ABSTRACT
Continuous blood pressure (BP) monitoring is important for patients with hypertension. However, BP measurement with a cuff may be cumbersome for the patient. To overcome this limitation, various studies have suggested cuffless BP estimation models using deep learning algorithms. A generalized model should be considered to decrease the training time, and the model reproducibility should be taken into account in multi-day scenarios. In this study, a BP estimation model with a bidirectional long short-term memory network is proposed. The features are extracted from the electrocardiogram, photoplethysmogram, and ballistocardiogram. The leave-one-subject-out (LOSO) method is incorporated to generalize the model and fine-tuning is applied. The model was evaluated using one-day and multi-day tests. The proposed model achieved a mean absolute error (MAE) of 2.56 and 2.05 mmHg for the systolic and diastolic BP (SBP and DBP), respectively, in the one-day test. Moreover, the results demonstrated that the LOSO method with fine-tuning was more compatible in the multi-day test. The MAE values of the model were 5.82 and 5.24 mmHg for the SBP and DBP, respectively.
Subject(s)
Memory, Short-Term , Photoplethysmography , Blood Pressure , Blood Pressure Determination , Humans , Pulse Wave Analysis , Reproducibility of ResultsABSTRACT
The aim of this study was to reconstruct a 12-lead electrocardiograph (ECG) with a universal transformation coefficient and find the appropriate electrode position and shape for designing a patch-type ECG sensor. A 35-channel ECG monitoring system was developed, and 14 subjects were recruited for the experiment. A feedforward neural network with one hidden layer was applied to train the transformation coefficient. Three electrode shapes (5 cm × 5 cm square, 10 cm × 10 cm square, and right-angled triangle) were considered for the patch-type ECG sensor. The mean correlation coefficient (CC) and minimum CC methods were applied to evaluate the reconstruction performance. The average CCs between the standard 12-lead ECG and reconstructed 12-lead ECG were 0.860, 0.893, and 0.893 for a 5 cm × 5 cm square, 10 cm × 10 cm square, and right-angled triangle shape. The right-angled triangle showed the highest performance among the considered shapes. The results also suggested that the bottom of the central area of the chest was the most suitable position for attaching the patch-type ECG sensor.
Subject(s)
Electrocardiography/methods , Adult , Algorithms , Electrodes , Heart Rate/physiology , Humans , Male , Neural Networks, Computer , Signal Processing, Computer-Assisted , Thorax , Wearable Electronic Devices , Young AdultABSTRACT
In general, three-dimensional ground reaction forces (GRFs) and ground reaction moments (GRMs) that occur during human gait are measured using a force plate, which are expensive and have spatial limitations. Therefore, we proposed a prediction model for GRFs and GRMs, which only uses plantar pressure information measured from insole pressure sensors with a wavelet neural network (WNN) and principal component analysis-mutual information (PCA-MI). For this, the prediction model estimated GRFs and GRMs with three different gait speeds (slow, normal, and fast groups) and healthy/pathological gait patterns (healthy and adolescent idiopathic scoliosis (AIS) groups). Model performance was validated using correlation coefficients (r) and the normalized root mean square error (NRMSE%) and was compared to the prediction accuracy of the previous methods using the same dataset. As a result, the performance of the GRF and GRM prediction model proposed in this study (slow group: r = 0.840-0.989 and NRMSE% = 10.693-15.894%; normal group: r = 0.847-0.988 and NRMSE% = 10.920-19.216%; fast group: r = 0.823-0.953 and NRMSE% = 12.009-20.182%; healthy group: r = 0.836-0.976 and NRMSE% = 12.920-18.088%; and AIS group: r = 0.917-0.993 and NRMSE% = 7.914-15.671%) was better than that of the prediction models suggested in previous studies for every group and component (p < 0.05 or 0.01). The results indicated that the proposed model has improved performance compared to previous prediction models.