ChatGPT’s performance in German OB/GYN exams—paving the way for AI-enhanced medical education and clinical practice
Open accessAbstract
Background: Chat Generative Pre-Trained Transformer (ChatGPT) is an artificial learning and large language model tool developed by OpenAI in 2022. It utilizes deep learning algorithms to process natural language and generate responses, which renders it suitable for conversational interfaces. ChatGPT's potential to transform medical education and clinical practice is currently being explored, but its capabilities and limitations in this domain remain incompletely investigated. The present study aimed to assess ChatGPT's performance in medical knowledge competency for problem assessment in obstetrics and gynecology (OB/GYN). Methods: Two datasets were established for analysis: questions (1) from OB/GYN course exams at a German university hospital and (2) from the German medical state licensing exams. In order to assess ChatGPT's performance, questions were entered into the chat interface, and responses were documented. A quantitative analysis compared ChatGPT's accuracy with that of medical students for different levels of difficulty and types of questions. Additionally, a qualitative analysis assessed the quality of ChatGPT's responses regarding ease of understanding, conciseness, accuracy, completeness, and relevance. Non-obvious insights generated by ChatGPT were evaluated, and a density index of insights was established in order to quantify the tool's ability to provide students with relevant and concise medical knowledge. Results: ChatGPT demonstrated consistent and comparable performance across both datasets. It provided correct responses at a rate comparable with that of medical students, thereby indicating its ability to handle a diverse spectrum of questions ranging from general knowledge to complex clinical case presentations. The tool's accuracy was partly affected by question difficulty in the medical state exam dataset. Our qualitative assessment revealed that ChatGPT provided mostly accurate, complete, and relevant answers. ChatGPT additionally provided many non-obvious insights, especially in correctly answered questions, which indicates its potential for enhancing autonomous medical learning. Conclusion: ChatGPT has promise as a supplementary tool in medical education and clinical practice. Its ability to provide accurate and insightful responses showcases its adaptability to complex clinical scenarios. As AI technologies continue to evolve, ChatGPT and similar tools may contribute to more efficient and personalized learning experiences and assistance for health care providers.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Reported growth in behavioral learning gains encompasses self-directed learning, diagnostic skills, clinical practice, engagement, and chatbot usage frequency.
“Reported growth in behavioral learning gains encompasses self-directed learning (16), diagnostic skills (44), clinical practice (26), engagement (19), and chatbot usage frequency (28).”
From Digital affordances of AI chatbots in nursing education: a systematic review of learning gains and gaps in the evidence (2026) · cites this paper as [44]
The Discussion (page unavailable) says AI simulations can let students practice diagnostic skills and receive feedback, supporting the diagnostic-skills point to which this source appears to be cited. It describes a potential use, not reported growth in behavioral learning gains; the study evaluated ChatGPT’s exam responses rather than changes in students’ skills. The other listed outcomes have separate citations and are not assessed here. (LLM, conf=0.84)
Experimental — accuracy not yet measuredPersonalization (n = 4) by AI chatbots, through timely feedback, has shown a significant impact on students' diagnostic skills, engagement, and frequency of chatbot use.
“Personalization (n = 4) by AI chatbots, through timely feedback, have shown a significant impact on students’ diagnostic skills, engagement, and frequency of chatbot use (19, 28, 44).”
From Digital affordances of AI chatbots in nursing education: a systematic review of learning gains and gaps in the evidence (2026) · cites this paper as [44]
The Discussion says ChatGPT can give personalized responses and that diagnostic exercises can provide immediate feedback. It does not report a demonstrated significant impact on students’ diagnostic skills, engagement, or frequency of chatbot use; the Introduction describes educational benefits as largely hypothetical. (LLM, conf=0.86)
Experimental — accuracy not yet measuredAcross all models, performance tended to decline with increased difficulty, especially for higher-level questions requiring multistep reasoning, where accuracy dropped markedly.
“Across all models, performance tended to decline with increased difficulty, especially for higher-level questions that required multistep reasoning, where accuracy dropped markedly [39-45].”
From Applications, Challenges, and Prospects of Generative Artificial Intelligence Empowering Medical Education: Scoping Review (2025) · cites this paper as [41]
The Results section reports that ChatGPT performed significantly better on easier state-exam questions, and the Discussion describes those questions as requiring more complex processing and weighing multiple pieces of clinical information. But the Results also say difficulty did not significantly affect performance on the OB/GYN course questions. This paper evaluates ChatGPT, not 'all models,' and does not specifically measure multistep reasoning. Page numbers were not provided in our copy. (LLM, conf=0.88)
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.
The citation lists haven’t been fetched yet
References 38 · Cited by 49
Research works printed but not linked: 1
- [4]Dai Z Yang Z Yang Y Carbonell J Le QV Salakhutdinov R (2019). Transformer-XL: Attentive language models beyond a fixed-length context. Available at: https://arxiv.org/abs/1901.02860 (Accessed September 17, 2023). · arXiv
- Authors
- Riedel, M., Kaefinger, K., Stuehrenberg, A., Ritter, V., Amann, N., Graf, A., Recker, F., Klein, E., Kiechle, M., Riedel, F., & Meyer, B.
- Affiliations
- TUM Klinikum (DE)
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- University Hospital Bonn (DE)
- University Hospital Heidelberg (DE)
- Corresponding author
- Riedel, Maximilian
- Venue
- Frontiers in Medicine
- Publisher
- Frontiers Media SA
- Published
- 2023-12-13
- Volume
- 10
- Pages
- 1296615-1296615
- ISSN
- 2296-858X (ISSN-L)
- PMC
- PMC10753765
- OpenAlex
- W4389683892
- Cited by
- 49
- References
- 38
- Citations by year
- 2026: 12 · 2025: 26 · 2024: 11
- FWCI
- 1.95
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Medicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) (submittedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Innovations in Medical Education
- Keywords
- ChatGPT, large language models, artificial intelligence in healthcare, obstetrics and gynecology, medical licensing examinations, medical education, medical students, self-directed learning, clinical case presentations
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
