Detection of physiological changes

• US 8,977,588 B1
• Filed: 09/16/2011
• Issued: 03/10/2015
• Est. Priority Date: 03/31/2011
• Status: Active Grant

• Current Assignee: Rockwell Collins, Inc. (Rtx Corporation)
• Original Assignee: Rockwell Collins, Inc. (Rtx Corporation)
• Inventors: Engler, Joseph J., Jones, Timothy B.
• Primary Examiner(s): GILBERT, ANDREW M
• Application Number:
  US13/235,096
• Time in Patent Office: 1,271 Days
• Field of Search: 604/500, 604/503, 604/65, 604/66, 707/603, 707687-704, 707790-801, 702/66, 702/71, 702/72, 702/73, 702179-191, 702/196, 702/19, 702/21, 705/7.11, 600/508, 600/515, 600/544, 607/45
• US Class Current: 707/603
• CPC Class Codes: G06F 21/552 involving long-term monitoring or reporting

Abstract

Systems and methods for detecting changes in a physiological system are provided. A method comprises embedding time series data relating to the physiological system within a reconstructed phase space and partitioning the reconstructed phase space into a plurality of regions. The method further comprises generating a first matrix having a plurality of cells. A value stored in each cell is based on a probability that the system will transition from a first region associated with the cell to a second region associated with the cell and a rate of separation of trajectories of the embedded data within at least one of the first region and the second region. The first matrix is associated with a normal operating condition of the physiological system. The method further comprises comparing the first matrix and a second matrix based on different data to detect an anomalous condition of the physiological system.

Claims

1. A method of detecting changes relating to activity of a heart, the method comprising:

embedding time series data relating to the activity of the heart within a reconstructed phase space to generate embedded time series data;

partitioning the reconstructed phase space into a plurality of regions;

generating a first matrix having a plurality of cells, wherein the first matrix comprises a row and a column for each of the plurality of regions, wherein a value stored in each cell is based on a probability the activity of the heart will transition from a first region associated with the cell to a second region associated with the cell and a rate of separation of trajectories of the embedded time series data within at least one of the first region and the second region, and wherein the first matrix is generated using a first set of the time series data associated with a normal operating condition of the heart;

generating a second matrix based on a second set of the time series data; and

comparing the first matrix and the second matrix to detect a heart attack;

wherein comparing the first matrix and the second matrix comprises;

calculating a state change parameter representing a degree of state change between a first state associated with the first matrix and a second state associated with the second matrix; and

comparing the state change parameter to a threshold value; and

wherein the method further comprises performing an action relating to the heart attack when the state change parameter exceeds the threshold value.

2. The method of claim 1, wherein the value stored in each cell is based on a maximum Lyapunov exponent associated with the first region or the second region.

3. The method of claim 1, wherein performing the action comprises activating an alarm indicating detection of the heart attack.

4. The method of claim 1, wherein performing the action comprises enacting one or more steps configured to counteract the heart attack.

5. The method of claim 4, wherein performing the action comprises administering a substance configured to counteract the heart attack, wherein an amount of the substance administered is based on the state change parameter.

6. The method of claim 1, further comprising generating an image based on at least one of the first matrix and the second matrix and transmitting the image to a display.

7. A system, comprising:

an electronic processor configured to

embed time series data relating to activity of a heart within a reconstructed phase space to generate embedded time series data;

partition the reconstructed phase space into a plurality of regions;

generate a first matrix having a plurality of cells, wherein the first matrix comprises a row and a column for each of the plurality of regions, wherein a value stored in each cell is based on a probability the activity of the heart will transition from a first region associated with the cell to a second region associated with the cell and a rate of separation of trajectories of the embedded time series data within at least one of the first region and the second region, and wherein the first matrix is generated using a first set of the time series data associated with a normal operating condition of the heart;

generate a second matrix based on a second set of the time series data; and

compare the first matrix and the second matrix to detect a heart attack by;

calculating a state change parameter representing a degree of state change between a first state associated with the first matrix and a second state associated with the second matrix; and

comparing the state change parameter to a threshold value; and

perform an action relating to the heart attack when the state change parameter exceeds the threshold value.

8. The system of claim 7, wherein the value stored in each cell is based on a maximum Lyapunov exponent associated with the first region or the second region.

9. The system of claim 7, wherein the action performed by the electronic processor when the state change parameter exceeds the threshold value comprises activating an alarm indicating detection of the heart attack.

10. The system of claim 7, wherein the action performed by the electronic processor when the state change parameter exceeds the threshold value comprises enacting one or more steps configured to counteract the heart attack.

11. The system of claim 10, wherein the action performed by the electronic processor when the state change parameter exceeds the threshold value comprises transmitting a signal to one or more machines, wherein the one or more machines, after receiving the signal, are configured to administer a substance that is configured to counteract the heart attack, wherein an amount of the substance administered is based on the state change parameter.

12. The system of claim 7, wherein the electronic processor is further configured to generate an image based on at least one of the first matrix and the second matrix and transmit the image to a display.

13. One or more non-transitory computer-readable media having instructions stored thereon, the instructions being executable by one or more processors to execute a method comprising:

embedding time series data within a reconstructed phase space to generate embedded time series data, wherein the time series data comprises heart activity data representative of activity of a heart of a person;

partitioning the reconstructed phase space into a plurality of regions;

generating a first matrix having a plurality of cells, wherein the first matrix comprises a row and a column for each of the plurality of regions, wherein a value stored in each cell is based on a probability the activity of the heart will transition from a first region associated with the cell to a second region associated with the cell and a rate of separation of trajectories of the embedded time series data within at least one of the first region and the second region;

generating a second matrix based on a second set of the time series data; and

comparing the first matrix and the second matrix to detect a heart attack by;

calculating a state change parameter representing a degree of state change between a first state associated with the first matrix and a second state associated with the second matrix; and

comparing the state change parameter to a threshold value; and

performing an action relating to the heart attack when the state change parameter exceeds the threshold value.

14. The one or more non-transitory computer-readable media of claim 13, wherein the value stored in each cell is based on a maximum Lyapunov exponent associated with the first region or the second region.

15. The one or more non-transitory computer-readable media of claim 13, wherein performing the action comprises activating an alarm indicating detection of the heart attack.

16. The one or more non-transitory computer-readable media of claim 13, wherein the method further comprises generating an image based on the matrix and transmitting the image to a display.