Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals (2404.15353v1)

Published 15 Apr 2024 in eess.SP, cs.AI, and cs.LG

Abstract: Atrial fibrillation (AF), a common cardiac arrhythmia, significantly increases the risk of stroke, heart disease, and mortality. Photoplethysmography (PPG) offers a promising solution for continuous AF monitoring, due to its cost efficiency and integration into wearable devices. Nonetheless, PPG signals are susceptible to corruption from motion artifacts and other factors often encountered in ambulatory settings. Conventional approaches typically discard corrupted segments or attempt to reconstruct original signals, allowing for the use of standard machine learning techniques. However, this reduces dataset size and introduces biases, compromising prediction accuracy and the effectiveness of continuous monitoring. We propose a novel deep learning model, Signal Quality Weighted Fusion of Attentional Convolution and Recurrent Neural Network (SQUWA), designed to learn how to retain accurate predictions from partially corrupted PPG. Specifically, SQUWA innovatively integrates an attention mechanism that directly considers signal quality during the learning process, dynamically adjusting the weights of time series segments based on their quality. This approach enhances the influence of higher-quality segments while reducing that of lower-quality ones, effectively utilizing partially corrupted segments. This approach represents a departure from the conventional methods that exclude such segments, enabling the utilization of a broader range of data, which has great implications for less disruption when monitoring of AF risks and more accurate estimation of AF burdens. Our extensive experiments show that SQUWA outperform existing PPG-based models, achieving the highest AUCPR of 0.89 with label noise mitigation. This also exceeds the 0.86 AUCPR of models trained with using both electrocardiogram (ECG) and PPG data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. An accurate non-accelerometer-based ppg motion artifact removal technique using cyclegan. ACM Transactions on Computing for Healthcare, 4(1):1–14, 2023.
  2. Review of deep learning: concepts, cnn architectures, challenges, applications, future directions. Journal of big Data, 8:1–74, 2021.
  3. Generalized denoising auto-encoders as generative models. Advances in neural information processing systems, 26, 2013.
  4. Generative adversarial networks in time series: A systematic literature review. ACM Computing Surveys, 55(10):1–31, 2023.
  5. The 2023 wearable photoplethysmography roadmap. Physiological measurement, 44(11):111001, 2023.
  6. Review of noise removal techniques in ecg signals. IET Signal Processing, 14(9):569–590, 2020.
  7. Dn-gan: Denoising generative adversarial networks for speckle noise reduction in optical coherence tomography images. Biomedical Signal Processing and Control, 55:101632, 2020.
  8. Atrial fibrillation identification with ppg signals using a combination of time-frequency analysis and deep learning. IEEE Access, 8:172692–172706, 2020.
  9. Worldwide epidemiology of atrial fibrillation: a global burden of disease 2010 study. Circulation, 129(8):837–847, 2014.
  10. A survey on heterogeneous transfer learning. Journal of Big Data, 4:1–42, 2017.
  11. Log-spectral matching gan: Ppg-based atrial fibrillation detection can be enhanced by gan-based data augmentation with integration of spectral loss. IEEE Journal of Biomedical and Health Informatics, 27(3):1331–1341, 2023.
  12. Learning from alarms: A robust learning approach for accurate photoplethysmography-based atrial fibrillation detection using eight million samples labeled with imprecise arrhythmia alarms. IEEE Journal of Biomedical and Health Informatics, pages 1–12, 2024. 10.1109/JBHI.2024.3360952.
  13. Remote heart rate estimation by signal quality attention network. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2122–2129, 2022.
  14. Attention mechanisms in computer vision: A survey. Computational visual media, 8(3):331–368, 2022.
  15. Siamaf: Learning shared information from ecg and ppg signals for robust atrial fibrillation detection. arXiv preprint arXiv:2310.09203, 2023.
  16. Meta-analysis: antithrombotic therapy to prevent stroke in patients who have nonvalvular atrial fibrillation. Annals of internal medicine, 146(12):857–867, 2007.
  17. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  18. Using fitness trackers and smartwatches to measure physical activity in research: analysis of consumer wrist-worn wearables. Journal of medical Internet research, 20(3):e110, 2018.
  19. Denoising criterion for variational auto-encoding framework. In Proceedings of the AAAI conference on artificial intelligence, volume 31, 2017.
  20. Transfer learning from synthetic to real-noise denoising with adaptive instance normalization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3482–3492, 2020.
  21. Dnae-gan: Noise-free acoustic signal generator by integrating autoencoder and generative adversarial network. International Journal of Distributed Sensor Networks, 16(5):1550147720923529, 2020.
  22. Detection of atrial fibrillation using a machine learning approach. Information, 11(12):549, 2020.
  23. Contribution of atrial fibrillation to incidence and outcome of ischemic stroke: results from a population-based study. Stroke, 36(6):1115–1119, 2005.
  24. Han-ecg: An interpretable atrial fibrillation detection model using hierarchical attention networks. Computers in biology and medicine, 127:104057, 2020.
  25. Atrial fibrillation classification and prediction explanation using transformer neural network. In 2022 International Joint Conference on Neural Networks (IJCNN), pages 01–08. IEEE, 2022.
  26. A review on the attention mechanism of deep learning. Neurocomputing, 452:48–62, 2021.
  27. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2009.
  28. Deep learning approaches for plethysmography signal quality assessment in the presence of atrial fibrillation. Physiological measurement, 40(12):125002, 2019a.
  29. A supervised approach to robust photoplethysmography quality assessment. IEEE journal of biomedical and health informatics, 24(3):649–657, 2019b.
  30. Photoplethysmogram signal quality evaluation by unsupervised learning approach. In 2020 IEEE Applied Signal Processing Conference (ASPCON), pages 6–10. IEEE, 2020.
  31. Motion artifact removal techniques for wearable eeg and ppg sensor systems. Frontiers in Electronics, 2:685513, 2021.
  32. A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology. In 2017 IEEE EMBS international conference on biomedical & health informatics (BHI), pages 141–144. IEEE, 2017.
  33. Data-gru: Dual-attention time-aware gated recurrent unit for irregular multivariate time series. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 930–937, 2020.
  34. Joint optimization framework for learning with noisy labels. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5552–5560, 2018.
  35. Multi-task deep learning for cardiac rhythm detection in wearable devices. NPJ digital medicine, 3(1):116, 2020.
  36. Symmetric cross entropy for robust learning with noisy labels. In Proceedings of the IEEE/CVF international conference on computer vision, pages 322–330, 2019.
  37. A review of recurrent neural networks: Lstm cells and network architectures. Neural computation, 31(7):1235–1270, 2019.
  38. Eeg-inception: an accurate and robust end-to-end neural network for eeg-based motor imagery classification. Journal of Neural Engineering, 18(4):046014, 2021a.
  39. Explainability metrics of deep convolutional networks for photoplethysmography quality assessment. IEEE Access, 9:29736–29745, 2021b.
  40. Learning noise invariant features through transfer learning for robust end-to-end speech recognition. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 7024–7028. IEEE, 2020.
  41. Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in neural information processing systems, 31, 2018.
  42. Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2921–2929, 2016.
  43. Atrial fibrillation detection and atrial fibrillation burden estimation via wearables. IEEE Journal of Biomedical and Health Informatics, 26(5):2063–2074, 2021.
  44. A generative adversarial approach for zero-shot learning from noisy texts. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1004–1013, 2018.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets