ChatGPT versus expert feedback on clinical reasoning questions and their effect on learning: a randomized controlled trial
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Purpose: To evaluate the effectiveness of ChatGPT-generated feedback compared to expert-written feedback in improving clinical reasoning skills among first-year medical students. Methods: This is a randomized controlled trial conducted at a single medical school and involved 129 first-year medical students who were randomly assigned to two groups. Both groups completed three formative tests with feedback on urinary tract infections (UTIs; uncomplicated, complicated, pyelonephritis) over five consecutive days as a spaced repetition, receiving either expert-written feedback (control, n = 65) or ChatGPT-generated feedback (experiment, n = 64). Clinical reasoning skills were assessed using Key-Features Questions (KFQs) immediately after the intervention and 10 days later. Students’ critical approach to artificial intelligence (AI) was also measured before and after disclosing the AI involvement in feedback generation. Results: There was no significant difference between the mean scores of the control (immediate: 78.5 ± 20.6 delayed: 78.0 ± 21.2) and experiment (immediate: 74.7 ± 15.1, delayed: 76.0 ± 14.5) groups in overall performance on Key-Features Questions (out of 120 points) immediately (P = .26) or after 10 days (P = .57), with small effect sizes. However, the control group outperformed the ChatGPT group in complicated urinary tract infection cases (P < .001). The experiment group showed a significantly higher critical approach to AI after disclosing, with medium-large effect sizes. Conclusions: ChatGPT-generated feedback can be an effective alternative to expert feedback in improving clinical reasoning skills in medical students, particularly in resource-constrained settings with limited expert availability. However, AI-generated feedback may lack the nuance needed for more complex cases, emphasizing the need for expert review. Additionally, exposure to the drawbacks in AI-generated feedback can enhance students’ critical approach towards AI-generated educational content.
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.
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
Kapur, M. (2008) · Cognition and Instruction · doi:10.1080/07370000802212669 · Cited by 867
A scoping review of artificial intelligence in medical education: BEME Guide No. 84
Gordon, M., Daniel, M., Ajiboye, A., Uraiby, H., Xu, N. Y., Bartlett, R., Hanson, J., Haas, M., Spadafore, M., Grafton-Clarke, C., et al. (2024) · Medical Teacher · doi:10.1080/0142159x.2024.2314198 · Cited by 679
Walker, H. L., Ghani, S., Kuemmerli, C., Nebiker, C. A., Müller, B. P., Raptis, D. A., & Staubli, S. M. (2023) · Journal of Medical Internet Research · doi:10.2196/47479 · Cited by 363
Kononowicz, A. A., Zary, N., Edelbring, S., Corral, J., & Hege, I. (2015) · BMC Medical Education · doi:10.1186/s12909-015-0296-3 · Cited by 203
Holderried, F., Stegemann-Philipps, C., Herrmann-Werner, A., Festl-Wietek, T., Holderried, M., Eickhoff, C., & Mahling, M. (2024) · JMIR Medical Education · doi:10.2196/59213 · Cited by 152
Masters, K. (2023) · Medical Teacher · doi:10.1080/0142159x.2023.2208731 · Cited by 76
Creating virtual patients using large language models: scalable, global, and low cost
Cook, D. A. (2025) · Medical Teacher · doi:10.1080/0142159x.2024.2376879 · Cited by 73
Productive failure as an instructional approach to promote future learning
Steenhof, N., Woods, N. N., Van Gerven, P. W. M., & Mylopoulos, M. (2019) · Advances in Health Sciences Education · doi:10.1007/s10459-019-09895-4 · Cited by 70
Coşkun, Ö., Kıyak, Y. S., & Budakoğlu, I. İ. (2025) · Medical Teacher · doi:10.1080/0142159x.2024.2327477 · Cited by 64
Self-citationTong, L., Wang, J., Rapaka, S., & Garg, P. S. (2025) · Medical Teacher · doi:10.1080/0142159x.2024.2363486 · Cited by 12
Research works printed but not linked: 18
- Holmboe, 2014, Assessing clinical reasoning: moving from in vitro to in vivo, Diagnosis, 1, 111, 10.1515/dx-2013-0029 · DOI
- Kononowicz, 2020, The need for longitudinal clinical reasoning teaching and assessment: results of an international survey, Medical Teacher, 42, 457, 10.1080/0142159X.2019.1708293 · DOI · Paper page
- Kıyak, 2021, ContExtended questions (CEQ) to teach and assess clinical reasoning: a new variant of F-type testlets, Rev Esp Edu Med, 2, 48, 10.6018/edumed.467921 · DOI
- Schank, 1975, Scripts, plans, and knowledge, IJCAI, 151
- Kıyak, 2023, Can preclinical students improve their clinical reasoning skills only by taking case-based online testlets? A randomized controlled study, Innov Educ Teach Int, 60, 325, 10.1080/14703297.2022.2041458 · DOI
- Kıyak, 2024, Test-only learning via virtual patients to improve surgical illness scripts of preclinical medical students as a preparation for clinical clerkships: an experimental study, Surg Innov, 31, 318, 10.1177/15533506241246333 · DOI
- Lam, Utility of large language models for creating clinical assessment items, Med Teach, 10.1080/0142159X.2024.2382860 · DOI
- Kıyak, ChatGPT prompts for generating multiple-choice questions in medical education and evidence on their validity: a literature review, Postgrad Med J, 100, 10.1093/postmj/qgae065 · DOI · Paper page
- Fink, 2024, AI-based avatars are changing the way we learn and teach: benefits and challenges, Front Educ, 9, 1416307, 10.3389/feduc.2024.1416307 · DOI
- Tomova, 2024, Leveraging Large Language Models to Construct Feedback from Medical Multiple-Choice Questions, 10.1038/s41598-024-79245-x · DOI
- Creswell, 2012, Educational Research: Planning, Conducting, and Evaluating Quantitative and Qualitative Research
- Kıyak, 2023, Exploratory factor analysis of a computerized case-based F-type testlet variant, MedSciEduc, 33, 1191, 10.1007/s40670-023-01876-y · DOI
- Bordage, 2018, The key-features approach to assess clinical decisions: validity evidence to date, Adv in Health Sci Educ, 23, 1005, 10.1007/s10459-018-9830-5 · DOI
- Sullivan, 2012, Using effect size—or why the P value is not enough, J Grad Med Educ, 4, 279, 10.4300/JGME-D-12-00156.1 · DOI · Paper page
- Downing, 2009, Assessment in Health Professions Education, 10.1080/00981380902765212 · DOI
- Leppink, 2022, Data analysis: more expensive does not imply better, Rev Esp Edu Med, 3, 12, 10.6018/edumed.516731 · doi:10.6018/edumed.516731
- Brauer, 2015, The integrated curriculum in medical education: AMEE guide No. 96, Med Teach., 37, 312, 10.3109/0142159X.2014.970998 · DOI · Paper page
- Deng, 2023, Limitations of large language models in medical applications, Postgrad Med J, 99, 1298, 10.1093/postmj/qgad069 · DOI
Cited by
Izquierdo-Condoy, J. S., Arias-Intriago, M., Tello-De-la-Torre, A., Busch, F., & Ortiz-Prado, E. (2025) · Journal of Medical Internet Research · doi:10.2196/76340 · Cited by 87
Generative AI for clinical reasoning: A scoping review
Liu, Y.-M., Chou, C.-C., Jaing, T.-H., & Okoli, C. T. C. (2026) · Teaching and Learning in Nursing · doi:10.1016/j.teln.2025.08.008 · Cited by 12
Fąferek, J., Kononowicz, A. A., Bogutska, N., Da Silva Domingues, V., Davydova, N., Frankowska, A., Iguacel, I., Mayer, A., Morin, L., Pavlyukovich, N., et al. (2025) · BMC Medical Education · doi:10.1186/s12909-025-08006-9 · Cited by 10
“Former research has shown a promising potential of generative AI, often ChatGPT, in creating educational content, such as multiple-choice questions [55, 56] assessment items [57], feedback to learners [58], and VPs and case vignettes [32, 33].”
TAY, Y. N., NEO, N. W. S., & SIAH, C. J. R. (2026) · Nurse Education Today · doi:10.1016/j.nedt.2026.107322 · Cited by 4
Kondo, T., Donkers, J., Nishigori, H., Rovers, S., & Heeneman, S. (2026) · JMIR Medical Education · doi:10.2196/90064 · Cited by 1
“Previous research has noted that AI feedback tends to provide comprehensive feedback closely tied to the target text [24,25], while human experts in specialized fields provide context-informed feedback that is perceived to be of higher quality [22,54].”
Metadata
- Authors
- Çiçek, F. E., Ülker, M., Özer, M., & Kıyak, Y. S.
- Venue
- Postgraduate Medical Journal
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-12-05
- Volume
- 101
- Issue
- 1195
- Pages
- 458-463
- ISSN
- 0032-5473 (ISSN-L)
- 1469-0756
- OpenAlex
- W4405228616
- Cited by
- 66
- References
- 10
- FWCI
- 5.29
- Type
- journal article
- Language
- en
- Open access
- hybrid
- Funders
- Scientific and Technological Research Council of Turkiye
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: ChatGPT versus expert feedback on clinical reasoning questions and their effect on learning: a randomized controlled trial. https://app.cochat.ai/papers/10.1093/postmj/qgae170
- The paper
- Çiçek, F. E., Ülker, M., Özer, M., & Kıyak, Y. S. (2025). ChatGPT versus expert feedback on clinical reasoning questions and their effect on learning: a randomized controlled trial. Postgraduate Medical Journal. https://doi.org/10.1093/postmj/qgae170
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.