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.

An example medical device system includes therapy delivery circuitry configured to deliver anti-tachycardia pacing (ATP) therapy to a heart of a patient via electrodes communicatively coupled to the therapy delivery circuitry. The ATP therapy includes one or more ATP trains. The medical device system also includes processing circuitry configured determine a first propagation time based on a comparison of features in a local electrogram and a far-field electrogram, such as the time from a fiducial point in the local electrogram and QRS onset in the far-field electrogram. The processing circuitry is also configured to determine, based on the first propagation time, a number of pulses to achieve a second propagation time and control the therapy delivery circuitry to deliver the ATP train of at least the number of pulses.

A subcutaneously implantable device includes a housing, a clip attached to the housing, a prong, and an electrode. The clip is configured to anchor the device to a muscle, a bone, and/or a first tissue. The prong has a base portion attached to the housing, an arm portion extending from the base portion so as to define a first plane that includes opposite ends of the arm portion of the prong and is perpendicular to a horizontal plane of the housing, and a contact portion that is configured to contact an organ, a nerve, the first tissue, and/or a second tissue. The contact portion is angled away from the first plane. The electrode is at the contact portion of the prong. The electrode is configured to contact the organ, the nerve, the first tissue, and/or a second tissue. Circuitry in the housing is in electrical communication with the electrode and is configured to provide monitoring, therapeutic, and/or diagnostic capabilities with respect to the organ, the nerve, the first tissue, and/or the second tissue.

A medical device system, such as an extra-cardiovascular implantable cardioverter defibrillator ICD, senses R-waves from a first cardiac electrical signal by a first sensing channel and stores a time segment of a second cardiac electrical signal in response to each sensed R-wave. The medical device system determines a morphology parameter correlated to signal noise from time segments of the second cardiac electrical signal, detects a noisy signal segment based on the signal morphology parameter; and withholds detection of a tachyarrhythmia episode in response to detecting a threshold number of noisy signal segments.

A system for guiding implantation of an energy delivery component of a cardiac pacing device at a fixation location within a heart of a patient is provided. During a procedure to implant an energy pulse delivery component, the system receives a patient cardiogram collected during pacing of the energy pulse delivery component while the energy pulse delivery component is positioned at a current location within the heart. The system then determines based on the patient cardiogram the current location of the energy pulse delivery component. The system then outputs an indication of the current location to guide affixing of the energy pulse delivery component at the intended fixation location. This process is repeated until the energy pulse delivery component is at the fixation location. The system also evaluates the effectiveness of pacing at intermediate location to optimize the final location based upon simulated electro-mechanics of the system in near-real time.

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 that includes a power source, a therapy delivery interface, therapy electrodes, electrocardiogram (ECG) sensing electrodes to sense ECG signal of a heart of a patient, a sensor interface to receive and digitize the ECG signal, and a processor. The processor is configured to analyze the ECG signal to determine a cardiac rhythm and a transform value representing a magnitude of a frequency component of the cardiac rhythm, analyze the cardiac rhythm and the transform value to detect a shockable cardiac arrhythmia by classifying the cardiac rhythm as a noise rhythm or a shockable cardiac arrhythmia rhythm based on the transform value, and causing the processor to detect the cardiac arrhythmia if classifying the cardiac rhythm as a shockable cardiac arrhythmia rhythm, initiate a treatment alarm sequence, adjust the shock delivery parameter for a defibrillation shock, and provide the defibrillation shock via the therapy electrodes.

An analysis device for supporting the implantation of a system for stimulating the human heart or animal heart, comprising a processor and a memory unit. The memory unit includes a computer-readable program, which prompts the processor to carry out the following steps when the program is being executed on the processor: a) receiving an electrocardiogram of a human heart or an animal heart into which a system for stimulating this heart is being implanted; b) automatically identifying signals of the electrocardiogram caused by a His bundle stimulation, a signal being identified which appears between an atrial signal and a ventricular signal; c) marking the previously identified signals in the received electrocardiogram; and d) outputting the electrocardiogram thus marked on an output device. The analysis device comprises a detection unit having a sensitivity of at least 0.25 mV.

Techniques are disclosed for determining, by an extracardiovascular implantable cardioverter defibrillator (ICD) implanted in a patient, whether one or more test therapy signals generated by another medical device implanted in the patient is detected. In response to detecting the one or more test therapy signals, the extracardiovascular ICD provides an indication that the extracardiovascular ICD has detected the one or more test therapy signals. In some examples, the indication is an audible tone provided to a clinician. In some examples, the other medical device is an intracardiac cardiac pacing device, and the one or more test therapy signals comprises a plurality of anti-tachycardia pacing (ATP) pulses.

A method includes, receiving from a calibration probe multiple data points acquired in an organ of a patient, each data point including (i) a respective position of the calibration probe, and (ii) a respective set of electrical values indicative of respective impedances between the position and multiple electrodes attached externally to the patient. A mapping between sets of the electrical values and respective positions in the organ is constructed, by performing for each received data point: if the mapping already contains one or more existing data points in a predefined vicinity of the data point, the one or more existing data points are adjusted responsively to the received data point, and if the predefined vicinity does not contain any existing data points, the received data point is added to the mapping. A position of a medical probe is subsequently tracked in the organ using the mapping.