Resumen
Objective: This study aims to introduce and assess a novel AI-driven tool developed for the classification of orthodontic arch shapes into square, ovoid, and tapered categories. Methods: Between 2016 and 2019, we collected 450 digital dental models. Applying our inclusion and exclusion criteria, we refined our dataset to 50 models, ensuring a focused and detailed analysis. Plaster casts were digitized into 3D models with AutoScan-DS-EX. Three trained evaluators then measured mesiodistal and arch widths using MeshLab. The development of DentalArch was undertaken in two versions: the first version incorporates 18 input parameters, including mesiodistal widths (from the first molar to the first molar, totaling 14) and arch widths (1 intercanine, 2 interpremolar, and 1 intermolar, totaling 4); the second version uses only 4 parameters related to arch widths. Both versions aim to predict the arch shape. An evaluation of 28 machine learning methods through a k = 5-fold cross-validation was conducted to determine the most effective techniques. Results: In the tests, the performance evaluation of the DentalArch software in detecting arch shapes revealed that version 1, which analyzes 18 parameters, achieved an accuracy of 94.7% for the lower arch and 93% for the upper arch. The more streamlined version 2, which assesses only four parameters, also showed high precision with an accuracy of 93.0% for the lower arch and 92.7% for the upper arch. Conclusions: DentalArch provides a tool with potential use in orthodontic diagnostics, particularly in the task of arch shape classification. The software offers a less subjective and data-driven approach to arch shape determination. Moreover, the open-source nature of DentalArch ensures its global availability and encourages contributions from the orthodontic community.