A Fully Integrated Orthodontic Aligner With Force Sensing Ability for Machine Learning-Assisted Diagnosis.

Area of Science:

• Biomedical Engineering
• Dental Technology
• Wearable Sensors

Background:

• Malocclusion diagnosis is complex, requiring advanced occlusal data monitoring tools.
• Current intraoral monitoring faces challenges in sampling and device miniaturization.

Purpose of the Study:

• To develop a fully integrated, flexible, and self-contained transparent aligner for continuous occlusal force detection.
• To utilize machine learning for identifying adverse oral habits and diagnosing malocclusion types.

Main Methods:

• Embedding high-performance piezoelectric sensors into occlusal surfaces using flexible printed circuits.
• Developing a transparent aligner with continuous pressure monitoring at eight distinct sites.
• Integrating a machine learning algorithm for data analysis and habit identification.

Main Results:

• The aligner demonstrated high sensitivity for occlusal force detection with a broad threshold.
• The system achieved 95% accuracy in determining malocclusion types using data from over 1400 models.
• The system successfully identified adverse oral habits like lip biting, thumb sucking, and teeth grinding.

Conclusions:

• The developed intraoral wearable sensor system represents a significant advancement in orthodontic monitoring.
• This technology facilitates remote orthodontic evaluation and offers a new approach to effective orthodontic care.