Machine Learning Algorithms for the Diagnosis of Class III Malocclusions in Children

Overview

Journal Children (Basel)

Specialty Health Services

Date 2024 Jul 27

PMID 39062212

Authors

Ling Zhao

Xiaozhi Chen

Juneng Huang

Shuixue Mo

Min Gu

Na Kang

Shaohua Song

Xuejun Zhang

Bohui Liang

Min Tang

Affiliations

Soon will be listed here.

Abstract

Objective: This study aims to propose an innovative machine learning (ML)-based diagnostic model for automatically classifies dental, skeletal and functional Class III malocclusions.

Methods: The collected data related to 46 cephalometric feature measurements from 4-14-year-old children ( = 666). The data set was divided into a training set and a test set in a 7:3 ratio. Initially, we employed the Recursive Feature Elimination (RFE) algorithm to filter the 46 input parameters, selecting 14 significant features. Subsequently, we constructed 10 ML models and trained these models using the 14 significant features from the training set through ten-fold cross-validation, and evaluated the models' average accuracy in test set. Finally, we conducted an interpretability analysis of the optimal model using the ML model interpretability tool SHapley Additive exPlanations (SHAP).

Results: The top five models ranked by their area under the curve (AUC) values were: GPR (0.879), RBF SVM (0.876), QDA (0.876), Linear SVM (0.875) and L2 logistic (0.869). The DeLong test showed no statistical difference between GPR and the other models ( > 0.05). Therefore GPR was selected as the optimal model. The SHAP feature importance plot revealed that he top five features were SN-GoMe (the ratio of the length of the anterior skull base SN to that of the mandibular base GoMe), U1-NA (maxillary incisor angulation to NA plane), Overjet (the distance between two lines perpendicular to the functional occlusal plane from U1 and L), ANB (the difference between angles SNA and SNB), and AB-NPo (the angle between the AB and N-Pog line).

Conclusions: Our findings suggest that ML models based on cephalometric data could effectively assist dentists to classify dental, functional and skeletal Class III malocclusions in children. In addition, features such as SN_GoMe, U1_NA and Overjet can as important indicators for predicting the severity of Class III malocclusions.

References

Fudalej P, Dragan M, Wedrychowska-Szulc B . Prediction of the outcome of orthodontic treatment of Class III malocclusions--a systematic review. Eur J Orthod. 2010; 33(2):190-7. DOI: 10.1093/ejo/cjq052. View

Fu M, Zhang D, Wang B, Deng Y, Wang F, Ye X . The prevalence of malocclusion in China--an investigation of 25,392 children. Zhonghua Kou Qiang Yi Xue Za Zhi. 2002; 37(5):371-3. View

Kim B, Kang B, Kim H, Baek S . Prognosis prediction for Class III malocclusion treatment by feature wrapping method. Angle Orthod. 2009; 79(4):683-91. DOI: 10.2319/071508-371.1. View

Ferro A, Nucci L, Ferro F, Gallo C . Long-term stability of skeletal Class III patients treated with splints, Class III elastics, and chincup. Am J Orthod Dentofacial Orthop. 2003; 123(4):423-34. DOI: 10.1067/mod.2003.70. View

Li Z, Hung K, Ai Q, Gu M, Su Y, Shan Z . Radiographic Imaging for the Diagnosis and Treatment of Patients with Skeletal Class III Malocclusion. Diagnostics (Basel). 2024; 14(5). PMC: 10931164. DOI: 10.3390/diagnostics14050544. View

Araki K, Matsumoto N, Togo K, Yonemoto N, Ohki E, Xu L . Developing Artificial Intelligence Models for Extracting Oncologic Outcomes from Japanese Electronic Health Records. Adv Ther. 2022; 40(3):934-950. PMC: 9988800. DOI: 10.1007/s12325-022-02397-7. View

Noseworthy P, Attia Z, Behnken E, Giblon R, Bews K, Liu S . Artificial intelligence-guided screening for atrial fibrillation using electrocardiogram during sinus rhythm: a prospective non-randomised interventional trial. Lancet. 2022; 400(10359):1206-1212. DOI: 10.1016/S0140-6736(22)01637-3. View

Ovsenik M, Farcnik F, Korpar M, Verdenik I . Follow-up study of functional and morphological malocclusion trait changes from 3 to 12 years of age. Eur J Orthod. 2007; 29(5):523-9. DOI: 10.1093/ejo/cjm065. View

Stensland A, Wisth P, Boe O . Dentofacial changes in children with negative overjet treated by a combined orthodontic and orthopaedic approach. Eur J Orthod. 1988; 10(1):39-51. DOI: 10.1093/ejo/10.1.39. View

10.

Nan L, Tang M, Liang B, Mo S, Kang N, Song S . Automated Sagittal Skeletal Classification of Children Based on Deep Learning. Diagnostics (Basel). 2023; 13(10). PMC: 10217682. DOI: 10.3390/diagnostics13101719. View

11.

Schulhof R, Nakamura S, Williamson W . Prediction of abnormal growth in class III malocclusions. Am J Orthod. 1977; 71(4):421-30. DOI: 10.1016/0002-9416(77)90245-7. View

12.

Zere E, Chaudhari P, Sharan J, Dhingra K, Tiwari N . Developing Class III malocclusions: challenges and solutions. Clin Cosmet Investig Dent. 2018; 10:99-116. PMC: 6016584. DOI: 10.2147/CCIDE.S134303. View

13.

Lee M, Le V, Kim J, Yang Y, Lee D . Prediction Model for Future Success of Early Orthopedic Treatment of Class III Malocclusion. Children (Basel). 2023; 10(2). PMC: 9955582. DOI: 10.3390/children10020355. View

14.

Yamamoto S, Kinugasa H, Hamada K, Tomiya M, Tanimoto T, Ohto A . The diagnostic ability to classify neoplasias occurring in inflammatory bowel disease by artificial intelligence and endoscopists: A pilot study. J Gastroenterol Hepatol. 2022; 37(8):1610-1616. DOI: 10.1111/jgh.15904. View

15.

Takada K, Yagi M, Horiguchi E . Computational formulation of orthodontic tooth-extraction decisions. Part I: to extract or not to extract. Angle Orthod. 2009; 79(5):885-91. DOI: 10.2319/081908-436.1. View

16.

Morch C, Atsu S, Cai W, Li X, Madathil S, Liu X . Artificial Intelligence and Ethics in Dentistry: A Scoping Review. J Dent Res. 2021; 100(13):1452-1460. DOI: 10.1177/00220345211013808. View

17.

Ngan P . Early treatment of Class III malocclusion: is it worth the burden?. Am J Orthod Dentofacial Orthop. 2006; 129(4 Suppl):S82-5. DOI: 10.1016/j.ajodo.2005.09.017. View

18.

Hwang H, Moon J, Kim M, Donatelli R, Lee S . Evaluation of automated cephalometric analysis based on the latest deep learning method. Angle Orthod. 2021; 91(3):329-335. PMC: 8084461. DOI: 10.2319/021220-100.1. View

19.

Wallace M, Sharma P, Bhandari P, East J, Antonelli G, Lorenzetti R . Impact of Artificial Intelligence on Miss Rate of Colorectal Neoplasia. Gastroenterology. 2022; 163(1):295-304.e5. DOI: 10.1053/j.gastro.2022.03.007. View

20.

Kaul V, Enslin S, Gross S . History of artificial intelligence in medicine. Gastrointest Endosc. 2020; 92(4):807-812. DOI: 10.1016/j.gie.2020.06.040. View