A Declaratory Model of Generalized Regression Neural Network (GRNN) for Estimating Sleep Apnea Index in the Elderly Suffering from Sleep Disturbance

Bingh Tang

doi:10.6000/1929-6029.2016.05.02.5

Authors

Bingh Tang Taipei Medical College, M P H, Mailman School of Public Health, Columbia University Diplomate, American Board of Neurological Surgery 1985, Research Consultant Emeritus, New York College of Traditional Chinese Medicine, Mineola, NY, USA

DOI:

https://doi.org/10.6000/1929-6029.2016.05.02.5

Keywords:

AHI, sleep apnea, elderly, GRNN, ROC

Abstract

Objective: The main objective of this paper is to present a novel model for classifying senior patients into different apnea/hypopnea index (AHI) categories based on their clinical variables.

Methods and Materials: The proposed model is a generalized regression neural network (GRNN). Three important variables were first selected from the original 30 clinical variables. The GRNN was trained using 75 patients that were randomly selected from the total117 patients. The remaining 42 patients were used for testing GRNN model. The design parameter of the network, i.e., the spread of the radial basis function, was empirically optimized. To alleviate the model complexity, the original AHI values were dichotomized into two different groups, i.e., AHI>13 and AHI<=13. The use of GRNN for this application appear fairly novel, notwithstanding that there is a host of literatures on predicting obstructive sleep apnea (OSA) syndrome from demographic or other easy means to assess clinical variables.

Results: The proposed model has sensitivity and specificity of 95.7% and 50.0%, respectively, for the training cases, while 88.0% and 52.9%, respectively, for the testing cases.

Conclusion: The proposed neural network model has outperformed existing classification approaches in terms of classification accuracy and generalization, thus it can be potentially used in clinical applications, which would lead to a reduction of the necessity of in-laboratory nocturnal sleep studies.

References

Moorcroft W, Belcher P. Understanding Sleep and Dreaming 2003, New York, NY: Springer 1st ed. pp. 360.

Lavie P, Herer P, Peled R, et al. Mortality in sleep apnea patients: a multivariate analysis of risk factors. Sleep 1995; 18: 149-157. DOI: https://doi.org/10.1093/sleep/18.3.149

Fein A, Niederman H, Sklarek, H, Montovanl R, Rosen H. Can clinical findings predict a positive sleep study (abstract)? Am Rev Respir Dis 1986; 133: A55.

Kapuniai L, Andrew D, Crowell D, Pearce J. Identifying sleep apnea from self-reports. Am Rev Respir Dis 1988; 11: 430-436. DOI: https://doi.org/10.1093/sleep/11.5.430

Crocker B, Olson L, Saunders N, Hensley M, McKeon J, et al. Estimation of the probability of disturbed breathing during sleep before a sleep study. Am Rev Respir Dis 1990; 142(1): 14-18. http://dx.doi.org/10.1164/ajrccm/142.1.14 DOI: https://doi.org/10.1164/ajrccm/142.1.14

Fontenla-Romero O, Guijarro-Berdiñas B, Alonso-Betanzos A, Moret-Bonillo V. A new method for sleep apnea classification using wavelets and feedforward neural networks. Artificial Intelligence in Medicine 2005; 34: 65-76. http://dx.doi.org/10.1016/j.artmed.2004.07.014 DOI: https://doi.org/10.1016/j.artmed.2004.07.014

Liu D, Pang Z, Lloyd S. A neural network method for detection of obstructive sleep apnea and narcolepsy based on pupil size and EEG. IEEE Trans Neural Network 2008; 19(2): 308-318. http://dx.doi.org/10.1109/TNN.2007.908634 DOI: https://doi.org/10.1109/TNN.2007.908634

US government. Health Insurance Portability and Accountability Act regulations (HIPAA) 1996.

Tang B. Living by a biological clock: age-related functional changes of sleep homeostasis in people aged 65–88.5 years. Sleep and Biological Rhythms 2007; 5(3): 180-195. http://dx.doi.org/10.1111/j.1479-8425.2007.00275.x DOI: https://doi.org/10.1111/j.1479-8425.2007.00275.x

Department of Health, Taiwan. Nutrition and Health Survey (National Science Council 93WFD2000205), between 1993 and 1996.

American Academy of Sleep Medicine. The degree of severity of sleep apnea in adults: recommendations for syndrome definition and measurement techniques in clinical research: the report of an American Academy of Sleep Medicine Task Force. Sleep 1999; 22: 667-689. DOI: https://doi.org/10.1093/sleep/22.5.667

Rechtschaffen A. Wolpert E, Dement W. Nocturnal sleep of narcoleptics. Electroencephalorgr Clin Neurophysiol 1963; 15: 599-609. http://dx.doi.org/10.1016/0013-4694(63)90032-4 DOI: https://doi.org/10.1016/0013-4694(63)90032-4

Haykin S. Neural Networks – a Comprehensive Foundation, generalize regression neural network (GRNN) 2nd ed., Printice Hall, Upper Saddle River, New Jersey 1999.

Specht D. A Generalized Regression Neural Network. IEEE Transactions on Neural Networks, 2, Nov. 1991; 568-576. http://dx.doi.org/10.1109/72.97934 DOI: https://doi.org/10.1109/72.97934

Pepe M. The statistical evaluation of medical tests for classification and prediction. Oxford; New York: Oxford University Press 2004.

Frost F, Karri V. Identifying Significant Parameters for Hall-Heroult Process Using General Regression Neural Networks. In R Loganantharaj, G Palm, A Moonis (Eds.), In Intelligent problem solving: methodologies & approaches: 13th International Conference on Industrial & Engineering Applications of Artificial Intelligence & Expert Systems. New York, NY: Springer 2000; pp. 73-78. http://dx.doi.org/10.1007/3-540-45049-1_9 DOI: https://doi.org/10.1007/3-540-45049-1_9

Provost F, Fawcett T. Analysis and visualization of classifier performation: Comparison under imprecise class and cost distribution. In: Proc. Third Internat. Conf. on Knowledge discovery and data mining (KDD-97) AAAI Press. Menlo Park 1997; pp 43-48.

Ożegowski S, Wilczyńska E, Piorunek T, Szymanowska K, Paluszkiewicz L. Usefulness of ambulatory ECG in the diagnosis of sleep-related breathing disorders. Kardiol Pol (Polish Heart Journal) 2007; 65: 1321-1328.

Siell I, Greenberg G, McKnight R, Nair R, McDowell R, et al. Decision rules for the use of radiography in acute ankle injuries: refinement and prospective validation. JAMA 1993; 269: 1127-1132. http://dx.doi.org/10.1001/jama.1993.03500090063034 DOI: https://doi.org/10.1001/jama.269.9.1127

Tsai W, John E, Remmers J, Brant R, Flemons W, et al. Decision Rule for Diagnostic Testing in Obstructive Sleep Apnea. American Journal of Respiratory and Critical Care Medicine 2003; 167: 1427-1432. http://dx.doi.org/10.1164/rccm.200112-110OC DOI: https://doi.org/10.1164/rccm.200112-110OC

Mokhlesi B, Tulaimat A, Faibussowitsch I, Wang Y, Evans A. Obesity hypoventilation syndrome: prevalence and predictors in patients with obstructive sleep apnea. Sleep and Breathing 2007; 11(2). http://dx.doi.org/10.1007/s11325-006-0092-8 DOI: https://doi.org/10.1007/s11325-006-0092-8

Vignatelli L, Plazzi G, Barbato A, Ferini-Strambi A, Manni R, et al. and on behalf of GINSEN. Italian version of the Epworth sleepiness scale: external validity. Neurological Science Neurological Science 2003; 23(6): 295-300. http://dx.doi.org/10.1007/s100720300004 DOI: https://doi.org/10.1007/s100720300004

Collop N, Anderson W, Boehlecke B, Claman D, Goldberg R, et al. American Academy of Sleep Medicine Clinical guidelines for the use of unattended portable monitors in the diagnosis of OSA in adult patients. Portable Monitoring Task Force of the American Academy of Sleep Medicine. J Clin Sleep Med 2007; 3(7): 737-747. DOI: https://doi.org/10.5664/jcsm.27032

Ancoli-Israel S, Kripke D, Klauber M. Morbidity, mortality and sleep-disordered breathing in community dwelling elderly. Chest 1996; 109: 890-5. DOI: https://doi.org/10.1378/chest.109.4.890

Lavie P, Lavie L, Herer P. All-cause mortality in males with sleep apnea syndrome: declining mortality rates with age. Eur Respir J 2005; 25: 514-20. http://dx.doi.org/10.1183/09031936.05.00051504 DOI: https://doi.org/10.1183/09031936.05.00051504

Kohavi, Provost F. Glossary of Terms- Special Issue on Applications of Machine Learning and the Knowledge Discovery Process. Machine Learning 1998; 30: 271-4. http://dx.doi.org/10.1023/A:1017181826899 DOI: https://doi.org/10.1023/A:1007442505281

Berger V. Improving the information content of categorical clinical trial endpoints. Control Clinical Trials 2002; 23: 502-514. http://dx.doi.org/10.1016/S0197-2456(02)00233-7 DOI: https://doi.org/10.1016/S0197-2456(02)00233-7

Ohayon M. The effects of breathing-related sleep disorders on mood disturbances in the general population. J Clin Psychiatry 2003; 64: 1195-1200. http://dx.doi.org/10.4088/JCP.v64n1009 DOI: https://doi.org/10.4088/JCP.v64n1009

Schröder M, O'Hara R. Depression and Obstructive Sleep Apnea (OSA) Annals of General Psychiatry 2005; 4: 13-19. http://dx.doi.org/10.1186/1744-859X-4-13 DOI: https://doi.org/10.1186/1744-859X-4-13

Collop NA, Anderson WM, Boehlecke B, Claman D, Goldberg R, et al. Portable Monitoring Task Force of the American Academy of Sleep Medicine 2007.

James G, Witten D, Hastie T, Tibshirani R. An Introduction to Statistical Learning. Springer 2013; p. 6. http://dx.doi.org/10.1007/978-1-4614-7138-7 DOI: https://doi.org/10.1007/978-1-4614-7138-7

Tang BH. Review Article Fisher-Mendel Controversy in Genetics: Scientific Argument, Intellectual Integrity, A Fair Society, Western Falls and Bioethical Evaluation. Journal of the College of Physicians and Surgeons Pakistan 2009; 19(10): 649-654.