Abstract
Cardiovascular diseases are the main cause of global non-communicable deaths, accounting for about one-third of the total deaths in the world. Wearable devices are used for early monitoring and early prevention of cardiovascular diseases. Aimed at the low configuration, low power consumption and personalized characteristics of the wearable ECG equipment, a transfer learned with deep LSTM model is proposed in this work. The model is computational efficient and serves as the patient-specific ECG anomaly detector that can be used on the wearable devices. Based on the MIT-BIH open dataset, the experiment results show that the transfer learning model produces superior weighted F2 scores compared to the general model and the naive model for detecting ECG anomalies, such as the premature ventricular contractions and atrial premature beats. The transfer learning model proposed here provides a sensitive, personalized ECG anomaly detection mechanism that has the added benefit of light, quick and robust learning process to be used on wearable devices, which can meet the requirement of ECG monitoring for patients by wearable devices.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sinha, A., Gopinathan, P., Chung, Y.D.: An aptamer based sandwich assay for simultaneous detection of multiple cardiovascular biomarkers on a multilayered integrated microfluidic system. In: IEEE 20th International Conference on Solid-State, pp. 1075–1077 (2019)
Research and Markets Authors: Single lead ECG equipment market size, share trends analysis report by end use (hospitals clinics, homecare, ascs), by indication (arrhythmia, syncope) (2019). https://www.researchandmarkets.com/reports/4751811/single-lead-ecg-equipment-market-size-share-and. Accessed 28 Apr 2019
Han, X., Hu, Y., Foschini, L.: Deep learning models for electrocardiograms are susceptible to adversarial attack. Nat. Med. 26(3), 360–363 (2020)
Acharya, U.R., Fujita, H., Lih, O.S., Hagiwara, Y., Tan, J.H., Adam, M.: Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inf. Sci. 405, 81–90 (2017)
Oh, S.L., Ng, E.Y., San Tan, R.: Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats. Comput. Biol. Med. 102, 278–287 (2018)
Warrick, P., Homsi, M.N.: Cardiac arrhythmia detection from ECG combining convolutional and long short-term memory networks. In: IEEE Computing in Cardiology (CinC), pp. 202–206 (2017)
Hannun, A.Y., Rajpurkar, P., Haghpanahi, M.: Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat. Med. 25(1), 65 (2019)
Kiranyaz, S., Ince, T., Gabbouj, M.: Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans. Biomed. Eng. 63(3), 664–675 (2015)
Kachuee, M., Fazeli, S., Sarrafzadeh, M.: ECG heartbeat classification: a deep transferable representation. In: IEEE International Conference on Healthcare Informatics (ICHI), pp. 443–444 (2018)
Jun, T.J., Nguyen, H.M., Kang, D.: ECG arrhythmia classification using a 2-D convolutional neural network. arXiv preprint arXiv:1804.06812 (2018)
Limam, M., Precioso, F.: Atrial fibrillation detection and ECG classification based on convolutional recurrent neural network. In: IEEE Computing in Cardiology (CinC), pp. 1–4 (2017)
Zihlmann, M., Perekrestenko, D., Tschannen, M.: Convolutional recurrent neural networks for electrocardiogram classification. In: IEEE Computing in Cardiology (CinC), pp. 12–16 (2017)
Singh, S., Pandey, S.K., Pawar, U., et al.: Classification of ECG arrhythmia using recurrent neural networks. Procedia Comput. Sci. 132, 1290–1297 (2018)
Chauhan, S., Vig, L.: Anomaly detection in ECG time signals via deep long short-term memory networks. In: IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 1–7 (2015)
Saadatnejad, S., Oveisi, M., Hashemi, M.: LSTM-based ECG classification for continuous monitoring on personal wearable devices. IEEE J. Biomed. Health Inf. 24(2), 515–523 (2019)
Keogh, K., Lin, J., Fu, A.: Hot sax: efficiently finding the most unusual time series subsequence. In: Fifth IEEE International Conference on Data Mining (ICDM 2005), pp. 8–10 (2005)
Moody, G.B., Mark, R.G.: The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 20(3), 45–50 (2001)
Joshi, S.L., Vatti, R.A., Tornekar, R.V.: A survey on ECG signal denoising techniques. In: IEEE 2013 International Conference on Communication Systems and Network Technologies, pp. 60–64 (2013)
Zhang, C., Wang, G., Zhao, J.: Patient-specific ECG classification based on recurrent neural networks and clustering technique. In: IEEE 13th IASTED International Conference on Biomedical Engineering (BioMed), pp. 63–67 (2017)
Yosinski, J., Clune, J., Bengio, Y., et al.: How transferable are features in deep neural networks? Adv. Neural Inf. Process. Syst. 8(6), 3320–3328 (2014)
Malhotra, P., Vig, L., Shroff, G., et al.: Long short term memory networks for anomaly detection in time series. In: Proceedings, vol. 89, pp. 89–94. Presses universitaires de Louvain, Belgium (2015)
Acknowledgments
This work was financially supported by the National Nature Science Foundation of China (No. 61806033, 61703065), the National Natural Science Foundation of Chongqing(cstc2020jcyj-msxm1555), the Scientific and Technological Research Program of Chongqing Municipal Education Commission (No. KJ202000646472197), the Key Industry Core Technology Innovation Project of CQ (cstc2017zdcy-zdyfX0012).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Deng, X., Zhou, J., Xiao, B., Xiang, X., Yuan, Y. (2021). Deep LSTM Transfer Learning for Personalized ECG Anomaly Detection on Wearable Devices. In: Sun, F., Liu, H., Fang, B. (eds) Cognitive Systems and Signal Processing. ICCSIP 2020. Communications in Computer and Information Science, vol 1397. Springer, Singapore. https://doi.org/10.1007/978-981-16-2336-3_32
Download citation
DOI: https://doi.org/10.1007/978-981-16-2336-3_32
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2335-6
Online ISBN: 978-981-16-2336-3
eBook Packages: Computer ScienceComputer Science (R0)