Truace
Subscribe

Effects of Generative AI-Supported Virtual Reality Dental Skill Training on Learning Performance, Visual Behavior, and Cortical Activation Among Dental Students: Stratified Randomized Controlled Trial

Background The rapid advancement of AI, particularly generative AI (GenAI), is reshaping educational paradigms. However, its utility in preclinical digital medical skills education remains insufficiently explored. Objective This study aims to investigate whether GenAI‑assisted training yields superior performance relative to traditional instruction in virtual reality (VR)-supported preclinical dental skill education. Methods A total of 123 eligible students from a top‑tier Chinese university completed the trial.…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-1444· cite & verify
Effects of Generative AI-Supported Virtual Reality Dental Skill Training on Learning Performance, Visual Behavior, and Cortical Activation Among Dental Students: Stratified Randomized Controlled Trial
"09-8018-23" by NavyMedicine is marked with Public Domain Mark 1.0. To view the terms, visit https://creativecommons.org/publicdomain/mark/1.0/.

In brief

In a stratified randomized controlled trial at a top-tier Chinese university, 123 dental students completed seven days of standardized virtual reality dental skill training. One arm received ChatGPT guidance without human tutoring, while the other received on-site instructor guidance, and the AI arm ended with a higher mean operative score.

The result suggests generative AI could supplement preclinical skills teaching where instructors are scarce. However, the authors describe the wider cognitive, behavioral, and brain-activity findings as exploratory, and the evidence covers only immediate scores, so lasting skill and clinical transfer remain unknown.

Main points

  1. The primary outcome was operative test score: the GenAI group averaged 77.25 versus 67.39 for the teacher-led control group.
  2. The reported effect size was Cohen d=0.70 with a statistically significant intergroup difference.
  3. Participants were stratified by baseline theoretical scores and then randomly assigned within each stratum to the two arms.
  4. Researchers monitored the ChatGPT outputs only for safety and error checking, not to provide tutoring.

The gain

Dental students randomized to ChatGPT-guided VR skill training scored higher on an immediate operative skills test than students taught by an on-site instructor.

The rundown

The trial enrolled students who completed the study, with 62 in the GenAI-assisted group and 61 in the teacher-led control group. Both groups used the same standardized VR-based dental training for 7 days, so the main difference was the source of guidance.

Beyond the skills exam, the researchers collected functional near-infrared spectroscopy recordings, continuous eye-tracking data, visual-spatial ability tests, and questionnaires on self-regulated learning, learning emotions, and engagement.

The authors conclude that these secondary measures pointed toward a link between GenAI exposure and variations in skill-acquisition metrics, and they frame the findings as preliminary insight into integrating GenAI into preclinical dental education. The trial was registered with the Chinese Clinical Trial Registry.

Sources

  1. Peer-reviewedJournal of Medical Internet Research2026-10-01

The debate