Related Experiment Video
Updated: Jan 12, 2026
07:51
A Novel Approach to Monitoring Graft Neovascularization in the Human Gingiva
Published on: January 12, 2019
7.1K
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.
Journal of Pharmacy & Bioallied Sciences
|October 30, 2025
Summary
Machine learning software accurately assesses gingival phenotype, matching traditional methods. This noninvasive technique offers a reliable alternative for evaluating gingival thickness and health.
Area of Science:
- Dentistry
- Periodontology
- Artificial Intelligence in Healthcare
Background:
- Conventional methods for assessing gingival phenotype have limitations.
- Evaluating noninvasive techniques is crucial for accurate periodontal diagnosis.
Purpose of the Study:
- To assess the effectiveness and accuracy of machine learning (ML) software for gingival phenotype assessment.
- To compare ML software with traditional methods like probe transparency and transgingival probing.
Main Methods:
- A study involving 382 periodontally healthy patients.
- Gingival phenotype assessment in the upper incisor region using probe transparency, transgingival probing, and ML software.
Main Results:
- No statistically significant differences were found between the three assessment methods, indicating their equivalence.
- Males exhibited a higher prevalence of thick gingival phenotype compared to females.
Conclusions:
- Machine learning software, specifically using convolution neural networks, is effective for identifying gingival phenotypes.
- ML software provides a viable and accurate noninvasive alternative for gingival phenotype assessment.
