ChatGPT and antimicrobial advice: the end of the consulting infection doctor?
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Despite these risks, LLMs have the potential to revolutionize patient monitoring, treatment personalization, and patient education, leading to improved outcomes and better quality of life for patients with diabetes.
“Despite these risks, LLMs have the potential to revolutionize patient monitoring, treatment personalization, and patient education, leading to improved outcomes and better quality of life for patients with diabetes.149,150”
From Artificial intelligence in diabetes management: Advancements, opportunities, and challenges (2023) · cites this paper as [150]
As the complexity of the scenarios increased, ChatGPT missed relevant issues.
“but as the complexity of the scenarios increased, it missed relevant issues Howard et al. (2023).”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
ChatGPT sometimes gave dangerous advice despite prompting.
“and sometimes gave dangerous advice despite prompting.”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
Duration appropriateness of ChatGPT's antimicrobial advice varied.
“duration appropriateness varied”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
The advice provided by ChatGPT sometimes changed when questioned repeatedly.
“However, the advice provided sometimes changed when questioned repeatedly.”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
ChatGPT's understanding of scenarios was evident from the accurate summaries provided at the beginning of its responses.
“The model's understanding of scenarios was evident from the accurate summaries provided at the beginning of its responses.”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
ChatGPT was able to recognize clinically important factors when they were explicitly provided.
“ChatGPT was able to recognize clinically important factors when they were explicitly provided”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
Important situational aspects were not always well distinguished from unimportant ones by ChatGPT.
“However, important situational aspects were not always well distinguished from unimportant ones.”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
With a few notable exceptions, ChatGPT demonstrated appropriate recognition of natural language.
“With a few notable exceptions, ChatGPT demonstrated appropriate recognition of natural language Howard et al. (2023).”
From Decoding ChatGPT: A taxonomy of existing research, current challenges, and possible future directions (2023) · cites this paper as Howard et al. (2023)
ChatGPT can increase its utility in assisting clinicians and patients by moving away from fictional scenarios and focusing on providing effective answers to real health care questions.
“By moving away from fictional scenarios and focusing on providing effective answers to real health care questions [3,21], ChatGPT can increase its utility in assisting clinicians and patients.”
From Ethical Considerations of Using ChatGPT in Health Care (2023) · cites this paper as [21]
Previous studies have reported concerns about the accuracy and reliability of AI Chatbots in healthcare, labeled as "Artificial Hallucinations".
“These findings are consistent with previous studies that have reported concerns about the accuracy and reliability of AI Chatbots in healthcare and were labeled as “Artificial Hallucinations” [26,27].”
From ChatGPT and the Future of Digital Health: A Study on Healthcare Workers’ Perceptions and Expectations (2023) · cites this paper as [26]
The citation lists haven’t been fetched yet
References 4 · Cited by 202
- Authors
- Howard, A., Hope, W., & Gerada, A.
- Affiliations
- University of Liverpool (GB)
- Corresponding author
- Howard, Alex
- Venue
- The Lancet Infectious Diseases
- Publisher
- Elsevier BV
- Published
- 2023-04
- Volume
- 23
- Issue
- 4
- Pages
- 405-406
- ISSN
- 1473-3099 (ISSN-L)
- OpenAlex
- W4321366933
- Cited by
- 202
- References
- 4
- Citations by year
- 2026: 15 · 2025: 52 · 2024: 65 · 2023: 70
- FWCI
- 7.50
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- The Lancet Infectious Diseases (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Life Sciences › Immunology and Microbiology › Applied Microbiology and Biotechnology › Antibiotic Use and Resistance
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- antimicrobial resistance, ChatGPT, large language models, generative AI, antimicrobial stewardship, antimicrobial prescribing, telemedicine, clinical decision support, antibiotic resistance, USMLE, AI regulation
- MeSH terms
- Anti-Infective Agents, Humans, Patient Acceptance of Health Care, Physicians
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
