Key result
CNN-LSTM accurately estimates blood pressure from PPG signals within ~4 mmHg MAE, meeting international standards.
Why the study?
Continuous noninvasive blood-pressure measurement based on PPG signals requires improved performance, as accuracy and precision are critical in clinical management.
Observational (n=55)
No
Answers are grounded in this paper and cite their sources.
A CNN-LSTM model optimized with grid search can accurately estimate continuous noninvasive blood pressure from PPG signals, meeting international standards for blood-pressure monitoring devices.
Researchers commonly use continuous noninvasive blood-pressure measurement (cNIBP) based on photoplethysmography (PPG) signals to monitor blood pressure conveniently. However, the performance of the system still needs to be improved. Accuracy and precision in blood-pressure measurements are critical factors in diagnosing and managing patients' health conditions. Therefore, we propose a convolutional long short-term memory neural network (CNN-LSTM) with grid search ability, which provides a robust blood-pressure estimation system by extracting meaningful information from PPG signals and reducing the complexity of hyperparameter optimization in the proposed model. The multiparameter intelligent monitoring for intensive care III (MIMIC III) dataset obtained PPG and arterial-blood-pressure (ABP) signals. We obtained 75,226 signal segments, with 60,180 signals allocated for training data, 12,030 signals allocated for the validation set, and 15,045 signals allocated for the test data. During training, we applied five-fold cross-validation with a grid-search method to select the best model and determine the optimal hyperparameter settings. The optimized configuration of the CNN-LSTM layers consisted of five convolutional layers, one long short-term memory (LSTM) layer, and two fully connected layers for blood-pressure estimation. This study successfully achieved good accuracy in assessing both systolic blood pressure (SBP) and diastolic blood pressure (DBP) by calculating the standard deviation (SD) and the mean absolute error (MAE), resulting in values of 7.89 ± 3.79 and 5.34 ± 2.89 mmHg, respectively. The optimal configuration of the CNN-LSTM provided satisfactory performance according to the standards set by the British Hypertension Society (BHS), the Association for the Advancement of Medical Instrumentation (AAMI), and the Institute of Electrical and Electronics Engineers (IEEE) for blood-pressure monitoring devices.
No takes yet. Share an insight, caveat, or question.
T et al. (2023) conducted an observational in Intensive care unit (ICU) patients requiring blood pressure monitoring (n=55). CNN-LSTM deep learning model with grid-search hyperparameter optimization using PPG signals vs. Invasive arterial blood pressure (ABP) reference and alternative models (LSTM, LSTM-autoencoder) was evaluated on Mean error (ME) and mean absolute error (MAE) of systolic blood pressure (SBP) and diastolic blood pressure (DBP) estimation (MD -0.13 mmHg for SBP (MAE 3.79 ± 7.89 mmHg); MD 0.45 mmHg for DBP (MAE 2.89 ± 5.34 mmHg), 95% CI -15.6 to 15.32). CNN-LSTM with grid-search optimization estimated blood pressure from PPG signals with an MAE ± SD of 3.79 ± 7.89 mmHg for SBP and 2.89 ± 5.34 mmHg for DBP, meeting IEEE, AAMI, and BHS standards.
Synapse has enriched 10 related papers. Consider them for comparative context: