EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access · CC BY 4.0

Endodontic diagnostics training in undergraduate dental education: An observational pilot study on AI‐driven virtual patient e‐learning

Marian Prinz, Edgar Schäfer iD, Sebastian Bürklein iD, David Donnermeyer iD

International Endodontic Journal · 2026-06 · 59 (6) · 1145-1159

DOI: 10.1111/iej.14277 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift International Endodontic Journal, online erschienen am 22.07.2025. Verfasst von Marian Prinz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Periodontology and Operative Dentistry, University of Münster, Münster, Germany. Hauptthemen laut MEDLINE: Education, Dental, Endodontics, Artificial Intelligence, Computer-Assisted Instruction. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

To develop and evaluate an e‐learning tool utilizing a generative pre‐trained transformer (GPT), a form of artificial intelligence (AI), to allow for realistic conversation on virtual patients when undergoing training on how to diagnose diseases of endodontic origin, and to evaluate improvements in self‐perceived skills. Methodology A web app consisting of three components [website for user access, database server with patient case information, GPT‐4‐turbo model (OpenAI)] was designed to serve as the e‐learning platform. Undergraduate students from 4th and 5th year at the dental school of the University of Münster, Germany, were asked to solve eight cases of virtual patients presenting with pain from endodontic or periodontal origin. Before, a questionnaire applying a 5‐point Likert scale served to evaluate the current self‐perceived state regarding the education, experience and skills in endodontic diagnostics and emergency treatment. After a 3‐month timeframe of working with the programme individually, the students were asked to answer a second questionnaire which focused on their experience and self‐perceived skills improvement after using the training software.

Results

Ninety‐two students participated in the first questionnaire and 72 students finished the second questionnaire, resulting in a drop‐out rate of 21.7%. Students in the 5th‐year reported more experience in dealing with emergency patients. Initially, both cohorts mainly did not feel confident to perform endodontic diagnostics independently. The evaluation of confidence to perform endodontic diagnostics independently, both by 4th‐ and 5th‐year students, seemed improved after the training on the e‐learning tool. The tool was recommended to be available for endodontic education by 72.2% of the students, who strongly agreed to such a statement. 76.4% of the participants strongly agreed to recommend the use of the tool to other students.

Conclusions

AI‐based interactive e‐learning programmes allowing for complex conversational patient encounters present a possibility to improve diagnostic and interactive skills of undergraduate students.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Education, DentalEndodonticsArtificial IntelligenceComputer-Assisted InstructionHumansPilot ProjectsSurveys and QuestionnairesStudents, DentalMaleClinical CompetenceFemaleGermany

Stichwörter der Autor:innen

artificial intelligence (AI)dental educationendodontic diagnosticse‐learninggenerative pre‐trained transformer (GPT)virtual patient

Autor:innen und Institutionen

  • Department of Periodontology and Operative Dentistry, University of Münster, Münster, Germany.
  • Central Interdisciplinary Ambulance in the School of Dentistry, University of Münster, Münster, Germany.
  • Department of Restorative, Preventive and Pediatric Dentistry, School of Dental Medicine, University of Bern, Bern, Switzerland.

ORCID-Profile: Edgar Schäfer, Sebastian Bürklein, David Donnermeyer

Zitieren

APA

Prinz, M., Schäfer, E., Bürklein, S., & Donnermeyer, D. (2026). Endodontic diagnostics training in undergraduate dental education: An observational pilot study on AI‐driven virtual patient e‐learning. International Endodontic Journal, 59(6), 1145-1159. https://doi.org/10.1111/iej.14277

Vancouver

Prinz M, Schäfer E, Bürklein S, Donnermeyer D. Endodontic diagnostics training in undergraduate dental education: An observational pilot study on AI‐driven virtual patient e‐learning. International Endodontic Journal. 2026;59(6):1145-1159. doi:10.1111/iej.14277

BibTeX
@article{Prinz2026,
  author = {Prinz, Marian and Schäfer, Edgar and Bürklein, Sebastian and Donnermeyer, David},
  title = {Endodontic diagnostics training in undergraduate dental education: An observational pilot study on AI‐driven virtual patient e‐learning},
  journal = {International Endodontic Journal},
  year = {2026},
  volume = {59},
  number = {6},
  pages = {1145--1159},
  doi = {10.1111/iej.14277}
}
Kostenlos starten →