Detection of type-2 diabetes using characteristics of toe photoplethysmogram by applying support vector machine

• Autorzy: Nirala Neelamshobha , Periyasamy R. , Singh Bikesh Kumar , Kumar Awanish

Identyfikatory

DOI

10.1016/j.bbe.2018.09.007

• Języki publikacji: EN

Abstrakty

EN

Diabetes mellitus (DM) is one of the most widespread and rapidly growing diseases. With its advancement, DM-related complications are also increasing. We used characteristic features of toe photoplethysmogram for the detection of type-2 DM using support vector machine (SVM). We collected toe PPG signal, from 58 healthy and 83 type-2 DM subjects. From each PPG signal 37 different features were extracted for further classification. To improve the performance of SVM and reduce the noisy data we employed hybrid feature selection technique that reduces the feature set of 37 to 10 on the basis of majority voting. Using 10 selected features set, we gained an accuracy of 97.87%, sensitivity of 98.78% and specificity of 96.61%. Further for the validation of our method we need to do random population test, so that it can be used as a non-invasive screening tool. Photoplethysmogram is an economic, technically easy and completely non-invasive method for both physician and subject. With the high accuracy that we obtained, we hope that our work will help the clinician in screening of diabetes and adopting suitable treatment plan for preventing end organ damage.

Słowa kluczowe

EN

type 2 diabetes; feature selection technique; photoplethysmogram; principal component analysis; second derivative; support vector machine

PL

cukrzyca typu 2; selekcja cech; fotopletyzmogram; analiza składników głównych; druga pochodna; maszyna wektorów nośnych

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 1
• Strony: 38--51
• Opis fizyczny: Bibliogr. 49 poz., rys., tab., wykr.

Twórcy

autor

Nirala Neelamshobha

• Department of Biomedical Engineering, National Institute of Technology Raipur, G.E. Road, Raipur 492010, Chhattisgarh, India

autor

Periyasamy R.

• Department of Biomedical Engineering, National Institute of Tiruchirappalli, Tamil Nadu, India

autor

Singh Bikesh Kumar

• Department of Biomedical Engineering, National Institute of Technology Raipur, Raipur, Chhattisgarh, India

autor

Kumar Awanish

• Department of Biotechnology, National Institute of Technology Raipur, Raipur, Chhattisgarh, India

Bibliografia

• [1] IDF. IDF Diabetes Atlas; 2015. http://dx.doi.org/10.1289/image.ehp.v119.i03.
• [2] World Health Organization. Global Report on Diabetes; 2016;88, ISBN 9789241565257.
• [3] Litwak L, Goh S-Y, Hussein Z, Malek R, Prusty V, Khamseh ME. Prevalence of diabetes complications in people with type 2 diabetes mellitus and its association with baseline characteristics in the multinational A1chieve study. Diabetol Metab Syndr 2013;5:57. http://dx.doi.org/10.1186/1758-5996-5-57.
• [4] Hubena G, Osina O, Prindesova B, Vasicko T. Assessment of the peripheral blood flow of lower limbs in patients with diabetes mellitus with the use of digital photoplethysmography. Acta Medica Martiniana 2015;15:21–9. http://dx.doi.org/10.1515/acm-2015-0008.
• [5] Girish M, Bengalorkar TNK. Culture and sensitivity pattern of micro-organism isolated from diabetic foot infections in a tertiary care hospital. Int J Cur Biomed Pharm Res 2011;1:34–40.
• [6] Mohan V, Sandeep S, Deepa R, Shah B, Varghese C. Epidemiology of type 2 diabetes: Indian scenario. Indian J Med Res 2007;125:217–30.
• [7] Adhikari P, Pathak R, Kotian S. Validation of the MDRF-Indian Diabetes Risk Score (IDRS) in another south Indian population through the Boloor Diabetes Study (BDS). J Assoc Physicians India 2010;58:434–6.
• [8] Shafique M, Kyriacou PA, Pal SK. Investigation of photoplethysmographic signals and blood oxygen saturation values on healthy volunteers during cuff-induced hypoperfusion using a multimode PPG/SpO2 sensor. Med Biol Eng Comput 2012;50:575–83.
• [9] Pilt K, Ferenets R, Meigas K, Lindberg L, Temitski K, Viigimaa M. New photoplethysmographic signal analysis algorithm for arterial stiffness estimation. Sci World J 2013;2013:1–9. http://dx.doi.org/10.1155/2013/169035.
• [10] Pilt K, Meigas K, Kööts K, Viigimaa M. Photoplethysmographic signal rising front analysis for the discrimination of subjects with increased arterial ageing. Proc Est Acad Sci 2014;63:309–14. http://dx.doi.org/10.3176/proc.2014.3.03.
• [11] Allen J. Photoplethysmography and its application in clinical physiological measurement. Physiol Meas 2007;28: R1–39. http://dx.doi.org/10.1088/0967-3334/28/3/R01.
• [12] Usman S, Reaz MBI, Ali MAM. Measuring arterial stiffness using photoplethysmogram. Acta Sci Technol 2014;36:123–8.
• [13] Spigulis J, Kukulis I, Fridenberga E, Venckus G. Potential of advanced photoplethysmography sensing for noninvasive vascular diagnostics and early screening. Proc Clin Diagnostic Syst Technol Instrum 2002;4625. http://dx.doi.org/10.1117/12.469789.
• [14] Usman S, Reaz MMBI, Ali MAM. Repeated measurement analysis of the area under the curve of photoplethysmogram among diabetic patients. Life Sci J 2013;10:532–9.
• [15] Rozi RM, Usman S, Mohd Ali MA, Reaz MBI. Second derivatives of photoplethysmography (PPG) for estimating vascular aging of atherosclerotic patients. 2012 IEEE-EMBS Conf Biomed Eng Sci IECBES. 2012. pp. 256–9. http://dx.doi.org/10.1109/IECBE.S.2012.6498064.
• [16] Usman bt S, Ali MA, bin M, Reaz MMBI, Chellapan K. Second derivative of photoplethysmogram in estimating vascular aging among diabetic patients. 2009 Int. Conf. Postgraduates Tech. IEEE. 2009. pp. 1–3. http://dx.doi.org/10.1109/TECHPOS.2009.5412099.
• [17] Keikhosravi A, Aghajani H, Zahedi E. Discrimination of bilateral finger photoplethysmogram responses to reactive hyperemia in diabetic and healthy subjects using a differential vascular model framework. Physiol Meas 2013;34:513–25. http://dx.doi.org/10.1088/0967-3334/34/5/513.
• [18] Moreno EM, Lujan MJA, Torrres Rusinol M, Fernandez PJ, Nunez Manrique P, Trivino CA, et al. Type 2 diabetes screening test by means of a pulse oximeter. IEEE Trans Biomed Eng 2017;64:341–51. http://dx.doi.org/10.1109/TBME.2016.2554661.
• [19] Reddy VR, Choudhury AD, Deshpande P, Jayaraman S, Thokala NK, Kaliaperumal V. DMSense: a non-invasive diabetes mellitus classification system using photoplethysmogram signal. 2017 IEEE Int Conf Pervasive Comput Commun Work PerCom Work. 2017. pp. 71–3. http://dx.doi.org/10.1109/PERCOMW.2017.7917526.
• [20] Polat K, Gunes S, Arslan A. A cascade learning system for classification of diabetes disease: generalized discriminant analysis and least square support vector machine. Expert Syst Appl 2008;34:482–7. http://dx.doi.org/10.1016/j.eswa.2006.09.012.
• [21] Purnami SW, Embong A, Zain JM, Rahayu SP. A new smooth support vector machine and its applications in diabetes disease diagnosis. J Comput Sci 2009;5:1003–8. http://dx.doi.org/10.13254/j.jare.2013.0223.
• [22] Barakat N, Bradley AP, Barakat MNH. Intelligible support vector machines for diagnosis of diabetes mellitus. Inf Technol Biomed IEEE Trans 2010;14:1114–20. http://dx.doi.org/10.1109/TITB.2009.2039485.
• [23] Çalisir D, Dogantekin E. An automatic diabetes diagnosis system based on LDA-wavelet support vector machine classifier. Expert Syst Appl 2011;38:8311–5. http://dx.doi.org/10.1016/j.eswa.11.01.017.
• [24] Giveki D, Salimi H, Bahmanyar G, Khademian Y. Automatic detection of diabetes diagnosis using feature weighted support vector machines based on mutual information and modified Cuckoo search; 2012.
• [25] Soliman SO, AboElhamd E. Classification of diabetes mellitus using modified particle swarm optimization and least squares support vector machine. Int J Comput Trends Technol 2014;8:38–44. http://dx.doi.org/10.14445/22312803/IJCTT-V8P108.
• [26] Ribeiro ÁC, Barros AK, Santana E, Príncipe JC. Diabetes classification using a redundancy reduction preprocessor. Rev Bras Eng Biomed 2015;31:97–106. http://dx.doi.org/10.1590/1517-3151.0608.
• [27] Osman AH, Aljahdali HM. Diabetes disease diagnosis method based on feature extraction using K-SVM. Int J Adv Comput Sci Appl 2017;8:236–44.
• 28] Ubeyli ED. Comparison of different classification algorithms in clinical decision-making. Expert Syst 2007;24:17–31.
• [29] Kandhasamy JP, Balamurali S. Performance analysis of classifier models to predict diabetes mellitus. Proc Comput Sci 2015;47:45–51. http://dx.doi.org/10.1016/j.procs.2015.03.182.
• [30] Nai-Arun N, Moungmai R. Comparison of classifiers for the risk of diabetes prediction. Proc Comput Sci 2015;69:132–42. http://dx.doi.org/10.1016/j.procs.2015.10.014.
• [31] Daghistani T, Alshammari R. Diagnosis of diabetes by applying data mining classification techniques. Int J Adv Comput Sci Appl 2016;7:329–32. http://dx.doi.org/10.14569/IJACSA.2016.070747.
• [32] Razavian N, Blecker S, Schmidt AM, Smith-McLallen A, Nigam S, Sontag D. Population-level prediction of type 2 diabetes from claims data and analysis of risk factors. Big Data 2015;3:277–87. http://dx.doi.org/10.1089/big.2015.0020.
• [33] Zhang J, Xu J, Hu X, Chen Q, Tu L, Huang J, et al. Diagnostic method of diabetes based on support vector machine and tongue images. Biomed Res Int 2017;2017. http://dx.doi.org/10.1155/2017/7961494.
• [34] Singh BK, Verma K, Thoke AS, Suri JS. Risk stratification of 2D ultrasound-based breast lesions using hybrid feature selection in machine learning paradigm. Measurement 2017;105:146–57. http://dx.doi.org/10.1016/j.measurement.2017.01.016.
• [35] Kong B, Kim D, Shahzad A, Yoon K, Kim K. A study on a hypertension diagnosis method using PPG and new features by PCA. Proc Symp Korean Inst Commun Inf Sci 2016;1:504–5.
• [36] Allen J, Oates CP, Lees TA, Murray A. Photoplethysmography detection of lower limb peripheral arterial occlusive disease: a comparison of pulse timing, amplitude and shape characteristics. Physiol Meas 2005;26:811–21. http://dx.doi.org/10.1088/0967-/26/5/3334018.
• [37] Alty SR, Angarita-Jaimes N, Millasseau SC, Chowienczyk PJ. Predicting arterial stiffness from the digital volume pulse waveform. IEEE Trans Biomed Eng 2007;54:2268–75. http://dx.doi.org/10.1109/TBME.2007.897805.
• [38] Guyon I. Practical feature selection: from correlation to causality; 2008;1–17.
• [39] Amit kumar Dewangan PA. Classification of sentimental reviews using machine learning techniques. Proc Comput Sci 2015;57:821–9. http://dx.doi.org/10.1016/j.procs.2015.07.523.
• [40] Singh BK, Verma K, Thoke AS. Fuzzy cluster based neural network classifier for classifying breast tumors in ultrasound images. Expert Syst Appl 2016;66:114–23. http://dx.doi.org/10.1016/j.eswa.2016.09.006.
• [41] Shrivastava VK, Londhe ND, Sonawane RS, Suri JS. A novel approach to multiclass psoriasis disease risk stratification: machine learning paradigm. Biomed Signal Process Control 2016;28:27–40. http://dx.doi.org/10.1016/j.bspc.2016.04.001.
• [42] Han L, Luo S, Yu J, Pan L, Chen S. Rule extraction from support vector machines using ensemble learning approach: an application for diagnosis of diabetes. IEEE J Biomed Heal Inf 2015;19:728–34. http://dx.doi.org/10.1109/JBHI.2014.2325615.
• [43] Balakrishnan S, Narayanaswamy R. Feature selection using FCBF in type II diabetes databases. Comput Internet 2009;1–8.
• [44] Kavakiotis I, Tsave O, Salifoglou A, Maglaveras N, Vlahavas I, Chouvarda I. Machine learning and data mining methods in diabetes research. Comput Struct Biotechnol J 2017;15:104–16. http://dx.doi.org/10.1016/j.csbj.2016.12.005.
• [45] Pimple MS. Application of support vector machine for diagnosis of diabetes: a systematic review. J Comput Eng 2016;13–7.
• [46] Kumari VA, Chitra R. Classification of diabetes disease using support vector machine. Int J Eng Res Appl 2013;3:1797–801.
• [47] Abdillah AA, Suwarno S. Diagnosis of diabetes using support vector machines with radial basis function kernels. Int J Technol 2016;7:849. http://dx.doi.org/10.14716/ijtech.v7i5.1370.
• [48] Shariati NH, Zahedi E, Jajai HM. Classification of vascular function in upper limb using bilateral photoplethysmographic signals. Physiol Meas 2008;29:365–74. http://dx.doi.org/10.1088/0967-3334/29/3/007.
• [49] Bharati S, Gidveer G. Waveform analysis of pulse wave detected in the finger tip with PPG 2012;3:92–100.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).