EUVIMEDEUVIMED entdecken
Randomisierte kontrollierte Studie

Large language model‐driven Socratic questioning for endodontic case analysis: A randomised controlled trial

Wenjing Liu iD, Xueying Huang, Minkang Zhan, Feihong Ye, Qin Yang, Haiyun Luo iD

International Endodontic Journal · 09.07.2026

DOI: 10.1111/iej.70222 ↗

Kurz gefasst

Randomisierte kontrollierte Studie in der Zeitschrift International Endodontic Journal, online erschienen am 09.07.2026. Verfasst von Wenjing Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Stomatological Hospital, School of Stomatology, Southern Medical University, Guangzhou, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: Basic and Applied Research Foundation of Guangdong Province, Teaching Quality and Teaching Reform Project of Southern Medical University, Medical Science Foundation of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Endodontic education requires structured clinical reasoning practise, but resource constraints often limit the delivery of case‐based instruction. This study developed a large language model (LLM)‐based Socratic questioning system for endodontic case‐analysis training and evaluated its feasibility, short‐term educational outcomes, learner experience, and direct faculty teaching time requirements compared with case‐based learning (CBL).

Methods

Seventy‐nine third‐year dental students who had completed endodontic theory courses were randomised to either an AI‐guided group ( n = 40) or a CBL group ( n = 39). The AI system was built using the FastGPT framework and included three modules: a Socratic questioning engine, a multidimensional case‐analysis scoring system, and an adaptive exercise recommendation module. The CBL group received instructor‐facilitated small‐group teaching from experienced endodontic instructors. Both groups completed a standardised one‐hour supplementary intervention before independent simulated case assessment. The primary outcome was the short‐term total simulated case‐analysis score. Secondary outcomes included domain‐specific scores, learner experience, and direct synchronous faculty teaching time.

Results

Seventy‐seven students completed the study (completion rate 97.47%). Both groups demonstrated significant within‐group improvements from baseline (AI: 78.02 ± 4.93 to 83.97 ± 6.69, p < 0.01; CBL: 78.54 ± 5.32 to 85.13 ± 5.90, p < 0.01). No statistically significant between‐group difference was detected in post‐training total scores (mean difference: 1.16 points; 95% CI: −1.68 to 4.00; p = 0.422) or score improvement (mean difference: 0.64 points; 95% CI: −1.74 to 3.02; p = 0.593). Domain‐specific and learner experience scores showed no statistically significant between‐group differences after correction for multiple comparisons. After deployment, the AI‐guided intervention required substantially less direct synchronous faculty teaching time per student than CBL (0.026 vs. 0.45 h).

Conclusions

This single‐center randomised educational trial indicates that an LLM‐based Socratic questioning system was feasible for standardised endodontic simulated case‐analysis training. After a one‐hour intervention, students' structured case‐analysis performance did not differ significantly from that of the faculty‐led CBL group. The system reduced direct synchronous faculty teaching time after deployment, serving as a valuable supplementary tool to address resource constraints in endodontic education. Future multicentre longitudinal studies are needed to evaluate long‐term knowledge retention and transferability to authentic clinical care.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecase‐based learningclinical reasoningendodontic educationlarge language modelssocratic questioning

Autor:innen und Institutionen

  • Stomatological Hospital, School of Stomatology, Southern Medical University, Guangzhou, China.
  • Guangzhou Zhiyu Feiye Intelligent Technology co., Ltd., Guangzhou, China.

ORCID-Profile: Wenjing Liu, Haiyun Luo

Förderung

  • Basic and Applied Research Foundation of Guangdong Province
  • Teaching Quality and Teaching Reform Project of Southern Medical University
  • Medical Science Foundation of Guangdong Province

Zitieren

APA

Liu, W., Huang, X., Zhan, M., Ye, F., Yang, Q., & Luo, H. (2026). Large language model‐driven Socratic questioning for endodontic case analysis: A randomised controlled trial. International Endodontic Journal. https://doi.org/10.1111/iej.70222

Vancouver

Liu W, Huang X, Zhan M, Ye F, Yang Q, Luo H. Large language model‐driven Socratic questioning for endodontic case analysis: A randomised controlled trial. International Endodontic Journal. 2026. doi:10.1111/iej.70222

BibTeX
@article{Liu2026,
  author = {Liu, Wenjing and Huang, Xueying and Zhan, Minkang and Ye, Feihong and Yang, Qin and Luo, Haiyun},
  title = {Large language model‐driven Socratic questioning for endodontic case analysis: A randomised controlled trial},
  journal = {International Endodontic Journal},
  year = {2026},
  doi = {10.1111/iej.70222}
}
Kostenlos starten →