Abstract: Embodiments of the present disclosure utilize DNNs for ECG interpretation, where original ECG waveforms are directly ingested by the DNNs using paired interpretation labels for training, without the need for explicatory feature extraction or rule-based criteria.

Abstract: Disclosed are devices and methods for determining and memorializing chest electrode placement locations on a user. The device utilizes two datum reference points in the patient's anatomy, the Jugular notch and the Xiphoid process, which are easily found and repeatable and which serve to ensure the device is in the correct position to memorialize chest electrode placement locations. The device may comprise a first plate and a second plate operatively coupled to the first plate so that the second plate slides along a vertical axis of the first plate and the first plate slides along a vertical access of the second plate. The device may further comprise a template grid having a plurality of cells printed thereon. The template grid may have a coordinate system for identifying each of the plurality of cells. The template grid may be modified to indicate a set of chest electrode placement locations on the user.

Abstract: The embodiments presented herein provide a device comprising a sensor assembly configured to sense physiological signals corresponding to physiological parameters of a user when in contact with the user, and to produce electrical signals representing the sensed physiological signals. The device may also comprise a converter assembly that is electrically connected to the sensor assembly, and is configured to convert the electrical signals to a modulated signal. The device may further comprise a transmitter that transmits the modulated signal wirelessly to a computing device. The device may include a housing that contains the sensor assembly, the converter assembly, and the transmitter.

Abstract: A smart watch to detect a presence of an arrhythmia of a user is disclosed. The smart watch comprising: a processing device and a photoplethysmography (“PPG”) sensor operatively coupled to the processing device, an ECG sensor comprising two or more ECG electrodes and operatively coupled to the processing device, a display operatively coupled to the processing device, and a memory, operatively coupled to the processing device. The memory may have instructions stored thereon that, when executed by the processing device, cause the processing device to: receive PPG data from the PPG sensor, receive ECG data from the ECG sensor, detect, based on the PPG data and the ECG data simultaneously, the presence of an arrhythmia, and provide one or more recommendations to the user based on the PPG data and the ECG data.

Abstract: Disclosed herein are devices, systems, methods and platforms for continuously monitoring the health status of a user, for example the cardiac health status. The present disclosure describes systems, methods, devices, software, and platforms for continuously monitoring a user's health-indicator data (for example and without limitation PPG signals, heart rate or blood pressure) from a user-device in combination with corresponding (in time) data related to factors that may impact the health-indicator (“other-factors”) to determine whether a user has normal health as judged by or compared to, for example and not by way of limitation, either (i) a group of individuals impacted by similar other-factors, or (ii) the user him/herself impacted by similar other-factors.

Abstract: Described herein are software platforms (or “platforms”), systems and methods for providing effective healthcare to a patient while increasing the efficiency of a healthcare provider. A healthcare provider system may receive physiological data of a user and generate an interface to provide a visualization of the physiological data and identifying information of the user. The system may analyze the physiological data to generate a risk score for the user based at least in part on the physiological data and transmit to a device of the user, a notification comprising the risk score.

Abstract: An apparatus includes sporting equipment, a sensor assembly, and a processing device. The sensor assembly includes a first sensor and a second sensor that are integrated into the sporting equipment to contact skin of a user. The sensor assembly produces electrical signals indicative of physiological signals of the user. The processing device generates an electrocardiogram (ECG) based on the electrical signals.

Abstract: A mobile electrocardiogram (ECG) device is described, comprising an electrode assembly comprising electrodes that sense heart-related signals when in contact with a body of a user, and produce electrical signals representing the sensed heart-related signals. The mobile ECG device further comprises a light-emitting device to facilitate an optimal placement of the electrode on the body of the user. The mobile ECG device further comprises a housing containing the electrode assembly, the converter assembly, the transmitter, and the light-emitting device. A first electrode of the electrode assembly forms a first side of the housing and comprises an opening through which the light-emitting device provides the UV light.

Abstract: Embodiments of the present disclosure provide a monitoring device that combines blood pressure, SpO2, and ECG monitoring functionality into a single handheld device and can measure these parameters simultaneously. The monitoring device may comprise a first sensor comprising an electrode to measure electrical signals corresponding to cardiac activity of a user's heart and a second sensor comprising an electrode as well as an optical sensor to perform a PPG and measure an amount of light absorbed by the blood of the user concurrently with measurement of the electrical signals. The optical sensor may generate a blood pressure signal and an oxygen saturation signal based at least in part on the amount of light absorbed by the blood of the user. The optical sensor may include a neural network trained to estimate blood pressure based on PPG measurements and demographic information of the user, as discussed in further detail herein.

Abstract: Apparatuses and methods for extracting, de-noising, and analyzing electrocardiogram signals. Any of the apparatuses described herein may be implemented as a (or as part of a) computerized system. For example, described herein are apparatuses and methods of using them or performing the methods, for extracting and/or de-noising ECG signals from a starting signal. Also described herein are apparatuses and methods for analyzing an ECG signal, for example, to generate one or more indicators or markers of cardiac fitness, including in particular indicators of atrial fibrillation. Described herein are apparatuses and method for determining if a patient is experiencing a cardiac event, such as an arrhythmia.

Abstract: Embodiments of the present disclosure provide a mobile electrocardiogram (ECG) sensor comprising an electrode assembly comprising electrodes, wherein the electrode assembly senses heart-related signals when in contact with a body of a user, and produces electrical signals representing the sensed heart-related signals. The ECG sensor further comprises a processing device, operatively coupled to the electrode assembly, the processing device to provide the sensed heart-related signals to a machine learning module trained to predict a twelve-lead QT interval (QTc) value from the mobile ECG sensor comprising less than twelve leads. The ECG sensor also comprises a housing containing the electrode assembly and the processing device.

Abstract: Disclosed are systems for non-invasively determining a measurement of an analyte. The systems include an electrocardiogram sensor and a processing device operatively coupled to the electrocardiogram sensor. The processing device can execute instructions to receive electrocardiogram data from the electrocardiogram sensor and apply a machine learning model, wherein the machine learning model has been trained based on previous electrocardiogram data associated with a subject and source of an analyte measurement associated with the subject. The system may also determine an indication of a level of the analyte based on the electrocardiogram data.

Abstract: A set of training electrocardiograms (ECGs) for each of a plurality of subjects is processed using a machine learning model to generate an output for each training ECG of each of the plurality of subjects. Training ECGs for each subject are labeled with an identity of the subject. A machine learning model is trained by comparing the output generated for each training ECG to a corresponding label of the training ECG to generate an identity model to identify ECGs of a first subject of the plurality of subjects. A first ECG is received from an ECG sensor and input to the identity model, which generates an output indicating whether the first ECG corresponds to the first subject. In response to the output indicating that the first ECG does not correspond to the first subject, a condition that the first subject has or may develop is determined based on the output.

Abstract: Described herein are devices, systems, and methods for sensing, generating, and time aligning one or more of the 12 leads of a standard ECG. A set of electrodes may be used to perform an electrocardiogram (ECG) of a user to generate a set of limb leads including a first lead I. A Wilson's Central Terminal (WCT) value may be determined using a subset of the set of limb leads. In response to an electrode of the set of electrodes contacting the user's chest, a precordial lead may be generated based on electric potentials sensed by the electrode while contacting the user's chest and the WCT value. As the precordial lead is generated, a corresponding second lead I is simultaneously generated. The corresponding second lead I is used to time align the set of limb leads and the precordial lead.

Abstract: A digital stethoscope includes a stethoscope housing defining a housing edge. The digital stethoscope also includes a surface region secured to the stethoscope housing at the housing edge, and a number of microphones. The digital stethoscope also includes a processing device disposed within the stethoscope housing and in communication with the microphones. The processing device receives the digital audio data from the microphones.

Abstract: Disclosed is an ECG sensor having a packaging label form factor. The ECG sensor may comprise a set of electrodes configured to sense heart-related electrical activity when in contact with skin of a user and produce electrocardiogram (ECG) waveforms representing the sensed heart-related electrical activity. The ECG sensor may further comprise a processor configured to: identify, using a machine learning model, the user based on the ECG waveforms, convert the ECG waveforms to a modulated signal that carries the ECG waveforms representing the sensed heart-related electrical activity, and transmit the modulated signal wirelessly to a computing device using a transmitter. The ECG sensor may also comprise a housing having a first layer and a second layer, wherein the set of electrodes, the processor, and the transmitter are all disposed between the first layer and the second layer of the housing, and wherein the housing has a packaging-label form factor.

Abstract: Disclosed are systems for non-invasively determining a measurement of an analyte. The systems include an electrocardiogram sensor and a processing device operatively coupled to the electrocardiogram sensor. The processing device can execute instructions to receive electrocardiogram data from the electrocardiogram sensor and apply a machine learning model, wherein the machine learning model has been trained based on previous electrocardiogram data associated with a subject and source of an analyte measurement associated with the subject. The system may also determine an indication of a level of the analyte based on the electrocardiogram data.

Abstract: Embodiments of the present disclosure are directed to an electrocardiogram (ECG) monitoring device embedded into the construct of a controller (e.g., video game controller, steering wheel etc.) to monitor a user's heart health and diagnose various conditions (e.g., AFib, tachycardia, bradycardia, etc.). The controller may comprise a set of electrodes including electrodes to contact the user's hands and one or more electrodes on the back of the controller that can be used to contact the user's extremities as a 3rd contact point to provide additional leads for higher accuracy ECG sensing. The set of electrodes may be positioned at locations on the controller where the user's hands are relatively stable, thus minimizing motion artifacts caused by muscular movement (thereby allowing for signal stability and longevity).

Abstract: Disclosed systems and method receive electrocardiogram (EKG) data of a subject. The EKG data comprises a record of at least a full beat of the subject. The EKG data is input into a machine learning model to generate an output. The output can include a segmentation of the full beat or a measurement of a QT interval of the subject.

Abstract: Embodiments of the present disclosure relate to determining an optimal location on the body of a person where heart sounds may be optimally heard. The optimal location may be determined at a time prior to the attempted auscultation and ECG data corresponding to the optimal location may be stored in a memory of an auscultation device. Subsequently, when a e.g., physician wishes to listen to the heart sounds of the person, the physician may place the auscultation device at a first location on the patient. The auscultation device may periodically perform an ECG at a current location and use the ECG data at the current location and the ECG data at the optimal location to determine and provide guidance to the physician regarding a direction in which the auscultation device should be moved in order to reach the optimal location.