EUVIMEDOpdag EUVIMED
VergleichsstudieOpen access · CC BY-NC 4.0

Development and Comparative Evaluation of a Reinstructed GPT ‐4o Model Specialized in Periodontology

Francesco Fanelli, Muhammad Saleh iD, Pasquale Santamaria iD, Khrystyna Zhurakivska, Luigi Nibali iD, Giuseppe Troiano iD

Journal of Clinical Periodontology · 2025-05 · 52 (5) · 707-716

DOI: 10.1111/jcpe.14101 ↗

At a glance

Vergleichsstudie in Journal of Clinical Periodontology, published online on 2024-12-26. Written by Francesco Fanelli and 5 co-authors. Institution: Department of Clinical and Experimental Medicine, University of Foggia, Foggia, Italy. Major MEDLINE topics: Periodontics, Artificial Intelligence. Cited 25 times so far (Crossref); 45 references. The full text is freely available (open access, CC BY-NC 4.0).

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Artificial intelligence (AI) has the potential to enhance healthcare practices, including periodontology, by improving diagnostics, treatment planning and patient care. This study introduces ‘PerioGPT’, a specialized AI model designed to provide up‐to‐date periodontal knowledge using GPT‐4o and a novel retrieval‐augmented generation (RAG) system.

Methods

PerioGPT was evaluated in two phases. First, its performance was compared against those of five other chatbots using 50 periodontal questions from specialists, followed by a validation with 71 questions from the 2023–2024 ‘In‐Service Examination’ of the American Academy of Periodontology (AAP). The second phase focused on assessing PerioGPT's generative capacity, specifically its ability to create complex and accurate periodontal questions.

Results

PerioGPT outperformed other chatbots, achieving a higher accuracy rate (81.16%) and generating more complex and precise questions with a mean complexity score of 3.81 ± 0.965 and an accuracy score of 4.35 ± 0.898. These results demonstrate PerioGPT's potential as a leading tool for creating reliable clinical queries in periodontology.

Conclusions

This study underscores the transformative potential of AI in periodontology, illustrating that specialized models can offer significant advantages over general language models for both educational and clinical applications. The findings highlight that tailoring AI technologies to specific medical fields may improve performance and relevance.

Subjects

MeSH terms (MEDLINE)

PeriodonticsArtificial IntelligenceHumans

Author keywords

ChatGPTartificial intelligenceclinical decision supportdental AIperiodontologyretrieval‐augmented generation

Authors and institutions

  • Department of Clinical and Experimental Medicine, University of Foggia, Foggia, Italy.
  • Department of Periodontics and Oral Medicine, University of Michigan School of Dentistry, Ann Arbor, Michigan, USA.
  • Centre for Host Microbiome Interactions, Faculty of Dentistry, Oral and Craniofacial Sciences, King's College London, London, UK.
  • Department of Medicine and Surgery, LUM University, Casamassima, Italy.

ORCID profiles: Muhammad Saleh, Pasquale Santamaria, Luigi Nibali, Giuseppe Troiano

Cite

APA

Fanelli, F., Saleh, M., Santamaria, P., Zhurakivska, K., Nibali, L., & Troiano, G. (2025). Development and Comparative Evaluation of a Reinstructed GPT ‐4o Model Specialized in Periodontology. Journal of Clinical Periodontology, 52(5), 707-716. https://doi.org/10.1111/jcpe.14101

Vancouver

Fanelli F, Saleh M, Santamaria P, Zhurakivska K, Nibali L, Troiano G. Development and Comparative Evaluation of a Reinstructed GPT ‐4o Model Specialized in Periodontology. Journal of Clinical Periodontology. 2025;52(5):707-716. doi:10.1111/jcpe.14101

BibTeX
@article{Fanelli2025,
  author = {Fanelli, Francesco and Saleh, Muhammad and Santamaria, Pasquale and Zhurakivska, Khrystyna and Nibali, Luigi and Troiano, Giuseppe},
  title = {Development and Comparative Evaluation of a Reinstructed GPT ‐4o Model Specialized in Periodontology},
  journal = {Journal of Clinical Periodontology},
  year = {2025},
  volume = {52},
  number = {5},
  pages = {707--716},
  doi = {10.1111/jcpe.14101}
}
Start for free →