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 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 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.

Abstract: Techniques are disclosed for using a computing system to selectively implement different review workflows for different categories of episodes, e.g., arrhythmia episodes, stored by medical devices. The different workflows may include different combinations of one or more human and/or machine reviewers, and different decision logic for determining whether and when to present an episode to the reviewers. Machine reviewers may utilize one or more machine learning models to annotate, e.g., classify, episodes.

Abstract: Techniques are disclosed for monitoring a patient for the occurrence of a cardiac arrhythmia. A computing system generates sample probability values by applying a machine learning model to sample patient data. The machine learning model determines a respective probability value that indicates a probability that the cardiac arrhythmia occurred during each respective temporal window. The computing system outputs a user interface comprising graphical data based on the sample probability values and receives, via the user interface, an indication of user input to select a probability threshold for a patient. The computing system receives patient data for the patient and applies the machine learning model to the patient data to determine a current probability value. In response to the determination that the current probability exceeds the probability threshold for the patient, the computing system generates an alert indicating the patient has likely experienced the occurrence of the cardiac arrhythmia.

Abstract: Techniques are disclosed for explaining and visualizing an output of a machine learning system that detects cardiac arrhythmia in a patient. In one example, a computing device receives cardiac electrogram data sensed by a medical device. The computing device applies a machine learning model, trained using cardiac electrogram data for a plurality of patients, to the received cardiac electrogram data to determine, based on the machine learning model, that an episode of arrhythmia has occurred in the patient and a level of confidence in the determination that the episode of arrhythmia has occurred in the patient. In response to determining that the level of confidence is greater than a predetermined threshold, the computing device displays, to a user, a portion of the cardiac electrogram data, an indication that the episode of arrhythmia has occurred, and an indication of the level of confidence that the episode of arrhythmia has occurred.

Abstract: Methods and apparatus to determine the presence of and track functional chronotropic incompetence (hereinafter “CI”) in an in-home setting under conditions of daily living. The functional CI of the patient may be determined with one or more of a profile of measured patient heart rates, a measured maximum patient heart rate, or a peak of the heart rate profile. The functional CI of the patient may be determined with the measured heart rate profile, in which the measured heart rate profile may correspond to heart rates substantially less than the maximum heart rate of the patient, such that the heart rate can be safely measured when the patient is remote from a health care provider. The functional CI of the patient may be determined based a peak of the remotely measured heart rate profile, for example a peak corresponding to the mode of the heart rate distribution profile.

Abstract: Described herein is a system and method of automatically monitoring QT intervals in a patient based on one or more EKG signals received from attached monitoring devices. Each EKG signal is analyzed to detect attributes of the first and second EKG signals, including QRS onset information, QRS peak information, and T-wave offset information. A QT interval is calculated based on QRS onset information derived from the first EKG signal and T-wave offset information derived from the second EKG signal. The calculated QT interval is compared to thresholds to detect elongation of the QT interval and an alert is generated in response to a detected elongated QT interval.

Abstract: A method of determining signal quality in a patient monitoring device includes acquiring one or more signals using the patient monitoring device. One or more signal quality metrics are determined based on the one or more acquired signals. A noise condition is detected based on the one or more signal quality metrics, and a determination is made whether the noise condition should be classified as intermittent or persistent. One or more actions are taken based on the classification of detected noise as intermittent or persistent.

Abstract: Embodiments of the present disclosure describe a method of monitoring a patient comprising generating an accelerometer signal of a patient via a patient medical device and capturing and sampling the accelerometer signal at a sampling rate that utilizes non-regular timing intervals. Embodiments further describe a patient medical device comprising sensors for monitoring an accelerometer signal of a patient and circuitry for sampling the accelerometer signal at a sampling rate that utilizes non-regular timing intervals. Embodiments also describe a method of processing physiological signals comprising monitoring ECG signals and accelerometer signals of a patient via a patient medical device and capturing an ECG segment and sampling the accelerometer signal at a sampling rate that utilizes non-regular timing intervals.

Abstract: In various examples, an apparatus includes an apparatus configured for implantation within a body of a patient. The apparatus, in some examples, includes a housing. At least one antenna extends from the housing, the antenna being flexible such that the antenna conforms to the body of the patient. In some examples, the apparatus includes at least three electrodes, wherein at least a first electrode is disposed on the antenna and at least a second electrode is disposed on the housing. The at least three electrodes are disposed in a non-linear configuration, allowing for differential processing of signals recorded by the at least three electrodes.

Abstract: A medical device includes a housing and an electrode arrangement coupled to the housing and configured to sense an electrical physiologic signal from a patient. The device also includes detection circuitry coupled to the electrode arrangement and configured to obtain a cardiac signal component and a non-cardiac signal component from the physiological signal. A processor is coupled to the detection circuitry. The processor is configured to detect patient activity using at least the non-cardiac signal component and discriminate between voluntary and involuntary activity of the patient based on a comparison of temporally aligned cardiac and non-cardiac signal components.

Abstract: A medical device is utilized to monitor physiological parameters of a patient and capture segments of the monitored physiological parameters. The medical device includes circuitry configured to monitor one or more physiological parameters associated with the patient and an analysis module that includes a buffer and a processor. The buffer stores monitored physiological parameters and the processor analyzes the monitored physiological parameters and triggers capture of segments from the buffer in response to a triggering criteria being satisfied. The analysis module selects a pre-trigger duration based at least in part on the triggering criteria.

Abstract: Embodiments of the present disclosure describe methods of adaptive arrhythmia detection comprising monitoring ECG signals of a patient via a patient medical device, detecting and capturing ECG segments based on a heart rate threshold and an initial sensitivity level associated with the heart rate threshold; and adjusting the sensitivity level based on previously captured ECG segments. Embodiments of the present disclosure further describe patient medical devices comprising one or more electrodes and sensing circuitry for monitoring ECG signals of a patient; and a processing module configured to receive the monitored ECG signal, wherein the processing module detects and captures ECG segments based on a plurality of heart rate thresholds and one or more sensitivity levels associated with each of the heart rate thresholds, and adjusts at least one of the one or more sensitivity levels associated with each of the heart rate thresholds.

Abstract: A system and method of flagging monitored ECG samples for urgent review by a human expert is described, and includes monitoring an electro-cardiogram (ECG) signal of the patient with an adherent device that includes a plurality of electrodes. Based on the monitored ECG signal, detected rhythm abnormalities in the patient are detected and ECG samples are collected with respect to detected rhythm abnormalities. One or more features are identified with respect to each ECG sample, and the features are utilized to flag ECG samples for urgent review by a human expert.

Abstract: A medical device is utilized to monitor physiological parameters of a patient and capture segments of the monitored physiological parameters. The medical device includes circuitry configured to monitor one or more physiological parameters associated with the patient and an analysis module that includes a buffer and a processor. The buffer stores monitored physiological parameters and the processor analyzes the monitored physiological parameters and triggers capture of segments from the buffer in response to a triggering criteria being satisfied. The analysis module selects a pre-trigger duration based at least in part on the triggering criteria.

Abstract: Embodiments of the present disclosure describe methods of adaptive arrhythmia detection comprising monitoring ECG signals of a patient via a patient medical device, detecting and capturing ECG segments based on a heart rate threshold and an initial sensitivity level associated with the heart rate threshold; and adjusting the sensitivity level based on previously captured ECG segments. Embodiments of the present disclosure further describe patient medical devices comprising one or more electrodes and sensing circuitry for monitoring ECG signals of a patient; and a processing module configured to receive the monitored ECG signal, wherein the processing module detects and captures ECG segments based on a plurality of heart rate thresholds and one or more sensitivity levels associated with each of the heart rate thresholds, and adjusts at least one of the one or more sensitivity levels associated with each of the heart rate thresholds.

Abstract: An apparatus, system, and method directed to detecting a physiological signal during discrete time separated detection windows, deriving one or more respiratory disturbance indices from the physiological signal, detecting a respiratory disturbance state in response to the one or more respiratory disturbance indices deviating from a threshold value, interpolating the one or more respiratory disturbance indices between adjacent time separated detection windows, and declaring a respiratory disturbance episode based on the detected respiratory disturbance state during the detection windows and the interpolation between detection windows.

Abstract: Embodiments of the present disclosure describe methods of adaptive arrhythmia detection comprising monitoring ECG signals of a patient via a patient medical device, detecting and capturing ECG segments based on a heart rate threshold and an initial sensitivity level associated with the heart rate threshold; and adjusting the sensitivity level based on previously captured ECG segments. Embodiments of the present disclosure further describe patient medical devices comprising one or more electrodes and sensing circuitry for monitoring ECG signals of a patient; and a processing module configured to receive the monitored ECG signal, wherein the processing module detects and captures ECG segments based on a plurality of heart rate thresholds and one or more sensitivity levels associated with each of the heart rate thresholds, and adjusts at least one of the one or more sensitivity levels associated with each of the heart rate thresholds.

Abstract: A system and method for detecting arrhythmic electrocardiogram (ECG) signals includes defining a plurality of threshold heart rates and rate-dependent sensitivity levels for detecting arrhythmic ECG episodes, wherein more clinically relevant heart rates are assigned rate-dependent sensitivity levels with higher sensitivities. ECG signals are monitored by a medical device, and monitored ECG signals are processed using the plurality of threshold heart rates and rate-dependent sensitivity levels to detect and capture arrhythmic ECG segments.