Monitoring projections along principal components of multiple sensors as an indicator of worsening heart failure

• US 8,858,448 B2
• Filed: 12/14/2011
• Issued: 10/14/2014
• Est. Priority Date: 12/20/2010
• Status: Active Grant

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Thakur, Pramodsingh Hirasingh, Patangay, Abhilash, Wariar, Ramesh, Hatlestad, John D., Zhang, Yi
• Primary Examiner(s): Mallari, Patricia
• Assistant Examiner(s): WESTON, TIFFANY C
• Application Number:
  US13/325,120
• Publication Number:
  US 20120157858A1
• Time in Patent Office: 1,035 Days
• Field of Search: 600481-504
• US Class Current: 600/481
• 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 5/053 Measuring electrical impedance or conductance of a portion of the body
• CPC Class Codes: A61B 5/0809 by impedance pneumography
• CPC Class Codes: A61B 5/1107 Measuring contraction of parts of the body, e.g. organ, muscle apparatus for measuring work or force in general G01L
• CPC Class Codes: A61B 5/283 Invasive
• CPC Class Codes: A61B 5/6869 Heart
• CPC Class Codes: A61B 5/7253 characterised by using transforms
• CPC Class Codes: A61B 7/023 for introduction into the body, e.g. into the oesophagus oesophageal ECG probes A61B5/285
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R
• CPC Class Codes: A61N 1/3627 for treating a mechanical deficiency of the heart, e.g. congestive heart failure or cardiomyopathy
• CPC Class Codes: A61N 1/37 Monitoring; Protecting

Abstract

A device can include at least a first physiologic sensor circuit configured to provide a first physiologic signal, a second physiologic sensor circuit configured to provide a second physiologic signal, and a processor circuit. The processor circuit includes a principal component analysis circuit configured to represent data determined from the at least first and second physiologic sensor circuits as at least first and second axes, respectively, in a multidimensional space, determine one or more principal components in the multidimensional space, determine a quantitative attribute of the first and the second physiologic signals using at least one of the determined principal components or a projection of the data along the at least one determined principal component, and provide an indication of heart failure status according to the quantitative attribute to at least one of a user or a process.

Claims

1. An implantable or other ambulatory apparatus comprising:

at least a first physiologic sensor circuit, configured to provide a first physiologic signal and a second physiologic sensor circuit configured to provide a second physiologic signal, wherein the first and second physiologic signals include physiological information of a subject;

a processor circuit, communicatively coupled to the first and second physiologic sensor circuits, wherein the processor circuit includes a principal component analysis (PCA) circuit configured to;

represent data determined from the at least first and second physiologic sensor circuits as at least first and second axes, respectively, in a multidimensional space;

determine one or more principal components in the multidimensional space;

determine a quantitative attribute of the first and the second physiologic signals using at least one of the determined principal components or a projection of the data along the at least one determined principal component; and

provide an indication of heart failure (HF) status according to the quantitative attribute to at least one of a user or a process.

2. The apparatus of claim 1, wherein the PCA circuit includes an ellipticity calculation circuit configured to:

calculate, as the quantitative attribute, ellipticity of a data cloud formed by representing the data from the first and second physiologic signals in the multi-dimensional space; and

provide the indication of HF according to the calculated ellipticity.

3. The apparatus of claim 2, wherein the ellipticity calculation circuit is configured to:

calculate a plurality of eigenvalues corresponding to the principal components in the multidimensional space; and

calculate ellipticity using the plurality of eigenvalues.

4. The apparatus of claim 2,

wherein the first physiologic signal is representative of an aspect of physiology of the subject that is dissimilar to an aspect of physiology represented by the second physiologic signal, and

wherein the PCA circuit is configured to provide an indication of worsening HF of the subject when detecting an increase in the ellipticity.

5. The apparatus of claim 4, wherein the first physiologic sensor circuit and the second physiologic sensor circuit include at least two of:

an impedance sensor, a respiration sensor, a heart sound sensor, a cardiovascular pressure sensor, and an activity sensor.

6. The apparatus of claim 4, wherein the PCA circuit is configured to provide an indication of stable HF of the subject when detecting that the ellipticity decreases below a specified ellipticity threshold value.

7. The apparatus of claim 2,

wherein the first physiologic signal is representative of an aspect of physiology of the subject that is similar to an aspect of physiology represented by the second physiologic signal, and

wherein the PCA circuit is configured to provide an indication of worsening HF of the subject when detecting a decrease in the ellipticity.

8. The apparatus of claim 7, wherein the PCA circuit is configured to represent a first axis and a second axis of the multidimensional space as at least one of:

a first impedance signal and a second impedance signal measured in a direction different from the first impedance signal;

an amplitude of a heart sound and an amplitude of a different heart sound;

respiration rate and tidal volume; and

a first statistical measure of an output of a physiological sensor and a second statistical measure of the output of the physiologic sensor.

9. The apparatus of claim 7, including:

at least a third physiologic sensor circuit configured to provide a third physiologic signal and a fourth physiologic sensor circuit configured to provide a fourth physiologic signal, wherein the third physiologic signal is representative of an aspect of physiology of the subject that is dissimilar to an aspect of physiology represented by the fourth physiologic signal;

wherein the PCA circuit is configured to;

represent output from the third physiologic sensor and the fourth physiologic sensor as a first axis and a second axis, respectively, in a second multidimensional space;

determine a quantitative attribute of the third physiologic signal and the fourth physiologic signal using the second multidimensional space; and

provide an indication of HF according to the quantitative attribute determined using the first multidimensional space and the quantitative attribute determined using the second multidimensional space.

10. The apparatus of claim 1, wherein the PCA circuit is configured to:

determine, as the quantitative attribute, an orientation of one or more of the principal components in the multi-dimensional space; and

provide an indication of worsening HF of the subject when detecting a shift in the orientation outside of a specified orientation range.

11. The apparatus of claim 1, including:

N physiologic sensor circuits configured to provide N physiologic signals, wherein N is an integer,

wherein the PCA circuit is configured to;

represent output from the N physiologic sensor circuits as N axes in the multidimensional space; and

determine a quantitative attribute of the N physiologic signals using the multidimensional space.

12. A method of operating an implantable or other ambulatory medical device, the method comprising:

sensing at least a first physiologic signal using a first physiologic sensor circuit and a second physiologic signal using a second physiologic sensor circuit, wherein the first and second physiologic signals include physiological information of a subject;

representing, using a processor circuit including a principal component analysis (PCA) circuit, data determined from the at least first physiologic signal and second physiologic signal as at least a first and a second axis, respectively, in a multidimensional space;

determining, using the processor circuit, one or more principal components of the data represented in the multidimensional space;

determining, using the processor circuit, a quantitative attribute of the data form the first and second physiologic signals using a least one of the one or more determined principal components or a projection of the data along the at least one determined principal component; and

providing, using the processor circuit, an indication of heart failure (HF) status to at least one of a user of a process according to the quantitative attribute.

13. The method of claim 12, wherein the quantitative attribute includes a measure of ellipticity of a data cloud formed by representing the data from the first and second physiologic signals in the multi-dimensional space.

14. The method of claim 13, including:

calculating a plurality of eigenvalues corresponding to the principal components in the multidimensional space; and

wherein calculating a measure of ellipticity includes calculating ellipticity using the plurality of eigenvalues.

15. The method of claim 13,

wherein the first physiologic signal represents an aspect of physiology of the subject that is dissimilar to an aspect of physiology represented by the second physiologic signal, and

wherein providing an indication of heart failure according to the quantitative attribute includes indicating worsening HF of the subject when detecting an increase in the quantitative attribute.

16. The method of claim 15, wherein the first physiologic signal and the second physiologic signal are representative of any two of:

impedance, a heart sound, cardiovascular pressure, and activity.

17. The method of claim 13,

wherein the first physiologic signal represents an aspect of physiology of the subject that is similar to an aspect of physiology represented by the second physiologic signal, and

wherein providing an indication of heart failure according to the quantitative attribute includes indicating worsening HF of the subject when detecting a decrease in the quantitative attribute.

18. The method of claim 17, wherein the first axis and the second axis of the multidimensional space represent at least one of:

a first impedance signal and a second impedance signal measured in a direction different from the first impedance signal;

an amplitude of a heart sound and an amplitude of a different heart sound;

respiration rate and tidal volume; and

a first statistical measure of an output of a physiological sensor and a second statistical measure of the output of the physiologic sensor.

19. The method of claim 17, including:

sensing at least a third physiologic signal using a third physiologic sensor circuit and a fourth physiologic signal using a fourth physiologic sensor circuit, wherein the third physiologic signal represents an aspect of physiology of the subject that is dissimilar to an aspect of physiology represented by the fourth physiologic signal;

representing output from the third physiologic sensor and the fourth physiologic sensor as first and second axes, respectively, in a second multidimensional space;

determining a quantitative attribute of the third physiologic signal and the fourth physiologic signal using the second multidimensional space; and

wherein providing an indication of HF includes providing an indication of HF according to the quantitative attribute determined using the first multidimensional space and the quantitative attribute determined using the second multidimensional space.

20. The method of claim 13,

wherein the quantitative attribute includes an orientation of one or more of the principal components in the multi-dimensional space, and

wherein providing an indication of heart failure includes providing an indication of worsening HF of the subject when detecting a shift in the orientation outside of a specified orientation range.