Computerized systems and methods for stability-theoretic prediction and prevention of sudden cardiac death

• US 9,585,589 B2
• Filed: 12/30/2010
• Issued: 03/07/2017
• Est. Priority Date: 12/31/2009
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McNair, Douglas S.
• Primary Examiner(s): Kahelin, Michael
• Assistant Examiner(s): PHAM, MINH DUC GIA
• Application Number:
  US12/982,625
• Publication Number:
  US 20110190650A1
• Time in Patent Office: 2,259 Days
• Field of Search: 600/59, 600/509, 600515-518
• US Class Current: 1/1
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/0004 characterised by the type of physiological signal transmitted
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/6831 Straps, bands or harnesses
• CPC Class Codes: A61B 5/6891 Furniture
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• 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 5/7267 involving training the classification device
• 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: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/7405 using sound
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: A61B 5/747 in case of emergency, i.e. alerting emergency services
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Systems, methods and computer-readable media are provided for automatic identification of patients according to near-term risk of ventricular arrhythmias and sudden cardiac death (SCD). Embodiments of the invention are directed to event prediction, risk stratification, and optimization of the assessment, communication, and decision-making to prevent SCD, and in one embodiment take the form of a platform for wearable, mobile, unteathered monitoring devices with embedded decision support. Thus embodiments relate to automatically identifying persons at risk for arrhythmias and SCD through the use of noninvasive, portable, wearable electronic device and sensors equipped with signal-processing software and statistical predictive algorithms that calculate stability-theoretic measures derived from the digital electrocardiogram timeseries acquired by the device. The measurements and predictive algorithms embedded within the device provide for unsupervised use in the home or in general acute-care and chronic-care venues and afford a degree of robustness against variations in individual anatomy and sensor placement.

Claims

1. One or more computer-readable storage devices having computer-executable instructions embodied thereon that when executed, facilitate a method for automatically providing a notification for ventricular arrhythmias in an individual that are likely to result in sudden cardiac death (SCD), the method comprising:

obtaining, from one or more sensors, signals representative of electrical activity of the heart of said individual;

determining, utilizing an objective function, a QT dispersion stability index (QTdSI) from said signals, the objective function comprising a timeseries calculated from serially-acquired waveform data;

the determining comprising calculating a moving average of Lyapunov exponents;

determining a difference between the determined QTdSI and a reference value to detect the presence of instability of QT interval dispersion or other measurements in said signals; and

providing a notification when an increased risk for SCD is determined;

a significant difference being indicative of an increased risk of said individual of sudden cardiac death (SCD);

the results of the objective function being used by a decision-support algorithm to determine a quantitative risk for SCD; and

the decision-support algorithm comprising at least one of a support vector machine, logistic regression equation, or a neural network.

2. The computer-readable storage devices of claim 1, wherein the objective function evaluates digitized electrocardiographic waveforms from one or a plurality of previous time intervals to classify a likelihood of a cascade of events leading to SCD within a future time interval.

3. The computer-readable storage devices of claim 1, wherein the Lyapunov exponent is evaluated on one or a plurality of ECG or other physiologic variables as functions of time.

4. The computer-readable storage devices of claim 1, wherein the decision-support algorithm comprises a support vector machine utilizing timeseries of calculated ECG variables including:

width of root-mean-square (RMS) T-wave, total cosine T-wave dispersion, T-wave loop dispersion, normalized T-wave loop area, and relative T-wave residuum.

5. The computer-readable storage devices of claim 1, wherein the decision-support algorithm comprises a combination of two or more of a Lyapunov-based algorithm, a decision tree algorithm, or a support vector machine.

6. The computer-readable storage devices of claim 1, wherein the QTdSI is determined as a function of a continuous QT interval timeseries.

7. The computer-readable storage devices of claim 1, wherein the QTdSI is determined as a function of a discrete QT interval timeseries.

8. The computer-readable storage devices of claim 1, wherein the Lyapunov exponent is calculated for each new heart beat.

9. The computer-readable storage devices of claim 1, wherein the timeseries comprises approximately 400 samples.

10. The computer-readable storage devices of claim 1, wherein the objective function comprises a second-order polynomial function determined using Taylor series regression or spectral analysis.

11. A method for automatically providing a notification for ventricular arrhythmias in an individual that are likely to result in sudden cardiac death (SCD), the method comprising:

obtaining, from one or more sensors, ECG signals representative of electrical activity of the heart of said individual; and

determining, utilizing an objective function, a QT dispersion stability index (QTdSI) from said signals, the objective function comprising a timeseries calculated from serially-acquired waveform data as functions of time the determining comprising calculating a moving average of Lyapunov exponents of a plurality of ECG or other physiologic variables;

determining a difference between the determined QTdSI and a reference value to detect the presence of instability of QT interval dispersion or other measurements in said signals;

a significant difference being indicative of an increased risk of said individual of SCD; and

providing a notification to a health care provider when said increased risk for SCD is indicated;

the results of the objective function being used by a decision-support algorithm to determine a quantitative risk for SCD; and

the decision-support algorithm comprising at least one of a support vector machine, logistic regression equation, or a neural network.

12. The method of claim 11, wherein the objective function evaluates digitized electrocardiographic waveforms from one or a plurality of previous time intervals to classify a likelihood of a cascade of events leading to SCD within a future time interval.

13. The method of claim 11, wherein the decision-support algorithm comprises a support vector machine utilizing timeseries of calculated ECG variables including:

width of root-mean-square (RMS) T-wave, total cosine T-wave dispersion, T-wave loop dispersion, normalized T-wave loop area, and relative T-wave residuum.

14. The method of claim 11, wherein the decision-support algorithm comprises a combination of two or more of a Lyapunov-based algorithm, a decision tree algorithm, or a support vector machine.

15. The method of claim 11, wherein the QTdSI is determined as a function of a continuous QT interval timeseries.

16. The method of claim 11, wherein the QTdSI is determined as a function of a discrete QT interval timeseries.