Machine learning in orthodontics: Challenges and perspectives

Abstract

Artificial intelligence (AI) applications have significantly improved our everyday quality of life. The last decade has witnessed the emergence of up-and-coming applications in the field of dentistry. It is hopeful that AI, especially machine learning (ML), due to its powerful capacity for image processing and decision support systems, will find extensive application in orthodontics in the future. We performed a comprehensive literature review of the latest studies on the application of ML in orthodontic procedures, including diagnosis, decision-making and treatment. Machine learning models have been found to perform similar to or with even higher accuracy than humans in landmark identification, skeletal classification, bone age prediction, and tooth segmentation. Meanwhile, compared to human experts, ML algorithms allow for high agreement and stability in orthodontic decision-making procedures and treatment effect evaluation. However, current research on ML raises important questions regarding its interpretability and dataset sample reliability. Therefore, more collaboration between orthodontic professionals and technicians is urged to achieve a positive symbiosis between AI and the clinic.

Ähnliche Arbeiten