Pacesetter, Inc.

Kevin J Davis

Aditya Goil

Fady Dawoud

Fujian Qu

Nima Badie

Mostafa Sadeghi

Leyla Sabet

Christopher Gloschat

A system and method for determining an arrhythmia risk are provided and include memory to store specific executable instructions and a machine learning (ML) model trained to predict an arrhythmia with a characteristic of interest (COI) that exhibits a non-physiologic behavior. One or more processors are configured to execute the specific executable instructions to obtain CA signals collected by an implantable medical device (IMD), wherein the COI exhibits a physiologic behavior and apply the ML model to the CA signals to identify a risk factor that a patient will experience the arrhythmia at a future point in time even though the COI in the CA signals, exhibits a physiologic behavior.

Methods and systems for predicting arrhythmia risk utilizing machine learning models

Embodiments described herein can reduce a burden associated with analyzing EGM segments obtained from an IMD that monitors for arrhythmic episodes. Respective EGM data and respective classification data is obtained for each arrhythmic episode detected by the IMD during a period of time. A representative R-R interval or HR for each of the arrhythmic episodes is also obtained, wherein a manner for determining the representative R-R interval or HR depends on the type of the arrhythmic episode, such that for at least two different types of arrhythmic episodes the manners differ. One or more arrhythmic episodes is/are selected for which corresponding EGM segments are to be displayed for each type of arrhythmic episode, wherein the selecting is performed based on the representative R-R intervals or HRs that are determined for the plurality of arrhythmic episodes. Additional and alternative embodiments are also described herein.

Methods and systems for arrhythmia episode prioritization and improving arrhythmia detection and classification to reduce clinical review burden

Systems, methods, and devices are provided for determining an early battery depletion (EBD) condition of an implantable medical device that includes a memory storing program instructions and a processor executing the program instructions. Circuitry is electrically coupled to the processor, and the circuitry and processor perform one or more tasks related to at least one of collecting signals indicative of physiologic activity, analyzing collected signals, delivering therapy, or communicating with an external device. A battery supplies energy to the circuitry and processor. A monitoring circuit coupled to the battery measures actual energy usage from the battery representing at least one of a current draw from the battery during corresponding tasks or a voltage measurement across the battery. Circuitry and processor calculate projected energy usage from the battery in connection with the corresponding tasks, and determine when an EBD condition exists based on projected energy usage and actual energy usage.

Method and device for detecting abnormal battery consumption due to extra-battery mechanisms

Growing community of inventors

Thousand Oaks, CA, United States of America

Kevin J Davis