Putting ChatGPT’s Medical Advice to the (Turing) Test: Survey Study
Open accessPublished version of a preprint
The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
Background: Chatbots are being piloted to draft responses to patient questions, but patients’ ability to distinguish between provider and chatbot responses and patients’ trust in chatbots’ functions are not well established. Objective: This study aimed to assess the feasibility of using ChatGPT (Chat Generative Pre-trained Transformer) or a similar artificial intelligence–based chatbot for patient-provider communication. Methods: A survey study was conducted in January 2023. Ten representative, nonadministrative patient-provider interactions were extracted from the electronic health record. Patients’ questions were entered into ChatGPT with a request for the chatbot to respond using approximately the same word count as the human provider’s response. In the survey, each patient question was followed by a provider- or ChatGPT-generated response. Participants were informed that 5 responses were provider generated and 5 were chatbot generated. Participants were asked—and incentivized financially—to correctly identify the response source. Participants were also asked about their trust in chatbots’ functions in patient-provider communication, using a Likert scale from 1-5. Results: A US-representative sample of 430 study participants aged 18 and older were recruited on Prolific, a crowdsourcing platform for academic studies. In all, 426 participants filled out the full survey. After removing participants who spent less than 3 minutes on the survey, 392 respondents remained. Overall, 53.3% (209/392) of respondents analyzed were women, and the average age was 47.1 (range 18-91) years. The correct classification of responses ranged between 49% (192/392) to 85.7% (336/392) for different questions. On average, chatbot responses were identified correctly in 65.5% (1284/1960) of the cases, and human provider responses were identified correctly in 65.1% (1276/1960) of the cases. On average, responses toward patients’ trust in chatbots’ functions were weakly positive (mean Likert score 3.4 out of 5), with lower trust as the health-related complexity of the task in the questions increased. Conclusions: ChatGPT responses to patient questions were weakly distinguishable from provider responses. Laypeople appear to trust the use of chatbots to answer lower-risk health questions. It is important to continue studying patient-chatbot interaction as chatbots move from administrative to more clinical roles in health care.
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
“GPT-4 can generate fluent, human-like text, even about complex topics like medicine58.”
From Text classification models for assessing the completeness of randomized controlled trial publications based on CONSORT reporting guidelines (2024) · cites this paper as [58]
Experimental — accuracy not yet measured
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
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1×
“Research to mitigate risks of AI chatbot–generated responses, including the potential for patient harm caused by incorrect answers; cybersecurity vulnerabilities [31]; and environmental, social, and financial risks [32] should also be further explored.”
BackgroundSurvey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 1×
“These include biases from the underlying data (eg, social biases such as racism and sexism) [7,8], the ability to “hallucinate” information that is untrue [9], and the lack of mental models that would allow for true reasoning rather than simply probabilistic text generation (leading it to make errors in response to qu…”
BackgroundFisher, R. A. (1936) · BMJ · doi:10.1136/bmj.1.3923.554-a · Cited by 4,980
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083 · cited 3×
“Recent studies have had health care professionals judge ChatGPT’s responses to health-related questions [14-16], with findings such as 84% of answers to cardiovascular disease prevention questions being appropriate [15] and ChatGPT overall scoring higher for quality and empathy than health care…”
BackgroundMethodInfluentialAyers, J. W., Poliak, A., Dredze, M., Leas, E. C., Zhu, Z., Kelley, J. B., Faix, D. J., Goodman, A. M., Longhurst, C. A., Hogarth, M., et al. (2023) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2023.1838 · Cited by 2,613
Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine
Lee, P., Bubeck, S., & Petro, J. (2023) · New England Journal of Medicine · doi:10.1056/nejmsr2214184 · Cited by 1,738
Nadarzynski, T., Miles, O., Cowie, A., & Ridge, D. (2019) · DIGITAL HEALTH · doi:10.1177/2055207619871808 · Cited by 810
Role of Chat GPT in public health
Biswas, S. S. (2023) · Annals of Biomedical Engineering · doi:10.1007/s10439-023-03172-7 · Cited by 673 · cited 1×
“Recently, the launch of ChatGPT (Chat Generative Pre-trained Transformer; OpenAI) [1] has prompted a surge of interest in AI-based chatbots, both from the health care field [2,3] and the general public [4,5].”
BackgroundPhysician stress and burnout: the impact of health information technology
Gardner, R. L., Cooper, E., Haskell, J., Harris, D. A., Poplau, S., Kroth, P. J., & Linzer, M. (2019) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy145 · Cited by 566
Research works printed but not linked: 1
- BolukbasiTChangKWZouJSaligramaVKalaiAMan is to computer programmer as woman is to homemaker? debiasing word embeddings2016125NIPS'16: 30th International Conference on Neural Information Processing SystemsDecember 5-10, 2016Barcelona, Spain43564364
Cited by
Gender bias and stereotypes in Large Language Models
Kotek, H., Dockum, R., & Sun, D. (2023) · Proceedings of The ACM Collective Intelligence Conference · doi:10.1145/3582269.3615599 · Cited by 381
The impact of generative artificial intelligence on socioeconomic inequalities and policy making
Capraro, V., Lentsch, A., Acemoglu, D., Akgun, S., Akhmedova, A., Bilancini, E., Bonnefon, J.-F., Brañas-Garza, P., Butera, L., Douglas, K. M., et al. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae191 · Cited by 371
Nikolic, S., Daniel, S., Haque, R., Belkina, M., Hassan, G. M., Grundy, S., Lyden, S., Neal, P., & Sandison, C. (2023) · European Journal of Engineering Education · doi:10.1080/03043797.2023.2213169 · Cited by 336
Large language models in patient education: a scoping review of applications in medicine
Aydin, S., Karabacak, M., Vlachos, V., & Margetis, K. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1477898 · Cited by 288
How Can Recommender Systems Benefit from Large Language Models: A Survey
Lin, J., Dai, X., Xi, Y., Liu, W., Chen, B., Zhang, H., Liu, Y., Wu, C., Li, X., Zhu, C., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3678004 · Cited by 242
Metadata
- Authors
- Nov, O., Singh, N., & Mann, D.
- Affiliations
- New York University (US)
- NYU Langone Health (US)
- Corresponding author
- Nov, Oded
- Venue
- JMIR Medical Education
- Publisher
- JMIR Publications Inc.
- Published
- 2023-07-10
- Volume
- 9
- Pages
- e46939
- ISSN
- 2369-3762 (ISSN-L)
- PMC
- PMC10366957
- OpenAlex
- W4380575774
- Cited by
- 198
- References
- 28
- Citations by year
- 2026: 35 · 2025: 67 · 2024: 68 · 2023: 28
- FWCI
- 7.91
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Medical Education (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Science Foundation (1928614, 2129076)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Keywords
- ChatGPT, large language models, chatbots, patient-provider communication, source identification, trust in chatbots, patient questions, health information seeking, artificial intelligence in healthcare, Turing test, health literacy, task complexity
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Putting ChatGPT’s Medical Advice to the (Turing) Test: Survey Study. https://app.cochat.ai/papers/10.2196/46939
- The paper
- Nov, O., Singh, N., & Mann, D. (2023). Putting ChatGPT’s Medical Advice to the (Turing) Test: Survey Study. JMIR Medical Education. https://doi.org/10.2196/46939
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.