Can ChatGPT‐4.5 Accurately Identify Teeth? A Cross‐Sectional Comparison With Dental Students and Parents

Özdemir M., Cömert H.

INTERNATIONAL JOURNAL OF PAEDIATRIC DENTISTRY, cilt.1, ss.1-8, 2025 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 1
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1111/ipd.70034
  • Dergi Adı: INTERNATIONAL JOURNAL OF PAEDIATRIC DENTISTRY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, CINAHL, EMBASE, MEDLINE
  • Sayfa Sayıları: ss.1-8
  • Lokman Hekim Üniversitesi Adresli: Evet

Özet

ABSTRACT

Background

Differentiating between primary and permanent teeth is a critical component of oral health knowledge, influencing both preventive care and clinical decisions. With the growing use of artificial intelligence (AI) in healthcare and education, its role in supporting learning is of increasing interest.

Aim

This study evaluated the diagnostic accuracy and internal consistency of ChatGPT-4.5 in classifying primary versus permanent teeth using intraoral photographs, compared to senior dental students and parents.

Methods

A comparative cross-sectional study was conducted involving 130 participants (65 senior dental students and 65 parents). ChatGPT-4.5 was also evaluated. An online survey with 16 intraoral images showing multiple teeth was used. Participants classified each tooth as either primary or permanent. Responses were reviewed by two pediatric dentistry experts. Accuracy was analyzed using ANOVA and Tukey's HSD test (p < 0.05). Internal consistency was assessed using Cronbach's alpha.

Results

ChatGPT-4.5 (82.9%) and dental students (82.1%) showed similar accuracy, while parents performed significantly lower (74.8%). A significant difference was found in posterior tooth classification (p = 0.009), favoring students. ChatGPT demonstrated good consistency (α = 0.74).

Conclusion

ChatGPT may be a useful tool in dental education and parental guidance, especially when professional access is limited.