Artificial Neural Network Assisted Selection of Extractionor Non-extraction Orthodontic Treatment for Malocclusion.

doi:10.13701/j.cnki.kqyxyj.2016.12.020

Abstract

Abstract: Objective: To use artificial neural networks (ANN) to create a decision-making expert system (ES) for determining whether extraction is needed in the orthodontic treatment of malocclusion patients. Methods: A total of 230 subjects were examined, of which 138 underwent extraction treatment and 92 underwent non-extraction treatment. In each case, 28 indices were ex-amined. Data from 207 patients were aggregated to construct the training set, and data from the other 23 patients were used as the testing set. A Back Propagation (BP) ANN model was constructed using the MATLAB language to assist in evaluating the necessity for extraction. Results: When data from the training set were tested, the ES was 100% correct. When data from the testing set were submitted to the ES, the treatment plan was correctly fore-casted in 82.6% of the cases (i.e., only 4 cases failed). Conclusion: The constructed ANN was useful in determining whether extraction or non-extraction treatment should be employed in malocclusion patients.

Key words: Artificial intel ligence , Neutral network, Tooth extraction, Malocclusion

CLC Number:

R783.5

HAN Lei, XIE Xiao-qiu, WANG A-ming, ZHAO Dan.. Artificial Neural Network Assisted Selection of Extractionor Non-extraction Orthodontic Treatment for Malocclusion.[J]. Journal of Oral Science Research, 2016, 32(12): 1308-1311.

References

[1] 方华.532例正畸拔牙回顾分析[J].口腔医学研究,2010, 26(4)∶610-610
[2] Suresh S, Saraswathi S, Sundararajan N. Performance enhancement of extreme learning machine for multi-category sparse data classification problems [J]. Engineering Applications of Artificial Intelligence 2010,23(10)∶1149-1157
[3] Torres JJ, Kappen HJ. Emerging phenomena in neural networks with dynamic synapses and their computational implications [J]. Front ComputNeurosci, 2013, 5(1)∶30-35
[4] CH Huang,CH Lin. Multiple harmonic-source classification using a Self-Organization Feature Map network with voltage-current wavelet transformation patterns [J]. Applied Mathematical Modelling, 2015,39(19)∶5849-5861
[5] Rumelhart DE, Hinton GE. Williams RJ. Learning representations by back-propagating errors [J]. Nature, 1986,323 (6088)∶533-536
[6] White SC. Decision-support systems in dentistry [J]. J Dent Educ, 1996,60(1)∶47-63
[7] Brickley MR, Shepherd JP, Armstrong RA. Neural networks: a new technique for development of decision support systems in dentistry [J]. J Dent, 1998,26(2)∶305-309
[8] KazemBahaa, Garma Noor, YousifYousif [M]. Principles in Contemporary Orthodon-tics,2001,21(3)∶452-492
[9] K Takada, M Yagi,E Horiguchi.Computational formulation of orthodontic tooth-extraction decisions [J]. Angle Orthodontist, 2009, 79(5)∶885-891
[10] Cook J, Mullings C, Vowles R, et al. Online orthodontic advice: a protocol for a pilotteledentistry system [J]. Journal of Telemedicine and Telecare, 2001, 7(2)∶324-333
[11] Noroozi H. Introduction of a new orthodontic treatment planning software; a fuzzy logic expert system [J]. International journal of orthodontics (Milwaukee, Wis.), 2006,17(1)∶25-29
[12] Xu TM, Liu Y, Yang MZ etc, Comparison of extraction versus nonextraction orthodontic treatment outcomes for borderline Chinese patients [J]. Am J Orthdo DentotacialOrthop, 2005, 129(5)∶673-679
[13] 何勇,丁寅,李菲菲,等.安氏Ⅰ类错合正畸拔牙和非拔牙主要指标的筛选和分析[J].口腔医学研究,2006, 22(2)∶191-194
[14] Bostwick DG, Burke HB. Prediction of individual patient outcome in cancer: comparison of artificial neural networks and Kaplan-Meier methods [J]. Cancer, 2001, 91(suppl)∶1643-1646
[15] Nakamura K, Yoshida H, Engelmann R. et al. Computerized analysis of the likelihood of malignancy in solitary pulmonary nodules with use of artificial neural networks [J]. Radiology, 2000,214(7)∶823-830