Agentic education · Learning science

Actionable companion · Learning design & outcomes

From AI evidence to responsible practice: Using ChatGPT as a Learning Tool in Acupuncture Education: Comparative Study

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): Age / stage not established. Verify the participants, intervention and comparator before applying this study in a new setting.

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

Background ChatGPT (Open AI) is a state-of-the-art artificial intelligence model with potential applications in the medical fields of clinical practice, research, and education. Objective This study aimed to evaluate the potential of ChatGPT as an educational tool in college acupuncture programs, focusing on its ability to support students in learning acupuncture point selection, treatment planning, and decision-making. Methods We collected case studies published in Acupuncture in Medicine between June 2022 and May 2023. Both ChatGPT-3.5 and ChatGPT-4 were used to generate suggestions for acupuncture points based on case presentations. A Wilcoxon signed-rank test was conducted to compare the number of acupuncture points generated by ChatGPT-3.5 and ChatGPT-4, and the overlapping ratio of acupuncture points was calculated. Results Among the 21 case studies, 14 studies were included for analysis. ChatGPT-4 generated significantly more acupuncture points (9.0, SD 1.1) compared to ChatGPT-3.5 (5.6, SD 0.6; P<.001). The overlapping ratios of acupuncture points for ChatGPT-3.5 (0.40, SD 0.28) and ChatGPT-4 (0.34, SD 0.27; P=.67) were not significantly different. Conclusions ChatGPT may be a useful educational tool for acupuncture students, providing valuable insights into personalized treatment plans. However, it cannot fully replace traditional diagnostic methods, and further studies are needed to ensure its safe and effective implementation in acupuncture education.

What kind of evidence is this?

Supporting AI learning science · Design requires full-text appraisal

Stage: Age / stage not established. 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

Eligible studies were collected from case studies published in Acupuncture in Medicine between June 2022 and May 2023. We included case reports that provided detailed descriptions of the case representations and the specific acupuncture points used. Studies were excluded based on the following criteria: (1) insufficient case presentation to inform the selection of acupuncture points; (2) no information on the specific acupuncture points used; (3) the use of other acupuncture-like interventions including moxibustion, cupping therapy, and miniscalpel acupuncture; and (4) studies not for reporting the effect of acupuncture treatment but for other purposes such as adverse events.

Limitations and uncertainty · source passage

Despite the overlap in acupuncture point suggestions from ChatGPT being less than half when compared to those used in the case reports, there are potential beneficial applications for acupuncture practitioners or trainees. First, ChatGPT can serve to encourage critical thinking. Rather than viewing the observed inconsistencies as a limitation, they can be reframed as opportunities for stimulating and enriching discussions. Practitioners or trainees can compare the acupuncture points suggested by ChatGPT with those used in real-world case reports. Delving deeper into the reasons behind these discrepancies can lead to a critical examination of their own understanding and approach to acupuncture point selection, fostering analytical and critical thinking skills. Second, ChatGPT can aid in the exploration of different views. Acupuncture is a practice steeped in history and varies substantially across cultures and regions. With ChatGPT being trained on a diverse range of sources, it can offer insights into these various practices. Such exposure can greatly enhance practitioners’ or trainees’ understanding of the field and help them appreciate its depth and diversity. It also introduces them to a wider range of potential applications of acupuncture, enriching their training experience. Lastly, ChatGPT can facilitate the expansion of case scenarios. Altering parts of a given case presentation, such as symptoms or physical examination findings, can generate different acupuncture point suggestions from ChatGPT. This feature can provide an opportunity to experience a broader range of case scenarios. It can also help acupuncture practitioners or trainees understand how changes in patient presentation can influence the selection of acupuncture points, fostering a more comprehensive and nuanced understanding of case management.

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.

  • Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.

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. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. 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. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. 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

Hyeonhoon Lee. Using ChatGPT as a Learning Tool in Acupuncture Education: Comparative Study. JMIR Medical Education (2023-08-17). https://doi.org/10.2196/47427

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.