# US 11,432,775 B2 · Apparatus and method for estimating blood pressure > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,432,775 B2 - Document ID: US11432775B2 - Status: Granted - Kind: B2 - Application number: 16/589,260 - Filed: 2019-10-01 - Published: 2020-06-25 - Granted: 2022-09-06 - Earliest claimed: 2018-12-21 - Assignees: Samsung Electronics Co., Ltd.; University of Maryland, College Park - Applicants: Samsung Electronics Co., Ltd.; University of Maryland, College Park - Inventors: Dae Geun Jang; Peyman Yousefian; Jin-Oh Hann; Ui Kun Kwon; Youn Ho Kim; Sungtae Shin - Web page: https://patentgrep.com/patent/US11432775B2 ## CPC - A61B 5/7278: {Artificial waveform generation or derivation, e.g. synthesizing signals from measured signals} - A61B 5/02125: {of pulse wave propagation time} - A61B 5/1102: {Ballistocardiography} - A61B 5/352: Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval - A61B 5/681: {Wristwatch-type devices} - A61B 5/7246: {using correlation, e.g. template matching or determination of similarity} - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - A61B 5/7289: {Retrospective gating, i.e. associating measured signals or images with a physiological event after the actual measurement or image acquisition, e.g. by simultaneously recording an additional physiological signal during the measurement or image acquisition} - A61B 5/0261: {using optical means, e.g. infrared light} - A61B 5/7267: {involving training the classification device} - A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor} - A61B 2560/0223: of calibration, e.g. protocols for calibrating sensors - A61B 2562/0219: Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) ## Abstract An apparatus for estimating blood pressure includes: a ballistocardiogram (BCG) sensor configured to measure a limb BCG signal from a user; and a processor configured to obtain blood pressure-related features from the measured limb BCG signal, according to sensing characteristics of the BCG sensor, and estimate a blood pressure of the user based on the obtained blood pressure-related features. ## Claims ### Claim 1 An apparatus for estimating blood pressure, the apparatus comprising: a ballistocardiogram (BCG) sensor comprising an acceleration sensor configured to measure a limb BCG signal from a user; and a processor configured to: based on a sensor type and a measurement position of the BCG sensor, at a time when the limb BCG signal is measured, corresponding to the acceleration sensor and a wrist of the user, respectively, calibrate a reference limb BCG prediction model based on a parameter that is set according to mass of an arm with the wrist, to obtain a personalized limb BCG prediction model, convert, by using the personalized limb BCG prediction model that is personalized based on the sensor type and the measurement position of the BCG sensor at the time when the limb BCG signal is measured, the measured limb BCG signal to a converted limb BCG signal, in which a noise effect caused by the sensor type and the measurement position of the BCG sensor is removed, obtain blood pressure-related features from the converted limb BCG signal, and estimate a blood pressure of the user based on the blood pressure-related features. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein the processor is further configured to extract the blood pressure-related features by performing beat gating on the converted limb BCG signal. ### Claim 3 (depends on 2) The apparatus of claim 2, wherein the processor is further configured to extract a representative signal from the converted limb BCG signal by performing the beat gating, and extract the blood pressure-related features from the extracted representative signal. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein the processor is further configured to obtain the blood pressure-related features from the converted limb BCG signal based on a correlation between a whole-body BCG signal and the converted limb BCG signal. ### Claim 5 (depends on 4) The apparatus of claim 4, wherein the processor is further configured to, based on the sensor type and the measurement position of the BCG sensor corresponding to the acceleration sensor and the wrist of the user, obtain a J-K interval of the converted limb BCG signal as a feature related to a pulse transit time (PTT), a K-wave amplitude of the converted limb BCG signal as a feature related to aortic pulse pressure (PP), and a K-L amplitude of the converted limb BCG signal as a feature related to a distal pulse pressure (PP). ### Claim 6 (depends on 1) The apparatus of claim 1, wherein the processor is further configured to estimate the blood pressure based on the blood pressure-related features by using at least one of a linear or nonlinear regression analysis model, a neural network model, and a deep learning model. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein the processor is further configured to estimate a blood pressure variation based on the blood pressure-related features, and estimate the blood pressure based on the estimated blood pressure variation and a reference blood pressure measured at a calibration time by an external blood pressure measuring device. ### Claim 8 (depends on 1) The apparatus of claim 1, further comprising: a pulse wave sensor configured to measure a pulse wave signal from the user, wherein the processor is further configured to estimate the blood pressure of the user based on the blood pressure-related features and the pulse wave signal. ### Claim 9 (depends on 8) The apparatus of claim 8, wherein the processor is further configured to: obtain a pulse transit time (PTT) based on a time interval between a predetermined characteristic point of the pulse wave signal and a predetermined characteristic point extracted from the limb BCG signal; and estimate the blood pressure based on the PTT and the blood pressure-related features. ### Claim 10 A method of estimating blood pressure, the method comprising: measuring a limb ballistocardiogram (BCG) signal from a user, by a BCG sensor comprising an acceleration sensor; based on a sensor type and a measurement position of the BCG sensor, at a time when the limb BCG signal is measured, corresponding to the acceleration sensor and a wrist of the user, respectively, calibrate a reference limb BCG prediction model based on a parameter that is set according to mass of an arm with the wrist, to obtain a personalized limb BCG prediction model; converting, by using the personalized limb BCG prediction model that is personalized based on the sensor type and the measurement position of the BCG sensor at the time when the limb BCG signal is measured, the measured limb BCG signal to a converted limb BCG signal, in which a noise effect caused by the sensor type and the measurement position of the BCG sensor is removed; obtaining blood pressure-related features from the converted limb BCG signal; and estimating a blood pressure of the user based on the blood pressure-related features. ### Claim 11 (depends on 10) The method of claim 10, further comprising extracting characteristic points by performing beat gating on the converted limb BCG signal. ### Claim 12 (depends on 11) The method of claim 11, wherein the extracting the characteristic points comprises extracting a representative signal from the converted limb BCG signal by performing the beat gating, and extracting the characteristic points from the extracted representative signal. ### Claim 13 (depends on 10) The method of claim 10, wherein the obtaining the blood pressure-related features comprises obtaining the blood pressure-related features from the converted limb BCG signal based on a correlation between a whole-body BCG signal and the converted limb BCG signal. ### Claim 14 (depends on 13) The method of claim 13, wherein the obtaining the blood pressure-related features comprises, based on the sensor type and the measurement position of the BCG sensor corresponding to the acceleration sensor and the wrist of the user, respectively, obtaining a J-K interval of the converted limb BCG signal as a feature related to a pulse transit time (PTT), a K-wave amplitude of the converted limb BCG signal as a feature related to aortic pulse pressure (PP), and a K-L amplitude of the converted limb BCG signal as a feature related to distal pulse pressure (PP). ### Claim 15 (depends on 10) The method of claim 10, wherein the estimating the blood pressure comprises estimating the blood pressure based on the blood pressure-related features by using at least one of a linear or nonlinear regression analysis model, a neural network model, and a deep learning model.