ARTIFICIAL INTELLIGENCE IN DENTAL IMPLANTOLOGY:A SCOPING REVIEW

Background: Artificial intelligence (AI) is rapidly transforming dental implantology by introducing advanced approaches for diagnosis, treatment planning, surgical guidance, and outcome prediction. The integration of AI with cone-beam computed tomography (CBCT), intraoral scanning, digital workflows, and computer-assisted implant surgery has created new opportunities for personalized and precision-based implant treatment. However, the current evidence remains heterogeneous, and a comprehensive mapping of AI applications in implant dentistry is needed. Objective: This scoping review aimed to map the current evidence regarding the applications of artificial intelligence in dental implantology, with particular emphasis on diagnostic performance, digital implant planning, surgical assistance, prediction models, and future clinical perspectives. Methods:A scoping review was conducted according to the methodological framework of the Joanna Briggs Institute (JBI) and reported following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines. A comprehensive literature search was performed in PubMed, Scopus, Web of Science, ScienceDirect, and Google Scholar. Studies investigating AI-based technologies applied to dental implantology were considered eligible. Data were extracted regarding study characteristics, AI algorithms, clinical applications, imaging modalities, outcomes, and reported limitations. Results:The available evidence indicates that AI applications in implant dentistry are primarily focused on automated radiographic analysis, anatomical structure recognition, implant position optimization, guided surgery, and prediction of clinical outcomes. Deep learning algorithms, particularly convolutional neural networks (CNNs), have demonstrated promising performance in CBCT-based anatomical identification and treatment planning. Emerging applications include AI-assisted prosthetic design, peri-implant disease prediction, and integration with three-dimensional digital workflows. Nevertheless, limitations related to dataset quality, external validation, standardization, and clinical implementation remain. Conclusion:Artificial intelligence represents a promising technological advancement in dental implantology, supporting a transition toward personalized, data-driven, and precision-based implant treatment. Further prospective clinical studies and standardized validation protocols are required before widespread routine application of AI systems in implant practice.