Actionable companion · Retention & transfer

Learning with agency: AI-Generated Microlearning for Plastic Surgery Residency: Single-Arm Pre-Post Feasibility 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): Age / stage not established. Verify the participant population and task before transferring the findings.

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

Abstract Background Surgical residency training faces mounting pressure from expanding subspecialty knowledge requirements alongside compressed learning opportunities. Microlearning, defined as brief, focused educational episodes, offers a pedagogically sound approach suited to fragmented clinical schedules, while large language models present capabilities for scalable content generation. However, the feasibility, quality, and educational value of large language model–generated microlearning in surgical training remain unexplored. Objective This study aimed to assess the feasibility and acceptability of artificial intelligence (AI)-generated microlearning modules among plastic surgery residents, evaluate content quality through systematic faculty evaluation, and generate preliminary effect size estimates for self-perceived knowledge and confidence changes. Methods A single-arm pilot feasibility study with a pre-post design was conducted at an academic plastic surgery residency program (N=11 residents) over 12 weeks. Six modules covering core subspecialties were developed using Google Gemini 2.5 Pro. From 60 AI-generated multiple-choice questions, 42 were selected following independent evaluation by 2 board-certified plastic surgeons using a 5-dimension rubric (accuracy, relevance, clarity, pedagogical value, and safety). Modules were released biweekly via Google Forms. Outcomes included retention, acceptability (7-point Likert scales), faculty evaluation ratings, item-level psychometrics, and pre-post changes in self-perceived knowledge and confidence. Composite scores were calculated as the mean change across all 6 subspecialty topics. Wilcoxon signed-rank tests served as the primary analysis for matched pairs (n=9). Analyses were conducted using Python 3.11. Results All 11 residents completed postassessments. Acceptability was high across all 6 subitems (all medians ≥5 out of 7). Faculty evaluation confirmed high content quality (mean quality index 4.68/5); interrater reliability was poor (intraclass correlation coefficient (3,1)=0.231). Among 9 matched pairs, composite confidence improved significantly (median change 0.33; d=0.65; P=.047), while composite knowledge showed a medium effect (d=0.71; P=.09). Topic-specific gains were largest where baseline was lowest: hand surgery knowledge (d=1.48; P=.02) and confidence (d=1.41; P=.02). Resource use and sense-of-community measures remained stable. Conclusions AI-generated microlearning modules are feasible and acceptable for plastic surgery residency education. Faculty-evaluated content achieved high quality ratings (mean 4.68/5), and residents showed strong engagement with preliminary improvements in self-perceived confidence. The intervention was integrated into existing learning ecosystems without disrupting traditional resources or peer dynamics. These findings provide effect size estimates to support the design of adequately powered randomized trials. Keywords: artificial intelligence, graduate medical education, plastic surgery, microlearning, large language models, feasibility studies, multiple-choice questions

What kind of evidence is this?

Supporting AI learning science · Randomized study reported

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

A single-arm pilot feasibility study with a pre-post design was conducted at the Department of Plastic and Reconstructive Surgery, University Hospital BG Bergmannsheil Bochum, an academic medical center with an accredited plastic surgery residency program in Bochum, Germany. The study spanned a 12-week intervention period from July through September 2025. Reporting was guided by relevant elements of the CONSORT (Consolidated Standards of Reporting Trials) extension for pilot and feasibility studies [24]. The intervention followed a rolling production model in which faculty evaluation and selection of subsequent modules occurred concurrently with the biweekly delivery of active modules to residents, ensuring continuous content delivery throughout the study period (Figure 1A).

Limitations and uncertainty · source passage

This study has several methodological strengths. The rolling production model enabled continuous content delivery while maintaining rigorous faculty evaluation, demonstrating a workflow for AI-assisted curriculum development. The standardized prompting strategy and comprehensive evaluation rubric provide reproducible frameworks for other programs seeking to implement similar interventions. The multidimensional assessment captured not only efficacy outcomes but also feasibility, acceptability, and ecosystem integration metrics essential for translating pilot findings into sustainable educational practice.

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.

Include a delayed assessment and an unfamiliar transfer problem without AI. Immediate supported performance cannot establish durable 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

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. 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.
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. 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

Marius Drysch; Sonja Verena Schmidt; Felix Reinkemeier; Flemming Puscz; Alexander Fiedler; Maria Fueth; Marcus Lehnhardt; Alexander Sogorski; Christoph Wallner. AI-Generated Microlearning for Plastic Surgery Residency: Single-Arm Pre-Post Feasibility Study. JMIR Medical Education (2026-07-14). https://doi.org/10.2196/88695

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.