A method and apparatus for calculating blood pressure values ​​using characteristic values ​​of photoplethysmography.

Abstract

The present disclosure relates to a method and an apparatus for calculating blood pressure values by using characteristic values of photoplethysmogram. The method according to an embodiment of the present disclosure receives photoplethysmogram data including a photoplethysmogram waveform, normalizes the photoplethysmogram waveform included in the photoplethysmogram data, uses the normalized photoplethysmogram waveform to detect characteristic values for calculating blood pressure values, and can calculate blood pressure values based on the photoplethysmogram data and the detected characteristic values.

Description

Technical Field

[0007] , , ,

[0001] The present invention relates to a method and an apparatus for calculating blood pressure values by using characteristic values of photoplethysmograms.

Background Art

[0002] Each time the heart contracts, blood is supplied from the heart to the whole body through the aorta. At this time, pressure fluctuations occur in the aorta. These pressure fluctuations are transmitted to the peripheral arterioles of the hands and feet, and the photoplethysmogram is a waveform representation of the volume fluctuations of the peripheral blood vessels due to the pressure fluctuations of the arteries.

[0003] When the volume of the blood vessel fluctuates due to such pulsation and light having a predetermined wavelength such as infrared light or visible light is applied to the blood vessel, the amount of light absorbed changes as the volume of the blood vessel increases or decreases. For example, when 100% of the light is emitted, the amount of light reflected without being absorbed changes due to pulsation.

[0004] After light is emitted through a light emitting unit by utilizing this principle, the speed or amount of the reflected infrared light is input to a light receiving unit, and the photoplethysmogram can be measured by utilizing the characteristic that the current and voltage appear differently depending on the speed or amount of the input infrared light.

[0005] However, the photoplethysmogram may vary depending on the physical condition of the subject, the environmental conditions at the time of measurement, etc. When measuring blood pressure by using such a photoplethysmogram, there is a problem that inaccurate results may be derived.

[0006] The above-mentioned background art is technical information that the inventor possessed in order to derive the present invention or acquired in the process of deriving the present invention, and it cannot necessarily be regarded as publicly known technology that was publicly disclosed to the general public before the filing of the present invention.

Summary of the Invention

[0008] The problems that this invention aims to solve are not limited to those mentioned above. Other problems and advantages of this invention that are not mentioned can be understood from the following description and may be more clearly understood from embodiments of this invention. It should also be understood that the problems and advantages that this invention aims to solve can be realized by the means and combinations of the claims. [Means for solving the problem]

[0009] As a technical means to achieve the aforementioned technical challenges, the first aspect of this disclosure provides a method for calculating blood pressure values ​​using characteristic values ​​of photoplethysmography, comprising the steps of: receiving photoplethysmography data including a photoplethysmography waveform; standardizing the photoplethysmography waveform included in the photoplethysmography data; detecting characteristic values ​​for calculating blood pressure values ​​using the standardized photoplethysmography waveform; and calculating blood pressure values ​​based on the photoplethysmography data and the detected characteristic values.

[0010] A second aspect of this disclosure is the provision of a computer device that calculates blood pressure values ​​using photoplethysmography data, comprising at least one memory and at least one processor, wherein the at least one processor receives photoplethysmography data including a photoplethysmography waveform, standardizes the photoplethysmography waveform included in the photoplethysmography data, detects feature values ​​for calculating blood pressure values ​​using the standardized photoplethysmography waveform, and calculates blood pressure values ​​based on the photoplethysmography data and the detected feature values.

[0011] A third aspect of this disclosure can provide a computer-readable recording medium that stores a program for causing a computer to perform the method according to the first aspect.

[0012] In addition, other methods, other systems for embodying the present invention, and computer-readable recording media storing computer programs for performing the said methods can also be provided.

[0013] Other aspects, features, and advantages not mentioned above may become clear from the following drawings, claims, and detailed description of the invention. [Effects of the Invention]

[0014] According to the aforementioned problem-solving means of this disclosure, the present disclosure receives photoplethysmography data including a photoplethysmography waveform, standardizes the photoplethysmography waveform, detects feature values ​​using the standardized photoplethysmography waveform, and calculates blood pressure values ​​based on the photoplethysmography data and feature values, thereby enabling the calculation of blood pressure values ​​from the photoplethysmography waveform with greater accuracy.

[0015] By correcting blood pressure values ​​based on personal and environmental information related to photoplethysmography data and blood pressure readings, it is possible to calculate blood pressure values ​​from photoplethysmography waveforms with greater accuracy.

[0016] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description. [Brief explanation of the drawing]

[0017] [Figure 1] This is a diagram illustrating an example of a system for calculating blood pressure values ​​using photoplethysmography data according to one embodiment. [Figure 2] This is a configuration diagram showing an example of a user terminal according to one embodiment. [Figure 3]This flowchart illustrates an example of a method for calculating blood pressure values ​​using characteristic values ​​of a photoplethysmography according to one embodiment. [Figure 4] This is a diagram illustrating an example of a processor according to one embodiment that detects feature values ​​using a standardized photoplethysmography waveform. [Figure 5] This diagram illustrates an example in which a processor according to one embodiment acquires blood pressure values ​​using a first neural network model. [Figure 6] This is a diagram illustrating an example in which a processor according to one embodiment corrects blood pressure values ​​using a correction calculation model. [Modes for carrying out the invention]

[0018] A method according to one embodiment of the present disclosure can receive photoplethysmography data including a photoplethysmography waveform, standardize the photoplethysmography waveform included in the photoplethysmography data, detect feature values ​​for calculating blood pressure values ​​using the standardized photoplethysmography waveform, and calculate blood pressure values ​​based on the photoplethysmography data and the detected feature values.

[0019] Embodiment Various embodiments of the present disclosure are described below in reference to the accompanying drawings. Various modifications and configurations are possible, and specific embodiments are illustrated in the drawings and described in detail. However, this should be understood not as an attempt to limit the various embodiments of the present disclosure to specific embodiments, but rather as including all modifications and / or equivalents or substitutes that fall within the concept and technical scope of the various embodiments of the present disclosure. Similar reference numerals are used for similar components in the drawings.

[0020] Expressions such as "comprising" or "can comprise" used in various embodiments of the present disclosure indicate the existence of the disclosed function, operation, component, etc., and do not limit one or more additional functions, operations, components, etc. Also, in various embodiments of the present disclosure, terms such as "comprising" or "having" are intended to specify the existence of the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and it should be understood that they do not preclude in advance the existence or possibility of addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0021] In various embodiments of the present disclosure, expressions such as "or" include any and all combinations of the words listed together. For example, "A or B" may include A, may include B, or may include both A and B.

[0022] Expressions such as "first", "second", "the first", or "the second" used in various embodiments of the present disclosure can modify various components of the various embodiments, but do not limit the components. For example, the above expressions do not limit the order and / or importance of the components. The above expressions can be used to distinguish one component from another. For example, the first user device and the second user device are both user devices and indicate different user devices from each other. For example, without departing from the scope of the rights of various embodiments of the present disclosure, the first component may be named the second component, and similarly, the second component may also be named the first component.

[0023] When it is mentioned that one component is “connected” or “linked” to another component, it should be understood that the first component is directly connected to the other component, or may be connected, but there may be a new other component between the first component and the other component. On the other hand, when it is mentioned that one component is “directly connected” or “directly linked” to another component, it should be understood that there is no new other component between the first component and the other component.

[0024] In embodiments of this disclosure, terms such as “module,” “unit,” and “part” refer to components that perform at least one function or operation, and such components may be embodied in hardware or software, or in a combination of hardware and software. Furthermore, multiple “modules,” “units,” and “parts” may be integrated into at least one module or chip and embodied in at least one processor, unless each needs to be embodied in separate, specific hardware.

[0025] The terms used in the various embodiments of this disclosure are used solely to describe specific embodiments and are not intended to limit the various embodiments of this disclosure. Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0026] Some embodiments of this disclosure are also represented by functional block configurations and various processing stages. Some or all of such functional blocks may also be embodied by various hardware and / or software configurations that perform a particular function. For example, a functional block of this disclosure may be embodied by one or more microprocessors or by a circuit configuration for a given function. Alternatively, for example, a functional block of this disclosure may be embodied by various programming or scripting languages. A functional block may also be embodied by an algorithm executed by one or more processors. Furthermore, this disclosure may employ prior art for electronic environment setup, signal processing and / or data processing, etc. Terms such as “mechanism,” “element,” “means,” and “configuration” are used broadly and are not limited to mechanical and physical configurations.

[0027] Furthermore, the connecting lines or members between components shown in the drawings are merely illustrative examples of functional and / or physical or circuit connections. In actual devices, connections between components may be indicated by a variety of interchangeable or additional functional, physical, or circuit connections.

[0028] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as they would be generally understood by a person skilled in the art to which the various embodiments of this disclosure belong.

[0029] Terms as defined in commonly used dictionaries should be interpreted to have meanings consistent with their meanings in the context of the relevant technology, and not to be interpreted in an ideal or overly formal sense unless expressly defined in the various embodiments of this disclosure.

[0030] The following describes various embodiments of the present invention in detail with reference to the attached drawings.

[0031] Figure 1 is a diagram illustrating an example of a system that calculates blood pressure values ​​using photoplethysmography data according to one embodiment.

[0032] Referring to Figure 1, System 1 includes a user terminal 10 and a server 20. For example, the user terminal 10 and the server 20 are connected by a wired or wireless connection and can send and receive data (e.g., photoplethysmography data including photoplethysmography waveforms) between them.

[0033] For the sake of explanation, Figure 1 shows that System 1 includes a user terminal 10 and a server 20, but is not limited to this. For example, System 1 may include other external devices (not shown), and the operations of the user terminal 10 and server 20 described below may also be embodied by a single device (e.g., user terminal 10 or server 20).

[0034] The user terminal 10 may be a computing device that includes a display device and a device for receiving user input (e.g., a keyboard, mouse, etc.), as well as memory and a processor. For example, the user terminal 10 may be a notebook PC, desktop PC, laptop, tablet computer, smartphone, etc., but is not limited to these.

[0035] Server 20 may be a device that communicates with external devices (not shown), including the user terminal 10. For example, Server 20 may be a device that stores various data, including photoplethysmography data, including photoplethysmography waveforms, and may also be a device equipped with autonomous computing capabilities. For example, Server 20 may be a cloud server, but is not limited to this.

[0036] The user terminal 10 calculates blood pressure values ​​using photoplethysmography data. Then, the user terminal 10 corrects the calculated blood pressure values ​​based on personal and environmental information related to those values.

[0037] System 1 according to one embodiment calculates blood pressure values ​​using photoplethysmography (PPS) data. Specifically, the user terminal 10 receives PPS data including the PPS waveform, standardizes the PPS waveform included in the PPS data, detects feature values ​​for calculating blood pressure values ​​using the standardized PPS waveform, and calculates blood pressure values ​​based on the PPS data and the detected feature values. The user 30 can then confirm the more accurately calculated blood pressure values ​​using the PPS data and feature values.

[0038] The following describes an example in which the user terminal 10 calculates blood pressure values ​​using photoplethysmography data, with reference to Figures 2 to 6. On the other hand, as mentioned above with reference to Figure 1, the operations described later with reference to Figures 2 to 6 may also be performed on the server 20.

[0039] Figure 2 is a configuration diagram showing an example of a user terminal according to one embodiment.

[0040] Referring to Figure 2, the user terminal 100 includes a processor 110 and memory 120. For convenience of explanation, only the components relating to the present invention are shown in Figure 2. Other general components may be further included in the user terminal 100 in addition to those shown in Figure 2. For example, the user terminal 100 may include an input / output interface (not shown) and / or a communication module (not shown). It will also be obvious to those ordinary skill in the art relating to the present invention that the processor 110 and memory 120 shown in Figure 2 may be embodied in separate devices.

[0041] The processor 110 can process computer program instructions by performing basic arithmetic, logic, and input / output operations. Instructions can be provided from memory 120 or an external device (e.g., server 20). The processor 110 can also generally control the operation of other components included in the user terminal 100.

[0042] Specifically, the processor 110 calculates blood pressure values ​​using photoplethysmography (PPS) data. Specifically, the processor 110 receives PPS data, including the PPS waveform. The processor 110 then standardizes the PPS waveform contained in the PPS data. The processor 110 then uses the standardized PPS waveform to detect feature values ​​for calculating blood pressure values. Finally, the processor 110 calculates blood pressure values ​​based on the PPS data and the detected feature values.

[0043] A specific example of how the processor 110 operates according to one embodiment will be described with reference to Figures 2 to 6.

[0044] The processor 110 may be embodied as an array of numerous logic gates, or as a combination of a general-purpose microprocessor and memory storing a program that can be executed by this microprocessor. For example, the processor 110 may include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, and the like. In some environments, the processor 110 may include an application-specific semiconductor (ASIC), a programmable logic device (PLD), a field-programmable gate array (FPGA), and the like. For example, the processor 110 may refer to a combination of processing devices such as a combination of a digital signal processor (DSP) and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors coupled with a digital signal processor (DSP) core, or any other combination of configurations.

[0045] Memory 120 can include any non-temporary computer-readable recording medium. For example, memory 120 may include a permanent mass storage device such as RAM (random access memory), ROM (read-only memory), a disk drive, an SSD, or flash memory. In other examples, a permanent mass storage device such as ROM, an SSD, flash memory, or a disk drive may be a separate persistent storage device distinct from memory. Memory 210 can also store an operating system (OS) and at least one program code (for example, code for the processor 110 to perform the operations described later with reference to Figures 2 to 6).

[0046] Such software components can be loaded from a computer-readable recording medium separate from memory 120. Such a separate computer-readable recording medium may be a recording medium that can be directly connected to the user terminal 100, and may include computer-readable recording media such as floppy drives, disks, tapes, DVD / CD-ROM drives, and memory cards. Alternatively, the software components can be loaded into memory 120 via a communication module (not shown) that is not a computer-readable recording medium. For example, at least one program can be loaded into memory 120 based on a computer program (for example, a computer program for the processor 110 to perform operations described later with reference to Figures 2 to 6) installed by a file provided via a communication module (not shown) by a developer or a file distribution system that distributes application installation files.

[0047] The input / output interface (not shown) may be connected to or included in the user terminal 100, or may be means for interfacing with an input or output device (e.g., keyboard, mouse, etc.). The input / output interface (not shown) may be configured separately from the processor 110, but is not limited thereto; the input / output interface (not shown) may be configured to be included in the processor 110.

[0048] A communication module (not shown) can provide configurations or functions for the server 20 and the user terminal 100 to communicate with each other via a network. The communication module (not shown) can also provide configurations or functions for the user terminal 100 to communicate with other external devices. For example, control signals, instructions, data, etc., provided by the processor 110 can be transmitted to the server 20 and / or external devices via the communication module (not shown) and the network.

[0049] On the other hand, although not shown in Figure 2, the user terminal 100 may further include a display device. Alternatively, the user terminal 100 may be connected to an independent display device by a wired or wireless connection, allowing data to be sent and received between them.

[0050] Figure 3 is a flowchart illustrating an example of a method for calculating blood pressure values ​​using characteristic values ​​of photoplethysmography according to one embodiment.

[0051] Referring to Figure 3, the method for calculating blood pressure values ​​using the characteristic values ​​of photoplethysmography consists of steps processed chronologically by the user terminals 10, 100, or processor 110 shown in Figures 1 and 2. Therefore, even if the details are omitted below, the information described above regarding the user terminals 10, 100, or processor 110 shown in Figures 1 and 2 can also be applied to the method for calculating blood pressure values ​​using the characteristic values ​​of photoplethysmography shown in Figure 3.

[0052] At step 310, the processor receives photoplethysmography data, including the photoplethysmography waveform.

[0053] The photoplethysmography (PPSW) data may include a color difference signal based on PPG detected in the user's facial region. The PPSW data may also include one waveform, either an rPPG waveform or a cPPG waveform. Furthermore, the PPSW data may include, but is not limited to, a pulse wave measured from the user via a PPG measuring device.

[0054] In 320 steps, the processor normalizes the photoplethysmography waveform contained in the photoplethysmography data.

[0055] First, the processor calculates the mean and standard deviation of the photoplethysmography waveform. The processor uses the photoplethysmography waveform corresponding to three cycles from the photoplethysmography data to calculate the mean and standard deviation.

[0056] The processor then uses the mean and standard deviation to standardize the photoplethysmography waveform.

[0057] As an example, the processor can standardize the photoplethysmography waveform using the following mathematical formula 1. The photoplethysmography waveform contained in the photoplethysmography data can be composed of n numerical data points in the format [x1, x2, x3, …, xn].

[0058] [Formula 1] TIFF0007898129000001.tif13138

[0059] Referring to Equation 1, the processor can obtain a standardized photoplethysmography data value (z(x)) using the photoplethysmography data value (x), mean (m), and standard deviation (σ).

[0060] At 330 steps, the processor detects feature values ​​to calculate blood pressure readings using standardized photoplethysmography waveforms.

[0061] The processor uses a standardized photoplethysmography waveform to detect a first feature value corresponding to the amplitude associated with systole, a second feature value corresponding to the amplitude associated with diastole, and a third feature value corresponding to the time-related interval of the waveform reflected by the vessel wall.

[0062] The following example illustrates how a processor uses a standardized photoplethysmography waveform to detect feature values, with reference to Figure 4.

[0063] Figure 4 is a diagram illustrating an example in which a processor according to one embodiment detects feature values ​​using a standardized photoplethysmography waveform. In Figure 4, the systolic phase (SP) refers to the interval from the start time (P0) of the cycle to the time when the maximum blood pressure value M2 of the cycle is obtained. In Figure 4, the diastolic phase (DP) refers to the interval from the time when the maximum blood pressure value M2 of the cycle is obtained to the time when the cycle ends.

[0064] The processor uses a standardized photoplethysmography waveform to detect a first feature value 410 corresponding to the amplitude associated with systolic SP, a second feature value 420 corresponding to the amplitude associated with diastolic DP, and a third feature value 430 corresponding to the time- and interval of the waveform reflected by the vessel wall.

[0065] The processor uses the maximum blood pressure value M2 and minimum blood pressure value M0 corresponding to the peak of the photoplethysmography waveform 41 to detect a first feature value 410 corresponding to the amplitude associated with the systolic SP. The first feature value 410 corresponds to the absolute difference between the maximum blood pressure value M2 and the minimum blood pressure value M0 of the photoplethysmography waveform 41. On the other hand, the first feature value 410 may be the average value corresponding to all the periods included in the photoplethysmography waveform.

[0066] Then, when the time P2 corresponds to the inflection point where the photoplethysmography waveform 42 obtained by applying differentiation has a minimum value, the processor uses the amplitude of the photoplethysmography waveform 41 at P2 to detect a second feature value 420 that corresponds to the amplitude associated with the diastolic DP. The second feature value 420 corresponds to the absolute value of the amplitude of the photoplethysmography waveform 41 at P2. On the other hand, the second feature value 420 may be the average value corresponding to all the periods included in the photoplethysmography waveform.

[0067] Then, the processor, taking P1 as the time corresponding to the point in the photoplethysmography waveform 42 obtained by applying differentiation where the absolute value of the slope after the maximum value becomes small and then large again, uses the time from the start time P0 to P1 in the photoplethysmography waveform 41 to detect a third feature value 430 that corresponds to the interval associated with the time of the waveform reflected by the blood vessel wall. The third feature value 430 corresponds to the absolute value of the time difference from the start time P0 to P1 in the photoplethysmography waveform 41. On the other hand, the third feature value 430 may be the average value corresponding to all the periods included in the photoplethysmography waveform.

[0068] Furthermore, referring to Figure 3, blood pressure values ​​are calculated in 340 steps based on photoplethysmography data and detected feature values.

[0069] The processor calculates systolic and diastolic blood pressure values ​​based on the detected feature values.

[0070] Meanwhile, the processor calculates blood pressure values ​​based on photoplethysmography data, first feature values, second feature values, and third feature values.

[0071] On the other hand, the processor can calculate blood pressure values ​​using the first neural network model. Specifically, the processor inputs photoplethysmography data and detected feature values ​​as input data to the first neural network model. The processor then obtains blood pressure values ​​as output data from the first neural network model.

[0072] The following example illustrates how a processor uses a first neural network model to obtain blood pressure readings, with reference to Figure 5.

[0073] Figure 5 is a diagram illustrating an example in which a processor according to one embodiment acquires blood pressure values ​​using a first neural network model.

[0074] The first neural network model 52 may be any form of deep learning model that acquires blood pressure values. For example, the first neural network model 52 may include a deep learning model of an RNN sequence that processes time-series data. In Figure 5, the first neural network model 52 is illustrated as an LSTM deep learning model, but is not limited to this. The first neural network model 52 may include multiple LSTM layers.

[0075] A deep learning model may include a neural network for acquiring blood pressure readings. In this specification, the terms neural network, network function, and neural network may be used interchangeably. A neural network can consist of a set of interconnected computational units, commonly referred to as nodes. Such nodes may be referred to as neurons. A neural network consists of at least one node. The nodes (or neurons) constituting the neural network may be interconnected by one or more links.

[0076] The processor inputs the photoplethysmography data and detected feature values ​​as input data 51 for the first neural network model 52. For example, the processor inputs the photoplethysmography data, the first feature value, the second feature value, and the third feature value as input data 51 for the first neural network model 52.

[0077] The input data 51 is a vector consisting of photoplethysmography data, a first feature value, a second feature value, and a third feature value. For example, the input data 51 may be a vector consisting of 878 values. These 878 values ​​include 875 values ​​corresponding to the photoplethysmography waveform contained in the photoplethysmography data, the first feature value, the second feature value, and the third feature value.

[0078] The first neural network model 52 inputs the input data 51 into the first LSTM layer (LSTM_1). The result values ​​derived in the LSTM layer (LSTM_1) are sequentially input into the next LSTM layer, then into the nth LSTM layer (LSTM_n), and finally into the fully connected layer.

[0079] When input data 51 is input to the first neural network model 52, the first neural network model 52 outputs systolic blood pressure values ​​(SBP) and diastolic blood pressure values ​​(DBP) as output data.

[0080] On the other hand, the processor corrects blood pressure readings based on personal information and environmental information related to blood pressure readings. For example, the processor can correct blood pressure readings calculated using a cohort model.

[0081] Personal information regarding blood pressure readings includes at least one piece of information about the subject's gender, age, physical characteristics, and disease. This personal information may be obtained from existing databases or from user input, but is not limited to these sources.

[0082] Environmental information related to blood pressure readings includes at least one piece of information: temperature information and atmospheric pressure information at the time of measurement of the photoplethysmography waveform.

[0083] The processor analyzes the correlation between blood pressure values ​​and personal information and environmental information related to blood pressure values ​​to calculate weighted values. For example, the processor uses gender information from personal information to analyze the correlation with blood pressure values ​​and calculates weighted values ​​corresponding to gender information. Another example is the processor using age information from personal information to group age groups, analyze the correlation between the grouping results and blood pressure values, and calculate weighted values ​​corresponding to age information. Yet another example is the processor using body information from personal information to analyze the correlation between BMI index and blood pressure values ​​and calculate weighted values ​​corresponding to body information. Yet another example is the processor using temperature information from environmental information to analyze the correlation between temperature and systolic and diastolic blood pressure values ​​and calculate weighted values ​​corresponding to temperature information. For example, the correlation may include a relationship where a 1-degree Celsius decrease in temperature is inversely proportional to a 1.3 mmHg increase in systolic blood pressure and a 0.6 mmHg increase in diastolic blood pressure.

[0084] On the other hand, the processor can correct the blood pressure values ​​using the correction calculation model 62. Specifically, the processor calculates weighted values ​​corresponding to personal information and environmental information. The processor then inputs the blood pressure values, personal information, environmental information, and weighted values ​​as input data 61 to the correction calculation model 62. The processor then obtains the corrected blood pressure values ​​as output data 63 from the correction calculation model 62.

[0085] The following example illustrates how the processor uses a correction calculation model to correct blood pressure readings, with reference to Figure 6.

[0086] Figure 6 is a diagram illustrating an example in which a processor according to one embodiment corrects blood pressure values ​​using a correction calculation model.

[0087] The correction calculation model 62 may be any form of machine learning model or deep learning model that acquires blood pressure values.

[0088] The processor inputs the calculated blood pressure value, personal information related to the blood pressure value, environmental information related to the blood pressure value, and the calculated weighted value as input data 61 to the correction calculation model 62.

[0089] As an example, the correction calculation model 62 applies the input data 61 to the following equations 2 and 3.

[0090] [Formula 2] Corrected SBP=β0+β1sSBP+β2s year+β3s gender+β4sBMI

[0091] The processor can obtain a corrected systolic blood pressure value (corrected SBP) using a weighted value (β0), systolic blood pressure value (SBP), a weighted value corresponding to the systolic blood pressure value (SBP) (β1), a value corresponding to the year (year), a weighted value corresponding to the year (β2), a value corresponding to the gender (gender), a weighted value corresponding to the gender (β3), a value corresponding to the BMI (BMI), and a weighted value corresponding to the BMI (β4).

[0092] [Formula 3] Corrected DBP=β5+β6sDBP+β7s year+β8s gender+β9sBMI

[0093] The processor can obtain a corrected diastolic blood pressure value (corrected DBP) using a weighted value (β5), diastolic blood pressure value (DBP), a weighted value corresponding to the diastolic blood pressure value (DBP) (β6), a value corresponding to the year (year), a weighted value corresponding to the year (β7), a value corresponding to the sex (sex), a weighted value corresponding to the sex (β8), a value corresponding to the BMI (BMI), and a weighted value corresponding to the BMI (β9).

[0094] When the input data 61 is input to the correction calculation model 62, the correction calculation model 62 outputs corrected systolic blood pressure values ​​(corrected SBP) and corrected diastolic blood pressure values ​​(corrected DBP) as output data.

[0095] As described above, the processor uses photoplethysmography (PPS) data and PPS data to calculate blood pressure values ​​based on detected feature values. Users can then view blood pressure values ​​calculated from the PPS waveform with greater accuracy.

[0096] On the other hand, the above-described method can be created as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that runs the program using a computer-readable recording medium. Furthermore, the data structure used in the above-described method can be recorded on a computer-readable recording medium by various means. The computer-readable recording medium includes storage media such as magnetic storage (e.g., ROM, RAM, USB, floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM, DVD, etc.).

[0097] Those with ordinary skill in the art relating to this embodiment should understand that it may be embodied in modified forms that do not deviate from the essential characteristics of the description above. Therefore, the disclosed method should be considered in an explanatory rather than restrictive sense, and the scope of rights should be interpreted as being shown in the claims and encompassing all differences within an equivalent scope, rather than in the description above.

Claims

1. In a method for calculating blood pressure values ​​using characteristic values ​​of photoplethysmography, The step of receiving photoplethysmography data, including the photoplethysmography waveform; A step of standardizing the photoplethysmography waveform included in the aforementioned photoplethysmography data; A step of detecting feature values ​​for calculating blood pressure values ​​using the standardized photoplethysmography waveform; and A step of calculating blood pressure values ​​based on the aforementioned photoplethysmography data and the detected feature values; Includes, The detection step includes the step of using the standardized photoplethysmography waveform to detect a first feature value corresponding to the amplitude associated with systole, a second feature value corresponding to the amplitude associated with diastole, and a third feature value corresponding to the time-related interval of the waveform reflected by the blood vessel wall; The calculation step described above is: The step of calculating the blood pressure value based on the photoplethysmography data, the first feature value, the second feature value, and the third feature value; The first characteristic value corresponds to the difference between the maximum blood pressure value and the minimum blood pressure value detected based on the photoplethysmography waveform. The second characteristic value corresponds to the difference between the blood pressure value at the inflection point detected based on the photoplethysmography waveform and the diastolic blood pressure value. The third characteristic value corresponds to the difference between the time at the inflection point detected based on the photoplethysmography waveform to which differentiation has been applied and the time at the starting point of the photoplethysmography waveform to which differentiation has been applied, when differentiation has been applied to the photoplethysmography waveform.

2. The aforementioned standardization step is, A step of calculating the mean value and standard deviation corresponding to the aforementioned photoelectric pulse wave waveform; and A step of standardizing the photoplethysmography waveform using the mean value and standard deviation; The method according to claim 1, including the method described in claim 1.

3. The calculation step described above is: The step of inputting the aforementioned photoplethysmography data and the detected feature values ​​as input data for the first neural network model; and Steps to obtain the blood pressure values ​​as output data of the first neural network model; The method according to claim 1, including the method described in claim 1.

4. The calculation step described above is: The method according to claim 1, comprising the step of calculating a systolic blood pressure value and a diastolic blood pressure value based on the detected characteristic values.

5. The method according to claim 1, further comprising the step of correcting the blood pressure values ​​based on personal information relating to the blood pressure values ​​and environmental information relating to the blood pressure values.

6. The aforementioned correction step is, The step of calculating weighted values ​​corresponding to the aforementioned personal information and the aforementioned environmental information; and A step in which the blood pressure values, personal information, environmental information, and weighted values ​​are input as input data to a correction calculation model, and the corrected blood pressure values ​​are obtained as output data from the correction calculation model; The method according to claim 5, including the method described in claim 5.

7. A computer-readable recording medium storing a program for causing a computer to perform the method described in claim 1.

8. In a device that calculates blood pressure values ​​using characteristic values ​​of photoplethysmography, At least one memory; and At least one processor; Includes, The at least one processor is The system receives photoplethysmography (PPS) data including the photoplethysmography waveform, standardizes the PPS waveform included in the PPS data, detects feature values ​​for calculating blood pressure values ​​using the standardized PPS waveform, and calculates blood pressure values ​​based on the PPS data and the detected feature values. The detection involves using the standardized photoplethysmography waveform to detect a first feature value corresponding to the amplitude associated with systole, a second feature value corresponding to the amplitude associated with diastole, and a third feature value corresponding to the time-related interval of the waveform reflected by the blood vessel wall. The calculation described above involves calculating the blood pressure value based on the photoplethysmography data, the first feature value, the second feature value, and the third feature value. The first characteristic value corresponds to the difference between the maximum blood pressure value and the minimum blood pressure value detected based on the photoplethysmography waveform, The second characteristic value corresponds to the difference between the blood pressure value at the inflection point detected based on the photoplethysmography waveform and the diastolic blood pressure value. The third characteristic value corresponds to the difference between the time at the inflection point detected based on the photoplethysmography waveform to which differentiation has been applied, and the time at the starting point of the photoplethysmography waveform to which differentiation has been applied, when differentiation has been applied to the photoplethysmography waveform, in the computer device.

Images