APPLICATION OF ARTIFICIAL INTELLIGENCE IN DIAGNOSTIC, PREVENTIVE, AND THERAPEUTIC PRACTICES WITHIN DENTISTRY A SYSTEMATIC REVIEW
Main Article Content
Abstract
Background: The integration of artificial intelligence (AI) into dentistry presents a paradigm shift with the potential to significantly enhance diagnostic accuracy, preventive strategies, and therapeutic workflows. Despite a growing body of primary research, a comprehensive synthesis of evidence across the entire spectrum of dental care is lacking, necessitating a systematic review to consolidate findings and evaluate the clinical readiness of these technologies.
Objective: This systematic review aimed to evaluate the evidence on how AI enhances diagnostic, preventive, and therapeutic practices within dentistry.
Methods A systematic search was conducted in PubMed/MEDLINE, Scopus, Web of Science, and the Cochrane Library for studies published between 2014 and 2024. Eligible studies included diagnostic accuracy studies, randomized controlled trials, and observational studies that evaluated AI applications in clinical dentistry against a conventional comparator. Study selection, data extraction, and risk of bias assessment (using QUADAS-2 and RoB 2 tools) were performed in duplicate. A narrative synthesis was conducted due to methodological heterogeneity.
Results: From 1,842 identified records, 32 studies were included. The findings demonstrated that AI models, particularly deep learning algorithms, achieved high diagnostic performance (sensitivity 0.79-0.92, specificity 0.83-0.95) in detecting pathologies such as dental caries and periapical lesions on radiographs, often matching expert clinician performance. Limited evidence on therapeutic applications showed AI could significantly streamline workflows, such as prosthetic design, and improve preventive patient coaching.
Conclusion: AI shows considerable promise as a tool to augment dental practice, primarily by enhancing diagnostic precision and operational efficiency. However, the current evidence is largely based on retrospective studies, highlighting a need for more robust, prospective clinical trials to validate efficacy in real-world settings and assess long-term impacts on patient care.
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.