A machine learning strategy for fast prediction of cardiac function based on peripheral pulse wave

Pulse wave signal-driven machine learning for identifying left ventricular enlargement in heart failure patients

BACKGROUND

Left ventricular enlargement (LVE) is a common manifestation of cardiac remodeling that is closely associated with cardiac dysfunction, heart failure (HF), and arrhythmias. This study aimed to propose a machine learning (ML)-based strategy to identify LVE in HF patients by means of pulse wave signals.

METHOD

We constructed two high-quality pulse wave datasets comprising a non-LVE group and an LVE group based on the 264 HF patients. Fourier series calculations were employed to determine if significant frequency differences existed between the two datasets, thereby ensuring their validity. Then, the ML-based identification was undertaken by means of classification and regression models: a weighted random forest model was employed for binary classification of the datasets, and a densely connected convolutional network was utilized to directly estimate the left ventricular diastolic diameter index (LVDdI) through regression. Finally, the accuracy of the two models was validated by comparing their results with clinical measurements, using accuracy and the area under the receiver operating characteristic curve (AUC-ROC) to assess their capability for identifying LVE patients.

RESULTS

The classification model exhibited superior performance with an accuracy of 0.91 and an AUC-ROC of 0.93. The regression model achieved an accuracy of 0.88 and an AUC-ROC of 0.89, indicating that both models can quickly and accurately identify LVE in HF patients.

CONCLUSION

The proposed ML methods are verified to achieve effective classification and regression with good performance for identifying LVE in HF patients based on pulse wave signals. This study thus demonstrates the feasibility and potential of the ML-based strategy for clinical practice while offering an effective and robust tool for diagnosing and intervening ventricular remodeling.

Robust arterial compliance estimation with Katz's fractal dimension of photoplethysmography

Arterial compliance (AC) plays a crucial role in vascular aging and cardiovascular disease. The ability to continuously estimate aortic AC or its surrogate, pulse pressure (PP), through wearable devices is highly desirable, given its strong association with daily activities. While the single-site photoplethysmography (PPG)-derived arterial stiffness indices show reasonable correlations with AC, they are susceptible to noise interference, limiting their practical use. To overcome this challenge, our study introduces a noise-resistant indicator of AC: Katz's fractal dimension (KFD) of PPG signals. We showed that KFD integrated the signal complexity arising from compliance changes across a cardiac cycle and vascular structural complexity, thereby decreasing its dependence on individual characteristic points. To assess its capability in measuring AC, we conducted a comprehensive evaluation using both in silico studies with 4374 virtual human data and real-world measurements. In the virtual human studies, KFD demonstrated a strong correlation with AC (r = 0.75), which only experienced a slight decrease to 0.66 at a signal-to-noise ratio of 15dB, surpassing the best PPG-morphology-derived AC measure (r = 0.41) under the same noise condition. In addition, we observed that KFD's sensitivity to AC varied based on the individual's hemodynamic status, which may further enhance the accuracy of AC estimations. These in silico findings were supported by real-world measurements encompassing diverse health conditions. In conclusion, our study suggests that PPG-derived KFD has the potential to continuously and reliably monitor arterial compliance, enabling unobtrusive and wearable assessment of cardiovascular health.

Risk prediction of pulse wave for hypertensive target organ damage based on frequency-domain feature map

The application of deep learning to the classification of pulse waves in Traditional Chinese Medicine (TCM) related to hypertensive target organ damage (TOD) is hindered by challenges such as low classification accuracy and inadequate generalization performance. To address these challenges, we introduce a lightweight transfer learning model named MobileNetV2SCP. This model transforms time-domain pulse waves into 36-dimensional frequency-domain waveform feature maps and establishes a dedicated pre-training network based on these maps to enhance the learning capability for small samples. To improve global feature correlation, we incorporate a novel fusion attention mechanism (SAS) into the inverted residual structure, along with the utilization of 3 × 3 convolutional layers and BatchNorm layers to mitigate model overfitting. The proposed model is evaluated using cross-validation results from 805 cases of pulse waves associated with hypertensive TOD. The assessment metrics, including Accuracy (92.74 %), F1-score (91.47 %), and Area Under Curve (AUC) (97.12 %), demonstrate superior classification accuracy and generalization performance compared to various state-of-the-art models. Furthermore, this study investigates the correlations between time-domain and frequency-domain features in pulse waves and their classification in hypertensive TOD. It analyzes key factors influencing pulse wave classification, providing valuable insights for the clinical diagnosis of TOD.

Pulse wave-based evaluation of the blood-supply capability of patients with heart failure via machine learning

Pulse wave, as a message carrier in the cardiovascular system (CVS), enables inferring CVS conditions while diagnosing cardiovascular diseases (CVDs). Heart failure (HF) is a major CVD, typically requiring expensive and time-consuming treatments for health monitoring and disease deterioration; it would be an effective and patient-friendly tool to facilitate rapid and precise non-invasive evaluation of the heart's blood-supply capability by means of powerful feature-abstraction capability of machine learning (ML) based on pulse wave, which remains untouched yet. Here we present an ML-based methodology, which is verified to accurately evaluate the blood-supply capability of patients with HF based on clinical data of 237 patients, enabling fast prediction of five representative cardiovascular function parameters comprising left ventricular ejection fraction (LVEF), left ventricular end-diastolic diameter (LVDd), left ventricular end-systolic diameter (LVDs), left atrial dimension (LAD), and peripheral oxygen saturation (SpO2). Two ML networks were employed and optimized based on high-quality pulse wave datasets, and they were validated consistently through statistical analysis based on the summary independent-samples t-test (p > 0.05), the Bland-Altman analysis with clinical measurements, and the error-function analysis. It is proven that evaluation of the SpO2, LAD, and LVDd performance can be achieved with the maximum error < 15%. While our findings thus demonstrate the potential of pulse wave-based, non-invasive evaluation of the blood-supply capability of patients with HF, they also set the stage for further refinements in health monitoring and deterioration prevention applications.

Development of evaluation system for cerebral artery occlusion in emergency medical services: noninvasive measurement and utilization of pulse waves

Rapid reperfusion therapy can reduce disability and death in patients with large vessel occlusion strokes (LVOS). It is crucial for emergency medical services to identify LVOS and transport patients directly to a comprehensive stroke center. Our ultimate goal is to develop a non-invasive, accurate, portable, inexpensive, and legally employable in vivo screening system for cerebral artery occlusion. As a first step towards this goal, we propose a method for detecting carotid artery occlusion using pulse wave measurements at the left and right carotid arteries, feature extraction from the pulse waves, and occlusion inference using these features. To meet all of these requirements, we use a piezoelectric sensor. We hypothesize that the difference in the left and right pulse waves caused by reflection is informative, as LVOS is typically caused by unilateral artery occlusion. Therefore, we extracted three features that only represented the physical effects of occlusion based on the difference. For inference, we considered that the logistic regression, a machine learning technique with no complex feature conversion, is a reasonable method for clarifying the contribution of each feature. We tested our hypothesis and conducted an experiment to evaluate the effectiveness and performance of the proposed method. The method achieved a diagnostic accuracy of 0.65, which is higher than the chance level of 0.43. The results indicate that the proposed method has potential for identifying carotid artery occlusions.

Deep Learning to Reveal the Distribution and Diffusion of Water Molecules in Fuel Cell Catalyst Layers

Water management in the catalyst layers (CLs) of proton-exchange membrane fuel cells is crucial for its commercialization and popularization. However, the high experimental or computational cost in obtaining water distribution and diffusion remains a bottleneck in the existing experimental methods and simulation algorithms, and further mechanistic exploration at the nanoscale is necessary. Herein, we integrate, for the first time, molecular dynamics simulation with our customized analysis framework based on a multiattribute point cloud dataset and an advanced deep learning network. This was achieved through our workflow that generates simulated transport data of water molecules in the CLs as the training and test dataset. Deep learning framework models the multibody solid-liquid system of CLs on a molecular scale and completes the mapping from the Pt/C substrate structure and Nafion aggregates to the density distribution and diffusion coefficient of water molecules. The prediction results are comprehensively analyzed and error evaluated, which reveals the highly anisotropic interaction landscape between 50,000 pairs of interacting nanoparticles and explains the structure and water transport property relationship in the hydrated Nafion film on the molecular scale. Compared to the conventional methods, the proposed deep learning framework shows computational cost efficiency, accuracy, and good visual display. Further, it has a generality potential to model macro- and microscopic mass transport in different components of fuel cells. Our framework is expected to make real-time predictions of the distribution and diffusion of water molecules in CLs as well as establish statistical significance in the structural optimization and design of CLs and other components of fuel cells.

Deep learning-based hemodynamic prediction of carotid artery stenosis before and after surgical treatments

Hemodynamic prediction of carotid artery stenosis (CAS) is of great clinical significance in the diagnosis, prevention, and treatment prognosis of ischemic strokes. While computational fluid dynamics (CFD) is recognized as a useful tool, it shows a crucial issue that the high computational costs are usually required for real-time simulations of complex blood flows. Given the powerful feature-extraction capabilities, the deep learning (DL) methodology has a high potential to implement the mapping of anatomic geometries and CFD-driven flow fields, which enables accomplishing fast and accurate hemodynamic prediction for clinical applications. Based on a brain/neck CT angiography database of 280 subjects, image based three-dimensional CFD models of CAS were constructed through blood vessel extraction, computational domain meshing and setting of the pulsatile flow boundary conditions; a series of CFD simulations were undertaken. A DL strategy was proposed and accomplished in terms of point cloud datasets and a DL network with dual sampling-analysis channels. This enables multimode mapping to construct the image-based geometries of CAS while predicting CFD-based hemodynamics based on training and testing datasets. The CFD simulation was validated with the mass flow rates at two outlets reasonably agreed with the published results. Comprehensive analysis and error evaluation revealed that the DL strategy enables uncovering the association between transient blood flow characteristics and artery cavity geometric information before and after surgical treatments of CAS. Compared with other methods, our DL-based model trained with more clinical data can reduce the computational cost by 7,200 times, while still demonstrating good accuracy (error<12.5%) and flow visualization in predicting the two hemodynamic parameters. In addition, the DL-based predictions were in good agreement with CFD simulations in terms of mean velocity in the stenotic region for both the preoperative and postoperative datasets. This study points to the capability and significance of the DL-based fast and accurate hemodynamic prediction of preoperative and postoperative CAS. For accomplishing real-time monitoring of surgical treatments, further improvements in the prediction accuracy and flexibility may be conducted by utilizing larger datasets with specific real surgical events such as stent intervention, adopting personalized boundary conditions, and optimizing the DL network.

Non-invasive hemodynamic diagnosis based on non-linear pulse wave theory applied to four limbs

Introduction: Hemodynamic diagnosis indexes (HDIs) can comprehensively evaluate the health status of the cardiovascular system (CVS), particularly for people older than 50 years and prone to cardiovascular disease (CVDs). However, the accuracy of non-invasive detection remains unsatisfactory. We propose a non-invasive HDIs model based on the non-linear pulse wave theory (NonPWT) applied to four limbs. Methods: This algorithm establishes mathematical models, including pulse wave velocity and pressure information of the brachial and ankle arteries, pressure gradient, and blood flow. Blood flow is key to calculating HDIs. Herein, we derive blood flow equation for different times of the cardiac cycle considering the four different distributions of blood pressure and pulse wave of four limbs, then obtain the average blood flow in a cardiac cycle, and finally calculate the HDIs. Results: The results of the blood flow calculations reveal that the average blood flow in the upper extremity arteries is 10.78 ml/s (clinically: 2.5-12.67 ml/s), and the blood flow in the lower extremity arteries is higher than that in the upper extremity. To verify model accuracy, the consistency between the clinical and calculated values is verified with no statistically significant differences (p < 0.05). Model IV or higher-order fitting is the closest. To verify the model generalizability, considering the risk factors of cardiovascular diseases, the HDIs are recalculated using model IV, and thus, consistency is verified (p < 0.05 and Bland-Altman plot). Conclusion: We conclude our proposed algorithmic model based on NonPWT can facilitate the non-invasive hemodynamic diagnosis with simpler operational procedures and reduced medical costs.