Title
Machine learning for early detection and risk prediction in peri-implantitis: A review
Authors
Olena Gutierrez1,*, Meryl Ovalles2, Douglas Javier Silva Salas3, Diani Vazquez Garcia4, Ninoska J. Barrios Barrios5 & Valeria Dennis Ramirez Freire6
Affiliation
1Department of Dentistry, American University (UAM), Managua, Nicaragua, America; 2Department of Dentistry, Santa Maria University, Caracas, Venezuela, America; 3Department of Dentistry, University Jose Antonio Paez, Valencia, Venezuela, America; 4Department of Dentistry, University of Medical Sciences of Villa Clara, Santa Clara, Cuba, Caribbean; 5Department of Dentistry, Central University of Venezuela, Caracas, Venezuela, America; 6Department of Dentistry International University of Ecuador (UIDE), Quito, Ecuador, America; *Corresponding author
Olena Gutierrez - E-mail: olenamgutierrez@gmail.com
Meryl Ovalles - E-mail: meryl.ovalles@gmail.com
Douglas Javier Silva Salas - E-mail: douglasjavierss@gmail.com
Diani Vázquez García - E-mail: ddentist00@gmail.com
Ninoska J. Barrios Barrios - E-mail: barriosnino@hotmail.com
Valeria Dennis Ramirez Freire - E-mail: ramirez-valeria@javeriana.edu.co
Article Type
Review
Date
Received July 1, 2026; Revised July 31, 2026; Accepted July 31, 2026, Published July 31, 2026
Abstract
Peri-implantitis causes progressive bone loss around dental implants and arises from interacting microbial, host, behavioral and implant factors. Conventional clinical and radiographic criteria capture this complexity only partially, whereas machine learning can integrate heterogeneous data across early detection, risk stratification and outcome prediction. Convolutional neural networks detect peri-implant bone loss on radiographs with high reported accuracy. Supervised models, such as random forests, combine clinical and patient-level data to estimate individual risk, often outperforming conventional statistics. Thus, data shows that evidence rests largely on small, single-center, retrospective datasets, so machine learning should augment rather than replace clinical judgment until standardized, externally validated models are available.
Keywords
Peri-implantitis, machine learning (ML), deep learning (DL), risk prediction, dental implants
Citation
Gutierrez et al. Bioinformation 22(7): 4449-4451 (2026)
Edited by
P Kangueane
ISSN
0973-2063
Publisher
License
This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.
