Medtronic, Inc.

Tarek D Haddad

Andrew Radtke

Donald R Musgrove

Rodolphe Katra

Lindsay A Pedalty

Siddharth Dani

Niranjan Chakravarthy

Eduardo N Warman

Subham Ghosh

Jeffrey M Gillberg

Karen J Kleckner

Zhongping C Yang

Mark L Brown

Vinod Sharma

Paul J Degroot

Paul Anthony Iaizzo

Michael D Eggen

Brian Bruce Lee

Eric D Corndorf

Paul J DeGroot

Jeffrey David Wilkinson

Elizabeth A Schotzko

Michelle M Galarneau

Marc C Steckler

Mugdha V Tasgaonkar

Athula I Abeyratne

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 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.

Machine learning based depolarization identification and arrhythmia localization visualization

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.

Selection of probability thresholds for generating cardiac arrhythmia notifications

Techniques are disclosed for monitoring a patient for the occurrence of cardiac arrhythmias. A computing system obtains a cardiac electrogram (EGM) strip for a current patient. Additionally, the computing system may apply a first cardiac rhythm classifier (CRC) with a segment of the cardiac EGM strip as input. The first CRC is trained on training cardiac EGM strips from a first population. The first CRC generates first data regarding an aspect of a cardiac rhythm of the current patient. The computing system may also apply a second CRC with the segment of the cardiac EGM strip as input. The second CRC is trained on training cardiac EGM strips from a smaller, second population. The second CRC generates second data regarding the aspect of the cardiac rhythm of the current patient. The computing system may generate output data based on the first and/or second data.

Personalization of artificial intelligence models for analysis of cardiac rhythms

Techniques are disclosed for a multi-tier system for delivering therapy to a patient. In one example, a first device senses parametric data for a patient and determines, based on a first analysis of the parametric data, that the patient is experiencing a treatable event. In response, the first device establishes wireless communication with a second device and transmits the parametric data to the second device. The second device verifies, based on a second analysis of the parametric data, whether the patient is experiencing the treatable event. The second device selects, based on the second analysis of the parametric data, an instruction for responding to the treatable event and transmits the instruction for responding to the treatable event to the first device. In some examples, in response to receiving the instruction, the first device aborts delivery of therapy for the treatable event or proceeds with delivering therapy for the treatable event.

Tiered detection of treatable events

Techniques are disclosed for explaining and visualizing an output of a machine learning system that detects cardiac arrhythmia in a patient. In one example, a computing device receives cardiac electrogram data sensed by a medical device. The computing device applies a machine learning model, trained using cardiac electrogram data for a plurality of patients, to the received cardiac electrogram data to determine, based on the machine learning model, that an episode of arrhythmia has occurred in the patient and a level of confidence in the determination that the episode of arrhythmia has occurred in the patient. In response to determining that the level of confidence is greater than a predetermined threshold, the computing device displays, to a user, a portion of the cardiac electrogram data, an indication that the episode of arrhythmia has occurred, and an indication of the level of confidence that the episode of arrhythmia has occurred.

Visualization of arrhythmia detection by machine learning

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.

Arrhythmia detection with feature delineation and machine learning

Techniques are disclosed for a multi-tier system for predicting cardiac arrhythmia in a patient. In one example, a computing device processes parametric patient data and provider data for a patient to generate a long-term probability that a cardiac arrhythmia will occur in the patient within a first time period. In response to determining that the cardiac arrhythmia is likely to occur within the first time period, the computing device causes a medical device to process the parametric patient data to generate a short-term probability that the cardiac arrhythmia will occur in the patient within a second time period. In response to determining that the cardiac arrhythmia is likely to occur within the second time period, the medical device performs a remediative action to reduce the likelihood that the cardiac arrhythmia will occur.

Multi-tier prediction of cardiac tachyarrythmia

Systems and methods are described herein for evaluation and adjustment cardiac therapy. The systems and methods may initially evaluate a first pacing parameter while other pacing parameters are fixed to, for example, nominal values, and determine an effective setting for the first pacing parameter. Then, a second pacing parameter may be evaluated while the first pacing parameter is fixed to the previously-determined effective setting. Each evaluation may not test every possible setting for the pacing parameters, and instead, may utilize various processes to limit the settings to a subset of settings to test.

Systems and methods for evaluating cardiac therapy

Techniques are disclosed for automatically calibrating a reference orientation of an implantable medical device (IMD) within a patient. In one example, sensors of an IMD sense a plurality of orientation vectors of the IMD with respect to a gravitational field. Processing circuitry of the IMD processes the plurality of orientation vectors to identify an upright vector that corresponds to an upright posture of the patient. The processing circuitry classifies the plurality of orientation vectors with respect to the upright vector to define a sagittal plane of the patient and a transverse plane of the patient. The processing circuitry determines, based on the upright vector, the sagittal plane, and the transverse plane, a reference orientation of the IMD within the patient. As the orientation of the IMD within the patient changes over time, the processing circuitry may recalibrate its reference orientation and accurately detect a posture of the patient.

Growing community of inventors

Minneapolis, MN, United States of America

Tarek D Haddad