How does ChatGPT-4 preform on non-English national medical licensing examination? An evaluation in Chinese language
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
ChatGPT, an artificial intelligence (AI) system powered by large-scale language models, has garnered significant interest in healthcare. Its performance dependent on the quality and quantity of training data available for a specific language, with the majority of it being in English. Therefore, its effectiveness in processing the Chinese language, which has fewer data available, warrants further investigation. This study aims to assess the of ChatGPT’s ability in medical education and clinical decision-making within the Chinese context. We utilized a dataset from the Chinese National Medical Licensing Examination (NMLE) to assess ChatGPT-4’s proficiency in medical knowledge in Chinese. Performance indicators, including score, accuracy, and concordance (confirmation of answers through explanation), were employed to evaluate ChatGPT’s effectiveness in both original and encoded medical questions. Additionally, we translated the original Chinese questions into English to explore potential avenues for improvement. ChatGPT scored 442/600 for original questions in Chinese, surpassing the passing threshold of 360/600. However, ChatGPT demonstrated reduced accuracy in addressing open-ended questions, with an overall accuracy rate of 47.7%. Despite this, ChatGPT displayed commendable consistency, achieving a 75% concordance rate across all case analysis questions. Moreover, translating Chinese case analysis questions into English yielded only marginal improvements in ChatGPT’s performance (p = 0.728). ChatGPT exhibits remarkable precision and reliability when handling the NMLE in Chinese. Translation of NMLE questions from Chinese to English does not yield an improvement in ChatGPT’s performance.
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
Kung, 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
Kung, 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
Huh, S. (2023) · Journal of Educational Evaluation for Health Professions · doi:10.3352/jeehp.2023.20.1 · Cited by 278
Lai, V. D., Ngo, N. T., Veyseh, A. P. B., Man, H., Dernoncourt, F., Bui, T., & Nguyen, T. H. (2023) · arXiv · doi:10.48550/arxiv.2304.05613 · Cited by 233
Cited by
Xu, X., Chen, Y., & Miao, J. (2024) · Journal of Educational Evaluation for Health Professions · doi:10.3352/jeehp.2024.21.6 · Cited by 169
Self-citationChatGPT failed Taiwan’s Family Medicine Board Exam
Weng, T.-L., Wang, Y.-M., Chang, S., Chen, T.-J., & Hwang, S.-J. (2023) · Journal of the Chinese Medical Association · doi:10.1097/jcma.0000000000000946 · Cited by 100
Self-citationJin, H. K., Lee, H. E., & Kim, E. (2024) · BMC Medical Education · doi:10.1186/s12909-024-05944-8 · Cited by 85
“Additionally, they have primarily reported the accuracy rate of a single version of ChatGPT instead of comparing different versions [17, 29, 32, 37, 39, 44].”
BackgroundLiu, M., Okuhara, T., Dai, Z., Huang, W., Gu, L., Okada, H., Furukawa, E., & Kiuchi, T. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105673 · Cited by 73
Analyzing evaluation methods for large language models in the medical field: a scoping review
Lee, J., Park, S., Shin, J., & Cho, B. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02709-7 · Cited by 52
Metadata
- Authors
- Fang, C., Wu, Y., Fu, W., Ling, J., Wang, Y., Liu, X., Jiang, Y., Wu, Y., Chen, Y., Zhou, J., Zhu, Z., Yan, Z., Yu, P., & Liu, X.
- Venue
- PLOS Digital Health
- Publisher
- Public Library of Science (PLoS)
- Published
- 2023-12-01
- Volume
- 2
- Issue
- 12
- Pages
- e0000397
- ISSN
- 2767-3170 (ISSN-L)
- OpenAlex
- W4389235809
- Cited by
- 91
- References
- 4
- FWCI
- 3.11
- Type
- journal article
- Language
- en
- Open access
- gold
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.