System and method to classify left ventricular and mitral valve function

• US 9,084,585 B1
• Filed: 10/06/2011
• Issued: 07/21/2015
• Est. Priority Date: 10/06/2011
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McNair, Douglas S.
• Primary Examiner(s): Natnithithadha, Navin
• Assistant Examiner(s): WEARE, MEREDITH H
• Application Number:
  US13/267,616
• Time in Patent Office: 1,384 Days
• Field of Search: 600/481, 600/485, 600/504, 600/506
• US Class Current: 1/1
• CPC Class Codes: A61B 5/02028 Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/0295 using plethysmography, i.e. measuring the variations in the volume of a body part as modified by the circulation of blood therethrough, e.g. impedance plethysmography
• CPC Class Codes: A61B 5/0535 Impedance plethysmography for measuring blood flow A61B5/0295
• CPC Class Codes: A61B 5/6824 Arm or wrist
• CPC Class Codes: A61B 5/7239 using differentiation including higher order derivatives
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• 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: G06F 2218/10 by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Methods, systems, and computer storage media are provided for determining whether a patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function. Transbrachial impedance velocimetry data and arterial pressure waveform data is received from a particular patient at a plurality of timepoints. An extent of deterioration is determined using a copula analysis of the patient data, and a statistical norm is determined for the patient'"'"'s left ventricular function and mitral valve function. A current data value is received from the patient, including current transbrachial impedance velocimetry data and arterial pressure waveform data. The current data value is compared to the patient'"'"'s statistical norm to determine whether the patient suffers from a recent deterioration in left ventricular function and/or mitral valve function.

Claims

1. One or more tangible computer storage devices storing computer-useable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform a method for classifying one or both of left ventricular function and mitral valve function, the method comprising:

receiving data from a particular patient at a plurality of timepoints, wherein the data comprises transbrachial impedance velocimetry data collected from the patient at the plurality of timepoints and arterial pressure waveform data collected from the patient at the plurality of timepoints;

determining an extent of deterioration at each of the plurality of timepoints of one or both of left ventricular function and mitral valve function based on the transbrachial impedance velocimetry data and the arterial pressure waveform data, the determining an extent of deterioration comprising determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a first and second interval at each of the plurality of timepoints;

determining a statistical norm for the particular patient based on the determined extent of deterioration;

receiving a current data value from the patient at a current timepoint, wherein the current data value comprises transbrachial impedance velocimetry data collected from the patient at the current timepoint and arterial pressure waveform data collected from the patient at the current timepoint;

determining whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function, wherein determining whether the patient suffers from a recent deterioration is based on the statistical norm for the patient and the current data value; and

generating a report indicating whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function.

2. The one or more storage devices of claim 1, wherein receiving data comprises receiving one or more items of data from a monitor associated with a brachial artery of the patient.

3. The one or more storage devices of claim 1, wherein receiving data comprises receiving serial transbrachial impedance velocimetry data and serial arterial pressure waveform data.

4. The one or more storage devices of claim 1, wherein determining an extent of deterioration of left ventricular function comprises determining whether the statistical copula between d²sqrt(Z(t)/Z₀)/dt² and dP/dt during the first and second intervals displays a bivariate dependency and is well-fit by an extreme value distribution.

5. The one or more storage devices of claim 1, wherein determining an extent of deterioration at each of the plurality of timepoints of mitral valve function comprises determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a third interval at each of the plurality of timepoints.

6. The one or more storage devices of claim 5, wherein determining an extent of deterioration of mitral valve function comprises determining whether the statistical copula between d²sqrt(Z(t)/Z₀)/dt² and dP/dt during the third interval displays a bivariate dependency and is well-fit by an extreme value distribution.

7. The one or more storage devices of claim 1, wherein determining a statistical norm for the particular patient based on the determined extent of deterioration comprises establishing a time-averaged baseline characterization of the impedance timeseries and the blood pressure timeseries over a statistically representative interval of time greater than 500 beats.

8. The one or more storage devices of claim 1, wherein determining whether the patient suffers from a recent deterioration in left ventricular function comprises determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a first and second interval at the current timepoint.

9. The one or more storage devices of claim 8, wherein determining whether the patient suffers from a recent deterioration in left ventricular function comprises determining whether the statistical copula between d²sqrt(Z(t)/Z₀)/dt² and dP/dt during the first and second intervals at the current timepoint displays a bivariate dependency and is well-fit by an extreme value distribution.

10. The one or more storage devices of claim 9, wherein determining whether the patient suffers from a recent deterioration in left ventricular function comprises comparing the statistical copula during the first and second intervals at the current timepoint with the statistical norm for the patient.

11. The one or more storage devices of claim 1, wherein determining whether the patient suffers from a recent deterioration in mitral valve function comprises determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a third interval at the current timepoint.

12. The one or more storage devices of claim 11, wherein determining whether the patient suffers from a recent deterioration in mitral valve function comprises determining whether the statistical copula between d²sqrt(Z(t)/Z₀)/dt² and dP/dt during the third interval at the current timepoint displays a bivariate dependency and is well-fit by an extreme value distribution.

13. The one or more storage devices of claim 12, wherein determining whether the patient suffers from a recent deterioration in mitral valve function comprises comparing the statistical copula during the third interval at the current timepoint with the statistical norm for the patient.

14. The one or more storage devices of claim 1, wherein the method further comprises communicating the determination of whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function to a user.

15. A method for classifying one or both of left ventricular function and mitral valve function, the method comprising:

receiving medical monitoring data from a particular patient, the medical monitoring data comprising transbrachial impedance velocimetry data and arterial pressure waveform data, wherein the medical monitoring data is received at a plurality of timepoints;

determining a statistical norm for the particular patient based on the medical monitoring data, the determining a statistical norm for the particular patient comprising determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Zo)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during two or more intervals at each of the plurality of timepoints;

receiving a current data value from the particular patient, the current data value comprising transbrachial impedance velocimetry data and arterial pressure waveform data;

based on the determined statistical norm and the received current data value, determining whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function; and

generating a report indicating whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function,

wherein the method is performed by one or more computing devices.

16. The method of claim 15, wherein determining a statistical copula comprises determining whether the statistical copula between d²sqrt(Z(t)/Z₀)/dt² and dP/dt during two or more intervals displays a bivariate dependency and is well-fit by an extreme value distribution.

17. One or more tangible computer storage devices storing computer-useable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform a method for classifying left ventricular function and mitral valve function, the method comprising:

receiving data from a particular patient at a plurality of timepoints, wherein the data comprises transbrachial impedance velocimetry data collected from the patient at the plurality of timepoints and arterial pressure waveform data collected from the patient at the plurality of timepoints;

determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a first and second interval at each of the plurality of timepoints;

determining an extent of deterioration at each of the plurality of timepoints of left ventricular function based on the statistical copula determined during the first and second intervals;

determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a third interval at each of the plurality of timepoints;

determining an extent of deterioration at each of the plurality of timepoints of mitral valve function based on the statistical copula determined during the third interval;

determining a statistical norm for the particular patient based on the determined extent of deterioration of left ventricular function and the determined extent of deterioration of mitral valve function;

receiving a current data value from the patient at a current timepoint, wherein the current data value comprises transbrachial impedance velocimetry data collected from the patient at the current timepoint and arterial pressure waveform data collected from the patient at the current timepoint;

determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a first and second interval at the current timepoint;

determining an extent of deterioration at the current timepoint of left ventricular function based on the statistical copula determined during the first and second intervals;

determining a statistical copula between a second derivative of square-root-transformed patient-calibrated transbrachial electrical impedance velocimetry waveform timeseries d²sqrt(Z(t)/Z₀)/dt² and a first derivative of arterial blood pressure waveform timeseries dP/dt during a third interval at the current timepoint;

determining an extent of deterioration at the current timepoint of mitral valve function based on the statistical copula determined during the third interval;

determining whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function, wherein determining whether the patient suffers from a recent deterioration is based on the statistical norm, the determined extent of deterioration of left ventricular function at the current timepoint, and the determined extent of deterioration of mitral valve function at the current timepoint; and

generating a report indicating whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function.

18. The one or more storage devices of claim 17, wherein determining whether the patient suffers from one or both of a recent deterioration in left ventricular function and a recent deterioration in mitral valve function comprises one or more of:

determining that the statistical copula between d²sqrt(Z(t)/Z₀)/dt² and dP/dt during the first and second intervals at the current timepoint displays a bivariate dependency and is well-fit by an extreme value distribution; and

determining that the statistical copula between d²sqrt(Z(t)/Z₀)/dt² and dP/dt during the third interval at the current timepoint displays a bivariate dependency and is well-fit by an extreme value distribution.