OA2‐AM23‐SN‐18 | Do Doctors Dream of Electric Blood Bankers? Publicly Available Artificial Intelligence Chatbots Make Transfusion Decisions with Accuracy and Precision.

  • Published In: Transfusion, 2023, v. 63, n. S5. P. 42A 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Hurley, N.; Hess, A. 3 of 3

Abstract

The article focuses on the evaluation of generative artificial intelligence (AI) tools, specifically large language models (LLMs) like ChatGPT, in the context of transfusion medicine. A study was conducted using a dataset of patient scenarios to assess the accuracy and precision of three LLMs—GPT 3.5, ChatGPT 4.0, and Bard—in making transfusion decisions. The results indicated that ChatGPT 4.0 outperformed the other models, achieving an accuracy of 91% and a precision of 80%, suggesting that LLMs can provide appropriate transfusion recommendations. The article emphasizes the need for further research to explore the practical applications of LLMs in transfusion medicine and the potential role of physicians in conjunction with these technologies. [Extracted from the article]

Additional Information

  • Source:Transfusion. 2023/10, Vol. 63, Issue S5, p42A
  • Document Type:Article
  • Subject Area:Physics
  • Publication Date:2023
  • ISSN:0041-1132
  • DOI:10.1111/trf.41_17554
  • Accession Number:191023733
  • Copyright Statement:Copyright of Transfusion is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.