Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: Comparison of artificial intelligence assisted training and traditional learning paths in clinical simulation skills training: meta-analysis of randomized controlled trials

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 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. Health-professions learning must be distinguished from K–12 instruction.

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

Abstract Background Artificial intelligence (AI) is increasingly integrated into clinical simulation training, yet its overall effectiveness compared to traditional learning remains unclear. This meta-analysis of randomized controlled trials (RCTs) aimed to evaluate the impact of AI-assisted training versus traditional instruction on clinical skills performance, procedure time, and learner satisfaction. Methods PubMed, Embase, and Web of Science were searched from inception to April 10, 2026. RCTs comparing AI-assisted training (real-time feedback, intelligent tutoring, AI-simulated patients, or image recognition support) with traditional instruction (expert-led, self-directed, or role-play) in simulation-based clinical skills training were included. The primary outcome was clinical skills score. Standardized mean differences (SMD) with 95% confidence intervals (CI) were calculated using fixed- or random-effects models based on heterogeneity. Results Twelve RCTs were included. Overall, significant difference was found between AI-assisted and traditional training for clinical skills score. Subgroup analysis revealed that AI significantly improved surgical and invasive procedural skills, but showed no advantage for clinical assessment and diagnostic skills. In addition, the vision-based deep-learning AI model may have more advantages in medical training than the traditional training method, while the large language model did not demonstrate statistically significant differences with the traditional training method. Procedure time and Operation completion rate did not differ between groups. Learner satisfaction and willingness to recommend the training and stress level of AI assisted training were higher than those of the control group. Conclusion This study shows that AI, especially the vision-based deep-learning, can effectively guide the training of procedural skills. However, for complex cognitive skills like clinical reasoning, AI is best used to replace inefficient peer practice with standardized, high-intensity training. Expert teachers should then focus on advanced clinical judgment, emotional communication, and personalized correction. Overall, AI offers a major opportunity to improve quality and scale up medical simulation education. Its best path is deep integration with traditional teaching—combining their strengths rather than simply replacing teachers. Systematic review registration https://www.crd.york.ac.uk/PROSPERO/view/CRD420261411402. The protocol was registered in advance in PROSPERO online platform as CRD420261411402. Keywords: artificial intelligence, clinical skill, medical education, simulation, traditional learning

What kind of evidence is this?

Intelligent tutoring & adaptive learning · Evidence synthesis

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

We systematically searched PubMed, Embase, and Web of Science for studies published from the inception of each database until April 10, 2026, that met the predefined eligibility criteria. The search strategy incorporated the following keywords: “artificial intelligence” OR “machine learning” OR “deep learning” OR “AI assisted” OR “AI guided” OR “intelligent tutoring,” combined with “simulation” OR “simulator” OR “virtual reality” OR “manikin,” as well as “technical skill” OR “procedural skill” OR “surgical skill” OR “operative performance.” Additionally, we manually screened the reference lists of relevant articles and previous systematic reviews to identify additional potentially eligible studies. Only RCTs were included. The systematic review and meta-analysis were conducted in accordance with the guidelines set forth by the Cochrane Collaboration, and the results were reported in adherence to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) reporting guidelines.

Limitations and uncertainty · source passage

Evidence from this study indicates that in simulation-based training for procedural skills, AI can effectively assume the primary instructional role; in contrast, for training involving complex cognitive skills such as clinical reasoning and assessment, AI should mainly be used to replace inefficient peer practice and provide standardized, high-intensity training, while expert teachers should focus on higher-order clinical judgment, emotional communication, and individualized error correction. Overall, AI presents a major opportunity for quality improvement and large-scale dissemination in medical simulation education, and its optimal application pathway is deep integration with traditional teaching—leveraging their respective strengths—rather than simple substitution.

Design the system before the pilot

Document the learner model, mastery rule, hint sequence and adaptation signal. Compare adaptive routing with the same content in a non-adaptive sequence. Check whether early errors lead to persistent low-expectation pathways.

  • Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
  • Use plan–attempt–check–reflect prompts and compare confidence with actual performance. Keep learner choice and reflection visible.
  • 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. 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

Sihan Che; Huan Zhao; Tianlin Lu; Zhen You. Comparison of artificial intelligence assisted training and traditional learning paths in clinical simulation skills training: meta-analysis of randomized controlled trials. Frontiers in Medicine (2026-08-21). https://doi.org/10.3389/fmed.2026.1915528

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.