‫ مدل‌سازی آشوب‌گرای سیگنال فوتوپلتیسموگرام جهت تخمین فشارخون مبتنی بر شبکه‌های عصبی عمیق کانولوشنی

مدل‌سازی آشوب‌گرای سیگنال فوتوپلتیسموگرام جهت تخمین فشارخون مبتنی بر شبکه‌های عصبی عمیق کانولوشنی

محمدباقر خدابخشی, نعیم اسلامیه‌همدانی, سیده‌زهره صدرالدینی

چکیده

تخمین فشار خون به صورت غیرتهاجمی از طریق پردازش سیگنال‌های محیطی شامل سیگنال‌های قلبی و فوتوپلتیسموگرام از مسائل مورد توجه در حوزه پردازش سیگنال‌های پزشکی است. عمده مطالعات بر استخراج ویژگی‌های متنوع از سیگنال‌های محیطی و تخمین فشار خون به وسیله مدل‌های مبتنی بر هوش محاسباتی متمرکز هستند. در این مقاله یک مدل شبکه عصبی عمیق کانولوشنی پیشنهاد شده که با به کارگیری شکل موج سیگنال فوتوپلتیسموگرام و ویژگی‌های آشوبگرای آن می‌تواند فشار خون را با دقت بالایی تخمین زند. ویژگی آشوب‌گرای سیگنال در فضای فاز با نام آنالیز کمی بازرخداد به همراه نمونه‌های سری زمانی فوتوپلتیسموگرام به عنوان ورودی مدل شبکه عصبی عمیق کانولوشنی در نظر گرفته شده‌اند. نتایج آزمون مدل پیشنهادی بر روی دادگان استخراجی از مجموعه داده MIMIC-II بر اساس استانداردهای انجمن فشار خون بریتانیا (BHS) و انجمن توسعه ابزار پزشکی (AAMI) نشان می‌دهد که این ترکیب در ورودی می‌تواند دقت بالایی در تخمین فشار خون فراهم کند. به طور خاص در تخمین فشار خون دیاستول و سیستول، معیار ضریب همبستگی پیرسون (R) برای روش پیشنهادی به ترتیب 93916/0 و 93357/0 به دست آمد. مطابق استاندارد BHS این روش حائز درجه کیفی A در تخمین فشارخون است و دارای میانگین و انحراف معیار خطای تخمین برای فشار خون دیاستول و سیستول به ترتیب برابر 5/3±45/0 و 69/6±48/0 مطابق نیازمندی‌های استاندارد AAMI می‌باشد.

کلمات کلیدی

پردازش سیگنال, شبکه‌های عصبی کانولوشنی, یادگیری عمیق, آشوب, آنالیز کمی بازرُخداد

مراجع

  • [1] W.-H. Lin, F. Chen, Y. Geng, N. Ji, P. Fang, and G. Li, "Towards accurate estimation of cuffless and continuous blood pressure using multi-order derivative and multivariate photoplethysmogram features," Biomedical Signal Processing and Control, vol. 63, p. 102198, 2021.
  • [2] M. S. Tanveer and M. K. Hasan, "Cuffless blood pressure estimation from electrocardiogram and photoplethysmogram using waveform based ANN-LSTM network," Biomedical Signal Processing and Control, vol. 51, pp. 382-392, 2019.
  • [3] J. Esmaelpoor, M. H. Moradi, and A. Kadkhodamohammadi, "A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals," Computers in Biology and Medicine, vol. 120, p. 103719, 2020.
  • [4] M. Simjanoska, M. Gjoreski, M. Gams, and A. Madevska Bogdanova, "Non-invasive blood pressure estimation from ECG using machine learning techniques," Sensors, vol. 18, no. 4, p. 1160, 2018.
  • [5] A. Attarpour, A. Mahnam, A. Aminitabar, and H. Samani, "Cuff-less continuous measurement of blood pressure using wrist and fingertip photo-plethysmograms: Evaluation and feature analysis," Biomedical Signal Processing and Control, vol. 49, pp. 212-220, 2019.
  • [6] C. El-Hajj and P. Kyriacou, "Deep learning models for cuffless blood pressure monitoring from PPG signals using attention mechanism," Biomedical Signal Processing and Control, vol. 65, p. 102301, 2021.
  • [7] H. Gesche, D. Grosskurth, G. Küchler, and A. Patzak, "Continuous blood pressure measurement by using the pulse transit time: comparison to a cuff-based method," European journal of applied physiology, vol. 112, no. 1, pp. 309-315, 2012.
  • [8] X.-R. Ding et al., "Continuous blood pressure measurement from invasive to unobtrusive: Celebration of 200th birth anniversary of Carl Ludwig," IEEE journal of biomedical and health informatics, vol. 20, no. 6, pp. 1455-1465, 2016.
  • [9] R. Mukkamala and J.-O. Hahn, "Toward ubiquitous blood pressure monitoring via pulse transit time: Predictions on maximum calibration period and acceptable error limits," IEEE Transactions on Biomedical Engineering, vol. 65, no. 6, pp. 1410-1420, 2017.
  • [10] T. H. Huynh, R. Jafari, and W.-Y. Chung, "Noninvasive cuffless blood pressure estimation using pulse transit time and impedance plethysmography," IEEE Transactions on Biomedical Engineering, vol. 66, no. 4, pp. 967-976, 2018.
  • [11] X.-R. Ding, Y.-T. Zhang, J. Liu, W.-X. Dai, and H. K. Tsang, "Continuous cuffless blood pressure estimation using pulse transit time and photoplethysmogram intensity ratio," IEEE Transactions on Biomedical Engineering, vol. 63, no. 5, pp. 964-972, 2015.
  • [12] Y. Z. Yoon, J. M. Kang, Y. Kwon, S. Park, S. Noh, Y. Kim, and S. W. Hwang, "Cuff-less blood pressure estimation using pulse waveform analysis and pulse arrival time," IEEE journal of biomedical and health informatics, vol. 22, no. 4, pp. 1068-1074, 2017.
  • [13] M. Kachuee, M. M. Kiani, H. Mohammadzade, and M. Shabany, "Cuffless blood pressure estimation algorithms for continuous health-care monitoring," IEEE Transactions on Biomedical Engineering, vol. 64, no. 4, pp. 859-869, 2016.
  • [14] M. Forouzanfar, S. Ahmad, I. Batkin, H. R. Dajani, V. Z. Groza, and M. Bolic, "Coefficient-free blood pressure estimation based on pulse transit time–cuff pressure dependence," IEEE Transactions on Biomedical Engineering, vol. 60, no. 7, pp. 1814-1824, 2013.
  • [15] I. Sharifi, S. Goudarzi, and M. B. Khodabakhshi, "A novel dynamical approach in continuous cuffless blood pressure estimation based on ECG and PPG signals," Artificial intelligence in medicine, vol. 97, pp. 143-151, 2019.
  • [16] F. Miao, B. Wen, Z. Hu, G. Fortino, X. P. Wang, and Y. Li, "Continuous blood pressure measurement from one-channel electrocardiogram signal using deep-learning techniques," Artificial Intelligence in Medicine, vol. 108, p. 101919, 2020.
  • [17] G. Ward, P. Milliken, B. Patel, and N. McMahon, "Comparison of non-invasive and implanted telemetric measurement of blood pressure and electrocardiogram in conscious beagle dogs," Journal of pharmacological and toxicological methods, vol. 66, no. 2, pp. 106-113, 2012.
  • [18] G. Thambiraj, U. Gandhi, U. Mangalanathan, V. J. M. Jose, and M. Anand, "Investigation on the effect of Womersley number, ECG and PPG features for cuff less blood pressure estimation using machine learning," Biomedical Signal Processing and Control, vol. 60, p. 101942, 2020.
  • [19] F. Riaz, M. A. Azad, J. Arshad, M. Imran, A. Hassan, and S. Rehman, "Pervasive blood pressure monitoring using Photoplethysmogram (PPG) sensor," Future Generation Computer Systems, vol. 98, pp. 120-130, 2019.
  • [20] U. Senturk, K. Polat, and I. Yucedag, "A non-invasive continuous cuffless blood pressure estimation using dynamic Recurrent Neural Networks," Applied Acoustics, vol. 170, p. 107534, 2020.
  • [21] Z. Xu, J. Liu, X. Chen, Y. Wang, and Z. Zhao, "Continuous blood pressure estimation based on multiple parameters from eletrocardiogram and photoplethysmogram by Back-propagation neural network," Computers in Industry, vol. 89, pp. 50-59, 2017.
  • [22] P. Melin, I. Miramontes, and G. Prado-Arechiga, "A hybrid model based on modular neural networks and fuzzy systems for classification of blood pressure and hypertension risk diagnosis," Expert Systems with Applications, vol. 107, pp. 146-164, 2018.
  • [23] A. Dervishi, "Fuzzy risk stratification and risk assessment model for clinical monitoring in the ICU," Computers in biology and medicine, vol. 87, pp. 169-178, 2017.
  • [24] Huang, J. Chi, Y. C. Tsai, P. Y. Wu, Y. H. Lien, C. Y. Chien, C. F. Kuo, J. F. Hung, S. C. Chen, and C. H. Kuo., "Predictive modeling of blood pressure during hemodialysis: a comparison of linear model, random forest, support vector regression, XGBoost, LASSO regression and ensemble method," Computer Methods and Programs in Biomedicine, vol. 195, p. 105536, 2020.
  • [25] M. W. K. Fong, E. Ng, K. E. Z. Jian, and T. J. Hong, "SVR ensemble-based continuous blood pressure prediction using multi-channel photoplethysmogram," Computers in biology and medicine, vol. 113, p. 103392, 2019.
  • [26] M. B. Khodabakhshi, M. H. Moradi, Z. M. Sanat, and P. Jafari Moghadam Fard, "Lung sound decomposition using recurrent fuzzy wavelet network," Journal of Intelligent & Fuzzy Systems, vol. 33, no. 4, pp. 2497-2508, 2017.
  • [27] F. Sohrabi and M. B. Khodabakhshi, "The trajectory intersection: an approach for nonlinear down-sampling," Chaos, Solitons & Fractals, vol. 124, pp. 10-17, 2019.
  • [28] G. Ouyang, X. Zhu, Z. Ju, and H. Liu, "Dynamical characteristics of surface EMG signals of hand grasps via recurrence plot," IEEE journal of biomedical and health informatics, vol. 18, no. 1, pp. 257-265, 2013.
  • [29] Y. Chen and H. Yang, "Multiscale recurrence analysis of long-term nonlinear and nonstationary time series," Chaos, Solitons & Fractals, vol. 45, no. 7, pp. 978-987, 2012.
  • [30] N. Marwan, N. Wessel, U. Meyerfeldt, A. Schirdewan, and J. Kurths, "Recurrence-plot-based measures of complexity and their application to heart-rate-variability data," Physical review E, vol. 66, no. 2, p. 026702, 2002.
  • [31] M. Saeed et al., "Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II): a public-access intensive care unit database," Critical care medicine, vol. 39, no. 5, p. 952, 2011.
  • [32] A. E. Johnson, M. M. Ghassemi, S. Nemati, K. E. Niehaus, D. A. Clifton, and G. D. Clifford, "Machine learning and decision support in critical care," Proceedings of the IEEE, vol. 104, no. 2, pp. 444-466, 2016.
  • [33] A. Ramakrishnan, A. Prathosh, and T. Ananthapadmanabha, "Threshold-independent QRS detection using the dynamic plosion index," IEEE Signal Processing Letters, vol. 21, no. 5, pp. 554-558, 2014.
  • [34] N. Marwan, Encounters with neighbours: current developments of concepts based on recurrence plots and their applications. Norbert Marwan, 2003.
  • [35] A. M. Fraser and H. L. Swinney, "Independent coordinates for strange attractors from mutual information," Physical review A, vol. 33, no. 2, p. 1134, 1986.
  • [36] M. B. Khodabakhshi and V. Saba, "A nonlinear dynamical approach to analysis of emotions using EEG signals based on the Poincaré map function and recurrence plots," Biomedical Engineering/Biomedizinische Technik, vol. 65, no. 5, pp. 507-520, 2020.
  • [37] U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, and H. Adeli, "Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals," Computers in biology and medicine, vol. 100, pp. 270-278, 2018.
  • [38] U. R. Acharya, H. Fujita, O. S. Lih, Y. Hagiwara, J. H. Tan, and M. Adam, "Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network," Information sciences, vol. 405, pp. 81-90, 2017.
  • [39] U. R. Acharya, H. Fujita, S. L. Oh, Y. Hagiwara, J. H. Tan, and M. Adam, "Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals," Information Sciences, vol. 415, pp. 190-198, 2017.
  • [40] R. Lawrence E., B. Williams, G. D. Johnston, G. A. MacGregor, L. Poston, J. F. Potter, N. R. Poulter, and G. Russell, "British Hypertension Society guidelines for hypertension management 1999: summary," Bmj, vol. 319, no. 7210, pp. 630-635, 1999.