2024-07-24-yan24a.md

title	abstract	year	volume	publisher	series	software	layout	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	genre	issued	pdf	extras
SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals	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.	2024	248	PMLR	Proceedings of Machine Learning Research	https://github.com/Runz96/SQUWA	inproceedings	2640-3498	yan24a	0	SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signals	105	119	105-119	105	false	Yan, Runze and Ding, Cheng and Xiao, Ran and Fedorov, Alex and Lee, Randall J and Nahab, Fadi and Hu, Xiao	given family Runze Yan given family Cheng Ding given family Ran Xiao given family Alex Fedorov given family Randall J Lee given family Fadi Nahab given family Xiao Hu	2024-07-24		Proceedings of the fifth Conference on Health, Inference, and Learning	inproceedings	date-parts 2024 7 24	https://raw.githubusercontent.com/mlresearch/v248/main/assets/yan24a/yan24a.pdf