Key result
Single-lead ECG deep learning model estimates continuous blood pressure with ~0.1 mmHg mean error.
Why the study?
Most wearable monitoring devices acquire only one physiological signal due to energy and size constraints, limiting dual-signal blood pressure estimation methods.
Does an adaptive weight learning-based multitask deep network accurately estimate continuous blood pressure using single-lead ECG signals?
Does an adaptive weight learning-based multitask deep network accurately estimate continuous blood pressure using single-lead ECG signals?
Answers are grounded in this paper and cite their sources.
A novel multitask deep learning framework using single-lead ECG signals can accurately estimate continuous blood pressure, potentially enabling long-term monitoring via wearable devices.
Estimating blood pressure via combination analysis with electrocardiogram and photoplethysmography signals has attracted growing interest in continuous monitoring patients' health conditions. However, most wearable/portal monitoring devices generally acquire only one kind of physiological signals due to the consideration of energy cost, device weight and size, etc. In this study, a novel adaptive weight learning-based multitask deep learning framework based on single lead electrocardiogram signals is proposed for continuous blood pressure estimation. Specifically, the proposed method utilizes a 2-layer bidirectional long short-term memory network as the sharing layer, followed by three identical architectures of 2-layer fully connected networks for task-specific blood pressure estimation. To learn the importance of task-specific losses automatically, an adaptive weight learning scheme based on the trend of validation loss is proposed. Extensive experiment results on Physionet Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) II waveform database demonstrate that the proposed method using electrocardiogram signals obtains estimating performance of 0.12±10.83 mmHg, 0.13±5.90 mmHg, and 0.08±6.47 mmHg for systolic blood pressure, diastolic blood pressure, and mean arterial pressure, respectively. It can meet the requirements of the British Hypertension Society standard and US Association of Advancement of Medical Instrumentation standard with a considerable margin. Combined with a wearable/portal electrocardiogram device, the proposed model can be deployed to a healthcare system to provide a long-term continuous blood pressure monitoring service, which would help to reduce the incidence of malignant complications to hypertension.
No takes yet. Share an insight, caveat, or question.
Fan et al. (2021) studied Blood pressure estimation (n=21,422). Adaptive weight learning-based multitask deep learning framework using single-lead ECG vs. Reference machine learning methods (Lasso, RF, SVR, Res2Net) was evaluated on Blood pressure estimation performance (Mean Error ± Standard Deviation). The proposed adaptive weight learning-based multitask deep learning framework using single-lead ECG signals estimated systolic, diastolic, and mean arterial blood pressure with errors of 0.12±10.83 mmHg, 0.13±5.90 mmHg, and 0.08±6.47 mmHg, respectively.
Synapse has enriched 10 related papers. Consider them for comparative context: