The Pros and Cons of Using ChatGPT in Medical Education: A Scoping Review
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
This scoping review explores the advantages and disadvantages of using ChatGPT in medical education. We searched PubMed, Google Scholar, Medline, Scopus, and Science Direct to identify relevant studies. Two reviewers independently conducted study selection and data extraction, followed by a narrative synthesis. Out of 197 references, 25 studies met the eligibility criteria. The primary applications of ChatGPT in medical education include automated scoring, teaching assistance, personalized learning, research assistance, quick access to information, generating case scenarios and exam questions, content creation for learning facilitation, and language translation. We also discuss the challenges and limitations of using ChatGPT in medical education, such as its inability to reason beyond existing knowledge, generation of incorrect information, bias, potential undermining of students’ critical thinking skills, and ethical concerns. These concerns include using ChatGPT for exam and assignment cheating by students and researchers, as well as issues related to patients’ privacy.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“These fabricated references may include convincing combinations of real author names, journal titles, and plausible publication years, making them difficult to detect without thorough verification.”
From Fabricated or accurate? Ethical concerns and citation hallucination in aI-generated scientific writing on musculoskeletal topics (2025) · cites this paper as [13]
In the citing paper
“Systematic and scoping reviews note that literature on the association between functional LLM-CB use and critical thinking skills remains inconclusive90–92.”
From A scoping review on the mental health harms of LLM-based chatbots (2026) · cites this paper as [91]
Citations
Cites
ChatGPT - Reshaping medical education and clinical management
Khan, R. A., Jawaid, M., Khan, A. R., & Sajjad, M. (2023) · Pakistan Journal of Medical Sciences · doi:10.12669/pjms.39.2.7653 · Cited by 628 · cited 4×
“Artificial Intelligence (AI) has transcended fiction and now permeates medical education and clinical management, as well as various aspects of daily life [1].”
BackgroundMethodInfluentialThe future of medical education and research: Is ChatGPT a blessing or blight in disguise?
Arif, T. B., Munaf, U., & Ul-Haque, I. (2023) · Medical Education Online · doi:10.1080/10872981.2023.2181052 · Cited by 317
Aubignat, M., & Diab, E. (2023) · Revue Neurologique · doi:10.1016/j.neurol.2023.03.004 · Cited by 20 · cited 3×
“These limitations can be addressed through advancing large language models, with major companies like Google, Apple, Facebook, Amazon, and Microsoft working on similar projects [3].”
BackgroundInfluential
Cited by
Items 101–116 of 116
Fontana, A., Sinatti, G., Cicchinelli, S., Santini, S. J., Caputo, V., Letteri, I., Vittorini, P., & Balsano, C. (2024) · International Conference on Information Technology Based Higher Education and Training (ITHET) · doi:10.1109/ithet61869.2024.10837651
“In the specific context of medical education, LLMs were found to have promising but mixed results [11], [12], [13].”
Evaluating the efficacy of the new electronic dental assistant training program
Tang, X., Gu, W., Hu, Y., & Yan, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-99856-2 · Cited by 1
“…it substantially reduce the probability of errors among medical practitioners in the execution of their professional responsibilities, but it also provides them with specialized training and educational opportunities, enabling them to explore more deeply into relevant professional knowledge 13,14 .”
Hirosawa, T., Yokose, M., Sakamoto, T., Harada, Y., Tokumasu, K., Mizuta, K., & Shimizu, T. (2025) · doi:10.2196/preprints.77332
Kohan, N., Ahmady, S., Yaseen, S., Hoshmandjah, M., Keshavarzi, M. H., & Rezaei, P. (2024) · JMIR Medical Education · doi:10.2196/56325
Stimmer, L., Kuiper, R., Polledo, L., Ressel, L., Rodríguez, J. M. M., Veiga, I. B., Williams, J. M., & Herder, V. (2025) · Veterinary Pathology · doi:10.1177/03009858251343215 · Cited by 1
Healthcare Education in the AI Chatbot Era: The Hidden Trap
Aljuraid, R. (2025) · Studies in health technology and informatics · doi:10.3233/shti250785
Yapay Zekâ ve Vergi Uygulamaları: ChatGPT’nin Kullanım Alanları, Etkileri ve Etik Zorluklar
Özdemir, H. (2025) · Fiscaoeconomia · doi:10.25295/fsecon.1573723 · Cited by 3
Strzelecki, A., Rutecka, P., Cicha, K., & Rizun, M. (2026) · Springer eBooks · doi:10.1007/978-981-95-4871-2_3
Assessing ChatGPT as an Educational Tool for Image Generation in Dermatology
Moschella, A., Akuffo‐Addo, E., Brathwaite, S., Lapa, T., Waugh, M., & Joseph, M. (2026) · Journal of Cutaneous Medicine and Surgery · doi:10.1177/12034754251411901
Arbor, S., Mojica-Henshaw, M. P., Ritchie, R. P., Fleet, V. V., & Arbor, T. C. (2026) · Artificial intelligence · doi:10.5772/intechopen.1012581
Zhang, Y.-Q., WANG, X., He, Y.-P., Rong, H., & Meng, Y.-Y. (2026) · Evidence-Based Chinese Medicine and Technology Assessment · doi:10.26599/ecmta.2026.9570027
The 3C model: a simple prompt engineering framework for generative artificial intelligence
Damania, R. C., Hrdy, M., Mehta, N., & Wolbrink, T. A. (2026) · Academic Medicine · doi:10.1093/acamed/wvag098
Engin, İ., Celik, M., & Ozkan, E. M. A. (2026) · Farabi Tıp Dergisi · doi:10.59518/farabimedj.1928053
Zhang, Q., Chen, G., Wu, X., Niu, X., & Chiang, F. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2026.2680593
Rathmann, R., Bozkurt, A., Kaindl, A., Piazza, A., & Garg, R. (2026) · Edition HMD · doi:10.1007/978-3-658-51795-3_19
Chai, B. S., Yim, M. M., Ranjbar, D., & Tang, D. T. (2026) · Global Surgical Education - Journal of the Association for Surgical Education · doi:10.21203/rs.3.rs-10198678/v1
Metadata
- Authors
- Mohammad, B., Supti, T., Alzubaidi, M., Shah, H., Alam, T., Shah, Z., & Househ, M.
- Affiliations
- Hamad bin Khalifa University (QA)
- Corresponding author
- Househ, Mowafa
- Venue
- Studies in Health Technology and Informatics
- Publisher
- IOS Press
- Published
- 2023-06-29
- Volume
- 305
- Pages
- 644-647
- ISSN
- 0926-9630 (ISSN-L)
- 1879-8365
- OpenAlex
- W4382632493
- Cited by
- 114
- References
- 3
- Citations by year
- 2026: 11 · 2025: 38 · 2024: 53 · 2023: 12
- FWCI
- 41.18
- Type
- book chapter
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Studies in health technology and informatics (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Social Sciences › Education › Artificial Intelligence in Education
- Social Sciences › Education › Innovations in Medical Education
- Keywords
- ChatGPT, large language models, medical education, automated grading, personalized learning, exam question generation, language translation, critical thinking, academic integrity, cheating, patient privacy, ethical considerations, algorithmic bias
- MeSH terms
- Education, Medical, Eligibility Determination, Humans, Learning, MEDLINE, Knowledge
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.