Non-invasive method and system for characterizing cardiovascular systems for all-cause mortality and sudden cardiac death risk

• US 9,955,883 B2
• Filed: 07/11/2016
• Issued: 05/01/2018
• Est. Priority Date: 08/17/2012
• Status: Active Grant

• Current Assignee: Analytics For Life
• Original Assignee: Analytics For Life, Inc.
• Inventors: Gupta, Sunny, Yazdi, Mohsen Najafi, Burton, Timothy William Fawcett, Ramchandani, Shyamlal, Exner, Derek Vincent
• Primary Examiner(s): MAHMOOD, NADIA AHMAD
• Application Number:
  US15/207,214
• Publication Number:
  US 20170035312A1
• Time in Patent Office: 659 Days
• Field of Search: 600512, 600523
• 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 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/026 Measuring blood flow A61B3/1233, A61B3/1241 take precedence
• CPC Class Codes: A61B 5/029 Measuring or recording blood output from the heart, e.g. minute volume A61B8/065 takes precedence
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/14552 Details of sensors specially adapted therefor
• CPC Class Codes: A61B 5/24 Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/339 Displays specially adapted therefor
• CPC Class Codes: A61B 5/341 Vectorcardiography [VCG]
• CPC Class Codes: A61B 5/344 Foetal cardiography
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/364 Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Methods and systems for evaluating the electrical activity of the heart to identify novel ECG patterns closely linked to the subsequent development of serious heart rhythm disturbances and fatal cardiac events. Two approaches are describe, for example a model-based analysis and space-time analysis, which are used to study the dynamical and geometrical properties of the ECG data. In the first a model is derived using a modified Matching Pursuit (MMP) algorithm. Various metrics and subspaces are extracted to characterize the risk for serious heart rhythm disturbances, sudden cardiac death, other modes of death, and all-cause mortality linked to different electrical abnormalities of the heart. In the second method, space-time domain is divided into a number of regions (e.g., 12 regions), the density of the ECG signal is computed in each region and input to a learning algorithm to associate them with these events.

Claims

1. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis comprising a phase space transformation, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, and wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia;

wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death.

2. The method of claim 1, wherein parts of the extracted metrics include a metric parameter associated with a determined density for each of the plurality of regions.

3. The method of claim 2, wherein the metric parameter is associated with at least 12 dimensional dynamic space densities.

4. The method of claim 1, wherein the generated space-time domain data set is divided into a plurality of regions from a center of mass of a space-time density structure associated with the generated space-time domain data set.

5. The method of claim 1, wherein the learning algorithm comprises a genetic algorithm.

6. The method of claim 1, wherein the generated space-time domain data set comprises an N-dimensional data set.

7. The method of claim 1, wherein the generated space-time domain data set comprises a subspace data set.

8. The method of claim 7, wherein the extracted metrics comprise one or more parameters selected from the group consisting of one or more CSF (complex-sub-harmonic-frequency) trajectory parameters, one or more quasi-periodic subspace parameters, one or more chaotic subspace parameters, one or more low-energy component subspace parameters, one or more high energy component subspace parameters, one or more fractional derivative parameters associated with a low-energy component subspace, and one or more fractional derivative parameters associated with a high-energy component subspace.

9. The method of claim 1, comprising:

generating, for display, by the one or more processors, a three dimensional phase space plot of the generated space-time domain data.

10. The method of claim 1, wherein the at least one heart beat cycle corresponds to a vector sum electrical activation pathway through the heart.

11. The method of claim 1, wherein the obtained electrophysiological data set comprising the at least one heart beat cycle is obtained over a predetermined time interval, the predetermined time interval being selected from group consisting of an interval of at least 50 seconds, an interval between 50 seconds and 700 seconds, and an interval between 100 seconds and 700 seconds.

12. A system for quantifying risk of serious arrhythmias, sudden cardiac death, or other modes of death and all-cause mortality events in mammals, the system comprising:

one or more processors; and

a memory having instructions stored thereon, wherein execution of the instructions by the one or more processors, cause the one or more processors to;

retrieve an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

process, via space-time analysis comprising a phase space transformation, the retrieved electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the retrieved electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, and wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia;

wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death.

13. The system of claim 12, wherein parts of the extracted metrics include a parameter associated with a determined density for each of the plurality of regions.

14. The system of claim 12, wherein the learning algorithm comprises a genetic algorithm.

15. The system of claim 12, wherein the generated space-time domain data set comprises an N-dimensional data set.

16. The system of claim 12, wherein the generated space-time domain data set comprises a subspace data set.

17. The system of claim 12, wherein the extracted metrics comprise one or more parameters selected from the group consisting of one or more CSF trajectory parameters, one or more quasi-periodic subspace parameters, one or more chaotic subspace parameters, one or more low-energy component subspace parameters, one or more high energy component subspace parameters, one or more fractional derivative parameters associated with a low-energy component subspace, and one or more fractional derivative parameters associated with a high-energy component subspace.

18. The system of claim 12, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

generate, for display, a three dimensional phase space plot of the generated space-time domain data.

19. The system of claim 12, wherein the retrieved electrophysiological data set comprising the at least one heart beat cycle is obtained over a predetermined time interval, the predetermined time interval being selected from group consisting of an interval of at least 50 seconds and an interval between 100 seconds and 700 seconds.

20. A non-transitory computer readable medium having instructions, wherein execution of the instructions, by a processor, cause the processor to:

obtain an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

process, via space-time analysis comprising a phase space transformation, the electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the retrieved electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, and wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia; and

wherein the one or more parameters parameter, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death.

21. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the generated space-time domain data set is divided into a plurality of regions from a center of mass of a space-time density structure associated with the generated space-time domain data set.

22. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the learning algorithm comprises a genetic algorithm.

23. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, ad wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the generated space-time domain data set comprises an N-dimensional data set.

24. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the generated space-time domain data set comprises a subspace data set.

25. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, and wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the extracted metrics comprise one or more parameters selected from the group consisting of one or more CSF trajectory parameters, one or more quasi-periodic subspace parameters, one or more chaotic subspace parameters, one or more low-energy component subspace parameters, one or more high energy component subspace parameters, one or more fractional derivative parameters associated with a low-energy component subspace, and one or more fractional derivative parameters associated with a high-energy component subspace.

26. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, and wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death; and

generating, for display, by the one or more processors, a three dimensional phase space plot of the generated space-time domain data.

27. A method for quantifying risk of cardiac morbidity or death, the method comprising:

obtaining, by one or more processors, an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

processing, by the one or more processors, via space-time analysis, the obtained electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the obtained electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the at least one heart beat cycle corresponds to a vector sum electrical activation pathway through the heart.

28. A system for quantifying risk of serious arrhythmias, sudden cardiac death, or other modes of death and all-cause mortality events in mammals, the system comprising:

one or more processors; and

a memory having instructions stored thereon, wherein execution of the instructions by the one or more processors, cause the one or more processors to;

retrieve an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

process, via space-time analysis, the retrieved electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the retrieved electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the learning algorithm comprises a genetic algorithm.

29. A system for quantifying risk of serious arrhythmias, sudden cardiac death, or other modes of death and all-cause mortality events in mammals, the system comprising:

one or more processors; and

a memory having instructions stored thereon, wherein execution of the instructions by the one or more processors, cause the one or more processors to;

retrieve an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

process, via space-time analysis, the retrieved electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the retrieved electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death,

wherein the generated space-time domain data set comprises an N-dimensional data set.

30. A system for quantifying risk of serious arrhythmias, sudden cardiac death, or other modes of death and all-cause mortality events in mammals, the system comprising:

one or more processors; and

a memory having instructions stored thereon, wherein execution of the instructions by the one or more processors, cause the one or more processors to;

retrieve an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

process, via space-time analysis, the retrieved electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the retrieved electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death,

wherein the generated space-time domain data set comprises a subspace data set.

31. A system for quantifying risk of serious arrhythmias, sudden cardiac death, or other modes of death and all-cause mortality events in mammals, the system comprising:

one or more processors; and

a memory having instructions stored thereon, wherein execution of the instructions by the one or more processors, cause the one or more processors to;

retrieve an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

process, via space-time analysis, the retrieved electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the retrieved electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death, and

wherein the extracted metrics comprise one or more parameters selected from the group consisting of one or more CSF trajectory parameters, one or more quasi-periodic subspace parameters, one or more chaotic subspace parameters, one or more low-energy component subspace parameters, one or more high energy component subspace parameters, one or more fractional derivative parameters associated with a low-energy component subspace, and one or more fractional derivative parameters associated with a high-energy component subspace.

32. A system for quantifying risk of serious arrhythmias, sudden cardiac death, or other modes of death and all-cause mortality events in mammals, the system comprising:

one or more processors; and

a memory having instructions stored thereon, wherein execution of the instructions by the one or more processors, cause the one or more processors to;

retrieve an electrophysiological data set associated with a measurement of an electrophysiological signal having been acquired from a noninvasive system configured to measure electrical properties of a heart over at least one heart beat cycle; and

process, via space-time analysis, the retrieved electrophysiological data set to extract metrics from a generated space-time domain data set generated from the space-time analysis of the retrieved electrophysiological data set, wherein the generated space-time domain data set is divided into a plurality of regions and metrics associated with each of the plurality of regions are extracted, wherein the extracted metrics are used, via a learning algorithm, to generate one or more parameters that characterize a risk selected from the group consisting of a risk for serious heart rhythm disturbances, a risk for sudden cardiac death, a risk for all-cause mortality linked to abnormalities of the heart, a risk associated with heart failure, a risk associated with ischemia, a risk associated with coronary artery disease, and a risk associated with cardiac arrhythmia, wherein the one or more parameters, or values associated therewith, are presented for clinical utility in predicting risk of cardiac morbidity or death; and

generate, for display, a three dimensional phase space plot of the generated space-time domain data.