The Consistency and Quality of ChatGPT Responses Compared to Clinical Guidelines for Ovarian Cancer: A Delphi Approach.

Publisher: MDPI Country of Publication: Switzerland NLM ID: 9502503 Publication Model: Electronic Cited Medium: Internet ISSN: 1718-7729 (Electronic) Linking ISSN: 11980052 NLM ISO Abbreviation: Curr Oncol Subsets: MEDLINE

Publication: 2021- : Basel, Switzerland : MDPI
Original Publication: Toronto : Multimed, c1994-

Ovarian Neoplasms* ; Delphi Technique* ; Practice Guidelines as Topic*; Medical Oncology/methods ; Medical Oncology/standards ; Humans ; Female ; Artificial Intelligence

Introduction: In recent years, generative Artificial Intelligence models, such as ChatGPT, have increasingly been utilized in healthcare. Despite acknowledging the high potential of AI models in terms of quick access to sources and formulating responses to a clinical question, the results obtained using these models still require validation through comparison with established clinical guidelines. This study compares the responses of the AI model to eight clinical questions with the Italian Association of Medical Oncology (AIOM) guidelines for ovarian cancer.
Materials and Methods: The authors used the Delphi method to evaluate responses from ChatGPT and the AIOM guidelines. An expert panel of healthcare professionals assessed responses based on clarity, consistency, comprehensiveness, usability, and quality using a five-point Likert scale. The GRADE methodology assessed the evidence quality and the recommendations' strength.
Results: A survey involving 14 physicians revealed that the AIOM guidelines consistently scored higher averages compared to the AI models, with a statistically significant difference. Post hoc tests showed that AIOM guidelines significantly differed from all AI models, with no significant difference among the AI models.
Conclusions: While AI models can provide rapid responses, they must match established clinical guidelines regarding clarity, consistency, comprehensiveness, usability, and quality. These findings underscore the importance of relying on expert-developed guidelines in clinical decision-making and highlight potential areas for AI model improvement.

Ann Oncol. 2019 May 1;30(5):672-705. (PMID: 31046081)
Healthcare (Basel). 2023 Mar 19;11(6):. (PMID: 36981544)
Clin Mol Hepatol. 2023 Jul;29(3):721-732. (PMID: 36946005)
BMJ Health Care Inform. 2023 Jun;30(1):. (PMID: 37399360)
J Natl Compr Canc Netw. 2021 Feb 02;19(2):191-226. (PMID: 33545690)
Front Artif Intell. 2023 May 04;6:1169595. (PMID: 37215063)
Clin Transl Med. 2023 Mar;13(3):e1216. (PMID: 36856370)
Ann Surg Oncol. 2023 Jun;30(6):3174-3176. (PMID: 37052826)
Int J Surg. 2023 Aug 01;109(8):2549-2550. (PMID: 37195797)
J Pediatr Urol. 2023 Oct;19(5):598-604. (PMID: 37328321)
Curr Oncol Rep. 2023 May;25(5):387-424. (PMID: 36811808)
BMC Nurs. 2023 Apr 6;22(1):102. (PMID: 37024875)
BMJ. 2008 Apr 26;336(7650):924-6. (PMID: 18436948)
JMIR Cancer. 2021 Nov 29;7(4):e27850. (PMID: 34847056)
Int J Radiat Oncol Biol Phys. 2023 Aug 1;116(5):977-983. (PMID: 37037358)
HERD. 2020 Jan;13(1):11-23. (PMID: 31887097)
J Med Syst. 2023 Mar 04;47(1):33. (PMID: 36869927)
Cureus. 2023 Apr 21;15(4):e37938. (PMID: 37220429)
Semin Oncol Nurs. 2023 Jun;39(3):151433. (PMID: 37137770)
Front Oncol. 2023 Sep 14;13:1265024. (PMID: 37790756)

Keywords: ChatGPT; artificial intelligence; guidelines; ovarian carcinoma

Date Created: 20240524 Date Completed: 20240524 Latest Revision: 20240526

20260130

PMC11119344

10.3390/curroncol31050212

38785493