Machine learning assisted Cameriere method for dental age estimation.

Area of Science:

• Forensic Anthropology
• Pediatric Dentistry
• Machine Learning Applications

Background:

• The Cameriere dental age estimation method is widely recognized.
• Machine learning (ML) offers potential accuracy improvements for dental age estimation.
• This study is innovative as it applies ML to the Cameriere method for the first time.

Purpose of the Study:

• To predict children's dental age using 7 lower left permanent teeth and three ML models (random forest, support vector machine, linear regression) based on the Cameriere method.
• To compare the accuracy of ML models against the traditional Cameriere age estimation.
• To evaluate the effectiveness of ML algorithms in enhancing dental age prediction.

Main Methods:

• Retrospective analysis of 748 children's (ages 5-13) orthopantomograms.
• Application of Cameriere method to 7 permanent developing teeth (left mandible).
• Comparison of traditional Cameriere formula with random forest (RF), support vector machine (SVM), and linear regression (LR) models using 20 repetitions of 80-20% training-test data splits.

Main Results:

• ML models demonstrated higher accuracy than the traditional Cameriere formula.
• SVM and RF models showed the lowest mean error (ME), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE).
• Specific error values for SVM and RF were significantly lower than those for European and Chinese Cameriere formulas.

Conclusions:

• ML methods, utilizing Cameriere's maturation stages, are more accurate for dental age estimation than the traditional Cameriere formula.
• The findings support the adoption of ML algorithms over the conventional Cameriere method.
• This research highlights the potential of ML to refine dental age assessment.