Скачать или смотреть AI in Orthodontics, Where Are We And Where Are We Going 10 MINUTE SUMMARY

Join me for a podcast summary looking at Ai in orthodontics and its clinical application. A growing topic in orthodontics, and one of the most featured topics at this years AAO. This summary is based on 3 lectures from this year’s summer meeting by Juan Francisco Gonzalez & Jean Marc Retrouvey, Tarek ElShebiny , Jonas Bianchi and Lucia Cevidanes. We will look what Ai is, the way it works and its clinical application, as well as a critical view on this young field.


What is Ai:
1. Technology that enables computers and machines to simulate human intelligence, perform 1 task very well, e.g. voice command, Youtube recommendations
2. Predictive modelling, makes calculations, convert information into numbers or categories and recognise patterns


Levels of Ai: Machine learning, Neural Networks and Deep Learning
1. Machine learning
a. The ability for a machine to learn from data and past experience to identify patterns and make predictions

2. Neural Networks
a. Specific model which relies on interconnected nodes, which perform a mathematical calculation of associations , patterns, and probabilities

3. Deep learning
a. Is a complex version of neural networks

Virtual patient
• CBCT segment + STL file – segmentation of the teeth and roots, with labelling of different stuctures
o Can print model, visualise ideal vector and calculate ideal vector
o However clinician still required to establish biomechanics

• CBCT integration for aligner cases, Unpublished thesis Khalid Alotaibi:
o Treatment planning confidence increased 50%, least change was treatment planning modification

Diagnostic data:
• Ai cephalometric tracing
o 46% of 24 landmarks 2.0mm within
o 4 different programmes Iortho, Webceph, Orthodc, cephx
o All landmarks had good overall agreement but variation in identification


• Facial Analysis
• Automated 3D facial asymmetry analysis using machine learning Adel 2025
o Study – 7 landmarks
o Identified manually and with deep learning
o 5 accurate, 2 significant difference but not clinically relevant

Diagnostic accuracy of photos
• Clinical photos assessment by Ai, and compared to clinical examination
• Sensitivity 72%, specificity 54% Vaughan & Ahmed 2025

Growth prediction
• Poor agreement age 9


Comparison between direct, virtual and AI bonding
• DIBs – uses Ai for bonding
• Compare Ai Vs user modified indirect bonding Vs direct bonding (gold standard), 0.5mm significant
• Incisors accurate
• Premolars and lower laterals inaccurate


Monitoring
Previous podcast exploring the accuracy of remote monitoring
o with Ferlito 2022 80% repeatability from 2 scans 44.7% repeatability and reproducibility

Bracket removal from scan and retainer fit
Tarek Assessment of virtual bracket removal by artificial intelligence and thermoplastic retainer fit AJODO 2024
o Retainers for both – clinically acceptable




FDA approval of Ai in dentistry
• FDA - Software of Medical Diagnosis
 4 dental:
• Dental Monitoring
• Ray Co
• X-Nav technologies
• Densply Sirona




What’s next
• More data learning to train AI model
• Robotics customising appliances per patient