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.

Techniques are disclosed for preparing data for use in artificial intelligence (AI)-based cardiac arrhythmia detection. In accordance with the techniques of this disclosure, a computing system may obtain a cardiac electrogram (EGM) strip that represents a waveform of a cardiac rhythm of a same patient. Additionally, the computing system may preprocess the cardiac EGM strip. The computing system may then apply a deep learning model to the preprocessed cardiac EGM strip to generate arrhythmia data indicating whether the cardiac EGM strip represents one or more occurrences of one or more cardiac arrhythmias.

Techniques are disclosed for automatically calibrating a reference orientation of an implantable medical device (IMD) within a patient. In one example, sensors of an IMD sense a plurality of orientation vectors of the IMD with respect to a gravitational field. Processing circuitry of the IMD processes the plurality of orientation vectors to identify an upright vector that corresponds to an upright posture of the patient. The processing circuitry classifies the plurality of orientation vectors with respect to the upright vector to define a sagittal plane of the patient and a transverse plane of the patient. The processing circuitry determines, based on the upright vector, the sagittal plane, and the transverse plane, a reference orientation of the IMD within the patient. As the orientation of the IMD within the patient changes over time, the processing circuitry may recalibrate its reference orientation and accurately detect a posture of the patient.

Computer implemented methods and systems for detecting noise in cardiac activity are provided. The method and system obtain a far field cardiac activity (CA) data set that includes far field CA signals for a series of beats, overlay a segment of the CA signals with a noise search window, and identify turns in the segment of the CA signals. The method and system determine whether the turns exhibit a turn characteristic that exceed a turn characteristic threshold, declare the segment of the CA signals as a noise segment based on the determining operation, shift the noise search window to a next segment of the CA signal and repeat the identifying, determining and declaring operations; and modify the CA signals based on the declaring the noise segments.

Methods and/or devices to determine patient respiration information are disclosed which comprise sensing acceleration.

Computer implemented methods and systems are provided that comprise, under control of one or more processors of a medical device, where the one or more processors are configured with specific executable instructions. The methods and systems obtain motion data indicative of at least one of a posture or a respiration cycle; obtain cardiac activity (CA) signals for a series of beats; identify whether a characteristic of interest (COI) from at least a first segment of the CA signals exceeds a COI limit; analyze the motion data to determine whether at least one of the posture or respiration cycle at least in part caused the COI to exceed the COI limit. Based on the analyzing operation, the methods and systems automatically adjust a CA sensing parameter utilized by the medical device to detect R-waves in subsequent CA signals; and detect an arrhythmia based on a presence or absence of one or more of the R-waves in at least a second segment of the CA signals.

Sensor-integrated prosthetic valves that can comprise a variety of features, including a plurality of valve leaflets, a frame assembly configured to support the plurality of valve leaflets and define a plurality of commissure supports terminating at an outflow end of the prosthetic valve, a sensor device associated with the frame assembly and configured to generate a sensor signal, for example, a sensor signal indicating deflection of one or more of the plurality of commissure supports, and a transmitter assembly configured to receive the sensor signal from the sensor device and wirelessly transmit a transmission signal that is based at least in part on the sensor signal.

The present technology relates to intracardiac pressure monitoring devices, and associated systems and methods. In some embodiments, the present technology includes a device for monitoring pressure within a patient's heart. The device can include a pressure sensor configured to reside within a first chamber of a heart of a patient, and a pressure transmission element configured to extend from the first chamber through a septal wall to a second chamber of the heart of the patient. When the device is implanted in the patient's heart, the pressure transmission element is configured to transmit pressure from the second chamber to the pressure sensor residing within the first chamber.

In some examples, determining a heart failure status includes using an implantable medical device configured for subcutaneous implantation and comprising a plurality of electrodes and an optical sensor. Processing circuitry of a system comprising the device may determine, for a patient, a current tissue oxygen saturation value based on a signal received from the at least one optical sensor, a current tissue impedance value based on a subcutaneous tissue impedance signal received from the electrodes, and a current pulse transit time value based on a cardiac electrogram signal received from the electrodes and at least one of the signal received from the optical sensor and the subcutaneous tissue impedance signal. The processing circuitry may further compare the current tissue oxygen saturation value, current tissue impedance value, and current pulse transit time value to corresponding baseline values, and determine the heart failure status of the patient based on the comparison.

Embodiments of the present disclosure relate to implantable biosensors configured to be implanted into tissue of a subject at an implantation site. In an exemplary embodiment, the implantable biosensor comprising: an electronic module and a compliant sensing tether extending from the electronic module. The compliant sensing tether comprising a proximal portion coupled to the electronic module, a distal portion spaced apart from the electronics module, and an intermediate portion joining the proximal portion to the distal portion. The proximal portion has a first flexibility and the distal portion having a second flexibility. The second flexibility of the distal portion being greater than the first flexibility of the proximal portion. The distal portion comprises a sensor configured to sense a signal corresponding to an analyte of the subject, wherein the signal corresponding to the analyte is transferred to the electronics module via the compliant sensing tether.