Method and electronic device for cuff-less blood pressure (BP) measurement
AssigneeSamsung Electronics Co., Ltd.
InventorsAman Gaurav, Maram Maheedhar, Vijay Narayan Tiwari, Rangavittal Narayanan
Life of this patent
Estimating the term…
Abstract
A method and an electronic device for measuring blood pressure are provided. The method includes illuminating, by a PPG sensor included in the electronic device, skin of a user and measuring a PPG signal based on an illumination absorption by the skin. Further, the method also includes extracting, by the electronic device, a plurality of parameters from the PPG signal, wherein the parameters may comprise PPG features, Heart Rate Variability (HRV) features, Acceleration Plethysmograph (APG) features, and non-linear features. The method also includes estimating, by the electronic device, the BP based on the extracted plurality of parameters.
Claims18
An electronic device for measuring Blood Pressure (BP), the electronic device comprising:
- a photoplethysmogram (PPG) sensor configured to illuminate skin of a user and measure a PPG signal based on illumination absorption by the skin;
- and
- a processor configured to:
- extract a plurality of parameters from the PPG signal, wherein the extracted plurality of parameters are derived from features of the PPG signal,
- estimate a diastolic blood pressure (DBP) based on the extracted plurality of parameters, and
- estimate a systolic blood pressure (SBP) based on the estimated DBP and the extracted plurality of parameters,
- wherein the processor is further configured to:
- estimate the DBP by using an artificial neural network (ANN) to output the DBP, and
- estimate the SBP, based on the DBP output from the ANN that is fed back into the ANN.
A method for measuring Blood Pressure (BP), the method comprising:
- illuminating, by a photoplethysmogram (PPG) sensor, skin of a user;
- receiving, by the PPG sensor, a PPG signal based on illumination absorption by the skin;
- extracting, by a processor, a plurality of parameters from the PPG signal, wherein the extracted plurality of parameters are derived from features of the PPG signal;
- estimating a diastolic blood pressure (DBP) based on the extracted plurality of parameters;
- and
- estimating a systolic blood pressure (SBP) based on the estimated DBP and the extracted plurality of parameters,
- wherein the estimating the DBP comprises estimating the DBP by using an artificial neural network (ANN) to output the DBP, and
- wherein the estimating the SBP comprises estimating the SBP, based on the DBP output from the ANN that is fed back into the ANN.
A device for measuring blood pressure comprising:
- a photoplethysmogram (PPG) sensor configured to illuminate skin of a user and measure a PPG signal based on illumination absorption by the skin;
- and
- a processor that receives data from the PPG sensor;
- wherein the processor is configured to:
- extract magnitude and temporal parameters from the PPG signal;
- determine a derivative of the PPG signal;
- extract non-linear features from the PPG signal;
- extract heart rate variability features from the PPG signal by computing a plurality of consecutive peak intervals of the PPG signal;
- and
- estimate blood pressure based on the magnitude and temporal parameters, the derivative, the non-linear features, and the heart rate variability features, wherein the magnitude and temporal parameters, the derivative, the non-linear features, and the heart rate variability features are extracted from the PPG signal,
- wherein the processor is further configured to:
- estimate a diastolic blood pressure (DBP) based on the magnitude and temporal parameters, the derivative, the non-linear features, and the heart rate variability features, and
- estimate a systolic blood pressure (SBP) based on the estimated DBP and the magnitude and temporal parameters, the derivative, the non-linear features, and the heart rate variability features,
- wherein the processor is further configured to:
- estimate the DBP by using an artificial neural network (ANN) to output the DBP, and
- estimate the SBP, based on the DBP output from the ANN that is fed back into the ANN.
Dependencies are inferred from the claim text.