Cited by 33Artificial Intelligence in Healthcare and EducationInnovations in Medical EducationSurgical Simulation and Training

Exploring the Application Capability of ChatGPT as an Instructor in Skills Education for Dental Medical Students: Randomized Controlled Trial

Open access
Huang, Siyu, Wen, Chang, Bai, Xueying, Li, Sihong, Wang, Shuining, Wang, Xiaoxuan, Yang, Dong·2025·Journal of Medical Internet Research

Published version of a preprint

Abstract

BACKGROUND: Clinical operative skills training is a critical component of preclinical education for dental students. Although technology-assisted instruction, such as virtual reality and simulators, is increasingly being integrated, direct guidance from instructors remains the cornerstone of skill development. ChatGPT, an advanced conversational artificial intelligence model developed by OpenAI, is gradually being used in medical education. OBJECTIVE: This study aimed to compare the effects of ChatGPT-assisted skill learning on performance, cognitive load, self-efficacy, learning motivation, and spatial ability, with the aim of evaluating the potential of ChatGPT in clinical operative skills education. METHODS: In this study, 187 undergraduate dental students recruited from a first-class university in China were randomly divided into a ChatGPT group and a blank control group. Among them, the control group used videos for skill acquisition, and the ChatGPT group used ChatGPT in addition to the videos. After 1 week of intervention, skills were tested using desktop virtual reality, and cognitive load was measured by recording changes in pupil diameter with an eye tracker. In addition, a spatial ability test was administered to analyze the effect of ChatGPT on those with different spatial abilities. Finally, a questionnaire was also used to assess cognitive load and self-efficacy during the learning process. RESULTS: A total of 192 dental undergraduates from a top-tier Chinese university were initially recruited for the experiment by October 25, 2024. Following eye-tracking calibration procedures, 5 participants were excluded, resulting in 187 eligible students successfully completing the experimental protocol by November 2, 2024. Following a short-term intervention administered through randomized allocation, superior performance (ChatGPT group: mean 73.12, SD 10.06; control group: mean 65.54, SD 12.48; P<.001) was observed among participants in the ChatGPT group, along with higher levels of self-efficacy (P=.04) and learning motivation (P=.02). In addition, cognitive load was lower in the ChatGPT group according to eye-tracking measures (ChatGPT group: mean 0.137, SD 0.036; control group: mean 0.312, SD 0.032; P<.001). The analysis of the learning performance of participants with different spatial abilities in the 2 modalities showed that compared to the learners with high spatial abilities (ChatGPT group: mean 76.58, SD 9.23; control group: mean 73.89, SD 11.75; P=.22), those with low spatial abilities (ChatGPT group: mean 70.20, SD 10.71; control group: mean 55.41, SD 13.31; P<.001) were more positively influenced by ChatGPT. CONCLUSIONS: ChatGPT has performed outstandingly in assisting dental skill learning, and the study supports the integration of ChatGPT into skills teaching and provides new ideas for modernizing skill teaching. TRIAL REGISTRATION: ClinicalTrials.gov NCT06942130;https://clinicaltrials.gov/study/NCT06942130.

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.

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

Integrity signals

Registry

Crossref · 10.2196/68538

Cites

54 of 54 references verified0 citation errors · 0 not checkable

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.

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

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?

  • In Huang et al. (2025), ChatGPT-3.5 added to instructional videos raised unassisted virtual-reality skill assessment scores by 0.67 SD.

    “The ChatGPT group scored 0.67 SD higher on an unassisted virtual-reality skill assessment.”

    From Experimental Evidence on the Learning Impact of Generative AI (2026) · cites this paper as Huang et al. (2025)

Self-check

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

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 55 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Authors
Huang, S., Wen, C., Bai, X., Li, S., Wang, S., Wang, X., & Yang, D.
Affiliations
Wuhan University (CN)
Venue
Journal of Medical Internet Research
Published
2025-05-27
Volume
27
Pages
e68538
ISSN
1438-8871 (ISSN-L)
OpenAlex
W4410775225
Cited by
33
References
55
Citations by year
2026: 26 · 2025: 7
FWCI
7.94
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Journal of Medical Internet Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Health Commission of Hubei Province
  • Natural Science Foundation of Hubei Province (2021CFB466)
  • Wuhan University
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Innovations in Medical Education
  • Health Sciences › Medicine › Surgery › Surgical Simulation and Training
Keywords
ChatGPT, large language models, dental education, cognitive load, self-efficacy, student motivation, spatial ability, eye tracking, virtual reality simulation, artificial intelligence in medical education, video-based instruction, skill performance, pupil size, undergraduate dental students
MeSH terms
Virtual Reality, Generative Artificial Intelligence, Adult, Artificial Intelligence, China, Clinical Competence, Education, Dental, Female, Humans, Male, Students, Dental, Self Efficacy, Young Adult

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