Digital dentistry has rapidly evolved through the integration of advanced imaging, computer-aided design (CAD) and manufacturing (CAM), and data-driven workflows, creating opportunities for artificial intelligence (AI)-enabled clinical support across multiple dental domains. Although numerous studies have explored AI in isolated diagnostic or restorative applications, a comprehensive synthesis spanning diagnosis, treatment planning, and prosthodontics remains limited, leaving uncertainty regarding the overall scope and maturity of current evidence. This systematic review aimed to consolidate and evaluate published research on AI applications within digital dentistry, with emphasis on data modalities, algorithmic tasks, and reported clinical outcomes. A Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-compliant search was conducted across PubMed/MEDLINE, Scopus, Web of Science, IEEE Xplore, and Google Scholar for studies published between 2015 and 2025. Eligible peer-reviewed studies reporting quantitative outcomes were systematically screened, extracted, and synthesized descriptively. The review identified a predominance of image-based diagnostic applications, particularly for caries detection and anatomical segmentation, with fewer studies addressing treatment planning and prosthodontic workflows. Deep learning models were most frequently employed, and reported outcomes commonly focused on accuracy, segmentation performance, and spatial agreement. The findings indicate that AI is increasingly embedded within digital dental workflows, primarily as a decision support tool rather than a standalone system. This synthesis clarifies current research trends, highlights the relative maturity of diagnostic applications, and underscores the expanding but uneven integration of artificial intelligence across interconnected stages of digital dentistry, providing a consolidated evidence base to inform clinicians and researchers.
Karvekar et al. (Fri,) studied this question.