Medical device for detecting a ventricular arrhythmia event

1. A method for a medical device for detecting a ventricular arrhythmia event comprising:

receiving an electrocardiogram (ECG) signal by way of input circuitry;

identifying a first P onset, a first Q onset, and a first S offset within a first heartbeat signal, a second P onset, a second Q onset, and a second S offset within a second heartbeat signal, and a third P onset, a third Q onset, and a third S offset within a third heartbeat signal of the ECG signal by way of processing circuitry coupled to the input circuitry, wherein the first heartbeat signal, the second heartbeat signal, and the third heartbeat signal are generated from three consecutive heartbeats;

determining QP interval variability from the first Q onset, the second P onset, the second Q onset, and the third P onset and SP interval variability from the first S offset, the second P onset, the second S offset, and the third P onset by way of feature extraction circuitry coupled to the processing circuitry; and

detecting a ventricular arrhythmia based on the QP interval variability and the SP interval variability by way of machine learning circuitry coupled to the feature extraction circuitry.

2. The method for the medical device of claim 1 wherein:

identifying further comprises identifying a first R peak and a first T onset within the first heartbeat signal and a second R peak and a second T onset within the second heartbeat signal by way of the processing circuitry;

determining further comprises determining RT interval variability from the first R peak, the first T onset, the second R peak, and the second T onset by way of the feature extraction circuitry; and

detecting further comprises detecting ventricular arrhythmia based upon the QP interval variability, the SP interval variability, and the RT interval variability by way of the machine learning circuitry.

3. The method for the medical device of claim 1 wherein:

identifying further comprises identifying a first R peak and a first T onset within the first heartbeat signal, a second R peak and a second T onset within the second heartbeat signal, and a third R peak and a third T onset within the third heartbeat signal by way of the processing circuitry;

determining further comprises determining RT interval variability from the first R peak, the first T onset, the second R peak, and the second T onset and determining TR interval variability from the first T onset, the second R peak, the second T onset, and the third R peak by way of the feature extraction circuitry; and

detecting further comprises detecting ventricular arrhythmia based upon the QP interval variability, the SP interval variability, the RT interval variability, and the TR interval variability by way of the machine learning circuitry.

4. The method for the medical device of claim 1 wherein:

identifying further comprises identifying a first R peak and a first T onset within the first heartbeat signal, a second R peak and a second T onset within the second heartbeat signal, and a third R peak and a third T onset within the third heartbeat signal by way of the processing circuitry;

determining further comprises determining RT interval variability from the first R peak, the first T onset, the second R peak, and the second T onset, determining TR interval variability from the first T onset, the second R peak, the second T onset, and the third R peak, and determining PQ interval variability from the first P onset, the first Q onset, the second P onset, and the second Q onset by way of the feature extraction circuitry; and

detecting further comprises detecting ventricular arrhythmia based upon the QP interval variability, the SP interval variability, the RT interval variability, the TR interval variability, and the PQ interval variability by way of the machine learning circuitry.

5. The method for the medical device of claim 1 wherein:

identifying further comprises identifying a first R peak and a first T onset within the first heartbeat signal, a second R peak and a second T onset within the second heartbeat signal, and a third R peak and a third T onset within the third heartbeat signal by way of the processing circuitry;

determining further comprises determining RT interval variability from the first R peak, the first T onset, the second R peak, and the second T onset, determining TR interval variability from the first T onset, the second R peak, the second T onset, and the third R peak, determining PQ interval variability from the first P onset, the first Q onset, the second P onset, and the second Q onset, and determining PS interval variability from the first P onset, the first S offset, the second P onset, and the second S offset by way of the feature extraction circuitry; and

detecting further comprises detecting ventricular arrhythmia based upon the QP interval variability, the SP interval variability, the RT interval variability, the TR interval variability, the PQ interval variability, and the PS interval variability by way of the machine learning circuitry.

6. A medical device for detecting a ventricular arrhythmia event comprising:

input circuitry configured to receive an electrocardiogram (ECG) signal;

processing circuitry coupled to the input circuitry and configured to identify a first P onset, a first Q onset, and a first S offset within a first heartbeat signal, a second P onset, a second Q onset, and a second S offset within a second heartbeat signal, and a third P onset, a third Q onset, and a third S offset within a third heartbeat signal of the ECG signal, wherein the first heartbeat signal, the second heartbeat signal, and the third heartbeat signal are generated from three consecutive heartbeats;

feature extraction circuitry coupled to the processing circuitry and configured to determine QP interval variability from the first Q onset, the second P onset, the second Q onset and the third P onset and SP interval variability from the first S offset, the second P onset, the second S offset, and the third P onset; and

machine learning circuitry coupled to the feature extraction circuitry and configured to detect ventricular arrhythmia based on the QP interval variability and the SP interval variability.

7. The medical device of claim 6 wherein:

the processing circuitry is further configured to identify a first R peak and a first T onset within the first heartbeat signal and identify a second R peak and a second T onset within the second heartbeat signal;

the feature extraction circuitry is further configured to determine RT interval variability from the first R peak, the first T onset, the second R peak and the second T onset; and

the machine learning circuitry is further configured to detect ventricular arrhythmia based upon the QP interval variability, the SP interval variability, and the RT interval variability.

8. The medical device of claim 6 wherein:

the processing circuitry is further configured to identify a first R peak and a first T onset within the first heartbeat signal, identify a second R peak and a second T onset within the second heartbeat signal, and identify a third R peak and third T onset within the third heartbeat signal;

the feature extraction circuitry is further configured to determine RT interval variability from the first R peak, the first T onset, the second R peak, and the second T onset, and determine TR interval variability from the first T onset, the second R peak, the second T onset, and the third R peak; and

the machine learning circuitry is further configured to detect ventricular arrhythmia based upon the QP interval variability, the SP interval variability, the RT interval variability, and the TR interval variability.

9. The medical device of claim 6 wherein:

the processing circuitry is further configured to identify a first R peak and a first T onset within the first heartbeat signal, identify a second R peak and a second T onset within the second heartbeat signal, and identify a third R peak and third T onset within the third heartbeat signal;

the feature extraction circuitry is further configured to determine RT interval variability from the first R peak, the first T onset, the second R peak, and the second T onset, determine TR interval variability from the first T onset, the second R peak, the second T onset, and the third R peak, and determine PQ interval variability from the first P onset, the first Q onset, the second P onset, and the second Q onset; and

the machine learning circuitry is further configured to detect ventricular arrhythmia based upon the QP interval variability, the SP interval variability, the RT interval variability, the TR interval variability, and the PQ interval variability.

10. The medical device of claim 6 wherein:

the processing circuitry is further configured to identify a first R peak and a first T onset within the first heartbeat signal, identify a second R peak and a second T onset within the second heartbeat signal, and identify a third R peak and third T onset within the third heartbeat signal;

the feature extraction circuitry is further configured to determine RT interval variability from the first R peak, the first T onset, the second R peak, and the second T onset, determine TR interval variability from the first T onset, the second R peak, the second T onset, and the third R peak, determine PQ interval variability from the first P onset, the first Q onset, the second P onset, and the second Q onset, and determine PS interval variability from the first P onset, the first S offset, the second P onset, and the second S offset; and

the machine learning circuitry is further configured to detect ventricular arrhythmia based upon the QP interval variability, the SP interval variability, the RT interval variability, the TR interval variability, the PQ interval variability, and the PS interval variability.