Single calibration-based non-invasive blood pressure continuous monitoring method and device and storage medium

Abstract

This invention provides a method, device, and storage medium for non-intrusive continuous blood pressure monitoring based on a single calibration. The method includes: during the device calibration phase, acquiring human monitoring signals during the measurement cycle of a pressure sphygmomanometer; calculating the periodic intensity of the signal at different monitoring distance units based on the human monitoring signals to determine the target monitoring position; continuously acquiring the human monitoring signals corresponding to the target monitoring position, extracting phase change signals and further extracting pulse wave signals, inputting them into a vascular feature extraction network to obtain vascular feature parameters; during the independent monitoring phase, continuously acquiring the human monitoring signals corresponding to the target monitoring position; and parallelly segmenting the human monitoring signals at the target monitoring position into multiple signal segments, inputting them along with the vascular feature parameters into a pre-trained blood pressure prediction model to obtain time-series prediction results characterizing systolic and diastolic blood pressure. This invention enables non-intrusive blood pressure measurement at night, while improving the accuracy and robustness of continuous nighttime blood pressure tracking.

Description

Technical Field

[0001] This invention relates to the field of blood pressure measurement technology, and in particular to a non-intrusive continuous blood pressure monitoring method, device, and storage medium based on a single calibration. Background Technology

[0002] In the field of cardiovascular monitoring, nocturnal blood pressure is defined as measured at intervals of ≤30 minutes between 22:00 and 6:00 with ≥20 valid readings. Normal "dipper" blood pressure refers to a 10-20% decrease in nighttime systolic blood pressure compared to daytime blood pressure, reflecting normal autonomic nervous system function; abnormal blood pressure includes non-dipper (decrease <10%), reverse dipper (nighttime blood pressure higher than daytime), and extreme dipper (decrease >20%). Diurnal blood pressure rhythm is an independent predictor of cardiovascular events, but routine clinic and home monitoring struggles to accurately identify it, leading to high missed diagnoses and exposing patients to long-term high risks. Therefore, there is an urgent need to develop a precise nocturnal blood pressure measurement method that meets the quantitative definition.

[0003] Traditional blood pressure measurement methods include those based on the oscillometric principle. This method involves gradually increasing the pressure of a cuff to compress the artery and impede blood flow. Acoustic or optical sensors are used to observe changes in the pulse waveform during this process. When the cuff pressure is below the diastolic pressure, the detected pulse is very weak. As the cuff pressure gradually increases, the pulse amplitude initially increases and then decreases. When the cuff pressure equals the systolic pressure, blood continues to flow through the blocked artery, but only the highest arterial pressure is detected. The mean pressure is determined by detecting the location of the largest pulse amplitude, and the systolic and diastolic pressures are determined by the peak amplitude ratio.

[0004] However, traditional blood pressure measurement methods require inflation every 30 minutes at night and pressurization to above systolic pressure. The noise generated can easily wake users at night, and prolonged excessive inflation can cause skin redness, swelling, and local bruising, affecting normal blood flow. This not only causes errors in the measurement results but may also damage the user's vascular health. Therefore, it is not suitable for nighttime blood pressure measurement and usually only provides instantaneous measurement results, making it unsuitable for comfortable continuous monitoring. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, device, and storage medium for continuous, non-intrusive blood pressure monitoring based on a single calibration, to eliminate or improve one or more defects existing in the prior art. It can solve the problems of traditional blood pressure measurement methods being cumbersome and unable to perform continuous monitoring at night.

[0006] One aspect of the present invention provides a method for continuous, non-intrusive blood pressure monitoring based on a single calibration, the method comprising the following steps:

[0007] During the equipment calibration phase, the target human body's human monitoring signal based on the millimeter-wave device is acquired during the measurement cycle of the pressurized blood pressure monitor.

[0008] Based on human body monitoring signals, the periodic intensity of the signal at different monitoring distance units is calculated, and the distance unit with the largest periodic intensity is determined as the target monitoring location;

[0009] The system continuously acquires human body monitoring signals corresponding to the target monitoring location, extracts phase change signals from them, and performs signal processing on the phase change signals to extract pulse wave signals that characterize arterial pulsation.

[0010] The pulse wave signal is input into a pre-trained vascular feature extraction network to obtain vascular feature parameters that characterize vascular elasticity and peripheral resistance.

[0011] During the independent monitoring phase, human body monitoring signals corresponding to the target monitoring location are continuously acquired; millimeter-wave equipment collects signals at a preset sampling rate.

[0012] Based on predetermined different time scales, the human monitoring signals at the target monitoring location are divided into multiple signal segments in parallel, and these segments are input into a pre-trained blood pressure prediction model along with vascular feature parameters to obtain time-series prediction results characterizing systolic and diastolic blood pressure. The blood pressure prediction model includes feature extraction pathways that correspond one-to-one with the multiple signal segments.

[0013] In some embodiments of the present invention, the blood pressure prediction model includes a first network branch, a second network branch, a cross-attention mechanism layer connected to the first network branch and the second network branch respectively, and a fully connected output layer connected to the cross-attention mechanism.

[0014] The first network branch includes multiple feature extraction pathways, which are used to extract joint feature tensors representing pulse wave waveforms, target human heart rate and respiration based on multiple signal segments;

[0015] The second network branch is used to receive vascular feature parameters;

[0016] The cross-attention mechanism layer is used to fuse vascular feature parameters as a conditional vector with the joint feature tensor to obtain fused features, which are then input into the fully connected output layer.

[0017] The fully connected output layer is used to output temporal prediction results based on fused features.

[0018] In some embodiments of the present invention, the first network branch includes a first path, a second path, a third path, a residual block with shared weights connected to the first path, the second path, and the third path respectively, an intra-path attention layer, an inter-path attention layer, and a feature splicing layer.

[0019] The first pathway is used to extract the waveform features of the pulse wave based on the signal segment; the second pathway is used to extract the heart rate features of the target human body based on the signal segment; and the third pathway is used to extract the respiratory features of the target human body based on the signal segment.

[0020] The input of the attention layer within the pathway is connected to the output of the residual block with shared weights, which is used to weight waveform features, heart rate features, and respiratory features.

[0021] The input end of the inter-path attention layer is connected to the output end of the intra-path attention layer to fuse weighted waveform features, heart rate features, and respiratory features;

[0022] The input of the feature splicing layer is connected to the output of the inter-path attention layer, which is used to integrate the fused features into a joint feature tensor.

[0023] In some embodiments of the present invention, based on predetermined different time scales, the human body monitoring signal from the target monitoring location is divided into multiple signal segments in parallel, including:

[0024] According to the first preset duration, the human body monitoring signal at the target monitoring location is divided into several first signal segments and input to the first channel;

[0025] According to the second preset duration, the human body monitoring signal at the target monitoring location is divided into several second signal segments and input to the second channel;

[0026] According to the third preset duration, the human body monitoring signal at the target monitoring location is divided into several third signal segments and input to the third channel; wherein, the first preset duration is shorter than the second preset duration, and the second preset duration is shorter than the third preset duration.

[0027] In some embodiments of the present invention, the blood pressure prediction model is trained through the following steps:

[0028] Acquire training data, which includes several batches of sample signal segments and corresponding sample time-series prediction results; each batch of sample signal segments includes the first sample signal segment, the second sample signal segment, and the third sample signal segment;

[0029] The training data is input into the initial blood pressure prediction model in batches to obtain the training results; the model structure of the initial blood pressure prediction model is the same as that of the blood pressure prediction model.

[0030] Input the training results and sample time-series prediction results into the preset loss function to obtain the loss value;

[0031] The initial blood pressure prediction model is iteratively trained using the loss value to obtain the blood pressure prediction model.

[0032] In some embodiments of the present invention, the blood vessel feature extraction network is trained through the following steps:

[0033] Acquire training data, which includes sample pulse wave signals and corresponding supervisory signals; the supervisory signals include sample cuff pressure signals synchronously acquired by the compression blood pressure monitor during the acquisition of sample pulse wave signals.

[0034] The sample pulse wave signal is input into the initial feature extraction network to obtain the training result;

[0035] The training results and supervision signals are input into a preset loss function to obtain the loss value;

[0036] The feature extraction network is iteratively trained using the loss value until the model converges, resulting in the vascular feature extraction network.

[0037] In some embodiments of the present invention, the human body monitoring signal is obtained by mixing the transmitted signal of the millimeter-wave device with the reflected signal corresponding to the transmitted signal to obtain an intermediate frequency signal, and then processing it through a fast Fourier transform.

[0038] Based on human body monitoring signals, the periodic intensity of the signal at different monitoring distance units is calculated, and the distance unit with the largest periodic intensity is determined as the target monitoring location, including:

[0039] Based on each peak value in the human body monitoring signal, the distance unit is determined and the intermediate frequency signal is mapped to each distance unit;

[0040] Based on the signal corresponding to each distance cell and the preset autocorrelation function, the autocorrelation function value corresponding to each distance cell is calculated; the magnitude of the autocorrelation function value is positively correlated with the period intensity.

[0041] According to the preset heart rate range, the distance cell corresponding to the maximum autocorrelation function value is found from the distance cells and used as the target distance cell;

[0042] The target monitoring location is determined based on the target distance unit.

[0043] In some embodiments of the present invention, signal processing is performed on the phase change signal to extract the pulse wave signal characterizing arterial pulsation, including:

[0044] Bandpass filtering is applied to the phase-changing signal to remove noise;

[0045] Wavelet transform is performed on the noise-removed reciprocal signals to obtain the pulse wave signal.

[0046] Another aspect of the present invention provides a non-contact continuous blood pressure monitoring device based on single calibration, comprising a processor, a memory, and a computer program / instructions stored in the memory. The processor is used to execute the computer program / instructions. When the computer program / instructions are executed, the device implements the steps of the non-contact continuous blood pressure monitoring method based on single calibration as described above. The device is communicatively connected to a millimeter-wave device to receive human body monitoring signals of the target human body collected in real time by the millimeter-wave device. The device is also communicatively connected to a pressure sphygmomanometer to receive cuff pressure signals collected in real time by the pressure sphygmomanometer.

[0047] Another aspect of the present invention provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the steps of the previously described method for continuous, non-intrusive blood pressure monitoring based on a single calibration.

[0048] The present invention provides a non-contact continuous blood pressure monitoring method and device based on single-calibration, which solves the problems of cumbersome procedures and inability to perform continuous monitoring at night in traditional blood pressure measurement methods. By simultaneously acquiring cuff pressure signals and human body monitoring signals from millimeter-wave devices during the brief inflatation process of a pressure-type blood pressure monitor, and combining this with a vascular feature extraction network, personalized vascular feature parameters reflecting vascular elasticity and peripheral resistance characteristics can be obtained with only a single calibration. This significantly reduces the reliance on frequent calibrations and avoids the sleep disturbances and potential vascular health risks caused by multiple inflatations in traditional solutions. Simultaneously, a multi-timescale analysis mechanism is employed to adaptively segment the human body monitoring signals, extracting features through multiple pathways of the blood pressure prediction model. This allows for sensitive detection of the dynamic changes in vascular characteristics at night, significantly improving the accuracy and robustness of continuous nighttime blood pressure tracking.

[0049] In addition, during the nighttime continuous monitoring phase, users only need to wear millimeter-wave monitoring devices to achieve imperceptible and non-intrusive continuous blood pressure monitoring. While ensuring the comfort of wearable devices, it meets clinical-grade accuracy requirements and can be applied to various scenarios that require long-term monitoring of blood pressure fluctuation patterns.

[0050] Additional advantages, objects, and features of the invention will be set forth in part in the description which follows, and will also become apparent in part to those skilled in the art upon studying the description, or may be learned by practice of the invention. The objects and other advantages of the invention can be realized and obtained by means of the structures specifically pointed out in the description and drawings.

[0051] Those skilled in the art will understand that the objectives and advantages achievable with the present invention are not limited to those specifically described above, and that the above and other objectives achievable with the present invention will become clearer from the following detailed description. Attached Figure Description

[0052] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, are not intended to limit the scope of the invention. In the drawings:

[0053] Figure 1 This is a flowchart of a non-intrusive continuous blood pressure monitoring method based on a single calibration, provided as an embodiment of the present invention.

[0054] Figure 2 This is a schematic diagram of the equipment calibration stage and the independent monitoring stage provided in an embodiment of the present invention.

[0055] Figure 3 This is a schematic diagram of the training process of a blood vessel feature extraction network provided in an embodiment of the present invention.

[0056] Figure 4 This is a schematic diagram of the feature extraction process of the first network branch in a blood pressure prediction model provided in an embodiment of the present invention.

[0057] Figure 5 This is a schematic diagram of the prediction process of a blood pressure prediction model provided in an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this invention are used to explain the invention, but are not intended to limit the invention.

[0059] It should also be noted that, in order to avoid obscuring the invention with unnecessary details, only the structures and / or processing steps closely related to the solution according to the invention are shown in the accompanying drawings, while other details that are not closely related to the invention are omitted.

[0060] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0061] It should also be noted that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection involving an intermediary.

[0062] In the following description, embodiments of the invention will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0063] The following is a detailed description of the non-intrusive continuous blood pressure monitoring method based on single calibration provided in this application.

[0064] like Figure 1As shown, the embodiments of this application provide a non-intrusive continuous blood pressure monitoring method based on single calibration. The implementation of this method can rely on a computer program, which can run on computer devices such as smartphones, tablets, and personal computers, or run on a server. This embodiment does not limit the operating entity of the method.

[0065] The non-contact continuous blood pressure monitoring method based on single-calibration provided in this embodiment is based on single-device calibration. It uses a millimeter-wave device to independently detect the pulse wave signal of the target human body in a non-contact manner, thereby predicting the target human body's nighttime blood pressure. Specifically, the method includes at least steps S101 to S106:

[0066] Step S101: During the equipment calibration phase, the target human body's human body monitoring signal based on the millimeter-wave device is acquired during the measurement cycle of the pressurized blood pressure monitor.

[0067] Among them, the pressure blood pressure monitor includes, but is not limited to, a pressure blood pressure monitor worn on the wrist of the target human body, or a pressure blood pressure monitor worn on the arm of the target human body. This embodiment does not limit the implementation method of the pressure blood pressure monitor.

[0068] Traditional cuffless blood pressure monitoring technology (based on optical sensors or millimeter-wave radar to extract pulse wave features) improves portability and comfort, but has significant calibration limitations due to changes in physiological characteristics such as blood vessel volume and elasticity at night: it requires real-time pressure calibration (which interferes with sleep continuity) and relies on long-term personalized data collection or stimulating experiments (such as cold pressurization tests), which leads to a deterioration in user experience and makes it difficult to meet the accurate monitoring needs of natural sleep at night.

[0069] To address the aforementioned technical challenges, this embodiment simultaneously acquires millimeter-wave radar signals and cuff pressure signals during the brief inflation calibration of the pressure monitor. A personalized vascular model is established through a single calibration to support subsequent long-term, continuous, and non-intrusive blood pressure monitoring. This single inflation calibration captures the unique vascular physiological characteristics of each individual, overcoming the limitations of traditional methods that require frequent calibration or rely on stimulating experiments, significantly improving user experience and monitoring accuracy.

[0070] like Figure 2 As shown, during the device calibration phase, by simultaneously acquiring the cuff pressure signal during the inflation process of the pressurized blood pressure monitor and the human body monitoring signal of the millimeter-wave device, more vascular characteristic parameters (such as pulse wave velocity, pulse pressure, etc.) for characterizing vascular elasticity and vascular characteristic parameters (such as total peripheral resistance, etc.) for characterizing peripheral vascular resistance are obtained through a single calibration.

[0071] The human body monitoring signal is obtained by mixing the transmitted signal of the millimeter-wave device with the corresponding reflected signal to obtain the intermediate frequency signal, and then processing it through Fast Fourier Transform (FFT).

[0072] Specifically, a millimeter-wave device (such as an FMCW millimeter-wave radar) worn on the wrist or placed at a designated location transmits a frequency-modulated continuous wave (FMCW) signal and receives the echo reflected from the target human body. The transmitted and received signals are down-converted by a mixer to obtain an intermediate frequency signal containing vital signs information of the target human body. This signal is modulated by periodic micro-movements on the target human body surface and carries rich respiratory and pulse characteristics.

[0073] The transmitted signal of the millimeter-wave device can be expressed by the following formula:

[0074]

[0075] In the formula, This represents a complex exponential signal emitted at time t; Indicates the amplitude of the signal transmitted by the millimeter-wave device; The basis for representing complex exponential functions; Represents the imaginary unit; This indicates the center carrier frequency at which millimeter-wave equipment operates; This represents the bandwidth of a linear frequency modulated pulse. This represents the period of a chirp signal.

[0076] The reflected signal can be represented by the following formula:

[0077]

[0078] In the formula, This represents the signal received by the millimeter-wave device at time t; Indicates the amplitude of the signal transmitted by the millimeter-wave device; Indicates the base; Represents the imaginary unit; This indicates the center carrier frequency at which millimeter-wave equipment operates; This represents the bandwidth of a linear frequency modulated pulse. This represents the period of a chirp signal; This indicates the time delay between the transmitted and received signals.

[0079] By performing a Fast Fourier Transform on the intermediate frequency signal, the time-domain signal can be converted to the frequency domain, generating a spectrum with clearly separated spectral peaks, thus obtaining the human body monitoring signal. In this spectrum, respiratory and heart rate frequencies are typically presented as significant and distinguishable peaks, thereby enabling non-contact monitoring and extraction of human vital signs.

[0080] The intermediate frequency signal can be represented by the following formula:

[0081]

[0082] In the formula, , indicating the amplitude of the intermediate frequency signal; , represents the frequency of the intermediate frequency signal, where, This indicates the speed at which millimeter waves propagate in the air; , representing the phase of the intermediate frequency signal, where, Indicates wavelength; Indicates the base; It represents the imaginary unit.

[0083] Step S102: Based on the human body monitoring signal, calculate the periodic intensity of the signal at different monitoring distance units, and determine the distance unit with the largest periodic intensity as the target monitoring location.

[0084] Because the frequency of the signal emitted by a millimeter-wave device changes over time, forming a continuous frequency-modulated signal, the distance between the millimeter-wave device and the monitoring location can be determined by measuring the frequency difference between the reflected signal from the target human body and the emitted signal.

[0085] Specifically, the distance between the millimeter-wave device and the monitoring location can be expressed by the following formula:

[0086]

[0087] In the formula, Indicates the distance between the millimeter-wave device and the monitoring location; Indicates the frequency of the intermediate frequency signal; This indicates the speed at which millimeter waves propagate in the air; This represents the period of a chirp signal; This represents the bandwidth of a linear frequency modulated pulse.

[0088] In the operation of millimeter-wave equipment, the reflected signal experiences varying time delays due to different monitoring locations at different distances. These delays, after mixing with the transmitted signal, result in multiple intermediate frequency (IF) signal components with different frequencies at the baseband. By performing a Fast Fourier Transform (FFT) on this composite IF signal, multiple separate peaks can be generated in the spectrum. Each peak appears at a specific distance unit, corresponding to a reflection point or object at a specific distance.

[0089] By leveraging the linear mapping relationship between frequency and distance, the radial distance of each monitoring location relative to the millimeter-wave device can be accurately calculated. This allows different detection locations to be mapped to different monitoring distance units based on the performance of the intermediate frequency signal in the frequency domain and the characteristics of the millimeter-wave device.

[0090] Meanwhile, pulse wave time series exhibit significant periodicity due to their rhythmic physiological activity. Based on this, the periodic intensity of a signal intensity time series can be measured by quantifying the degree of deviation between the time series and itself at different time offsets. That is, the periodic intensity is quantified by calculating its autocorrelation function to measure the similarity between the intermediate frequency signal and itself at different time delays.

[0091] The autocorrelation function can be expressed by the following formula:

[0092]

[0093] In the formula, This represents the signal strength of the intermediate frequency signal at time t; Indicates the elapsed time The signal strength afterward; This indicates the length of the entire time series.

[0094] In this embodiment, the value of the autocorrelation function is positively correlated with the signal period intensity. Based on this relationship, by calculating the autocorrelation function of the signal corresponding to each distance unit, the distance unit with the largest autocorrelation function value is determined as the target distance unit, thereby accurately locating the target monitoring location—that is, the area where the target artery is located.

[0095] Meanwhile, to accurately extract the pulse wave signal, the calculation of the autocorrelation function needs to be constrained within a physiologically reasonable heart rate range. Given that the normal heart rate range is 50~160 bpm, this is converted into a corresponding time frequency range, and the global maximum value of the autocorrelation function is found within this range to determine the spatial coordinates of the wrist artery.

[0096] The global maximum value of the autocorrelation function within the time frequency range corresponding to the normal heart rate variation interval can be expressed by the following formula:

[0097]

[0098] In the formula, This represents the minimum time delay used to calculate the autocorrelation function, corresponding to the cycle represented by the highest heart rate (e.g., 160 bpm); This represents the maximum time delay used when calculating the autocorrelation function, corresponding to the cycle represented by the lowest heart rate (e.g., 50 bpm).

[0099] in, , Indicates the minimum heart rate. Indicates the signal sampling rate; , This indicates the maximum heart rate.

[0100] The spatial coordinates of the wrist artery can be determined by the following formula:

[0101]

[0102] In the formula, Represents the target distance unit; This means searching across all distance cells d to find the d that maximizes the function value; This represents the maximum value of the autocorrelation function corresponding to the distance unit d within the set heart rate range.

[0103] Specifically, based on the human body monitoring signal, the periodic intensity of the signal at different monitoring distance units is calculated, and the distance unit with the largest periodic intensity is determined as the target monitoring location. This includes: determining the distance unit based on each peak value in the human body monitoring signal and mapping the intermediate frequency signal to each distance unit; calculating the autocorrelation function value corresponding to each distance unit based on the signal corresponding to each distance unit and the preset autocorrelation function; finding the distance unit corresponding to the largest autocorrelation function value from the distance units according to the preset heart rate range, and using it as the target distance unit; and determining the target monitoring location based on the target distance unit.

[0104] In some embodiments of the present invention, the target distance unit includes a distance unit where the main target artery is located and a distance unit corresponding to its adjacent reference area.

[0105] Accordingly, the target monitoring location includes the location of the target artery and the location of the adjacent reference area of ​​the target artery. Among them, the adjacent reference area of ​​the target artery is located in the same scanning area as the target artery and has no obvious large blood vessels or significant periodic activity.

[0106] Step S103: Continuously acquire human body monitoring signals corresponding to the target monitoring location, extract phase change signals from them, and perform signal processing on the phase change signals to extract pulse wave signals that characterize arterial pulsation.

[0107] The phase signal at the target location is continuously monitored over time, and its phase change sequence is recorded. Then, a pulse wave signal representing arterial pulsation is extracted through a signal processing workflow. First, bandpass filtering is used to suppress low-frequency interference in the environment and high-frequency noise from the radar system. Next, wavelet transform is applied to accurately separate the periodic pulse wave signal from the processed signal.

[0108] Specifically, signal processing is performed on the phase change signal to extract the pulse wave signal that represents arterial pulsation, including: performing bandpass filtering on the phase change signal to remove noise; and performing wavelet transform on the noise-removed phase change signal to obtain the pulse wave signal.

[0109] Step S104: Input the pulse wave signal into the pre-trained vascular feature extraction network to obtain vascular feature parameters that characterize vascular elasticity and peripheral resistance.

[0110] The blood vessel feature extraction network was pre-trained through the following steps:

[0111] Step S1041: Obtain training data.

[0112] like Figure 3 As shown, the training data includes sample pulse wave signals and corresponding supervisory signals; the supervisory signals include sample cuff pressure signals synchronously acquired by the compression blood pressure monitor during the acquisition of sample pulse wave signals.

[0113] Step S1042: Input the sample pulse wave signal into the initial feature extraction network to obtain the training result.

[0114] In this embodiment, the feature extraction network is a convolutional temporal network, whose input is the millimeter-wave pulse wave signal during the calibration process. The convolutional temporal network captures vascular motion characteristics, using synchronously acquired sample cuff pressure signals as supervisory values. It learns the pressure magnitude corresponding to different pulse waveform shapes and amplitudes, reflecting vascular changes under different pressure states. Finally, it extracts personalized vascular feature parameters reflecting vascular elasticity and peripheral resistance, providing a dynamic modeling basis for continuous nighttime blood pressure monitoring.

[0115] Step S1043: Input the training results and supervision signals into a preset loss function to obtain the loss value. Here, the preset loss function refers to a loss function that has been pre-set.

[0116] In some embodiments of the present invention, the preset loss function includes, but is not limited to, the mean squared error loss function or the smoothing L1 loss function. This embodiment does not limit the implementation of the preset loss function.

[0117] Step S1044: Use the loss value to iteratively train the feature extraction network until the model converges, and obtain the blood vessel feature extraction network.

[0118] Specifically, based on the loss value, the parameters of the feature extraction network are iteratively updated using the backpropagation algorithm until the model converges, ultimately yielding a trained vascular feature extraction network.

[0119] Step S105: During the independent monitoring phase, continuously acquire human body monitoring signals corresponding to the target monitoring location; the millimeter-wave device collects signals at a preset sampling rate.

[0120] like Figure 2 As shown, during the independent nighttime monitoring phase, a millimeter-wave device is worn on the wrist of the target human body to collect signals at a preset sampling rate (e.g., 10Hz, 30Hz, or 100Hz). The acquired transmitted signal is mixed with the corresponding transmitted signal to obtain an intermediate frequency signal, which is then subjected to a fast Fourier transform to obtain the human body monitoring signal.

[0121] Step S106: Based on predetermined different time scales, the human monitoring signal at the target monitoring location is segmented into multiple signal segments in parallel, and these segments, along with vascular feature parameters, are input into a pre-trained blood pressure prediction model to obtain time-series prediction results characterizing systolic and diastolic blood pressure. The blood pressure prediction model includes feature extraction pathways that correspond one-to-one with each of the multiple signal segments.

[0122] In some embodiments of the present invention, the blood pressure prediction model includes a first network branch, a second network branch, a cross-attention mechanism layer connected to the first network branch and the second network branch respectively, and a fully connected output layer connected to the cross-attention mechanism.

[0123] The first network branch includes multiple feature extraction pathways, which are used to extract joint feature tensors representing pulse wave waveforms, target human heart rate and respiration based on multiple signal segments.

[0124] Traditional cuffless blood pressure monitoring technology uses optical sensors, millimeter-wave radar, and other methods to sense arterial pulsation and extract blood pressure-related features such as pulse wave amplitude, pulse wave propagation time, reflected wave propagation time, and systolic-diastolic ratio. This can improve portability and comfort, but it ignores the vascular characteristics of the oscilloscope envelope response during the pressurization process, leading to failure in subsequent long-term measurements.

[0125] To solve the above technical problems, such as Figure 4 As shown, in this embodiment, the nighttime human body monitoring signal is divided into multiple signal segments according to different time scales, and each segment is input into a different pathway. A convolutional neural network is used to process and extract physiological features at different time scales, including pulse waveform features (e.g., the amplitude ratio of the main wave to the dicrotic wave) extracted from the short-term pathway, heart rate features (e.g., heart rate variability) extracted from the medium-term pathway, and respiratory features (e.g., the respiratory rhythm coupling effect of the 0.1-0.3Hz frequency band) extracted from the long-term pathway. Simultaneously, each pathway adopts a residual block structure with shared weights, and the output features are fused through intra- and inter-path attention mechanisms to form a joint feature tensor of "pulse wave-heart rate-respiration".

[0126] Specifically, the first network branch includes a first path, a second path, a third path, residual blocks with shared weights connected to the first path, the second path, and the third path respectively, an intra-path attention layer, an inter-path attention layer, and a feature splicing layer;

[0127] The first path is used to extract the waveform features of the pulse wave based on the signal segment; the second path is used to extract the heart rate features of the target human body based on the signal segment; and the third path is used to extract the respiratory features of the target human body based on the signal segment. The input of the attention layer within each path is connected to the output of the residual block with shared weights, and is used to weight the waveform features, heart rate features, and respiratory features.

[0128] Specifically, based on predetermined different time scales, the human monitoring signal from the target monitoring location is divided into multiple signal segments in parallel, and these segments, along with vascular feature parameters, are input into a pre-trained blood pressure prediction model. This includes: dividing the human monitoring signal from the target monitoring location into several first signal segments according to a first preset duration and inputting them into a first pathway; dividing the human monitoring signal from the target monitoring location into several second signal segments according to a second preset duration and inputting them into a second pathway; dividing the human monitoring signal from the target monitoring location into several third signal segments according to a third preset duration and inputting them into a third pathway; wherein the first preset duration is shorter than the second preset duration, and the second preset duration is shorter than the third preset duration; and inputting vascular feature parameters into a second network branch.

[0129] In some embodiments of the present invention, the first preset duration is 2 seconds; the second preset duration is 4 seconds; and the third preset duration is 32 seconds.

[0130] In actual implementation, the first preset duration can be 1.5 seconds or 2.5 seconds, etc.; the second preset duration can be 3.5 seconds or 4.5 seconds, etc.; and the third preset duration can be 31 seconds or 33 seconds, etc. The values ​​of the first, second, or third preset durations can be adjusted according to actual needs. The blood pressure prediction model may also include other feature extraction pathways. This embodiment does not limit the values ​​of the first, second, or third preset durations, nor the implementation method of the blood pressure prediction model.

[0131] In this embodiment, the input of the inter-path attention layer is connected to the output of the intra-path attention layer, and is used to fuse weighted waveform features, heart rate features, and respiratory features. The input of the feature splicing layer is connected to the output of the inter-path attention layer, and is used to integrate the fused features into a joint feature tensor.

[0132] like Figure 5As shown, the second network branch is used to receive vascular feature parameters. By using the vascular feature parameters obtained during the device calibration phase as a conditional vector, and fusing them with the joint feature tensor through an attention mechanism, the final output layer predicts the time series results of systolic and diastolic blood pressure.

[0133] Specifically, the cross-attention mechanism layer is used to fuse vascular feature parameters as conditional vectors with joint feature tensors to obtain fused features, which are then input into the fully connected output layer; the fully connected output layer is used to output temporal prediction results based on the fused features.

[0134] In summary, the non-contact blood pressure continuous monitoring method based on single calibration provided in this embodiment acquires the human body monitoring signal of the target human body based on the millimeter-wave device during the measurement cycle of the pressurized blood pressure monitor during the device calibration stage; based on the human body monitoring signal, the periodic intensity of the signal at different monitoring distance units is calculated, and the distance unit with the largest periodic intensity is determined as the target monitoring position;

[0135] The system continuously acquires human monitoring signals corresponding to the target monitoring location, extracts phase change signals from these signals, and processes these signals to extract pulse wave signals representing arterial pulsation. The pulse wave signals are then input into a pre-trained vascular feature extraction network to obtain vascular feature parameters representing vascular elasticity and peripheral resistance. During the independent monitoring phase, human monitoring signals corresponding to the target monitoring location are continuously acquired. A millimeter-wave device collects signals at a preset sampling rate. Based on predetermined different time scales, the human monitoring signals at the target monitoring location are divided into multiple signal segments in parallel, and these segments, along with the vascular feature parameters, are input into a pre-trained blood pressure prediction model to obtain time-series prediction results representing systolic and diastolic blood pressure. This approach solves the problems of cumbersome processes and the inability to perform continuous monitoring at night in traditional blood pressure measurement methods. By simultaneously acquiring cuff pressure signals and human monitoring signals from the millimeter-wave device during the brief inflation of the pressure monitor, and combining this with the vascular feature extraction network, personalized vascular feature parameters reflecting vascular elasticity and peripheral resistance can be obtained with only a single calibration. This significantly reduces the reliance on frequent calibrations and avoids user sleep disturbances and potential vascular health risks caused by multiple inflations in traditional solutions. Meanwhile, a multi-timescale analysis mechanism is adopted to adaptively segment human monitoring signals and extract features through multiple pathways of the blood pressure prediction model, thereby sensitively detecting the dynamic changes in vascular characteristics at night and significantly improving the accuracy and robustness of continuous nighttime blood pressure tracking.

[0136] Furthermore, during the continuous nighttime monitoring phase, users only need to wear millimeter-wave monitoring devices to achieve seamless and non-intrusive continuous blood pressure monitoring. While ensuring the comfort of wearable devices, it meets clinical-grade accuracy requirements and is applicable to various scenarios that require long-term monitoring of blood pressure fluctuation patterns, including automatic identification of dipper / non-dipper blood pressure rhythms in hypertensive patients, monitoring of blood pressure compensatory changes related to sleep apnea syndrome, and nighttime blood pressure assessment needs in the management of other chronic diseases, providing an effective technical means for nighttime blood pressure health management.

[0137] Corresponding to the above method, the present invention also provides a non-contact continuous blood pressure monitoring device based on single calibration. This device includes a computer device comprising a processor and a memory. The memory stores computer instructions, and the processor executes the computer instructions stored in the memory. When the computer instructions are executed by the processor, the non-contact continuous blood pressure monitoring device based on single calibration implements the steps of the method described above. The device is communicatively connected to a millimeter-wave device to receive human body monitoring signals from a target human body collected in real time by the millimeter-wave device; the device is also communicatively connected to a pressure sphygmomanometer to receive cuff pressure signals collected in real time by the pressure sphygmomanometer.

[0138] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the aforementioned method. The computer-readable storage medium may be a tangible storage medium, such as random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, floppy disk, hard disk, removable storage disk, CD-ROM, or any other form of storage medium known in the art.

[0139] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the desired tasks. The programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave.

[0140] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0141] In this invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

[0142] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and variations of the embodiments of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for continuous, non-intrusive blood pressure monitoring based on a single calibration, characterized in that, The method includes the following steps: During the equipment calibration phase, the target human body's human monitoring signal based on the millimeter-wave device is acquired during the measurement cycle of the pressurized blood pressure monitor. Based on the human body monitoring signal, the periodic intensity of the signal at different monitoring distance units is calculated, and the distance unit with the largest periodic intensity is determined as the target monitoring location; The system continuously acquires human body monitoring signals corresponding to the target monitoring location, extracts phase change signals from them, and performs signal processing on the phase change signals to extract pulse wave signals that characterize arterial pulsation. The pulse wave signal is input into a pre-trained vascular feature extraction network to obtain vascular feature parameters characterizing vascular elasticity and peripheral resistance. During the independent monitoring phase, human body monitoring signals corresponding to the target monitoring location are continuously acquired; the millimeter-wave device collects signals at a preset sampling rate. Based on predetermined different time scales, the human monitoring signals at the target monitoring location are segmented into multiple signal segments in parallel, and these segments are input into a pre-trained blood pressure prediction model along with the vascular feature parameters to obtain time-series prediction results characterizing systolic and diastolic blood pressure; wherein, the blood pressure prediction model includes feature extraction pathways that correspond one-to-one with the multiple signal segments. The blood pressure prediction model includes a first network branch, a second network branch, a cross-attention mechanism layer connected to both the first and second network branches, and a fully connected output layer connected to the cross-attention mechanism. The first network branch includes multiple feature extraction paths for extracting a joint feature tensor representing the pulse wave waveform, target heart rate, and respiration based on multiple signal segments. The second network branch receives the vascular feature parameters. The cross-attention mechanism layer uses the vascular feature parameters as a conditional vector and fuses them with the joint feature tensor to obtain fused features, which are then input into the fully connected output layer. The fully connected output layer outputs the time-series prediction result based on the fused features. The human body monitoring signal is obtained by mixing the transmitted signal of the millimeter-wave device with the reflected signal corresponding to the transmitted signal to obtain an intermediate frequency signal, and then processing it through a fast Fourier transform. The step of calculating the periodic intensity of the signal at different monitoring distance units based on the human body monitoring signal and determining the distance unit with the largest periodic intensity as the target monitoring location includes: determining distance units based on each peak value in the human body monitoring signal and mapping the intermediate frequency signal to each distance unit; calculating the autocorrelation function value corresponding to each distance unit based on the signal corresponding to each distance unit and a preset autocorrelation function; the magnitude of the autocorrelation function value is positively correlated with the periodic intensity; searching for the distance unit corresponding to the largest autocorrelation function value from the distance units according to a preset heart rate range, and using it as the target distance unit; and determining the target monitoring location based on the target distance unit.

2. The method according to claim 1, characterized in that, The first network branch includes a first path, a second path, a third path, a residual block with shared weights connected to the first path, the second path, and the third path respectively, an intra-path attention layer, an inter-path attention layer, and a feature splicing layer; The first path is used to extract the waveform features of the pulse wave based on the signal segment; the second path is used to extract the heart rate features of the target human body based on the signal segment; and the third path is used to extract the respiratory features of the target human body based on the signal segment. The input of the attention layer within the pathway is connected to the output of the residual block with shared weights, and is used to weight the waveform features, the heart rate features, and the respiratory features. The input end of the inter-path attention layer is connected to the output end of the intra-path attention layer, and is used to fuse the weighted waveform features, heart rate features, and respiratory features; The input of the feature splicing layer is connected to the output of the inter-path attention layer, and is used to integrate the fused features into the joint feature tensor.

3. The method according to claim 2, characterized in that, The method involves dividing the human body monitoring signal from the target monitoring location into multiple signal segments in parallel based on predetermined different time scales, including: According to a first preset duration, the human body monitoring signal at the target monitoring location is divided into several first signal segments and input to the first channel; According to the second preset duration, the human body monitoring signal at the target monitoring location is divided into several second signal segments and input to the second channel; According to the third preset duration, the human body monitoring signal at the target monitoring location is divided into several third signal segments and input to the third channel; wherein, the first preset duration is shorter than the second preset duration, and the second preset duration is shorter than the third preset duration.

4. The method according to claim 3, characterized in that, The blood pressure prediction model was trained through the following steps: Acquire training data, which includes several batches of sample signal segments and corresponding sample time-series prediction results; each batch of sample signal segments includes a first sample signal segment, a second sample signal segment, and a third sample signal segment; The training data is input into the initial blood pressure prediction model in batches to obtain the training results; the model structure of the initial blood pressure prediction model is the same as that of the blood pressure prediction model. The training results and the sample time-series prediction results are input into a preset loss function to obtain the loss value; The initial blood pressure prediction model is iteratively trained using the loss value to obtain the blood pressure prediction model.

5. The method according to claim 1, characterized in that, The vascular feature extraction network was trained through the following steps: Acquire training data, which includes sample pulse wave signals and corresponding monitoring signals; the monitoring signals include sample cuff pressure signals synchronously acquired by the pressure-adjustable blood pressure monitor during the acquisition of the sample pulse wave signals. The sample pulse wave signal is input into the initial feature extraction network to obtain the training result; The training results and the supervision signal are input into a preset loss function to obtain the loss value; The feature extraction network is iteratively trained using the loss value until the model converges, thus obtaining the blood vessel feature extraction network.

6. The method according to claim 1, characterized in that, The step of processing the phase change signal to extract the pulse wave signal characterizing arterial pulsation includes: The phase-change signal is bandpass filtered to remove noise; The pulse wave signal is obtained by performing wavelet transform on the noise-removed reciprocal signal.

7. A non-contact continuous blood pressure monitoring device based on single calibration, comprising a processor, a memory, and a computer program / instructions stored in the memory, characterized in that, The processor is used to execute the computer program / instructions, and when the computer program / instructions are executed, the device implements the steps of the method as described in any one of claims 1 to 6; the device is communicatively connected to a millimeter-wave device to receive human body monitoring signals of the target human body collected in real time by the millimeter-wave device; the device is communicatively connected to a pressure sphygmomanometer to receive cuff pressure signals collected in real time by the pressure sphygmomanometer.

8. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1 to 6.

Images