Search

US-20260123844-A1 - Machine Learning-Based System and Method for Contactless Arterial Blood Pressure Waveform Monitoring

US20260123844A1US 20260123844 A1US20260123844 A1US 20260123844A1US-20260123844-A1

Abstract

The present invention provides machine learning-based system and method for contactless ABPW monitoring. The method comprises: utilizing a mm Wave radar to transmit a mmWave signal waveform and to receive reflection signals from a subject's chest; extracting complex-valued mmWave IQ data from the received reflection signals; utilizing a beamforming-based data augmentation module to steer the complex-valued mmWave IQ data to form target signal beams; and utilizing a mmWave-ABPW transformer to estimate ABPW from the target signal beams. During training stage, the beamforming-based data augmentation module is configured to generate mm Wave signal beam data from different angles for training the mmWave-ABPW transformer; and a cross-modality knowledge transfer module is utilized to generate a teacher model to co-supervise training of the mmWave-ABPW transformer.

Inventors

  • Qingyong HU
  • Qian Zhang
  • YUXUAN ZHOU

Assignees

  • THE HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Dates

Publication Date
20260507
Application Date
20251030

Claims (20)

  1. 1 . A machine learning-based system for contactless ABPW monitoring, comprising: a mmWave radar; one or more processors in communication with the mmWave radar; machine learning tools in communication with the one or more processors; a memory device storing the machine learning tools and inter-operably coupled with the one or more processors; wherein: the machine learning tools include an mmWave-ABPW transformer and a beamforming-based data augmentation module; the mm Wave radar is configured to transmit a mm Wave signal waveform and to receive reflection signals from a subject's chest; the memory device further stores instructions that, when executed, cause the one or more processors to: extract complex-valued mm Wave IQ data from the received reflection signals; utilize the beamforming-based data augmentation module to steer the complex-valued mmWave IQ data to form target signal beams; and utilize the mmWave-ABPW transformer to estimate ABPW from the target signal beams.
  2. 2 . The machine learning-based system of claim 1 , wherein: the transmitted mmWave signal waveform is a frequency modulated continuous waveform; and the mm Wave radar is further configured to mix the received reflection signals with the transmitted mmWave signal waveform to obtain intermediate frequency signals.
  3. 3 . The machine learning-based system of claim 2 , wherein the one or more processors are configured to: apply range-fast Fourier transformation on the intermediate frequency signals to obtain frequency and phase of the intermediate frequency signals; detect the signal regions of the subject's chest from the frequency and phase of the intermediate frequency signals using a constant false alarm rate algorithm; search range bins with largest reflection energy from the detected signal regions; and extract the complex-valued mm Wave IQ data from the searched range bins.
  4. 4 . The machine learning-based system of claim 1 , wherein the mmWave-ABPW transformer includes a ABPW feature extractor comprising: an encoder configured to encode the target signal beams and generate a compressed feature tensor; a self-attention transformer configured to perform global context modelling and spatial attention refinement on the compressed feature tensor to obtain a refined feature tensor; a decoder configured to decode the refined feature tensor and generate an ABPW feature tensor; and a plurality of spatially-aware attention modules bridging intermediate layers of the encoder and the decoder to facilitate the ABPW feature extractor to concatenate feature tensors at different spatial dimensions by selectively re-weight feature activations according to importances of the target signal beams from different reflection areas.
  5. 5 . The machine learning-based system of claim 4 , wherein the mmWave-ABPW transformer further includes a personalization waveform regressor comprising: a plurality of expert regressor models trained respectively with a plurality of training data sets corresponding to respective blood pressure categories; and an explicit gate configured to select an appropriate expert regressor model for ABPW estimation based on a coarse blood pressure category of the subject.
  6. 6 . The machine learning-based system of claim 5 , wherein the appropriate expert regressor model is further trained using ABPW data of the subject.
  7. 7 . The machine learning-based system of claim 1 , wherein the beamforming-based data augmentation module comprises: a first neural network configured to estimate heart rate of the subject from the complex-valued mmWave IQ data; and a second neural network configured to identify spectral features of the complex-valued mmWave IQ data and identify the target signal beams based on the estimated heart rate and the identified spectral features.
  8. 8 . The machine learning-based system of claim 1 , wherein the beamforming-based data augmentation module is configured to generate mmWave signal beam data from different angles for training the mmWave-ABPW transformer.
  9. 9 . The machine learning-based system of claim 1 , wherein the machine learning tools further include a cross-modality knowledge transfer module configured to generate a teacher model to co-supervise training of the mmWave-ABPW transformer.
  10. 10 . The machine learning-based system of claim 1 , wherein the teacher model is a transformer model trained on a public ECG/PPG dataset to predict ECG/PPG signals from mmWave data.
  11. 11 . A machine learning-based method for contactless ABPW monitoring, comprising: utilizing a mmWave radar to transmit a mmWave signal waveform and to receive reflection signals from a subject's chest; extracting complex-valued mmWave IQ data from the received reflection signals; utilizing a beamforming-based data augmentation module to steer the complex-valued mmWave IQ data to form target signal beams; and utilizing a mmWave-ABPW transformer to estimate ABPW from the target signal beams; wherein the beamforming-based data augmentation module and the mmWave-ABPW transformer are machine learning tools in communication with one or more processors and stored in a memory device inter-operably coupled with the one or more processors.
  12. 12 . The machine learning-based method of claim 11 , wherein: the transmitted mmWave signal waveform is a frequency modulated continuous waveform; and the machine learning-based method further comprises mixing the received reflection signals with the transmitted mmWave signal waveform to obtain intermediate frequency signals.
  13. 13 . The machine learning-based method of claim 12 , wherein the complex-valued mmWave IQ data is extracted by the one or more processor through: applying range-fast Fourier transformation on the intermediate frequency signals to obtain frequency and phase of the intermediate frequency signals; detecting the signal regions of the subject's chest from the frequency and phase of the intermediate frequency signals using a constant false alarm rate algorithm; searching range bins with largest reflection energy from the detected signal regions; and extracting the complex-valued mmWave IQ data from the searched range bins.
  14. 14 . The machine learning-based method of claim 11 , wherein the mmWave-ABPW transformer includes a ABPW feature extractor comprising: an encoder, a self-attention transformer, a decoder and a plurality of spatially-aware attention modules bridging intermediate layers of the encoder and the decoder; the estimation of the ABPW from the target signal beams comprises: utilizing the encoder to encode the target signal beams and generate a compressed feature tensor; utilizing the self-attention transformer to perform global context modelling and spatial attention refinement on the compressed feature tensor to obtain a refined feature tensor; utilizing the decoder to decode the refined feature tensor and generate an ABPW feature tensor; and utilizing the plurality of spatially-aware attention modules to facilitate the ABPW feature extractor to concatenate feature tensors at different spatial dimensions by selectively re-weight feature activations according to importances of the target signal beams from different reflection areas.
  15. 15 . The machine learning-based method of claim 14 , wherein the mmWave-ABPW transformer further includes a personalization waveform regressor comprising a plurality of expert regressor models; the machine learning-based method further comprises training the plurality of expert regressor models respectively with a plurality of training data sets corresponding to respective blood pressure categories; and selecting, among the plurality of trained expert regressor model, an appropriate expert regressor model for ABPW estimation based on a coarse blood pressure category of the subject.
  16. 16 . The machine learning-based method of claim 15 , further comprising training the appropriate expert regressor model using ABPW data of the subject.
  17. 17 . The machine learning-based method of claim 11 , wherein the beamforming-based data augmentation module comprises a first neural network and a second neural network; and the target signal beams are formed by: utilizing the first neural network to estimate heart rate of the subject from the complex-valued mmWave IQ data; and utilizing the second neural network to identify spectral features of the complex-valued mmWave IQ data and identify the target signal beams based on the estimated heart rate and the identified spectral features.
  18. 18 . The machine learning-based method of claim 11 , further comprising utilizing the beamforming-based data augmentation module to generate mmWave signal beam data from different angles for training the mmWave-ABPW transformer.
  19. 19 . The machine learning-based method of claim 11 , further comprising utilizing a cross-modality knowledge transfer module to generate a teacher model to co-supervise training of the mmWave-ABPW transformer.
  20. 20 . The machine learning-based method of claim 11 , wherein the teacher model is a transformer model trained on a public ECG/PPG dataset to predict ECG/PPG signals from mmWave data.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application claims priority from the U.S. Provisional Patent Application No. 63/714,886 filed Nov. 1, 2024, and the disclosure of which is incorporated herein by reference in its entirety. FIELD OF THE INVENTION The present invention generally relates to machine learning technology, and more specifically relates to machine-learning-based system and method for contactless arterial blood pressure waveform monitoring. BACKGROUND OF THE INVENTION Blood pressure (BP) monitoring is vital to assess the health status of the heart and cerebral vessels. While discrete systolic/diastolic blood pressure (SBP/DBP) values are commonly measured, they are insufficient for detailed assessment of cardiac indicators (e.g., stroke volume, cardiac output (CO), and vascular resistance), which are associated with prevalent cardiac diseases like heart failure and cardiogenic shock that affect more than 64 million people around the world. Beyond discrete values, the arterial blood pressure waveform (ABPW) contains finer-grained information that depicts the complete cardiac cycle, including the rise of blood pressure due to the blood ejection in the systole stage, the descent at the closure of the aortic valve, and the trough state when blood flows out of the aorta as shown in FIG. 1. With detailed BP variations inside heartbeats, ABPW can also depict abnormalities with internal cardiovascular statuses beyond discrete BP values, some of which may not even be reflected in ECG signals, and offer comprehensive insights into cardiovascular health compared to discrete blood pressure measurements. FIG. 2 shows several cases of cardiac abnormalities that may have similar discrete BP values but behave quite distinctly in ABPW. Continuous ABPW monitoring is significant for assessing the overall cardiovascular status to help diagnose relevant cardiac diseases. Existing ABPW monitoring methods require invasive procedures or continuous skin contact, which are inconvenient and uncomfortable. The arterial catheter-based method inserts a tube into blood vessels. It is a clinical gold standard method but is limited to intensive care unit (ICU) scenarios due to its invasiveness. For non-invasive methods, some prior works, including cuff-based auscultatory and oscillometric methods, wearable methods, contactless solutions, etc., estimate discrete SBP/DBP values as coarse approximations of ABPW, missing essential information on variation trends. Nonetheless, existing contactless solutions all fail to achieve continuous ABPW monitoring, because they require a period of clean signals (several cardiac cycles) to summarize one discrete result based on the pulse transit time (PTT) methodology. Recently, some progress in ABPW monitoring, including the volume clamp method and wearable methods has been made to obtain ABPW in a non-invasive manner. However, they require either dedicated and expensive hardware (˜40K USD) or close skin contact, leading to discomfort and inconvenience in daily scenarios. On the other hand, ABPW is found relating blood volume changes in the vessels and electrical cardiac activities. FIG. 3 exemplifies ABPW during a single cardiac cycle. In the systole stage, the left ventricle ejects blood into the aorta. The kinetic energy of the ejected blood forces the elastic aortic wall to expand, causing an increase in blood pressure. When the aortic valve closes, the previously ejected blood returns to the heart, resulting in a reduction of blood pressure. The highest, lowest, and mean values of the waveform correspond to SBP, DBP, and MAP, respectively. ABPW encompasses vital cardiac information that holds clinical significance. For example, the slope of the ascending waveform reflects myocardial contractility while the slope of the downstroke waveform is related to systemic vascular resistance that is associated with the stress developed in the left ventricular during ejection. The systolic area and diastolic area reflect the ventricular wall stress and contractility. The cumulative area under the ABPW curve (AUC) exhibits a strong correlation with CO, a pivotal measure for evaluating circulatory performance and preventing heart failure. FIG. 2 illustrates several abnormal cases of ABPW. For example, aortic regurgitation is characterized by its bifid waveform is caused by abnormal blood circulation which blood pumped out of the left ventricle leaks backward. Some methods have been using mm Wave signals to reflect chest vibrations caused by cardiac activities. However, it is not straightforward to obtain ABPW from mmWave signals. As ABPW requires accurate estimation for both pressure values and waveform shapes while ECG/PPG/SCG-like signals only require accurate shapes, it is more challenging for contactless ABPW monitoring. From the technique aspect, previous works are mainly based on neural networks with one-level bottleneck with a coarse resolution. Due to the complexity of the cardiac