Application of artificial intelligence technologies for the detection of early childhood caries
Abstract Early Childhood Caries (ECC) is one of the most prevalent non-communicable diseases. It includes a range of environmental and genetic risk factors due to its multifaceted nature. The use of artificial intelligence technologies like Machine learning (ML) and Deep learning (DL) in the field o...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-07-01
|
| Series: | Discover Artificial Intelligence |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44163-025-00391-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Early Childhood Caries (ECC) is one of the most prevalent non-communicable diseases. It includes a range of environmental and genetic risk factors due to its multifaceted nature. The use of artificial intelligence technologies like Machine learning (ML) and Deep learning (DL) in the field of dentistry helps improve the diagnosis and treatment of ECC. It provides personalized precision in big data and caries prediction. This study mainly focuses on the different risk factors, dental caries indexes, and the importance of early caries prediction and treatment. In this review, we systematically surveyed previous studies on applying ML and DL algorithms for caries prediction. Oral health surveys, longitudinal studies, and databases with dental imaging and demographic data are some of the data sources from these articles. This study examined various approaches, datasets, methodologies, and algorithms. The inclusion criteria are the accuracy of models, the investigation of different risk factors, and the applicability of ML and DL in caries prediction. Results showed that ML algorithms, such as Support Vector Machines, achieved an accuracy of 88.76% on smartphone images, while XGBoost reached 97% accuracy on a health survey dataset, and the Random Forest attained 92% accuracy in a large-scale survey. The DL algorithms, such as the Convolutional Neural Networks, achieved up to 93.3% accuracy on tooth photographs, while Artificial Neural Networks reached 99% accuracy for primary molar caries. By leveraging these technologies, dental care can achieve improved diagnostic precision, early treatment strategies, and personalized healthcare solutions. |
|---|---|
| ISSN: | 2731-0809 |