CoChat

Exploring the potential of artificial intelligence to enhance the writing of english academic papers by non-native english-speaking medical students - the educational application of ChatGPT

Open access
Li, Jiakun, Zong, Hui, Wu, Erman, Wu, Rongrong, Peng, Zhufeng, Zhao, Jing, Yang, Lu, Xie, Hong, Shen, Bairong · 2024 · BMC Medical Education

The DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index; 7 of the 36 sources its claims cite were checked for support.

Abstract

Background: Academic paper writing holds significant importance in the education of medical students, and poses a clear challenge for those whose first language is not English. This study aims to investigate the effectiveness of employing large language models, particularly ChatGPT, in improving the English academic writing skills of these students. Methods: A cohort of 25 third-year medical students from China was recruited. The study consisted of two stages. Firstly, the students were asked to write a mini paper. Secondly, the students were asked to revise the mini paper using ChatGPT within two weeks. The evaluation of the mini papers focused on three key dimensions, including structure, logic, and language. The evaluation method incorporated both manual scoring and AI scoring utilizing the ChatGPT-3.5 and ChatGPT-4 models. Additionally, we employed a questionnaire to gather feedback on students’ experience in using ChatGPT. Results: After implementing ChatGPT for writing assistance, there was a notable increase in manual scoring by 4.23 points. Similarly, AI scoring based on the ChatGPT-3.5 model showed an increase of 4.82 points, while the ChatGPT-4 model showed an increase of 3.84 points. These results highlight the potential of large language models in supporting academic writing. Statistical analysis revealed no significant difference between manual scoring and ChatGPT-4 scoring, indicating the potential of ChatGPT-4 to assist teachers in the grading process. Feedback from the questionnaire indicated a generally positive response from students, with 92% acknowledging an improvement in the quality of their writing, 84% noting advancements in their language skills, and 76% recognizing the contribution of ChatGPT in supporting academic research. Conclusion: The study highlighted the efficacy of large language models like ChatGPT in augmenting the English academic writing proficiency of non-native speakers in medical education. Furthermore, it illustrated the potential of these models to make a contribution to the educational evaluation process, particularly in environments where English is not the primary language.

Overview

CoChat Summary

TL;DR

This pilot study found that a two-week ChatGPT-3.5 revision intervention improved Chinese non-native English-speaking medical students’ English mini-paper scores across manual, ChatGPT-3.5, and ChatGPT-4 evaluations. ChatGPT-4 scoring did not differ significantly from manual grading, suggesting possible grading-support potential.

Key findings

  • Manual total scores rose from 46.45 ± 3.59 to 50.68 ± 2.03 after ChatGPT use, an improvement of 4.23 points (95% CI 2.64, 5.82); ChatGPT-3.5 total scores increased by 4.82 points (95% CI 2.47, 7.17), and ChatGPT-4 total scores by 3.84 points (95% CI 0.83, 6.85).
  • Manual scoring improved significantly in structure, logic, language, and total score (all p < 0.001); ChatGPT-3.5 scoring improved significantly in all dimensions and total score (all p < 0.05); ChatGPT-4 scoring improved significantly in structure, logic, and total score (all p < 0.05), but not language (β 1.02, 95% CI −0.15, 2.19, p = 0.10).
  • ChatGPT-3.5 scores differed significantly from manual grading, while ChatGPT-4 scores did not differ significantly from manual grading, suggesting ChatGPT-4 may assist teachers in grading.
  • Questionnaire feedback: 92% reported improved writing quality, 84% reported language-skill advancement, 76% saw ChatGPT as useful for academic research/literature review, and 100% used it for English polishing.

Methods

  • Two-stage pre-post study with 25 third-year medical students from West China School of Medicine, Sichuan University, all non-native English speakers; 27 were initially included and 2 were excluded for late submission.
  • Students first wrote an English “mini paper,” then revised it using ChatGPT-3.5 over two weeks; papers were scored before and after by two teachers using blind review (averaged), by ChatGPT-3.5, and by ChatGPT-4.
  • Scoring covered structure, logic, and language, each 0–20 for a 60-point total; analysis used Kruskal-Wallis, paired t-test, and univariate/multivariate regression adjusted for gender, plus a 31-item experience questionnaire.

Limitations

  • The paper states limitations including language barriers and cultural differences, difficulty with non-English languages, lack of human-like creative thinking and contextual understanding, and concerns about authenticity and credibility of ChatGPT-generated information.
  • Participant-reported limitations included difficulty verifying information authenticity (96%), lack of human-like creative thinking (72%), absence of clinical practice insights (52%), and language/cultural differences (40%).
  • Evident from the text: this was a small, single-institution pilot with 25 students, a short two-week intervention, no separate control group, and questionnaire outcomes based on self-report.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s12909-024-05738-y

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Using ChatGPT improved the quality of students’ academic papers. A statistical analysis of the manual scoring showed that the quality of students’ academic papers improved after using ChatGPT for revision in terms of structure, logic, language, and overall score. The results showed statistical significance. ***p < 0.001, ****p < 0.0001
Fig. 1 Using ChatGPT improved the quality of students’ academic papers. A statistical analysis of the manual scoring showed that the quality of students’ academic papers improved after using ChatGPT for revision in terms of structure, logic, language, and overall score. The results showed statistical significance. ***p < 0.001, ****p < 0.0001CC BY · PubMed Central
Fig. 2 Potential of ChatGPT assisting teachers in evaluating papers. The results showed that there was a significant statistical difference between the scoring results of the GPT3.5 and the manual scoring results, both for the unrevised mini papers (left) and the revised mini papers (right) using ChatGPT. However, there was no significant statistical difference between the scoring results of GPT4 and the manual scoring results, which mean that GPT4 might be able to replace teachers in scoring in the future. ns: no significance, *** p < 0.001, **** p < 0.0001
Fig. 2 Potential of ChatGPT assisting teachers in evaluating papers. The results showed that there was a significant statistical difference between the scoring results of the GPT3.5 and the manual scoring results, both for the unrevised mini papers (left) and the revised mini papers (right) using ChatGPT. However, there was no significant statistical difference between the scoring results of GPT4 and the manual scoring results, which mean that GPT4 might be able to replace teachers in scoring in the future. ns: no significance, *** p < 0.001, **** p < 0.0001CC BY · PubMed Central

Verification

Claims the paper makes

5 Valid · 0 Not valid · 18 Not checked · 40 Own results and interpretations

24 more claims

Create a free account to see all 63 claims and to verify the 29 references still open.

See all claims — free account
  • Probably not a substantial claim. 24
  • It may state two separate claims as one. 15
  • The quote only partly states this claim. 3

Create a free account to see these claims.

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?

4 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Show all 39 references

Cited by

See all 104

Metadata

Authors
Li, J., Zong, H., Wu, E., Wu, R., Peng, Z., Zhao, J., Yang, L., Xie, H., & Shen, B.
Affiliations
Sichuan University (CN)
Corresponding author
  • Xie, Hong
  • Shen, Bairong
Venue
BMC Medical Education
Published
2024-07-09
Volume
24
Issue
1
Pages
736-736
ISSN
1472-6920 (ISSN-L)
OpenAlex
W4400475545
Cited by
104
References
34
Citations by year
2026: 41 · 2025: 51 · 2024: 11
FWCI
38.73
Type
journal article
Language
en
Open access
Licence
Locations
  • BMC Medical Education (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • Fundamental Research Funds for the Central Universities (2023SCU12057)
  • National Natural Science Foundation of China (32070671)
Topics
  • Social Sciences › Education › Artificial Intelligence in Education
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
Keywords
ChatGPT, large language models, English academic writing, non-native English speakers, medical students, writing support, AI scoring, automated essay evaluation, writing revision, student feedback
MeSH terms
Artificial Intelligence, China, Education, Medical, Undergraduate, Female, Humans, Language, Male, Students, Medical, Writing

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.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).

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: Exploring the potential of artificial intelligence to enhance the writing of english academic papers by non-native english-speaking medical students - the educational application of ChatGPT. https://app.cochat.ai/papers/10.1186/s12909-024-05738-y
The paper
Li, J., Zong, H., Wu, E., Wu, R., Peng, Z., Zhao, J., Yang, L., Xie, H., & Shen, B. (2024). Exploring the potential of artificial intelligence to enhance the writing of english academic papers by non-native english-speaking medical students - the educational application of ChatGPT. BMC Medical Education. https://doi.org/10.1186/s12909-024-05738-y

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.