Hyp-Net: Automated detection of hypertension using deep convolutional neural network and Gabor transform techniques with ballistocardiogram signals

• Autorzy: Gupta Kapil , Bajaj Varun , Ansari Irshad Ahmad , Acharya U. Rajendra

Identyfikatory

DOI

10.1016/j.bbe.2022.06.001

• Języki publikacji: EN

Abstrakty

EN

Hypertension (HPT) is a physiological abnormality characterized by high blood pressure, headache, wooziness, and fainting that may lead to various heart, kidney, or brain diseases. Detection and continuous monitoring of HPT by sphygmometer is arduous and hectic. Nowadays, ballistocardiogram (BCG) signals are used to determine HPT as it indicates the vibration of the heart. Usual linear and nonlinear hand-crafted machine learning methods are subjective, involve decomposition of signal, features elicitation, selection, and classification steps. In this work, a completely automated HPT detection system is proposed using time–frequency (T-F) spectral images and a convolutional neural network (CNN) for the accurate detection of HPTusing BCG signals. The BCG signals are subjected to Gabor transform (GT), smoothed pseudo-Wigner Ville distribution (SPWVD), and short-time Fourier transform (STFT) techniques to obtain T-F spectral images. These T-F spectral images are fed to benchmarked Alex-Net, Res-Net50, and proposed CNN (Hyp-Net) to develop the automated HPT detection model with a 10-fold cross-validation scheme. The proposed Hyp-Net obtained the highest detection accuracy of 97.65% with GT-based spectral images. In comparison to Alex-Net and Res-Net50 pre-trained models, our developed Hyp-Net needs minimal learnable parameters, makes it computationally fast and more efficient. This shows that our proposed model has outperformed other two transfer learning methods. The experimental results with collected BCG signals from a public dataset are provided to show the effectiveness of the presented technique for automated detection of HPT.

Słowa kluczowe

EN

ballistocardiography; hypertension; time frequency; spectral image; convolutional neural network

PL

balistokardiografia; nadciśnienie tętnicze; częstotliwość czasowa; obraz widmowy; sieć neuronowa konwolucyjna

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 3
• Strony: 784--796
• Opis fizyczny: Bibliogr. 68 poz., rys., tab., wykr.

Twórcy

autor

Gupta Kapil

• Electronics and Communication Discipline, Indian Institute of Information Technology Design and Manufacturing, Jabalpur, MP 482005, India

autor

Bajaj Varun

• Electronics and Communication Discipline, Indian Institute of Information Technology Design and Manufacturing, Jabalpur, India

autor

Ansari Irshad Ahmad

• Electronics and Communication Discipline, Indian Institute of Information Technology Design and Manufacturing, Jabalpur, India

autor

Acharya U. Rajendra

• School of Engineering, Division of ECE, Ngee Ann Polytechnic, Singapore
• Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore
• Department of Biomedical Informatics and Medical Engineering, Asia University, Taiwan

Bibliografia

• [1] Groenland EH, Spiering W. Baroreflex amplification and carotid body modulation for the treatment of resistant hypertension. Curr Hypertens Rep 2020;22(4):1–8.
• [2] Sharma M, Rajput JS, Tan RS, Acharya UR. Automated detection of hypertension using physiological signals: A review. Int J Environ Res Public Health 18 (11). doi:10.3390/ijerph18115838.
• [3] Dziuda Lukasz, Skibniewski FW. A new approach to ballistocardiographic measurements using fibre bragg grating-based sensors. Biocybern Biomed Eng 2014;34(2):101–116. doi:10.1016/j.bbe.2014.02.001.
• [4] Jezek F, Randall EB, Carlson BE, Beard DA. Systems analysis of the mechanisms governing the cardiovascular response to changes in posture and in peripheral demand during exercise. J Mol Cell Cardiol 2022;163:33–55. https://doi.org/10.1016/j.yjmcc.2021.09.013.
• [5] Cui XX, ZQ. The research and progress of ballistocardiogram-based blood pressure monitoring technology. Yixue Xinzhi Zazhi 31 (2). doi:10.12173/j.issn.1004-5511.2021.02.07.
• [6] Sadek I, Biswas J, Abdulrazak B. Ballistocardiogram signal processing: a review. Health Inf Sci Syst 2019;7(1):1–23.
• [7] Chai SS, Goh KL, Cheah WL, Chang YHR, Ng GW. Hypertension prediction in adolescents using anthropometric measurements: Do machine learning models perform equally well? Appl Sci 2022;12(3):1600.
• [8] Fan R, Bowd C, Christopher M, Brye N, Proudfoot JA, Rezapour J, et al. Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning. JAMA Ophthalmol 2022;140(4):383–91. https://doi.org/10.1001/jamaophthalmol.2022.0244.
• [9] Mazza O, Shehory O, Lev N. Machine learning techniques in blood pressure management during the acute phase of ischemic stroke. Front Neurol 2022;12 . https://doi.org/ 10.3389/fneur.2021.743728 743728.
• [10] Tan P, Xi Y, Chao S, Jiang D, Liu Z, Fan Y, Li Z. An artificial intelligence-enhanced blood pressure monitor wristband based on piezoelectric nanogenerator. Biosensors 2022;12(4):234.
• [11] Ran X, Luo F, Lin Z, Zhu Z, Liu C, Chen B. Blood pressure monitoring via double sandwich-structured triboelectric sensors and deep learning models. Nano Res 2022:1–10. https://doi.org/10.1007/s12274-022-4172-2.
• [12] Malayeri AB, Khodabakhshi MB. Concatenated convolutional neural network model for cuffless blood pressure estimation using fuzzy recurrence properties of ppg signals. PREPRINT (Version 1). doi:10.21203/rs.3.rs-1231567/v1.
• [13] Zhou K, Yin Z, Peng Y, Zeng Z. Methods for continuous blood pressure estimation using temporal convolutional neural networks and ensemble empirical mode decomposition. Electronics 2022;11(9):1378.
• [14] Park J, Yang S, Sohn J, Lee J, Lee S, Ku Y, Kim HC. Cuffless and continuous blood pressure monitoring using a single chestworn device. IEEE Access 2019;7:135231–46.
• [15] Tabei F, Gresham JM, Askarian B, Jung K, Chong JW. Cuff-less blood pressure monitoring system using smartphones. IEEE Access 2020;8:11534–45.
• [16] Yousefian P, Shin S, Mousavi A, Kim C-S, Mukkamala R, Jang D-G, et al. The potential of wearable limb ballistocardiogram in blood pressure monitoring via pulse transit time. Scientific Rep 2019;9(1):1–11.
• [17] Marazzi NM, Guidoboni G, Zaid M, Sala L, Ahmad S, Despins L, et al. Combining physiology-based modeling and evolutionary algorithms for personalized, noninvasive cardiovascular assessment based on electrocardiography and ballistocardiography. Front Physiol 12. doi:10.3389/fphys.2021.739035.
• [18] Lai WX, Visaria A, Østbye T, Malhotra R. Prevalence and correlates of use of digital technology for managing hypertension among older adults. J Hum Hypertens 2022:1–8.
• [19] Padmanabhan S, Tran TQB, Dominiczak AF. Artificial intelligence in hypertension: seeing through a glass darkly. Circ Res 2021;128(7):1100–18.
• [20] Tsoi K, Yiu K, Lee H, Cheng H-M, Wang T-D, Tay J-C, et al. Applications of artificial intelligence for hypertension management. J Clin Hypertens 2021;23(3):568–74.
• [21] Kitt J, Fox R, Tucker KL, McManus RJ. New approaches in hypertension management: a review of current and developing technologies and their potential impact on hypertension care. Curr Hypertens Rep 2019;21(6):1–8.
• [22] Martinez-Ríos E, Montesinos L, Alfaro-Ponce M, Pecchia L. A review of machine learning in hypertension detection and blood pressure estimation based on clinical and physiological data. Biomed Signal Process Control 2021;68 102813.
• [23] Sharma M, Rajput JS, Tan RS, Acharya UR. Automated detection of hypertension using physiological signals: A review. Int J Environ Res Public Health 2021;18(11):5838.
• [24] Etminani K, Göransson C, Galozy A, Pejner MN, Nowaczyk S, et al. Improving medication adherence through adaptive digital interventions (imeda) in patients with hypertension: Protocol for an interrupted time series study. JMIR Res Protocols 2021;10(5) e24494.
• [25] Kobetic MD, Burchell AE, Ratcliffe LE, Neumann S, Adams ZH, Nolan R, et al. Sympathetic-transduction in untreated hypertension. J Hum Hypertens 2021:1–8.
• [26] Lari A, Sohouli MH, Fatahi S, Cerqueira HS, Santos HO, Pourrajab B, Rezaei M, Saneie S, Rahideh ST. The effects of the dietary approaches to stop hypertension (dash) diet on metabolic risk factors in patients with chronic disease: A systematic review and meta-analysis of randomized controlled trials. Nutrition Metabolism Cardiovasc Dis 2021;31(10):2766–78. https://doi.org/10.1016/j.numecd.2021.05.030.
• [27] Chai SS, Cheah WL, Goh KL, Chang YHR, Sim KY, Chin KO. A multilayer perceptron neural network model to classify hypertension in adolescents using anthropometric measurements: A cross-sectional study in sarawak, malaysia. Comput Math Methods Med 2021. https://doi.org/10.1155/2021/2794888.
• [28] Seok W, Lee KJ, Cho D, Roh J, Kim S. Blood pressure monitoring system using a two-channel ballistocardiogram and convolutional neural networks. Sensors 2021;21(7). https://doi.org/10.3390/s21072303.
• [29] Yen C-T, Chang S-N, Liao C-H. Deep learning algorithm evaluation of hypertension classification in less photoplethysmography signals conditions. Meas Control 2021;54(3–4):439–45.
• [30] Wu J, Liang H, Ding C, Huang X, Huang J, Peng Q. Improving the accuracy in classification of blood pressure from photoplethysmography using continuous wavelet transform and deep learning. Int J Hypertens 2021;2021. https://doi.org/10.1155/2021/9938584. 2090–0384.
• [31] Nour M, Polat K. Automatic classification of hypertension types based on personal features by machine learning algorithms. Math Problems Eng 2020. https://doi.org/10.1155/2020/2742781.
• [32] Liu, et al. Deep convolutional neural network-aided detection of portal hypertension in patients with cirrhosis. Clin Gastroenterol Hepatol 2020;18(13):2998–3007.e5. doi:10.1016/j.cgh.2020.03.034.
• [33] 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;7:144777–89.
• [34] Wu J-H, Wei W, Zhang L, Wang J, Damaševičius R, Li J, et al. Risk assessment of hypertension in steel workers based on lvq and fisher-svm deep excavation. IEEE Access 2019;7:23109–19.
• [35] Chang IS, Armanfard N, Javaid AQ, Boger J, Mihailidis A. Unobtrusive detection of simulated orthostatic hypotension and supine hypertension using ballistocardiogram and electrocardiogram of healthy adults. IEEE J Transl Eng Health Med 2018;6:1–13.
• [36] Tjahjadi H, Ramli K, Murfi H. Noninvasive classification of blood pressure based on photoplethysmography signals using bidirectional long short-term memory and time-frequency analysis. IEEE Access 2020;8:20735–48.
• [37] Melillo P, Izzo R, Orrico A, Scala P, Attanasio M, Mirra M, et al. Automatic prediction of cardiovascular and cerebrovascular events using heart rate variability analysis. PloS One 2015;10(3) e0118504.
• [38] Chamidah N, Santoni MM, Matondang N, et al. The effect of oversampling on the classification of hypertension with the naive bayes algorithm, decision tree, and artificial neural network (ann). Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 2020:635–41.
• [39] Soh DCK, Ng E, Jahmunah V, Oh SL, San TR, Acharya UR. A computational intelligence tool for the detection of hypertension using empirical mode decomposition. Comput Biol Med 2020;118 . https://doi.org/10.1016/j.compbiomed.2020.103630 103630.
• [40] Koichubekov B, Sorokina M, Laryushina Y, Turgunova L, Korshukov I. Nonlinear analyses of heart rate variability in hypertension 2018;67:174–9. https://doi.org/10.1016/j.ancard.2018.04.014.
• [41] Rajput JS, Sharma M, Acharya UR. Hypertension diagnosis index for discrimination of high-risk hypertension ecg signals using optimal orthogonal wavelet filter bank. Int J Environ Res Public Health 2019;16(21):4068.
• [42] Rajput JS, Sharma M, Kumbhani D, Acharya UR. Automated detection of hypertension using wavelet transform and nonlinear techniques with ballistocardiogram signals. Inf Med Unlocked 2021;26 . https://doi.org/10.1016/j.imu.2021.100736 100736.
• [43] Rajput JS, Sharma M, Kumar TS, Acharya UR. Automated detection of hypertension using continuous wavelet transform and a deep neural network with ballistocardiography signals. Int J Environ Res Public Health 2022;19(7):4014.
• [44] Soh DCK, Ng E, Jahmunah V, Oh SL, Tan RS, Acharya U. Automated diagnostic tool for hypertension using convolutional neural network. Comput Biol Med 2020;126. https://doi.org/10.1016/j.compbiomed.2020.103999 103999.
• [45] Liu F, Zhou X, Wang Z, Wang T, Zhang Y. Identification of hypertension by mining class association rules from multidimensional features. In: 2018 24th International Conference on Pattern Recognition (ICPR), IEEE. p. 3114–9.
• [46] Jain P, Gajbhiye P, Tripathy R, Acharya UR. A two-stage deep cnn architecture for the classification of low-risk and high-risk hypertension classes using multi-lead ecg signals. Inf Med Unlocked 2020;21 . https://doi.org/10.1016/j.imu.2020.100479 100479.
• [47] Rajput JS, Sharma M, Tan RS, Acharya UR. Automated detection of severity of hypertension ecg signals using an optimal bi-orthogonal wavelet filter bank. Comput Biol Med 2020;123 . https://doi.org/10.1016/j.compbiomed.2020.103924103924.
• [48] Gupta K, Khare SK, Bajaj V, Ansari IA. Automatic detection of hypertension by flexible analytic wavelet transform using electrocardiogram signals. In High Performance Computing for Intelligent Medical Systems, 2053–2563, IOP Publishing, 2021, pp. 1–1 to 1–18. doi:10.1088/978-0-7503-3815-8ch1.
• [49] Ni H, Cho S, Mankoff J, Yang J, et al. Automated recognition of hypertension through overnight continuous hrv monitoring. J Ambient Intell Humanized Comput 2018;9(6):2011–23.
• [50] Song Y, Ni H, Zhou X, Zhao W, Wang T. Extracting features for cardiovascular disease classification based on ballistocardiography. In 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing, IEEE; 2015. pp. 1230–1235.
• [51] Yongbo L, Chen Z, Ward R, Elgendi M. Hypertension assessment using photoplethysmography: a risk stratification approach. J Clin Med 2019;8(1):12.
• [52] Liang Y, Chen Z, Ward R, Elgendi M. Photoplethysmography and deep learning: enhancing hypertension risk stratification. Biosensors 2018;8(4):101.
• [53] Lan K-C, Raknim P, KaoW-F, Huang J-H. Toward hypertension prediction based on ppg-derived hrv signals: a feasibility study. J Med Syst 2018;42(6):1–7.
• [54] Inan OT, Migeotte P-F, Park K-S, Etemadi M, Tavakolian K, Casanella R, et al. Ballistocardiography and seismocardiography: A review of recent advances. IEEE J Biomed Health Inf 2015;19:1414–27.
• [55] Liu F, Zhou X, Wang Z, Cao J, Wang H, Zhang Y. Unobtrusive mattress-based identification of hypertension by integrating classification and association rule mining. Sensors 2019;19(7):1489.
• [56] Zhao W, Ni H, Zhou X, Song Y, Wang T. Identifying sleep apnea syndrome using heart rate and breathing effort variation analysis based on ballistocardiography. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE; 2015. pp. 4536–4539.
• [57] Li X, Li Y. J peak extraction from non-standard ballistocardiography data: A preliminary study. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2016. pp. 688–691. doi:10.1109/EMBC.2016.7590795.
• [58] Pan J, Tompkins WJ. A real-time qrs detection algorithm. IEEE Trans Biomed Eng BME-32 1985;3:230–6. https://doi.org/10.1109/TBME.1985.325532.
• [59] Lu W-K, Zhang Q. Deconvolutive short-time fourier transform spectrogram. IEEE Signal Process Lett 2009;16(7):576–9. https://doi.org/10.1109/LSP.2009.2020887.
• [60] Cho S-H, Jang G, Kwon S-H. Time-frequency analysis of power-quality disturbances via the gabor-wigner transform. IEEE Trans Power Delivery 2010;25(1):494–9. https://doi.org/10.1109/TPWRD.2009.2034832.
• [61] Bajaj V, Pachori RB. Automatic classification of sleep stages based on the time-frequency image of eeg signals. Comput Methods Programs Biomed 2013;112(3):320–8. https://doi.org/10.1016/j.cmpb.2013.07.006.
• [62] Altintop Çigdem Gülüzar, Latifoğlu F, Karayol Akin A, Çetin B. A novel approach for detection of consciousness level in comatose patients from eeg signals with 1-d convolutional neural network. Biocybern Biomed Eng 2022;42 (1):16–26. doi:10.1016/j.bbe.2021.11.003.
• [63] Gupta K, Bajaj V, Ansari IA. Osacn-net: Automated classification of sleep apnea using deep learning model and smoothed gabor spectrograms of ecg signal. IEEE Trans Instrum Meas 2022;71:1–9. https://doi.org/10.1109/TIM.2021.3132072.
• [64] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 2012;25:1097–105.
• [65] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 770–8.
• [66] Gupta K, Bajaj V, Ansari IA. An improved deep learning model for automated detection of bbb using s-t spectrograms of smoothed vcg signal. IEEE Sens J 2022;22(9):8830–7. https://doi.org/10.1109/JSEN.2022.3162022.
• [67] Dhillon A, Verma GK. Convolutional neural network: a review of models, methodologies and applications to object detection. Prog Artif Intell 2020;9(2):85–112.
• [68] Brown CD, Davis HT. Receiver operating characteristics curves and related decision measures: A tutorial. Chemometrics Intell Lab Syst 2006;80(1):24–38.