Vital signs monitoring system

• US 10,624,580 B2
• Filed: 04/08/2016
• Issued: 04/21/2020
• Est. Priority Date: 04/09/2015
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: DeGroot, Koen Theo Johan, Bonomi, Alberto Giovanni
• Primary Examiner(s): Layno, Carl H
• Assistant Examiner(s): Lau, Michael J
• Application Number:
  US15/564,593
• Publication Number:
  US 20180078202A1
• Time in Patent Office: 1,474 Days
• Field of Search: 600301
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/4866 Evaluating metabolism A61B5/083 takes precedence
• CPC Class Codes: A61B 5/681 Wristwatch-type devices

Abstract

A vital signs monitoring system comprises a processing unit (300) for estimating an activity energy expenditure (AEE), a first activity energy expenditure determining unit (320) for determining a first activity energy expenditure (AEEHR) based on heart rate data (HR), a second activity energy expenditure determining unit (330) for determining a second activity energy expenditure (AEEAC) based on motion data (AC), and a weighting unit (340) for determining a first and second weighting factor (wHR, wAC) based on a first and second probability relating to a high exertion (hH) and relating to a low exertion (hL), and activity energy expenditure calculating unit (350) for computing an overall activity energy expenditure (AEEO) based on the first activity energy expenditure (AEEHR) weighted by the first weighting factor (wHR) and on the second activity energy expenditure (AEEAC) weighted by the second weighting factor (wAC).

Claims

1. A vital signs monitoring system, comprising:

a processing unit configured to estimate an activity energy expenditure of a user, said processing unit comprises;

a first input interface configured to receive heart rate data from at least one heart rate sensor configured to measure or determine a heart rate of a user,

a second input interface configured to receive motion or acceleration data from at least one motion sensor configured to detect motion or acceleration data of a user,

a first activity energy expenditure determining unit configured to determine a first activity energy expenditure based on heart rate data received via the first input interface,

a second activity energy expenditure determining unit configured to determine a second activity energy expenditure based on motion or acceleration data received via the second input interface;

a probability estimating unit configured to calculate a first probability of a high exertion of a user and a second probability of a low exertion of the user wherein the probability estimating unit comprises;

a feature set unit configured to extract a feature set F based on at least one of the heart rate data and/or the motion or acceleration data, wherein the feature set F serve as predictors of a high or low exertion,

a classification unit configured to classify an exertion level and to output the first probability and the second probability as a function of the feature set F,

a weighting unit configured to determine a first weighting factor and a second weighting factor based on the first and the second probability, respectively, and

an activity energy expenditure calculating unit configured to compute an overall activity energy expenditure based on the first activity energy expenditure based on heart rate data weighted by the first weighting factor and on the second activity energy expenditure based on motion or acceleration data weighted by the second weighting factor;

wherein the first probability of a high exertion of the user (h_H) is calculated using the formula;

h_H(F)=P(y=1/F;

B_c), and the second probability of a low exertion of the user (h_L) is calculated using the formula;

h_L(F)=P(y=0|F;

B_c), where B_c is a parameter set derived during a training phase for the use; and

a display to output the overall activity energy expenditure.

2. The vital signs monitoring system according to claim 1, further comprising a heart rate sensor in form of a photoplethysmographic sensor configured to measure or determine a heart rate of a user, and at least one motion or acceleration sensor configured to determine motion or acceleration data of a user.

3. A wearable device, comprising;

a display,

a heart rate sensor,

a motion sensor, and

a processing unit comprising;

a first input interface configured to receive heart rate data from the heart rate sensor,

a second input interface configured to receive motion or acceleration data from the motion sensor,

a first activity energy expenditure determining unit configured to determine a first activity energy expenditure based on heart rate data received via the first input interface,

a second activity energy expenditure determining unit configured to determine a second activity energy expenditure based on motion or acceleration data received via the second input interface,

a probability unit configured to calculate a first probability of a high exertion of a user and a second probability of a low exertion of the user, wherein the probability unit comprises;

a feature set unit configured to extract a feature set F based on at least one of the heart rate data and the motion or acceleration data, wherein the feature set F serves as predictors of a high or low exertion, and

a classification unit configured to classify an exertion level and to output the first probability and the second probability as a function of the feature set F;

a weighting unit configured to determine a first weighting factor and a second weighting factor based on the first probability and the second probability, and

an activity energy expenditure calculating unit configured to compute an overall activity energy expenditure based on the first activity energy expenditure based on heart rate data weighted by the first weighting factor and on the second activity energy expenditure based on motion or acceleration data weighted by the second weighting factor;

wherein the first probability of a high exertion of the user (h_H) is calculated using the formula;

h_H(F)=P(y=1/F;

B_c), and the second probability of a low exertion of the user (h_L) is calculated using the formula;

h_L(F)=P(y=0|F;

B_c), where B_c is a parameter set derived during a training phase for the user, and wherein the overall activity expenditure is displayed on the display.

4. A method of monitoring vital signs or physiological parameters of a user, comprising the steps of:

receiving heart rate data from at least one heart rate sensor configured to measure or determine a heart rate of a user;

receiving motion or acceleration data from at least one motion sensor configured to detect motion or acceleration data of a user;

determining a first activity energy expenditure based on the received heart rate data;

determining a second activity energy expenditure based on the received motion or acceleration data;

calculating a first probability of a high exertion of a user and a second probability of a low exertion of the user;

extracting a feature set F based on at least one of the heart rate data and the motion or acceleration data, wherein the feature set F serve as predictors of a high or low exertion;

classifying an exertion level and outputting the first and second probability as a function of the feature set F;

determining a first and second weighting factor based on the first probability and the second probability;

computing an overall activity expenditure based on the first activity energy expenditure based on heart rate data weighted by the first weighting factor and on the second activity energy expenditure based on motion or acceleration data weighted by the second weighting factor; and

displaying the overall activity expenditure on a display;

wherein the first probability of a high exertion of the user (h_H) is calculated using the formula;

h_H(F)=P(y=1/F;

B_c), and the second probability of a low exertion of the user (h_L) is calculated using the formula;

h_L(F)=P(y=0|F;

B_c), where B_c is a parameter set derived during a training phase for the user.

5. A non-transitory computer program product comprising computer program code instructions that, when executed, perform the steps of:

receiving heart rate data from at least one heart rate sensor configured to measure or determine a heart rate of a user;

receiving motion or acceleration data from at least one motion sensor configured to detect motion or acceleration data of a user;

determining a first activity energy expenditure based on the received heart rate data;

determining a second activity energy expenditure based on the received motion or acceleration data;

calculating a first probability of a high exertion of a user and a second probability of a low exertion of the user;

extracting a feature set F based on at least one of the heart rate data and the motion or acceleration data, wherein the feature set F serve as predictors of a high or low exertion;

classifying an exertion level and outputting the first and second probability as a function of the feature set F;

determining a first and second weighting factor based on the first probability and the second probability;

computing an overall activity energy expenditure based on the first activity energy expenditure based on heart rate data weighted by the first weighting factor and on the second activity energy expenditure based on motion or acceleration data weighted by the second weighting factor; and

displaying the overall activity energy expenditure on a display;

wherein the first probability of a high exertion of the user (h_H) is calculated using the formula;

h_H(F)=P(y=1/F;

B_c), and the second probability of a low exertion of the user (h_L) is calculated using the formula;

h_L(F)=P(y=0|F;

B_c), where B_c is a parameter set derived during a training phase for the user.