A wearable device is provided. The wearable device is used by being attached to a user's skin. The wearable device includes a main body unit having a housing and a substrate, the substrate being arranged inside the housing, an electrode unit including a sensing electrode connected to the main body unit, and a patch unit including one or more conductive members, the one or more conductive members being configured to electrically connect the electrode unit to the user's skin. The electrode unit includes a shielding layer that is not electrically connected to the main body unit. The shielding layer is conductive with a floating potential.

Disclosed herein is a cardiac monitoring system comprising a monitoring device comprising a plurality of electrodes and one or more processors. The one or more processors are configured to, when the monitoring device is placed around an extremity of a patient, control the plurality of electrodes to record one or more electrocardiogram signals. The one or more processors are further configured to receive, from the monitoring device, one or more data packets, the one or more data packets indicative of the one or more electrocardiogram signals. The one or more processors are also configured to apply one or more adaptive software filters to the one or more data packets to extract an electrocardiogram for the patient. The one or more processors are also configured to analyze the extracted electrocardiograms using one or more cardiac detection tools to identify abnormal electrocardiograms and output the identified abnormal electrocardiograms.

Disclosed herein is a cardiac monitoring system comprising a monitoring device comprising a plurality of electrodes and one or more processors. The one or more processors are configured to, when the monitoring device is placed around an extremity of a patient, control the plurality of electrodes to record one or more electrocardiogram signals. The one or more processors are further configured to receive, from the monitoring device, one or more data packets, the one or more data packets indicative of the one or more electrocardiogram signals. The one or more processors are also configured to apply one or more adaptive software filters to the one or more data packets to extract an electrocardiogram for the patient. The one or more processors are also configured to analyze the extracted electrocardiograms using one or more cardiac detection tools to identify abnormal electrocardiograms and output the identified abnormal electrocardiograms.

In at least one example, a medical device is provided. The medical device includes at least one therapy electrode, at least one electrocardiogram (ECG) electrode, at least one acoustic sensor, and at least one processor coupled with the at least one acoustic sensor, the at least one ECG electrode, and the at least one therapy electrode. The at least one processor can receive at least one acoustic signal from the at least one acoustic sensor, receive at least one electrode signal from the ECG electrode, detect at least one unverified cardiopulmonary anomaly using the at least one electrode signal, and verify the at least one unverified cardiopulmonary anomaly with reference to data descriptive of the at least one acoustic signal.

In at least one example, a medical device is provided. The medical device includes at least one therapy electrode, at least one electrocardiogram (ECG) electrode, at least one acoustic sensor, and at least one processor coupled with the at least one acoustic sensor, the at least one ECG electrode, and the at least one therapy electrode. The at least one processor can receive at least one acoustic signal from the at least one acoustic sensor, receive at least one electrode signal from the ECG electrode, detect at least one unverified cardiopulmonary anomaly using the at least one electrode signal, and verify the at least one unverified cardiopulmonary anomaly with reference to data descriptive of the at least one acoustic signal.

Deep Learning (DL) performs well in cardiovascular disease (CVD) classification using 12-lead Electrocardiogram (ECG). However, explainable artificial intelligence in CVD classification still remains largely qualitative. Embodiments of the present disclosure provide systems and methods that implement a Region of Interest (ROI) based quantifiable explanation for multi-lead ECG. CVD specific post-processing steps are added, to increase the explanation performance. Furthermore, the system enables selection of an optimal DL model, within the performance space defined by classification, explanation, and time-complexity.

Deep Learning (DL) performs well in cardiovascular disease (CVD) classification using 12-lead Electrocardiogram (ECG). However, explainable artificial intelligence in CVD classification still remains largely qualitative. Embodiments of the present disclosure provide systems and methods that implement a Region of Interest (ROI) based quantifiable explanation for multi-lead ECG. CVD specific post-processing steps are added, to increase the explanation performance. Furthermore, the system enables selection of an optimal DL model, within the performance space defined by classification, explanation, and time-complexity.

The invention relates to a method to check a medical device (1,1), to a method of operating such a medical device (1,1) and to the respective medical device (1,1). The medical device (1,1) comprises at least two electrode groups (5) and a pulse generator (6), wherein each electrode group (5) comprises at least two electrodes (4), wherein the at least two electrode groups (5) are arranged on a surface (3) of at least one lead body (2,12), wherein the pulse generator (6) comprises at least one port (9), wherein the number of connections (10) of the at least one port (9) is equal to or greater than the number of electrodes (4) of all electrode groups (5) and form connection groups (11) corresponding to the electrode groups (5). In order to check whether the electrodes (4) of the at least one lead body (2) are correctly electrically linked to the pulse generator (6), the method is used.

Various methods for making probe devices that include the addition of electrode contact material using various different processes and/or techniques, along with the resulting devices. Some methods include adding electrode contact material such that the resulting electrode contacts are suitable for direct contact with patient tissue while encapsulating materials that are not.

In one example, an ambulatory medical device is provided. The ambulatory medical device includes a plurality of subsystems, at least one sensor configured to acquire data descriptive of a patient, a user interface and at least one processor coupled to the at least one sensor and the user interface. The at least one processor is configured to identify subsystem status information descriptive of an operational status of each subsystem of the plurality of subsystems and to provide a device health report for the ambulatory medical device via the user interface, the device health report being based on the operational status of each subsystem.