Applications of artificial intelligence and machine learning in orthodontics: a scoping review

Abstract

Introduction This scoping review aims to provide an overview of the existing evidence on the use of artificial intelligence (AI) and machine learning (ML) in orthodontics, its translation into clinical practice, and what limitations do exist that have precluded their envisioned application. Methods A scoping review of the literature was carried out following the PRISMA-ScR guidelines. PubMed was searched until July 2020. Results Sixty-two articles fulfilled the inclusion criteria. A total of 43 out of the 62 studies (69.35%) were published this last decade. The majority of these studies were from the USA (11), followed by South Korea (9) and China (7). The number of studies published in non-orthodontic journals (36) was more extensive than in orthodontic journals (26). Artificial Neural Networks (ANNs) were found to be the most commonly utilized AI/ML algorithm (13 studies), followed by Convolutional Neural Networks (CNNs), Support Vector Machine (SVM) (9 studies each), and regression (8 studies). The most commonly studied domains were diagnosis and treatment planning—either broad-based or specific (33), automated anatomic landmark detection and/or analyses (19), assessment of growth and development (4), and evaluation of treatment outcomes (2). The different characteristics and distribution of these studies have been displayed and elucidated upon therein. Conclusion This scoping review suggests that there has been an exponential increase in the number of studies involving various orthodontic applications of AI and ML. The most commonly studied domains were diagnosis and treatment planning, automated anatomic landmark detection and/or analyses, and growth and development assessment.

Cephalometric Analysis in Orthodontics Using Artificial Intelligence—A Comprehensive Review

“…As computational technology and power have increased exponentially, scientists have created more difficult and deeper neural network models to resolve more challenging and complex problems. DL is the new name for the neural network [ 7 ].…”

“…AI allows for the organizing, investigation, categorization, and depiction of health data, and its influential design-obtaining and evaluated algorithms aid in the growth of science in general [ 6 ]. According to Morgan Stanley, the worldwide usage of AI in the medical sector might grow from $1.30 billion to $10 billion by 2024, a 40% annual growth rate [ 7 ].…”

Artificial Intelligence in Dentistry—Narrative Review

“…Artificial intelligence is spreading widely in the field of orthodontics. The most often used types of algorithms in orthodontics are artificial neural networks (ANN), convolutional neural networks (CNN), support vector machine, and regression algorithms [ 32 ]. Peilini et al used an ANN in their study to predict whether patients need extractions or not in their treatment plan.…”

“…To resume, the most common fields of orthodontics where neural networks may be used are in diagnosis and treatment planning, automated anatomic analyses, assessment of growth and development, and the evaluation of treatment outcomes ( Table 3 ) [ 32 ]. It seems that artificial intelligence in orthodontics may be widely used and its use for sure can be extended even further.…”

The Validity of Machine Learning Procedures in Orthodontics: What Is Still Missing?

“…In recent years, an excessive tendency to rely on ML systems (“over-reliance”), overdependence, “deskilling”, and even potential desensitization to patient problems have been the most common criticisms related to the use of these models in medicine [ 18 , 19 , 20 , 21 ]. Concerns have arisen regarding the possibility of incorporating “dirty” data and spurious correlations based on uncertain clinical interpretations [ 22 ]. Some practitioners believe that using computational systems could lead to the establishment of a new, problematic medical empiricism, based not on concrete facts and data relating to patients but rather on interconnections of data, meaning that the most straightforward clinical situations can become complicated and confusing [ 23 ].…”