Analysis of Palm Perspiration Effect with SVM for Diabetes in People

Authors: Hamdi Melih Saraoğlu, Muhlis Yıldırım, Abdurrahman Özbeyaz, Feyzullah Temurtas

Abstract:

In this research, the diabetes conditions of people (healthy, prediabete and diabete) were tried to be identified with noninvasive palm perspiration measurements. Data clusters gathered from 200 subjects were used (1.Individual Attributes Cluster and 2. Palm Perspiration Attributes Cluster). To decrase the dimensions of these data clusters, Principal Component Analysis Method was used. Data clusters, prepared in that way, were classified with Support Vector Machines. Classifications with highest success were 82% for Glucose parameters and 84% for HbA1c parametres.

Keywords: Palm perspiration, Diabetes, Support Vector Machine, Classification.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1328340

References:

[1] Arısoy, E.S., T.C. Ministry of Health, Diagnosis and Treatment Guides for Primary Healthcare 2003,T.C. Miistry of Health, 2003
[2] Wild S., Roglic G, Green A, Sicree R, King H. "Global prevalence of diabetes estimates for the year 2000 and projections for 2030", Diabetes Care, 2004, Vol 27, pp 1047-1053
[3] International Diabetes Federation. Diabetes Atlas, World Diabetes Foundation, 2006
[4] Satman I., "The update criteria and the reasons of them in diagnosis and follow up of diabetes mellitus",A T├╝rkiye Klinikleri Journal of Internal Medical Sciences, 2007,Vol 3,pp 1-15
[5] Temurtas, H., Yumusak, N., & Temurtas, F. (2009), "A comparative study on diabetes disease diagnosis using neural networks", Expert Systems with Applications, 36, 8610-8615.
[6] Mohamed, E. I., Linderm, R., Perriello, G., Di Daniele, N., Poppl, S. J., & De Lorenzo, A. (2002), "Predicting type 2 diabetes using an electronic nose-base artificial neural network analysis", Diabetes Nutrition & Metabolism, 15(4), 215-221.
[7] Saraoglu, H.M., & Kocan, M. (2010), "A study on non-invasive detection of blood glucose concentration from human palm perspiration by using artificial neural networks", Expert Systems, 27(3), 156-165.
[8] Diabetes Care, American Diabetes Association, January 2008, Vol 31,pp 55-60
[9] Diabetes Care, American Diabetes Association, January 2010, Vol 33,pp 11-13
[10] Diabetes Voice, December 2007, Vol 52, pp 33-34
[11] Kamei, T., T. Tsuda, Y. Mibu, S. Kitagawa, H. Wada, K. Naitoh and K. Nakashima (1998a), "Novel instrumentation for determination of ethanol concentrations in human perspiration by gas chromatography and a good interrelationship between ethanol concentrations in sweat and blood", Analytica Chimica Acta, 365 (1-3), 259-266.
[12] Kamei, T., T. Tsuda, S. Kitagawa, K. Naitoh, K. Nakashima and T. Ohhashi (1998b), "Physical stimuli and emotional stress-induced sweat secretions in the human palm and forehead", Analytica Chimica Acta, 365, 319-326
[13] Saraoglu, H. M. ve Koçan M., "Determination of Blood Glucose Level Based Breath Analysis by a Quartz Crystal Microbalance Sensor Array", IEEE Sensors Journal, Special Issue on the Future of Sensors and Instrumentation for Human Breath Analysis, 10, 104-109, 2010
[14] Masumura, M., S. Shinomiya, K. Nagata, T. Kato, Y. Matsuzaki, S. Nagaoka, R. Inoue, J. Perspiration Res., 3, 43-45, 1996
[15] Kuno, Y., Human Perspiration, C.C. Thomas Publisher, Springfield,IL, 1956.
[16] Ohhashi T., M. Uono (eds.), "Palmer perspiration - measurement and clinical applications (in Japanese)", Life Medicom Co, Ltd., Nagoya, 1993.
[17] Groscurth, P., "Anatomy of sweat glands". In: Kreyden OP, Bo¨ni R, Burg G, editors. Hyperhidrosis and botulinum toxin in dermatology. Basel: Karger, 1-9, 2002.
[18] Kamei, T., T. Tsuda, S. Kitagawa, K. Naitoh, K. Nakashima, T. Ohhashi, "Physical stimuli and emotional stress-induced sweat secretions in the human palm and forehead", Analytica Chimica Acta, 365, 319-326, 1998 b
[19] Huestis, M.A., J.M. Oyler , E.J. Cone , A.T. Wstadik , D. Schoendorfer , R.E. Joseph JR., "Sweat testing for cocaine, codeine and metabolites by gas chromatography-mass spectrometry, Journal of Chromatography ", 733, 247-264, 1999.
[20] Chang, B.W., S.J. Yeh, P.P. Tsai, H.C. Chang, "Monitoring perspiration from palms of hypohidrosis patients with a stopped-flow conductometric mini-system",Clinica Chimica Acta, 348, 107- 111, 2004.
[21] Asahina, M., A. Suzuki, M. Mori, T. Kanesaka, T. Hattori, "Emotional sweating response in a patient with bilateral amygdala damage", International Journal of Psychophysiology, 47, 87-93, 2003.
[22] Saraoglu, H. M. ve Koçan M., "A Study on Non-Invasive Detection of Blood Glucose Concentration from Human Palm Perspiration by Using Artificial Neural Networks", Expert Systems, 27(3), 156-165, 2010
[23] Vapnik, V. , Statistical Learning Theory, Wiley,1998
[24] Brownz M.P.S., Grundyz W.N., Linz D., Cristianini N., Sugnet C., Ares, JR. M., Hausslerz D., "Support Vector Machine Classification of Microarray Gene Expression Data", UCSC-CRL-99-09
[25] Burges, C. J. C. (1998). "A tutorial on support vector machines for pattern recognition", Data Mining and Knowledge Discovery, 2(2):121- 167.
[26] V.N. Vapnik, "An Overview of Statistical Learning Theory", IEEE Trans. Neural Networks 10 (5) (1999).
[27] Saraoglu, H.M., Yildirim, M., Ozbeyaz, A., TEMURTAS, F., (2011), "Kandaki Glikoz ve HbA1c Diyabet Tanı Değerlerinin Avuç İçi Terleme Ölçümleri Kullanılarak DVM ile Sınıflandırması", In Proceedings of Tip Teknolojileri Ulusal Kongresi (Tip Tekno 11), October 13-16, Antalya
[28] (2012),Univesty of Strathclyde website. (Online). Available:http://www.strath.ac.uk/media/departments/eee/cesip/cesipse minar/Jinchang_Ren_seminar. Pdf
[29] (2012), A-SVM based server for rice website. (Online). Available:www.imtech.res.in/raghava/rbpred/algorithm.html.