Evaluating ChatGPT as an Adjunct for Radiologic Decision-Making
Open accessThe DOI matches its Crossref record; 23 of the 25 references it cites were found in a registry or an index, and 2 are not checked yet.
Abstract
BACKGROUND: ChatGPT, a popular new large language model (LLM) built by OpenAI, has shown impressive performance in a number of specialized applications. Despite the rising popularity and performance of AI, studies evaluating the use of LLMs for clinical decision support are lacking. PURPOSE: To evaluate ChatGPT’s capacity for clinical decision support in radiology via the identification of appropriate imaging services for two important clinical presentations: breast cancer screening and breast pain. MATERIALS AND METHODS: We compared ChatGPT’s responses to the American College of Radiology (ACR) Appropriateness Criteria for breast pain and breast cancer screening. Our prompt formats included an open-ended (OE) format, where ChatGPT was asked to provide the single most appropriate imaging procedure, and a select all that apply (SATA) format, where ChatGPT was given a list of imaging modalities to assess. Scoring criteria evaluated whether proposed imaging modalities were in accordance with ACR guidelines. RESULTS: ChatGPT achieved an average OE score of 1.83 (out of 2) and a SATA average percentage correct of 88.9% for breast cancer screening prompts, and an average OE score of 1.125 (out of 2) and a SATA average percentage correct of 58.3% for breast pain prompts. CONCLUSION: Our results demonstrate the feasibility of using ChatGPT for radiologic decision making, with the potential to improve clinical workflow and responsible use of radiology services.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“ChatGPT-3.5 offers improved workflow to support clinical decision making in radiology [9].”
From Is there any room for ChatGPT AI bot in speech-language pathology? (2025) · cites this paper as [9]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Unintended negative consequences, such as inappropriate or inaccurate content, pose significant risks in health care settings, necessitating careful consideration before its adoption in health care education [9,69-71].”
From Assessing Health Students' Attitudes and Usage of ChatGPT in Jordan: Validation Study (2023) · cites this paper as [69]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Ethical issues including the risk of bias and transparency issues appeared as recurring major concerns [51,68,69,77].”
From ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns (2023) · cites this paper as [69]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In the area of personalized medicine, the lack of transparency and unclear information regarding the sources of data used for ChatGPT training are important issues in health care settings considering the variability observed among different populations in several health-related traits [69].”
From ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns (2023) · cites this paper as [69]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Moreover, ChatGPT showed moderate accuracy in determining the imaging steps needed in breast cancer screening and in the evaluation of breast pain, which can be a promising application in decision making in radiology [69].”
From ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns (2023) · cites this paper as [69]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Kung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115
Breast Cancer Statistics, 2022
Giaquinto, A. N., Sung, H., Miller, K. D., Kramer, J. L., Newman, L. A., Minihan, A., Jemal, A., & Siegel, R. L. (2022) · CA: A Cancer Journal for Clinicians · doi:10.3322/caac.21754 · Cited by 2,286
ChatGPT is fun, but not an author
Thorp, H. H. (2023) · Science · doi:10.1126/science.adg7879 · Cited by 1,437
ChatGPT and other large language models are double-edged swords
Shen, Y., Heacock, L., Elias, J., Hentel, K. D., Reig, B., Shih, G., & Moy, L. (2023) · Radiology · doi:10.1148/radiol.230163 · Cited by 1,008 · cited 1×
“Concomitant improvements in CDS infrastructure to enhance provider accuracy of appropriate imaging orders will emerge as a major priority and the involvement of ChatGPT-like AI is already being discussed 22 .”
BackgroundChatGPT listed as author on research papers: many scientists disapprove
Stokel-Walker, C. (2023) · Nature · doi:10.1038/d41586-023-00107-z · Cited by 868 · cited 1×
“ChatGPT’s ability to simulate highly technical language has prompted researchers to credit the chatbot authorship in biomedical literature 9,10 with scientific journals scrambling to clarify publishing ethics in response 11–13 .”
BackgroundTools such as ChatGPT threaten transparent science; here are our ground rules for their use
(2023) · Nature · doi:10.1038/d41586-023-00191-1 · Cited by 605
ChatGPT and the future of medical writing
Biswas, S. (2023) · Radiology · doi:10.1148/radiol.223312 · Cited by 571 · cited 1×
“ChatGPT’s ability to simulate highly technical language has prompted researchers to credit the chatbot authorship in biomedical literature 9,10 with scientific journals scrambling to clarify publishing ethics in response 11–13 .”
BackgroundFlanagin, A., Bibbins-Domingo, K., Berkwits, M., & Christiansen, S. L. (2023) · JAMA · doi:10.1001/jama.2023.1344 · Cited by 420
GPT Takes the Bar ExamPreprint
Bommarito, M., & Katz, D. (2022) · Social Science Research Network · doi:10.48550/arxiv.2212.14402 · Cited by 195
Bommarito, M. J., & Katz, D. M. (2022) · doi:10.2139/ssrn.4314839 · Cited by 181
Characterizing and quantifying low-value diagnostic imaging internationally: a scoping review
Kjelle, E., Andersen, E. R., Krokeide, A. M., Soril, L. J. J., van Bodegom‐Vos, L., Clement, F. M., & Hofmann, B. (2022) · BMC Medical Imaging · doi:10.1186/s12880-022-00798-2 · Cited by 120
Artificial Intelligence and Clinical Decision Support for Radiologists and Referring Providers
Bizzo, B. C., Almeida, R. R., Michalski, M. H., & Alkasab, T. K. (2019) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2019.06.010 · Cited by 98
Gpt as Knowledge Worker: A Zero-Shot Evaluation of (AI)CPA Capabilities
Bommarito, J., Bommarito, M. J., Katz, J., & Katz, D. M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4322372 · Cited by 68
Overutilization of Health Care Resources for Breast Pain
Kushwaha, A. C., Shin, K., Kalambo, M. J., Legha, R. S., Gerlach, K. E., Kapoor, M. M., & Yang, W. T. (2018) · American Journal of Roentgenology · doi:10.2214/ajr.17.18879 · Cited by 46
Shah, C., Davtyan, K., Nasrallah, I., Bryan, R. N., & Mohan, S. (2022) · Journal of Digital Imaging · doi:10.1007/s10278-022-00713-9 · Cited by 44
Factors Influencing Overuse of Breast Cancer Screening: A Systematic Review
Sharma, R., Pannikottu, J., Xu, Y., Tung, M. L., Nothelle, S. K., Oakes, A. H., & Segal, J. B. (2018) · Journal of Women s Health · doi:10.1089/jwh.2017.6689 · Cited by 23
Austin, J. D., Tehranifar, P., Rodriguez, C. B., Brotzman, L., Agovino, M., Ziazadeh, D., Moise, N., & Shelton, R. C. (2021) · Implementation Science Communications · doi:10.1186/s43058-021-00217-7 · Cited by 19
GPT as Knowledge Worker: A Zero-Shot Evaluation of (AI)CPA CapabilitiesPreprint
Bommarito, J., Bommarito, M. J., Katz, D. M., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.04408 · Cited by 15
Overutilization of Breast Cancer Screening in the US: Awareness of a Growing Problem
Schonberg, M. A. (2017) · Journal of General Internal Medicine · doi:10.1007/s11606-017-4258-9 · Cited by 10
Habib, A. R., Grady, D. G., & Redberg, R. F. (2021) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2021.0161 · Cited by 10
Sadigh, G., Duszak, R., Ward, K. C., Jiang, R., Switchenko, J. M., Applegate, K. E., & Carlos, R. C. (2017) · Journal of General Internal Medicine · doi:10.1007/s11606-017-4212-x · Cited by 3
Research works printed but not linked: 2
- 17. [Goyal, A. Breast pain. BMJ Clin. Evid. 2014 , 0812 (2014).](https://www.zotero.org/google-docs/?gi5GFo)
- 20. [ACR Appropriateness Criteria®. https://www.acr.org/Clinical-Resources/ACR-Appropriateness-Criteria.](https://www.zotero.org/google-docs/?gi5GFo) All rights reserved. No reuse allowed without permission. (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. medRxiv preprint doi: https://doi.org/10.1101/2023.02.02.23285399; this version posted February 7, 2023. The copyright holder for this preprint
Cited by
Sallam, M. (2023) · Healthcare · doi:10.3390/healthcare11060887 · Cited by 3,126
“Ethical issues including the risk of bias and transparency issues appeared as recurring major concerns [51,68,69,77].”
BackgroundInfluentialSallam, M. (2023) · doi:10.1101/2023.02.19.23286155 · Cited by 3,123
“Moreover, ChatGPT showed moderate accuracy to determine the imaging steps needed in breast cancer screening and evaluation of breast pain which can be a promising application in decision making in radiology [50].”
BackgroundInfluentialRay, P. P. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.04.003 · Cited by 2,463
A Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3744746 · Cited by 1,257
ChatGPT for Education and Research: Opportunities, Threats, and Strategies
Rahman, M. M., & Watanobe, Y. (2023) · Applied Sciences · doi:10.3390/app13095783 · Cited by 1,080
“[45] 11 Adjunct for radiologic decision-making”
Metadata
- Authors
- Rao, A., Kim, J., Kamineni, M., Pang, M., Lie, W., & Succi, M. D.
- Affiliations
- Harvard University (US)
- Massachusetts General Hospital (US)
- Corresponding author
- Succi, Marc D.
- Venue
- medRxiv
- Publisher
- openRxiv
- Published
- 2023-02-07
- PMC
- PMC9934725
- OpenAlex
- W4319341091
- Cited by
- 257
- References
- 21
- Citations by year
- 2026: 17 · 2025: 48 · 2024: 96 · 2023: 94
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- medRxiv (acceptedVersion)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion)
- Funders
- National Institutes of Health
- National Institute of General Medical Sciences (T32GM144273)
- 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 › Artificial Intelligence › AI in cancer detection
- Keywords
- ChatGPT, large language models, clinical decision support, ACR Appropriateness Criteria, breast cancer screening, breast pain, imaging modality selection, artificial intelligence in radiology
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.