Reconstruction of central arterial pressure waveform based on CNN-BILSTM

Personalized Pressure Conditions and Calibration for a Predictive Computational Model of Coronary and Myocardial Blood Flow

Predictive modeling of hyperemic coronary and myocardial blood flow (MBF) greatly supports diagnosis and prognostic stratification of patients suffering from coronary artery disease (CAD). In this work, we propose a novel strategy, using only readily available clinical data, to build personalized inlet conditions for coronary and MBF models and to achieve an effective calibration for their predictive application to real clinical cases. Experimental data are used to build personalized pressure waveforms at the aortic root, representative of the hyperemic state and adapted to surrogate the systolic contraction, to be used in computational fluid-dynamics analyses. Model calibration to simulate hyperemic flow is performed in a "blinded" way, not requiring any additional exam. Coronary and myocardial flow simulations are performed in eight patients with different clinical conditions to predict FFR and MBF. Realistic pressure waveforms are recovered for all the patients. Consistent pressure distribution, blood velocities in the large arteries, and distribution of MBF in the healthy myocardium are obtained. FFR results show great accuracy with a per-vessel sensitivity and specificity of 100% according to clinical threshold values. Mean MBF shows good agreement with values from stress-CTP, with lower values in patients with diagnosed perfusion defects. The proposed methodology allows us to quantitatively predict FFR and MBF, by the exclusive use of standard measures easily obtainable in a clinical context. This represents a fundamental step to avoid catheter-based exams and stress tests in CAD diagnosis.

Calibration-free blood pressure estimation based on a convolutional neural network

In this study, we conducted research on a deep learning-based blood pressure (BP) estimation model suitable for wearable environments. To measure BP while wearing a wearable watch, it needs to be considered that computing power for signal processing is limited and the input signals are subject to noise interference. Therefore, we employed a convolutional neural network (CNN) as the BP estimation model and utilized time-series electrocardiogram (ECG) and photoplethysmogram (PPG) signals, which are quantifiable in a wearable context. We generated periodic input signals and used differential and thresholding methods to decrease noise in the preprocessing step. We then applied a max-pooling technique with filter sizes of 2 × 1 and 5 × 1 within a 3-layer convolutional neural network to estimate BP. Our method was trained, validated, and tested using 2.4 million data samples from 49 patients in the intensive care unit. These samples, totaling 3.1 GB were obtained from the publicly accessible MIMIC database. As a result of a test with 480,000 data samples, the average root mean square error in BP estimation was 3.41, 5.80, and 2.78 mm Hg in the prediction of pulse pressure, systolic BP (SBP), and diastolic BP (DBP), respectively. The cumulative error percentage less than 5 mm Hg was 68% and 93% for SBP and DBP, respectively. In addition, the cumulative error percentage less than 15 mm Hg was 98% and 99% for SBP and DBP. Subsequently, we evaluated the impact of changes in input signal length (1 cycle vs. 30 s) and the introduction of noise on BP estimation results. The experimental results revealed that the length of the input signal did not significantly affect the performance of CNN-based analysis. When estimating BP using noise-added ECG signals, the mean absolute error (MAE) for SBP and DBP was 9.72 and 6.67 mm Hg, respectively. Meanwhile, when using noise-added PPG signals, the MAE for SBP and DBP was 26.85 and 14.00 mm Hg, respectively. Therefore, this study confirmed that using ECG signals rather than PPG signals is advantageous for noise reduction in a wearable environment. Besides, short sampling frames without calibration can be effective as input signals. Furthermore, it demonstrated that using a model suitable for information extraction rather than a specialized deep learning model for sequential data can yield satisfactory results in BP estimation.

Hybrid Deep Morpho-Temporal Framework for Oscillometric Blood Pressure Measurement

Oscillometric blood pressure (BP) measurement devices are widely utilized as the primary automated BP measurement tools in non-specialist environments. However, their accuracy and reliability vary under different settings and for different age groups and health conditions. An essential constraint of current oscillometric BP measurement devices is their analysis algorithms' incapacity to capture the BP information encoded in the pattern of recorded oscillometric pulses to its fullest extent. In this article, we propose a new 2D oscillometric data representation that enables a full characterization of arterial system and empowers the application of deep learning to extract the most informative features correlated with BP. A hybrid convolutional-recurrent neural network was developed to capture the oscillometric pulses morphological information as well as their temporal evolution over the cuff deflation period from the 2D structure, and estimate BP. The performance of the proposed method was verified on three oscillometric databases collected from the wrist and upper arms of 245 individuals. It was found that it achieves a mean error and a standard deviation of error of as low as 0.08 mmHg and 2.4 mmHg in the estimation of systolic BP, and 0.04 mmHg and 2.2 mmHg in the estimation of diastolic BP, respectively. Our proposed method outperformed the state-of-the-art techniques and satisfied the current international standards for BP monitors by a wide margin. The proposed method shows promise toward robust and objective BP estimation in a variety of patients and monitoring situations.

Reconstruction of central arterial pressure waveform based on CBi-SAN network from radial pressure waveform

The central arterial pressure (CAP) is an important physiological indicator of the human cardiovascular system which represents one of the greatest threats to human health. Accurate non-invasive detection and reconstruction of CAP waveforms are crucial for the reliable treatment of cardiovascular system diseases. However, the traditional methods are reconstructed with relatively low accuracy, and some deep learning neural network models also have difficulty in extracting features, as a result, these methods have potential for further advancement. In this study, we proposed a novel model (CBi-SAN) to implement an end-to-end relationship from radial artery pressure (RAP) waveform to CAP waveform, which consisted of the convolutional neural network (CNN), the bidirectional long-short-time memory network (BiLSTM), and the self-attention mechanism to improve the performance of CAP reconstruction. The data on invasive measurements of CAP and RAP waveform were used in 62 patients before and after medication to develop and validate the performance of CBi-SAN model for reconstructing CAP waveform. We compared it with traditional methods and deep learning models in mean absolute error (MAE), root mean square error (RMSE), and Spearman correlation coefficient (SCC). Study results indicated the CBi-SAN model performed great performance on CAP waveform reconstruction (MAE: 2.23 ± 0.11 mmHg, RMSE: 2.21 ± 0.07 mmHg), concurrently, the best reconstruction effect was obtained in the central artery systolic pressure (CASP) and the central artery diastolic pressure(CADP) (RMSECASP: 2.94 ± 0.48 mmHg, RMSECADP: 1.96 ± 0.06 mmHg). These results implied the performance of the CAP reconstruction based on CBi-SAN model was superior to the existing methods, hopped to be effectively applied to clinical practice in the future.

Central Aortic Blood Pressure Waveform Estimation with a Temporal Convolutional Network

A novel temporal convolutional network (TCN) model is utilized to reconstruct the central aortic blood pressure (aBP) waveform from the radial blood pressure waveform. The method does not need manual feature extraction as traditional transfer function approaches. The data acquired by the SphygmoCor CVMS device in 1,032 participants as a measured database and a public database of 4,374 virtual healthy subjects were used to compare the accuracy and computational cost of the TCN model with the published convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model. The TCN model was compared with CNN-BiLSTM in the root mean square error (RMSE). The TCN model generally outperformed the existing CNN-BiLSTM model in terms of accuracy and computational cost. For the measured and public databases, the RMSE of the waveform using the TCN model was 0.55 ± 0.40 mmHg and 0.84 ± 0.29 mmHg, respectively. The training time of the TCN model was 9.63 min and 25.51 min for the entire training set; the average test time was around 1.79 ms and 8.58 ms per test pulse signal from the measured and public databases, respectively. The TCN model is accurate and fast for processing long input signals, and provides a novel method for measuring the aBP waveform. This method may contribute to the early monitoring and prevention of cardiovascular disease.