JOURNAL ARTICLE
Can Chatbot Artificial Intelligence Replace Infectious Diseases Physicians in the Management of Bloodstream Infections? A Prospective Cohort Study.
Published In: Clinical Infectious Diseases, 2024, v. 78, n. 4. P. 825 1 of 3
Database: Academic Search Ultimate 2 of 3
Authored By: Maillard, Alexis; Micheli, Giulia; Lefevre, Leila; Guyonnet, Cécile; Poyart, Claire; Canouï, Etienne; Belan, Martin; Charlier, Caroline 3 of 3
Abstract
This article evaluates the quality and safety of management plans proposed by Chat Generative Pre-training Transformer 4 (ChatGPT-4), a chatbot artificial intelligence (AI), for patients with positive blood cultures in a tertiary care hospital setting. Over a one-month period, ChatGPT-4's diagnostic and therapeutic recommendations were compared prospectively with those of infectious diseases (ID) specialist consultants, using standardized clinical data. While ChatGPT-4 provided detailed and well-structured responses, its management plans were optimal in only 2% of cases, appropriate in 39%, inadequate in 43%, and potentially harmful in 16%, particularly due to errors in source control and antibiotic therapy. The study concludes that, as of 2023, relying solely on ChatGPT-4 for expert medical advice in severe infectious diseases remains unsafe, though future AI developments may enhance clinical decision support.
Additional Information
- Source:Clinical Infectious Diseases. 2024/04, Vol. 78, Issue 4, p825
- Document Type:Article
- Subject Area:Health and Medicine
- Publication Date:2024
- ISSN:1058-4838
- DOI:10.1093/cid/ciad632
- Accession Number:176557948
- Copyright Statement:Copyright of Clinical Infectious Diseases is the property of Oxford University Press / USA 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.