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 medical device is configured to sense event signals from a cardiac electrical signal and determine maximum amplitudes of cardiac electrical signal segments associated with sensed event signals. The medical device is configured to determine at least one tachyarrhythmia metric based on at least a greatest one of the determined maximum amplitudes. The medical device may determine when the at least one tachyarrhythmia metric does not meet true tachyarrhythmia evidence and, in response, determine when the maximum amplitudes meet suspected noise criteria. The medical device may withhold a tachyarrhythmia detection and tachyarrhythmia therapy when suspected noise criteria are met.

A medical device such as an external defibrillator delivers electrical therapy using a special pulse sequence. The special pulse sequence includes a defibrillation shock that is automatically followed by a quick succession of automatic post-shock anti-tachycardia (APSAT) pacing pulses. Because of the pacing pulses, the defibrillation shock can be of lesser energy than an equivalent defibrillation shock of a larger energy. Accordingly, the external defibrillator can be made physically smaller and weigh less, without sacrificing the therapeutic effect of a larger external defibrillator that would deliver a defibrillation shock of higher energy. As such, the defibrillator is easier to configure for transporting, handling, and even wearing.

A computer implemented method for detecting pocket stability for an implantable cardiac monitor, including under control of one or more processors in the ICM, collecting impedance data over at least one cardiac cycle. The impedance data is processed to separate an impedance waveform that varies over the at least one cardiac cycle in a manner representative of cardiac functionality over the at least one cardiac cycle. A characteristic of interest is analyzed from the impedance waveform over the at least one cardiac cycle. A pocket stability state of the ICM is identified and recorded based on the analyzing operation.

An apparatus for terminating or unpinning rotating electric activity in a cardiac tissue analyzes an electric parameter for rotating electric activity in the cardiac tissue, and generates electric pulses in response to the rotating electric activity. The electric pulses are applied as electric field pulses and include a plurality of rotating electric activity synchronization pulses arranged at first intervals and a rotating electric activity termination or unpinning pulse following to the last synchronization pulse at a second interval which is similar to one of the first intervals. A maximum electric field strength caused the synchronization pulses is not more than 82% of a maximum electric field strength caused by the termination or unpinning pulse, and an electric pulse energy delivered to the cardiac tissue by each of the synchronization pulses is not more than 67% of an electric pulse energy delivered by the termination or unpinning pulse.

Systems, devices, and techniques that enable medical devices to integrate and interoperate with one another are provided. In some examples, a wearable cardiac defibrillator (WCD) advantageously interoperates with an implanted pacemaker to provide a variety of benefits. For instance, in some examples, the WCD oversees execution of an antitachycardia (ATP) protocol by the implanted pacemaker and intervenes as needed. In other examples, the WCD drives an ATP protocol in which internal pacing pulses are provided by the implanted pacemaker under the control of the WCD. In other examples, the WCD monitors the activity of the implanted pacemaker to identify potential maintenance issues affecting the implanted pacemaker. The WCD and the implanted pacemaker may also interoperate to classify and act upon particular arrhythmia conditions.

A stimulation device includes an energy source; an electronics unit; an actuator that is coupled with the electronics unit and/or the energy source. The electronics unit includes a controller. The energy source, the electronics unit and the actuator are arranged in a housing. A fixing unit which is coupled with the housing and affixes the stimulation device on a heart or in a heart. The actuator emits electromagnetic waves for the stimulation of genetically manipulated tissue, and the controller controls the stimulation of the tissue by way of the electromagnetic waves of the actuator.

A patient-worn ambulatory cardiac monitoring device for monitoring a patient during a patient activity includes at least one physiological sensor configured to detect signals indicative of cardiac activity, an activity sensor and associated circuitry configured to monitor patient movements, and a vibrational sensor configured to monitor a cardio-vibrational signal of the patient. The at least one physiological sensor can include one of an ECG sensor and a heart rate sensor. At least one processor in communication with the at least one physiological sensor, the activity sensor, and the vibrational sensor, is configured to measure, during the patient activity, at least one time interval between an ECG fiducial point in an ECG signal and a cardio-vibrational fiducial point in the cardio-vibrational signal during a cardiac cycle of the patient’s heart.

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.

A medical device is configured to receive sensed cardiac event data including a value of a feature determined from each one of a plurality of cardiac events sensed from a cardiac signal according to a first setting of a sensing control parameter. The medical device is configured to classify each value of the feature of each one of the sensed cardiac events as either a predicted sensed event or a predicted undersensed event according to a second setting of the sensing control parameter that is less sensitive to sensing cardiac events than the first setting. The medical device is configured to determine a predicted sensed event interval between each consecutive pair of the predicted sensed events and predict that an arrhythmia is detected or not detected based on the predicted sensed event intervals.