Abstract
Nowadays, one of the causes leading to death in all over the world is the occurrence of arterial and cardiovascular events, which results in heart failure and premature deaths occurring in the form of myocardial infarction, stroke, and fainting. Therefore, it is essential to inform people before disasters occurring to prevent and warn of abnormal conditions. In this paper, a deep learning approach was used to predict arterial events over the course of a few weeks/months prior to the event using a 5-min electrocardiogram (ECG) recording and extracting time–frequency features of ECG signals. Considering the possibility of learning long-term dependencies to identify and prevent these events as quickly as possible, the Long Short-Term Memory (LSTM) neural network was used. A Deep Belief Network (DBN) was also used to represent and select more efficient and effective features of the recorded dataset. This approach is briefly called LSTM-DBN. Four publicly available datasets in the field of health care were used to evaluate the proposed approach. These data were collected from wearable heart rate monitoring sensors along with demographic features in the context of the Internet of Things. The prediction results of the proposed LSTM-DBN were compared with other deep learning approaches (simple RNN, GRU, CNN and Ensemble), and traditional classification approaches (MLP, SVM, Logistic Regression and Random Forest). In addition, DBN performance was compared with other methods of feature selection and representation such as PCA and AutoEncoder. Experimental results showed that the proposed LSTM-DBN (88.42% mean accuracy) had significantly better performance in comparison with all other deep learning approaches and traditional classifications.
Similar content being viewed by others
References
Arunan A, Pathinarupothi RK, Ramesh MV (2016) A real-time detection and warning of cardiovascular disease LAHB for a wearable wireless ECG device. In: 2016 IEEE-EMBS international conference on biomedical and health informatics (BHI). IEEE, pp 98–101
Xie X, Wu D, Liu S, Li R (2017) IoT data analytics using deep learning. arXiv preprint 1708.03854.
Lu P, Guo S, Zhang H, Li Q, Wang Y, Wang Y, Qi L (2018) Research on improved depth belief network-based prediction of cardiovascular diseases. J Healthcare Eng 20:1–9
Billeci L, Marino D, Insana L, Vatti G, Varanini M (2018) Patient-specific seizure prediction based on heart rate variability and recurrence quantification analysis. PloS One 13(9):e0204339
Ebrahimzadeh E, Pooyan M, Bijar A (2014) A novel approach to predict sudden cardiac death (SCD) using nonlinear and time–frequency analyses from HRV signals. PloS One 9(2):e81896
Melillo P, Izzo R, Orrico A, Scala P, Attanasio M, Mirra M et al (2015) Automatic prediction of cardiovascular and cerebrovascular events using heart rate variability analysis. PloS One 10(3):e0118504
Yadav A, Singh A, Dutta MK, Travieso CM (2019) Machine learning-based classification of cardiac diseases from PCG recorded heart sounds. Neural Comput Appl 19:1–14
Zhang X, Yao L, Wang X, Monaghan J, Mcalpine D, Zhang Y (2019) A survey on deep learning based brain computer interface. Recent Adv New Front. arXiv preprint 1905.04149
Zhang X, Yao L, Dong M, Liu Z, Zhang Y, Li Y (2020) Adversarial representation learning for robust patient-independent epileptic seizure detection. IEEE J Biomed Health Inf 24(10):2852–2859
Jiao Y, Zhang Y, Wang Y, Wang B, Jin J, Wang X (2018) A novel multilayer correlation maximization model for improving CCA-based frequency recognition in SSVEP brain–computer interface. Int J Neural Syst 28(4):1750039
Beritelli F, Capizzi G, Sciuto GL, Napoli C, Woźniak M (2018) A novel training method to preserve generalization of RBPNN classifiers applied to ECG signals diagnosis. Neural Netw 108:331–338
Chen G, Chen M, Zhang J, Zhang L, Pang C (2020) A crucial wave detection and delineation method for twelve-lead ECG signals. IEEE Access 8:10707–10717
Zheng Z, Chen Z, Hu F, Zhu J, Tang Q, Liang Y (2020) An automatic diagnosis of arrhythmias using a combination of CNN and LSTM technology. Electronics 9(1):121
Fu L, Lu B, Nie B, Peng Z, Liu H, Pi X (2020) Hybrid network with attention mechanism for detection and location of myocardial infarction based on 12-lead electrocardiogram signals. Sensors 20(4):1020
Pan J, Tompkins WJ (1985) A real-time QRS detection algorithm. IEEE Trans Biomed Eng 3:230–236
Obayya M, Abou-Chadi F (2008) Data fusion for heart diseases classification using multi-layer feed forward neural network. In: 2008 international conference on computer engineering and systems. IEEE, pp 67–70
Martinmäki K, Rusko H, Saalasti S, Kettunen J (2006) Ability of short-time Fourier transform method to detect transient changes in vagal effects on hearts: a pharmacological blocking study. Am J Physiol-Heart Circ Physiol 290(6):H2582–H2589
Keselbrener L, Akselrod S (1996) Selective discrete Fourier transform algorithm for time-frequency analysis: method and application on simulated and cardiovascular signals. IEEE Trans Biomed Eng 43(8):789–802
Zang W, Miao F, Gravina R, Sun F, Fortino G, Li Y (2019) CMDP-based intelligent transmission for wireless body area network in remote health monitoring. Neural Comput Appl 32:1–9
Thapliyal H, Khalus V, Labrado C (2017) Stress detection and management: a survey of wearable smart health devices. IEEE Consumer Electron Mag 6(4):64–69
Suo Q, Ma F, Yuan Y, Huai M, Zhong W, Gao J, Zhang A (2018) Deep patient similarity learning for personalized healthcare. IEEE Trans Nanobiosci 17(3):219–227
Zhao L, Zhou Y, Lu H, Fujita H (2019) Parallel computing method of deep belief networks and its application to traffic flow prediction. Knowl-Based Syst 163:972–987
Wang L, Zhou W, Chang Q, Chen J, Zhou X (2019) Deep ensemble detection of congestive heart failure using short-term RR intervals. IEEE Access 7:69559–69574
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dami, S., Yahaghizadeh, M. Predicting cardiovascular events with deep learning approach in the context of the internet of things. Neural Comput & Applic 33, 7979–7996 (2021). https://doi.org/10.1007/s00521-020-05542-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05542-x