Prediction of the mesiodistal size of unerupted canines and premolars for a group of Romanian children: a comparative study

Objectives:

The aim of the present study was to develop an optimization method of multiple linearregression equation (MLRE), using a genetic algorithm to determine a set of coefficientsthat minimize the prediction error for the sum of permanent premolars and caninedimensions in a group of young people from a central area of Romania represented by acity called Sibiu.

Material and Methods:

To test the proposed method, we used a multiple linear regression equation derivedfrom the estimation method proposed by Mojers, to which we adjusted regressioncoefficients using the Breeder genetic algorithm. A total of 92 children were selectedwith complete permanent teeth with no clinically visible dental caries, proximalrestorations or orthodontic treatment. A hard dental stone was made for each of thesemodels, which was then measured with a digital calliper. The Dahlberg analyses ofvariance had been performed to determine the error of method, then the Correlation tTest was applied, and finally the MLRE equations were obtained using the version 16 forWindows of the SPSS program.

Results:

The correlation coefficient of MLRE was between 51-67% and the significance level wasset at α=0.05. Comparing predictions provided by the new and respectively old method, wecan conclude that the Breeder genetic algorithm is capable of providing the best valuesfor parameters of multiple linear regression equations, and thus our equations areoptimized for the best performance.

Conclusion:

The prediction error rates of the optimized equations using the Breeder geneticalgorithm are smaller than those provided by the multiple linear regression equationsproposed in the recent study.