REMOTE MONITORING OF VITAL SIGNS

• US 20140303454A1
• Filed: 08/16/2012
• Published: 10/09/2014
• Est. Priority Date: 08/22/2011
• Status: Active Grant

• Current Assignee: Oxehealth Limited
• Original Assignee: Isis Innovation Limited
• Inventors: Clifton, David Andrew, Tarassenko, Lionel, Montoya, Mauricio Christian Villarroel
• Granted Patent: US 9,615,749 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• 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 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/1176 Recognition of faces
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: G06F 2218/20 by applying autoregressive analysis
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30076 Plethysmography
• CPC Class Codes: G06T 2207/30088 Skin; Dermal
• CPC Class Codes: G06T 2207/30104 Vascular flow; Blood flow; Perfusion
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 5/10 using non-spatial domain filtering
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• CPC Class Codes: G06V 40/15 Biometric patterns based on physiological signals, e.g. heartbeat, blood flow

Abstract

A method of remote monitoring of vital signs by detecting the PPG signal in an image of a subject taken by a video camera such as a webcam. The PPG signal is identified by auto-regressive analysis of ambient light reflected from a region of interest on the subject'"'"'s skin. Frequency components of the ambient light and aliasing artefacts resulting from the frame rate of the video camera are cancelled by auto-regressive analysis of ambient light reflected from a region of interest not on the subject'"'"'s skin, e.g. in the background. This reveals the spectral content of the ambient light allowing identification of the subject'"'"'s PPG signal. Heart rate, oxygen saturation and breathing rate are obtained from the PPG signal. The values can be combined into a wellness index based on a statistical analysis of the values.

Claims

1. A method of suppressing ambient light interference in a PPG image signal comprising the steps of:

imaging a region of interest on a subject'"'"'s skin using a video camera to obtain a PPG image signal comprising periodic intensity variations in ambient light reflected from the region of interest;

imaging a reference region of interest not on the subject'"'"'s skin using the same video camera to obtain a reference signal;

spectrally analysing the reference signal using an auto-regressive (AR) all pole model and identifying poles corresponding to spectral components;

spectrally analysing the PPG image signal using an auto-regressive (AR) all pole model to identify poles corresponding to spectral components therein and ignoring poles corresponding to those identified as spectral components of the reference signal.

2. The method according to claim 1 wherein the reference signal and PPG signal are the output signals from at least one of the red, green and blue channels of the video camera or the infra-red channel from another camera.

3. The method according to claim 1 further comprising imaging a plurality of regions of interest on the subject'"'"'s skin and imaging a plurality of reference regions of interest.

4. The method according to claim 3 wherein each region of interest is centred on a single camera pixel.

5. The method according to claim 1 further comprising the step of obtaining vital-sign data from remaining components of the PPG signal.

6. The method according to claim 1 wherein the reference signal and the PPG signal are each analysed using a plurality of models of different order.

7. The method according to claim 6 wherein the plurality of models of different order comprise models of order 8 to 20.

8. The method according to claim 6 wherein the spectral components corresponding to the identified poles are averaged over different order models.

9. The method according to claim 1 further comprising the step of obtaining a measurement of the heart rate of the subject by identifying a pole in the PPG signal which is not present in the reference signal.

10. The method according to claim 9 wherein the measurement of the heart rate (HR) is obtained by identifying a pole corresponding to a spectral component having a frequency in the range of HR_min to HR_max (typically 0.67 to 4 Hz).

19. The computer program adapted to produce a measurement of one or more of a subject'"'"'s vital signs by a method including PPG imaging of the subject and suppression of ambient light interference by the method of claim 1.

21. A method according to claim 20 wherein the PPG imaging includes suppression of interference by the method of claim 1.

22. A method according to claim 1 further comprising the step of obtaining a measurement of the breathing rate of the subject by low-pass filtering and downsampling the PPG signal before spectrally analysing it using another set of all-pole models.

23. A method according to claim 1 further comprising the step of obtaining a measurement of the subject'"'"'s blood oxygen saturation by obtaining the ratio of intensity of light at two different wavelengths reflected from the region of interest on the subject'"'"'s skin, the intensity being obtained from the magnitude of the pole identified as representing the heart rate.

24. A method according to claim 23 wherein the two different wavelengths are the red and green wavelengths detected by the video camera.

25. A method according to claim 23 wherein the two different wavelengths comprise the red wavelength detected by the video camera and an infrared wavelength detected by a second video camera.

11. A method of obtaining an estimate of heart rate of a human or animal subject comprising the steps of obtaining a PPG signal from the subject, spectrally analysing the PPG signal using a plurality of auto-regressive (AR) all pole models of different order to identify from each model a spectral component representing the heart rate and producing a heart rate estimate corresponding to that spectral component, fusing the estimates of the heart rate from the different models thereby producing a robust heart rate estimate.

12. The method according to claim 11 wherein the fusing step comprises taking the median of the heart rate estimates from the different models.

13. The method according to claim 11 wherein the PPG signal is a PPG image signal.

14. The method according to claim 11 further comprising the step of obtaining a measurement of the breathing rate of the subject by low-pass filtering and downsampling the PPG signal before spectrally analysing it using another set of all-pole models.

16. The method according to claim 11 further comprising the step of obtaining a measurement of the subject'"'"'s blood oxygen saturation by obtaining the ratio of intensity of light at two different wavelengths reflected from the region of interest on the subject'"'"'s skin, the intensity being obtained from the magnitude of the pole identified as representing the heart rate.

17. The method according to claim 16 wherein the two different wavelengths are the red and green wavelengths detected by the video camera.

18. The method according to claim 16 wherein the two different wavelengths comprise the red wavelength detected by the video camera and an infrared wavelength detected by a second video camera.

26. A computer program adapted to produce a measurement of one or more of a subject'"'"'s vital signs by a method including PPG imaging of the subject and suppression of ambient light interference by the method of claim 11.

27. A method according to claim 20 wherein the PPG imaging includes suppression of interference by the method of claim 11.

15. A method of obtaining an estimate of breathing rate of a human or animal subject comprising the steps of obtaining a PPG signal from the subject, filtering and downsampling the PPG signal before spectrally analysing it using a plurality of auto-regressive (AR) all pole models of different order to identify from each model a spectral component representing the breathing rate and producing a breathing rate estimate corresponding to that spectral component, fusing the estimates of the breathing rate from the different models thereby producing a robust breathing rate estimate.

20. A method of measuring one or more of a subject'"'"'s vital signs by PPG imaging of the subject using a video camera and performing a facial recognition process on an image of the subject obtained by the same camera to link the identity of the subject to the vital signs measurement.