Identifying ECG signals having the same morphology

An apparatus, comprising:

• a set of electrodes configured to be positioned in a heart of a human subject for acquiring electrocardiograph (ECG) signals over a plurality of channels;
• and
• a processor, configured for:
• processing a first set of electrocardiograph (ECG) signals taken over a single heartbeat of a human subject;
• receiving reference annotations of the first set of ECG signals;
• selecting a subset of the first set of ECG signals captured at a point in time with a window of interest (WOI) time period around the reference annotations of the first set of ECG signals, the subset of signals each having a morphology pattern within the WOI;
• storing the morphology patterns of the subset of ECG signals;
• receiving continuous sets of ECG signals taken over a plurality of heartbeats of the human subject, the continuous sets of ECG signals being received over the plurality of channels, each of the continuous sets of ECG signals having a morphology pattern within a time period equal to the WOI time period for each heartbeat;
• performing a correlation between the stored morphology patterns of the first set of ECG signals and the morphology patterns of each of the continuous sets of ECG signals for each heartbeat;
• generating for each heartbeat of the plurality of heartbeats a correlation coefficient that is a measure of a goodness of fit between geometries of the first set of ECG signals and each of the continuous sets of ECG signals;
• and
• identifying each heartbeat of the plurality of heartbeats having a correlation coefficient that exceeds a threshold coefficient as having been caused by an arrhythmia.

A computer program product comprising:

• program instructions on a non-transitory computer-readable storage medium, where execution of the program instructions using a computer causes the computer to perform a method, comprising:
• processing a first set of electrocardiograph (ECG) signals taken over a single heartbeat of a human subject, the first set of ECG signals being received over a plurality of channels;
• receiving reference annotations of the first set of ECG signals;
• selecting a subset of the first set of ECG signals captured at a point in time with a window of interest (WOI) time period around the reference annotations of the first set of ECG signals, the subset of signals each having a morphology pattern within the WOI;
• storing the morphology patterns of the subset of ECG signals;
• receiving continuous sets of ECG signals taken over a plurality of heartbeats of the human subject, the continuous sets of ECG signals being received over the plurality of channels, each of the continuous sets of ECG signals having a morphology pattern within a time period equal to the WOI time period for each heartbeat;
• performing a correlation between the stored morphology patterns of the first set of ECG signals and the morphology patterns of each of the continuous sets of ECG signals for each heartbeat;
• generating for each heartbeat of the plurality of heartbeats a correlation coefficient that is a measure of a goodness of fit between geometries of the first set of ECG signals and each of the continuous sets of ECG signals;
• and
• identifying each heartbeat of the plurality of heartbeats having a correlation coefficient that exceeds a threshold coefficient as having been caused by an arrhythmia.