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 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.

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: 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: A method of non-invasively monitoring advanced glycation end-product (AGE) concentrations includes providing incident light to patient tissue at one or more excitation wavelengths and monitoring the one or more emission responses at one or more emission wavelengths. Based on the emission responses monitored, a ratio is calculated based on a ratio of the first emission response to the second emission response.

Abstract: A method of non-invasively monitoring hemoglobin concentration includes providing incident light to patient tissue at a first excitation wavelength. The method further includes monitoring a first emission response at a first emission wavelength, wherein the first emission wavelength is selected to correspond with a maximum of the emission response, and monitoring a second emission response at a second emission wavelength, wherein the second emission wavelength is selected to correspond with a minimum of the emission response. A hemoglobin concentration is calculated based on a ratio of the first emission response to the second emission response.

Abstract: A method of non-invasively monitoring hematocrit levels includes monitoring a first emission response to the light provided at the first excitation wavelength, wherein the first emission response is monitored at a first wavelength and monitoring a second emission response to the light provided at the first excitation wavelength, wherein the second zemission response is monitored at a second wavelength. A ratiometric value is calculated based on a ratio of the first emission response to the second emission response, wherein the ratiometric value corresponds with hematocrit level of the patient.

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 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: In some examples, a medical system includes a medical device. The medical device may include a housing configured to be implanted in a target site of a patient, a light emitter configured to emit a signal configured to cause a fluorescent marker to emit a fluoresced signal into the target site, and a light detector that may be configured to detect the fluoresced signal. The medical system may include processing circuitry configured to determine a characteristic of the fluorescent marker based on the emitted signal and the fluoresced signal. The characteristic of the fluorescent marker may be indicative of a presence of a compound in the patient, and the processing circuitry may be configured to track the presence of the compound of the patient based on the characteristic of the fluorescent marker.

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.

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: An apparatus comprises an input configured to receive electrocardiogram (ECG) data detected by a patient monitoring device, the ECG data containing a physiologic signal and one or more segments of noise within the ECG data. A scrubber comprises a plurality of scrubbing modules each configured to process the ECG data and noise in a manner differing from other scrubbing modules. The scrubber is configured to filter the one or more noise segments that overlap with the physiologic signal, and consolidate the ECG data to eliminate the one or more noise segments that are non-overlapping with the physiologic signal. An output is configured to output scrubbed ECG data.