A61B5/316

Reduced power machine learning system for arrhythmia detection

Techniques are disclosed for using feature delineation to reduce the impact of machine learning cardiac arrhythmia 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 arrhythmia 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 arrhythmia.

Reduced power machine learning system for arrhythmia detection

Techniques are disclosed for using feature delineation to reduce the impact of machine learning cardiac arrhythmia 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 arrhythmia 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 arrhythmia.

Control method and system for filtering power line interferences

A control method and system for filtering power line interference is disclosed. The control method includes the following steps. First, ECG signals are pre-segmented and rectified; then the sinusoidal frequency, amplitude, and phase of the rectified segmented signals are extracted. These estimated sinusoidal parameters from each recorded channel are weighted by their individual signal to noise ratios before being averaged to achieve the optimal powerline frequency, amplitude, and phase. Based on these optimal sinusoidal parameters, the individual sinusoidal waveform is reconstructed and then is subtracted from the corresponding ECG segment, in order to obtain the clean ECG signals. This method of filtering the powerline interference through removal from recorded signals enables accurate measurement without any ringing effect that could lead to signal distortion issues. Thus this invention solves the ringing problem encountered by traditional notch filter techniques when signal amplitude suddenly changes in a measurement.

Methods and systems for electroporation

This document describes methods and materials for improving the delivery of electroporation. For example, this document describes methods and devices for delivering electroporation while mitigating risks of ventricular fibrillation.

Methods and systems for electroporation

This document describes methods and materials for improving the delivery of electroporation. For example, this document describes methods and devices for delivering electroporation while mitigating risks of ventricular fibrillation.

Device and method for detecting ventricular fibrillation

The present invention relates to a medical device, in particular to an implantable medical device, comprising at least one implantable or non-implantable hemodynamic sensor configured for detecting hemodynamic cardiac signals, a controller configured for processing and analyzing the detected cardiac hemodynamic signals or signals derived from the detected cardiac hemodynamic signals by applying to said signals a Teager Energy Operator (TEO). The controller further comprises at least one algorithm configured to determine the need for a defibrillation operation by taking into account the at least one output hemodynamic signal. The present invention also provides a method and software for detecting or treating a ventricular fibrillation episode by taking into account cardiac hemodynamic signals.

Apparatus and method for measuring electrode impedance during electrophysiological measurements

The present disclosure is related to methods, systems and apparatus for performing electrophysiological measurements utilizing three or more electrodes attached to a patient. The system in various embodiments may include three or more electrodes attached to the patient and at least one analog-to-digital converter with external circuitry electrically coupled to the electrodes. The system may further include a microprocessor for driving the analog-to-digital conversion process, various inputs and variable frequency current outputs electrically coupled to the microprocessor for receiving signals from the electrodes and sending driven current signals to the electrodes.

Apparatus and method for measuring electrode impedance during electrophysiological measurements

The present disclosure is related to methods, systems and apparatus for performing electrophysiological measurements utilizing three or more electrodes attached to a patient. The system in various embodiments may include three or more electrodes attached to the patient and at least one analog-to-digital converter with external circuitry electrically coupled to the electrodes. The system may further include a microprocessor for driving the analog-to-digital conversion process, various inputs and variable frequency current outputs electrically coupled to the microprocessor for receiving signals from the electrodes and sending driven current signals to the electrodes.

Method of searching optimal zones for electropulse therapy (variants)

The invention comprises providing electric stimuli, which are generated by forming the following ringing circuit: active electrode—inductive storage unit—passive electrode—interelectrode tissues—active electrode, the electric stimuli creating oscillations which are used as a test signal. In one variant of the method, the electrodes are successively applied (in another variant—moved uniformly) across the skin area. Every time the electrodes-to-skin contact is detected, the oscillation parameters are recorded after a delay. Moreover, the values of parameters can be averaged. The invention allows for both combined and disjointed (i.e. separated) electrode placement. An optimal zone for electropulse therapy is identified by a minimal or maximal value of one or more parameters of the aforementioned oscillations and the use of the principle of small asymmetry. The invention further provides for an increase in the accuracy with which zones optimal for electropulse therapy are identified and localized.

Method of searching optimal zones for electropulse therapy (variants)

The invention comprises providing electric stimuli, which are generated by forming the following ringing circuit: active electrode—inductive storage unit—passive electrode—interelectrode tissues—active electrode, the electric stimuli creating oscillations which are used as a test signal. In one variant of the method, the electrodes are successively applied (in another variant—moved uniformly) across the skin area. Every time the electrodes-to-skin contact is detected, the oscillation parameters are recorded after a delay. Moreover, the values of parameters can be averaged. The invention allows for both combined and disjointed (i.e. separated) electrode placement. An optimal zone for electropulse therapy is identified by a minimal or maximal value of one or more parameters of the aforementioned oscillations and the use of the principle of small asymmetry. The invention further provides for an increase in the accuracy with which zones optimal for electropulse therapy are identified and localized.