Limits...
Predicting tooth surface loss using genetic algorithms-optimized artificial neural networks.

Al Haidan A, Abu-Hammad O, Dar-Odeh N - Comput Math Methods Med (2014)

Bottom Line: The optimized constructed ANN consisted of 2-layer network with 15 neurons in the first layer and one neuron in the second layer.The data of 46 subjects were used to build the model, while the data of 15 subjects were used to test the model.Accepting an error of ±5 scores for all chosen teeth, the accuracy of the network becomes more than 80%.

View Article: PubMed Central - PubMed

Affiliation: College of Dentistry, Taibah University, Al Madina Al Munawara, Saudi Arabia.

ABSTRACT
Our aim was to predict tooth surface loss in individuals without the need to conduct clinical examinations. Artificial neural networks (ANNs) were used to construct a mathematical model. Input data consisted of age, smoker status, type of tooth brush, brushing, and consumption of pickled food, fizzy drinks, orange, apple, lemon, and dried seeds. Output data were the sum of tooth surface loss scores for selected teeth. The optimized constructed ANN consisted of 2-layer network with 15 neurons in the first layer and one neuron in the second layer. The data of 46 subjects were used to build the model, while the data of 15 subjects were used to test the model. Accepting an error of ±5 scores for all chosen teeth, the accuracy of the network becomes more than 80%. In conclusion, this study shows that modeling tooth surface loss using ANNs is possible and can be achieved with a high degree of accuracy.

Show MeSH

Related in: MedlinePlus

Deviations of the predicted TSL score values for the 15 test subjects.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4120478&req=5

fig7: Deviations of the predicted TSL score values for the 15 test subjects.

Mentions: Results show that about 73.3% of the predicted TSL scores of the testing sample deviate from the actual scores by ±5 scores. Accepting this ±5 error in TSL scores is so small considering the maximal possible TSL scores of “336” for any given subject (i.e., the error margin being calculated as 10/336 × 100% = 3%). Moreover, the results show that all predicted TSL scores lie within ±8.3 TSL scores of the actual recordings (i.e., error here becomes 16.6/336 × 100% = 4.9%), Figure 7.


Predicting tooth surface loss using genetic algorithms-optimized artificial neural networks.

Al Haidan A, Abu-Hammad O, Dar-Odeh N - Comput Math Methods Med (2014)

Deviations of the predicted TSL score values for the 15 test subjects.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4120478&req=5

fig7: Deviations of the predicted TSL score values for the 15 test subjects.
Mentions: Results show that about 73.3% of the predicted TSL scores of the testing sample deviate from the actual scores by ±5 scores. Accepting this ±5 error in TSL scores is so small considering the maximal possible TSL scores of “336” for any given subject (i.e., the error margin being calculated as 10/336 × 100% = 3%). Moreover, the results show that all predicted TSL scores lie within ±8.3 TSL scores of the actual recordings (i.e., error here becomes 16.6/336 × 100% = 4.9%), Figure 7.

Bottom Line: The optimized constructed ANN consisted of 2-layer network with 15 neurons in the first layer and one neuron in the second layer.The data of 46 subjects were used to build the model, while the data of 15 subjects were used to test the model.Accepting an error of ±5 scores for all chosen teeth, the accuracy of the network becomes more than 80%.

View Article: PubMed Central - PubMed

Affiliation: College of Dentistry, Taibah University, Al Madina Al Munawara, Saudi Arabia.

ABSTRACT
Our aim was to predict tooth surface loss in individuals without the need to conduct clinical examinations. Artificial neural networks (ANNs) were used to construct a mathematical model. Input data consisted of age, smoker status, type of tooth brush, brushing, and consumption of pickled food, fizzy drinks, orange, apple, lemon, and dried seeds. Output data were the sum of tooth surface loss scores for selected teeth. The optimized constructed ANN consisted of 2-layer network with 15 neurons in the first layer and one neuron in the second layer. The data of 46 subjects were used to build the model, while the data of 15 subjects were used to test the model. Accepting an error of ±5 scores for all chosen teeth, the accuracy of the network becomes more than 80%. In conclusion, this study shows that modeling tooth surface loss using ANNs is possible and can be achieved with a high degree of accuracy.

Show MeSH
Related in: MedlinePlus