Medtronic, Inc.

Medtronic Monitoring, Inc.

Greatbatch Ltd.

Corventis, Inc.

Greatbach Ltd.

Rodolphe Katra

Niranjan Chakravarthy

Andrew Radtke

Tarek D Haddad

Donald R Musgrove

Lindsay A Pedalty

Siddharth Dani

Imad Libbus

Scott Kimmel

Scott Williams

Eduardo N Warman

Jonathan L Kuhn

Arthur Lai

John E Burnes

James Kevin Carney

Lawrence Kane

Jesper Svenning Kristensen

Brion C Finlay

Daniel Chase

Mark J Phelps

Avram Scheiner

Yong Kyun Cho

Can Cinbis

Thomas J Mullen

David A Anderson

Richard J O'Brien

Walter John Dobrovolny

Rajan Prakash

Kevin Pietsch

Tyler Stigen

John C Doerfler

Jordon D Honeck

Grant Alexander Scheibe

Jeffrey Zweber

Blane Larson

Michael Erich Jordan

Andrew C Frye

Amie Bucksa

Matthew Edelman

Brian Loushine

Ed Goff

Amie K Bucksa

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

A method of non-invasively monitoring hemoglobin concentration includes providing incident light to patient tissue at a first excitation wavelength. The method further includes monitoring a first emission response at a first emission wavelength, wherein the first emission wavelength is selected to correspond with a maximum of the emission response, and monitoring a second emission response at a second emission wavelength, wherein the second emission wavelength is selected to correspond with a minimum of the emission response. A hemoglobin concentration is calculated based on a ratio of the first emission response to the second emission response.

System and method for non-invasive monitoring of hemoglobin

A method of determining signal quality in a patient monitoring device includes acquiring one or more signals using the patient monitoring device. One or more signal quality metrics are determined based on the one or more acquired signals. A noise condition is detected based on the one or more signal quality metrics, and a determination is made whether the noise condition should be classified as intermittent or persistent. One or more actions are taken based on the classification of detected noise as intermittent or persistent.

System and method of patient monitoring and signal quality analysis

Techniques are disclosed for detecting arrhythmia episodes for a patient. A medical device may receive one or more sensor values indicative of motion of a patient. The medical device may determine, based at least in part on the one or more sensor values, an activity level of the patient. The medical device may determine a heart rate threshold for triggering detection of an arrhythmia episode based at least in part on the activity level of the patient. The medical device may determine whether to trigger detection of the arrhythmia episode for the patient based at least in part on comparing a heart rate of the patient with the heart rate threshold. The medical device may, in response to triggering detection of the arrhythmia episode, collect information associated with the arrhythmia episode.

Triggering arrhythmia episodes for heart failure and chronotropic incompetence diagnosis and monitoring

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

A method of non-invasively monitoring hematocrit levels includes monitoring a first emission response to the light provided at the first excitation wavelength, wherein the first emission response is monitored at a first wavelength and monitoring a second emission response to the light provided at the first excitation wavelength, wherein the second emission response is monitored at a second wavelength. A ratiometric value is calculated based on a ratio of the first emission response to the second emission response, wherein the ratiometric value corresponds with hematocrit level of the patient.

System and method for non-invasive monitoring of hematocrit concentration

Techniques for remote monitoring of a patient and corresponding medical device(s) are described. The remote monitoring comprises determining identification data and identifying implantable medical device (IMD) information, initiating an imaging device and determining an imaging program, receiving one or more frames of image data including image(s) of an implantation site, identifying an abnormality at the implantation site, triggering a supplemental image capture mode, receiving one or more supplemental images of the implantation site, and outputting the one or more supplemental images of the implantation site.

Post operative implantation site monitoring

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

In some examples, a medical system includes a medical device. The medical device may include a housing configured to be implanted in a target site of a patient, a light emitter configured to emit a signal configured to cause a fluorescent marker to emit a fluoresced signal into the target site, and a light detector that may be configured to detect the fluoresced signal. The medical system may include processing circuitry configured to determine a characteristic of the fluorescent marker based on the emitted signal and the fluoresced signal. The characteristic of the fluorescent marker may be indicative of a presence of a compound in the patient, and the processing circuitry may be configured to track the presence of the compound of the patient based on the characteristic of the fluorescent marker.

Marker monitoring via a medical device

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

In some examples, a computing device may receive diagnostic data of a medical device implanted in a patient. The computing device may determine a use case associated with analyzing the diagnostic data out of a plurality of use cases for analyzing the diagnostic data. The computing device may determine, based at least in part on the use case, one or more device characteristics data to be compared against the diagnostic data. The computing device may analyze, based at least in part on comparing the diagnostic data with the one or more device characteristics data, the diagnostic data to determine an operating status of the medical device.

System and method for core-device monitoring

A method of non-invasively monitoring advanced glycation end-product (AGE) concentrations includes providing incident light to patient tissue at one or more excitation wavelengths and monitoring the one or more emission responses at one or more emission wavelengths. Based on the emission responses monitored, a ratio is calculated based on a ratio of the first emission response to the second emission response.

System and method for non-invasive monitoring of advanced glycation end-products (AGE)

Growing community of inventors

Blaine, MN, United States of America

Rodolphe Katra