A wearable therapeutic device to facilitate care of a subject is provided. The wearable therapeutic device can include a garment having a sensing electrode. The garment includes at least one of an inductive element and a capacitive element, and a controller identifies an inductance of the inductive element or a capacitance of the capacitive element, and determines a confidence level of information received from the sensing electrode based on the inductance or the capacitance. The wearable therapeutic device also includes an alarm module coupled with the controller and configured to provide a notification to a subject based on the confidence level.

Hemodynamic performance of a heart may be improved by determining, from a location associated with a diaphragm, an occurrence of a valid cardiac event; and then delivering asymptomatic electrical stimulation therapy directly to the diaphragm at termination of a diaphragmatic stimulation delay period that is timed relative to the occurrence of the valid cardiac event. The diaphragmatic stimulation delay period may be automatically established by sensing a plurality of cardiac events directly from a diaphragm; and for each of the sensed cardia events, determining whether the sensed cardiac event represents a valid cardiac event or a non-valid cardiac event. The diaphragmatic stimulation delay period is then calculated based on a plurality of sensed cardia events that are determined to be valid.

Hemodynamic performance of a heart may be improved by determining, from a location associated with a diaphragm, an occurrence of a valid cardiac event; and then delivering asymptomatic electrical stimulation therapy directly to the diaphragm at termination of a diaphragmatic stimulation delay period that is timed relative to the occurrence of the valid cardiac event. The diaphragmatic stimulation delay period may be automatically established by sensing a plurality of cardiac events directly from a diaphragm; and for each of the sensed cardia events, determining whether the sensed cardiac event represents a valid cardiac event or a non-valid cardiac event. The diaphragmatic stimulation delay period is then calculated based on a plurality of sensed cardia events that are determined to be valid.

An ambulatory medical device is provided. The ambulatory medical device includes at least one sensor configured to acquire data descriptive of a patient, a memory, a user interface, and at least one processor coupled with the memory, the at least one sensor, and the user interface. The at least one processor is configured to determine whether the ambulatory medical device is within a predefined range of a reference location and to initiate location-specific processing in response to determining that the ambulatory medical device is within the predefined range. The location-specific processing includes at least one of issuing a notification and adapting the user interface.

A system for unobtrusively determining a fertile window includes a contact sensor in contact with the woman and configured to provide a signal indicative of respiration of the woman. A processor is configured to process the signal to obtain a biomechanical parameter indicative of the respiration, and determine the fertile window of the woman based on a change in the obtained biomechanical parameter.

The present invention relates to a computer-implemented medical method for improving the suitability of a tracking structure for tracking by tessellating the tracking structure into a plurality of sub-tracking structures. The invention also relates to a computer configured to execute a program corresponding to the method and a medical system for improving the suitability of a tracking structure for tracking, the system including the aforementioned computer.

Methods and/or devices to identify disease burden indication are disclosed. One type of disease comprises sleep disordered breathing and/or related parameters, which may be sensed via implantable sensors such as an acceleration sensor.

Provided is a system, method, and device for non-invasive hemodynamic measurement of a subject. The method includes identifying vibrational pulses V1 and V2 and vibrations corresponding to cardiac mechanical motion from vibrational cardiography (VCG) data, the VCG data derived from a vibration signal acquired at the surface of the chest of the subject corresponding to cardiac-induced vibrations; determining a vibration feature from the vibration signal; and determining a hemodynamic measurement from the vibration feature.

A measurement unit (110) performs a measurement process for measuring a biological signal (21) from a target person (20). The biological signal (21) contains a plurality of components and can be measured in a manner to be unnoticeable by the target person (20). A component extraction unit (120) extracts an authentication component, which is to be used for authentication, from the plurality of components. A feature amount extraction unit (130) extracts a current feature amount indicating a present feature amount of the authentication component, from the authentication component. A registration unit (140) registers an identifier, which is used for identifying the target person (20), and a template feature amount, which is a feature amount extracted from the target person (20) in the past, in a storage unit (160), as template information (161). A comparison unit (150) compares the current feature amount to the template feature amount. When a difference between the current feature amount and the template feature amount is within a tolerance value (162), the comparison unit (150) returns processing to the measurement process and the authentication is repeated. When the difference between the current feature amount and the template feature amount is larger than the tolerance value (162), the processing is ended.

Provided herein are methods and systems to train and execute a motion model that uses artificial intelligence methodologies (e.g., deep-learning) to learn and predict location of a patient's internal structures. A method comprises receiving respiratory data of a patient from an electronic sensor in addition to a medical image, such as kV image; executing an artificial intelligence model using the respiratory data and predicting deformation data for at least one internal structure of the patient, wherein the artificial intelligence model is trained in accordance with a training dataset comprising a set of participants, their corresponding respiratory data, and their corresponding deformation data; and outputting the predicted deformation data.