Each variable for the dataset.
<div><p>Background</p><p>Malocclusion is a common anomaly and is frequently observed in children and adults. Early detection and treatment of malocclusion is necessary to prevent and minimize complications. Therefore, developing a tool to check dentition at an early stage and...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | <div><p>Background</p><p>Malocclusion is a common anomaly and is frequently observed in children and adults. Early detection and treatment of malocclusion is necessary to prevent and minimize complications. Therefore, developing a tool to check dentition at an early stage and motivate patients themselves to visit the dentist is required.</p><p>Objective</p><p>This study aimed to examine the feasibility of building an AI model that can detect malocclusion in children during the mixed dentition stage.</p><p>Methods</p><p>This study was conducted as a feasibility study using cross-sectional data. Subjects were recruited from panelists registered with Macromill, Inc. (approximately 1.3 million registered in 2021). A total of 519 elementary school children (275 boys and 244 girls in Grades 3–6) were included in this study. Questionnaire data and tooth alignment images of the children were collected. The dataset was created, and AI-based binary classification models for malocclusion were developed using an automated machine learning platform (DataRobot) to construct three algorithms for determining malocclusion (deep bite, maxillary protrusion, and crowding). Using a test dataset, the model’s performance was assessed through sensitivity, specificity, accuracy, precision, F1 score, receiver operating characteristic (ROC) curves, and area under the ROC curves (AUC).</p><p>Results</p><p>Three dental images were used for all model building, and questionnaire data used all four questions about oral habits (Q1: mouth open during the day, Q2: sleep with mouth open, Q3: have difficulty eating hard foods, Q4: prefer soft foods) for the deep bite classification model, Q1 and Q3 for the maxillary protrusion classification model, and Q1 and Q4 for the crowding classification model. The maxillary protrusion and crowding classification models showed moderate accuracy (AUC > 0.70), and the deep bite classification model showed high accuracy (AUC > 0.90). The permutation importance showed that dental image was the highest contributing factor in each model. Furthermore, while questionnaire data on oral habits were not an important factor in determining deep bite, these questionnaire data were an important factor in determining maxillary protrusion and crowding. Also, statistical analysis of the association between malocclusion and these oral habits revealed a significant association between maxillary protrusion or crowding and the presence or absence of oral habits.</p><p>Conclusion</p><p>For the detection of malocclusion in mixed dentition, AI-based binary classification models are a promising approach as a screening tool.</p></div> |
|---|