System and method for distinguishing a cardiac event from noise in an electrocardiogram (ECG) signal

1. A cardiac monitoring device comprising:

at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from a patient;

a processing unit comprising at least one processor operatively coupled to the at least one sensing electrode; and

at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the cardiac monitoring device to:

obtain the ECG signal from the at least one sensing electrode;

determine a transformed ECG signal based on the ECG signal;

extract at least one value representing at least one feature of the transformed ECG signal;

provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score;

compare the ECG-derived score to a predetermined threshold score determined by machine learning; and

provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score,

wherein the machine learning is one of a multivariate adaptive regression splines classifier and a neural network classifier.

2. The cardiac monitoring device of claim 1 , wherein the transformed ECG signal comprises a frequency-domain representation of the ECG signal.

3. The cardiac monitoring device of claim 1 , wherein the transformed ECG signal comprises a representation of a power distribution of the ECG signal over a range of frequencies of the ECG signal.

4. The cardiac monitoring device of claim 1 , wherein the transformed ECG signal comprises a power spectral density (PSD) of the ECG signal, the PSD being determined by calculating a fast Fourier transform (FFT) of the ECG signal.

5. The cardiac monitoring device of claim 4 , wherein determining the PSD comprises calculating the fast Fourier transform (FFT) of the ECG signal and performing a square of a modulus of the FFT to transform the FFT into a real number.

6. The cardiac monitoring device of claim 4 , wherein at least four features of the PSD are extracted and provided to the machine learning.

7. The cardiac monitoring device of claim 6 , wherein the at least four features of the PSD that are extracted are: at least one value representing a dominant frequency of the PSD; at least one value representing in-band entropy of the PSD between frequencies of 2 Hz and 6 Hz; at least one value representing first-band entropy of the PSD between frequencies of 0 Hz and 2 Hz; and at least one value representing a variance of the PSD.

8. The cardiac monitoring device of claim 1 , wherein the cardiac monitoring device is one of a wearable defibrillator, an implantable defibrillator, an automated external defibrillator (AED), a mobile cardiac telemetry device, an ECG rhythm classifier, a ventricular arrhythmia detector, and a Holter monitor.

9. The cardiac monitoring device of claim 1 , further comprising:

providing an instruction signal for taking an action based on the indication.

10. The cardiac monitoring device of claim 9 , wherein the action is at least one of applying a therapy to a patient and providing a warning signal to the patient.

11. The cardiac monitoring device of claim 9 , further comprising an alert device operatively coupled to the at least one processor for providing the instruction signal to the patient.

12. The cardiac monitoring device of claim 11 , wherein the alert device is configured to provide the instruction signal as at least one of an audio signal and a visual signal.

13. The cardiac monitoring device of claim 1 , wherein the program instructions that are executed by the at least one processor are initiated for a portion of the ECG signal that is stored in a memory device when the at least one processor detects a triggering event.

14. The cardiac monitoring device of claim 13 , wherein the portion of the ECG signal is a predetermined time period of the ECG signal that precedes the triggering event.

15. The cardiac monitoring device of claim 14 , wherein the predetermined time period is 20 seconds.

16. The cardiac monitoring device of claim 13 , wherein the triggering event is at least one of detection of a ventricular fibrillation (VF) in the ECG signal and detection of a ventricular tachycardia (VT) event in the ECG signal.

17. The cardiac monitoring device of claim 1 , wherein the indication of the cardiac event is provided if the ECG-derived score is one of above or below the predetermined threshold score.

18. A cardiac monitoring device comprising:

at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from a patient;

a processing unit comprising at least one processor operatively coupled to the at least one sensing electrode; and

at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the cardiac monitoring device to:

obtain the ECG signal from the at least one sensing electrode;

determine a transformed ECG signal based on the ECG signal;

extract at least one value representing at least one feature of the transformed ECG signal;

provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score;

compare the ECG-derived score to a predetermined threshold score determined by machine learning; and

provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score,

wherein the machine learning is based on a training data set comprising a collection of ECG signals associated with treatments performed by a plurality of defibrillators.

19. The cardiac monitoring device of claim 18 , wherein the collection of ECG signal includes at least noisy normal sinus rhythm signals and tachyarrhythmia signals.

20. A cardiac monitoring device comprising:

at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from a patient;

a processing unit comprising at least one processor operatively coupled to the at least one sensing electrode; and

at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the cardiac monitoring device to:

obtain the ECG signal from the at least one sensing electrode;

determine a transformed ECG signal based on the ECG signal;

extract at least one value representing at least one feature of the transformed ECG signal;

provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score;

compare the ECG-derived score to a predetermined threshold score determined by machine learning; and

provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score,

wherein the machine learning is based on a training data set comprising a collection of ECG signals stored in a memory of the cardiac monitoring device.

21. A cardiac monitoring device comprising:

at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from a patient;

a processing unit comprising at least one processor operatively coupled to the at least one sensing electrode; and

at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the cardiac monitoring device to:

obtain the ECG signal from the at least one sensing electrode;

determine a transformed ECG signal based on the ECG signal;

extract at least one value representing at least one feature of the transformed ECG signal;

provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score;

compare the ECG-derived score to a predetermined threshold score determined by machine learning; and

provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score,

wherein the transformed ECG signal comprises a power spectral density (PSD) of the ECG signal, the PSD being determined by calculating a fast Fourier transform (FFT) of the ECG signal and at least four features of the PSD are extracted and provided to the machine learning.

22. A cardiac monitoring device comprising:

at least one sensing electrode for obtaining an electrocardiogram (ECG) signal from a patient;

a processing unit comprising at least one processor operatively coupled to the at least one sensing electrode; and

at least one non-transitory computer-readable medium comprising program instructions that, when executed by the at least one processor, causes the cardiac monitoring device to:

obtain the ECG signal from the at least one sensing electrode;

determine a transformed ECG signal based on the ECG signal;

extract at least one value representing at least one feature of the transformed ECG signal;

provide the at least one value to determine a score associated with the ECG signal, thereby providing an ECG-derived score;

compare the ECG-derived score to a predetermined threshold score determined by machine learning; and

provide an indication of a cardiac event based on the comparison of the ECG-derived score with the predetermined threshold score,

wherein the transformed ECG signal comprises a power spectral density (PSD) of the ECG signal, the PSD being determined by calculating a fast Fourier transform (FFT) of the ECG signal and determining the PSD comprises calculating the fast Fourier transform (FFT) of the ECG signal and performing a square of a modulus of the FFT to transform the FFT into a real number.