Artificial Intelligence-Based ChatGPT Responses for Patient Questions on Optic Disc Drusen.
Accuracy
Artificial intelligence
ChatGPT
Optic disc drusen
Patient information
Journal
Ophthalmology and therapy
ISSN: 2193-8245
Titre abrégé: Ophthalmol Ther
Pays: England
ID NLM: 101634502
Informations de publication
Date de publication:
Dec 2023
Dec 2023
Historique:
received:
09
06
2023
accepted:
21
08
2023
medline:
12
9
2023
pubmed:
12
9
2023
entrez:
12
9
2023
Statut:
ppublish
Résumé
Optic disc drusen (ODD) are acellular deposits in the optic nerve head, which are most often benign and asymptomatic. Patients may develop visual field defects and be at increased risk of ischemic co-morbidities. As ODD can be difficult to distinguish from papilledema, patients are at risk of unnecessary clinical workups. Patient information is a key aspect of ODD management. In this study, we explored the accuracy of ChatGPT responses for typical patient questions on ODD. Two content experts reached consensus on 20 typical patient questions. We retrieved five separate responses for each question from ChatGPT, totaling 100 responses. Each response was evaluated on a 5-point Likert-scale on accuracy by each content expert in an individual fashion. The two experts were in fair/substantial agreement in the evaluation of responses (Cronbach's alpha: 0.64). Of the 100 responses, 17 were relevant and without any inaccuracies, 78 were relevant and with inaccuracies not being harmful, and five were relevant and with inaccuracies potentially harmful. The lowest accuracy scores were obtained for questions dealing with treatment and prognosis. ChatGPT often provides relevant answers for patient questions on ODD, but inaccuracies become potentially harmful when questions deal with treatment and prognosis.
Identifiants
pubmed: 37698823
doi: 10.1007/s40123-023-00800-2
pii: 10.1007/s40123-023-00800-2
pmc: PMC10640407
doi:
Types de publication
Journal Article
Langues
eng
Pagination
3109-3119Informations de copyright
© 2023. The Author(s).
Références
J Neuroophthalmol. 2020 Sep;40(3):356-361
pubmed: 31972711
Am J Ophthalmol. 2020 Sep;217:174-181
pubmed: 32298654
Am J Ophthalmol. 2023 Apr;248:137-144
pubmed: 36516916
Eur J Hum Genet. 2023 May 29;:
pubmed: 37246194
Acta Ophthalmol. 2023 May 5;:
pubmed: 37144704
Am J Ophthalmol. 1989 Mar 15;107(3):236-40
pubmed: 2923150
Clin Ophthalmol. 2016 Aug 16;10:1535-41
pubmed: 27574393
Arch Ophthalmol. 2004 Jan;122(1):48-53
pubmed: 14718294
Acta Ophthalmol. 2021 Dec;99(8):931-933
pubmed: 33880859
Acta Ophthalmol. 2018 Nov;96(7):673-684
pubmed: 29659172
J Neuroophthalmol. 2018 Sep;38(3):299-307
pubmed: 29095768
Acta Ophthalmol. 2020 Mar;98(2):195-200
pubmed: 31264343
Acta Ophthalmol. 2023 Nov;101(7):829-831
pubmed: 36912780
Dan Med J. 2014 Feb;61(2):A4787
pubmed: 24495891
JMIR Mhealth Uhealth. 2015 Jul 27;3(3):e79
pubmed: 26215371
J Med Internet Res. 2021 Jul 2;23(7):e21680
pubmed: 33979776
J Med Internet Res. 2015 Mar 25;17(3):e81
pubmed: 25830358
Graefes Arch Clin Exp Ophthalmol. 2023 Oct;261(10):3041-3043
pubmed: 37129631
J Neuroophthalmol. 2021 Jun 1;41(2):200-205
pubmed: 32358432
Proc Natl Acad Sci U S A. 2023 Feb 7;120(6):e2218523120
pubmed: 36730192