A Systematic Review and Meta-Analysis for Dental Implant Recognition Using Machine Learning: Models, Diagnostic Performance, and Clinical Evidence

Hinostroza-De-La-Peña C.; Arroyo-Pérez C.; Astete-Llerena J.; Del Carpio Delgado F.; Nolasco Valenzuela L.E.; Amayo-Gamboa F.; López-Ramírez B.C. · Computacion y Sistemas (2026) · DOI: 10.13053/cys-30-1-6347

Resumen

Dental implant recognition using Machine Learning has gained increasing relevance in digital dentistry; however, the rapid expansion of publications and the heterogeneity of approaches, metrics, and validation contexts make it difficult to accurately identify which strategies demonstrate greater robustness and what gaps persist in the literature. In this context, the objective of this study was to analyze the state of the art of Machine Learning applied to dental implant recognition, with emphasis on its methodological approaches, scientific collaboration patterns, conceptual definitions, and dominant thematic lines. To this end, a systematic review and meta-analysis were conducted based on an adaptation of the Kitchenham approach and the PRISMA guidelines, using structured search equations in Scopus, PubMed, IEEE Xplore, Cochrane Library, and Wiley Online Library; after the screening, eligibility, and quality assessment processes, 65 primary studies were included. The results show the predominance of Transfer Learning and Supervised Learning as central methodological strategies, a co-authorship network fragmented into relatively closed communities, a conceptual concentration on implant detection and classification and surgical planning, and a thematic map in which AI Dentistry appears as a specialized core, while most topics remain in a marginal condition. In conclusion, the field exhibits relevant technical advances, but still requires greater methodological standardization, external validation, and conceptual articulation to consolidate its clinical applicability.

Instituciones: Universidad Nacional Mayor de San Marcos; Universidad Nacional de Trujillo; Universidad San Ignacio de Loyola; Universidad Tecnológica del Perú; Universidad Nacional de Moquegua