Method and system for determining blogging blood pressure in real time

Abstract

The embodiment of the invention provides a method and system for determining the blogging blood pressure in real time. The method for determining the blogging blood pressure in real time comprises the steps of periodically obtaining to-be-processed data; performing feature extraction on the to-be-processed data to obtain a time domain feature flow of the to-be-processed data; the time domain feature flow of the to-be-processed data and the static physiological parameters corresponding to the to-be-processed data serve as input and are input into a pre-trained Blog-by-Blog blood pressure generation model, Blog-by-Blog blood pressure corresponding to the to-be-processed data is generated, the pre-trained Blog-by-Blog blood pressure generation model is a full-connection neural network, and Blog-by-Blog blood pressure corresponding to the to-be-processed data is generated. The pre-trained blogging-by-blogging blood pressure generation model is composed of three full-connection layers.

Description

Technical Field

[0001] The embodiments of the present application belong to the technical field of blood pressure measurement, and in particular, relate to a method and system for determining beat-to-beat blood pressure in real time. Background Art

[0002] Cardiovascular diseases (CVDs) are the number one "killer" worldwide, and hypertension is a regulated early warning factor for cardiovascular diseases. Hypertension is a common fatal disease. If not discovered and treated in time, it may induce heart disease, stroke, myocardial infarction, heart failure, myocardial ischemia and other diseases. Therefore, early detection of hypertension is very important for reducing the risk of cardiovascular disease. Because the blood pressure of the human body at different times will change according to changes in the external environment to maintain homeostasis. Therefore, traditional clinic blood pressure only measures the blood pressure value at a certain moment, and it is slightly inappropriate to use it as an assessment of the patient's blood pressure throughout the day. Therefore, long-term, continuous, and accurate dynamic blood pressure monitoring has outstanding advantages in judging the patient's blood pressure.

[0003] At present, the commonly used non-invasive blood pressure measurement methods include auscultation, oscillometric method, tension measurement method, volume clamp method, pulse wave velocity method (PWV) and pulse wave velocity method (PTT). Among them, the PTT method is the best method to measure beat-to-beat blood pressure, but the current PTT algorithms are all based on retrospective calculations. Therefore, there is no need to consider resource consumption and time costs in the application. However, the current PTT algorithm is applied to the scenario of real-time blood pressure monitoring, which has great limitations and is not suitable for real-time blood pressure monitoring scenarios.

[0004] Based on this, the embodiments of this specification provide a method and system for determining beat-to-beat blood pressure in real time. Summary of the invention

[0005] The embodiments of this specification provide a method and system for determining beat-to-beat blood pressure in real time to solve some or all of the problems: At present, PTT algorithms are all based on retrospective calculations. Therefore, there is no need to consider resource consumption and time costs in applications. However, at present, PTT algorithms are applied to scenarios of real-time blood pressure monitoring, which has great limitations and is not suitable for scenarios of real-time blood pressure monitoring.

[0006] To solve the above technical problems, the embodiments of this specification are implemented as follows:

[0007] The present specification provides a method for determining beat-to-beat blood pressure in real time. The method for determining beat-to-beat blood pressure in real time includes:

[0008] Periodically obtain data to be processed;

[0009] Extracting features from the data to be processed to obtain a time domain feature stream of the data to be processed;

[0010] The time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed are taken as input and input into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed. The pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers.

[0011] The embodiment of the present specification also provides a system for determining beat-to-beat blood pressure in real time, the system for determining beat-to-beat blood pressure in real time comprising:

[0012] Acquisition module, periodically acquires data to be processed;

[0013] An extraction module performs feature extraction on the data to be processed to obtain a time domain feature stream of the data to be processed;

[0014] A processing module takes the time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed as input, and inputs them into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed. The pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers.

[0015] At least one of the above-mentioned technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects: periodically acquiring data to be processed; performing feature extraction on the data to be processed to obtain the time domain feature stream of the data to be processed; using the time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed as input, and inputting them into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed, wherein the pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers, which can realize low-cost real-time monitoring of beat-to-beat blood pressure without adding additional equipment, and realize fast and accurate blood pressure monitoring, has strong universality, and can be applied to a variety of blood pressure measurement scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. Some specific embodiments of the present application will be described in detail in an illustrative and non-restrictive manner with reference to the drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings:

[0017] Figure 1A schematic diagram of the system architecture of a method for determining beat-to-beat blood pressure in real time provided in an embodiment of this specification;

[0018] Figure 2 A flow chart of a method for real-time determination of beat-to-beat blood pressure provided in an embodiment of this specification;

[0019] Figure 3 A schematic diagram of a system for determining beat-to-beat blood pressure in real time is provided for the present illustrative embodiment. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0021] Among the commonly used non-invasive blood pressure measurement methods at this stage, auscultation, oscillometric, tension measurement, volume clamping, pulse wave velocity (PWV) and pulse wave velocity (PTT) each have their own advantages and disadvantages, as shown in Figure 1.

[0022] Table 1: Comparison of advantages and disadvantages of non-invasive blood pressure measurement methods

[0023]

[0024]

[0025] Although the PTT method is the best method for measuring beat-to-beat blood pressure, it still has many shortcomings.

[0026] The specific algorithm of the PTT method will be described in detail below.

[0027] In the PTT method, Chen's method is based on the MK formula, which calculates SBP from the changes in PTT by combining the high-frequency components of PTT and the low-frequency components of BP.

[0028] In the PTT method, the Poon method is based on the MK formula and can calculate SBP and DBP relatively accurately at the same time.

[0029] 4The PTT method also includes linear regression and nonlinear regression.

[0030] The PTT method is based on retrospective calculations and has great limitations when applied to real-time blood pressure monitoring scenarios. It is not suitable for real-time blood pressure monitoring scenarios.

[0031] Based on this, an embodiment of this specification provides a method for determining beat-to-beat blood pressure in real time.

[0032] Figure 1 A schematic diagram of the system architecture of a method for real-time beat-to-beat blood pressure determination provided in an embodiment of this specification. Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0033] The terminal devices 101, 102, 103 interact with the server 105 via the network 104 to receive or send messages, etc. Various client applications may be installed on the terminal devices 101, 102, 103, such as dedicated programs for real-time determination of beat-to-beat blood pressure, etc.

[0034] The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various dedicated or general electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc. When the terminal devices 101, 102, 103 are software, they may be installed in the electronic devices listed above. They may be implemented as multiple software or software modules (e.g., multiple software or software modules for providing distributed services), or they may be implemented as a single software or software module.

[0035] The server 105 may be a server that provides various services, such as a backend server that provides services for client applications installed on the terminal devices 101, 102, 103. For example, the server may determine the beat-to-beat blood pressure in real time so as to display the result of the real-time determination of the beat-to-beat blood pressure on the terminal device server 101, 102, 103, or the server may determine the beat-to-beat blood pressure in real time so as to display the result of the real-time determination of the beat-to-beat blood pressure on the terminal devices 101, 102, 103.

[0036] The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server 105 is software, it may be implemented as multiple software or software modules (e.g., multiple software or software modules for providing distributed services), or as a single software or software module.

[0037] Figure 2 The flowchart of a method for determining beat-to-beat blood pressure in real time provided by the embodiment of this specification is shown in FIG. From the program perspective, the execution subject of the process can be a program installed on an application server or an application terminal. It can be understood that the method can be executed by any device, equipment, platform, or device cluster with computing and processing capabilities. Figure 2 As shown, the method for determining beat-to-beat blood pressure in real time includes:

[0038] Step S201: periodically obtain data to be processed.

[0039] In the embodiment of the present specification, the data to be processed includes: data generated based on ECG signals and data generated based on PPG signals. Specifically, the data to be processed includes: electrocardiogram data and blood volume change data.

[0040] ECG signal refers to electrocardiography (ECG or EKG), which is a method of recording the electrophysiological activity of the heart in units of time through the chest cavity. The potential transmission of the heart can be detected by using electrodes attached to the surface of human skin. What the electrocardiogram records is not the potential changes of a single ventricular or atrial cell, but the potential changes of the heart as a whole. The results of the electrocardiogram are usually displayed in wave types, which basically include P wave, QRS wave group, and T wave. The P wave represents atrial contraction, the QRS wave group represents ventricular contraction, and the T wave represents ventricular relaxation. The measurement or evaluation of heart rate is represented by the interval time between R waves. The larger the RR interval, the lower the heart rate, and the smaller the RR interval, the higher the heart rate.

[0041] PPG signal refers to photoplethysmography (PPG for short), which is a non-invasive detection method for detecting blood volume changes in living tissues by photoelectric means. When a beam of light of a certain wavelength is irradiated on the surface of the fingertip skin, the contraction and expansion of blood vessels will affect the transmission of light (for example, in transmission PPG), the light passing through the fingertips or the reflection of light (for example, in reflection PPG, the light from the surface near the wrist). When the light passes through the skin tissue and then reflects to the photosensitive sensor, the light will be attenuated to a certain extent. The absorption of light by muscles, bones, veins and other connecting tissues is basically unchanged (provided that there is no significant movement of the measurement site), but arteries are different. Since there is blood pulsation in the arteries, the absorption of light will naturally change. When we convert light into electrical signals, it is precisely because the absorption of light by arteries changes while the absorption of light by other tissues remains basically unchanged that the obtained signal can be divided into direct current (DC) and alternating current (AC) signals. Extracting the AC signal can reflect the characteristics of blood flow.

[0042] In the embodiment of the present specification, the electrocardiogram data can be obtained by using a three-lead electrocardiogram with a sampling frequency of 1000 Hz; the blood volume change data can be obtained by using a two-channel blood oxygen volume wave with a sampling frequency of 1000 Hz, and the two channels are respectively a red light spectrum channel and an infrared spectrum channel.

[0043] In the embodiment of this specification, the periodic acquisition of the data to be processed specifically includes:

[0044] The data to be processed is acquired based on a preset multiple of a generation frequency of the data to be processed.

[0045] In one embodiment of the present specification, the generation frequency of the data to be processed is 5 / s, and the generation period of the data to be processed is 200ms, that is, the periodic time is 200ms. In the present application, the preset multiple is 5.

[0046] Step S203: extracting features from the data to be processed to obtain a time domain feature stream of the data to be processed.

[0047] In the embodiment of this specification, the feature extraction of the data to be processed to obtain the time domain feature stream of the data to be processed specifically includes:

[0048] Performing window segmentation on the data to be processed, and performing bandpass filtering within the window to obtain a window segmentation result;

[0049] Based on the signal type of the data to be processed, performing feature extraction on the window segmentation result to obtain extracted features;

[0050] Structural maintenance is performed based on the extracted features to obtain a time domain feature stream of the data to be processed.

[0051] The band-pass filter can be regarded as the result of the synergistic effect of high-pass and low-pass filters, and the cut-off frequencies of the high-pass and low-pass filters can be used as the lower and upper limits of the passband. Its main parameters are the center frequency and bandwidth, and the difference between the upper and lower limits is the bandwidth of the filter. In the embodiment of the present specification, it is possible to obtain a signal of a specific frequency of interest. In the embodiment of the present specification, based on band-pass filtering, data containing only ECG signals and PPG signals can be obtained, thereby ensuring the accuracy of the data to be processed and reducing the amount of calculation for processing the data to be processed.

[0052] In the embodiments of the present specification, window segmentation is performed on the data to be processed, and bandpass filtering is performed within the window. Before obtaining the window segmentation result, data cleaning is also included. Specifically, the validity of the data to be processed is judged based on the value domain and frequency domain of the data to be processed; based on the validity judgment result of the data to be processed, the valid data in the data to be processed is marked for structured storage for subsequent window segmentation.

[0053] In the embodiment of the present specification, the validity of the data to be processed is judged based on the value domain and frequency domain of the data to be processed, and the WIP validity rule is adopted. Specifically, the WIP validity rule is based on the normal heart rate range. In the embodiment of the present specification, the range of the WIP validity rule is 60-150 beats / minute. The WIP validity rule is (work in progress), and the validity judgment is performed based on the data results of real-time monitoring.

[0054] In the embodiment of this specification, the window segmentation of the data to be processed and the bandpass filtering in the window to obtain the window segmentation result specifically include:

[0055] Based on the signal type of the data to be processed, the data to be processed is segmented into windows according to preset parameters, and bandpass filtering is performed within the window to obtain the window segmentation result;

[0056] If the type of the data signal to be processed is an ECG signal, the preset parameters are: window size = 4000, peak window size = 400, window step length = 500, window cutoff length = 1000, activation count lower limit = 1;

[0057] If the signal type of the data to be processed is a PPG signal, the preset parameters are: window size = 6000, peak window size = 300, window step length = 500, window truncation length = 2000, activation count lower limit = 1.

[0058] In the embodiment of the present specification, the extracted feature has a timestamp, and the feature extraction is performed on the window segmentation result based on the signal type of the data to be processed to obtain the extracted feature, which specifically includes:

[0059] If the signal type of the data to be processed is an ECG signal, extracting the r wave peak time point from the window segmentation result to perform feature extraction to obtain the extracted feature;

[0060] If the signal type of the data to be processed is a PPG signal, the pulse wave arrival time point is extracted from the window segmentation result to perform feature extraction to obtain the extracted feature.

[0061] In the embodiment of the present specification, after the extracted features are obtained, the validity of the extracted features is further judged. Specifically, the validity judgment of the extracted features can be based on the WIP validity rule.

[0062] In the embodiment of this specification, the structured maintenance based on the extracted features to obtain the time domain feature stream of the data to be processed specifically includes:

[0063] Based on the data structure of the red-black tree, the extracted features are structured and maintained to obtain the time domain features of the data to be processed, where the time domain features of the data to be processed are composed of the r peak of the ECG signal with a timestamp and the arrival time point of the pulse wave of the PPG signal.

[0064] A red-black tree is a self-balancing binary search tree. The red-black tree makes the tree close to balance by marking each node with a color to reduce the rotation of the tree when inserting nodes; a new storage bit is added to each node to represent the node color, which can be red or black; by restricting the coloring of each node on any path from the root to the leaf, the red-black tree ensures that no path is twice as long as other paths, so it is close to balance.

[0065] Step S205: Taking the time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed as input, input them into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed. The pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers.

[0066] In an embodiment of the present specification, the pre-trained beat-to-beat blood pressure generation model includes a first fully connected layer, a second fully connected layer and a third fully connected layer, the number of nodes in the first fully connected layer is 64, and the activation function of the first fully connected layer is a Relu function, the number of nodes in the second fully connected layer is 64, and the activation function of the second fully connected layer is a Relu function, the number of nodes in the third fully connected layer is 32, and the activation function of the third fully connected layer is a Relu function.

[0067] Relu function (Rectified Linear Unit) is a linear rectifier function, also known as the rectified linear unit Relu, which usually refers to nonlinear functions represented by ramp functions and their variants. Since the Relu function is a non-saturated activation function, it is not easy for the gradient to disappear, so it can effectively alleviate the overfitting problem, and will not cause gradient disappearance or gradient explosion, and the calculation is simple.

[0068] In the embodiment of the present specification, during the training process of the pre-trained beat-to-beat blood pressure generation model, the step size is 500, the batch size is 4, the optimizer is Adam, the patience value of the early stopping strategy is 50, and the loss function is MSE.

[0069] MSE (mean-square error) is a measure of the difference between the estimator and the estimated quantity. During the training process, we hope that the MSE is as small as possible.

[0070] In the embodiment of the present specification, the static physiological parameters corresponding to the data to be processed include the age, gender, weight and height of the subject corresponding to the data to be processed.

[0071] In the embodiment of the present specification, in order to obtain a pre-trained beat-to-beat blood pressure generation model with higher accuracy, the full data of the tilt test is used for calibration. Specifically, the full data of the tilt test includes: static physiological parameters, dynamic electrocardiogram data and dynamic blood volume change data.

[0072] The method for determining beat-to-beat blood pressure in real time provided in the embodiments of this specification can be used in a tilt test when applied specifically, and can be applied to other scenarios that require non-invasive, real-time and accurate acquisition of beat-to-beat blood pressure.

[0073] The method for real-time determination of beat-to-beat blood pressure provided in the embodiments of this specification is adopted, by periodically acquiring data to be processed; performing feature extraction on the data to be processed to obtain a time domain feature stream of the data to be processed; using the time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed as input, inputting them into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed, wherein the pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers, which can realize low-cost real-time monitoring of beat-to-beat blood pressure without adding additional equipment, and realize fast and accurate blood pressure monitoring, has strong universality, and can be applied to a variety of blood pressure measurement scenarios.

[0074] The aforementioned embodiments of this specification provide a method for determining beat-to-beat blood pressure in real time. Based on the same idea, the embodiments of this specification also provide a system for determining beat-to-beat blood pressure in real time. Figure 3 A schematic diagram of a system for determining beat-to-beat blood pressure in real time is provided for this illustrative embodiment. Figure 3 As shown, the system for determining beat-to-beat blood pressure in real time includes:

[0075] An acquisition module 301 periodically acquires data to be processed;

[0076] The extraction module 303 performs feature extraction on the data to be processed to obtain a time domain feature stream of the data to be processed;

[0077] The processing module 305 takes the time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed as input, and inputs them into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed. The pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers.

[0078] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, electronic device, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0080] The apparatus, electronic device, non-volatile computer storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, electronic device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, electronic device and non-volatile computer storage medium will not be repeated here.

[0081] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0082] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0083] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0084] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0085] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0086] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0089] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0090] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0091] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0092] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0093] The specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0094] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0095] The above is only an embodiment of this specification and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for determining beat-to-beat blood pressure in real time, characterized in that: The method for determining beat-to-beat blood pressure in real time comprises: Periodically obtain data to be processed; Extracting features from the data to be processed to obtain a time domain feature stream of the data to be processed; The time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed are taken as input and input into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed. The pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers.

2. The method for real-time determination of beat-to-beat blood pressure according to claim 1, characterized in that: The pre-trained beat-to-beat blood pressure generation model includes a first fully connected layer, a second fully connected layer and a third fully connected layer. The number of nodes in the first fully connected layer is 64, and the activation function of the first fully connected layer is a Relu function. The number of nodes in the second fully connected layer is 64, and the activation function of the second fully connected layer is a Relu function. The number of nodes in the third fully connected layer is 32, and the activation function of the third fully connected layer is a Relu function.

3. The method for real-time determination of beat-to-beat blood pressure according to claim 1, characterized in that: During the training process of the pre-trained beat-to-beat blood pressure generation model, the step size is 500, the batch size is 4, the optimizer is Adam, the patience value of the early stopping strategy is 50, and the loss function is MSE.

4. The method for real-time determination of beat-to-beat blood pressure according to claim 1, characterized in that: The periodic acquisition of the data to be processed specifically includes: The data to be processed is acquired based on a preset multiple of a generation frequency of the data to be processed.

5. The method for real-time determination of beat-to-beat blood pressure according to claim 1, characterized in that: The static physiological parameters corresponding to the data to be processed include the age, gender, weight and height of the subject corresponding to the data to be processed.

6. The method for real-time determination of beat-to-beat blood pressure according to claim 1, characterized in that: The extracting features of the data to be processed to obtain the time domain feature stream of the data to be processed specifically includes: Performing window segmentation on the data to be processed, and performing bandpass filtering within the window to obtain a window segmentation result; Based on the signal type of the data to be processed, performing feature extraction on the window segmentation result to obtain extracted features; Structural maintenance is performed based on the extracted features to obtain a time domain feature stream of the data to be processed.

7. The method for real-time determination of beat-to-beat blood pressure according to claim 6, characterized in that: The step of performing window segmentation on the data to be processed and performing bandpass filtering in the window to obtain the window segmentation result specifically includes: Based on the signal type of the data to be processed, the data to be processed is segmented into windows according to preset parameters, and bandpass filtering is performed within the window to obtain the window segmentation result; If the type of the data signal to be processed is an ECG signal, the preset parameters are: window size = 4000, peak window size = 400, window step length = 500, window cutoff length = 1000, activation count lower limit = 1; If the signal type of the data to be processed is a PPG signal, the preset parameters are: window size = 6000, peak window size = 300, window step length = 500, window truncation length = 2000, activation count lower limit = 1.

8. The method for real-time determination of beat-to-beat blood pressure according to claim 1, characterized in that: The extracted feature has a timestamp, and based on the signal type of the data to be processed, the feature extraction is performed on the window segmentation result to obtain the extracted feature, which specifically includes: If the signal type of the data to be processed is an ECG signal, extracting the r wave peak time point from the window segmentation result to perform feature extraction to obtain the extracted feature; If the signal type of the data to be processed is a PPG signal, the pulse wave arrival time point is extracted from the window segmentation result to perform feature extraction to obtain the extracted feature.

9. The method for real-time determination of beat-to-beat blood pressure according to claim 1, characterized in that: The performing structured maintenance based on the extracted features to obtain the time domain feature stream of the data to be processed specifically includes: Based on the data structure of the red-black tree, the extracted features are structured and maintained to obtain the time domain features of the data to be processed, where the time domain features of the data to be processed are composed of the r peak of the ECG signal with a timestamp and the arrival time point of the pulse wave of the PPG signal.

10. A system for determining beat-to-beat blood pressure in real time, characterized in that: The system for determining beat-to-beat blood pressure in real time comprises: Acquisition module, periodically acquires data to be processed; An extraction module performs feature extraction on the data to be processed to obtain a time domain feature stream of the data to be processed; A processing module takes the time domain feature stream of the data to be processed and the static physiological parameters corresponding to the data to be processed as input, and inputs them into a pre-trained beat-to-beat blood pressure generation model to generate the beat-to-beat blood pressure corresponding to the data to be processed. The pre-trained beat-to-beat blood pressure generation model is a fully connected neural network, and the pre-trained beat-to-beat blood pressure generation model consists of 3 fully connected layers.

Images