Hanbin Zhang
Skip Abstract Section
Abstract
Early detection and accurate burden estimation of atrial fibrillation (AFib) can provide the foundation for effective physician treatment. New approaches to accomplish this have attracted tremendous attention in recent years. In this paper, we develop a novel passive smartwatch-based system to detect AFib episodes and estimate the AFib burden in an ambulatory free-living environment without user engagement. Our system leverages a built-in PPG sensor to collect heart rhythm without user engagement. Then, a data preprocessor module includes time-frequency (TF) analysis to augment features in both the time and frequency domain. Finally, a lightweight multi-view convolutional neural network consisting of 19 layers achieves the AFib detection. To validate our system, we carry out a research study that enrolls 53 participants across three months, where we collect and annotate more than 27,622 hours of data. Our system achieves an average of 91.6% accuracy, 93.0% specificity, and 90.8% sensitivity without dropping any data. Moreover, our system takes 0.51 million parameters and costs 5.18 ms per inference. These results reveal that our proposed system can provide a clinical assessment of AFib in daily living.
- S. Colilla, A. Crow, W. Petkun, D. E. Singer, T. Simon, and X. Liu, "Estimates of current and future incidence and prevalence of atrial fibrillation in the us adult population," The American journal of cardiology, vol. 112, no. 8, pp. 1142--1147, 2013.Google Scholar
Cross Ref
- H. Calkins, M. R. Reynolds, P. Spector, M. Sondhi, Y. Xu, A. Martin, C. J. Williams, and I. Sledge, "Treatment of atrial fibrillation with antiarrhythmic drugs or radiofrequency ablation: two systematic literature reviews and meta-analyses," Circulation: Arrhythmia and Electrophysiology, vol. 2, no. 4, pp. 349--361, 2009.Google ScholarCross Ref
- T. Proesmans, C. Mortelmans, R. Van Haelst, F. Verbrugge, P. Vandervoort, and B. Vaes, "Mobile phone-based use of the photoplethysmography technique to detect atrial fibrillation in primary care: Diagnostic accuracy study of the fibricheck app," JMJR mHealth and uHealth, vol. 7, no. 3, p. e12284, 2019.Google Scholar
- M. V. Perez, K. W. Mahaffey, H. Hedlin, J. S. Rumsfeld, A. Garcia, T. Ferris, V. Balasubramanian, A. M. Russo, A. Rajmane, L. Cheung et al., "Large-scale assessment of a smartwatch to identify atrial fibrillation," New England Journal of Medicine, vol. 381, no. 20, pp. 1909--1917, 2019.Google ScholarCross Ref
- J. Lee, B. A. Reyes, D. D. McManus, O. Maitas, and K. H. Chon, "Atrial fibrillation detection using an iphone 4s" IEEE Transactions on Biomedical Engineering, vol. 60, no. 1, pp. 203--206, 2012.Google ScholarCross Ref
- G. Y. Lip, R. Nieuwlaat, R. Pisters, D. A. Lane, and H. J. Crijns, "Refining clinical risk stratification for predicting stroke and thromboembolism in atrial fibrillation using a novel risk factor-based approach: the euro heart survey on atrial fibrillation," Chest, vol. 137, no. 2, pp. 263--272, 2010.Google ScholarCross Ref
- B. S. Kirchhof, D. Kotecha, A. Ahlsson, D. Atar, B. Casadei et al., "Esc guidelines for the management of atrial fibrillation developed in collaboration with eacts," European heart journal, vol. 37, no. 7, pp. 2893--2962, 2016.Google ScholarCross Ref
- D. A. Lane and G. Y. Lip, "Stroke prevention in atrial fibrillation: can we do better?" Nature Reviews Cardiology, vol. 13, no. 9, pp. 511--512, 2016.Google ScholarCross Ref
- L. B. Goldstein, R. Adams, K. Becker, C. D. Furberg, P. B. Gorelick, G. Hademenos, M. Hill, G. Howard, V. J. Howard, B. Jacobs et al., "Primary prevention of ischemic stroke: a statement for healthcare professionals from the stroke council of the american heart association," Stroke, vol. 32, no. 1, pp. 280--299, 2001.Google ScholarCross Ref
- K. Shelley, S. Shelley, and C. Lake, "Pulse oximeter waveform: photoelectric plethysmography," Clinical monitoring, pp. 420--428, 2001.Google Scholar
- T. Pereira, N. Tran, K. Gadhoumi, M. M. Pelter, D. H. Do, R. J. Lee, R. Colorado, K. Meisel, and X. Hu, "Photoplethysmography based atrial fibrillation detection: A review," NPJ digital medicine, vol. 3, no. 1, pp. 1--12, 2020.Google ScholarCross Ref
- S.-C. Tang, P.-W. Huang, C.-S. Hung, S.-M. Shan, Y.-H. Lin, J.-S. Shieh, D.-M. Lai, A.-Y. Wu, and J.-S. Jeng, "Identification of atrial fibrillation by quantitative analyses of fingertip photoplethysmogram," Scientific reports, vol. 7, p. 45644, 2017.Google ScholarCross Ref
- A. Tarniceriu, J. Harju, Z. R. Yousefi, A. Vehkaoja, J. Parak, A. Yli-Hankala, and I. Korhonen, "The accuracy of atrial fibrillation detection from wrist photoplethysmography. a study on post-operative patients" in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2018, pp. 1--4.Google Scholar
- A. G. Bonomi, F. Schipper, L. M. Eerikäinen, J. Margarito, R. M. Aarts, S. Babaeizadeh, H. M. de Morree, and L. Dekker, "Atrial fibrillation detection using photo-plethysmography and acceleration data at the wrist," in 2016 Computing in Cardiology Conference (CinC). IEEE, 2016, pp. 277--280.Google Scholar
- S. P. Shashikumar, A.J. Shah, Q. Li, G. D. Clifford, and S. Nemati, "A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology" in 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI). IEEE, 2017, pp. 141--144.Google Scholar
- S. Nemati, M. M. Ghassemi, V. Ambai, N. Isakadze, O. Levantsevych, A. Shah, and G. D. Clifford, "Monitoring and detecting atrial fibrillation using wearable technology," in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2016, pp. 3394--3397.Google Scholar
- T. Pereira, J. S. Paiva, C. Correia, and J. Cardoso, "An automatic method for arterial pulse waveform recognition using knn and svm classifiers," Medical & biological engineering & computing, vol. 54, no. 7, pp. 1049--1059, 2016.Google Scholar
- J. S. Paiva, J. Cardoso, and T. Pereira, "Supervised learning methods for pathological arterial pulse wave differentiation: a svm and neural networks approach," International journal ofmedical informatics, vol. 109, pp. 30--38, 2018.Google Scholar
- T. Pereira, K. Gadhoumi, M. Ma, X. Liu, R. Xiao, R. A. Colorado, K. J. Keenan, K. Meisel, and X. Hu, "A supervised approach to robust photoplethysmography quality assessment," IEEE Journal ofBiomedical and Health Informatics, vol. 24, no. 3, pp. 649--657, 2019.Google ScholarCross Ref
- S. Fallet, M. Lemay, P. Renevey, C. Leupi, E. Pruvot, and J.-M. Vesin, "Can one detect atrial fibrillation using a wrist-type photoplethysmographic device?" Medical & Biological Engineering & Computing, vol. 57, no. 2, pp. 477--487, 2019.Google ScholarCross Ref
- J. W. Chong, C. H. Cho, F. Tabei, D. Le-Anh, N. Esa, D. D. Mcmanus, and K. H. Chon, "Motion and noise artifact-resilient atrial fibrillation detection using a smartphone" IEEE journal on emerging and selected topics in circuits and systems, vol. 8, no. 2, pp. 230--239, 2018.Google Scholar
- Y. Shen, M. Voisin, A. Aliamiri, A. Avati, A. Hannun, and A. Ng, "Ambulatory atrial fibrillation monitoring using wearable photoplethysmography with deep learning," in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 1909--1916.Google Scholar
- M. P. Turakhia, M. Desai, H. Hedlin, A. Rajmane, N. Talati, T. Ferris, S. Desai, D. Nag, M. Patel, P. Kowey et al., "Rationale and design of a large-scale, app-based study to identify cardiac arrhythmias using a smartwatch: The apple heart study," American heart journal, vol. 207, pp. 66--75, 2019.Google ScholarCross Ref
- Y. Guo, H. Wang, H. Zhang, T. Liu, Z. Liang, Y. Xia, L. Yan, Y. Xing, H. Shi, S. Li et al., "Mobile health technology for atrial fibrillation screening using photoplethysmography-based smart devices: The huawei heart study" Journal of the American College of Cardiology, 2019.Google Scholar
- L.Cohen, Time-frequency analysis. Prentice hall, 1995, vol. 778.Google Scholar
- E. Sejdic, I. Djurovic, and L. Stankovic, "Quantitative performance analysis of scalogram as instantaneous frequency estimator," IEEE Transactions on Signal Processing, vol. 56, no. 8, pp. 3837--3845, 2008.Google ScholarDigital Library
- H. van Steenis, W. Martens, and J. Tulen, "The instantaneous frequency of cardiovascular time series: a comparison of methods," Computer methods and programs in biomedicine, vol. 71, no. 3, pp. 211--224, 2003.Google Scholar
- K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770--778.Google Scholar
- A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "Mobilenets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017.Google Scholar
- J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. Ieee, 2009, pp. 248--255.Google Scholar
- I. Loshchilov and F. Hutter, "Sgdr: Stochastic gradient descent with warm restarts," arXiv preprint arXiv:1608.03983, 2016.Google Scholar
- "A new lightweight, modular, and scalable deep learning framework," https://research.fb.com/downloads/caffe2/, accessed 07/29/19.Google Scholar
- "Protocol buffers," https://developers.google.com/protocol-buffers/, accessed 08/06/19.Google Scholar
- "Transfering a model from pytorch to caffe2 and mobile using onnx," https://pytorch.org/tutorials/advanced/super_resolution_with_caffe2.html, accessed 08/06/19.Google Scholar
- "Transfering a model from pytorch to caffe2 and mobile using onnx," https://github.com/pytorch/pytorch/blob/master/binaries/speed_benchmark.cc, accessed 07/25/19.Google Scholar
- X. Liu, T. Chen, F. Qian, Z. Guo, F. X. Lin, X. Wang, and K. Chen, "Characterizing smartwatch usage in the wild," in Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services, ser. MobiSys '17. New York, NY, USA: Association for Computing Machinery, 2017, p. 385--398. [Online]. Available: https://doi.org/10.1145/3081333.3081351Google ScholarDigital Library
- H. Zamani, F. Marefat, and P. Mohseni, "Block-sparse compressive sensing for high-fidelity recording of photoplethysmogram," in 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS), 2018, pp. 1--4.Google Scholar
- A. Shcherbina, C. M. Mattsson, D. Waggott, H. Salisbury, J. W. Christle, T. Hastie, M. T. Wheeler, and E. A. Ashley, "Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort" Journal of personalized medicine, vol. 7, no. 2, p. 3, 2017.Google ScholarCross Ref
- B. A. Fallow, T. Tarumi, and H. Tanaka, "Influence of skin type and wavelength on light wave reflectance," Journal of clinical monitoring and computing, vol. 27, no. 3, pp. 313--317, 2013.Google ScholarCross Ref
Index Terms
- Towards Early Detection and Burden Estimation of Atrial Fibrillation in an Ambulatory Free-living Environment
Recommendations
Impaired coronary blood flow at higher heart rates during atrial fibrillation: Investigation via multiscale modelling
Highlights- We computationally study the role of atrial fibrillation (AF) on coronary perfusion.
Abstract BackgroundDifferent mechanisms have been proposed to relate atrial fibrillation (AF) and coronary flow impairment, even in absence of relevant coronary artery disease (CAD). However, the underlying hemodynamics remains ...
Beat-to-beat P-wave morphology as a predictor of paroxysmal atrial fibrillation
Systematic beat to beat analysis of the P-wave characteristics in vectorcardiography during sinus rhythm, following time domain and time-frequency domain analysis.Adaptive clustering method for the identification of multiple P-wave morphologies in beat ...
A framework for the atrial fibrillation prediction in electrophysiological studies
HighlightsHRV analysis, designed to work with R wave, also works on A-waves.pre-AFib signal portions are predictive of spontaneous AFib onset.An automatic device to alert the physician about an incoming AFib onset can be built. Background and ...
Comments