Abstract: This disclosure is directed to devices, systems, and techniques for determining an efficacy of a treatment program. For example, a medical device system includes a medical device including one or more sensors configured to generate a signal that indicates a parameter of a patient. Additionally, the medical device system includes processing circuitry configured to receive data indicative of a user selection of a reference time; determine a plurality of parameter values of the parameter based on a portion of the signal corresponding to a period of time including the reference time. Additionally, the processing circuitry is configured to identify, based on a first set of parameter values, a reference parameter value, calculate a parameter change value, and determine, based on the parameter change value, whether an improvement or a worsening of the patient has occurred responsive to a treatment administered beginning at the reference time.

Abstract: The disclosure describes techniques for delivering electrical stimulation to decrease the ventricular rate response during an atrial tachyarrhythmia, such as atrial fibrillation. AV nodal stimulation is employed during an atrial tachyarrhythmia episode with rapid ventricular conduction to distinguish ventricular tachyarrhythmia from supraventricular tachycardia and thereby prevent delivering inappropriate therapy to a patient.

Abstract: Techniques that include applying machine learning models to episode data, including a cardiac electrogram, stored by a medical device are disclosed. In some examples, based on the application of one or more machine learning models to the episode data, processing circuitry derives, for each of a plurality of arrhythmia type classifications, class activation data indicating varying likelihoods of the classification over a period of time associated with the episode. The processing circuitry may display a graph of the varying likelihoods of the arrhythmia type classifications over the period of time. In some examples, processing circuitry may use arrhythmia type likelihoods and depolarization likelihoods to identify depolarizations, e.g., QRS complexes, during the episode.

Abstract: A method of detecting sleep apnea includes generating a cardiac signal indicating activity of a heart of a patient. The method further includes determining a short-term average heart rate and a long-term average heart rate. The method further includes determining a start and end of a heart rate cycle based on the short-term average heart rate and the long-term average heart rate. The method further includes determining physiological parameter values occurring during the heart rate cycle. The method further includes determining whether patient has or has not experienced a sleep apnea event based on whether one or more conditions are satisfied by one or more parameter values for one or more heart rate cycles and responsively generating an indication that patient has or has not experienced a sleep apnea event.

Abstract: Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.

Abstract: Techniques that include applying machine learning models to episode data, including a cardiac electrogram, stored by a medical device are disclosed. In some examples, based on the application of one or more machine learning models to the episode data, processing circuitry derives, for each of a plurality of arrhythmia type classifications, class activation data indicating varying likelihoods of the classification over a period of time associated with the episode. The processing circuitry may display a graph of the varying likelihoods of the arrhythmia type classifications over the period of time. In some examples, processing circuitry may use arrhythmia type likelihoods and depolarization likelihoods to identify depolarizations, e.g., QRS complexes, during the episode.

Abstract: Techniques for transmitting diagnostic information stored in an implantable medical device (IMD) based on patient hospitalization are described. For example, the IMD may transmit higher resolution diagnostic information to a clinician and/or an external device during a hospitalization period to aid the clinician in evaluating heart failure treatment and when discharge is proper. This higher resolution diagnostic information may include one or more patient metrics automatically generated and transmitted by the IMD at least once every two hours. During a post-hospitalization period, the IMD may transmit lower resolution diagnostic information to a clinician that indicates a risk level of re-hospitalization. The lower resolution diagnostic information may include the risk level and/or patient metrics once a day, for example. In this manner, the IMD transmitted diagnostic information may be tailored to the specific heart failure monitoring needed by the patient.

Abstract: Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.

Abstract: A method of detecting sleep apnea includes generating a cardiac signal indicating activity of a heart of a patient. The method further includes determining a short-term average heart rate and a long-term average heart rate. The method further includes determining a start and end of a heart rate cycle based on the short-term average heart rate and the long-term average heart rate. The method further includes determining physiological parameter values occurring during the heart rate cycle. The method further includes determining whether patient has or has not experienced a sleep apnea event based on whether one or more conditions are satisfied by one or more parameter values for one or more heart rate cycles and responsively generating an indication that patient has or has not experienced a sleep apnea event.

Abstract: A method for heart failure management may include volume overload intervention in response to sensor-based parameters indicating volume overload. The method may include administering non-volume overload intervention in response to the sensor-based parameters not indicating volume overload. Volume overload may be determined based on monitoring sensor-based parameters. Sensor-based parameters may be monitored in response to receiving an alert indicative of a worsening heart failure score or status for a patient.

Abstract: 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.

Abstract: This disclosure is directed to systems and techniques for detecting change in patient health and if a change in patient health is detected, direct a medical device to generate for display output indicating the detection of the change in patient health. An example medical system or technique applies a model to values of configurable settings that are programmed into detection logic of a medical device; based on the application, determine whether modified values of the configurable settings, when implemented by the detection logic, would change a determination, by the medical device, regarding whether sensed physiological activity is indicative of cardiac episode for a patient; and in response to a determination that the modified values would change the determination regarding whether the sensed physiological activity is indicative of the cardiac episode for the patient, generate output data indicative of the modified values for the configurable settings for the medical device.

Abstract: This disclosure is directed to a medical system and technique for a filter-based approach to arrhythmia detection. In one example, the medical system comprises one or more sensors configured to sense physiological parameter(s); sensing circuitry configured to generate patient data based on the sensed physiological parameter(s), the patient data comprising signal data to represent cardiac activity of the patient; and processing circuitry configured to: detect a cardiac arrhythmia for the patient based on a classification of the signal data in accordance with a machine learning model, wherein the machine learning model comprises filter(s) for at least one portion of the signal data, wherein the at least one filter corresponds to a feature set that maps to the cardiac activity represented by the portion(s) of the signal data; and generate for display output data indicative of a positive detection of the cardiac arrhythmia.

Abstract: Systems and methods include differential diagnosis for acute heart failure to provide treatment to a patient including determining whether the patient has cardiac volume overload, determining whether the patient has decreased abdominal venous system volume, and providing the appropriate treatment in response to the determinations. A multi-sensor system may be used to determine cardiac volume and abdominal venous system volume. Fluid redistribution treatment may be provided when cardiac volume overload is accompanied by a decrease in abdominal venous system volume. Fluid accumulation treatment may be provided when cardiac volume overload is not accompanied by a decrease in abdominal venous system volume.

Abstract: A medical system includes communication circuitry configured to receive episode data for an episode sensed by a medical device of a patient, wherein the episode data comprises a cardiac electrogram sensed by the medical device during a period of time; and processing circuitry configured to generate an image based on the episode data, wherein the image is associated with an interval within the period of time; apply, by the processing circuitry, one or more machine learning models to the image, the one or more machine learning models configured to determine whether the image corresponds to an arrythmia type; and output an indication of whether the image corresponds to the arrythmia type.

Abstract: A method of detecting sleep apnea includes generating a cardiac signal indicating activity of a heart of a patient. The method further includes determining a short-term average heart rate and a long-term average heart rate. The method further includes determining a start and end of a heart rate cycle based on the short-term average heart rate and the long-term average heart rate. The method further includes determining physiological parameter values occurring during the heart rate cycle. The method further includes determining whether patient has or has not experienced a sleep apnea event based on whether one or more conditions are satisfied by one or more parameter values for one or more heart rate cycles and responsively generating an indication that patient has or has not experienced a sleep apnea event.

Abstract: Techniques that include applying machine learning models to episode data, including a cardiac electrogram, stored by a medical device are disclosed. In some examples, based on the application of one or more machine learning models to the episode data, processing circuitry derives, for each of a plurality of arrhythmia type classifications, class activation data indicating varying likelihoods of the classification over a period of time associated with the episode. The processing circuitry may display a graph of the varying likelihoods of the arrhythmia type classifications over the period of time. In some examples, processing circuitry may use arrhythmia type likelihoods and depolarization likelihoods to identify depolarizations, e.g., QRS complexes, during the episode.

Abstract: In some examples, controlling delivery of CRT includes controlling an implantable medical device to deliver ventricular pacing according to a sequence of different values of a CRT parameter, and acquiring first and second electrograms from respective first and second electrode vectors. For each value of the CRT parameter, a value of a metric of comparison of a first activation interval between occurrences of a first fiducial of a cardiac cycle and a second fiducial of the cardiac cycle detected in the first electrogram to a second activation interval between occurrences of the first fiducial and the second fiducial detected in the second electrogram may be determined. A target value of the metric of comparison may be identified and an updated value of the CRT parameter determined based on the target value. The system then may control the IMD to deliver ventricular pacing at the updated value of the CRT parameter.

Abstract: This disclosure is directed to devices, systems, and techniques for determining an efficacy of a treatment program. For example, a medical device system includes a medical device including one or more sensors configured to generate a signal that indicates a parameter of a patient. Additionally, the medical device system includes processing circuitry configured to receive data indicative of a user selection of a reference time; determine a plurality of parameter values of the parameter based on a portion of the signal corresponding to a period of time including the reference time. Additionally, the processing circuitry is configured to identify, based on a first set of parameter values, a reference parameter value, calculate a parameter change value, and determine, based on the parameter change value, whether an improvement or a worsening of the patient has occurred responsive to a treatment administered beginning at the reference time.

Abstract: Techniques that include applying machine learning models to episode data, including a cardiac electrogram, stored by a medical device are disclosed. In some examples, based on the application of one or more machine learning models to the episode data, processing circuitry derives, for each of a plurality of arrhythmia type classifications, class activation data indicating varying likelihoods of the classification over a period of time associated with the episode. The processing circuitry may display a graph of the varying likelihoods of the arrhythmia type classifications over the period of time. In some examples, processing circuitry may use arrhythmia type likelihoods and depolarization likelihoods to identify depolarizations, e.g., QRS complexes, during the episode.