Determining pulse transit time non-invasively using handheld devices

• US 9,504,391 B2
• Filed: 03/04/2013
• Issued: 11/29/2016
• Est. Priority Date: 03/04/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Morris, Daniel, Saponas, T. Scott, Tan, Desney S., Dixon, Morgan, Khullar, Siddharth, Vathsangam, Harshvardhan
• Primary Examiner(s): D ABREU, MICHAEL JOSEPH
• Application Number:
  US13/783,395
• Publication Number:
  US 20140249398A1
• Time in Patent Office: 1,366 Days
• Field of Search: 600/479, 600/500, 600/509
• US Class Current: 1/1
• CPC Class Codes: A61B 2560/0462 Apparatus with built-in sensors
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• CPC Class Codes: A61B 5/02125 of pulse wave propagation time
• CPC Class Codes: A61B 5/282 Holders for multiple electrodes for introduction into the body A61B5/287
• CPC Class Codes: A61B 5/332 Portable devices specially adapted therefor
• CPC Class Codes: A61B 5/6815 Ear
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7278 Artificial waveform generation or derivation, e.g. synthesising signals from measured signals A61B5/327 takes precedence
• CPC Class Codes: A61B 5/748 Selection of a region of interest, e.g. using a graphics tablet

Abstract

A system and method to determine pulse transit time using a handheld device. The method includes generating an electrocardiogram (EKG) for a user of the handheld device. Two portions of the user'"'"'s body are in contact with two contact points of the handheld device. The method also includes de-noising the EKG to identify a start time when a blood pulse leaves a heart of the user. The method further includes de-noising a plurality of video images of the user to identify a pressure wave indicating an arterial site and a time when the pressure wave appears. Additionally, the method includes determining the PTT based on the de-noised EKG and the de-noised video images.

Claims

1. A method for determining pulse transit time (PTT) non-invasively, the method comprising:

generating an electrocardiogram (EKG) for a user of a handheld device, wherein the EKG is generated from two conductive contact points on the handheld device in contact with two portions of the user'"'"'s body;

de-noising the EKG to identify a start time of the PTT, the start time of the PTT being a time when a blood pulse leaves a heart of the user;

receiving a plurality of video images of the user;

finding the user'"'"'s face in the plurality of images;

cropping the plurality of images to generate cropped images that include the user'"'"'s face;

de-noising the cropped images to identify a pressure wave indicating an arterial site and an end time of the PTT, the end time of the PTT being a time when the pressure wave appears;

determining the PTT by computing a difference between the start time of the PTT and the end time of the PTT; and

determining a blood pressure measurement for the user based on the PTT.

2. The method recited in claim 1, comprising:

presenting the blood pressure measurement using the handheld device.

3. The method recited in claim 1, wherein one of the conductive contact points comprises a contact point on a conductive touch screen surface of the handheld device.

4. The method recited in claim 1, wherein one of the conductive contact points comprises a contact point on a back of the handheld device.

5. The method recited in claim 1, wherein one of the conductive contact points comprises a contact point in an earphone connected to a body of the handheld device.

6. The method recited in claim 1, comprising:

identifying a facial region of the video images;

identifying a left cheek region of the video images;

identifying a right cheek region of the video images;

generating a red-green-blue (RGB) signal for the facial region, left cheek region, and right cheek region;

performing independent component analysis (ICA) on the RGB signals to generate components of the ICA;

identifying the pressure wave based on a component of the ICA having a lowest Kurtosis of the components of the ICA.

7. A system for determining pulse transit time (PTT) non-invasively, the system comprising:

a processing unit; and

a system memory, wherein the system memory comprises code configured to direct the processing unit to;

generate an electrocardiogram (EKG) for a user of a handheld device, wherein the EKG is generated from two conductive contact points on the handheld device in contact with two portions of the user'"'"'s body;

de-noise the EKG to identify a start time of the PTT, the start time of the PTT being a time when a blood pulse leaves a heart of the user;

receive a plurality of video images of the user;

identify a facial region of the plurality of video images;

crop the plurality of images to generate cropped images that include the facial region;

de-noise the cropped images to identify a pressure wave indicating an arterial site and an end time of the PTT, the end time of the PTT being a time when the pressure wave appears;

determine the PTT based on the de-noised EKG and the de-noised video images; and

determine a blood pressure measurement for the user based on the PTT.

8. The system recited in claim 7, wherein one of the conductive contact points comprises a contact point on a conductive touch screen surface of the handheld device.

9. The system recited in claim 7, wherein one of the conductive contact points comprises a contact point on a back of the handheld device.

10. The system recited in claim 7, wherein one of the conductive contact points comprises a contact point in an earphone connected to a body of the handheld device.

11. The system recited in claim 7, comprising code configured to direct the processing unit to:

identify a facial region of the video images;

identify a left cheek region of the video images;

identify a right cheek region of the video images;

generate a red-green-blue (RGB) signal for the facial region, left cheek region, and right cheek region;

perform independent component analysis (ICA) on the RGB signals to generate components of the ICA;

identify the pressure wave based on a component of the ICA having a lowest Kurtosis of the components of the ICA.

12. One or more computer-readable storage memory for determining pulse transit time (PTT) non-invasively, the computer-readable storage memory comprising code configured to direct a processing unit to:

generate an electrocardiogram (EKG) for a user of a handheld device, wherein the EKG is generated from two conductive contact points on the handheld device in contact with two portions of the user'"'"'s body;

de-noise the EKG to remove electrical noise associated with movement of the user;

identify a start time of the PTT based on the de-noised EKG, the start time of the PTT being a time when a blood pulse leaves a heart of the user;

receive a plurality of video images of the user;

identify a facial region of the plurality of video images;

crop the plurality of images to generate cropped images that include the facial region;

de-noise the cropped images to identify a pressure wave indicating an arterial site and an end time of the PTT, the end time of the PTT being a time when the pressure wave appears;

determine a pulse transit time (PTT) based on the de-noised EKG and the de-noised video images; and

determine a blood pressure measurement for the user based on the PTT.

13. The computer-readable storage memory recited in claim 12, the code configured to direct the processing unit to determine a biological metric comprising code configured to direct the processing unit to:

present the blood pressure measurement using the handheld device.

14. The computer-readable storage memory recited in claim 12, wherein one of the conductive contact points comprises a contact point on a conductive touch screen surface of the handheld device, and one of the contact points comprises a contact point on a back or side of the handheld device.

15. The computer-readable storage memory recited in claim 12, comprising code configured to direct the processing unit to:

identify a start time of the PTT, wherein the start time is determined from the de-noised EKG; and

identify an end time of the PTT, wherein the end time is the time when the pressure wave appears.

16. The computer-readable storage memory recited in claim 12, comprising code configured to direct the processing unit to:

identify a facial region of the video images;

identify a left cheek region of the video images;

identify a right cheek region of the video images;

generate a red-green-blue (RGB) signal for the facial region, left cheek region, and right cheek region; and

perform independent component analysis (ICA) on the RGB signals to generate components of the ICA.

17. The computer-readable storage memory recited in claim 12, wherein the handheld device comprises a game controller.