Access to preventive dental care remains a critical global public health challenge: approximately 3.5 billion people worldwide suffer from oral diseases, yet systemic barriers, including geographic isolation, financial constraints, workforce shortages, and low oral health literacy, prevent timely preventive intervention. The purpose of this study is to analyze the primary access barriers to preventive dental care and to propose a scalable, AI-based screening model capable of addressing these barriers across diverse socioeconomic and geographic contexts. The methodology combines a systematic literature review of peer-reviewed publications from Scopus, PubMed, and IEEE databases with comparative case analysis of existing AI deployment scenarios in low- and high-income countries. The results demonstrate that AI-powered triage systems can reduce diagnostic delays by up to 73%, lower first-contact costs, and extend screening reach to underserved populations through mobile-first architectures. The proposed model integrates convolutional neural networks, natural language processing, and risk stratification logic into a three-tier workflow. The findings are relevant for public health policymakers, digital health developers, and dental professionals seeking evidence-based strategies to advance equitable preventive oral healthcare at scale.