Abstract: A medical system including processing circuitry configured to receive a cardiac signal indicative of a cardiac characteristic of a patient from sensing circuitry and configured to receive a glucose signal indicative of a glucose level of the patient. The processing circuitry is configured to formulate a training data set including one or more training input vectors using the cardiac signal and one or more training output vectors using the glucose signal. The processing circuitry is configured to train a machine learning algorithm using the formulated training data set. The processing circuitry is configured to receive a current cardiac signal from the patient and determine a representative glucose level using the current cardiac signal and the trained machine learning algorithm.

Abstract: An example device for detecting one or more parameters of a cardiac signal is disclosed herein. The device includes one or more electrodes and sensing circuitry configured to sense a cardiac signal via the one or more electrodes. The device further includes processing circuitry configured to determine a representative signal based on the cardiac signal, the representative signal having a single polarity, and determine an end of a T-wave of the cardiac signal based on an area under the representative signal.

Abstract: In some examples, determining a heart failure status using a medical device comprising one or more sensors includes determining a first value of a heart beat variability metric of a patient while an activity state of a patient satisfies an inactivity criterion based on a signal received from the one or more sensors, and determining, within a predetermined period of time after further determining that the activity state of the patient no longer satisfies the inactivity criterion, a second value of the heart beat variability metric while the activity state of the patient no longer satisfies the inactivity criterion based on the signal. A difference between the first value of the heart beat variability metric and the second value of the heart beat variability metric may be determined and the heart failure status of the patient may be determined based on the difference.

Abstract: A medical system including processing circuitry configured to receive a cardiac signal indicative of a cardiac characteristic of a patient from sensing circuitry and configured to receive a glucose signal indicative of a glucose level of the patient. The processing circuitry is configured to formulate a training data set including one or more training input vectors using the cardiac signal and one or more training output vectors using the glucose signal. The processing circuitry is configured to train a machine learning algorithm using the formulated training data set. The processing circuitry is configured to receive a current cardiac signal from the patient and determine a representative glucose level using the current cardiac signal and the trained machine learning algorithm.

Abstract: In some examples, determining a heart failure status using a medical device comprising one or more sensors includes determining a first value of a heart beat variability metric of a patient while an activity state of a patient satisfies an inactivity criterion based on a signal received from the one or more sensors, and determining, within a predetermined period of time after further determining that the activity state of the patient no longer satisfies the inactivity criterion, a second value of the heart beat variability metric while the activity state of the patient no longer satisfies the inactivity criterion based on the signal. A difference between the first value of the heart beat variability metric and the second value of the heart beat variability metric may be determined and the heart failure status of the patient may be determined based on the difference.

Abstract: A medical system including processing circuitry configured to receive a cardiac signal indicative of a cardiac characteristic of a patient from sensing circuitry and configured to receive a glucose signal indicative of a glucose level of the patient. The processing circuitry is configured to formulate a training data set including one or more training input vectors using the cardiac signal and one or more training output vectors using the glucose signal. The processing circuitry is configured to train a machine learning algorithm using the formulated training data set. The processing circuitry is configured to receive a current cardiac signal from the patient and determine a representative glucose level using the current cardiac signal and the trained machine learning algorithm.

Abstract: A medical device is configured to determine tachyarrhythmia evidence in a cardiac signal segment received from a cardiac electrical signal sensed during a pacing escape interval started to schedule a pending cardiac pacing pulse. The medical device may delay the pending cardiac pacing pulse in response to determining the tachyarrhythmia evidence during the pacing escape interval.

Abstract: A medical device is configured to determine an amplitude metric from a cardiac signal segment sensed over a predetermined time interval and determine if the amplitude metric meets an amplitude threshold. The medical device is configured to perform a first analysis of the cardiac electrical signal segment for detecting a first arrhythmia when the amplitude metric does not meet the amplitude threshold and perform a second analysis of the cardiac electrical signal segment for detecting a second arrhythmia different than the first arrhythmia in response to the amplitude metric meeting the amplitude threshold.

Abstract: A medical device is configured to receive cardiac electrical signals and sense ventricular event signals from the cardiac electrical signals. The medical device may start a validation window in response to sensing a ventricular event signal and determine if the ventricular event signal is a valid event signal or an invalid event signal based on processing of a different cardiac electrical signal than the cardiac electrical signal from which the ventricular event signal was sensed.

Abstract: A medical device is configured to sense first ventricular event signals from a first cardiac electrical signal and sense second ventricular event signals from a second cardiac electrical signal. The medical device is configured to determine sensed event data in response to the first ventricular event signals and the second ventricular event signals. The medical device may select one of the first cardiac electrical signal or the second cardiac electrical signal for providing input for tachyarrhythmia detection based on the sensed event data.

Abstract: A medical system including processing circuitry configured to receive a cardiac signal indicative of a cardiac characteristic of a patient from sensing circuitry and configured to receive a glucose signal indicative of a glucose level of the patient. The processing circuitry is configured to formulate a training data set including one or more training input vectors using the cardiac signal and one or more training output vectors using the glucose signal. The processing circuitry is configured to train a machine learning algorithm using the formulated training data set. The processing circuitry is configured to receive a current cardiac signal from the patient and determine a representative glucose level using the current cardiac signal and the trained machine learning algorithm.

Abstract: Techniques are described including sensing at least one cardiac signal for a patient during a specified time period; determining a short-term variability (STV) metric for the patient based on the at least one cardiac signal sensed during the specified time period, wherein determining the STV metric comprises at least one of: controlling the determined STV metric based on one or more confounding factors, or correcting the determined STV metric based on the one or more confounding factors, wherein the one or more confounders comprise T-wave morphology; and generating a corresponding notification based on the STV metric to one or more computing devices.

Abstract: An example device for detecting one or more parameters of a cardiac signal is disclosed herein. The device includes one or more electrodes and sensing circuitry configured to sense a cardiac signal via the one or more electrodes. The device further includes processing circuitry configured to determine a representative signal based on the cardiac signal, the representative signal having a single polarity, and determine an end of a T-wave of the cardiac signal based on an area under the representative signal.

Abstract: A medical system including processing circuitry configured to receive a cardiac signal indicative of a cardiac characteristic of a patient from sensing circuitry and configured to receive a glucose signal indicative of a glucose level of the patient. The processing circuitry is configured to formulate a training data set including one or more training input vectors using the cardiac signal and one or more training output vectors using the glucose signal. The processing circuitry is configured to train a machine learning algorithm using the formulated training data set. The processing circuitry is configured to receive a current cardiac signal from the patient and determine a representative glucose level using the current cardiac signal and the trained machine learning algorithm.

Abstract: An example device for detecting one or more parameters of a cardiac signal is disclosed herein. The device includes one or more electrodes and sensing circuitry configured to sense a cardiac signal via the one or more electrodes. The device further includes processing circuitry configured to determine a representative signal based on the cardiac signal, the representative signal having a single polarity, and determine an end of a T-wave of the cardiac signal based on an area under the representative signal.

Abstract: A method includes detecting whether one or more myocardial infarctions (MI) has occurred using vectorcardiographic (VCG) signals with gradient boosting, the VCG signals including VCG loops, and determining an MI location using the VCG signals and gradient boosting.

Abstract: An example device for detecting one or more parameters of a cardiac signal is disclosed herein. The device includes one or more electrodes and sensing circuitry configured to sense a cardiac signal via the one or more electrodes. The device further includes processing circuitry configured to determine a representative signal based on the cardiac signal, the representative signal having a single polarity, and determine an end of a T-wave of the cardiac signal based on an area under the representative signal.

Abstract: In some examples, determining a heart failure status using a medical device comprising one or more sensors includes determining a first value of a heart beat variability metric of a patient while an activity state of a patient satisfies an inactivity criterion based on a signal received from the one or more sensors, and determining, within a predetermined period of time after further determining that the activity state of the patient no longer satisfies the inactivity criterion, a second value of the heart beat variability metric while the activity state of the patient no longer satisfies the inactivity criterion based on the signal. A difference between the first value of the heart beat variability metric and the second value of the heart beat variability metric may be determined and the heart failure status of the patient may be determined based on the difference.

Abstract: An example device for detecting one or more parameters of a cardiac signal is disclosed herein. The device includes one or more electrodes and sensing circuitry configured to sense a cardiac signal via the one or more electrodes. The device further includes processing circuitry configured to determine a representative signal based on the cardiac signal, the representative signal having a single polarity, and determine an end of a T-wave of the cardiac signal based on an area under the representative signal.

Abstract: Methods and related systems and devices for cardiac therapy use pseudo-electric vectors (PEVs) for characterizing and representing the electrical forces generated by a patient's heart in a three-dimensional (3D) manner. PEVs may be used to predict whether a patient will respond to pacing therapy prior to implant, during implant, or in the follow-up after implant. Various cardiac therapy systems and devices, such as an electrocardiogram (ECG) belt or vest, which may include a plurality of external electrodes, may be used to obtain electrical activity information to generate the PEVs. One or more spatio-temporal PEVs may be determined using one or more sensors at one or more points in time. Spatial representation data may be determined based on the PEVs.