Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec;33(12):3971-3980.
doi: 10.1007/s11695-023-06903-w. Epub 2023 Oct 27.

Bariatric Evaluation Through AI: a Survey of Expert Opinions Versus ChatGPT-4 (BETA-SEOV)

Affiliations

Bariatric Evaluation Through AI: a Survey of Expert Opinions Versus ChatGPT-4 (BETA-SEOV)

Amir Hossein Davarpanah Jazi et al. Obes Surg. 2023 Dec.

Abstract

Background: Recent advancements in artificial intelligence, such as OpenAI's ChatGPT-4, are revolutionizing various sectors, including healthcare. This study investigates the use of ChatGPT-4 in identifying suitable candidates for bariatric surgery and providing surgical recommendations to improve decision-making in obesity treatment amid the global obesity epidemic.

Methods: We devised ten patient scenarios, thoughtfully encompassing a spectrum that spans from uncomplicated cases to more complex ones. Our objective was to delve into the decision-making process regarding the recommendation of bariatric surgery. From July 29th to August 10th, 2023, we conducted a voluntary online survey involving thirty prominent bariatric surgeons, ensuring that there was no predetermined bias in the selection of a specific type of bariatric surgery. This survey was designed to collect their insights on these scenarios and gain a deeper understanding of their professional experience and background in the field of bariatric surgery. Additionally, we consulted ChatGPT-4 in two separate conversations to evaluate its alignment with expert opinions on bariatric surgery options.

Results: In 40% of the scenarios, disparities were identified between the two conversations with ChatGPT-4. It matched expert opinions in 30% of cases. Differences were noted in cases like gastrointestinal metaplasia and gastric adenocarcinoma, but there was alignment with conditions like endometriosis and GERD.

Conclusion: The evaluation of ChatGPT-4's role in determining bariatric surgery suitability uncovered both potential and shortcomings. Its alignment with experts was inconsistent, and it often overlooked key factors, emphasizing human expertise's value. Its current use requires caution, and further refinement is needed for clinical application.

Keywords: Artificial Intelligence; Bariatric Evaluation; Bariatric Surgery; ChatGPT; Health Literacy; Language Learning Models.

PubMed Disclaimer

References

    1. Jin L, Tan F, Jiang S. Generative adversarial network technologies and applications in computer vision. Comput Intell Neurosci. 2020;2020:1459107. - DOI - PubMed - PMC
    1. Pan Z, Yu W, Yi X, Khan A, Yuan F, Zheng Y. Recent progress on generative adversarial networks (GANs): A survey. IEEE Access. 2019;7:36322–33. https://doi.org/10.1109/ACCESS.2019.2905015 . - DOI
    1. Sarraju A, Bruemmer D, Van Iterson E, et al. Appropriateness of cardiovascular disease prevention recommendations obtained from a popular online chat-based artificial intelligence model. JAMA. 2023;329(10):842–4. - DOI - PubMed - PMC
    1. Kung TH, Cheatham M, Medenilla A, et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit Heal. 2023;2(2):e0000198. - DOI
    1. Morreel S, Mathysen D, Verhoeven V. Aye, AI! ChatGPT passes multiple-choice family medicine exam. Med Teacher. 2023;45:665–6 (England). - DOI

LinkOut - more resources