ELECTROCARDIOGRAM WAVE SEGMENTATION USING MACHINE LEARNING

    公开(公告)号:WO2023076357A1

    公开(公告)日:2023-05-04

    申请号:PCT/US2022/047852

    申请日:2022-10-26

    Abstract: A method includes retrieving a plurality of indications of cardiac events in a patient, heart rates of the patient during the cardiac events, and durations of the cardiac events. The method also includes selecting a subset of indications from the plurality of indications based on the heart rates of the patient during the cardiac events and the durations of the cardiac events and sorting the subset of indications based on heart rates of the patient during the cardiac event indicated by the subset of indications and based on durations of the cardiac events indicated by the subset of indications to produce a sorted list of indications. The method further includes communicating, from the sorted list, an indication that is first in the sorted list for clinical review.

    早搏检测方法及其电子设备和介质

    公开(公告)号:WO2021233319A1

    公开(公告)日:2021-11-25

    申请号:PCT/CN2021/094485

    申请日:2021-05-19

    Abstract: 本申请涉及信息技术处理领域,公开了一种早搏检测方法及其电子设备和介质。本申请的早搏检测方法包括:采用早搏检测功能对用户进行早搏检测,在采用早搏检测功能检测出用户出现早搏的情况下,采用早搏类型判断功能判断用户出现的早搏类型,并基于早搏检测功能得到的检测数据计算用户的早搏负荷,在计算出的早搏负荷大于早搏类型判断功能判断出的早搏类型所对应的早搏负荷阈值的情况下,对用户进行早搏风险提醒。本申请的早搏检测技术避免了电子设备的单一检测功能能够持续进行早搏检测但无法识别早搏类型的缺点,综合利用两个检测功能实现早搏的持续检测和早搏类型的判定,进而实现两种不同类型早搏的差异化风险提醒,避免大量错误提醒或对风险认识不足。

    A METHOD FOR DETECTING AN ECTOPIC SIGNAL IN AN ELECTROCARDIOGRAM

    公开(公告)号:WO2021219426A1

    公开(公告)日:2021-11-04

    申请号:PCT/EP2021/060174

    申请日:2021-04-20

    Abstract: A method for detecting an ectopic signal in an electrocardiogram is disclosed. This method comprises the following steps: detecting consecutive R-R intervals in an electrocardiogram; calculating an average R-R interval for a determinable number of latest R-R intervals; recognizing a signal as ectopic signal if the signal belongs to at least one of two consecutive R-R intervals, wherein i) a first of the two consecutive R-R intervals is significantly shorter than the average R-R interval; and ii) a second of the two consecutive R-R intervals is significantly longer than the average R-R interval, wherein the second R-R interval occurs later than the first R-R interval; wherein the first and the second of the two consecutive R-R intervals are discarded from calculating the average R-R interval, if the signal is recognized as ectopic signal.

    IMPLANTABLE MEDICAL DEVICE FOR DETECTING ATRIAL UNDERSENSING

    公开(公告)号:WO2021197819A1

    公开(公告)日:2021-10-07

    申请号:PCT/EP2021/056512

    申请日:2021-03-15

    Abstract: The invention relates to an implantable medical device, comprising a processor, a memory unit, a first detection unit configured to detect an atrial electric signal of a human or animal heart, and a second detection unit configured to detect a ventricular electric signal of the same heart. During operation of the device, atrial events are evaluated in the atrial electric signal detected by the first detection unit and/or ventricular events are evaluated in the ventricular electric signal detected by the second detection unit for recognizing a condition of the implantable medical device in which atrial electric signals are detected only insufficiently. This evaluation is done by applying at least one of the following criteria: - morphology of the detected atrial electric signals; - lacking stability of atrial events; - absence of atrial events over a first period of time; - detection of an amplitude of the detected atrial electric signal being lower than a predefined threshold value; - absence of atrial events during detection of ventricular electric signals at the same time; comparison of atrial events sensed with a first sensing profile of the first detection unit and atrial events sensed with a second sensing profile of the first detection unit, the second sensing profile being more sensitive than the first sensing profile.

    METHODS AND SYSTEMS FOR DETECTING ECG ANOMALIES

    公开(公告)号:WO2022087349A1

    公开(公告)日:2022-04-28

    申请号:PCT/US2021/056167

    申请日:2021-10-22

    Abstract: Methods, apparatus and systems for robust and accurate detection of anomalies in medical images and electrocardiograms are disclosed. One example system for training a neural network engine includes a processor that is configured to receive a set of training electrocardiogram signals. At least one electrocardiogram signal in the set of training electrocardiogram signals is associated with metadata identifying a region of interest that includes a heart anomaly. The processor is configured to input the set of training electrocardiogram signals into the neural network engine. The neural network engine is trained using an objective function having a first regularization parameter and a second regularization parameter. The processor is also configured to operate the neural network engine to identify the heart anomaly by classifying the set of training electrocardiogram signals and adjust the neural network engine based on the identified heart anomaly and the metadata.

    TRIGGERING STORAGE OF ELECTROCARDIOGRAPHS FOR DETECTED PREMATURE VENTRICULAR CONTRACTIONS (PVCS)

    公开(公告)号:WO2021086574A1

    公开(公告)日:2021-05-06

    申请号:PCT/US2020/054895

    申请日:2020-10-09

    Abstract: Techniques for triggering the storage or transmission of cardiac electrogram (EGM) signals associated with a premature ventricular contractions (PVC) include sensing a cardiac EGM signal of a patient via a plurality of electrodes, detecting a premature ventricular contraction (PVC) within the cardiac EGM signal, determining whether PVC storage criteria is met, in response to a determination that the PVC storage criteria is met, storing a portion of the cardiac EGM signal associated with the PVC, and in response to a determination that the PVC storage criteria is not met, eschewing storing the portion of the cardiac EGM signal associated with the PVC.

Patent Agency Ranking