A method of generating a model for generating a synthetic electrocardiography (ECG) signal comprises: receiving subject-specific training data for machine learning, said training data comprising a photoplethysmography (PPG) signal acquired from the subject and an ECG signal acquired from the subject, wherein the ECG signal provides a ground truth of the subject for associating the ECG signal with the PPG signal; using associated pairs of a time-series of the PPG signal and a corresponding time-series of the ECG signal as input to a deep neural network, DNN; and determining, through the DNN, a subject-specific model relating the PPG signal of the subject to the ECG signal of the subject for converting the PPG signal to a synthetic ECG signal using the subject-specific model.

A method of generating a model for generating a synthetic electrocardiography (ECG) signal comprises: receiving subject-specific training data for machine learning, said training data comprising a photoplethysmography (PPG) signal acquired from the subject and an ECG signal acquired from the subject, wherein the ECG signal provides a ground truth of the subject for associating the ECG signal with the PPG signal; using associated pairs of a time-series of the PPG signal and a corresponding time-series of the ECG signal as input to a deep neural network, DNN; and determining, through the DNN, a subject-specific model relating the PPG signal of the subject to the ECG signal of the subject for converting the PPG signal to a synthetic ECG signal using the subject-specific model.

An apparatus for generating ECG recordings and a method for using the same are disclosed. The apparatus includes a handheld device having four electrodes on an outer surface thereof, the handheld device having an extended configuration and a storage configuration. The apparatus also includes a controller configured to measure signals between the electrodes to provide signals that are used to generate an ECG recording selected from the group consisting of standard lead traces and precordial traces. When the handheld device is in the extended configuration and the first and second electrodes contact a first hand of a patient such that the first and second electrodes contact different locations on the first hand, the third electrode is in contact with a location on the patient's other hand and the fourth electrode contacts a point on the patient's body that depends on the particular trace being measured.

An apparatus for generating ECG recordings and a method for using the same are disclosed. The apparatus includes a handheld device having four electrodes on an outer surface thereof, the handheld device having an extended configuration and a storage configuration. The apparatus also includes a controller configured to measure signals between the electrodes to provide signals that are used to generate an ECG recording selected from the group consisting of standard lead traces and precordial traces. When the handheld device is in the extended configuration and the first and second electrodes contact a first hand of a patient such that the first and second electrodes contact different locations on the first hand, the third electrode is in contact with a location on the patient's other hand and the fourth electrode contacts a point on the patient's body that depends on the particular trace being measured.

A method includes the step of receiving electrocardiogram (ECG) data associated with a plurality of patients and an electrocardiogram configuration including a plurality of leads and a time interval. The electrocardiogram data includes, for each lead included in the plurality of leads, voltage data associated with at least a portion of the time interval. The method also includes training an artificial intelligence model on the ECG data, tuning the artificial intelligence model using data from a device having fewer leads than the plurality of leads, and evaluating the artificial intelligence model on additional data received from the ECG data.

A computer-implemented method for direct photoplethysmography or direct PPG comprises obtaining during a time interval plural PPG signals for respective sensors in a wearable device; and combining the plural PPG signals to thereby obtain a multi-sensor PPG signal.

A fully automated ultrasound apparatus includes a sensor or probe which can be initially manually attached to a side of the neck of a patient, an ultrasound interface to control the sensor and periodically acquire raw ultrasound data, a signal and image processing system to autonomously convert the raw ultrasound data into a measurement that is useful to physicians, and a display to relay the current measurements and measurement history to provide data trends. The sensor can include one or more ultrasound transducers built into a housing. A disposable component can serve to secure the sensor to the neck of the patient and to provide a coupling medium between the sensor and the skin of the patient.

An aspect of the present disclosure calculates a phase variance value indicating a degree of variance of a phase in a surrounding of each position in a biological tissue, based on phase values of excitation wave at respective positions in the biological tissue that acts in response to excitation caused by propagation of the excitation wave in the tissue, and generates an analysis map, based on a time series of at least part of the phase variance values at the respective positions. Since the phase variance value indicates the degree of variance of the phase in the surrounding, a position having a large degree of variance of the phase in the surrounding may be specified as a rotation center of rotating excitation wave.

An aspect of the present disclosure calculates a phase variance value indicating a degree of variance of a phase in a surrounding of each position in a biological tissue, based on phase values of excitation wave at respective positions in the biological tissue that acts in response to excitation caused by propagation of the excitation wave in the tissue, and generates an analysis map, based on a time series of at least part of the phase variance values at the respective positions. Since the phase variance value indicates the degree of variance of the phase in the surrounding, a position having a large degree of variance of the phase in the surrounding may be specified as a rotation center of rotating excitation wave.

An example method includes establishing a communications link between an electrophysiology (EP) monitoring system and an implantable medical device (IMD). IMD electrical data is received at the monitoring system via the communications link. The IMD electrical data may be synchronized with EP measurement data to provide synchronized electrical data based on timing of a synchronization signal sensed by an IMD electrode and/or EP electrodes. The method also includes computing reconstructed electrical signals for locations on a surface of interest within the patient's body based on the synchronized electrical data and geometry data. The geometry data represents locations of the EP electrodes, a location of the IMD electrode within the patient's body and the surface of interest.