An end-to-end deep learning architecture using an attention mechanism estimated continuous blood pressure with mean absolute errors of 4.06 ± 4.04 for SBP and 3.33 ± 3.42 for DBP.
Does an end-to-end deep learning architecture using raw signals and an attention mechanism improve continuous blood pressure estimation compared to conventional methods?
An end-to-end deep learning architecture using raw physiological signals and an attention mechanism can accurately estimate continuous blood pressure, complying with global standards.
Effect estimate: MAE 4.06 (SBP), 3.33 (DBP)
Blood pressure (BP) is a vital sign that provides fundamental health information regarding patients. Continuous BP monitoring is important for patients with hypertension. Various studies have proposed cuff-less BP monitoring methods using pulse transit time. We propose an end-to-end deep learning architecture using only raw signals without the process of extracting features to improve the BP estimation performance using the attention mechanism. The proposed model consisted of a convolutional neural network, a bidirectional gated recurrent unit, and an attention mechanism. The model was trained by a calibration-based method, using the data of each subject. The performance of the model was compared to the model that used each combination of the three signals, and the model with the attention mechanism showed better performance than other state-of-the-art methods, including conventional linear regression method using pulse transit time (PTT). A total of 15 subjects were recruited, and electrocardiogram, ballistocardiogram, and photoplethysmogram levels were measured. The 95% confidence interval of the reference BP was 86.34, 143.74 and 51.28, 88.74 for systolic BP (SBP) and diastolic BP (DBP), respectively. The R 2 values were 0.52 and 0.49, and the mean-absolute-error values were 4.06 ± 4.04 and 3.33 ± 3.42 for SBP and DBP, respectively. In addition, the results complied with global standards. The results show the applicability of the proposed model as an analytical metric for BP estimation.
Eom et al. (Mon,) conducted a other in Blood pressure estimation (n=15). End-to-end deep learning architecture with attention mechanism vs. Conventional linear regression using pulse transit time (PTT) was evaluated on Mean absolute error (MAE) and R2 for SBP and DBP (MAE 4.06 (SBP), 3.33 (DBP)). An end-to-end deep learning architecture using an attention mechanism estimated continuous blood pressure with mean absolute errors of 4.06 ± 4.04 for SBP and 3.33 ± 3.42 for DBP.