Abstract: Systems and methods to improve patient monitoring and device operation during a near-implant time period are disclosed, including determining a representative value of physiologic information of a patient sensed in a near-implant time period after implant of an implantable medical device in the patient, determining an absolute or hybrid baseline corresponding to the near-implant time period using information from at least one of an imputed baseline corresponding to a pre-implant time period preceding implant of the implantable medical device in the patient or an initial value of the received physiologic information of the patient in an initial portion of the near-implant time period, and determining an indication of patient condition as a function of the determined representative value and the determined absolute or hybrid baseline.

Abstract: Systems and methods to improve patient monitoring and device operation during a near-implant time period are disclosed, including determining a representative value of received physiologic information of a patient sensed by an implantable medical device implanted in the patient, determining a hybrid or relative baseline for the patient using the received physiologic information, and determining an indication of patient condition as a weighted function of (1) the representative value of the received physiologic information, (2) an absolute baseline, and (3) the hybrid or relative determined relative baseline, with a weight of at least one the determined absolute baseline or the determined relative baseline changing with time relative to a time of implant of the implantable medical device.

Abstract: Systems and methods for recognizing and tracking heart sound components are disclosed. An exemplary medical-device system includes a data receiver to receive heart sound information, and a heart sound recognition circuit to generate a representative heart sound segment such as an ensemble average of a selected portion of heart sound segments. The heart sound recognition circuit recognizes a heart sound component from the representative heart sound segment using a time-based tracking algorithm, and evaluates a performance index of the time-based heart sound tracking algorithm. Based on the performance index, a decision can be made whether or not to switch to a spectral-based tracking algorithm to recognize the heart sound component from the representative heart sound segment. A physiologic event detector can detect a cardiac event using the recognized heart sound component.

Abstract: Systems and methods are disclosed to an ambulatory medical device. The ambulatory medical device comprising an activity sensor configured to produce an activity signal representative of activity level of a patient, a heart sound sensor configured to produce a heart sound signal, and a control circuit. The control circuit is configured to detect a change in activity level of the patient using the activity signal, enable monitoring of the heart sound signal in response to detecting the change in activity level, measure intensity of an S3 heart sound in the heart sound signal, and produce an indication of pulmonary hypertension (PH) when the measured intensity of the S3 heart sound exceeds a PH detection threshold intensity.

Abstract: Systems and methods for monitoring and staging sleep using cardiac and respiration information are disclosed. An exemplary system comprises a storage device to store a trained hybrid sleep detection and classification model that comprise a plurality of trained machine-learning models each trained to map input cardiac and respiratory data into one of multiple distinct model-specific awake or sleep classes, and a trained regression model to combine the model-specific awake or sleep classes to a composite awake or sleep classification. A sleep detector applies patient cardiac and respiratory information to the trained hybrid sleep detection and classification model to determine a composite awake or sleep classification for the patient. The composite awake or sleep classification is used to diagnose medical conditions including sleep apnea.

Abstract: Systems and methods for monitoring and managing aortic stenosis are disclosed. An exemplary medical-device system comprises a data receiver to receive heart sound information sensed by ambulatory heart sound sensors, and a stenosis detector to detect a change in aortic valve surface area from a baseline stenosis-free state using heart sound components such as S1 and S2 sounds. Based on the change in aortic valve surface area, the stenosis detector can generate an aortic stenosis indicator indicating a presence and severity of aortic stenosis. Such indicator can be provided to a user, trigger symptom monitoring and evaluation of functional deterioration in the patient, facilitate assessment of patient candidacy for aortic valve replacement, or triage heart failure management strategies.

Abstract: Systems and methods are disclosed to determine a composite health index for the patient as a function of a plurality of features, including determining validity of a first feature of the plurality of features and adjusting the function used to determine the composite health index in response to a determination that the first feature is not valid.

Abstract: Systems and methods for detecting a blockage in a patient's cardiac conduction system using heart sound information is disclosed. An exemplary medical-device system includes a data receiver circuit to receive heart sound information sensed from a patient, and a controller circuit to generate a heart sound metric or characteristic from the received heart sound information. The heart sound metric can include one indicative of a presence or absence of split S1 sound. The controller circuit can detect a bundle branch block (BBB), including to discriminate a left bundle branch block (LBBB) from a right bundle branch block (RBBB), based at least in part on the heart sound metric. The BBB indicator can be provided to a user or a process executable by the medical-device system to optimize cardiac pacing and restore cardiac synchrony.

Abstract: Systems and methods for recognizing and tracking heart sound components are disclosed. An exemplary medical-device system comprises a data receiver circuit to receive heart sound information, and a heart sound recognition circuit to generate a representative heart sound segment within a cardiac cycle, such as an ensemble average of a plurality of heart sound segments taken from multiple cardiac cycles. The heart sound recognition circuit can partition the representative heart sound segment into multiple heart sound data windows, calculate spectral entropy values respectively for each of the multiple heart sound data windows, and determine one or more heart sound components including an S2 component using the calculated spectral entropy values. A physiologic event detector can detect a cardiac event using the recognized one or more heart sound components.

Abstract: Systems and methods are disclosed to determine a syncope metric for a patient as a function of cardiac acceleration information and the blood pressure information received from a signal receiver circuit and to determine an indication of a worsening risk of syncope or a syncope event for a patient using the determined syncope metric, wherein the determined indication of worsening risk of syncope or the syncope event can be provided to a user or a process.

Abstract: Systems and methods are disclosed to determine a P wave window for a patient using cardiac acceleration information of the patient, including a determined time of an S4 heart sound. Correlations between an S4 template and cardiac acceleration information in an S4 window having a duration longer than the S4 template can be determined. An S4 centroid can be determined as a peak of the determined multiple correlations, and the P wave window can be determined using the determined S4 centroid and an electromechanics delay.

Abstract: Systems and methods are disclosed to determine an indication of one of an atrial fibrillation S4 heart sound or a non-atrial fibrillation S4 heart sound for an S4 signal portion of cardiac acceleration information of a patient based on determined first and second correlations of a morphology of the S4 signal portion to atrial-fibrillation and non-atrial fibrillation S4 templates, respectively, and to determine an atrial fibrillation event of the patient using cardiac electrical information of the patient and the determined indication for the S4 signal portion.