Device and method for estimating blood pressure and wearable device

Abstract

Devices, methods, and wearable devices for estimating blood pressure are disclosed. A device for estimating blood pressure according to an exemplary embodiment of the present disclosure includes: a pulse wave sensor configured to measure a pulse wave signal from a subject; and a processor configured to: obtain a first feature and a heart rate based on the pulse wave signal, estimate a mean arterial pressure (MAP) and a pulse pressure (PP) based on the first feature and the heart rate, and estimate a first blood pressure based on the MAP and the PP.

Description

[0001] This application claims priority to Korean Patent Application No. 10-2021-0108068, filed on Aug. 17, 2021, with the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0002] One or more example embodiments relate to detecting a pulse wave signal from a subject and non-invasively estimating the blood pressure of the subject based on the pulse wave signal. Background Art

[0003] To address the aging population structure, rapidly increasing medical costs, and shortage of professional medical service personnel, research on IT-medical convergence technology that combines information technology (IT) and medical technology is currently underway. Specifically, the monitoring of the health status of the human body is not limited to a fixed location (such as a hospital), but is expanding to the field of mobile healthcare for monitoring the health status of users anytime and anywhere in daily life at home and in the office. Summary of the Invention

[0004] According to an aspect of the present disclosure, a device for estimating blood pressure may include: a pulse wave sensor configured to measure a pulse wave signal from an object; and a processor configured to: obtain a first feature and a heart rate based on the pulse wave signal, estimate a mean arterial pressure (MAP) and a pulse pressure (PP) based on the first feature and the heart rate, and estimate a first blood pressure based on the MAP and the PP.

[0005] The first feature may include a ratio between a first amplitude at a first time point and a second amplitude at a second time point in the pulse wave signal.

[0006] The processor may also be configured to: segment the pulse wave signal into a plurality of unit waveforms, and obtain the heart rate by using the plurality of unit waveforms.

[0007] The processor may also be configured to: normalize the heart rate and the first feature respectively based on a reference heart rate and a reference first feature obtained at a calibration time, obtain a change in the pulse wave signal based on the normalized heart rate and the normalized first feature, and obtain the MAP based on the change in the pulse wave signal and a reference MAP measured at the calibration time.

[0008] The processor may also be configured to: obtain the PP by using a reference blood pressure at the calibration time.

[0009] The processor may also be configured to: obtain the first blood pressure by combining the MAP and the PP.

[0010] The processor may also be configured to: obtain one or more second features based on the pulse wave signal, and estimate a second blood pressure by using the one or more second features.

[0011] The processor may also be configured to: normalize the one or more second features based on reference second features obtained at a calibration time, obtain a variation of the pulse wave signal based on the normalized one or more second features, and estimate a second blood pressure based on the variation of the pulse wave signal and a reference blood pressure at the calibration time.

[0012] The processor may also be configured to: determine the reliability of the estimated blood pressure based on the variation directions of the first blood pressure and the second blood pressure compared to the calibration time, and obtain a third blood pressure based on the determined reliability by using at least one of the first blood pressure and the second blood pressure.

[0013] The processor may also be configured to: when the determined reliability is high, obtain, as the third blood pressure, one of the first blood pressure and the second blood pressure that has a greater variation compared to the reference blood pressure measured at the calibration time, and the processor may also be configured to: when the determined reliability is low, obtain the average value of the first blood pressure and the second blood pressure as the third blood pressure.

[0014] If a first value obtained by subtracting the reference blood pressure from the first blood pressure and a second value obtained by subtracting the reference blood pressure from the second blood pressure have the same sign, the processor determines that the reliability is high; if not, the processor determines that the reliability is low.

[0015] According to another aspect of the present disclosure, a method for estimating blood pressure may include: measuring a pulse wave signal from an object; obtaining a first feature and a heart rate based on the pulse wave signal; estimating a mean arterial pressure (MAP) and a pulse pressure (PP) based on the first feature and the heart rate; and estimating a first blood pressure based on the MAP and the PP.

[0016] The step of estimating the MAP may include: normalizing the heart rate and the first feature respectively based on a reference heart rate and a reference first feature obtained at a calibration time; obtaining a variation of the pulse wave signal based on the normalized heart rate and the normalized first feature; and obtaining the MAP based on the variation of the pulse wave signal and the reference MAP measured at the calibration time.

[0017] The method may also include: obtaining one or more second features based on the pulse wave signal; and estimating a second blood pressure based on the one or more second features.

[0018] The steps of estimating the second blood pressure may include: normalizing the obtained one or more second features based on a reference second feature obtained at a calibration time; obtaining a change in a pulse wave signal based on the normalized one or more second features; and estimating the second blood pressure based on the change in the pulse wave signal and a reference blood pressure at the calibration time.

[0019] The method may further include: determining the reliability of the estimated blood pressure based on a direction of change in the first blood pressure and a direction of change in the second blood pressure compared to the calibration time; and obtaining a third blood pressure based on the reliability by using at least one of the first blood pressure and the second blood pressure.

[0020] The step of obtaining the third blood pressure may include: obtaining, in response to determining that the reliability is high, one of the first blood pressure and the second blood pressure that has a greater change compared to the reference blood pressure measured at the calibration time as the third blood pressure, and obtaining, in response to determining that the reliability is low, an average value of the first blood pressure and the second blood pressure as the third blood pressure.

[0021] The step of determining the reliability may include: determining that the reliability is high if a first value obtained by subtracting the reference blood pressure from the first blood pressure and a second value obtained by subtracting the reference blood pressure from the second blood pressure have the same sign, and determining that the reliability is low if not.

[0022] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium stores instructions that, when executed by a processor, configure the processor to perform a method of estimating blood pressure, the method including: measuring a pulse wave signal from an object; obtaining a first feature and a heart rate based on the pulse wave signal; estimating a mean arterial pressure (MAP) based on the first feature and the heart rate; and estimating a first blood pressure based on the MAP and a pulse pressure (PP).

[0023] According to another aspect of the present disclosure, a wearable device may include: a main body; and a band connected to the main body, wherein the main body may include: a photoplethysmography (PPG) sensor including a plurality of light sources configured to emit green light, red light, and infrared light and disposed on a rear surface of the main body to obtain a pulse wave signal by using the plurality of light sources; and a processor configured to: obtain calibration information including a reference pulse wave signal measured by the PPG sensor when a user of the wearable device is in a resting state and user profile information including the gender and age of the user; and estimate a cardiovascular state of the user based on the pulse wave signal at a measurement time of the cardiovascular state and the calibration information.

[0024] The processor may also be configured to: obtain a feature representing a change in the amplitude of a pulse wave signal between two time points; estimate a mean arterial pressure (MAP) and a pulse pressure (PP) based on the feature representing the change in the amplitude of the pulse wave signal; and estimate the cardiovascular state of a user based on the MAP, the PP, and calibration information. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0026] Figure 1 is a block diagram showing a device for estimating blood pressure according to an exemplary embodiment of the present disclosure;

[0027] Figure 2 is a diagram showing the principle of generating a component waveform included in a unit waveform of a pulse wave signal;

[0028] Figure 3 is a block diagram showing the configuration of a processor according to an exemplary embodiment of the present disclosure;

[0029] Figure 4 is a block diagram showing the configuration of a processor according to another exemplary embodiment of the present disclosure;

[0030] Figure 5 is a block diagram showing a device for estimating blood pressure according to another exemplary embodiment of the present disclosure;

[0031] Figure 6 is a flowchart showing a method for estimating blood pressure according to an exemplary embodiment of the present disclosure;

[0032] Figure 7 is a flowchart showing a method for estimating blood pressure according to another exemplary embodiment of the present disclosure;

[0033] Figure 8 is a diagram showing Figure 7 an example of obtaining a third blood pressure in;

[0034] Figure 9 is a diagram showing Figure 7 another example of obtaining a third blood pressure in; and

[0035] Figures 10 to 12 is a block diagram showing various structures of an electronic device including a device for estimating blood pressure. DETAILED DESCRIPTION

[0036] Exemplary embodiments will be described in more detail below with reference to the drawings.

[0037] In the following description, even though the same reference numerals are used for the same elements in different drawings, the same reference numerals are used for the same elements. Matters defined in the specification (such as detailed configurations and elements) are provided to assist in a comprehensive understanding of the exemplary embodiments. However, it is clear that the exemplary embodiments can be practiced without those specifically defined matters. In addition, since well-known functions or configurations would obscure the description with unnecessary details, they are not described.

[0038] When an expression such as "at least one of..." follows a list of elements, it modifies the entire list of elements and not a single element in the list. For example, the expression "at least one of a, b, and c" should be understood to include only a, only b, only c, both a and b, both a and c, both b and c, all of a, b, and c, or any variation of the foregoing examples.

[0039] It will be understood that although the terms "first", "second", etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. Any reference to the singular may include the plural unless otherwise expressly stated. Additionally, unless expressly described to the contrary, an expression such as "comprising" or "including" will be understood to imply the inclusion of the stated element but not the exclusion of any other element. Further, terms such as "unit" or "module" should be understood to be a unit for performing at least one function or operation, and the unit may be implemented as hardware, software, or a combination thereof.

[0040] Figure 1 is a block diagram showing a device for estimating blood pressure according to an exemplary embodiment of the present disclosure.

[0041] Various examples of the device for estimating blood pressure can be installed in an electronic device (such as a smart phone, a tablet PC, a desktop computer, a laptop computer, and a wearable device (including a wristwatch-type wearable device, a bracelet-type wearable device, a wristband-type wearable device, a ring-type wearable device, a glasses-type wearable device, a headband-type wearable device, etc.)).

[0042] Refer to Figure 1 , the device 100 for estimating blood pressure includes a pulse wave sensor 110 and a processor 120.

[0043] The pulse wave sensor 110 can measure a pulse wave signal from an object (including a photoplethysmogram (PPG) signal and / or an electrocardiogram (ECG)). The pulse wave sensor 110 can include a PPG sensor and an ECG sensor to estimate the blood pressure of a human body by analyzing the form of the pulse wave signal reflecting the cardiovascular state. Specifically, the object can be a body part that can be in contact with the pulse wave sensor 110, and can be, for example, a body part where the pulse wave can be easily measured. For example, the object can be a skin area adjacent to the radial artery on the wrist and a skin area through which venous blood or capillary blood of the human body passes. However, the object is not limited to the above examples, and can be a peripheral part of the human body where blood vessels are densely distributed (such as fingers, toes, etc.).

[0044] The pulse wave sensor 110 can include one or more light sources and one or more detectors. The one or more light sources are used to emit light toward the object, and the one or more detectors are used to detect the light scattered or reflected from the object or the light transmitted into the object after the light source emits light. The light source can include a light-emitting diode (LED), a laser diode (LD), a phosphor, etc. The multiple light sources can emit light of one or more wavelengths (for example, green wavelength, red wavelength, blue wavelength, and infrared wavelength). The detector can include one or more photodiodes, phototransistors (PTrs), image sensors (such as complementary metal oxide semiconductor (CMOS) image sensors), etc., but is not limited thereto.

[0045] The processor 120 can be electrically connected or functionally connected to the pulse wave sensor 110, and can control the pulse wave sensor 110 to acquire a pulse wave signal. When receiving the pulse wave signal from the pulse wave sensor 110, the processor 120 can perform preprocessing (such as removing noise from the received pulse wave signal). For example, the processor 120 can perform signal correction (such as filtering (for example, band-pass filtering between 0.4 Hz and 10 Hz), amplifying the pulse wave signal, converting the signal into a digital signal, smoothing, performing overall averaging on continuously measured pulse wave signals, etc.).

[0046] The processor 120 can estimate the blood pressure by analyzing the waveform of the pulse wave signal measured at the blood pressure estimation time. Hereinafter, unless otherwise indicated, the term "blood pressure" can represent any one or both of diastolic blood pressure (DBP) and systolic blood pressure (SBP).

[0047] For example, the processor 120 can obtain the pulse wave signals continuously measured during a predetermined period, and can divide the pulse wave signals into multiple unit waveforms according to the period of the pulse wave signals. The processor 120 can determine any one of the unit waveforms or a waveform generated by combining two or more of the multiple unit waveforms as a representative waveform, and can estimate the blood pressure by using the determined representative waveform.

[0048] For example, among multiple unit waveforms, the processor 120 may determine as the representative waveform "the unit waveform having the highest amplitude at the maximum point or the waveform formed by superimposing unit waveforms having an amplitude greater than or equal to a threshold at the maximum point". In another example, the processor 120 may determine as the representative waveform the overall average of the unit waveforms having the highest average value of similarity among multiple unit waveforms, or the overall average of the unit waveforms having an average value of similarity greater than or equal to a threshold among multiple unit waveforms. However, the representative waveform is not limited thereto. Specifically, various similarity calculation algorithms (including Euclidean distance, Manhattan distance, cosine distance, Mahalanobis distance, Jaccard coefficient, extended Jaccard coefficient, Pearson correlation coefficient, Spearman correlation coefficient, etc.) can be used.

[0049] Figure 2 is a diagram showing the principle of generating component waveforms included in the unit waveforms of the pulse wave signal.

[0050] Referring to Figure 2 , the pulse wave signal may be composed of one propagation wave and multiple reflection waves. Specifically, the pulse wave signal may be the sum of "propagation wave #1 that propagates from the heart to the peripheral part of the body or a branch point in a blood vessel through left ventricular ejection" and "reflection waves #2 and #3 that return from the peripheral part of the body or a branch point in a blood vessel". The propagation wave #1 is related to cardiac characteristics, and the reflection waves #2 and #3 are related to vascular characteristics. Generally, the propagation wave #1 generated by left ventricular ejection is mainly reflected from the renal artery and the iliac artery to generate the first reflection wave #2 and the second reflection wave #3. As described above, by dividing the unit waveform of the pulse wave signal into respective component waveforms #1, #2, and #3, and by analyzing the time points T1, T2, and T3 associated with the component waveforms #1, #2, and #3 and / or the amplitudes P1, P2, and P3 of the pulse wave signal, etc., the processor 120 can measure blood pressure.

[0051] The processor 120 can estimate the mean arterial pressure (MAP) and / or the pulse pressure (PP, also referred to as "pulse pressure") by analyzing the waveform of the pulse wave signal, and can estimate blood pressure based on the estimated MAP and / or PP.

[0052] Generally, as shown in Equation 1 below, the change in MAP is usually proportional to the cardiac output (CO) and the total peripheral resistance (TPR).

[0053] [Equation 1]

[0054] ΔMAP = CO × TPR

[0055] Here, ΔMAP represents the difference in MAP between the left ventricle and the right atrium, where the MAP of the right atrium is typically in the range of 3 mmHg to 5 mmHg, such that the MAP in the right atrium is similar to the MAP in the left ventricle or the MAP in the upper arm. If the absolute actual CO value and TPR value are known, the MAP can be obtained from the aorta or the upper arm. However, it may be difficult to estimate the absolute CO and TPR values based on the pulse wave signal.

[0056] Accordingly, the processor 120 can extract features related to cardiac output (CO) (hereinafter referred to as "CO features") and features related to total peripheral resistance (TPR) (hereinafter referred to as "TPR features") from the pulse wave signal, and can obtain the MAP by using the CO features and the TPR features. Here, the CO feature can be a feature value showing an increasing or decreasing trend proportional to the actual CO value, where, in a non-steady state, when the actual TPR value does not change significantly, the actual CO value tends to increase or decrease relatively. In addition, the TPR feature can be a feature value showing an increasing / decreasing trend proportional to the actual TPR value, where, in a non-steady state, when the actual CO value does not change significantly, the actual TPR value tends to increase or decrease relatively.

[0057] Hereinafter, reference will be made to Figure 3 and Figure 4 to describe various examples of estimating blood pressure by the processor 120.

[0058] Figure 3 is a block diagram showing the configuration of a processor according to an exemplary embodiment of the present disclosure.

[0059] Referring to Figure 3 , the processor 300 according to an exemplary embodiment of the present disclosure includes a feature extractor 310, a MAP estimator 320, a PP estimator 330, and a blood pressure estimator 340.

[0060] The feature extractor 310 can analyze the representative waveform of the pulse wave signal to extract CO features and TPR features for estimating the MAP.

[0061] For example, as described above, the feature extractor 310 can obtain the heart rate (HR) by analyzing the period of the unit waveform of the pulse wave signal continuously measured during a predetermined period, and can determine the obtained heart rate as the CO feature.

[0062] The feature extractor 310 can obtain the value SVTPR obtained by multiplying the stroke volume (SV) by the TPR (for example, the ratio between the amplitude at the first time point and the amplitude at the second time point in the representative waveform of the pulse wave signal) as the TPR feature. The first time point and the second time point can be associated with the time point T1 of the propagation wave #1 and the time point T2 of the reflected wave #2 in the component waveforms #1, #2, and #3 described above, respectively. Specifically, the TPR feature can represent the ratio (for example, P2 / P1) between the amplitude P1 corresponding to the time point T1 of the propagation wave #1 and the amplitude P2 corresponding to the time point T2 of the reflected wave #2. In addition, the first time point and the second time point can be time points predefined to be commonly applied to multiple users. However, the time points are not limited to this, and personalized time points reflecting user characteristics can also be used.

[0063] The examples of the CO feature and the TPR feature are described above, but the features are not limited to this. For example, the feature extractor 310 can obtain the values obtained by using an appropriate combination of one or two or more of the following as the CO feature and the TPR feature: the time points and amplitudes of the component waveforms of the pulse wave signal, the shape of the waveform of the pulse wave signal, the time points and amplitudes at the maximum point of the pulse wave signal, the time points and amplitudes at the minimum point of the pulse wave signal, the area of the entire region of the waveform of the pulse wave signal, the area of a partial region (for example, the systolic region, the diastolic region) of the waveform of the pulse wave signal, and the elapsed time of the pulse wave signal.

[0064] The MAP estimator 320 can obtain the CO feature and the TPR feature from the feature extractor 310, and can estimate the MAP based on the CO feature and the TPR feature. For example, the MAP estimator 320 can normalize the extracted CO feature and TPR feature by using the CO feature and TPR feature obtained at the calibration time (for example, in the resting state), and can obtain the change in MAP by linearly or nonlinearly combining the normalized values. In addition, the MAP estimator 320 can obtain the MAP based on the change in MAP and the reference MAP measured at the calibration time.

[0065] The following Equation 2 is an example of normalizing the CO feature and the TPR feature.

[0066] [Equation 2]

[0067]

[0068]

[0069] Here, Δfeat_CO represents the normalized value of the CO feature, i.e., the change in the CO feature compared to the calibration time; feat_CO_est represents the CO feature at the blood pressure estimation time; feat_CO_cal represents the CO feature at the calibration time; Δfeat_TPR represents the normalized value of the TPR feature, i.e., the change in the TPR feature compared to the calibration time; feat_TPR_est represents the TPR feature at the blood pressure estimation time; feat_TPR_cal represents the TPR feature at the calibration time.

[0070] The following Equation 3 is an example of calculating MAP.

[0071] [Equation 3]

[0072] ΔΔMAP = f(Δfeat_CO, Δfeat_TPR)

[0073] MAP est = ΔMAP + MAP cal

[0074] Here, ΔMAP represents the change in MAP; Δfeat_CO and Δfeat_TPR respectively represent the normalized value of the CO feature and the normalized value of the TPR feature; f(Δfeat_CO, Δfeat_TPR) represents a predetermined linear / nonlinear function for combining the normalized value of the CO feature and the normalized value of the TPR feature; MAP est represents the estimated MAP value; MAP cal represents the reference MAP at the calibration time.

[0075] The PP estimator 330 can estimate the pulse pressure at the current time. For example, the PP estimator 330 can use the reference pulse pressure at the calibration time as the pulse pressure at the current time as it is. For example, the PP estimator 330 can obtain the pulse pressure at the current time by using the reference blood pressure (i.e., the reference systolic blood pressure and the reference diastolic blood pressure) measured at the calibration time. Specifically, the reference blood pressure can be the blood pressure value measured by a device (such as a cuff blood pressure monitor) or by the device 100 at the calibration time when the user is at rest. The following Equation 4 is an example of obtaining the pulse pressure.

[0076] [Equation 4]

[0077] PP est = SBP cal - DBP cal

[0078] Herein, SBP cal and DBP cal respectively represent the systolic blood pressure and the diastolic blood pressure at the calibration time; PP estrepresents an estimated pulse pressure value at the current time, and a reference pulse pressure value (SBP cal -DBP cal ) at the calibration time is available as the estimated pulse pressure value at the current time.

[0079] In another example, the PP estimator 330 can estimate the pulse pressure at the current time by using features related to pulse pressure (hereinafter referred to as PP features) extracted from the pulse wave signal. For example, the PP estimator 330 can normalize the PP features by using the PP features at the calibration time, and can obtain the change in pulse pressure by using the normalized values. Additionally, the PP estimator 330 can estimate the pulse pressure at the current time by combining the obtained change in pulse pressure and the reference pulse pressure at the calibration time using a predefined equation.

[0080] In this case, the feature extractor 310 can extract a combination of one or two or more of the above-described various information items that can be obtained by analyzing the waveform of the pulse wave signal as PP features. For example, the feature extractor 310 can extract the ratio between the area of the systolic phase and the area of the diastolic phase in the representative waveform of the pulse wave signal, or the ratio between the time interval of the systolic phase and the time interval of the diastolic phase as PP features, but the PP features are not limited thereto. In this case, the systolic phase can represent the region from the starting point of the representative waveform to the point of the dicrotic notch (DN), and the diastolic phase can represent the region from the point of the dicrotic notch (DN) to the end point.

[0081] The blood pressure estimator 340 can estimate the blood pressure by using the obtained MAP and PP. For example, the blood pressure estimator 340 can independently obtain the diastolic blood pressure and the systolic blood pressure by applying MAP and PP to diastolic blood pressure equations and systolic blood pressure equations defined as linear / nonlinear equations. Equation 5 below is an example of the diastolic blood pressure equation and the systolic blood pressure equation.

[0082] [Equation 5]

[0083] SBP est = MAP est +(1 - α)PP est

[0084] DBP est = MAP est - αPP est

[0085] Here, SBP est and DBP est represent the estimated SBP value and DBP value respectively; MAP est and PP est represent the estimated MAP value and PP value respectively; α is a predefined value.

[0086] Figure 4 It is a block diagram showing the configuration of a processor according to another exemplary embodiment of the present disclosure.

[0087] In this embodiment, two or more blood pressure values can be estimated by using two or more algorithm modules, and a final blood pressure value can be obtained based on the change direction of each estimated blood pressure value.

[0088] Referring to Figure 4 , the processor 400 may include a first algorithm module 410, a second algorithm module 420, and a combiner 430. The first algorithm module 410 is configured to obtain a first blood pressure, the second algorithm module 420 is configured to obtain a second blood pressure, and the combiner 430 is configured to obtain a third blood pressure by using the first blood pressure and the second blood pressure.

[0089] The first algorithm module 410 may include a feature extractor 411, a MAP estimator 412, a PP estimator 413, and a first blood pressure estimator 414. The corresponding components of the first algorithm module 410 are described above with reference to Figure 3 , such that their detailed descriptions will be omitted. In one example, the first blood pressure estimator 414 may obtain a first blood pressure (SBP1 / DBP1).

[0090] The second algorithm module 420 may include a feature extractor 421 and a second blood pressure estimator 422. The second algorithm module 420 may use a feature extraction method and a blood pressure estimation method different from those of the first algorithm module 410. The first algorithm module 410 is configured to estimate blood pressure based on the analysis of MAP and PP of the pulse wave signal. The blood pressure estimation result of the first algorithm module 410 can be used to evaluate the reliability of the blood pressure estimation result of the second algorithm module 420, and / or combined with the blood pressure estimation result of the second algorithm module 420 to improve the accuracy of blood pressure estimation.

[0091] The feature extractor 421 can extract various characteristic points by using the pulse wave signal, the derivative signal and the integral signal of the pulse wave signal, etc. For example, by analyzing the waveform of the pulse wave signal, the feature extractor 421 can obtain various information (such as the shape of the waveform, the time point and amplitude at the maximum point of the pulse wave signal, the time point and amplitude at the minimum point of the pulse wave signal, the area of the entire region of the pulse wave signal, the area of a partial region (e.g., the systolic region, the diastolic region) of the pulse wave signal, the elapsed time of the pulse wave signal, etc.). In addition, by obtaining, for example, the second derivative signal of the pulse wave signal and by detecting the local minimum point of the second derivative signal, the feature extractor 421 can obtain the time and amplitude information associated with the component waveforms that make up the unit waveform of the pulse wave signal.

[0092] When obtaining various information from the pulse wave signal, the feature extractor 421 may obtain one or more features related to blood pressure by using a combination of one or two or more of the obtained information. Specifically, the feature extractor 421 may obtain the same features of DBP and SBP, or may obtain different features of each of DBP and SBP. For example, the feature extractor 421 may extract the ratio between the amplitude at the maximum point of the pulse wave among the component waveforms of the unit waveform constituting the pulse wave signal and the area of the pulse wave signal, and / or the ratio between the amplitude at the point of the first reflected wave (e.g., the maximum point) and the amplitude at the point of the propagation wave (e.g., the maximum point), etc. as features. However, these features are merely exemplary.

[0093] The second blood pressure estimator 422 may estimate the second blood pressure by using the features obtained by the feature extractor 421.

[0094] For example, the second blood pressure estimator 422 may normalize the features at the current estimation time by using the features at the calibration time as shown in Equation 2 above, may obtain the changes in the second blood pressure (DBP change and SBP change) by using the normalized values, and may obtain the second blood pressure (DBP2 and SBP2) by combining the changes in the second blood pressure and the reference blood pressure (reference DBP and reference SBP) at the calibration time. The following Equation 6 is an example of the equation for calculating the changes in the second blood pressure and the second blood pressure, but is not limited thereto.

[0095] [Equation 6]

[0096] ΔBP = f(Δfeat_1,..., Δfeat_n)

[0097] BP est = ΔBP + BP cal

[0098] Here, Δfeat_1,..., and Δfeatn represent the normalized values of n features, where n is a natural number greater than 1; f(Δfeat_1,..., and Δfeatn) is a predefined linear / nonlinear equation for combining the normalized values of n features, and may be defined differently for each of DBP and SBP; ΔBP represents the change in the second blood pressure; BP est represents the estimated second blood pressure value; BP cal represents the reference blood pressure at the calibration time.

[0099] In another example, the second blood pressure estimator 422 may obtain the SBP in the second blood pressure based on the change in SBP as described above, and may obtain the DBP based on the change in MAP. For example, the second blood pressure estimator 422 may normalize the features of SBP by using the features of SBP at the calibration time, and may obtain the change in SBP and SBP by combining the features as shown in Equation 6 above.

[0100] In addition, the second blood pressure estimator 422 may normalize the MAP-related features (hereinafter referred to as MAP features) and PP features extracted by the feature extractor 421 by using the MAP features and PP features at the calibration time, and may obtain the change in MAP and the change in PP by combining the normalized values. Specifically, the MAP features may include, for example, the ratio between the maximum amplitude value of the pulse wave signal and the area of the entire region or a partial region (e.g., the systolic region or the diastolic region), and / or the ratio between the amplitude at the point of the reflected wave (e.g., the maximum point) and the amplitude at the point of the propagating wave (e.g., the maximum point), etc., but the MAP features are not limited thereto. The PP features may include the ratio between the area of the systolic region and the area of the diastolic region, and / or the ratio between the time interval of the systolic region and the time interval of the diastolic region, etc., but the PP features are not limited thereto. As shown in Equation 7 below, the second blood pressure estimator 422 may estimate the DBP by combining the obtained change in MAP, the change in PP, and the reference DBP. However, Equation 7 is merely an example.

[0101] [Equation 7]

[0102] DBP est =(ΔMAP - αΔPP)+DBP cal

[0103] Here, DBP est represents the estimated DBP value; ΔMAP represents the change in MAP; ΔPP represents the change in PP; DBP cal represents the reference DBP at the calibration time; α is a predetermined value.

[0104] The combiner 430 may obtain a third blood pressure (e.g., SBP3 / DBP3) by using the first blood pressure and the second blood pressure. For example, the combiner 430 may determine the reliability of the estimated blood pressure by using the first blood pressure and the second blood pressure, and may obtain the third blood pressure based on the determined reliability by using a combination of any one or two or more of the first blood pressure and the second blood pressure.

[0105] For example, the combiner 430 may determine the reliability based on the change directions of the first blood pressure and the second blood pressure. For example, if the first blood pressure and the second blood pressure show the same change direction (i.e., if the first value obtained by subtracting the reference blood pressure from the first blood pressure and the second value obtained by subtracting the reference blood pressure from the second blood pressure have the same sign), the combiner 430 may determine that the reliability is high; if the change directions are different (i.e., if the first value and the second value have different signs), the combiner 430 may determine that the reliability is low.

[0106] In another example, in addition to the change direction of the blood pressure, the combiner 430 may also determine the reliability based on the magnitude of the blood pressure change. For example, even when the reliability is determined to be low based on different change directions of the blood pressure, if there is a small difference between the magnitude of the first value (the absolute value of the first value) and the magnitude of the second value (the absolute value of the second value) (i.e., if the difference between the magnitude of the first value and the magnitude of the second value is less than or equal to a predetermined threshold), the combiner 430 may determine the reliability to be high again.

[0107] The combiner 430 may obtain a third blood pressure based on the reliability according to a predetermined criterion. For example, if the reliability is high, the combiner 430 may obtain the one with the larger change among the first blood pressure and the second blood pressure as the third blood pressure; if the reliability is low, the combiner 430 may obtain the statistical value (e.g., the average value) of the first blood pressure and the second blood pressure as the third blood pressure. Optionally, if the reliability is high, the combiner 430 may obtain the first blood pressure (or the second blood pressure) as the third blood pressure; if the reliability is low, the combiner 430 may obtain the second blood pressure (or the first blood pressure) as the third blood pressure value. Optionally, if the reliability is high, the combiner 430 may obtain the first blood pressure (or the second blood pressure) as the third blood pressure; if the reliability is low, the combiner 430 may obtain the statistical value (e.g., the average value) of the first blood pressure and the second blood pressure as the third blood pressure. Optionally, if the reliability is high, the combiner 430 may obtain the one with the larger change among the first blood pressure and the second blood pressure as the third blood pressure; if the reliability is low, the combiner 430 may obtain any one of the first blood pressure and the second blood pressure as the third blood pressure. Optionally, if the reliability is high, the combiner 430 may obtain the one with the larger change among the first blood pressure and the second blood pressure as the third blood pressure; if the reliability is low, the combiner 430 may obtain the one with the smaller change among the first blood pressure and the second blood pressure as the third blood pressure. However, these examples may be variously changed.

[0108] The combiner 430 may exclude blood pressure values with small variations from the determination of reliability. For example, if the magnitude of the second value (or the first value) is less than a predetermined magnitude, the combiner 430 may exclude the second value (or the first value), and may obtain the first blood pressure (or the second blood pressure) as the third blood pressure. Specifically, if the remaining blood pressure value after excluding any one of the first blood pressure and the second blood pressure is not the blood pressure value estimated by the predetermined main algorithm module, or if both the first blood pressure and the second blood pressure are less than the predetermined magnitude, the combiner 430 may guide the user to measure the blood pressure again or perform calibration again.

[0109] The above description gives an example of estimating two blood pressure values by using two algorithm modules 410 and 420 and estimating the final blood pressure based on the two blood pressure values. However, the present disclosure is not limited thereto.

[0110] For example, the processor 400 may include three or more predefined algorithm modules and a combiner 430. Each of the three or more algorithm modules may estimate blood pressure by using its own predefined method. The combiner 430 may determine the reliability based on three or more directions of the estimated blood pressure change, and may obtain the final blood pressure based on the reliability according to a predefined criterion. For example, when three blood pressure values are estimated, if all three blood pressure values show the same change direction, the combiner 430 may determine that the reliability is high, and may select the blood pressure value with the largest change as the final blood pressure. Alternatively, if two of the three blood pressure values show the same change direction, the combiner 430 may determine that the reliability is medium, and by applying a predetermined weight to the two blood pressure values showing the same change direction, the combiner 430 may calculate the average value of all blood pressure values, or may only calculate the average value of the two blood pressure values showing the same change direction to determine the final blood pressure. There may be various other criteria for determining reliability according to the number of algorithm modules and criteria for determining blood pressure based on reliability.

[0111] The first algorithm module 410, the second algorithm module 420, and the combiner 430 of the processor 400 may process the pulse wave signal to estimate the blood pressure in real time while the pulse wave sensor 110 continuously measures the pulse wave signal from the user.

[0112] Figure 5 is a block diagram showing a device for estimating blood pressure according to another exemplary embodiment of the present disclosure.

[0113] Referring to Figure 5 , the device 500 for estimating blood pressure includes a pulse wave sensor 110, a processor 120, a communication interface 510, an output interface 520, and a storage device 530. The pulse wave sensor 110 and the processor 120 have been described in detail above, so their descriptions will be omitted.

[0114] The communication interface 510 may be electrically or functionally connected to the processor 120 and may communicate with an external electronic device under the control of the processor 120 by using various communication technologies to send and receive necessary data (e.g., reference blood pressure, various blood pressure estimation equations, blood pressure estimation results, etc.). The external electronic device may include a smart phone, a tablet PC, a desktop computer, a laptop computer, a wearable device, etc., but is not limited thereto. The communication technologies may include 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, 3G communication, 4G communication, and 5G communication, etc. However, the communication technologies are not limited thereto.

[0115] The output interface 520 may output the processing results of the pulse wave sensor 110 and / or the processor 120. The output interface 520 may provide information to the user through various visual / non-visual methods by using a visual output module (including a display), an audio output module (such as a speaker), or a tactile module using vibration, touch, etc.

[0116] The storage device 530 may store the data required by the pulse wave sensor 110 and / or the processor 120, and / or the processing results of the pulse wave sensor 110 and / or the processor 120. For example, the storage device 530 may store blood pressure estimation equations, criteria for determining reliability, user characteristics (e.g., gender, age, health status, etc.), pulse wave signals obtained during calibration, features and reference blood pressure, and pulse wave signals, features, and estimated blood pressure values generated at the blood pressure estimation time, etc. Information on user characteristics may be input by the user (e.g., by using a screen touch-based user interface or an input device (such as a keyboard)) to be stored in the storage device 530. The information on user characteristics may also be referred to as user profile information.

[0117] The storage device 530 may include at least one storage medium such as a flash memory type, a hard disk type, a multimedia card micro memory, a card type memory (e.g., SD memory, XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read only memory (ROM), an electrically erasable programmable read only memory (EEPROM), a programmable read only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk, etc., but is not limited thereto.

[0118] Figure 6 is a flowchart showing a method for estimating blood pressure according to an exemplary embodiment of the present disclosure. Figure 6 The method of Figure 1 and Figure 5Example of a method for estimating blood pressure performed by a device for estimating blood pressure.

[0119] First, in operation 610, a device for estimating blood pressure may measure a pulse wave signal from an object in response to a request for estimating blood pressure.

[0120] Then, in operation 620, a device for estimating blood pressure may obtain a heart rate and TPR feature by analyzing the waveform of the pulse wave signal. For example, a device for estimating blood pressure may obtain a plurality of unit waveforms by dividing the waveform of the pulse wave signal continuously measured during a predetermined period into a plurality of cycles, and may obtain a heart rate by using the obtained plurality of unit waveforms. In addition, a device for estimating blood pressure may obtain at least one representative waveform by using the plurality of unit waveforms, and may analyze the obtained representative waveform to obtain, for example, a ratio between an amplitude corresponding to a time point of a reflected wave (e.g., a time point corresponding to a maximum point) and an amplitude corresponding to a time point of a propagating wave (e.g., a time point corresponding to a maximum point) as a TPR feature. Specifically, the time point of the reflected wave and the time point of the propagating wave may be predefined fixed time points to be commonly applied to a plurality of users, but the exemplary embodiments of the present disclosure are not limited thereto.

[0121] Subsequently, in operation 630, a device for estimating blood pressure may estimate MAP by using the obtained heart rate and TPR feature. For example, by normalizing the extracted heart rate and TPR feature and by combining the normalized values, a device for estimating blood pressure may obtain a change in MAP, and may obtain MAP based on the obtained change in MAP and a reference MAP measured at a calibration time.

[0122] In addition, in operation 640, a device for estimating blood pressure may obtain PP based on a reference blood pressure. For example, as described above, a device for estimating blood pressure may use a reference PP at a calibration time as a PP at a current time. However, PP is not limited thereto, and a device for estimating blood pressure may obtain a PP feature by using the pulse wave signal measured in operation 610, and may estimate PP by using the obtained PP feature.

[0123] Next, in operation 650, a device for estimating blood pressure may estimate blood pressure by using MAP and PP. For example, a device for estimating blood pressure may independently obtain DBP and SBP based on MAP and PP by using a predefined equation for each of DBP and SBP.

[0124] Then, in operation 660, a device for estimating blood pressure may output an estimated blood pressure value by using various output devices (such as a display, a speaker, a tactile device, etc.) to provide the estimated value to a user.

[0125] Figure 7 It is a flowchart showing a method for estimating blood pressure according to another exemplary embodiment of the present disclosure. Figure 7 The method is an example of a method for estimating blood pressure performed by the device for estimating blood pressure described in detail above Figure 1 or Figure 2 and will be briefly described below.

[0126] First, in operation 711, the device for estimating blood pressure may measure a pulse wave signal from an object in response to a request for estimating blood pressure.

[0127] Then, the device for estimating blood pressure may obtain a first feature related to TPR and a heart rate related to CO from the measured pulse wave signal in operation 712, and may estimate MAP based on the obtained first feature and heart rate in operation 713. As described above, by normalizing the extracted heart rate and TPR features using the heart rate and TPR features at the calibration time and by combining the normalized values, the device for estimating blood pressure may obtain a change in MAP, and may obtain MAP by combining the obtained change in MAP and the reference MAP measured at the calibration time.

[0128] In addition, the device for estimating blood pressure may obtain PP based on the reference blood pressure in operation 714, and may estimate a first blood pressure by using the obtained PP and the MAP obtained in operation 713 in operation 715. As described above, the device for estimating blood pressure may obtain the first blood pressure based on MAP and PP by using a predefined first blood pressure estimation equation.

[0129] Additionally, the device for estimating blood pressure may obtain a second feature from the obtained pulse wave signal in operation 716, and may obtain a second blood pressure by using the second feature in operation 717. Specifically, as described above, by analyzing the waveform of the pulse wave signal, the device for estimating blood pressure may obtain various characteristic point information, and may obtain one or more second features related to blood pressure by using one or a combination of two or more of the obtained characteristic point information. In addition, as described above, the device for estimating blood pressure may normalize the second feature using the second feature at the calibration time to obtain a change in the second feature, and may obtain the second blood pressure based on the change in the second feature by using a predefined second blood pressure estimation equation.

[0130] Next, the device for estimating blood pressure may obtain a third blood pressure based on the first blood pressure and the second blood pressure in operation 718, and may output the obtained third blood pressure as the final blood pressure in operation 719. For example, the device for estimating blood pressure may evaluate the reliability of the estimated blood pressure based on the change directions of the first blood pressure and the second blood pressure compared to the calibration time, and may obtain the third blood pressure based on the first blood pressure and the second blood pressure according to the reliability evaluation result.

[0131] Figure 8 is a flowchart showing an example of obtaining the third blood pressure in operation 718 in Figure 7 the.

[0132] Referring to Figure 8 , the device for estimating blood pressure may obtain a first value ΔBP1 by subtracting the reference blood pressure BP at the calibration time from the first blood pressure BP1 in operation 811. The first value ΔBP1 represents the change of the first blood pressure compared to the calibration time, and the device for estimating blood pressure may obtain a second value ΔBP2 by subtracting the reference blood pressure BP from the second blood pressure BP2 in operation 812. The second value ΔBP2 represents the change of the second blood pressure compared to the calibration time. cal and, cal thereby obtaining a second value ΔBP2, where the second value ΔBP2 represents the change of the second blood pressure compared to the calibration time.

[0133] Then, in operation 813, by multiplying the first value ΔBP1 by the second value ΔBP2 and determining whether the resulting value is greater than 0, the device for estimating blood pressure may evaluate the reliability of the estimated blood pressure.

[0134] Subsequently, when determining, if the value obtained by multiplying the first value ΔBP1 by the second value ΔBP2 is greater than 0, such that the first blood pressure and the second blood pressure show the same change direction, the device for estimating blood pressure may evaluate that the reliability is high, and may compare the magnitude (|ΔBP1|) of the first value with the magnitude (|ΔBP2|) of the second value in operation 814 to determine the one of the first value and the second value that is greater than the other as the third blood pressure in operations 815 and 816. On the contrary, when determining, if the value obtained by multiplying the first value ΔBP1 by the second value ΔBP2 in operation 813 is not greater than 0, such that the first blood pressure and the second blood pressure show different change directions, then in operation 817, the device for estimating blood pressure may evaluate that the reliability is low, and may determine the average value of the first blood pressure BP1 and the second blood pressure BP2 as the third blood pressure. However, the example of determining the third blood pressure based on the reliability evaluation result is not limited to this.

[0135] Figure 9 is a flowchart showing another example of obtaining the third blood pressure in operation 718 in Figure 7 the.

[0136] Referring to Figure 9, a device for estimating blood pressure can obtain a first value ΔBP1 in operation 911 by subtracting a reference blood pressure BP at a calibration time from a first blood pressure BP1, and can obtain a second value ΔBP2 in operation 912 by subtracting the reference blood pressure BP from a second blood pressure BP2. cal Then, in operation 913, by multiplying the first value ΔBP1 by the second value ΔBP2 and determining whether the resulting value is greater than 0, the device for estimating blood pressure can evaluate the reliability of the estimated blood pressure. cal Subsequently, if the value obtained by multiplying the first value ΔBP1 by the second value ΔBP2 is greater than 0 (i.e., if the first blood pressure and the second blood pressure show the same direction of change), the device for estimating blood pressure can evaluate that the reliability is high, and can compare the magnitude (|ΔBP1|) of the first value with the magnitude (|ΔBP2|) of the second value in operation 914 to determine, in operations 915 and 916, the one of the first value BP1 and the second value BP2 that is greater than the other as a third blood pressure.

[0137] If the value obtained by multiplying the first value ΔBP1 by the second value ΔBP2 in operation 913 is not greater than 0, then in operation 917, the device for estimating blood pressure can determine whether the difference between the magnitude (|ΔBP1|) of the first value and the magnitude (|ΔBP2|) of the second value (i.e., the absolute value of the value obtained by subtracting the magnitude (|ΔBP2|) of the second value from the magnitude (|ΔBP1|) of the first value) is less than or equal to a preset threshold TH. When making the determination in operation 917, if the difference between the magnitude (|ΔBP1|) of the first value and the magnitude (|ΔBP2|) of the second value is not large, the device for estimating blood pressure can evaluate that the reliability is high and can perform the operations in operation 914 and the operations after the operations in operation 914; if the difference between the magnitude (|ΔBP1|) of the first value and the magnitude (|ΔBP2|) of the second value is large, the device for estimating blood pressure can evaluate that the reliability is low and can determine the average value of the first blood pressure BP1 and the second blood pressure BP2 as the third blood pressure in operation 918.

[0138]

[0139]

[0140] Figures 10 to 12 Figure 1 Figure 5 is a block diagram showing various structures of an electronic device of a device 100 or 500 for estimating blood pressure including or

[0141]

[0141] ​The electronic device may include, for example, various types of wearable devices (e.g., smart watches, smart wristbands, smart glasses, smart earphones, smart rings, smart patches, and smart necklaces) and mobile devices (such as smart phones, tablet PCs, etc.) or home appliances or various Internet of Things (IoT) devices based on IoT technology (e.g., home IoT devices, etc.).

[0142] 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 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 pulse wave sensor of devices 100 and 500 for estimating blood pressure, and may also include additional sensors (such as a gyro sensor, a Global Positioning System (GPS), etc.).

[0143] The processor may execute a program stored in the storage device to control components connected to the processor, and may perform various data processing or calculations (including the estimation of blood pressure). 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 in combination with the main processor.

[0144] The input device may receive commands and / or data to be used by each component of the electronic device from a user or the like. The input device may include, for example, a microphone, a mouse, a keyboard, or a digital pen (e.g., a stylus, etc.).

[0145] The communication module may support establishing a direct (e.g., wired) communication channel and / or a wireless communication channel between the electronic device and other electronic devices, servers, or sensor devices within a network environment, and perform communication via the established communication channel. The communication module may include one or more communication processors, and the one or more communication processors 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 separately implemented as multiple chips. The wireless communication module may identify and authenticate the electronic device in a communication network by using user information (e.g., an International Mobile Subscriber Identity (IMSI), etc.) stored in a user identification module.

[0146] The camera module can capture still images or moving images. The 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 can collect light emitted from a subject to be photographed.

[0147] The output device can output data generated or processed by the electronic device visually / non-visually. The output device may include a sound output device, a display device, an audio module, and / or a haptic module.

[0148] The sound output device can output a sound signal 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 playing a recording), and the receiver can be used for incoming calls. The receiver can be implemented separately from the speaker or as part of the speaker.

[0149] 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 for controlling the device. The display device may include a touch circuit suitable for detecting a touch and / or a sensor circuit suitable for measuring the intensity of a force caused by the touch (e.g., a pressure sensor, etc.).

[0150] 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 headphones of another electronic device, and the other electronic device is directly or wirelessly connected to the electronic device.

[0151] The haptic module can convert an electrical signal into a mechanical stimulus (e.g., vibration, movement, etc.) or an electrical stimulus that can be recognized by the user through touch or kinesthesia. The haptic module may include, for example, a motor, a piezoelectric element, and / or an electrical stimulator.

[0152] The storage device can 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 related to commands for input data and / or output data. The storage device may include a volatile memory and / or a non-volatile memory.

[0153] The power module can manage the power supplied to the electronic device. The power module can be implemented as part of, for example, a power management integrated circuit (PMIC). The power module may include a battery, and the battery may include a non-rechargeable primary battery, a rechargeable secondary battery, and / or a fuel cell.

[0154] Refer to Figure 10, the electronic device can be implemented as a wristwatch wearable device 1000, and may include a main body and a wristband. A display is provided on the front surface of the main body, and can display various application screens (including time information, received message information, etc.). The sensor device 1010 can be provided on the rear surface and / or side surface of the main body. For example, a PPG sensor can be provided on the rear surface, and an ECG sensor can be provided on the side surface of the main body.

[0155] Referring to Figure 11 , the electronic device can be implemented as a mobile device 1100 (such as a smart phone).

[0156] The mobile device 1100 may include a housing and a display panel. The housing can form the appearance of the mobile device 1100. The housing has a first surface, on which the display panel and a cover glass can be sequentially provided, and the display panel can be exposed to the outside through the cover glass. The sensor device 1110, a camera module, and / or an infrared sensor, etc. can be provided on the second surface of the housing. A processor and various other components can be provided in the housing.

[0157] Referring to Figure 12 , the electronic device can be implemented as an ear-worn device 1200.

[0158] The ear-worn device 1200 may include a main body and an ear strap. The user can wear the ear-worn device 1200 by hanging the ear strap on the auricle. Depending on the shape of the ear-worn device 1200, the ear strap can be omitted. The main body can be inserted into the external auditory canal. The sensor device 1210 can be installed in the main body. In addition, a processor can be provided in the main body, and can estimate blood pressure by using the pulse wave signal measured by the sensor device 1210. Optionally, the ear-worn device 1200 can estimate blood pressure by interacting with an external device. For example, the ear-worn device 1200 can send the pulse wave signal measured by the sensor device 1210 of the ear-worn device 1200 to an external device (such as a smart phone, a tablet PC, etc.) through a communication module provided in the main body, so that the processor of the external device can estimate blood pressure, and the estimated blood pressure value can be output through a sound output module provided in the main body of the ear-worn device 1200.

[0159] This disclosure can be implemented as computer-readable code written on a computer-readable recording medium. The computer-readable recording medium can be any type of recording device that stores data in a computer-readable manner.

[0160] Although not limited thereto, example 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-ROMs, magnetic tapes, floppy disks, and optical data storage devices. The computer-readable recording medium may also be distributed over networked computer systems so that the computer-readable code is stored and executed in a distributed manner. In addition, example embodiments may be written as a computer program that is transmitted through a computer-readable transmission medium such as a carrier wave and received and executed in a general-purpose or special-purpose digital computer that executes the program. Further, it should be understood that in example embodiments, one or more units of the above-described devices and apparatuses may include circuits, processors, microprocessors, etc., and may execute a computer program stored in a computer-readable medium.

[0161] The foregoing exemplary embodiments are merely exemplary and should not be construed as limiting. The present teachings can be readily applied to other types of devices. Further, the description of the exemplary embodiments is intended to be illustrative and not to limit the scope of the claims, and many alternatives, modifications, and variations will be apparent to those skilled in the art.

Claims

1. A device for estimating blood pressure, the device comprising: A pulse wave sensor configured to measure a pulse wave signal from an object; And A processor configured to: Obtain a first feature and a heart rate based on the pulse wave signal, Estimate the mean arterial pressure based on the first feature and the heart rate, and Estimate a first blood pressure based on the mean arterial pressure and the pulse pressure, Wherein the processor is further configured to: obtain one or more second features based on the pulse wave signal, and estimate a second blood pressure by using the one or more second features, Wherein the processor is further configured to: determine the reliability of the estimated blood pressure based on the change directions of the first blood pressure and the second blood pressure compared with a calibration time, and obtain a third blood pressure based on the determined reliability by using at least one of the first blood pressure and the second blood pressure, Wherein the first feature includes a ratio between a first amplitude at a first time point and a second amplitude at a second time point in the pulse wave signal, and the one or more second features include a ratio between an amplitude at a maximum point of the pulse wave among component waveforms of a unit waveform constituting the pulse wave signal and an area of the pulse wave signal, and / or a ratio between an amplitude at a point of a first reflected wave and an amplitude at a point of a propagated wave.

2. The device according to claim 1, wherein The processor is further configured to: segment the pulse wave signal into a plurality of unit waveforms, and obtain the heart rate by using the plurality of unit waveforms.

3. The device according to claim 1, wherein The processor is further configured to: Normalize the heart rate and the first feature respectively based on a reference heart rate and a reference first feature obtained at the calibration time, Obtain a change in the mean arterial pressure based on the normalized heart rate and the normalized first feature, and Obtain the mean arterial pressure based on the change in the mean arterial pressure and a reference mean arterial pressure measured at the calibration time.

4. The device according to claim 1, wherein The processor is further configured to: obtain the pulse pressure by using a reference blood pressure at the calibration time.

5. The device according to claim 1, wherein, The processor is further configured to: Normalize the one or more second features based on a reference second feature obtained at the calibration time, Obtain a change in the second blood pressure based on the normalized one or more second features, and Estimate the second blood pressure based on the change in the second blood pressure and the reference blood pressure at the calibration time.

6. The apparatus according to claim 1, wherein The processor is further configured to: when determining that the reliability is high, obtain, as the third blood pressure, one of the first blood pressure and the second blood pressure that has a greater change compared with the reference blood pressure measured at the calibration time, The processor is further configured to: when determining that the reliability is low, obtain the average value of the first blood pressure and the second blood pressure as the third blood pressure.

7. The device according to claim 1, wherein If a first value obtained by subtracting the reference blood pressure from the first blood pressure and a second value obtained by subtracting the reference blood pressure from the second blood pressure have the same sign, the processor determines that the reliability is high; if not, the processor determines that the reliability is low.

8. A method for estimating blood pressure, the method comprising: Measuring a pulse wave signal from an object; Obtaining a first feature and a heart rate based on the pulse wave signal; Estimating the mean arterial pressure based on the first feature and the heart rate; And Estimating a first blood pressure based on the mean arterial pressure and the pulse pressure, Wherein, the method further includes: obtaining one or more second features based on the pulse wave signal, and estimating a second blood pressure based on the one or more second features. Wherein, the method further includes: determining the reliability of the estimated blood pressure based on the change directions of the first blood pressure and the second blood pressure compared with the calibration time, and obtaining a third blood pressure based on the reliability by using at least one of the first blood pressure and the second blood pressure. Wherein, the first feature includes the ratio between the first amplitude at the first time point and the second amplitude at the second time point in the pulse wave signal, and the one or more second features include the ratio between the amplitude at the maximum point of the pulse wave among the component waveforms of the unit waveform constituting the pulse wave signal and the area of the pulse wave signal, and / or the ratio between the amplitude at the point of the first reflected wave and the amplitude at the point of the propagated wave.

9. The method according to claim 8, wherein, The step of estimating the mean arterial pressure includes: Normalizing the heart rate and the first feature respectively based on the reference heart rate and the reference first feature obtained at the calibration time; Obtaining the change of the mean arterial pressure based on the normalized heart rate and the normalized first feature; and Obtaining the mean arterial pressure based on the change of the mean arterial pressure and the reference mean arterial pressure measured at the calibration time.

10. The method according to claim 8, wherein, The step of estimating the second blood pressure includes: Normalizing the obtained one or more second features based on the reference second feature obtained at the calibration time; Obtaining the change of the second blood pressure based on the normalized one or more second features; and Estimating the second blood pressure based on the change of the second blood pressure and the reference blood pressure at the calibration time.

11. The method according to claim 8, wherein The step of obtaining the third blood pressure includes: in response to determining that the reliability is high, obtaining, as the third blood pressure, one of the first blood pressure and the second blood pressure that has a greater change compared with the reference blood pressure measured at the calibration time, and in response to determining that the reliability is low, obtaining the average value of the first blood pressure and the second blood pressure as the third blood pressure.

12. The method according to claim 8, wherein The step of determining the reliability includes: determining that the reliability is high if a first value obtained by subtracting the reference blood pressure from the first blood pressure and a second value obtained by subtracting the reference blood pressure from the second blood pressure have the same sign, and determining that the reliability is low if not.

13. A wearable device including the device for estimating blood pressure according to any one of claims 1-7.

Images