A novel pulse plethysmograph signal analysis method for identification of myocardial infarction, dilated cardiomyopathy, and hypertension

Cardiac diseases (CDs) are one of the leading causes of the growing global mortality rate. Early detection of CDs is necessary to avoid a high increase in the mortality rate. Machine learning-based computer-aided diagnosis of CDs using various physiological signals has recently been used by researchers. Since pulse plethysmograph (PuPG) signal contains a wealth of information about cardiac pathologies, therefore, this paper presents an expert system design for the automatic diagnosis of cardiac disorders like hypertension, dilated cardiomyopathy and myocardial infarction using a novel fingertip PuPG signal analysis. The proposed system first performs signal denoising of raw PuPG sensor data using discrete wavelet transform (DWT). After signal segmentation, it extracts discriminant and simplest time- domain features, which are used to perform the detection of normal and abnormal subjects through a support vector machine (SVM) classifier. The proposed detection and classification systems are tested using 10-fold cross-validation which yielded an average accuracy of 98.90%, sensitivity of 100.00%, and specificity of 98.02% for detection (normal vs. abnormal) experiments with only four features and an average accuracy of 97.57% for the multiclass problem using five computationally inexpensive features. Comparative analysis with existing methods based on electrocardiogram, photoplethysmograph, and phonocardiogram revealed that the proposed system has high eﬀiciency in terms of CD detection with very low computational complexity. The findings of this work provide insights into the contribution of PuPG signal analysis towards accurate detection of cardiac disorders through innovative, low cost, and noninvasive methods. Such a system with mobile cardiac health monitoring could be used as a counterpart or second opinion with clinical diagnoses and provide patients with additional but subtle indicators of varying heart dynamics.

PDF

___

1] Banerjee R, Bhattacharya S, Bandyopadhyay S, Pal A, Mandana K. Non-invasive detection of coronary artery disease based on clinical information and cardiovascular signals: a two-stage classification approach. In: IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS); Karlstad, Sweden; 2018. pp. 205-210.
[2] McGill Jr HC, McMahan CA, Gidding SS. Preventing heart disease in the 21st century: implications of the Pathobiological Determinants of Atherosclerosis in Youth (PDAY) study. Circulation 2008; 117 (9): 1216-1227.
[3] Rubins U, Grabovskis A, Grube J, Kukulis I. Photoplethysmography analysis of artery properties in patients with cardiovascular diseases. In: 14th Nordic-Baltic Conference on Biomedical Engineering and Medical Physics; Riga, Latvia; 2008. pp. 319-322.
[4] Gunarathne A, Patel JV, Hughes EA, Lip GY. Measurement of stiffness index by digital volume pulse analysis technique: clinical utility in cardiovascular disease risk stratification. American Journal of Hypertension 2008; 21 (8): 866-872.
[5] Bedford DE. The ancient art of feeling the pulse. British Heart Journal 1951; 13 (4): 423.
[6] Caragnano A, Aleksova A, Bulfoni M, Cervellin C, Rolle IG et al. Autophagy and inflammasome activation in dilated cardiomyopathy. Journal of Clinical Medicine 2019; 8 (10): 1519.
[7] Towbin JA, Bowles NE. The failing heart. Nature 2002; 415 (6868): 227-233. doi: 10.1038/415227a
[8] Calvillo L, Gironacci MM, Crotti L, Meroni PL, Parati G. Neuroimmune crosstalk in the pathophysiology of hypertension. Nature Reviews Cardiology 2019. doi: 10.1038/s41569-019-0178-1
[9] Solak Y, Afsar B, Vaziri ND, Aslan G, Yalcin CE et al. Hypertension as an autoimmune and inflammatory disease. Hypertension Research 2016; 39: 567. doi: 10.1038/hr.2016.35
[10] Chan G, Cooper R, Hosanee M, Welykholowa K, Kyriacou PA et al. Multi-site photoplethysmography technology for blood pressure assessment: challenges and recommendations. Journal of Clinical Medicine 2019; 8 (11): 1827.
[11] Thygesen K, Alpert JS, Jaffe AS, Simoons ML, Chaitman BR et al. Third universal definition of myocardial infarction. Nature Reviews Cardiology 2012; 9: 620. doi: 10.1038/nrcardio.2012.122
[12] Sharma M, San Tan R, Acharya UR. A novel automated diagnostic system for classification of myocardial infarction ECG signals using an optimal biorthogonal filter bank. Computers in Biology and Medicine 2018; 102: 341-356.
[13] Adam M, Oh SL, Sudarshan VK, Koh JE, Hagiwara Y et al. Automated characterization of cardiovascular diseases using relative wavelet nonlinear features extracted from ECG signals. Computer Methods and Programs in Biomedicine 2018; 161: 133-143.
[14] Kora P. ECG based myocardial infarction detection using hybrid firefly algorithm. Computer Methods and Programs in Biomedicine 2017; 152: 141-148.
[15] Tripathy R, Dandapat S. Detection of cardiac abnormalities from multilead ECG using multiscale phase alternation features. Journal of Medical Systems 2016; 40 (6): 143.
[16] Zarrabi M, Parsaei H, Boostani R, Zare A, Dorfeshan Z et al. A system for accurately predicting the risk of myocardial infarction using PCG, ECG and clinical features. Biomedical Engineering: Applications, Basis and Communications 2017; 29 (03): 1750023.
[17] Sharma L, Tripathy R, Dandapat S. Multiscale energy and eigenspace approach to detection and localization of myocardial infarction. IEEE Transactions on Biomedical Engineering 2015; 62 (7): 1827-1837.
[18] Fu L, Lu B, Nie B, Peng Z, Liu H et al. Hybrid network with attention mechanism for detection and location of Myocardial Infarction based on 12-lead electrocardiogram signals. Sensors 2020; 20 (4): 1020.
[19] Kamshilin AA, Margaryants NB. Origin of photoplethysmographic waveform at green light. Physics Procedia 2017; 86: 72-80.
20] Khan MU, Aziz S, Malik A, Imtiaz MA. Detection of myocardial infarction using pulse plethysmograph signals. In: 2019 International Conference on Frontiers of Information Technology (FIT); Islamabad, Pakistan; 2019. pp. 95-955.
[21] Khan MU, Aziz S, Amjad F, Mohsin M. Detection of dilated cardiomyopathy using pulse plethysmographic signal analysis. In: 22nd International Multitopic Conference (INMIC); Islamabad, Pakistan; 2019. pp. 1-5.
[22] Khan MU, Aziz S, Iqtidar K, Zainab A, Saud A. Prediction of acute coronary syndrome using pulse Plethysmograph. In: 4th International Conference on Emerging Trends in Engineering, Sciences and Technology (ICEEST); Karachi, Pakistan; 2019. pp. 1-6.
[23] Paradkar N, Chowdhury SR. Coronary artery disease detection using photoplethysmography. In: 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Bali, Indonesia; 2017. pp. 100-103.
[24] Ave A, Fauzan H, Adhitya SR, Zakaria H. Early detection of cardiovascular disease with photoplethysmogram (PPG) sensor. In: International Conference on Electrical Engineering and Informatics (ICEEI); Bali, Indonesia; 2015. pp. 676-681.
[25] Mahri N, Gan KB, Meswari R, Jaafar MH, Mohd Ali MA. Utilization of second derivative photoplethysmographic features for myocardial infarction classification. Journal of Medical Engineering & Technology 2017; 41 (4): 298-308.
[26] Fitriyani NL, Syafrudin M, Alfian G, Rhee J. Development of disease prediction model based on ensemble learning approach for diabetes and hypertension. IEEE Access 2019; 7: 144777-144789.
[27] Lan Kc, Raknim P, Kao WF, Huang JH. Toward hypertension prediction based on PPG-derived HRV signals: a feasibility study. Journal of Medical Systems 2018; 42 (6): 103.
[28] Liang Y, Chen Z, Ward R, Elgendi M. Hypertension assessment using photoplethysmography: a risk stratification approach. Journal of Clinical Medicine 2019; 8 (1): 12.
[29] Liu F, Zhou X, Wang Z, Cao J, Wang H et al. Unobtrusive mattress-based identification of hypertension by integrating classification and association rule mining. Sensors 2019; 19 (7): 1489.
[30] Baranchuk A, Kang J, Shaw C, Campbell D, Ribas S et al. Electromagnetic interference of communication devices on ECG machines. Clinical Cardiology: An International Indexed and Peer‐Reviewed Journal for Advances in the Treatment of Cardiovascular Disease 2009; 32 (10): 588-592.
[31] Klein A, Djaiani G. Mobile phones in the hospital–past, present and future. Anaesthesia 2003; 58 (4): 353-357.
[32] Sujadevi V, Soman K, Vinayakumar R, Sankar AP. Anomaly detection in phonocardiogram employing deep learning. In: Computational Intelligence in Data Mining; Xiamen, China; 2019. pp. 525-534.
[33] Kranjec J, Beguš S, Geršak G, Drnovšek J. Non-contact heart rate and heart rate variability measurements: a review. Biomedical Signal Processing and Control 2014; 13: 102-112.
[34] Wang D, Khuon L. Using myDAQ and LabView to develop a single-channel EEG for a multi-modality epileptic seizure detection platform. In: 39th Annual Northeast Bioengineering Conference; New York, NY, USA; 2013. pp. 161-162.
[35] Başpınar U, Şenyürek VY, Doğan B, Varol HS. A comparative study of denoising sEMG signals. Turkish Journal of Electrical Engineering & Computer Sciences 2015; 23 (4): 931-944.
[36] Hekim M. The classification of EEG signals using discretization-based entropy and the adaptive neuro-fuzzy inference system. Turkish Journal of Electrical Engineering & Computer Sciences 2016; 24 (1): pp. 285-297.
[37] Bhowmik T, Dey J, Tiwari VN. A novel method for accurate estimation of HRV from smartwatch PPG signals. In: 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Honolulu, HI, USA; 2017. pp. 109-112.
[38] Arvanaghi R, Daneshvar S, Seyedarabi H, Goshvarpour A. Fusion of ECG and ABP signals based on wavelet transform for cardiac arrhythmias classification. Computer Methods and Programs in Biomedicine 2017. 151: 71-78.
39] Joseph G, Joseph A, Titus G, Thomas RM, Jose D. Photoplethysmogram (PPG) signal analysis and wavelet de-noising. In: Annual International Conference on Emerging Research Areas: Magnetics, Machines and Drives (AICERA/iCMMD); India; 2014. pp. 1-5.
[40] Ghazali F, Hacine-Gharbi A, Ravier P, Mohamadi T. Extraction and selection of statistical harmonics features for electrical appliances identification using k-NN classifier combined with voting rules method. Turkish Journal of Electrical Engineering & Computer Sciences 2019; 27 (4): 2980-2997. doi: 10.3906/elk-1812-80
[41] Khan MU, Aziz S, Ibraheem S, Butt A, Shahid H. Characterization of term and preterm deliveries using electro- hysterograms signatures. In: IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON); New York, NY, USA; 2019. pp. 899-905.
[42] Kabaoğlu RO. A fault detection, diagnosis, and reconfiguration method via support vector machines. Turkish Journal of Electrical Engineering & Computer Sciences 2015; 23 (2): 589-601. doi: 10.3906/elk-1301-96
[43] Işık Ş, Özkan K, Ergin S. Biometric person authentication framework using polynomial curve fitting-based ECG feature extraction. Turkish Journal of Electrical Engineering & Computer Sciences 2019; 27 (5): 3682-3698.
[44] Aziz S, Khan MU, Alhaisoni M, Akram T, Altaf M. Phonocardiogram Signal Processing for Automatic Diagnosis of Congenital Heart Disorders through Fusion of Temporal and Cepstral Features. Sensors 2020; 20 (13): 3790. doi: 10.3390/s20133790
[45] Weston J, Watkins C. Multi-class support vector machines. Technical Report CSD-TR-980-4. London, UK: Royal Holloway University of London, 1998.
[46] Aziz S, Awais M, Akram T, Khan U, Alhussein M et al. Automatic scene recognition through acoustic classification for behavioral robotics. Electronics 2019; 8 (5): 483. doi: 10.3390/electronics8050483
[47] Khan MU, Aziz S, Zainab A, Tanveer H, Iqtidar K et al. Biometric system using PCG signal analysis: a new method of person identification. In: International Conference on Electrical, Communication, and Computer Engineering (ICECCE); İstanbul, Turkey; 2020. pp. 1-6.
[48] Khan MU, Aziz S, Ch JM, Shahjehan A, Imtiaz A et al. Detection of acute coronary syndrome using electrocar- diogram signal analysis. In: International Conference on Electrical, Communication, and Computer Engineering (ICECCE); İstanbul, Turkey; 2020. pp. 1-6.
[49] Banerjee R, Vempada R, Mandana K, Choudhury AD, Pal A. Identifying coronary artery disease from photo- plethysmogram. In: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct; USA; 2016. pp. 1084-1088.
[50] Mahri N, Gan KB, Mohd Ali MA, Jaafar MH, Meswari R. Analysis of myocardial infarction signals using optical technique. Journal of Medical Engineering & Technology 2016; 40 (4): 155-161.