Apparatus and method for estimating blood pressure
Apparatus and method for estimating blood pressure, including a plurality of sensors; and at least one processor configured to: determine situation information and posture information prior to estimation of blood pressure of a user based on data acquired using the plurality of sensors, select a cardiovascular feature from among a plurality of predetermined cardiovascular features based on the situation information and the posture information, generate a blood pressure estimation model based on the cardiovascular feature, the situation information, and the posture information, and estimate the blood pressure of the user based on the generated blood pressure estimation model.
1 . An apparatus for estimating blood pressure, the apparatus comprising:
a plurality of sensors comprising a photoplethysmogram (PPG) sensor; and
at least one processor configured to:
determine situation information and posture information of a user based on data acquired by the plurality of sensors,
select a cardiac output (CO) feature and a total peripheral resistance (TPR) feature from among a plurality of predetermined CO features and TPR features based on the situation information and the posture information,
generate a blood pressure estimation model based on the CO feature and the TPR feature, the situation information, and the posture information, and
estimate a blood pressure of the user based on the generated blood pressure estimation model,
wherein the situation information comprises information about at least one of a mental activity, a physical activity, and a surrounding environment of the user, and
wherein the posture information indicates at least one of a sitting posture, a supine posture, and a standing posture,
wherein the at least one processor is further configured to determine a modeling coefficient of the blood pressure estimation model based on the situation information and the posture information.
2 . The apparatus of claim 1 , wherein the plurality of sensors comprises at least one of an acceleration sensor, an angular velocity sensor, a geomagnetic sensor, a gyroscopic sensor, a temperature sensor, and a pressure sensor.
3 . The apparatus of claim 2 , wherein the at least one processor is further configured to:
extract a feature value corresponding to the CO feature and the TPR feature,
apply the extracted feature value to the generated blood pressure estimation model, and
estimate the blood pressure of the user by linearly combining a reference blood pressure with a result obtained from the generated blood pressure estimation model.
4 . The apparatus of claim 3 , wherein the reference blood pressure is measured by a cuff at a calibration time.
5 . The apparatus of claim 2 , wherein the PPG sensor comprises a light source configured to emit light to an object, and a detector configured to detect the light after the light is reflected by or scattered from the object.
6 . The apparatus of claim 1 , further comprising an output interface configured to provide the estimated blood pressure to the user visually or non-visually.
7 . A method of estimating blood pressure, the method comprising:
acquiring data from among a plurality of sensors, the plurality of sensors comprising a photoplethysmogram (PPG) sensor;
determining situation information and posture information of a user based on the acquired data by the plurality of sensors;
selecting a cardiac output (CO) feature and a total peripheral resistance (TPR) feature from among a plurality of predetermined CO features and TPR features based on the situation information and the posture information;
generating a blood pressure estimation model based on the CO feature, the TPR feature, the cardiovascular feature, the situation information, and the posture information; and
estimating a blood pressure of the user based on the generated blood pressure estimation model,
wherein the situation information comprises information about at least one of a mental activity, a physical activity, and a surrounding environment of the user, and
wherein the posture information indicates at least one of a sitting posture, a supine posture, and a standing posture,
wherein the generating of the blood pressure estimation model comprises determining a modeling coefficient of the blood pressure estimation model based on the situation information and the posture information.
8 . The method of claim 7 , wherein the estimating of the blood pressure comprises:
extracting a feature value corresponding to the selected cardiac output (CO) feature and total peripheral resistance (TPR) feature;
applying the extracted feature value to the generated blood pressure estimation model, and
estimating the blood pressure of the user by linearly combining a reference blood pressure with a result obtained from the generated blood pressure estimation model.
9 . The method of claim 8 , wherein the reference blood pressure is measured by a cuff at a calibration time.
10 . The method of claim 7 , further comprising outputting the estimated blood pressure to the user visually or non-visually.