Skip to content

Implement AI-assisted PBL within a teacher-led framework with faculty review of AI-generated content

Design · All designs
Evidence · 1 claim (1 mixed) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

The article implements DeepSeek-assisted PBL inside a teacher-led structure: instructors reviewed AI-generated materials before class, joined discussions, and corrected misleading outputs in real time. Students were required to "critically cross-reference AI-generated information against standard ophthalmology textbooks" rather than treat AI answers as authoritative. The authors argue this mitigates risks from LLM hallucinations in clinically complex fields.

Design Implications

Context

Requirements

  • Instructors review AI-generated materials prior to classroom use
  • Students receive training in critically evaluating AI-generated information

Constraints

  • Medical students' skepticism alone is insufficient to guard against AI-generated misinformation, per the article citing prior work

Target Learners

  • fourth-year undergraduate medical students

Learning Goals

  • clinical reasoning in glaucoma
  • critical evaluation of AI-generated medical information

Claims

Examples

-

Key Sources

  • Gu Zheyao, Xi Ting, Zhang Chunyuan. (2026). DeepSeek-assisted problem-based learning for glaucoma education in an undergraduate ophthalmology clerkship: a randomized educational pilot study. Scientific Reports 16, 24184. https://doi.org/10.1038/s41598-026-58447-5
Page metadata
Field Value
type design
id teacher-supervised-ai-pbl-framework
title Implement AI-assisted PBL within a teacher-led framework with faculty review of AI-generated content
description The article implements DeepSeek-assisted PBL inside a teacher-led structure: instructors reviewed AI-generated materials before class, joined discussions, and corrected misleading outputs in real time.
status review
generated by process:settle-candidates on 2026-11-04
trust unverified — no one has confirmed this page's content
sources 1 — gu-zheyao-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.