International dental journal最新文献

Aim: This study aimed to examine the global burden, trends, and socioeconomic inequalities associated with oral disorders in adults aged 65 years and older from 1990 to 2021, and to project future trends to inform targeted public health strategies.

Methods: Using data from the Global Burden of Disease Study 2021, we examined age-standardized DALY rates for oral conditions. Analytical methods included Joinpoint regression (for trend analysis), the slope index of inequality and concentration index(for inequality assessment), frontier analysis (for efficiency assessment), and autoregressive integrated moving average modelling (to project trends through 2035).

Conclusion: Absolute case counts for all oral diseases increased significantly (by 112%-142%) from 1990 to 2021. Although age-standardized disability rates declined for edentulism, dental caries, and other oral disorders, they remained stagnant for periodontal diseases and lip/oral cavity cancer. Socioeconomic disparities persisted or even widened, with disease-specific patterns. Projections to 2035 indicate a growing burden among older populations, highlighting an urgent need for equitable and targeted public health interventions.

Introduction and aims: Artificial intelligence (AI) has rapidly transformed dental imaging by enabling automated detection, diagnosis, and analysis of various dental conditions. However, a comprehensive synthesis of United States Food and Drug Administration (FDA)-cleared, clinically validated AI solutions in dental imaging remains limited. This review aims to catalog all standalone, cloud-based dental AI platforms with FDA clearance, highlighting their clinical applications, performance outcomes, and supporting evidence to guide evidence-based integration.

Methods: A two-phase systematic search was conducted. In the first phase, searches of U.S. FDA regulatory databases (510[k], De Novo, and PMA) were performed through July 2025 to identify standalone, cloud-based dental AI imaging devices cleared or authorized for autonomous or semi-autonomous analysis. In the second phase, PubMed, Web of Science, and Google Scholar were systematically searched to retrieve studies assessing the performance or clinical utility of the identified platforms. Two independent reviewers performed data screening and extraction, with discrepancies resolved by a third reviewer.

Results: Thirteen companies were identified as offering twenty-nine FDA-cleared AI products for dental imaging. These solutions addressed diverse clinical tasks, including caries detection, periodontal disease assessment, cephalometric analysis, multi-pathology diagnostics, automated dental charting, and three-dimensional segmentation. Performance outcomes reported by the FDA demonstrated high accuracy, sensitivity, and specificity across most platforms, particularly for caries detection, periodontal disease measurement, and cephalometric analysis. Among these, Relu Creator and WebCeph were supported by the highest number of peer-reviewed publications, whereas several newer platforms lacked independent clinical validation.

Conclusion: Standalone, FDA-cleared AI platforms represent a paradigm shift in dental imaging, providing clinically validated tools for diagnosis, treatment planning, and patient monitoring. By systematically cataloging these solutions, this review delivers an evidence-based reference for clinicians and researchers, supporting informed adoption and identifying areas for future investigation.