ARTIFICIAL INTELLIGENCE IN AUTOMATED INTERPRETATION OF DENTAL RADIOGRAPHS: A SYSTEMATIC REVIEW

Abstract

Background: Artificial intelligence (AI) is increasingly being integrated into dental diagnostics, particularly in the interpretation of radiographic images. Despite promising developments, current evidence on the diagnostic performance, error rates, and time-efficiency of AI algorithms in dental radiology remains fragmented. This creates uncertainty about the clinical utility and reliability of AI applications in real-world dental practice.

Objective: This systematic review aimed to evaluate the diagnostic accuracy, error rate, and time-efficiency of AI algorithms in analyzing dental radiographs compared to traditional clinician-led interpretation.

Methods: A systematic review was conducted following PRISMA guidelines. Databases searched included PubMed, Scopus, Web of Science, and the Cochrane Library from January 2019 to May 2024. Eligible studies included observational and experimental designs that compared AI-based radiographic interpretation with human performance, focusing on diagnostic accuracy, interpretation time, and error rates. Data extraction and risk of bias assessments were performed independently by two reviewers using standardized tools (Cochrane RoB 2.0 and Newcastle-Ottawa Scale). A narrative synthesis was conducted due to heterogeneity in study designs and outcomes.

Results: Eight studies involving various AI models and a total of over 25,000 dental radiographic images were included. AI algorithms demonstrated high diagnostic accuracy (ranging from 80.2% to 96.5%), reduced error rates, and significantly improved time-efficiency in most studies (p < 0.05). The performance of AI systems was comparable to or better than experienced clinicians across multiple radiographic modalities, including bitewing, panoramic, and periapical images.

Conclusion: AI shows strong potential in supporting dental professionals by enhancing diagnostic accuracy and efficiency in radiographic interpretation. However, variability in methodologies and limited external validation call for further large-scale, prospective studies to confirm its generalizability and clinical integration.