Relevance. Artificial intelligence (AI) has become a key technological advancement in orthodontics. Neural network algorithms successfully automate comprehensive diagnostics, effectively segment bone structures, and predict treatment outcomes based on individual patient characteristics. In orthognathic surgery, AI not only determines the indications for surgery but also provides precise 3D surgical planning. The visualization of treatment outcomes is forging a new paradigm for doctor-patient communication. Subject. The subject of this research is artificial intelligence algorithms for the automation of diagnosis, orthodontic treatment planning, and the prediction of its results. Aim. To conduct an analysis of the literature dedicated to the application of artificial intelligence technologies in orthodontic practice, in order to identify the key vectors of the digital transformation in this field of dentistry. Materials and Methods. A literature review from 2019 to 2025 on the application of artificial intelligence in orthodontics was conducted based on an analysis of the eLIBRARY, Scopus, Google Scholar, PubMed/MEDLINE, and MDPI databases. As a result of the analysis, 110 scientific studies were selected and examined in detail. Results. To date, the digital transformation of orthodontics has demonstrated significant progress through the implementation of neural network models. AI assists in identifying and classifying dentofacial anomalies from photographs, determining skeletal maturity stages, and performing comprehensive diagnosis, including identifying the causes of anomalies, cephalometric analysis, 3D modeling, assessment of temporomandibular joint (TMJ) condition, and facial scanning. These systems optimize clinicians' work: they speed up data analysis, provide a "second opinion" in complex cases, minimize diagnostic errors, and create clear visualizations of potential treatment outcomes. Conclusions 4. Modern technologies open up new possibilities for improving the quality of orthodontic care. 5. However, for the successful integration of AI, systemic challenges must be addressed: improving the quality of input data, preventing model overfitting, and conducting comprehensive clinical validation of the algorithms. 6. At the current stage, the field is transitioning from experimental developments to practical application, where the leading role remains with the clinician, and AI serves as a decision-support tool.
Ivanov et al. (Fri,) studied this question.