Classification of Postural Profiles among Mouth-breathing Children by Learning Vector Quantization

Summary

Background: Mouth breathing is a chronic syndrome that may bring about postural changes. Finding characteristic patterns of changes occurring in the complex musculoskeletal system of mouth-breathing children has been a challenge. Learning vector quantization (LVQ) is an artificial neural network model that can be applied for this purpose.

Objectives: The aim of the present study was to apply LVQ to determine the characteristic postural profiles shown by mouth-breathing children, in order to further understand abnormal posture among mouth breathers.

Methods: Postural training data on 52 children (30 mouth breathers and 22 nose breathers) and postural validation data on 32 children (22 mouth breathers and 10 nose breathers) were used. The performance of LVQ and other classification models was compared in relation to self-organizing maps, back-propagation applied to multilayer perceptrons, Bayesian networks, naive Bayes, J48 decision trees, k*, and k-nearest-neighbor classifiers. Classifier accuracy was assessed by means of leave-one-out cross-validation, area under ROC curve (AUC), and inter-rater agreement (Kappa statistics).

Results: By using the LVQ model, five postural profiles for mouth-breathing children could be determined. LVQ showed satisfactory results for mouth-breathing and nose-breathing classification: sensitivity and specificity rates of 0.90 and 0.95, respectively, when using the training dataset, and 0.95 and 0.90, respectively, when using the validation dataset.

Conclusions: The five postural profiles for mouth-breathing children suggested by LVQ were incorporated into application software for classifying the severity of mouth breathers’ abnormal posture.

Keywords

Neural networks (computer) - clinical decision support systems - posture and mouth breathing

• References

• 1 Guyton AC, Hall JE. Textbook of Medical Physiology. 11th ed. Saunders; 2005
• 2 Hess DR, Bigatello LM. The chest wall in acute lung injury/acute respiratory distress syndrome. Curr Opin Crit Care 2008; 14 (01) 94-102.
• 3 Weider DJ, Baker GL, Salvatoriello FW. Dental malocclusion and upper airway obstruction, an otolaryngologist’s perspective. Int J Pediatr Otorhinolaryngol 2003; 67 (04) 323-331.
• 4 Hruska RJ. Influences of dysfunctional respiratory mechanics on orofacial pain. Dent Clin North Am 1997; 41 (02) 211-227.
• 5 Jardim JR, Camelier A, Dal Corso S, Rodrigues JE. Strength and endurance of the respiratory and handgrip muscles after the use of flunisolide in normal subjects. Respir Med 2007; 101 (07) 1594-1599.
• 6 Hamaoui A, Le Bozec S, Poupard L, Bouisset S. Does postural chain muscular stiffness reduce postural steadiness in a sitting posture?. Gait Posture 2007; 25 (02) 199-204.
• 7 Cossette I, Monaco P, Aliverti A, Macklem PT. Chest wall dynamics and muscle recruitment during professional flute playing. Respir Physiol Neurobiol 2008; 160 (02) 187-195.
• 8 Greenough A, Dimitriou G, Prendergast M, Milner AD. Synchronized mechanical ventilation for respiratory support in newborn infants. Cochrane Database Syst Rev. 2008 (1): CD000456
• 9 Corrêa ECR, Bérzin F. Efficacy of physical therapy on cervical muscle activity and on body posture in school-age mouth breathing children. Int J Pediatr Otorhinolaryngol 2007; 71 (10) 1527-1535.
• 10 Yi LC, Jardim JR, Inoue DP, Pignatari SSN. The relationship between excursion of the diaphragm and curvatures of the spinal column in mouth breathing children. J Pediatr (Rio J) 2008; 84 (02) 171-177.
• 11 Shortliffe EH, Cimino JJ. Biomedical Informatics: Computer Applications in Health Care and Biomedicine. 3rd ed. Springer; 2006
• 12 Lisboa PJG. A review of evidence of health benefit from artificial neural networks in medical intervention. Neural Netw 2002; 15 (01) 11-39.
• 13 Akay M. Nonlinear Biomedical Signal Processing, Fuzzy Logic, Neural Networks, and New Algorithms. IEEE Press Series on Biomedical Engineering. Wiley-IEEE Press; 2000
• 14 Bishop CM. Pattern Recognition and Machine Learning. 1st ed. Springer; 2007
• 15 Lisboa PJ, Ifeachor EC, Szczepaniak PS. Artificial Neural Networks in Biomedicine. 1st ed. Springer; 2000
• 16 Campos LFA, Silva AC, Barros AK. Independent component analysis and neural networks applied for classification of malignant, benign and normal tissue in digital mammography. Methods Inf Med 2007; 46 (02) 212-215.
• 17 Tzallas AT, Karvelis PS, Katsis CD, Fotiadis DI, Giannopoulos S, Konitsiotis S. A method for classification of transient events in EEG recordings: application to epilepsy diagnosis. MethodsInf Med 2006; 45 (06) 610-621.
• 18 Linder R, König IR, Weimar C, Diener HC, Pöppl SJ, Ziegler A. Two models for outcome prediction-a comparison of logistic regression and neural networks. Methods Inf Med 2006; 45 (05) 536.
• 19 Haykin S. Neural Networks: A Comprehensive Foundation. 2nd ed. Prentice Hall; 1998
• 20 Duda RO, Hart PE, Stork DG. Pattern Classification. 2nd ed. Wiley-Interscience; 2000
• 21 Heckerling PS, Canaris GJ, Flach SD, Tape TG, Wigton RS, Gerber BS. Predictors of urinary tract infection based on artificial neural networks and genetic algorithms. Int J Med Inform 2007; 76 (04) 289-296.
• 22 Mancini F, Alves D, Shizue Nagata Pignatari S, Yi Liu C, Torres Pisa I. Postural qualitative analysis in mouth breath children. Physical Therapy in Movement 2007; 20 (02) 119-126.
• 23 Kohonen T. Self-Organizing Maps. 3rd ed. Springer; 2000
• 24 Du K. Clustering: A neural network approach. Neural Networks (Internet). Cited: Nov 14, 2009. In Press, Corrected Proof. Available from: http://www.sciencedirect.com/science/article/B6T08-4X3W45J-2/2/ee12f68ee20eb829d8b0a655d64bb eb0
• 25 Bellazzi R, Zupan B. Predictive data mining in clinical medicine: current issues and guidelines. Int J Med Inform 2008; 77 (02) 81-97.
• 26 Witten IH, Frank E. Data Mining: Practical Machine Learning Tools and Techniques, Second Edition. 2nd ed. Morgan Kaufmann; 2005
• 27 John GH, Langley P. Estimating continuous distributions in Bayesian classifiers. In: Proceedings of the eleventh conference on uncertainty in artificial intelligence. 1995 pp 338-345.
• 28 Quinlan JR. C4. 5: programs for machine learning. Morgan Kaufmann; 2003
• 29 Cleary JG, Trigg LE. K*: An Instance-based Learner Using an Entropic Distance Measure. In: Machine Learning-international workshop conference. 1995 pp 108-114.
• 30 Aha DW, Kibler D, Albert MK. Instance-based learning algorithms. Machine learning 1991; 6 (01) 37-66.
• 31 Cristianini N, Shawe-Taylor J. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. 1st ed. Cambridge University Press; 2000
• 32 Brodsky L. Modern assessment of tonsils and adenoids. Pediatric clinics of North America 1989; 36 (06) 1551.
• 33 Demšar J. Statistical comparisons of classifiers over multiple data sets. The Journal of Machine Learning Research 2006; 7: 1-30.
• 34 Pesonen E, Eskelinen M, Juhola M. Comparison of different neural network algorithms in the diagnosis of acute appendicitis. Int J Biomed Comput 1996; 40 (03) 227-233.
• 35 Dieterle F, Müller-Hagedorn S, Liebich HM, Gauglitz G. Urinary nucleosides as potential tumor markers evaluated by learning vector quantization. Artif Intell Med 2003; 28 (03) 265-279.
• 36 Burnham KP, Anderson D. Model Selection and Multi-Model Inference. 2nd ed. Springer; 2003
• 37 Metz CE. Basic principles of ROC analysis. In: Seminars in nuclear medicine. Semin Nucl Med. 1978 pp 283.
• 38 Davison AC, Hinkley DV. Bootstrap Methods and Their Application. 1st ed. Cambridge University Press; 1997
• 39 Altman DG. Practical Statistics for Medical Research. 1st ed. Chapman & Hall/CRC; 1990
• 40 Alhoniemi E, Himberg J, Parhankangas J, Vesanto J. SOM Toolbox (Internet). Laboratory of Information and Computer Science. Helsinki University of Technology; Available from: http://www.cis.hut.fiprojects/somtoolbox/
• 41 Markey MK, Lo JY, Tourassi GD, Floyd CE. Self-organizing map for cluster analysis of a breast cancer database. Artif Intell Med 2003; 27 (02) 113-127.