Comparative Validation of the Mixed and Permanent Dentition at Web-Based Artificial Intelligence Cephalometric Analysis

This retrospective study aimed to evaluate the difference in measurement between conventional orthodontic analysis and artificial intelligence pediatric adolescent patients aged 7 - 15 with mixed permanent dentition. A total of 60 (30 dentition, 30 dentition) who underwent lateral cephalometric radiograph for diagnosis were randomly selected. Seventeen landmarks identified, 22 measurements calculated by 1 examiner, using both method deep learning-based method. Errors due repeated assessed Pearson’s correlation coefficient. For dentition group group, respectively, a paired t-test was used 2 methods. The methods 8 statistically significant group: APDI, SNA, SNB, Mandibular plane angle, LAFH (p < 0.001), Facial ratio = U1 SN 0.012), A-Pg 0.021). In 4 showed methods: ODI 0.020), Wits appraisal 0.025), 0.026), 0.001). Compared time-consuming analysis, system can be clinically acceptable terms reliability validity. However, it is essential understand limitations programs use these proper assessment.