Join me for a podcast summary looking at Ai in orthodonticsand its clinical application. A growing topic in orthodontics, and one of themost featured topics at this years AAO. This summary is based on 3 lectures fromthis year’s summer meeting by Juan Francisco Gonzalez & Jean Marc Retrouvey,Tarek ElShebiny , Jonas Bianchi and Lucia Cevidanes. We will look whatAi is, the way it works and its clinical application, as well as a criticalview on this young field.  What is Ai: 1.       Technology that enables computers and machinesto simulate human intelligence, perform 1 task very well, e.g. voice command, Youtuberecommendations2.       Predictive modelling, makes calculations,  convert information into numbers or categoriesand recognise patterns  Levels of Ai: Machine learning, Neural Networks and Deep Learning1.       Machine learninga.       The ability for a machine to learn from data andpast experience to identify patterns and make predictions  2.       Neural Networks  a.       Specific model which relies on interconnectednodes, which perform a mathematical calculation of associations , patterns, andprobabilities 3.       Deep learninga.       Is a complex version of neural networks Virtual patient·     CBCT segment + STL file – segmentation of theteeth and roots, with labelling of different stuctureso  Can print model, visualise ideal vector andcalculate ideal vectoro  However clinician still required to establish biomechanics ·     CBCT integration for aligner cases, Unpublishedthesis Khalid Alotaibi:o  Treatment planning confidence increased 50%, leastchange was treatment planning modification  Diagnostic data:·     Ai cephalometric tracingo  46% of 24 landmarks 2.0mm withino  4 different programmes  Iortho, Webceph, Orthodc, cephxo  All landmarks had good overall agreement butvariation in identification  ·     Facial Analysis·     Automated 3D facial asymmetry analysis usingmachine learning  Adel 2025o  Study – 7 landmarks o  Identified manually and with deep learning o  5 accurate, 2 significant difference but notclinically relevant Diagnostic accuracy of photos·     Clinical photos assessment by Ai, and comparedto clinical examination·     Sensitivity 72%, specificity 54% Vaughan & Ahmed2025  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 Vsdirect bonding (gold standard), 0.5mm significant ·     Incisors accurate·     Premolars and lower laterals inaccurate  Monitoring Previous podcast exploring the accuracy of remote monitoringo   with Ferlito 2022 80%repeatability from 2 scans 44.7% repeatability and reproducibility  Bracket removal from scan and retainer fitTarek Assessment of virtual bracket removal by artificialintelligence and thermoplastic retainer fit AJODO 2024o  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    

Ver todos los episodios