Periodontitis risk assessment using two artificial neural network algorithms – a comparative study
Background: Artificial neural networks are currently used for a variety of complex problem solving approaches where a conventional method may not be feasible. Aims & objectives: Levenberg Marquardt and Scaled Conjugate Gradient feed forward back propagation neural network algorithms were compared to assess accuracy for periodontitis risk prediction. Material and Methods: In the present study 230 subjects were assessed for major and minor periodontitis risk factors such as; age, gender, family history of periodontitis, history of periodontal surgery, diet, smoking history, pan chewing habit, history of diabetes, history of hypertension, presence of sub gingival restorations, bleeding on probing, debris index (OHI-S), average pocket probing depth, presence of root calculus, presence of furcation involvement and vertical bone loss. Periodontitis risk assessment was done on a grade of 1 to 5. Results: The Levenberg Marquardt algorithm performed considerably better than Scaled Conjugate Gradient algorithm by converging faster with lesser iterations and produced minimum mean square error in both training and simulation phases. Conclusion: A properly trained neural network with Levenberg Marquardt back propagation algorithm can effectively be used for periodontitis risk prediction.
Brickley M, Shepherd J, Armstrong R. Neural networks: a new technique for development of decision support systems in dentistry. Journal of dentistry. 1998;26(4):305-9.
Ainamo J, Ainamo A. Risk assessment of recurrence of disease during supportive periodontal care. Journal of clinical periodontology. 2005;23(3):232-9.
Lopez R. The recording methods used to investigate the epidemiology of early periodontitis. International Journal of Dental Clinics. 2011;3(3).
Lopez R. Understanding periodontitis in adolescents: Historical background. International Journal of Dental Clinics. 2011;3(2).
Mudda JA, Gaddale R. Periodontal status among relatives of aggressive periodontitis Patients. International Journal of Dental Clinics. 2011;3(3).
Shankarapillai R, Mathur LK, Nair MA, Rai N, Mathur A. Periodontitis Risk Assessment using two artificial Neural Networks-A Pilot Study. International Journal of Dental Clinics. 2010;2(4).
Page RC, Krall EA, Martin J, Mancl L, Garcia RI. Validity and accuracy of a risk calculator in predicting periodontal disease. Journal-American Dental Association. 2002;133(5):569-76.
Demuth H, Beale M. Neural Network Toolbox: For Use with MATLAB®. Mathworks; 2001.
Møller MF. A scaled conjugate gradient algorithm for fast supervised learning. Neural networks. 1993;6(4):525-33.
Löe H, Silness J. Periodontal disease in pregnancy I. Prevalence and severity. Acta Odontologica. 1963;21(6):533-51.
Greene JC, Vermillion JR. The simplified oral hygiene index. Journal of the American Dental Association (1939). 1964;68:7.
Ahmed FE. Artificial neural networks for diagnosis and survival prediction in colon cancer. Molecular cancer. 2005;4(1):29.
Hagan MT, Menhaj MB. Training feedforward networks with the Marquardt algorithm. Neural Networks, IEEE Transactions on. 1994;5(6):989-93.
Trivedy C, Craig G, Warnakulasuriya S. The oral health consequences of chewing areca nut. Addiction biology. 2006;7(1):115-25.
Chang YC, Lii CK, Tai KW, Chou MY. Adverse effects of arecoline and nicotine on human periodontal ligament fibroblasts in vitro. Journal of clinical periodontology. 2001;28(3):277-82.
Page RC, Martin J, Krall EA, Mancl L, Garcia R. Longitudinal validation of a risk calculator for periodontal disease. Journal of clinical periodontology. 2003;30(9):819-27.
Page RC, Martin JA, Loeb CF. The Oral Health Information Suite (OHIS): its use in the management of periodontal disease. Journal of dental education. 2005;69(5):509-20.
- There are currently no refbacks.
|Published by Celesta Software Pvt Ltd|