Related Experiment Video
Updated: Jan 12, 2026
A Novel Approach to Monitoring Graft Neovascularization in the Human Gingiva
Published on: January 12, 2019
Comparative Evaluation of Gingival Phenotype Assessment with Machine Learning Software and the Conventional Methods-A
Supriya S Kaule1, Surekha R Rathod1, Vibha R Bora2
1Department of Periodontics and Implant Dentistry, Ranjeet Deshmukh Dental College and Research Centre, Nagpur, Maharashtra, India.
Background:
Given these limitations, this study aims to evaluate the effectiveness and accuracy of machine learning (ML) software as a noninvasive technique for assessing gingival phenotype, compared to conventional methods like probe transparency and transgingival probing.
Methods:
A total of 382 periodontally healthy patients were recruited for this study. Gingival phenotype assessment was performed in the upper incisor region using three methods: probe transparency, transgingival probing, and ML software.
Results:
Gingival phenotype assessment by all the three methods, namely, probe transparency, transgingival probing, and ML software methods, showed no statistically significant difference, indicating that the three methods are equivalent. Males had a higher prevalence of the thick gingival phenotype in comparison with females.
Conclusion:
We came to conclusion that our research on the use of convolution neural networks to identify gingiva phenotypes.
