Actionable companion · Assessment & reasoning

Learning with agency: Application of the artificial intelligence-assisted World Café teaching model in clinical pharmacology graduate course: a pilot study

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

Read original paper Search paper agent CC 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 learning must be distinguished from K–12 instruction.

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

Abstract Background To investigate the application effectiveness of an artificial intelligence (AI)-assisted World Café teaching model in graduate-level clinical pharmacology course and to evaluate its impact on facilitating students’ acquisition and integration of professional knowledge, developing clinical decision-making competencies, and enriching the teaching-learning experience. Methods A pilot study was conducted involving 56 first-year master’s students enrolled in a clinical pharmacology course at Kunming Medical University. Instruction was organized around a complex comprehensive clinical case of depression. Students participated in a structured five-stage seminar using the World Café format, supported by AI tools to facilitate group discussions and learning. A multi-method assessment strategy was employed, integrating a teaching effectiveness perception questionnaire, a specialized knowledge test, and a comparative analysis of AI-generated versus instructor-generated scores on case discussion records. Results Student evaluations of the teaching model were favorable, with agreement rates exceeding 90% across all items assessing the learning experience. Mean self-rated scores for clinical decision-making abilities each exceeded 4.0 points. Following the intervention, post-test accuracy on depression etiology knowledge improved significantly (median increase from 60.71 to 78.43%; p 0.05). Conclusion The AI-assisted World Café model effectively promotes the assimilation of complex knowledge and fosters higher-order clinical decision-making abilities among clinical pharmacology graduate students. It facilitates a pedagogical shift from passive knowledge transmission toward active capacity building. Furthermore, AI demonstrated reliability and promising utility as a tool for formative assessment, offering empirical support for innovative human-computer collaborative teaching approaches. Keywords: artificial intelligence, clinical decision-making, clinical pharmacology, formative assessment, medical education, teaching reform, World Café

What kind of evidence is this?

Supporting AI learning science · Comparative / pre-post 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

Participants were first-year master’s students enrolled in the clinical pharmacology course during the autumn semester (September 2025 to January 2026) at Kunming Medical University. A total of 56 students were included, with a male-to-female ratio of 20:36 and a median age of 24 years. All participants provided voluntary informed consent. Two questionnaire surveys were administered: the first yielded 56 valid responses, and the second yielded 51. There were no statistically significant differences in gender, age, and interest in learning clinical pharmacology between students participating in the pre-test and post-test (all p > 0.05) (Supplementary material 1).

Limitations and uncertainty · source passage

The lack of a control group precludes definitive attribution of the observed improvements to the AI-assisted World Café model. Therefore, this study is presented as a pilot investigation, and future randomized controlled trials are needed to confirm its effectiveness. Due to the anonymous data collection, individual pre-test and post-test responses could not be matched, limiting the analysis to descriptive statistics; future studies should adopt a paired design with identifiable data to enable more robust inferential evaluation. We acknowledge that social desirability bias constitutes a limitation of the present study. Future investigations should incorporate more objective measures, such as direct observation, standardized patient interactions, or performance-based assessments.

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.

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

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.
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.
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.
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

Ying Guo; Lan Chun Zhang; Qiong Li; Yun Xia Xiong; Wei Yan Hu; Hai Yun Luo; Jian Ping Xie; Hao Fei Yu. Application of the artificial intelligence-assisted World Café teaching model in clinical pharmacology graduate course: a pilot study. Frontiers in Public Health (2026-04-24). https://doi.org/10.3389/fpubh.2026.1805521

Companion prepared 2026-10-30. 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.