Journal of Clinical Pediatric Dentistry. 2026; 50(3): 301-301. doi: 10.22514/jocpd.2026.085
Corrections

Correction: Evaluating the efficacy of large language models in providing information for parental inquiries regarding primary care of pediatric oral and dental health

Ceren Sağlam1, Aslı Aşık2,*,, Elif Kuru3, Handan Çelik4, Nazan Ersin1, Arzu Aykut Yetkiner1, Dilşah Çoğulu1

1Department of Pediatric Dentistry, Faculty of Dentistry, Ege University, 35040 Izmir, Turkey

2Department of Pediatric Dentistry, Faculty of Dentistry, Izmir Tınaztepe University, 35400 Izmir, Turkey

3Department of Pediatric Dentistry, Faculty of Dentistry, Uşak University, 64200 Uşak, Turkey

4Department of Pediatric Dentistry, Faculty of Dentistry, Izmir Demokrasi University, 35140 Izmir, Turkey

*Corresponding Author(s):asli.asik@tinaztepe.edu.tr (Aslı Aşık)

History Submitted: 13 March 2026 | Accepted: 16 March 2026 | Published: 03 May 2026
Copyright:  ©2026 The Author(s). Published by MRE Press.
This is an open access article under the CC BY 4.0 license (https://creativecommons.org/licenses/by/4.0/).

Collapse table of contents

Abstract

No abstract available.

Keywords:None.
PDF(312.9 kB)|EndNote (RIS)|BibTeX|RefMan|RefWorks

Cite this article

Ceren Sağlam, Aslı Aşık, Elif Kuru, Handan Çelik, Nazan Ersin, Arzu Aykut Yetkiner, Dilşah Çoğulu. Correction: Evaluating the efficacy of large language models in providing information for parental inquiries regarding primary care of pediatric oral and dental health. Journal of Clinical Pediatric Dentistry. 2026; 50(3): 301-301. doi: 10.22514/jocpd.2026.085

Error in Fig. 1

In the article titled “Evaluating the efficacy of large language models in providing information for parental inquiries regarding primary care of pediatric oral and dental health” [1], published in March 2026, there is an error in the rendering of Fig. 1.

The correct Fig. 1 is as follows:

Heatmap illustrating the accuracy scores (%) of four LLMs. Kruskal-Wallis test + Dunn’s post hoc test (Bonferroni correction), (ChatGPT 4.0, Google Gemini, Microsoft Copilot, and DeepSeek-R1) across three major domains: Tooth eruption/Dental visits/Treatment needs (4 questions), Oral health (11 questions), and Diet (5 questions). Darker shades indicate higher accuracy percentages. Full numerical data are provided in Supplementary Table 1.

Fig. 1.Heatmap illustrating the accuracy scores (%) of four LLMs. Kruskal-Wallis test + Dunn’s post hoc test (Bonferroni correction), (ChatGPT 4.0, Google Gemini, Microsoft Copilot, and DeepSeek-R1) across three major domains: Tooth eruption/Dental visits/Treatment needs (4 questions), Oral health (11 questions), and Diet (5 questions). Darker shades indicate higher accuracy percentages. Full numerical data are provided in Supplementary Table 1.

This correction addresses a formatting/layout issue during proofreading and does not affect the scientific content, data, results, prevalence findings, or conclusions of the article.

References

Sağlam C, Aşık A, Kuru E, Çelik H, Ersin N, Aykut Yetkiner A, et al. Evaluating the efficacy of large language models in providing information for parental inquiries regarding primary care of pediatric oral and dental health. Journal of Clinical Pediatric Dentistry. 2026; 50: 132–141.

[Google Scholar]