Modern Approaches to the Integration of Artificial Intelligence into the Diagnosis and Screening of Periodontal Diseases

Erbol Ayash, Ismailova Aa, Kenesh Oskonbaevich Dzhusupov, Akerke Chayakova, A. I. Aidarkhanova, А.С. ЗЕЙНОЛДИНА

2026

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.32921/2663-1776-2026-61-1-jhd059
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Periodontal diseases represent a major global health burden and are closely associated with systemic conditions such as cardiovascular diseases and diabetes, making early detection and screening essential priorities in public health. The rapid development of digital dentistry has led to the accumulation of diverse clinical and non-clinical datasets, including intraoral images, radiographic data, salivary biomarkers, and electronic health records. These developments create opportunities for the application of AItechnologies in improving diagnostic accuracy, standardization, and accessibility of periodontal care.This review aims to systematically analyze current approaches to the application of AIin periodontology and to propose a structured framework for integrating AItools into clinical practice and population-based screening programs. A structured literature search was conducted in major databases including PubMed, Scopus, and Google Scholar, covering publications from 2005 to 2025. The review includes studies focusing on image-based analysis, radiographic interpretation, predictive modeling, natural language processing, and telemedicine applications.The results demonstrate that AImodels, particularly deep learning architectures such as convolutional neural networks, show high accuracy in detecting gingival inflammation, dental plaque, and alveolar bone loss. Machine learning methods are also effectively used for risk prediction and stratification based on clinical parameters and biomarkers. Additionally, natural language processing techniques enable automated extraction of diagnostic information from electronic dental records, enhancing data usability and clinical decision-making.Despite promising results, the evidence remains heterogeneous, with common limitations including small sample sizes, lack of external validation, and variability in reference standards. Implementation challenges include data standardization, regulatory requirements, and integration into clinical workflows.In conclusion, AIhas significant potential to transform periodontal diagnostics and screening through improved accuracy, scalability, and accessibility. However, successful implementation requires robust validation, standardized data protocols, and alignment with clinical and ethical guidelines.Keywords:artificial intelligence,periodontitis,screening,panoramic radiography,Cone beam computed tomography,intraoral images,teledentistry.