib19
  article-title: Diagnostic capabilities of ChatGPT in ophthalmology
  publication-title: Graefes Arch Clin Exp Ophthalmol
– ident: bib37
  article-title: OpenAI trust center
– volume: 6
  start-page: 112
  year: 2023
  ident: bib8
  article-title: A generalizable deep learning regression model for automated glaucoma screening from fundus images
  publication-title: NPJ Digital Med
– volume: 12
  start-page: 3395
  year: 2023
  end-page: 3402
  ident: bib22
  article-title: What can GPT-4 do for diagnosing rare eye diseases? A pilot study
  publication-title: Ophthalmol Ther
– year: 2019
  ident: bib4
  article-title: Ophthalmic diagnostic imaging: glaucoma in
  publication-title: High resolution imaging in microscopy and ophthalmology: new frontiers in biomedical optics
– volume: 20
  start-page: 265
  year: 2000
  end-page: 273
  ident: bib3
  article-title: Observer variability in optic disc assessment: implications for glaucoma shared care
  publication-title: Ophthalmic Physiol Opt
– volume: 2010
  start-page: 3065
  year: 2010
  end-page: 3068
  ident: bib28
  article-title: ORIGA(-light): an online retinal fundus image database for glaucoma analysis and research
  publication-title: Annu Int Conf IEEE Eng Med Biol Soc
– volume: 316
  start-page: 2402
  year: 2016
  end-page: 2410
  ident: bib6
  article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs
  publication-title: JAMA
– volume: 12
  start-page: 3121
  year: 2023
  end-page: 3132
  ident: bib26
  article-title: The use of chatgpt to assist in diagnosing glaucoma based on clinical case reports
  publication-title: Ophthalmol. Ther
– volume: 3
  year: 2023
  ident: bib17
  article-title: Evaluating the performance of chatgpt in ophthalmology: an analysis of its successes and shortcomings
  publication-title: Ophthalmol Sci
– volume: 4
  year: 2024
  ident: bib23
  article-title: Evaluating the strengths and limitations of multimodal ChatGPT-4 in detecting glaucoma using fundus images
  publication-title: Front Ophthalmol
– volume: 8
  year: 2018
  ident: bib31
  article-title: Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs
  publication-title: Sci Rep
– volume: 121
  start-page: 2081
  year: 2014
  end-page: 2090
  ident: bib1
  article-title: Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis
  publication-title: Ophthalmology
– year: 2024
  ident: bib14
  article-title: Mm-llms: recent advances in multimodal large language models
  publication-title: arXiv
– volume: 37
  start-page: 3694
  year: 2023
  end-page: 3695
  ident: bib20
  article-title: Comparison of GPT-3.5, GPT-4, and human user performance on a practice ophthalmology written examination
  publication-title: Eye
– volume: 11
  year: 2021
  ident: 10.1016/j.xops.2024.100667_bib9
  article-title: Deep learning on fundus images detects glaucoma beyond the optic disc
  publication-title: Sci Rep
  doi: 10.1038/s41598-021-99605-1
– volume: 3
  year: 2023
  ident: 10.1016/j.xops.2024.100667_bib17
  article-title: Evaluating the performance of chatgpt in ophthalmology: an analysis of its successes and shortcomings
  publication-title: Ophthalmol Sci
  doi: 10.1016/j.xops.2023.100324
– volume: 4
  year: 2024
  ident: 10.1016/j.xops.2024.100667_bib23
  article-title: Evaluating the strengths and limitations of multimodal ChatGPT-4 in detecting glaucoma using fundus images
  publication-title: Front Ophthalmol
  doi: 10.3389/fopht.2024.1387190
– volume: 18
  start-page: 29
  year: 2019
  ident: 10.1016/j.xops.2024.100667_bib27
  article-title: CNNs for automatic glaucoma assessment using fundus images: an extensive validation
  publication-title: Biomed Eng Online
  doi: 10.1186/s12938-019-0649-y
– start-page: 200
  year: 2022
  ident: 10.1016/j.xops.2024.100667_bib13
– volume: 2010
  start-page: 3065
  year: 2010
  ident: 10.1016/j.xops.2024.100667_bib28
  article-title: ORIGA(-light): an online retinal fundus image database for glaucoma analysis and research
  publication-title: Annu Int Conf IEEE Eng Med Biol Soc
– start-page: 6
  year: 2022
  ident: 10.1016/j.xops.2024.100667_bib12
– volume: 9
  start-page: 27
  year: 2020
  ident: 10.1016/j.xops.2024.100667_bib32
  article-title: Effects of study population, labeling and training on glaucoma detection using deep learning algorithms
  publication-title: Transl Vis Sci Technol
  doi: 10.1167/tvst.9.2.27
– volume: 20
  start-page: 265
  year: 2000
  ident: 10.1016/j.xops.2024.100667_bib3
  article-title: Observer variability in optic disc assessment: implications for glaucoma shared care
  publication-title: Ophthalmic Physiol Opt
  doi: 10.1046/j.1475-1313.2000.00528.x
– volume: 262
  start-page: 2345
  year: 2024
  ident: 10.1016/j.xops.2024.100667_bib19
  article-title: Diagnostic capabilities of ChatGPT in ophthalmology
  publication-title: Graefes Arch Clin Exp Ophthalmol
  doi: 10.1007/s00417-023-06363-z
– volume: 121
  start-page: 2081
  year: 2014
  ident: 10.1016/j.xops.2024.100667_bib1
  article-title: Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2014.05.013
– year: 2024
  ident: 10.1016/j.xops.2024.100667_bib24
  article-title: Performance of GPT-4V(ision) in ophthalmology: use of images in clinical questions
  publication-title: medRxiv
– year: 2019
  ident: 10.1016/j.xops.2024.100667_bib4
  article-title: Ophthalmic diagnostic imaging: glaucoma in
– volume: 128
  start-page: 383
  year: 2021
  ident: 10.1016/j.xops.2024.100667_bib7
  article-title: Detection of progressive glaucomatous optic nerve damage on fundus photographs with deep learning
  publication-title: Ophthalmology
  doi: 10.1016/j.ophtha.2020.07.045
– volume: 3
  year: 2023
  ident: 10.1016/j.xops.2024.100667_bib10
  article-title: Detecting glaucoma from fundus photographs using deep learning without convolutions: transformer for improved generalization
  publication-title: Ophthalmol Sci
  doi: 10.1016/j.xops.2022.100233
– volume: 8
  year: 2018
  ident: 10.1016/j.xops.2024.100667_bib31
  article-title: Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs
  publication-title: Sci Rep
  doi: 10.1038/s41598-018-35044-9
– volume: 311
  year: 2024
  ident: 10.1016/j.xops.2024.100667_bib33
  article-title: Evaluating GPT-V4 (GPT-4 with vision) on detection of radiologic findings on chest radiographs
  publication-title: Radiology
– year: 2024
  ident: 10.1016/j.xops.2024.100667_bib18
  article-title: EyeGPT: ophthalmic assistant with large language models
  publication-title: arXiv
– start-page: 1
  year: 2011
  ident: 10.1016/j.xops.2024.100667_bib30
– year: 2024
  ident: 10.1016/j.xops.2024.100667_bib35
  article-title: Advancing multimodal medical capabilities of Gemini
  publication-title: arXiv
– volume: 6
  start-page: 112
  year: 2023
  ident: 10.1016/j.xops.2024.100667_bib8
  article-title: A generalizable deep learning regression model for automated glaucoma screening from fundus images
  publication-title: NPJ Digital Med
  doi: 10.1038/s41746-023-00857-0
– volume: 254
  start-page: 141
  year: 2023
  ident: 10.1016/j.xops.2024.100667_bib21
  article-title: Performance of generative large language models on ophthalmology board-style questions
  publication-title: Am J Ophthalmol
  doi: 10.1016/j.ajo.2023.05.024
– volume: 311
  start-page: 1901
  year: 2014
  ident: 10.1016/j.xops.2024.100667_bib2
  article-title: The pathophysiology and treatment of glaucoma: a review
  publication-title: JAMA
  doi: 10.1001/jama.2014.3192
– volume: 12
  start-page: 3121
  year: 2023
  ident: 10.1016/j.xops.2024.100667_bib26
  article-title: The use of chatgpt to assist in diagnosing glaucoma based on clinical case reports
  publication-title: Ophthalmol. Ther
  doi: 10.1007/s40123-023-00805-x
– volume: 12
  start-page: 17290
  year: 2024
  ident: 10.1016/j.xops.2024.100667_bib11
  article-title: Automated tool support for glaucoma identification with explainability using fundus images
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2024.3359698
– volume: 316
  start-page: 2402
  year: 2016
  ident: 10.1016/j.xops.2024.100667_bib6
  article-title: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs
  publication-title: JAMA
  doi: 10.1001/jama.2016.17216
– volume: 39
  start-page: 161
  year: 2020
  ident: 10.1016/j.xops.2024.100667_bib29
  article-title: RIM-ONE dl: a unified retinal image database for assessing glaucoma using deep learning
  publication-title: Image Anal Stereol
  doi: 10.5566/ias.2346
– year: 2024
  ident: 10.1016/j.xops.2024.100667_bib36
  article-title: Pefomed: parameter efficient fine-tuning on multimodal large language models for medical visual question answering
  publication-title: arXiv
– year: 2024
  ident: 10.1016/j.xops.2024.100667_bib15
  article-title: A review of multi-modal large language and vision models
  publication-title: arXiv
– year: 2024
  ident: 10.1016/j.xops.2024.100667_bib34
– year: 2024
  ident: 10.1016/j.xops.2024.100667_bib14
  article-title: Mm-llms: recent advances in multimodal large language models
  publication-title: arXiv
– volume: 12
  start-page: 3395
  year: 2023
  ident: 10.1016/j.xops.2024.100667_bib22
  article-title: What can GPT-4 do for diagnosing rare eye diseases? A pilot study
  publication-title: Ophthalmol Ther
  doi: 10.1007/s40123-023-00789-8
– volume: 37
  start-page: 3694
  year: 2023
  ident: 10.1016/j.xops.2024.100667_bib20
  article-title: Comparison of GPT-3.5, GPT-4, and human user performance on a practice ophthalmology written examination
  publication-title: Eye
  doi: 10.1038/s41433-023-02564-2
– year: 2023
  ident: 10.1016/j.xops.2024.100667_bib16
  article-title: Gpt-4 technical report
  publication-title: arXiv
– volume: 132
  start-page: 560
  year: 2014
  ident: 10.1016/j.xops.2024.100667_bib5
  article-title: Glaucomatous optic neuropathy evaluation project: factors associated with underestimation of glaucoma likelihood
  publication-title: JAMA Ophthalmol
  doi: 10.1001/jamaophthalmol.2014.96
– volume: 142
  start-page: 371
  year: 2024
  ident: 10.1016/j.xops.2024.100667_bib25
  article-title: Assessment of a large language model's responses to questions and cases about glaucoma and retina management
  publication-title: JAMA Ophthalmol
  doi: 10.1001/jamaophthalmol.2023.6917
SSID ssj0002513241
Score 2.3113434
Snippet The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations. Evaluation...
PurposeThe aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations....
The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations.PurposeThe...
Purpose: The aim is to assess GPT-4V's (OpenAI) diagnostic accuracy and its capability to identify glaucoma-related features compared to expert evaluations....
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
elsevier
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 100667
SubjectTerms Artificial intelligence
Fundus image analysis
Glaucoma detection
GPT-4V
Large multimodal models
Ophthalmology
Original
Title Glaucoma Detection and Feature Identification via GPT-4V Fundus Image Analysis
URI https://www.clinicalkey.com/#!/content/1-s2.0-S2666914524002033
https://www.clinicalkey.es/playcontent/1-s2.0-S2666914524002033
https://dx.doi.org/10.1016/j.xops.2024.100667
https://www.ncbi.nlm.nih.gov/pubmed/39877464
https://www.proquest.com/docview/3160939915
https://pubmed.ncbi.nlm.nih.gov/PMC11773068
https://doaj.org/article/3c1f903e5c9a4fc7badc40083db8d07d
Volume 5
WOSCitedRecordID wos001398692700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals (ODIN)
  customDbUrl:
  eissn: 2666-9145
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002513241
  issn: 2666-9145
  databaseCode: DOA
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2666-9145
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002513241
  issn: 2666-9145
  databaseCode: M~E
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Jb9QwFH6CCiEuiJ2wVEbihiLiJV6OLJ3CoaNKFDQ3y7EdMahkqplJxam_vc9ZhhlA7YVLDokdR8_Pz5_jz98DeO28EE4wl6sQQi6UN3lVCpUbRrnk3IhSuy7ZhJpO9WxmjrdSfSVOWC8P3BvuLfe0NgWPpTdO1F5VLniRgEOodChUSNG3UGZrMZViMM7aiBTocEqmJ3T9WpwlfW4mEjNAdonlf89EnWD_zoT0N-D8kze5NRFN7sHdAUGSd_2X34cbsXkAt4-GPfKHMD08dS36kSMf47ojWjXENYEksNcuI-mP5tbDvzpyPnfk8PgkF9_IpE15PMjnnxhjyKhW8gi-Tg5OPnzKh6wJuZdMr_O6qKqAqCJqVkmPaMilvIyMOYzKtfaGxhAdrjqcrLVynJZVYM64uoi1khLx3mPYaxZNfAokBhkZjz4qn3TZjaZllD5q4ytEu8JnQEcLWj9IiqfMFqd25I79sMnqNlnd9lbP4M2mzlkvqHFl6fepYzYlkxh2dwNdxA4uYq9zkQz42K12PG-KERJfNL-yafWvWnE1DPKVpXbFbGG_IMaRhooy0XFZwXkG5abmgGN6fHJti69Gn7M4yNPOjWviol1ZTmVhEErSMoMnvQ9uTMKNRggvRQZ6xzt3bLb7pJl_74TE04Y9Lhn1s_9h5edwh6XcyB0_7wXsrZdtfAm3_Pl6vlruw0010_vdIMXr0cXBJf15Qpg
linkProvider Directory of Open Access Journals
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=Glaucoma+Detection+and+Feature+Identification+via+GPT-4V+Fundus+Image+Analysis&rft.jtitle=Ophthalmology+science+%28Online%29&rft.au=Jalili%2C+Jalil&rft.au=Jiravarnsirikul%2C+Anuwat&rft.au=Bowd%2C+Christopher&rft.au=Chuter%2C+Benton&rft.date=2025-03-01&rft.issn=2666-9145&rft.eissn=2666-9145&rft.volume=5&rft.issue=2&rft.spage=100667&rft_id=info:doi/10.1016%2Fj.xops.2024.100667&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_xops_2024_100667
thumbnail_m http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F26669145%2FS2666914524X00032%2Fcov150h.gif