Using ChatGPT for Clinical Practice and Medical Education: Cross-Sectional Survey of Medical Students’ and Physicians’ Perceptions
Open accessPublished version of a preprint
The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
Background: ChatGPT is a well-known large language model–based chatbot. It could be used in the medical field in many aspects. However, some physicians are still unfamiliar with ChatGPT and are concerned about its benefits and risks. Objective: We aim to evaluate the perception of physicians and medical students toward using ChatGPT in the medical field. Methods: A web-based questionnaire was sent to medical students, interns, residents, and attending staff with questions regarding their perception toward using ChatGPT in clinical practice and medical education. Participants were also asked to rate their perception of ChatGPT’s generated response about knee osteoarthritis. Results: Participants included 124 medical students, 46 interns, 37 residents, and 32 attending staff. After reading ChatGPT’s response, 132 of the 239 (55.2%) participants had a positive rating about using ChatGPT for clinical practice. The proportion of positive answers was significantly lower in graduated physicians (48/115, 42%) compared with medical students (84/124, 68%; P<.001). Participants listed a lack of a patient-specific treatment plan, updated evidence, and a language barrier as ChatGPT’s pitfalls. Regarding using ChatGPT for medical education, the proportion of positive responses was also significantly lower in graduate physicians (71/115, 62%) compared to medical students (103/124, 83.1%; P<.001). Participants were concerned that ChatGPT’s response was too superficial, might lack scientific evidence, and might need expert verification. Conclusions: Medical students generally had a positive perception of using ChatGPT for guiding treatment and medical education, whereas graduated doctors were more cautious in this regard. Nonetheless, both medical students and graduated doctors positively perceived using ChatGPT for creating patient educational materials.
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
“In a medical environment, GAI-generated treatment plans, although generally reasonable, often fail to consider individual patient characteristics, such as the severity of the disease, lifestyle, and personal preferences [105].”
From Applications, Challenges, and Prospects of Generative Artificial Intelligence Empowering Medical Education: Scoping Review (2025) · cites this paper as [105]
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
“The content generated by GAI lacks personalization tailored to individual needs.”
From Applications, Challenges, and Prospects of Generative Artificial Intelligence Empowering Medical Education: Scoping Review (2025) · cites this paper as [105]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“First, although the number of respondents exceeded the required sample size, the response rate was lower compared with similar studies [19, 21, 22, 24, 25, 29, 31, 34, 37, 40, 62], which may limit the generalizability of the findings.”
The cited source says what the claim attributes to it.
In the citing paper
“Eight studies examined the knowledge, attitudes, and skills of medical students and educators regarding LLMs, specifically ChatGPT [24, 26–29, 79–81]. Students generally expressed a more positive attitude toward LLMs than practicing physicians, showing optimism about their potential to support learners and educators [81]. Those who were more knowledgeable about LLMs tended to hold a more positive”
From Artificial intelligence in undergraduate medical education: an updated scoping review (2025) · cites this paper as [81]
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
1 retracted
Huynh, L. M., Bonebrake, B. T., Schultis, K., Quach, A., & Deibert, C. M. (2023) · Urology Practice · doi:10.1097/upj.0000000000000406 · Cited by 46 · cited 1×
“For more advanced examination levels, such as resident-level examinations, ChatGPT performed more poorly [7,34,35].”
BackgroundRetractedKung, 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 · cited 1×
“However, the results of using ChatGPT were quite varied, from passing the exam to failing some [7,8,10,30-33].”
ResultKung, 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
Large language models in medicine
Thirunavukarasu, A. J., Ting, D. S. J., Elangovan, K., Gutierrez, L., Tan, T. F., & Ting, D. S. W. (2023) · Nature Medicine · doi:10.1038/s41591-023-02448-8 · Cited by 3,944
Gilson, A., Safranek, C. W., Huang, T., Socrates, V., Chi, L., Taylor, R. A., & Chartash, D. (2023) · JMIR Medical Education · doi:10.2196/45312 · Cited by 2,078
Dergaa, I., Chamari, K., Zmijewski, P., & Ben Saad, H. (2023) · Biology of Sport · doi:10.5114/biolsport.2023.125623 · Cited by 796 · cited 1×
“In the medical field, it has been used to help write manuscripts [3-5].”
BackgroundLarge Language Models in Medical Education: Opportunities, Challenges, and Future Directions
Abd-alrazaq, A., AlSaad, R., Alhuwail, D., Ahmed, A., Healy, P. M., Latifi, S., Aziz, S., Damseh, R., Alabed Alrazak, S., & Sheikh, J. (2023) · JMIR Medical Education · doi:10.2196/48291 · Cited by 722 · cited 1×
“In medical education, ChatGPT could be used in various aspects [27].”
MethodMájovský, M., Černý, M., Kasal, M., Komarc, M., & Netuka, D. (2023) · Journal of Medical Internet Research · doi:10.2196/46924 · Cited by 301 · cited 1×
“However, researchers were still concerned about the contents’ethical consideration and validity [6].”
BackgroundSamaan, J. S., Yeo, Y. H., Rajeev, N., Hawley, L., Abel, S., Ng, W. H., Srinivasan, N., Park, J., Burch, M., Watson, R., et al. (2023) · Obesity Surgery · doi:10.1007/s11695-023-06603-5 · Cited by 282 · cited 1×
“For example, bariatric surgeons rated responses of ChatGPT as “comprehensive” for 86.8% of the questions asked [18].”
BackgroundInfluentialHuh, S. (2023) · Journal of Educational Evaluation for Health Professions · doi:10.3352/jeehp.2023.20.1 · Cited by 278 · cited 1×
“However, the results of using ChatGPT were quite varied, from passing the exam to failing some [7,8,10,30-33].”
Result
Cited by
Items 101–122 of 122
Meta-Analysis on the Effect Size of Chatbot Integration in Student Science Performance
Villanueva, J. C. P. M., Atalia, G. D. N., & Villamin, J. L. A. (2026) · International Journal of Information and Education Technology · doi:10.18178/ijiet.2026.16.6.2633
“16.6.2633 Manuscript received June 25, 2025; revised July 17, 2025; accepted November 24, 2025; published June 24, 2026 instructors viewed them as beneficial [20].”
InfluentialAlotaibi, M. M., & Alotaibi, H. M. (2026) · BMC Medical Education · doi:10.1186/s12909-026-09755-x
“These issues are especially significant in high-stakes professional learning environments where educational outcomes are directly connected to future clinical practice [50], [54], [32].”
Reshetnikov, R. V., Vasilev, Y. A., Федоровна, Ш. Ю., Альфредовна, А. Д., Alymova, Y. A., Vladzymyrskyy, A. V., Tyrov, I. A., Omelyanskaya, O. V., & Blokhin, I. A. (2026) · European Journal of Investigation in Health Psychology and Education · doi:10.3390/ejihpe16070094
“…or informational tasks, such as documentation support, summarization, or generation of patient educational materials, whereas greater caution is expressed when LLMs are expected to support diagnosis, treatment planning, or clinical judgment (Blease et al., 2025; Tangadulrat et al., 2023).”
Baek, G., Lee, H., Yang, D. H., Kang, M., Lee, K. H., Choi, M., Lee, Y., & Lee, K. H. (2026) · JMIR Medical Education · doi:10.2196/97822
“…(BEME) scoping review by Gordon et al [10] confirmed that published AI education programs remain predominantly foundational—covering AI literacy, prompt engineering, and learners’ perceptions of generative AI tools such as ChatGPT [11-13]—and target mainly medical students and residents [14,15].”
InfluentialOsijirin, A. N., Sada, S. M., Egbeh, F. N., Ezeagwu, P. C., Umah, D. N., & Anumaka, C. I. (2026) · Research Square · doi:10.21203/rs.3.rs-10534067/v1
ChatGPT as a Learning Assistant in Medical Education Student Perceptions and Academic Performance
Lakshmi, R., Srevatsa, K., & Moudgalya, A. (2026) · International Journal of Medical and Biomedical Studies · doi:10.32553/7757w633
Li, Y., Li, J., Yan, J., Li, Y., & Li, Q. (2026) · Journal of Craniofacial Surgery · doi:10.1097/scs.0000000000013217
Cole, R., Hemmer, P. A., Moores, L. K., Mears, D., Samuel, A., Croix, C. L. L., Pearce, E., & Elster, E. A. (2026) · JMIR Medical Education · doi:10.2196/preprints.109763
Cohen, S., Tailor, P. D., Au, A., Vu, J. T., Marin, A. I., Prasad, P. S., Kwon, J., Hosseini, H., & Sridhar, J. (2026) · Journal of VitreoRetinal Diseases · doi:10.1177/24741264261469005
“46 With regard to concerns regarding hallucinations, our study found that responses to patients’ frequently asked questions and organically created patient education materials for uncommon retinal conditions were, on average, rated between “accurate” and “very accurate.””
Brzezicki, M. A., & Zakowicz, P. T. (2026) · International Journal of Psychiatry in Clinical Practice · doi:10.1080/13651501.2026.2718248
Structured prompting as reusable clinical tools
Husum, D., & Hügle, T. (2026) · EULAR Rheumatology Open · doi:10.1016/j.ero.2026.100230
“Rather than entering keywords into a search engine, clinicians could now pose clinical questions in natural language and receive synthesised, narrative responses [18].”
Ozaki, N., Shikino, K., Araki, N., Tajima, H., Kasai, H., Shimizu, I., Yamauchi, K., & Ito, S. (2026) · JMIR Formative Research · doi:10.2196/102390
“Recent JMIR Medical Education studies have highlighted the educational potential of ChatGPT-based tools and the need for expert verification, evidence awareness, and safeguards [22,23].”
Elucidating the transformative role of large language models in advancing anesthesiology education
Zhu, Y., Xie, D., Liang, R., Yang, J.-J., Du, X.-Y., & Zhou, C.-M. (2026) · Journal of International Medical Research · doi:10.1177/03000605261483195
“…responses with accuracy comparable to that of human faculty; and (c) instructional design support for curriculum and learning resource development .11 However, key limitations remain unaddressed, including variable output accuracy for high-stakes clinical content and the risk of impaired critical…”
Almalki, M. H., & Al-Mubarak, S. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1932876
“Such findings align with previous studies indicating that younger physicians, as digital natives, view AI tools as a natural extension of clinical practice (50, 51).”
Orhan, S. S., Dinçal, T., Arzu, U., Özdamar, İ., & Gencer, B. (2026) · Anatolian Journal of Emergency Medicine · doi:10.54996/anatolianjem.1772154
Henning, M. A., Geng, Z., Krägeloh, C. U., Ng, L., Chen, Y., Li, A., & Webster, C. S. (2026) · Education in Medicine Journal · doi:10.21315/eimj2026.18.3.18
Generative AI in Dentistry: Transforming Patient Care and Treatment Planning
Manisha Murella, D. D. D., Dharma, D., Neelam, S., Misrabi, A., Deshpande, A. S., & Wajid, M. (2025) · South Eastern European Journal of Public Health
Arias, L. M. D., Ospina, D. A., & Ríos, M. A. L. (2026) · Archivos de Medicina (Manizales) · doi:10.30554/archmed.26.2.5667.2026
“La adopción también se describe en poblaciones fuera de Norteamérica, con patrones de utilidad académica coexistiendo con inquietudes por confiabilidad y prácticas indebidas [6].”
Kassem, A. A., Mohamed, S. F., Aboraya, A. A., & Hashish, A. (2026) · Tanta Medical Journal · doi:10.4103/tmj.tmj_117_25
Poulose, P., Paulose, D., & Bourne, D. (2026) · Cureus · doi:10.7759/cureus.118211
Xiaoli, D., & Guohong, W. (2026) · Advances in Medical Education and Practice · doi:10.2147/amep.s635200
“24,25 In addition, The TOPSIS-RSR composite ranking is a point estimate without confidence intervals, and further sensitivity analyses are needed to confirm the robustness of the results through multi-centre, large-sample validation.”
Badakhshan, U., Ahadi, N., & Athavale, R. (2026) · doi:10.2196/preprints.116174
Metadata
- Authors
- Tangadulrat, P., Sono, S., & Tangtrakulwanich, B.
- Affiliations
- Prince of Songkla University (TH)
- Corresponding author
- Tangtrakulwanich, Boonsin
- Venue
- JMIR Medical Education
- Publisher
- JMIR Publications Inc.
- Published
- 2023-12-22
- Volume
- 9
- Pages
- e50658
- ISSN
- 2369-3762 (ISSN-L)
- PMC
- PMC10770783
- OpenAlex
- W4390114552
- Cited by
- 99
- References
- 39
- Citations by year
- 2026: 36 · 2025: 31 · 2024: 32
- FWCI
- 3.95
- 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)
- Greater South Information System
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Technology and Human Factors in Education and Health
- Social Sciences › Education › Artificial Intelligence in Education
- Keywords
- ChatGPT, large language models, medical students, physicians, artificial intelligence in medical education, knee osteoarthritis, patient education materials
- MeSH terms
- Cross-Sectional Studies, Education, Medical, Humans, Language, Physicians, Students, Medical
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.