Electronic device and apparatus for estimating blood pressure

Abstract

An electronic device and an apparatus for estimating blood pressure are provided. The apparatus may include a memory storing one or more instructions and a processor configured to execute the one or more instructions to extract a cardiac output (CO) feature, a first candidate total peripheral resistance (TPR) feature, and a second candidate TPR feature from a biosignal; determine one of the first candidate TPR feature and the second candidate TPR feature as a TPR feature based on a change direction of the CO feature and a change direction of the first candidate TPR feature between a blood pressure measurement time and a calibration time; and estimate blood pressure based on the TPR feature and the CO feature.

Description

[0001] This application claims priority from Korean Patent Application No. 10-2021-0183193 filed on December 20, 2021, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference in its entirety for all purposes. Technical Field

[0002] One or more example embodiments are directed to estimating blood pressure based on features extracted from a pulse wave signal. Background Art

[0003] In order to solve the problems of an aging population structure, a rapid increase in medical expenses and a shortage of professional medical personnel, research on IT-medical fusion technology that combines information technology (IT) with medical technology is being carried out recently. Specifically, the monitoring of human health status is not limited to fixed locations (such as hospitals), but is being expanded to mobile healthcare sectors for monitoring the health status of users at any time and any place in daily life at home and in the office. Electrocardiogram (ECG) signals, photoplethysmography (PPG) signals and electromyography (EMG) signals are examples of biological signals that indicate the health status of an individual. Various signal sensors are being developed to measure such signals in daily life. In particular, in the case of a PPG sensor, the blood pressure of a human body can be estimated by analyzing the shape of the pulse wave that reflects the cardiovascular state.

[0004] The PPG signal is the sum of the propagation wave that propagates from the heart to the peripheral parts of the body and the reflected wave that returns from the peripheral parts of the body. It is known that information used to estimate blood pressure can be obtained by extracting various features related to the propagation wave or the reflected wave. Summary of the Invention

[0005] According to one aspect of the present disclosure, a device for estimating blood pressure may include: a memory storing one or more instructions; and a processor configured to execute the one or more instructions to: extract a cardiac output (CO) feature, a first candidate total peripheral resistance (TPR) feature, and a second candidate TPR feature from a biological signal, determine one of the first candidate TPR feature and the second candidate TPR feature as a TPR feature based on a change direction of the CO feature and a change direction of the first candidate TPR feature between a blood pressure measurement time and a calibration time, and estimate blood pressure based on the TPR feature and the CO feature.

[0006] The CO feature may include at least one of a heart rate and a ratio between an amplitude at a predetermined point and an area under a waveform of the biosignal.

[0007] The predetermined point may include a point at which a slope of a waveform of the biosignal in a cardiac systole phase is closest to zero.

[0008] The first candidate TPR feature may include the ratio between the amplitude of the propagation wave component of the biosignal and the amplitude of the reflected wave component. The second candidate TPR feature may include the ratio between the amplitude of the reflected wave component and the amplitude at an internal dividing point between the point of the propagation wave component and a predetermined point of the biosignal.

[0009] The processor may be further configured to: obtain a second-order derivative signal of the biosignal; and detect a local minimum point of the second-order derivative signal as a point of the propagation wave component and a point of the reflection wave component.

[0010] In response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, the processor may be further configured to: determine the first candidate TPR feature as the TPR feature; and in response to the change directions being the same, the processor may be further configured to: determine the second candidate TPR feature as the TPR feature.

[0011] In response to the CO feature changing in a different direction than the first candidate TPR feature, and the change in the first candidate TPR feature being less than a predetermined threshold, the processor may be further configured to determine the first candidate TPR feature as the TPR feature. In response to the CO feature changing in a different direction than the first candidate TPR feature, and the change in the first candidate TPR feature being greater than or equal to the predetermined threshold, the processor may be further configured to determine the second candidate TPR feature as the TPR feature. In response to the CO feature changing in the same direction as the first candidate TPR feature, the processor may be further configured to determine the second candidate TPR feature as the TPR feature.

[0012] The predetermined threshold may include a value obtained by applying a predetermined weight to a change in the CO characteristic.

[0013] The processor can also be configured to: determine the change of the first candidate TPR feature by dividing the first candidate TPR feature value at the blood pressure measurement time by the reference TPR feature value at the calibration time to obtain a first division result, and by subtracting 1 from the first division result; and determine the change of the CO feature by dividing the CO feature value at the blood pressure measurement time by the reference CO feature value at the calibration time to obtain a second division result, and by subtracting 1 from the second division result.

[0014] The processor may be further configured to estimate the blood pressure by applying a predefined blood pressure estimation model to a result obtained by combining the CO feature and the TPR feature.

[0015] According to another aspect of the present disclosure, a method for estimating blood pressure may include: measuring a biosignal from a subject; extracting a cardiac output (CO) feature, a first candidate total peripheral resistance (TPR) feature, and a second candidate TPR feature based on the biosignal; determining one of the first candidate TPR feature and the second candidate TPR feature as a TPR feature based on a change direction of the CO feature and a change direction of the first candidate TPR feature between a blood pressure measurement time and a calibration time; and estimating blood pressure based on the TPR feature and the CO feature.

[0016] The CO feature may include at least one of a heart rate and a ratio between an amplitude at a predetermined point and an area under a waveform of the biosignal.

[0017] The predetermined point may include a point at which a slope of a waveform of the biosignal in a cardiac systole phase is closest to zero.

[0018] The first candidate TPR feature may include the ratio between the amplitude of the propagation wave component of the biosignal and the amplitude of the reflected wave component. The second candidate TPR feature may include the ratio between the amplitude of the reflected wave component and the amplitude at an internal dividing point between the point of the propagation wave component and a predetermined point of the biosignal.

[0019] The step of determining the TPR feature may include determining the first candidate TPR feature as the TPR feature in response to a change direction of the CO feature being different from a change direction of the first candidate TPR feature, and determining the second candidate TPR feature as the TPR feature in response to the change directions being the same.

[0020] The step of determining the TPR feature may include: in response to a change direction of the CO feature being different from a change direction of the first candidate TPR feature and a change of the first candidate TPR feature being less than a predetermined threshold, determining the first candidate TPR feature as the TPR feature; in response to a change direction of the CO feature being different from a change direction of the first candidate TPR feature and a change of the first candidate TPR feature being greater than or equal to the predetermined threshold, determining the second candidate TPR feature as the TPR feature; and in response to a change direction of the CO feature being the same as a change direction of the first candidate TPR feature, determining the second candidate TPR feature as the TPR feature.

[0021] The predetermined threshold may include a value obtained by applying a predetermined weight to a change in the CO characteristic.

[0022] The estimating of the blood pressure may include estimating the blood pressure by applying a predefined blood pressure estimation model to a result obtained by combining the CO feature and the TPR feature.

[0023] According to another aspect of the present disclosure, an electronic device may include: a main body; a photoplethysmography (PPG) sensor configured to: measure a PPG signal from a subject; and a processor configured to: extract a cardiac output (CO) feature and a first candidate total peripheral resistance (TPR) feature from the PPG signal, determine a TPR feature based on whether a change direction of the CO feature between a blood pressure measurement time and a calibration time is the same as a change direction of the first candidate TPR feature, and estimate blood pressure based on the TPR feature and the CO feature.

[0024] In response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, the processor may be further configured to: determine the first candidate TPR feature as the TPR feature, and in response to the change directions being the same, the processor may be further configured to: extract the second candidate TPR feature as the TPR feature, the second candidate TPR feature having a smaller change than the first candidate TPR feature between the blood pressure measurement time and the calibration time. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and / or other aspects will become more apparent by describing certain example embodiments with reference to the accompanying drawings, in which:

[0026] Figure 1 is a block diagram illustrating an apparatus for estimating blood pressure according to an example embodiment of the present disclosure;

[0027] Figures 2A to 2F is a diagram explaining an example of obtaining features related to blood pressure;

[0028] Figure 3 is a block diagram illustrating an apparatus for estimating blood pressure according to another example embodiment of the present disclosure;

[0029] Figure 4 is a flowchart illustrating a method of estimating blood pressure according to an example embodiment of the present disclosure;

[0030] Figures 5 to 8 is a diagram illustrating a method of extracting TPR features according to an exemplary embodiment of the present disclosure; and

[0031] Figures 9 to 11 is a block diagram illustrating various structures of an electronic device including an apparatus for estimating blood pressure. DETAILED DESCRIPTION

[0032] Example embodiments are described in more detail below with reference to the accompanying drawings.

[0033] In the following description, the same reference numerals are used for the same elements even in different drawings. Matters defined in the description, such as detailed configurations and elements, are provided to assist in a comprehensive understanding of the example embodiments. However, it is apparent that the example embodiments can be practiced without those specifically defined matters. In addition, well-known functions or configurations are not described in detail because they would obscure the description with unnecessary detail.

[0034] It will be understood that although the terms first, second, etc. can be used to describe various elements herein, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. Unless otherwise clearly stated, any reference to the singular form may include the plural form. In addition, unless explicitly described to the contrary, statements (such as, "including" or "comprising") will be understood to indicate that the elements included in the statement do not exclude any other elements. In addition, terms (such as, "unit" or "module", etc.) should be understood as units for performing at least one function or operation, and units can be implemented as hardware, software, or a combination thereof.

[0035] When a phrase (such as "at least one of") appears after a list of elements, it modifies the entire list of elements and does not modify the individual elements of the list. For example, the phrase "at least one of a, b, and c" should be read to mean: including only a, including only b, including only c, including both a and b, including both a and c, including both b and c, including all of a, b, and c, or any variation of the foregoing.

[0036] Figure 1 is a block diagram illustrating an apparatus for estimating blood pressure according to an example embodiment of the present disclosure.

[0037] Reference Figure 1 , an apparatus 100 for estimating blood pressure includes a sensor 110 and a processor 120 .

[0038] Sensor 110 may acquire biological signals from a subject and transmit the acquired biological signals to processor 120. Specifically, the biological signals may include various biological signals (such as electrocardiogram (ECG) signals, photoplethysmography (PPG) signals, and electromyography (EMG) signals), and the biological signals may be modeled by summing multiple waveform components. Sensor 110 may include a PPG sensor, an ECG sensor, and / or an EMG sensor to estimate a person's blood pressure by analyzing the shape of a pulse wave signal reflecting cardiovascular status.

[0039] For example, sensor 110 may be a spectrometer or PPG sensor for measuring PPG signals. As shown here, sensor 110 may include a light source 111 for emitting light onto a subject, and a detector 112 for detecting light that has returned from the subject's body tissue after being emitted by light source 111, either through scattering or reflection from the body tissue or through transmission into the body tissue. Light source 111 may be implemented as one or more light sources or an array of light sources, and each light source may be implemented as a light-emitting diode (LED), a laser diode (LD), a phosphor, or the like. The multiple light sources may emit light of different wavelengths (e.g., red, green, blue, infrared, etc.), without particular limitation. The multiple light sources may be driven simultaneously or sequentially in a time-division manner. Detector 112 may include a photodiode, a phototransistor, an image sensor (e.g., a complementary metal oxide semiconductor (CMOS) image sensor), a spectrometer, or the like. Detector 112 may be implemented as one or more detectors or an array of detectors.

[0040] The sensor 110 can measure biological signals from an object under the control of the processor 120. When a user places an object on the sensor 110 and gradually increases or decreases the pressure, the sensor 110 can continuously measure the biological signals during a predetermined time period. The object can be a body part that can be in contact with the sensor 110, and can be, for example, a body part where a pulse wave can be easily measured. For example, the object can be the surface of the wrist adjacent to the radial artery and the upper part of the wrist where venous blood or capillary blood passes. When the pulse wave is measured on the skin surface of the wrist where the radial artery passes, the influence of external factors that cause measurement errors (such as the thickness of the skin tissue inside the wrist) can be relatively small. However, the object is not limited to the above example and can be a peripheral area of ​​the human body (such as fingers, toes, etc.), which is an area in the human body with a high blood vessel density.

[0041] A force sensor for measuring a change in force applied to the sensor 110 by an object may be provided at an upper end or a lower end of the sensor 110. Here, the force sensor may refer to a pressure sensor, and the force measured by the force sensor may also refer to pressure.

[0042] The processor 120 may control the sensor 110 upon receiving a request for estimating blood pressure from the user or an external device. When the force sensor measures pressure applied to the sensor 110 by the object, the processor 120 may guide the user to apply appropriate pressure based on the measured force.

[0043] The processor 120 may be electrically or functionally connected to the sensor 110 and may control the sensor 110 to acquire a biosignal. Upon receiving the biosignal from the sensor 110, the processor 120 may perform preprocessing (such as filtering to remove noise from the received signal). For example, the processor 120 may perform signal correction (such as filtering (e.g., bandpass filtering between 0.4 Hz and 10 Hz)), biosignal amplification, signal conversion to a digital signal, smoothing, and overall averaging of continuously measured biosignals. Furthermore, a representative periodic signal for estimating blood pressure may be acquired from the continuous biosignal.

[0044] The processor 120 can estimate blood pressure by analyzing the waveform of the measured biosignal. Hereinafter, unless otherwise indicated, the term "blood pressure" may refer to any one or any combination of mean arterial pressure (AMP), diastolic blood pressure (DBP), and systolic blood pressure (SBP). The processor 120 can extract features related to blood pressure from the received biosignal and can estimate blood pressure by using the extracted features. However, bioinformation is not limited to blood pressure, and the processor 120 can estimate additional bioinformation (such as vascular age, arterial hardness, aortic pressure waveform, stress index, fatigue level, etc.).

[0045] Changes in MAP are proportional to cardiac output (CO) and total peripheral resistance (TPR), as shown below in Equation 1. CO represents the volume of blood pumped by the heart in one minute and can be calculated by multiplying heart rate by stroke volume.

[0046] [Equation 1]

[0047] ΔMAP=COxTPR

[0048] Here, ΔMAP represents the difference in MAP between the left ventricle and the right atrium, where the MAP of the right atrium is generally in the range of 3 mmHg to 5 mmHg, making the MAP in the right atrium similar to the MAP in the left ventricle or the MAP of the upper arm. If the absolute actual CO value and TPR value are known, MAP can be obtained from the aorta or the upper arm. However, it can be difficult to estimate the absolute CO value and TPR value based on biosignals. Under normal circumstances, the human body has the ability to regulate blood pressure levels. For example, when blood pressure increases due to a rapid increase in CO, blood vessels dilate, allowing TPR to decrease, thereby allowing blood pressure to return to normal levels.

[0049] The processor 120 may extract a feature related to cardiac output (CO) (hereinafter referred to as a "CO feature") and a feature related to total peripheral resistance (TPR) (hereinafter referred to as a "TPR feature") from the biosignal, and may estimate blood pressure based on the CO feature and the TPR feature. For example, the processor 120 may extract a plurality of characteristic points by analyzing the biosignal and / or a derivative signal (e.g., a first-order derivative signal or a second-order derivative signal) of the biosignal, and may obtain the CO feature and / or the TPR feature based on one or a combination of two or more of the extracted characteristic points. Here, the CO feature may be a feature value that shows an increasing or decreasing trend proportional to an actual CO value, where the actual CO value changes relative to an actual TPR value, and the actual TPR value does not change significantly in an unsteady state compared to a stable state. Furthermore, the TPR feature may be a feature value that shows an increasing or decreasing trend proportional to an actual TPR value, where the actual TPR value changes relative to an actual CO value, and the actual CO value does not change significantly in an unsteady state compared to a stable state.

[0050] Figures 2A to 2F : is a diagram explaining an example of obtaining features related to blood pressure.

[0051] Reference Figure 2A and Figure 2B , the pulse wave signal 20 measured from the peripheral body part B1 may be composed of the sum of the propagation wave P1 propagated from the heart via the blood jet from the left ventricle to the peripheral parts of the body and the branch points in the blood vessels, and the reflected waves P2 and P3 returning from the peripheral parts of the body or the branch points in the blood vessels. For example, Figure 2A and Figure 2B As shown in FIG, the waveform of the pulse wave signal consists of a propagating wave P1 generated by blood ejection from the left ventricle, and a first reflected wave P2 and a second reflected wave P3 primarily reflected from the renal arteries and iliac arteries. The propagating wave P1 is associated with cardiac characteristics, while the reflected waves P2 and P3 are associated with vascular characteristics. Therefore, based on the time points associated with the individual pulses P1, P2, and P3 that make up the waveform of the pulse wave signal 20 and / or the amplitude of the pulse wave signal, the processor 120 can extract a CO feature and / or a TPR feature, and can measure blood pressure by combining the extracted CO and TPR features.

[0052] Figure 2C and Figure 2D : is a diagram showing various characteristic points that can be obtained from a biological signal. The characteristic points shown here are just examples.

[0053] For example, the processor 120 may extract the heart rate as a characteristic point from the biological signal 20. Figure 2C, the processor 120 may extract, from the biosignal 20, the time point T1 and / or the amplitude P1 associated with the propagation wave, and the time points T2 and T3 and / or the amplitudes P2 and P3 associated with the reflection wave as characteristic points. Specifically, the processor 120 may derive a second-order derivative signal of the biosignal and detect local minimum points of the second-order derivative signal to extract the positions of the first local minimum point, the second local minimum point, and the third local minimum point as the time point T1 of the propagation wave component, the time point T2 of the first reflection wave component, and the time point T3 of the second reflection wave component.

[0054] In addition, the processor 120 may extract the time point Tmax and / or the amplitude Pmax at the maximum amplitude point in the cardiac contraction phase (for example, the period from the starting point of the dicrotic notch (DN) to the point (Tdic)) as a characteristic point. In this case, the maximum amplitude point may represent a point in the cardiac contraction phase at which the slope is closest to zero. The processor 120 may derive a first-order derivative signal of the biosignal 20, and may extract the point at which the slope is closest to zero by using the first-order derivative signal. In addition, the processor 120 may extract the time point Tsys and / or the amplitude Psys at the midpoint between a predetermined position (for example, the position of the propagation wave component and the maximum amplitude position or a point at which the position of the propagation wave component and the maximum amplitude position are internally divided at a predetermined ratio) as a characteristic point.

[0055] In addition, refer to Figure 2D , the processor 120 may extract the area PP Garea under the waveform of the biosignal 20 as a characteristic point. Specifically, the area PP Garea under the waveform may be the area of ​​a portion determined based on the period T period of the biosignal 20 and the random values ​​τ1 and τ2. As described above, by adjusting the random values ​​τ1 and τ2, the processor 120 may extract the total area of ​​the waveform of the biosignal 20 or the area of ​​a predetermined region (e.g., the area during the cardiac systolic phase, the area during the cardiac diastolic phase, etc.) as a characteristic point.

[0056] When extracting the characteristic points, the processor 120 may obtain the CO feature and the TPR feature by using one or a combination of two or more of the extracted characteristic points.

[0057] For example, the processor 120 may obtain the heart rate HR (not shown) or the ratio between the amplitude Pmax at the maximum amplitude point and the waveform area PPGarea (Pmax / PPGarea) as the CO feature. However, the CO feature is not limited thereto, and the processor 120 may obtain PPGarea, P3 / Pmax, P3 / Psys, 1 / (T3-T1), 1 / (T3-Tsys), 1 / (T3-Tmax), 1 / (T2-T1), P2 / P1, P2 / Psys, P3 / Pmax, P3 / P1, etc. as the CO feature.

[0058] In addition, the processor 120 may first obtain two or more candidate TPR features, and may obtain one of the two or more candidate TPR features as the final TPR feature. For example, the processor 120 may obtain a first candidate TPR feature (e.g., P2 / P1) defined as the most suitable TPR feature and a second candidate TPR feature (e.g., P2 / Psys) that changes in a relatively stable manner when compared with the first candidate TPR feature, and may determine one of the first candidate TPR feature and the second candidate TPR feature as the final TPR feature based on the relationship between the first candidate TPR feature and the CO feature. The first candidate TPR feature and the second TPR feature are not limited to the above example and may be one of the above examples of the CO feature.

[0059] Under normal circumstances, the human body has the ability to regulate blood pressure. For example, when blood pressure increases due to a rapid increase in CO, blood vessels dilate, reducing TPR. Conversely, when blood vessels constrict, reducing vessel diameter and increasing TPR, CO decreases, allowing blood pressure to return to normal. Therefore, due to the physiological characteristics of the body's ability to regulate blood pressure, CO and TPR characteristics generally tend to change in opposite directions.

[0060] In one embodiment, the processor 120 may determine one of the first candidate TPR feature and the second candidate TPR feature as the TPR feature based on the directionality of the change in the CO feature and the first candidate TPR feature at the blood pressure measurement time compared to the calibration time. In this case, when the feature increases at the current (blood pressure measurement) time compared to the calibration time, the directionality of the change may be defined as a positive direction, and when the feature decreases at the current time compared to the calibration time, the directionality of the change may be defined as a negative direction.

[0061] Reference Figure 2E , it can be seen that compared with the calibration time T0, CO characteristic f CO And the first candidate TPR feature f TPR1 Both increase at the current time Tm, so that the characteristics change in the same positive direction. The processor 120 can change the characteristics f CO The second candidate TPR feature f changes in the opposite direction and shows a relatively stable change TPR2 is determined as the final TPR feature so as to be more suitable for the ability to regulate blood pressure levels. Unlike this example, Figure 2F The CO characteristic f is shown compared with the calibration time T0 CO And the first candidate TPR feature f TPR1 Examples of changes in different directions at the current time Tm, where the CO feature f COchanges in the negative direction, and the first candidate TPR feature f TPR1 As described above, when the direction of change is different, the processor 120 may change the first candidate TPR feature f TPR1 Determined as the final TPR feature.

[0062] In another example, when the CO feature and the first candidate TPR feature change in different directions, the processor 120 may determine the final TPR feature by further considering the change of the first candidate TPR feature. Figure 2F As shown in the figure, even when the CO characteristic f CO And the first candidate TPR feature f TPR1 When the first candidate TPR feature f changes in different directions and can therefore be adapted to physiological characteristics, TPR1 Change of |Δf TPR1 Excessively greater than CO characteristic f CO Change of |Δf CO |, then the first candidate TPR feature f TPR1 It may also be unstable. Here, the change of each characteristic |Δf TPR1 | and |Δf CO | is the degree of change at the current time Tm compared to the calibration time T0, and may be a value normalized, for example, by dividing the feature value at the current time by the feature value at the calibration time and subtracting 1 from the resulting value. In one embodiment, the change |Δf of the first candidate TPR feature at the blood pressure measurement time may be determined by dividing the first candidate TPR feature value at the blood pressure measurement time by the reference TPR feature value at the calibration time and subtracting 1 from the resulting value. TPR1 In another embodiment, the change in CO characteristic |Δf can be determined by dividing the CO characteristic value at the blood pressure measurement time by the reference CO characteristic value at the calibration time and by subtracting 1 from the result value. CO |. Therefore, the processor 120 can TPR1 Change of |Δf TPR1 | is compared with a predetermined threshold, and if the change is greater than or equal to the threshold, the processor 120 may select a second candidate TPR feature f that shows a relatively stable change TPR2 is determined as the final TPR feature; and if the change is less than the threshold, the processor 120 may TPR1 is determined as the final TPR feature. In this case, the threshold can be defined as the value obtained by applying a predetermined weight α to the CO feature f CO Change of |Δf CO The value α|Δf obtained COThe predetermined weight α may be defined as a value greater than 1 (eg, 3), and may be a fixed value that may be universally applied, or may be a value personalized for each user.

[0063] Upon obtaining the CO and TPR features, processor 120 may estimate blood pressure using a blood pressure estimation model that defines the relationship between the obtained features and blood pressure. The blood pressure estimation model may be predefined as a linear or nonlinear function that defines the correlation between the CO and TPR features and blood pressure. The CO and TPR features may be obtained for SBP and DBP, respectively. By using the obtained CO and TPR features, processor 120 may estimate SBP and DBP independently of each other.

[0064] When predetermined calibration conditions are met, the processor 120 may perform calibration to obtain reference information (such as CO characteristics, TPR characteristics, cuff blood pressure, a blood pressure estimation model, etc.). For example, if the reference information required for estimating blood pressure does not exist (such as when the device 100 is being used for blood pressure estimation for the first time or when the device 100 is initialized), the processor 120 may first perform calibration. In another example, the processor 120 may determine whether to perform calibration by analyzing the blood pressure estimation results. For example, when the blood pressure estimation is completed, if the estimated blood pressure value falls outside a predetermined normal range, if the number of times the estimated blood pressure value falls outside the predetermined normal range is greater than or equal to a threshold, or if the estimated blood pressure value falls outside the predetermined normal range continuously or the number of times it falls outside the normal range within a predetermined time period is greater than or equal to a threshold, the processor 120 may determine that calibration is required. However, the calibration conditions are not limited to these, and the processor 120 may perform calibration at calibration intervals or in response to a user's request.

[0065] When determining to perform calibration, the processor 120 may guide the user on the calibration. For example, the processor 120 may guide the user to place an object on the measurement position of the sensor 110, or may guide the user on the contact pressure. In addition, as described above, the processor 120 may control the sensor 110 to acquire biosignals, and may obtain CO features, first candidate TPR features, second candidate TPR features, TPR features, etc. from the acquired biosignals. In addition, by using the communication module included in the device 100, the processor 120 may receive a reference cuff blood pressure from an external device (e.g., a cuff pressure gauge), or may output a user interface on the display to directly receive the reference cuff blood pressure from the user. In addition, the processor 120 may update the blood pressure estimation model by using the obtained CO features, TPR features, and reference blood pressure.

[0066] Figure 3is a block diagram illustrating an apparatus for estimating blood pressure according to another example embodiment of the present disclosure.

[0067] Reference Figure 3 , the apparatus 300 for estimating blood pressure may include a sensor 110, a processor 120, an output interface 310, a storage device 320, and a communication interface 330. The sensor 110 and the processor 120 are described above in detail, and thus a description thereof will be omitted.

[0068] The output interface 310 may output the biosignals measured by the sensor 110 and / or the data generated or processed by the processor 120 through various visual / non-visual methods. The output interface 310 may directly include a display device, an audio device, a tactile device, etc., or may be connected to a display device, an audio device, a tactile device, etc. installed in an external device through wired communication and wireless communication.

[0069] For example, once the user's blood pressure is estimated, the output interface 310 can output the estimated blood pressure to a display device using various visual methods (such as by changing the color, line thickness, font, etc. based on whether the estimated blood pressure falls within or outside the normal range). In addition, the output interface 310 can output the estimated blood pressure by voice using an audio device, or can output a notification of whether the blood pressure is abnormal by vibration or touch using a tactile device. In addition, by analyzing the blood pressure estimation history, the processor 120 can monitor the user's health status. In this case, the output interface 310 can provide information about actions that the user needs to take (such as warning messages, food information that the user should pay attention to, hospital appointment information, etc.).

[0070] The storage device 320 may store reference information obtained by the processor 120 during calibration. Furthermore, the storage device 320 may store biosignals, CO2 characteristics, TPR characteristics, estimated blood pressure values, and the like obtained during blood pressure estimation. Specifically, the reference information may include user information obtained during calibration (such as the user's age, gender, occupation, current health status, and the like) and / or biosignals, CO2 characteristics, TPR characteristics, reference cuff blood pressure, a blood pressure estimation model, and the like, but the reference information is not limited thereto. Specifically, the storage device 320 may include at least one storage medium selected from, but not limited to, flash memory, hard disk memory, multimedia card memory, micro card memory (e.g., SD memory, XD memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk.

[0071] The communication interface 330 can be connected to an external device using a communication technology to transmit and receive various data with the external device. For example, the communication interface 330 can receive reference information related to estimated blood pressure, and can transmit the biosignals measured by the sensor 110 and the data generated or processed by the processor 120 (e.g., estimated blood pressure values) to the external device. In particular, examples of the external device may include another device for estimating blood pressure, a cuff blood pressure device for measuring cuff blood pressure, a smartphone, a tablet PC, a desktop computer, a laptop computer, etc., but are not limited thereto.

[0072] In particular, the communication interface 330 may communicate with an external device by using various wired and wireless communication technologies, including Bluetooth communication, Bluetooth Low Energy (BLE) communication, near field communication (NFC), WLAN communication, Zigbee communication, Infrared Data Association (IrDA) communication, Wi-Fi Direct (WFD) communication, Ultra-Wideband (UWB) communication, Ant+ communication, WIFI communication, third generation (3G) communication, fourth generation (4G) communication, fifth generation (5G) communication, and sixth generation (6G) communication, etc. However, the communication technology is not limited thereto.

[0073] Figure 4 is a flowchart illustrating a method of estimating blood pressure according to an example embodiment of the present disclosure.

[0074] Figure 4 The method is an example of a method of estimating blood pressure performed by the aforementioned apparatuses 100 and 300 for estimating blood pressure and will be briefly described below to avoid redundancy.

[0075] First, in response to a request for estimating blood pressure, the apparatuses 100 and 300 for estimating blood pressure may measure a biological signal of a subject from a user in operation 410. Upon receiving a request for estimating blood pressure from a user through a user interface or from an external device, or at predetermined intervals, the apparatuses 100 and 300 for estimating blood pressure may measure the biological signal by driving a light source of a sensor to emit light onto the subject and detecting light scattered or reflected from the subject using a detector.

[0076] Then, in operation 420, the apparatuses 100 and 300 for estimating blood pressure may obtain a CO characteristic by using the biosignal. For example, the apparatuses 100 and 300 for estimating blood pressure may obtain the heart rate, the maximum amplitude in the cardiac systole phase, and the ratio of the area of ​​the waveform of the biosignal as the CO characteristic.

[0077] In addition, in operation 430, the apparatuses 100 and 300 for estimating blood pressure may obtain a TPR feature by using a biosignal. In particular, the apparatuses 100 and 300 for estimating blood pressure may determine a first candidate TPR feature having a high correlation with vascular resistance, and may obtain the TPR feature based on the directionality of the change in the first candidate TPR feature and the CO feature obtained in operation 420. The first candidate TPR feature may be defined as, for example, a value obtained by dividing the amplitude of the first reflected wave component by the amplitude of the propagation wave component. However, examples of the first candidate TPR feature are not limited thereto, and the first candidate TPR feature may include a ratio between the amplitude of the propagation wave component and the amplitude of the reflected wave component of the biosignal. Hereinafter, reference will be made to Figures 5 to 8 Various examples of obtaining TPR features are described.

[0078] Subsequently, in operation 440, the apparatuses 100 and 300 for estimating blood pressure may estimate blood pressure using the CO feature and the TPR feature. Specifically, the apparatuses 100 and 300 for estimating blood pressure may estimate blood pressure using a blood pressure estimation model that defines the correlation between a value obtained by combining the CO feature and the TPR feature and blood pressure. When estimating blood pressure, the apparatuses 100 and 300 for estimating blood pressure may provide information (such as estimated blood pressure, health status, warnings, response actions, etc.) to the user through various visual / non-visual methods.

[0079] In one example embodiment, in operation 410 , while the sensor 110 continuously measures a pulse wave signal from a user, the processor 120 may perform operations 420 to 440 in real time.

[0080] Figure 5 is a flowchart illustrating an example of obtaining TPR features in operation 430 .

[0081] First, in operation 510, the apparatuses 100 and 300 for estimating blood pressure may extract a first candidate TPR feature f TPR1 and the second candidate TPR feature f TPR2 For example, the first candidate TPR feature may be the ratio between the amplitude of the first reflected wave component and the amplitude of the propagating wave. In addition, the second candidate TPR feature may be the ratio between the amplitude of the first reflected wave component and the amplitude at the inner dividing point between the position of the propagating wave component and the maximum amplitude position.

[0082] Then, in operation 520, the apparatuses 100 and 300 for estimating blood pressure may determine whether the change direction of the CO characteristic is the same as the change direction of the TPR characteristic when compared with the calibration time. For example, the apparatuses 100 and 300 for estimating blood pressure may determine whether the CO characteristic change Δf CO The change Δf from the first candidate TPR featureTPR1 multiplied, and if the result value is less than zero, the apparatuses 100 and 300 for estimating blood pressure may determine that the change directions are different; and if the result value is not less than zero, the apparatuses 100 and 300 for estimating blood pressure may determine that the change directions are the same.

[0083] Then, if the change directions are different, in operation 530, the apparatuses 100 and 300 for estimating blood pressure may select the first candidate TPR feature f TPR1 Determined as the final TPR feature f TPR If the change directions are the same, then in operation 540, the apparatuses 100 and 300 for estimating blood pressure may select the second candidate TPR feature f TPR2 Determined as the final TPR feature f TPR .

[0084] Figure 6 is a flowchart illustrating another example of obtaining the TPR feature in operation 430 .

[0085] First, in operation 610, the apparatuses 100 and 300 for estimating blood pressure may extract a first candidate TPR feature f from a biosignal. TPR1 and the second candidate TPR feature f TPR2 .

[0086] In operation 620 , based on the CO characteristic change Δf CO and the first candidate TPR feature change Δf TPR1 Based on the determination of whether the product of is less than zero, the apparatuses 100 and 300 for estimating blood pressure may determine whether the change directions of the features are the same.

[0087] Then, if the CO characteristic changes Δf CO The change Δf from the first candidate TPR feature TPR1 is less than zero, so that the change directions are different, then in operation 630, the apparatuses 100 and 300 for estimating blood pressure may determine the absolute value of the change of the first candidate TPR feature |Δf TPR1 Is |less than a predetermined threshold α|Δf CO |.

[0088] Next, if the absolute value of the change in the first candidate TPR feature is less than a predetermined threshold, in operation 640, the apparatuses 100 and 300 for estimating blood pressure may change the first candidate TPR feature f to TPR1 Determined as the final TPR feature f TPR If the absolute value of the change in the first candidate TPR feature is not less than the predetermined threshold, then in operation 650, the apparatuses 100 and 300 for estimating blood pressure may be the second candidate TPR feature f TPR2 Determined as the final TPR feature f TPR.

[0089] If, in operation 620, the CO characteristic changes Δf CO The change Δf from the first candidate TPR feature TPR1 is not less than zero, then in operation 660, the apparatuses 100 and 300 for estimating blood pressure may select the second candidate TPR feature f TPR2 Determined as the final TPR feature f TPR .

[0090] Figure 7 is a flowchart illustrating yet another example of obtaining the TPR feature in operation 430 .

[0091] First, in operation 710, the apparatuses 100 and 300 for estimating blood pressure may extract a first candidate TPR feature f from a biosignal. TPR1 .

[0092] Then, in operation 720 , the apparatuses 100 and 300 for estimating blood pressure may determine whether a change direction of the CO feature is the same as a change direction of the first candidate TPR feature when compared with the calibration time.

[0093] Then, if the change directions are different, in operation 730, the apparatuses 100 and 300 for estimating blood pressure may select the first candidate TPR feature f TPR1 Determined as the final TPR feature f TPR and if the change directions are the same, then in operation 740, the apparatuses 100 and 300 for estimating blood pressure may extract a second candidate TPR feature f TPR2 , and in operation 750, the apparatuses 100 and 300 for estimating blood pressure may extract the second candidate TPR feature f TPR2 Determined as the final TPR feature f TPR .

[0094] Figure 8 is a flowchart illustrating yet another example of obtaining the TPR feature in operation 430 .

[0095] First, in operation 810, the apparatuses 100 and 300 for estimating blood pressure may extract a first candidate TPR feature f from a biosignal. TPR1 .

[0096] Then, in operation 820 , the apparatuses 100 and 300 for estimating blood pressure may determine whether a change direction of the CO feature is the same as a change direction of the first candidate TPR feature when compared with the calibration time.

[0097] Next, if the change directions are different, in operation 830 , the apparatuses 100 and 300 for estimating blood pressure may determine an absolute value of the change of the first candidate TPR feature |ΔfTPR1 Is |less than a predetermined threshold α|Δf CO |, and if the absolute value is less than a predetermined threshold, in operation 840, the apparatuses 100 and 300 for estimating blood pressure may select the first candidate TPR feature f TPR1 Determined as the final TPR feature f TPR If the absolute value is not less than the predetermined threshold, then in operation 850, the apparatuses 100 and 300 for estimating blood pressure may extract a second candidate TPR feature f TPR2 , and in operation 860, the apparatuses 100 and 300 for estimating blood pressure may TPR2 Determined as the final TPR feature f TPR .

[0098] If the change directions are the same in operation 820, the apparatuses 100 and 300 for estimating blood pressure may extract a third candidate TPR feature f in operation 870. TPR3 , and in operation 880, the apparatuses 100 and 300 for estimating blood pressure may extract the third candidate TPR feature f TPR3 Determined as the final TPR feature f TPR In particular, the third candidate TPR feature f TPR3 It can be the second candidate TPR feature f TPR2 The same value, or a value showing a relatively stable change compared to the second candidate TPR feature.

[0099] Figures 9 to 11 It is shown that Figure 1 The device 100 for estimating biological information or Figure 3 FIG. 3 is a block diagram of various structures of an electronic device of an apparatus 300 for estimating biological information.

[0100] The electronic device may include, for example, various types of wearable devices (e.g., smart watches, smart bands, smart glasses, smart headphones, smart rings, smart patches, and smart necklaces) and mobile devices (such as smart phones, tablet PCs, etc.), or household appliances or various Internet of Things (IoT) devices based on Internet of Things (IoT) technology (e.g., household IoT devices, etc.).

[0101] The electronic device may include a sensor device, a processor, an input device, a communication module, a camera module, an output device, a storage device, and a power supply module. All components of the electronic device may be integrally mounted in a specific device, or may be distributed in two or more devices. The sensor device may include a sensor (e.g., a PPG sensor) of the apparatuses 100 and 300 for estimating biometric information, and may also include additional sensors (e.g., a gyroscope sensor, a global positioning system (GPS), etc.).

[0102] The processor can execute a program stored in a storage device to control components connected to the processor, and the processor can perform various data processing or calculations including estimation of biological information (e.g., blood pressure). For example, the processor can evaluate the quality of a PPG signal measured by a PPG sensor of a sensor device, and can estimate blood pressure based on the evaluation result. Various embodiments for estimating blood pressure have been described above, so a detailed description thereof will be omitted. The processor may include a main processor (e.g., a central processing unit (CPU) or an application processor (AP), etc.) and an auxiliary processor (e.g., a graphics processing unit (GPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP), etc.), and the auxiliary processor may operate independently of the main processor or operate in conjunction with the main processor.

[0103] The input device may receive commands and / or data to be used by each component of the electronic device from a user, etc. The input device may include, for example, a microphone, a mouse, a keyboard, or a digital pen (eg, a stylus, etc.).

[0104] The communication module can support the establishment of a direct (e.g., wired) communication channel and / or a wireless communication channel between an electronic device and other electronic devices, a server, or a sensor device within a network environment, and perform communication via the established communication channel. The communication module may include one or more communication processors, which may operate independently of the processor and support direct communication and / or wireless communication. The communication module may include a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module, etc.) and / or a wired communication module (e.g., a local area network (LAN) communication module, a power line communication (PLC) module, etc.). These various types of communication modules may be integrated into a single chip, or may be implemented separately as multiple chips. The wireless communication module may identify and authenticate the electronic device in the communication network by using subscriber information (e.g., an international mobile subscriber identity (IMSI)), etc.) stored in a subscriber identification module.

[0105] A camera module can capture still images or moving images. A camera module may include a lens assembly having one or more lenses, an image sensor, an image signal processor, and / or a flash. The lens assembly included in the camera module may collect light emitted from an object to be imaged.

[0106] The output device may visually / non-visibly output data generated or processed by the electronic device (eg, estimated blood pressure value, health condition, warning, action, etc.) The output device may include a sound output device, a display device, an audio module, and / or a haptic module.

[0107] The sound output device can output sound signals to the outside of the electronic device. The sound output device may include a speaker and / or a receiver. The speaker can be used for general purposes (such as playing multimedia or recordings), and the receiver can be used for incoming calls. The receiver can be implemented separately from the speaker or as part of the speaker.

[0108] The display device can visually provide information to the outside of the electronic device. The display device may include, for example, a display, a holographic device, or a projector, and a control circuit system for controlling the device. The display device may include a touch circuit system suitable for detecting a touch and / or a sensor circuit system suitable for measuring the strength of the force caused by the touch (e.g., a pressure sensor, etc.).

[0109] The audio module can convert sound into an electrical signal and vice versa. The audio module can obtain sound via an input device, or can output sound via a sound output device and / or a speaker and / or earphone of another electronic device directly or wirelessly connected to the electronic device.

[0110] The haptic module may convert the electrical signal into mechanical stimulation (eg, vibration, motion, etc.) or electrical stimulation that can be recognized by the user through tactile or kinesthetic sense. The haptic module may include, for example, a motor, a piezoelectric element, and / or an electrical stimulator.

[0111] The storage device may store driving conditions required to drive the sensor device and various data required by other components of the electronic device. The various data may include, for example, software and input data and / or output data for commands associated with the software. The storage device may include volatile memory and / or non-volatile memory.

[0112] The power module can manage the power supplied to the electronic device. The power module can be implemented as part of a power management integrated circuit (PMIC), for example. The power module can include a battery, which can include a non-rechargeable primary battery, a rechargeable secondary battery, and / or a fuel cell.

[0113] Reference Figure 9 The electronic device may be implemented as a wristwatch wearable device 900 and may include a main body and a wristband. A display is provided on the front surface of the main body and may display various application screens including time information, received message information, etc. A sensor device 910 may be provided on the rear surface of the main body.

[0114] Reference Figure 10 , the electronic device may be implemented as a mobile device 1000 such as a smart phone.

[0115] Mobile device 1000 may include a housing and a display panel. The housing may form the exterior of mobile device 1000. The housing has a first surface, on which the display panel and cover glass may be sequentially disposed, with the display panel exposed to the outside through the cover glass. A sensor device 1010, a camera module, and / or an infrared sensor, etc. may be disposed on a second surface of the housing. A processor and various other components may be disposed within the housing.

[0116] Reference Figure 11 , the electronic device can be implemented as an ear-worn device 1100.

[0117] The ear-worn device 1100 may include a main body and an earband. A user may wear the ear-worn device 1100 by hanging the earband on the auricle. Depending on the shape of the ear-worn device 1100, the earband may be omitted. The main body may be placed in the external auditory canal. The sensor device 1110 may be installed in the main body. In addition, a processor may be provided in the main body, and blood pressure may be estimated by using the PPG signal measured by the sensor device 1110. Alternatively, the ear-worn device 1100 may estimate blood pressure by interacting with an external device. For example, the ear-worn device 1100 may transmit the pulse wave signal measured by the sensor device 1110 of the ear-worn device 1100 to an external device (e.g., a mobile device, a tablet PC, etc.) via a communication module provided in the main body, so that the processor of the external device can estimate the blood pressure, and the estimated blood pressure value may be output via a sound output module provided in the main body of the ear-worn device 1100.

[0118] Although not limited thereto, the exemplary embodiments may be implemented as computer-readable code on a computer-readable recording medium. A computer-readable recording medium is any data storage device that can store data that can be read by a computer system later. Examples of computer-readable recording media include read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage devices. The computer-readable recording medium may also be distributed on a networked computer system so that the computer-readable code is stored and executed in a distributed manner. In addition, the exemplary embodiments may be written as a computer program transmitted by a computer-readable transmission medium (such as a carrier wave) and received and implemented in a general-purpose digital computer or a special-purpose digital computer that executes the program. In addition, it should be understood that in the exemplary embodiments, one or more units of the above-mentioned devices and apparatus may include a circuit system, a processor, a microprocessor, etc., and may execute a computer program stored in a computer-readable medium.

[0119] The foregoing example embodiments are merely exemplary and should not be construed as limiting. The present teachings can be readily applied to other types of devices. Furthermore, the description of the example embodiments is intended to illustrate, not to limit, the scope of the claims, and will be readily apparent to those skilled in the art.

[0120] Many alternatives, modifications, and variations will be apparent.

Claims

1. A device for estimating blood pressure, the device comprising: a memory storing one or more instructions; and A processor configured to execute the one or more instructions to: Extracting a cardiac output CO feature, a first candidate total peripheral resistance TPR feature, and a second candidate TPR feature from a biological signal, wherein the biological signal is a photoplethysmography signal, Based on the change direction of the CO feature and the change direction of the first candidate TPR feature between the blood pressure measurement time and the calibration time, one of the first candidate TPR feature and the second candidate TPR feature is determined as the TPR feature, and Estimate blood pressure based on TPR features and CO features, wherein the CO feature is a feature value showing an increasing trend or a decreasing trend in proportion to the actual CO value, and the first candidate TPR feature and the second candidate TPR feature are feature values ​​showing an increasing trend or a decreasing trend in proportion to the actual TPR value, Among them, the second candidate TPR feature has a smaller change between the blood pressure measurement time and the calibration time than the first candidate TPR feature, In which, in response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, the processor is further configured to: determine the first candidate TPR feature as the TPR feature, and in response to the change direction of the CO feature being the same as the change direction of the first candidate TPR feature, the processor is further configured to: determine the second candidate TPR feature as the TPR feature, or In which, in response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, and the change of the first candidate TPR feature being less than a predetermined threshold, the processor is further configured to: determine the first candidate TPR feature as the TPR feature; in response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, and the change of the first candidate TPR feature being greater than or equal to the predetermined threshold, the processor is further configured to: determine the second candidate TPR feature as the TPR feature; and in response to the change direction of the CO feature being the same as the change direction of the first candidate TPR feature, the processor is further configured to: determine the second candidate TPR feature as the TPR feature.

2. The device according to claim 1, wherein The CO feature includes at least one of a heart rate and a ratio between an amplitude at a predetermined point and an area under a waveform of the biosignal.

3. The device according to claim 2, wherein The predetermined point includes a point at which the slope of the waveform of the biosignal in the cardiac systole phase is closest to zero.

4. The apparatus according to claim 1, wherein The first candidate TPR feature includes: a ratio between the amplitude of a reflected wave component and the amplitude of a propagated wave component of the biosignal, and Among them, the second candidate TPR feature includes: the ratio between the amplitude of the reflected wave component and "the amplitude at the inner dividing point between the position of the propagated wave component and the maximum amplitude position of the biological signal".

5. The device according to claim 4, wherein The processor is further configured to: obtain a second-order derivative signal of the biosignal; and detect positions of a first local minimum point and a second local minimum point of the second-order derivative signal as positions of a propagation wave component and a reflection wave component, respectively.

6. The apparatus according to claim 1, wherein The predetermined threshold value includes a value obtained by applying a predetermined weight to a change in the CO characteristic.

7. The apparatus according to claim 6, wherein The processor is also configured to: determining a change in the first candidate TPR feature by dividing the first candidate TPR feature value at the blood pressure measurement time by the reference TPR feature value at the calibration time to obtain a first division result, and by subtracting 1 from the first division result; and The change in the CO characteristic is determined by dividing the CO characteristic value at the blood pressure measurement time by the reference CO characteristic value at the calibration time to obtain a second division result, and by subtracting 1 from the second division result.

8. The apparatus according to any one of claims 1 to 7, wherein: The processor is further configured to estimate blood pressure by applying a predefined blood pressure estimation model to a result obtained by combining the CO feature and the TPR feature.

9. A computer-readable medium storing a program, wherein: When the program is executed by a processor, the processor executes a method for estimating blood pressure, the method comprising: measuring a biosignal from the subject, wherein the biosignal is a photoplethysmographic signal; Extracting cardiac output CO feature, first candidate total peripheral resistance TPR feature and second candidate TPR feature based on biological signals; determining one of the first candidate TPR feature and the second candidate TPR feature as the TPR feature based on a change direction of the CO feature and a change direction of the first candidate TPR feature between a blood pressure measurement time and a calibration time; and Estimate blood pressure based on TPR features and CO features, wherein the CO feature is a feature value showing an increasing trend or a decreasing trend in proportion to the actual CO value, and the first candidate TPR feature and the second candidate TPR feature are feature values ​​showing an increasing trend or a decreasing trend in proportion to the actual TPR value, Among them, the second candidate TPR feature has a smaller change between the blood pressure measurement time and the calibration time than the first candidate TPR feature, The step of determining the TPR feature includes: in response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, determining the first candidate TPR feature as the TPR feature, and in response to the change direction of the CO feature being the same as the change direction of the first candidate TPR feature, determining the second candidate TPR feature as the TPR feature, or The step of determining the TPR feature includes: in response to a change direction of the CO feature being different from a change direction of the first candidate TPR feature and a change of the first candidate TPR feature being less than a predetermined threshold, determining the first candidate TPR feature as the TPR feature; in response to a change direction of the CO feature being different from a change direction of the first candidate TPR feature and a change of the first candidate TPR feature being greater than or equal to the predetermined threshold, determining the second candidate TPR feature as the TPR feature; and in response to a change direction of the CO feature being the same as a change direction of the first candidate TPR feature, determining the second candidate TPR feature as the TPR feature.

10. The computer-readable medium of claim 9, wherein: The CO feature includes at least one of a heart rate and a ratio between an amplitude at a predetermined point and an area under a waveform of the biosignal.

11. The computer-readable medium of claim 10, wherein: The predetermined point includes a point at which the slope of the waveform of the biosignal in the cardiac systole phase is closest to zero.

12. The computer-readable medium of claim 9, wherein: The first candidate TPR feature includes: a ratio between the amplitude of a reflected wave component and the amplitude of a propagated wave component of the biosignal, and Among them, the second candidate TPR feature includes: the ratio between the amplitude of the reflected wave component and "the amplitude at the inner dividing point between the position of the propagated wave component and the maximum amplitude position of the biological signal".

13. The computer-readable medium of claim 9, wherein: The predetermined threshold value includes a value obtained by applying a predetermined weight to a change in the CO characteristic.

14. The computer-readable medium according to any one of claims 9 to 13, wherein: The step of estimating the blood pressure includes estimating the blood pressure by applying a predefined blood pressure estimation model to a result obtained by combining the CO feature and the TPR feature.

15. An electronic device comprising: main body; a photoplethysmographic sensor configured to: measure a photoplethysmographic signal from a subject; and The processor is configured to: Extract cardiac output CO features and first candidate total peripheral resistance TPR features from the photoplethysmography signal, Based on whether the change direction of the CO feature between the blood pressure measurement time and the calibration time is the same as the change direction of the first candidate TPR feature, one of the first candidate TPR feature and the second candidate TPR feature is determined as the TPR feature, and Estimate blood pressure based on TPR features and CO features, wherein the CO feature is a feature value showing an increasing trend or a decreasing trend in proportion to the actual CO value, and the first candidate TPR feature and the second candidate TPR feature are feature values ​​showing an increasing trend or a decreasing trend in proportion to the actual TPR value, Among them, the second candidate TPR feature has a smaller change between the blood pressure measurement time and the calibration time than the first candidate TPR feature, In which, in response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, the processor is further configured to: determine the first candidate TPR feature as the TPR feature, and in response to the change direction of the CO feature being the same as the change direction of the first candidate TPR feature, the processor is further configured to: extract the second candidate TPR feature as the TPR feature, or In which, in response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, and the change of the first candidate TPR feature being less than a predetermined threshold, the processor is further configured to: determine the first candidate TPR feature as the TPR feature; in response to the change direction of the CO feature being different from the change direction of the first candidate TPR feature, and the change of the first candidate TPR feature being greater than or equal to the predetermined threshold, the processor is further configured to: determine the second candidate TPR feature as the TPR feature; and in response to the change direction of the CO feature being the same as the change direction of the first candidate TPR feature, the processor is further configured to: determine the second candidate TPR feature as the TPR feature.

Images