Apparatus and method for estimating blood glucose

Patent metadata

Field	Value
Publication number	US-2020187835-A1
Application number	US-201916506656-A
Country	US
Kind code	A1
Filing date	Jul 9, 2019
Priority date	Dec 13, 2018
Publication date	Jun 18, 2020
Grant date	—

Abstract

An apparatus for estimating blood glucose using a photoplethysmography (PPG) signal is provided. The apparatus for estimating blood glucose includes: a pulse wave sensor configured to obtain a pulse wave signal from an object; and a processor configured to obtain at least two points from a waveform of the pulse wave signal, to extract a feature based on time values of the obtained at least two points, and to estimate blood glucose based on the extracted feature.

First claim

What is claimed is:

1 . An apparatus for estimating blood glucose, the apparatus comprising:
a pulse wave sensor configured to obtain a pulse wave signal from an object; and a processor configured to obtain at least two points from a waveform of the pulse wave signal, to extract a feature based on time values of the obtained at least two points, and to estimate blood glucose based on the extracted feature.

2 . The apparatus of claim 1 , wherein the pulse wave sensor comprises:
at least one light source configured to emit light of at least one wavelength onto the object; and at least one detector configured to detect the light of the at least one wavelength that is scattered or reflected from the object.

3 . The apparatus of claim 2 , wherein the at least one wavelength comprise at least one of a red wavelength, a green wavelength, a blue wavelength, and an infrared wavelength.

4 . The apparatus of claim 1 , wherein the processor is further configured to obtain a first point in a systolic interval of the pulse wave signal, and a second point in a diastolic interval of the pulse wave signal.

5 . The apparatus of claim 4 , wherein the processor is further configured to extract, as the feature, at least one of a difference between a time value of the first point and a time value of the second point, and a time difference ratio obtained by dividing the difference by the time value of the first point or the time value of the second point.

6 . The apparatus of claim 4 , wherein the processor is further configured to obtain a component of a pulse waveform forming the waveform of the pulse wave signal, and obtain the first point and the second point based on the obtained component of the pulse waveform.

7 . The apparatus of claim 6 , wherein the processor is further configured to detect a local minimum point from a waveform of a differential signal, obtained by performing differentiation on the pulse wave signal, and obtain at least one of a time value and a signal strength of the detected local minimum point as the component of the pulse waveform.

8 . The apparatus of claim 1 , wherein the feature comprises at least one of pulse rate variability, heart rate variability, heart rate, pulse rate, arterial stiffness, blood pressure, perfusion index, and pulsatile volume.

9 . The apparatus of claim 1 , wherein the processor is further configured to estimate the blood glucose by applying a blood glucose estimation model to the extracted feature.

10 . The apparatus of claim 1 , further comprising an output interface configured to provide a processing result of the processor.

11 . A method of estimating blood glucose, the method comprising:
obtaining a pulse wave signal from an object; obtaining at least two points from the pulse wave signal; extracting a feature based on time values of the obtained at least two points; and estimating blood glucose based on the extracted feature.

12 . The method of claim 11 , wherein the obtaining the at least two points comprises obtaining a first point in a systolic interval of the pulse wave signal, and a second point in a diastolic interval of the pulse wave signal.

13 . The method of claim 12 , wherein the extracting the feature comprises extracting, as the feature, at least one of a difference between a time value of the first point and a time value of the second point, and a time difference ratio obtained by dividing the difference by the time value of the first point or the time value of the second point.

14 . The method of claim 12 , wherein the obtaining the at least two points further comprises obtaining a component of a pulse waveform forming a waveform of the pulse wave signal, and obtaining the first point and the second point based on the obtained component of the pulse waveform.

15 . The method of claim 14 , wherein the obtaining the at least two points further comprises detecting a local minimum point from a waveform of a differential signal, obtained by performing differentiation on the pulse wave signal, and obtaining at least one of a time value and a signal strength of the detected local minimum point as the component of the pulse waveform.

16 . An apparatus for estimating blood glucose, the apparatus comprising:
a pulse wave sensor configured to obtain a pulse wave signal from an object; a metabolism information obtainer configured to obtain metabolism information of a user; and a processor configured to estimate a first blood glucose value based on a feature extracted from the pulse wave signal, to estimate a second blood glucose value based on the metabolism information, and to estimate a final blood glucose value based on the first blood glucose value and the second blood glucose value.

17 . The apparatus of claim 16 , wherein the processor is further configured to extract the feature based on time values of at least two points of a waveform of the pulse wave signal.

18 . The apparatus of claim 16 , wherein the processor is further configured to:
obtain a first point in a systolic interval of a waveform of the pulse wave signal, and a second point in a diastolic interval of the waveform of the pulse wave signal; and extract, as the feature, at least one of a difference between a time value of the first point and a time value of the second point, and a time difference ratio obtained by dividing the difference by the time value of the first point or the time value of the second point.

19 . The apparatus of claim 18 , wherein the processor is further configured to obtain a component of a pulse waveform forming the waveform of the pulse wave signal, and obtain the first point and the second point based on the obtained component of the pulse waveform.

20 . The apparatus of claim 16 , wherein the metabolism information obtainer is further configured to obtain the metabolism information based on at least one of sensor information and user input information, the sensor information being received from at least one of the pulse wave sensor, a food intake sensor, and a blood glucose sensor.

21 . The apparatus of claim 20 , wherein the metabolism information obtainer is further configured to obtain the metabolism information by applying at least one of the sensor information and the user input information to a metabolism model.

22 . The apparatus of claim 20 , wherein the metabolism information comprises at least one of a blood glucose change rate over time, a blood glucose variation, and a probability or a frequency of stages of blood glucose change.

23 . The apparatus of claim 16 , wherein the processor is further configured to estimate the second blood glucose value based on a calibration blood glucose value obtained by a blood glucose sensor, and the metabolism information.

24 . The apparatus of claim 16 , wherein the processor is further configured to estimate the final blood glucose value by applying a blood glucose estimation model to the first blood glucose value and the second blood glucose value.

25 . The apparatus of claim 24 , wherein the blood glucose estimation model is predefined based on at least one of weighted summation, Kalman Filter, regression, and Artificial Intelligence.

26 . A method of estimating blood glucose, the method comprising:
obtaining a pulse wave signal from an object; obtaining metabolism information of a user; extracting a feature from the pulse wave signal; estimatin

Assignees

• Samsung Electronics Co Ltd

Inventors

• Choi Ka Ram
• Bae Sang Kon
• Lee So Young
• Yoon Seung Keun

Classifications

• A61B5/02007

  Evaluating blood vessel condition, e.g. elasticity, compliance · CPC title

• A61B5/021

  Measuring pressure in heart or blood vessels · CPC title

• A61B5/742

  using visual displays (displays for heart-related electrical signals, e.g. ECG, A61B5/339) · CPC title

• A61B5/14532 Primary

  for measuring glucose, e.g. by tissue impedance measurement · CPC title

• A61B5/0059

  using light, e.g. diagnosis by transillumination, diascopy, fluorescence (photoacoustic A61B5/0093; optical measurement of heart rate A61B5/02416; optical measurement of blood flow A61B5/0261; optical measurement of analytes A61B5/1455) · CPC title