A system is provided for generating a classifier for classifying electromagnetic data (e.g., ECG) derived from an electromagnetic source (e.g., heart). The system accesses a computational model of the electromagnetic source. The computational model models the electromagnetic output of the electromagnetic source over time based on a source configuration (e.g., rotor location) of the electromagnetic source. The system generates, for each different source configuration (e.g., different rotor locations), a modeled electromagnetic output (e.g., ECG) of the electromagnetic source for that source configuration. For each modeled electromagnetic output, the system derives the electromagnetic data for the modeled electromagnetic output and generates a label (e.g., rotor location) for the derived electromagnetic data from the source configuration for the modeled electromagnetic data. The system trains a classifier with the derived electromagnetic data and the labels as training data. The classifier can then be used to classify the electromagnetic output collected from patients.

Methods and systems are provided for detecting arrhythmias in cardiac activity. The methods and systems declare a current beat, from the CA signals, to be a candidate beat or an ineligible beat based on whether the current beat satisfies the rate based selection criteria. The determining and declaring operations are repeated for multiple beats to form an ensemble of candidate beats. The method and system calculate a P-wave segment ensemble from the ensemble of candidate beats, perform a morphology-based comparison between the P-wave segment ensemble and at least one of a monophasic or biphasic template, declare a valid P-wave to be present within the CA signals based on the morphology-based comparison, and utilize the valid P-wave in an arrhythmia detection process to determine at least one of an arrhythmia entry, arrhythmia presence or arrhythmia exit.

Methods, systems, and apparatus for detecting and/or validating a detection of a state change by matching the shape of one or more of an cardiac data series, a heart rate variability data series, or at least a portion of a heart beat complex, derived from cardiac data, to an appropriate template.

Disclosed herein are example methods and systems for non-invasive cardiovascular risk assessment using heart rate variability fragmentation. A first set of electrocardiogram (ECG) signals may be received from a subject. Data from the first set of ECG signals may be analyzed to identify sign changes in heart rate acceleration in the first set of ECG signals. Based on the identified sign changes in heart rate acceleration, a degree of fragmentation in the first set of ECG signals may be determined. Afterwards, cardiovascular risk of the subject may be assessed based on the degree of fragmentation.

A heartbeat analyzing method and a heartbeat analyzing system are provided. The heartbeat analyzing method includes: sensing a user using a wearable device and acquiring a physiological signal record; performing a dispersion calculation to the physiological signal record using the wearable device and generating a Poincar plot of the physiological signal record; and inputting the Poincar plot into a heart rhythm classifier model and determining a heartbeat classification of the user based on personal health data of the user.

Systems and techniques for managing biological signals. In one implementation, a method includes receiving a cardiac biological signal that includes information describing events, determining a merit of each event based on one or more of a severity of a cardiac condition associated with the event and a quality of the event, and handling a subset of the events that meet a merit criterion. The subset can be handled for medical purposes.

Disclosed herein are implantable medical devices and systems, and methods for used therewith, that selectively perform atrial overdrive pacing while an intrinsic atrial rate of a patient is within a specified range. Such a method can involve measuring intervals between a plurality of intrinsic atrial depolarizations that occur during a specified period, and classifying intrinsic atrial activity as stable or unstable based on the measured intervals. In response to classifying the intrinsic atrial activity as stable, atrial overdrive pacing is performed. In response to classifying the intrinsic atrial rate as unstable, atrial overdrive pacing is not performed (i.e., is abstained from being performed). Over time, effectiveness of performing atrial overdrive pacing using various different atrial interval shorting deltas are recorded in a log and updated, and the log is used to determine a preferred rate at which to perform atrial overdrive pacing for various different measured intervals.

A convolutional neural cardiac diagnostic system employs an echocardiogram diagnostic controller for controlling a diagnosis of an echocardiogram including a temporal sequence of echocardiac cycles. The echocardiogram diagnostic controller includes a diagnostic periodic volume generator generating an echocardiogram diagnostic volume including a periodic stacking of the temporal sequence of echocardiac cycles, and further includes a diagnostic convolutional neural network classifying the echocardiogram as either a normal echocardiogram or an abnormal echocardiogram based on a convolutional neural analysis of the echocardiogram diagnostic volume. The diagnostic periodic volume generator may further generate an electrocardiogram diagnostic volume including a periodic stacking of the temporal sequence of electrocardiac waves, and the convolutional neural network may classify the echocardiogram as either a normal echocardiogram or an abnormal echocardiogram based on a convolutional neural analysis of both the echocardiogram diagnostic volume and the electrocardiogram diagnostic volume.

A method of obtaining and analyzing ECG data from a patient or group of patients is disclosed. The ECG data is obtained from the patient at an acquisition device. Once the ECG data is obtained, the ECG data is transmitted to an analysis server that is operated by an analysis provider and is located remote from the location of the acquisition device. Along with the ECG data, acquisition parameters are transmitted to the analysis server. At the analysis server, one of a plurality of algorithms is selected to analyze the ECG data. If an abnormality is detected, the patient information is directed to a healthcare provider who can then contact the patient to schedule an appointment. Based upon the referral, a referral fee can be transferred from the healthcare provider to the analysis provider. The patient can be prompted to provide additional information and selections that dictate the level of analysis generated.

This disclosure is directed to techniques for identifying false detection of asystole in a cardiac electrogram that include determining whether at least one of a plurality of false asystole detection criteria are satisfied. In some examples, the plurality of false asystole detection criteria includes a first false asystole detection criterion including a reduced amplitude threshold for detecting cardiac depolarizations in the cardiac electrogram, and a second false asystole detection criterion for detecting decaying noise in the cardiac electrogram.