Agentic education · Learning science

Actionable companion · Cognitive load & attention

From AI evidence to responsible practice: Exploring the Application Capability of ChatGPT as an Instructor in Skills Education for Dental Medical Students: Randomized Controlled Trial

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not findings or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Higher education. Health-professions education findings do not establish effectiveness in K–12 classrooms.

Original authors’ abstract, reproduced under the linked source license:

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

What kind of evidence is this?

Supporting AI learning science · Randomized study reported

Stage: Higher education. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

This study recruited 192 dentistry students (female: n=98, 51.04%; male: n=94, 48.96%) from a first-class university. In China, the dental medicine curriculum during the first 3 years of university focuses on foundational medical sciences and basic clinical medicine, with the aim of progressively developing clinical reasoning skills. In the fourth and fifth years, students transition to systematic instruction encompassing both theoretical knowledge and clinical skills in core dental disciplines. Therefore, participants in the study were in their fourth or fifth years of a 5-year dental education program and had received theoretical knowledge in courses. They ranged in age from 20 to 25 years, with an average age of 22.53 (SD 1.47) years. All participants’ visual acuity was normal or had been corrected to be normal.

Limitations and uncertainty · source passage

First, it is important to recognize that ChatGPT has some inherent limitation types, although ChatGPT is trained on big data, there is a possibility that the training data may be inherently biased or there may be errors in the training process, which leads to the accuracy and reliability of the information provided will also be affected [54]. During the skill learning process, individuals will have their distinctive queries, so for this study checking the accuracy of the answers to the ChatGPT responses was difficult. Second, this study was conducted using the free version of ChatGPT-3.5, and more research is needed to explore whether ChatGPT-4.0 would be more advantageous in aiding skill instruction [55]. Besides, the study compares ChatGPT with a blank control group based on videos, and further research is required to investigate the detailed strengths and weaknesses of ChatGPT in comparison to other methods.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Limit simultaneous instructions and unnecessary dialogue. Compare task performance and a suitable mental-effort measure; easier-feeling work is not automatically better learning.
  • Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.
  • Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Siyu Huang; Chang Wen; Xueying Bai; Sihong Li; Shuining Wang; Xiaoxuan Wang; Dong Yang. Exploring the Application Capability of ChatGPT as an Instructor in Skills Education for Dental Medical Students: Randomized Controlled Trial. Journal of Medical Internet Research (2025-05-27). https://doi.org/10.2196/68538

Companion prepared 2026-11-01. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.