An artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus, the method comprising data preprocessing, heartbeat feature detection, interference signal detection and heartbeat classification based on deep learning, signal quality evaluation and lead combination, heartbeat verification, analysis and calculation of electrocardiography events and parameters, and finally automatic output of reporting data, realizing an automated analysis method having a complete and rapid flow. The automatic electrocardiography analysis method may also record modification information of an automatic analysis result, collect modified data, and feed same back to the depth learning model to continue training, thereby continuously making improvements and improving the accuracy of the automatic analysis method.

An artificial intelligence self-learning-based automatic electrocardiography analysis method and apparatus, the method comprising data preprocessing, heartbeat feature detection, interference signal detection and heartbeat classification based on deep learning, signal quality evaluation and lead combination, heartbeat verification, analysis and calculation of electrocardiography events and parameters, and finally automatic output of reporting data, realizing an automated analysis method having a complete and rapid flow. The automatic electrocardiography analysis method may also record modification information of an automatic analysis result, collect modified data, and feed same back to the depth learning model to continue training, thereby continuously making improvements and improving the accuracy of the automatic analysis method.

Computer-implemented methods of enabling an on-the-fly generation of at least one user-defined montage from EEG electrodes positioned in a patient's brain, on the patient's brain and/or on the patient's scalp. The methods includes generating a graphical interface to display a view of the patient's brain and/or scalp overlaid with the EEG electrodes, each of which is uniquely identified with reference to its position in the patient's brain, on the patient's brain and/or on the patient's scalp, displaying a tool within the graphical interface for selecting at least one electrode from the displayed EEG electrodes, indicating a reference electrode corresponding to the selected electrode, accessing EEG signals corresponding to the electrode and the reference electrode, and generating another graphical interface to display an EEG trace indicative of a comparison of EEG signals of the electrode and the reference electrode.

The invention provides systems and methods for monitoring the wellbeing of a fetus by the non-invasive detection and analysis of fetal cardiac electrical activity data.

A method of identifying an epileptogenic zone of a subjects brain includes: receiving a plurality N of physiological brain signals that extend over a duration, each of the plurality N of physiological brain signals acquired from the subjects brain; calculating within a time window a state transition matrix based on at least a portion of each of the plurality N of physiological brain signals, wherein the state transition matrix is a linear time invariant model of a network of N nodes corresponding to the plurality N of physiological brain signals; calculating a minimum norm of a perturbation on the state transition matrix that causes the network to transition from a stable state to an unstable state; and assigning a fragility metric to each of the plurality N of physiological brain signals based on the minimum norm of the perturbation for that physiological brain signal.

Systems and methods for monitoring physiologic response to Valsalva maneuver (VM) are disclosed. An exemplary patient monitor may detect a natural incidence of a VM session occurred in an ambulatory setting using a heart sound (HS) signal sensed from the patient. The patient monitor may include a physiologic response analyzer to sense patient physiologic response during the detected VM session, and generate a cardiovascular or autonomic function indicator based on the sensed physiologic response to the VM. Using the physiologic response to the VM, the system may detect a target physiologic event using the sensed physiologic response to the VM.

The present disclosure provides methods for diagnosing and determining the disease progression of neurodegenerative disorders in patients using neurophysiological biomarkers.

The present disclosure provides methods for diagnosing and determining the disease progression of neurodegenerative disorders in patients using neurophysiological biomarkers.

This specification describes methods of performing ECG analyses. In one approach, the system receives an ECG recording for a first duration, automatically performs a first analysis of the ECG recording for the first duration to detect events with reference to each of a plurality of arrhythmias, generates a GUI where areas within the GUI are designated for displaying detected events for each of the arrhythmias and enables a user to select at least one ECG segment of a second duration of the ECG recording. In response to the user's selection of the at least one ECG segment, the system presents the user with at least one option, and in response to the user's selection of the option, the system performs a second analysis of the ECG segment of the second duration and displays at least one output corresponding to the second analysis.

This specification describes methods of performing ECG analyses. In one approach, the system receives an ECG recording for a first duration, automatically performs a first analysis of the ECG recording for the first duration to detect events with reference to each of a plurality of arrhythmias, generates a GUI where areas within the GUI are designated for displaying detected events for each of the arrhythmias and enables a user to select at least one ECG segment of a second duration of the ECG recording. In response to the user's selection of the at least one ECG segment, the system presents the user with at least one option, and in response to the user's selection of the option, the system performs a second analysis of the ECG segment of the second duration and displays at least one output corresponding to the second analysis.