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

Runze Yan, Cheng Ding, Ran Xiao, Alex Fedorov, Randall J Lee, Fadi Nahab, Xiao Hu
Proceedings of the fifth Conference on Health, Inference, and Learning, PMLR 248:105-119, 2024.

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, \textbf{\underline{S}}ignal \textbf{\underline{Qu}}ality \textbf{\underline{W}}eighted Fusion of \textbf{\underline{A}}ttentional 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. Moreover, SQUWA utilizes variable-sized convolutional kernels to capture complex PPG signal patterns across different resolutions for enhanced learning. 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v248-yan24a, title = {SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals}, author = {Yan, Runze and Ding, Cheng and Xiao, Ran and Fedorov, Alex and Lee, Randall J and Nahab, Fadi and Hu, Xiao}, booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning}, pages = {105--119}, year = {2024}, editor = {Pollard, Tom and Choi, Edward and Singhal, Pankhuri and Hughes, Michael and Sizikova, Elena and Mortazavi, Bobak and Chen, Irene and Wang, Fei and Sarker, Tasmie and McDermott, Matthew and Ghassemi, Marzyeh}, volume = {248}, series = {Proceedings of Machine Learning Research}, month = {27--28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v248/main/assets/yan24a/yan24a.pdf}, url = {https://proceedings.mlr.press/v248/yan24a.html}, 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, \textbf{\underline{S}}ignal \textbf{\underline{Qu}}ality \textbf{\underline{W}}eighted Fusion of \textbf{\underline{A}}ttentional 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. Moreover, SQUWA utilizes variable-sized convolutional kernels to capture complex PPG signal patterns across different resolutions for enhanced learning. 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.} }
Endnote
%0 Conference Paper %T SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals %A Runze Yan %A Cheng Ding %A Ran Xiao %A Alex Fedorov %A Randall J Lee %A Fadi Nahab %A Xiao Hu %B Proceedings of the fifth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2024 %E Tom Pollard %E Edward Choi %E Pankhuri Singhal %E Michael Hughes %E Elena Sizikova %E Bobak Mortazavi %E Irene Chen %E Fei Wang %E Tasmie Sarker %E Matthew McDermott %E Marzyeh Ghassemi %F pmlr-v248-yan24a %I PMLR %P 105--119 %U https://proceedings.mlr.press/v248/yan24a.html %V 248 %X 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, \textbf{\underline{S}}ignal \textbf{\underline{Qu}}ality \textbf{\underline{W}}eighted Fusion of \textbf{\underline{A}}ttentional 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. Moreover, SQUWA utilizes variable-sized convolutional kernels to capture complex PPG signal patterns across different resolutions for enhanced learning. 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.
APA
Yan, R., Ding, C., Xiao, R., Fedorov, A., Lee, R.J., Nahab, F. & Hu, X.. (2024). SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals. Proceedings of the fifth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 248:105-119 Available from https://proceedings.mlr.press/v248/yan24a.html.

Related Material