Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: Exploring the role of AI in dental education: a mixed-method experimental study from Pakistan

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 Case-based learning (CBL) is a cornerstone of dental education, fostering critical thinking and clinical reasoning. In Pakistan, challenges like low facilitator-to-student ratios and faculty shortages hinder CBL effectiveness. Artificial intelligence (AI) offers potential solutions through scalable, structured facilitation, yet its role in dental CBL remains underexplored. Objective The objective of this study was to evaluate the effectiveness and acceptability of artificial intelligence (AI) as a facilitator in case-based learning (CBL) for dental education. It aimed to compare learning outcomes between AI- and human-facilitated sessions using a randomized crossover design, and to explore students’ perceptions and experiences of AI-mediated learning through focus group discussions. Methodology A sequential mixed-methods design (QUAN → QUAL) was employed with 16 final-year BDS students in a randomized two-period crossover trial. Phase 1 compared AI-facilitated (via ChatGPT-3.5) and human-facilitated CBL using pre- and post-test MCQs, analyzed with Wilcoxon signed-rank and Mann-Whitney U tests. Phase 2 explored student experiences through focus group discussions (FGDs), analyzed thematically using Braun and Clarke’s framework. Ethical approvals were obtained (ERC #2023-6789-12345, IRB-789/LCMD/2023). Results Both AI- and human-facilitated groups showed significant post-test score improvements (p < 0.012), with no significant inter-group differences (p ≥ 0.130). AI excelled in factual recall and structured feedback, while human facilitation enhanced emotional engagement and clinical reasoning. FGDs revealed themes of AI’s consistency but limited emotional depth, with students favoring a hybrid model. Conclusion AI-facilitated CBL yields comparable academic outcomes to human facilitation, offering scalability in resource-limited settings. However, human facilitators remain vital for emotional and adaptive learning. A blended approach, integrating AI’s structure with human mentorship, is recommended for optimal dental education. Keywords: Artificial intelligence, Case-based learning, Dental education, Mixed-methods study, ChatGPT, Health professions education, Pakistan, Educational technology, Clinical reasoning, Student perception

What kind of evidence is this?

Intelligent tutoring & adaptive learning · 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

The study complies with the Helsinki Declaration under the Ethics approval and consent. Ethical clearance was obtained through the Institutional Review Board (IRB) approval letter (Ref: IRB/D-000077/23), along with a No Objection Certificate (NOC) for data collection from students was obtained from the institution (Ref: LCMD/BDS/PO/LET-24/00271), and Aga Khan University Ethical Review Committee (ERC #2023-6789-12345). Written informed consent was obtained individually from each participant prior to their inclusion in the study. The study was conducted at Liaquat College of Medicine and Dentistry (LCMD) in 2024, Karachi, involving final-year BDS students during their clinical rotation in the Oral and Maxillofacial Surgery department. Willing to participate in both the Case-Based Learning (CBL) sessions and the subsequent Focus Group Discussions (FGDs). Students who had prior exposure to AI-facilitated CBL sessions (to avoid bias from previous experience with the intervention) were excluded.

Limitations and uncertainty · source passage

This study involved a small cohort from a single institution, limiting generalizability. The short-term nature of the intervention and the use of MCQs also constrain conclusions about long-term learning, clinical reasoning, or affective development. Even though the AI tool was a working prototype, it might not accurately reflect the range and potential of current AI learning platforms. Furthermore, despite scientific rigor, interpretation bias is a risk associated with the subjective nature of qualitative data analysis. It’s also possible that during group talks, some individuals repressed critical opinions out of social desirability or peer presence. Larger, multi-center studies with longitudinal follow-up that address these limitations in future research may offer more thorough insights into how AI is changing dental education.

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.
  • 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. 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

Tahera Ayub; Muhammad Shahid Shamim; Rahila Ali; Syed Shirjeel Husain. Exploring the role of AI in dental education: a mixed-method experimental study from Pakistan. BMC Medical Education (2026-02-10). https://doi.org/10.1186/s12909-026-08728-4

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.