EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI in the Chair: A Multi‐Centre Study of Doctor AI Answering Orthodontic Patient Questions

Ruijie Zhang, Melody Liu, Olivia Liong, Leo Liu, Simon Guan, Kun Chen, Yu Li, Xianglong Han, Li Mei

Journal of the Royal Society of New Zealand · 2026-04 · 56 (2)

DOI: 10.1002/snz2.70035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Royal Society of New Zealand, online erschienen am 23.03.2026. Verfasst von Ruijie Zhang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To investigate the performance of Doctor AI in answering frequently asked questions (FAQs) and to analyse the advantages and potential limitations.

Methods

Twenty validated FAQs were entered into ChatGPT‐4 and DeepSeek‐v3 to compare the responses generated by the two models and their unmodified responses were assessed by expert panels from English‐, Chinese‐, and bilingual‐speaking institutions. Responses were rated across six dimensions: accuracy, comprehensiveness, detail, relevance, readability, and logic.

Results

Both AI models generated high‐quality answers, scoring above 8/10 across all dimensions. ChatGPT outperformed DeepSeek in relevance (9.01 ± 0.33 vs. 8.69 ± 0.42; p = 0.005), while DeepSeek scored higher in comprehensiveness (9.21 ± 0.31 vs. 8.27 ± 0.65; p < 0.001). No significant differences were observed in accuracy, detail, readability, or logic ( p > 0.100 for all). The word counts generated by ChatGPT (243.20 ± 58.27) and DeepSeek (257.35 ± 44.65) across 20 FAQs were similar ( p = 0.223).

Conclusions

Doctor AI such as ChatGPT and DeepSeek are capable of delivering high‐quality responses to orthodontic FAQs. ChatGPT may provide more relevant answers, while DeepSeek offers greater comprehensiveness. Combining their outputs may improve patient understanding, but AI‐generated information should supplement, not replace, guidance from qualified orthodontic professionals.

Zitieren

APA

Zhang, R., Liu, M., Liong, O., Liu, L., Guan, S., Chen, K., Li, Y., Han, X., & Mei, L. (2026). AI in the Chair: A Multi‐Centre Study of Doctor AI Answering Orthodontic Patient Questions. Journal of the Royal Society of New Zealand, 56(2). https://doi.org/10.1002/snz2.70035

Vancouver

Zhang R, Liu M, Liong O, Liu L, Guan S, Chen K, et al. AI in the Chair: A Multi‐Centre Study of Doctor AI Answering Orthodontic Patient Questions. Journal of the Royal Society of New Zealand. 2026;56(2). doi:10.1002/snz2.70035

BibTeX
@article{Zhang2026,
  author = {Zhang, Ruijie and Liu, Melody and Liong, Olivia and Liu, Leo and Guan, Simon and Chen, Kun and Li, Yu and Han, Xianglong and Mei, Li},
  title = {AI in the Chair: A Multi‐Centre Study of Doctor AI Answering Orthodontic Patient Questions},
  journal = {Journal of the Royal Society of New Zealand},
  year = {2026},
  volume = {56},
  number = {2},
  doi = {10.1002/snz2.70035}
}
Kostenlos starten →