Key result
A CNN-LSTM deep neural network model accurately estimated continuous blood pressure from fingertip photoplethysmogram signals, achieving a mean error of 0.21 ± 6.40 mmHg for systolic and 0.19 ± 4.71 mmHg for diastolic blood pressure.
Why the study?
Continuous blood pressure monitoring helps reduce the prevalence and mortality of cardiovascular diseases, motivating cuff-less estimation of SBP and DBP from fingertip photoplethysmogram waveforms using deep neural networks.
Does a CNN-LSTM deep neural network model accurately estimate continuous blood pressure from fingertip PPG signals compared to other algorithms?
Does a CNN-LSTM deep neural network model accurately estimate continuous blood pressure from fingertip PPG signals compared to other algorithms?
A deep neural network model combining CNN and LSTM can accurately estimate continuous blood pressure from fingertip PPG signals, meeting international medical instrumentation standards.
Supports cuffless continuous BP monitoring development; leaves open prospective clinical validation before adoption.
Objective Blood pressure (BP) is an important physiological index reflecting cardiovascular function. Continuous blood pressure monitoring helps to reduce the prevalence and mortality of cardiovascular diseases. In this study, we aim to estimate systolic blood pressure (SBP) and diastolic blood pressure (DBP) values continuously based on fingertip photoplethysmogram (PPG) waveforms using deep neural network models. Methods Two models were proposed and both models consisted of three stages. The only difference between them was the method of extracting features from PPG signals in the first stage. Model 1 adopted Bidirectional Long Short-Term Memory (BiLSTM), while the other used convolutional neural network. Then, the residual connection was applied to multiple stacked LSTM layers in the second stage, following by the third stage with two fully connected layers. Results Our proposed models outperformed other methods based on similar dataset or framework, while in our proposed models, the model 2 was superior to model 1. It satisfied the standard of Association for the Advancement of the Medical Instrumentation (AAMI) and obtained grade A for SBP and DBP estimation according to the British Hypertension Society (BHS) standard. The mean error (ME) and standard deviation (STD) for SBP and DBP estimations were 0.21 ± 6.40 mmHg and 0.19 ±4.71 mmHg, respectively. Conclusion Our proposed models could extract important features of fingertip PPG waveforms automatically and realize cuff-less continuous BP monitoring, which can be helpful in the identification and early treatment of abnormal blood pressure, thus may reduce the occurrence of cardiovascular malignant events.
No takes yet. Share an insight, caveat, or question.
Yu Chen (2022) studied Blood pressure monitoring. CNN-LSTM deep neural network model (Model 2) vs. BiLSTM model (Model 1) and other existing algorithms was evaluated on Mean error (ME) and standard deviation (STD) for SBP and DBP estimation. A CNN-LSTM deep neural network model accurately estimated continuous blood pressure from fingertip photoplethysmogram signals, achieving a mean error of 0.21 ± 6.40 mmHg for systolic and 0.19 ± 4.71 mmHg for diastolic blood pressure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: