Modelling of Chest Wall Motion for Cardiorespiratory Activity for Radar-Based NCVS Systems

Chest Wall Motion Model of Cardiac Activity for Radar-Based Vital-Sign-Detection System

An increasing number of studies on non-contact vital sign detection using radar are now beginning to turn to data-driven neural network approaches rather than traditional signal-processing methods. However, there are few radar datasets available for deep learning due to the difficulty of acquiring and labeling the data, which require specialized equipment and physician collaboration. This paper presents a new model of heartbeat-induced chest wall motion (CWM) with the goal of generating a large amount of simulation data to support deep learning methods. An in-depth analysis of published CWM data collected by the VICON Infrared (IR) motion capture system and continuous wave (CW) radar system during respiratory hold was used to summarize the motion characteristics of each stage within a cardiac cycle. In combination with the physiological properties of the heartbeat, appropriate mathematical functions were selected to describe these movement properties. The model produced simulation data that closely matched the measured data as evaluated by dynamic time warping (DTW) and the root-mean-squared error (RMSE). By adjusting the model parameters, the heartbeat signals of different individuals were simulated. This will accelerate the application of data-driven deep learning methods in radar-based non-contact vital sign detection research and further advance the field.

Heart Rate Variability Monitoring Based on Doppler Radar Using Deep Learning

The potential of microwave Doppler radar in non-contact vital sign detection is significant; however, prevailing radar-based heart rate (HR) and heart rate variability (HRV) monitoring technologies often necessitate data lengths surpassing 10 s, leading to increased detection latency and inaccurate HRV estimates. To address this problem, this paper introduces a novel network integrating a frequency representation module and a residual in residual module for the precise estimation and tracking of HR from concise time series, followed by HRV monitoring. The network adeptly transforms radar signals from the time domain to the frequency domain, yielding high-resolution spectrum representation within specified frequency intervals. This significantly reduces latency and improves HRV estimation accuracy by using data that are only 4 s in length. This study uses simulation data, Frequency-Modulated Continuous-Wave radar-measured data, and Continuous-Wave radar data to validate the model. Experimental results show that despite the shortened data length, the average heart rate measurement accuracy of the algorithm remains above 95% with no loss of estimation accuracy. This study contributes an efficient heart rate variability estimation algorithm to the domain of non-contact vital sign detection, offering significant practical application value.

Laser spectroscopic method for remote sensing of respiratory rate

Noncontact sensing methods for measuring vital signs have recently gained interest, particularly for long-term monitoring. This study introduces a new method for measuring respiratory rate remotely. The proposed method is based on the reflection of a laser beam off a striped card attached to a moving platform simulating chest wall displacements. A wide range of frequencies (n = 35) from 0.06 to 2.2 Hz corresponding to both normal and pathological human respiratory rates were simulated using a moving mechanical platform. Reflected spectra (n = 105) were collected by a spectrometer in a dynamic mode. Fourier analysis was performed to retrieve the breathing frequency. The results show a striking agreement between measurements and reference frequencies. The results also show that low frequencies corresponding to respiratory rates can be detected with high accuracy (uncertainty is well below 5%). A validation test of the measuring method on a human subject demonstrated a great potential for remote respiration rate monitoring of adults and neonates in a clinical environment.

Associations of Three-Dimensional Anthropometric Body Surface Scanning Measurements and Coronary Artery Disease

Background and Objectives: The relationship between three-dimensional (3D) scanning-derived body surface measurements and biomarkers in patients with coronary artery disease (CAD) were assessed. Methods and Methods: The recruitment of 98 patients with CAD confirmed by cardiac catheterization and 98 non-CAD patients were performed between March 2016 and December 2017. A health questionnaire on basic information, life style variables, and past medical and family history was completed. 3D body surface measurements and biomarkers were obtained. Differences between the two groups were assessed and multivariable analysis performed. Results: It was found that chest width (odds ratio [OR] 0.761, 95% confidence interval [CI] = 0.586-0.987, p = 0.0399), right arm length (OR 0.743, 95% CI = 0.632-0.875, p = 0.0004), waist circumference (OR 1.119, 95% CI = 1.035-1.21, p = 0.0048), leptin (OR 1.443, 95% CI = 1.184-1.76, p = 0.0003), adiponectin (OR 0.978, 95% CI = 0.963-0.994, p = 0.006), and interleukin 6 (OR 1.181, 95% CI = 1.021-1.366, p = 0.0254) were significantly associated with CAD. The combination of biomarker scores and body measurement scores had the greatest area under the curve and best association with CAD (area under the curve of 0.8049 and 95% CI = 0.7440-0.8657). Conclusions: Our study suggests that 3D derived body surface measurements in combination with leptin, adiponectin, and interleukin 6 levels may direct us to those at risk of CAD, allowing a non-invasive approach to identifying high-risk patients.