Techniques are disclosed for using feature delineation to reduce the impact of machine learning cardiac arrythmia detection on power consumption of medical devices. In one example, a medical device performs feature-based delineation of cardiac electrogram data sensed from a patient to obtain cardiac features indicative of an episode of arrythmia in the patient. The medical device determines whether the cardiac features satisfy threshold criteria for application of a machine learning model for verifying the feature-based delineation of the cardiac electrogram data. In response to determining that the cardiac features satisfy the threshold criteria, the medical device applies the machine learning model to the sensed cardiac electrogram data to verify that the episode of arrhythmia has occurred or determine a classification of the episode of arrythmia.

Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.

Described herein are methods, devices, and systems that improve arrhythmia episode detection specificity, such as, but not limited to, atrial fibrillation (AF) episode detection specificity. Such a method can include obtaining an ordered list of R-R intervals within a window leading up to a detection of a potential arrhythmia episode, determining a measure of a dominant repeated R-R interval pattern within the window, and comparing the measure of the dominant repeated R-R interval pattern to a pattern threshold. If the measure of the dominant repeated R-R interval pattern is below the pattern threshold, that is indicative of a regularly irregular pattern being present, and there is a determination that the detection of the potential arrhythmia episode does not correspond to an actual arrhythmia episode. Such embodiments can beneficially be used to significantly reduce the number of false positive arrhythmia detections.

A medical device is configured to deliver therapeutic electrical stimulation pulses by generating frequency modulated electrical stimulation pulse signals. The medical device includes a pulse signal source and a modulator. The pulse signal source generates an electrical stimulation pulse signal having a pulse width. The modulator may include a high frequency modulator configured to modulate a frequency of the pulse signal from a starting frequency down to a minimum frequency during the pulse width. The modulator may include a low frequency bias generator to modulate the offset of the pulse signal between a minimum offset and a maximum offset in other examples.

Described herein are methods, devices, and systems that improve arrhythmia episode detection specificity, such as, but not limited to, atrial fibrillation (AF) episode detection specificity. Such a method can include obtaining an ordered list of R-R intervals within a window leading up to a detection of a potential arrhythmia episode, determining a measure of a dominant repeated R-R interval pattern within the window, and comparing the measure of the dominant repeated R-R interval pattern to a pattern threshold. If the measure of the dominant repeated R-R interval pattern is below the pattern threshold, that is indicative of a regularly irregular pattern being present, and there is a determination that the detection of the potential arrhythmia episode does not correspond to an actual arrhythmia episode. Such embodiments can beneficially be used to significantly reduce the number of false positive arrhythmia detections.

This document describes methods and materials for mapping and modulating repolarization. For example, this document relates to methods and devices for mapping and modulating repolarization to target atrial and ventricular arrhythmias to deliver electrical stimulation pacing, ablation and/or electroporation.

Techniques that include applying machine learning models to episode data, including a cardiac electrogram, stored by a medical device are disclosed. In some examples, based on the application of one or more machine learning models to the episode data, processing circuitry derives, for each of a plurality of arrhythmia type classifications, class activation data indicating varying likelihoods of the classification over a period of time associated with the episode. The processing circuitry may display a graph of the varying likelihoods of the arrhythmia type classifications over the period of time. In some examples, processing circuitry may use arrhythmia type likelihoods and depolarization likelihoods to identify depolarizations, e.g., QRS complexes, during the episode.

A method and medical device for determining sensing vectors that includes sensing cardiac signals from a plurality of electrodes, the plurality of electrodes forming a plurality of sensing vectors, determining a sensing vector metric in response to the sensed cardiac signals, determining a morphology metric associated with a morphology of the sensed cardiac signals, determining vector selection metrics in response to the determined sensing vector metric and the determined morphology setting, and selecting a sensing vector of the plurality of sensing vectors in response to the determined vector selection metrics.

An extra-cardiovascular implantable cardioverter defibrillator (ICD) system receives a cardiac electrical signal by an electrical sensing circuit via an extra-cardiovascular sensing electrode vector and senses cardiac events from the cardiac electrical signal. The ICD system detects tachycardia from the cardiac electrical signal and determines a tachycardia cycle length from the cardiac electrical signal. The ICD system determines an ATP interval based on the tachycardia cycle length and sets an extended ATP interval that is longer than the ATP interval. The ICD delivers ATP pulses to a patient's heart via an extra-cardiovascular pacing electrode vector different than the sensing electrode vector. The ATP pulses include a leading ATP pulse delivered at the extended ATP interval after a cardiac event is sensed from the cardiac electrical signal and a second ATP pulse delivered at the ATP interval following the leading ATP pulse.

Techniques are disclosed for monitoring a patient for the occurrence of a cardiac arrhythmia. A computing system generates sample probability values by applying a machine learning model to sample patient data. The machine learning model determines a respective probability value that indicates a probability that the cardiac arrhythmia occurred during each respective temporal window. The computing system outputs a user interface comprising graphical data based on the sample probability values and receives, via the user interface, an indication of user input to select a probability threshold for a patient. The computing system receives patient data for the patient and applies the machine learning model to the patient data to determine a current probability value. In response to the determination that the current probability exceeds the probability threshold for the patient, the computing system generates an alert indicating the patient has likely experienced the occurrence of the cardiac arrhythmia.