Leveraging large language models for patient instructions in dentistry—A systematic review and meta‐analysis
Journal of Prosthodontics · 10.12.2025
DOI: 10.1111/jopr.70068 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Journal of Prosthodontics, online erschienen am 10.12.2025. Verfasst von Rui Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Prosthodontics, Stomatology Center, Peking University Shenzhen Hospital, Shenzhen, Guangdong, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Shenzhen Clinical Research Center for Oral Diseases (20210617170745001), Science and Technology Innovation Commission of Shenzhen, Shenzhen High-Level Hospital Construction Fund.
Abstract (Originalsprache)
Purpose
This systematic review evaluated the application of ChatGPT and other large language models in answering dental patient inquiries and explored their accuracy.
Methods
Following PRISMA guidelines, seven databases, including PubMed, Scopus, and Cochrane, were searched for studies published between November 2022 and June 2024. The review focused on publications addressing large language models’ performance in responding to patients’ questions, with studies evaluated for quality using the modified QUADAS‐2 framework. Data on accuracy were extracted, and a meta‐analysis was conducted. Subgroup and sensitivity analyses were performed to explore variations in performance and ensure robustness.
Results
A total of 25 studies were included, evaluating ChatGPT and other large language models. The pooled accuracy score for all large language models included was 81.87% (95% CI: 77.24%–86.51%), and 69.9% (95% CI: 57.3%–82.6%) of responses were considered clinically acceptable. Subgroup analysis revealed that the accuracy score of responses from ChatGPT‐3.5 was significantly higher than Microsoft Bing but not different from ChatGPT‐4.0 and Google Bard.
Conclusion
ChatGPT and other LLMs are promising alternatives for addressing patient inquiries and providing oral health education. However, challenges remain regarding accuracy, variability, and their ability to handle complex clinical scenarios, and further research is needed.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Prosthodontics, Stomatology Center, Peking University Shenzhen Hospital, Shenzhen, Guangdong, China.
- Department of Dentistry, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, Guangdong, China.
- Second Dental Clinical Division, Peking University School and Hospital of Stomatology, Beijing, China.
- Shenzhen Clinical Research Center for Oral Diseases, Peking University Shenzhen Hospital, Shenzhen, Guangdong Province, China.
- Faculty of Dentistry, Restorative Dental Sciences, The University of Hong Kong, Hong Kong SAR, China.
ORCID-Profile: Rui Zhang, Yu Pan, Edmond Ho Nang Pow
Förderung
- Shenzhen Clinical Research Center for Oral Diseases (20210617170745001)
- Science and Technology Innovation Commission of Shenzhen
- Shenzhen High-Level Hospital Construction Fund
- Peking University Shenzhen Hospital Scientific Research Fund
Zitieren
APA
Zhang, R., Pan, Y., Liu, Y., Deng, Y., & Pow, E. H. N. (2025). Leveraging large language models for patient instructions in dentistry—A systematic review and meta‐analysis. Journal of Prosthodontics. https://doi.org/10.1111/jopr.70068
Vancouver
Zhang R, Pan Y, Liu Y, Deng Y, Pow EHN. Leveraging large language models for patient instructions in dentistry—A systematic review and meta‐analysis. Journal of Prosthodontics. 2025. doi:10.1111/jopr.70068
BibTeX
@article{Zhang2025,
author = {Zhang, Rui and Pan, Yu and Liu, Yushu and Deng, Yinlong and Pow, Edmond Ho Nang},
title = {Leveraging large language models for patient instructions in dentistry—A systematic review and meta‐analysis},
journal = {Journal of Prosthodontics},
year = {2025},
doi = {10.1111/jopr.70068}
}
EUVIMED