CoChat

How does ChatGPT-4 preform on non-English national medical licensing examination? An evaluation in Chinese language

Open access
Fang, Changchang, Wu, Yuting, Fu, Wanying, Ling, Jitao, Wang, Yue, Liu, Xiaolin, Jiang, Yuan, Wu, Yifan, Chen, Yixuan, Zhou, Jing, Zhu, Zhichen, Yan, Zhiwei, Yu, Peng, Liu, Xiao · 2023 · PLOS Digital Health
Cited by 91

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pdig.0000397

Cites

4 of 4 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 4 references

Cited by

See all 91

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
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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: How does ChatGPT-4 preform on non-English national medical licensing examination? An evaluation in Chinese language. https://app.cochat.ai/papers/10.1371/journal.pdig.0000397
The paper
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. (2023). How does ChatGPT-4 preform on non-English national medical licensing examination? An evaluation in Chinese language. PLOS Digital Health. https://doi.org/10.1371/journal.pdig.0000397

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.