CoChat
Sign Up
Cited by 38Artificial Intelligence in Healthcare and EducationArtificial Intelligence in HealthcareMultimodal Machine Learning Applications

Evaluation of ChatGPT and Google Bard using prompt engineering in cancer screening algorithms

Nguyen, Daniel, Swanson, Daniel, Newbury, Alex, Kim, Young H.·2024·Academic Radiology
DOI 10.1016/j.acra.2023.11.002
Open this paper in CoChat — free account

Abstract

Large language models (LLMs) such as ChatGPT and Bard have emerged as powerful tools in medicine, showcasing strong results in tasks such as radiology report translations and research paper drafting. While their implementation in clinical practice holds promise, their response accuracy remains variable. This study aimed to evaluate the accuracy of ChatGPT and Bard in clinical decision-making based on the American College of Radiology Appropriateness Criteria for various cancers. Both LLMs were evaluated in terms of their responses to open-ended (OE) and select-all-that-apply (SATA) prompts. Furthermore, the study incorporated prompt engineering (PE) techniques to enhance the accuracy of LLM outputs. The results revealed similar performances between ChatGPT and Bard on OE prompts, with ChatGPT exhibiting marginally higher accuracy in SATA scenarios. The introduction of PE also marginally improved LLM outputs in OE prompts but did not enhance SATA responses. The results highlight the potential of LLMs in aiding clinical decision-making processes, especially when guided by optimally engineered prompts. Future studies in diverse clinical situations are imperative to better understand the impact of LLMs in radiology.

Integrity signals

Registry

Crossref · 10.1016/j.acra.2023.11.002

Cites

10 of 10 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

  • Fine-tuning allows models to adapt to the unique linguistic and contextual challenges presented by medical texts, potentially improving the accuracy and relevance of extracted information.

    “Fine-tuning allows models to adapt to the unique linguistic and contextual challenges presented by medical texts, potentially improving the accuracy and relevance of extracted information [29].”

    From Large Language Model Applications for Health Information Extraction in Oncology: Scoping Review (2025) · cites this paper as [29]

  • LLMs have in-context learning capabilities that allow them to adapt to the given prompt.

    “LLMs have in-context learning capabilities that allow them to adapt to the given prompt, so prompts can be intentionally designed to support performance on further tasks, such as patient communication, administrative tasks, risk assessments, or clinical decision-making.160,161”

    From Large Language Models for Chatbot Health Advice Studies: A Systematic Review (2025) · cites this paper as [161]

  • Prompts can be intentionally designed to support performance on further tasks, such as patient communication, administrative tasks, risk assessments, or clinical decision-making.

    “LLMs have in-context learning capabilities that allow them to adapt to the given prompt, so prompts can be intentionally designed to support performance on further tasks, such as patient communication, administrative tasks, risk assessments, or clinical decision-making.160,161”

    From Large Language Models for Chatbot Health Advice Studies: A Systematic Review (2025) · cites this paper as [161]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Nguyen, D., Swanson, D., Newbury, A., & Kim, Y. H.
Affiliations
University of Massachusetts Chan Medical School (US)
Corresponding author
Nguyen, Daniel
ORCID
Venue
Academic Radiology
Publisher
Elsevier BV
Published
2024-05
Volume
31
Issue
5
Pages
1799-1804
ISSN
1076-6332 (ISSN-L)
DOI
10.1016/j.acra.2023.11.002
OpenAlex
W4389780040
Cited by
38
References
10
Citations by year
2026: 6 · 2025: 20 · 2024: 12
FWCI
1.54
Type
journal article
Language
en
Open access
closed
Licence
Locations
  • Academic Radiology (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
large language models, ChatGPT, Google Bard, prompt engineering, cancer screening, clinical decision support, radiology, open-ended prompts
MeSH terms
Clinical Decision-Making, Algorithms, Humans, Neoplasms, Radiology Information Systems, Early Detection of Cancer

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