Abstract: A system for identifying arrhythmias based on cardiac waveforms includes a storage system storing a trained deep neural network system, wherein the trained deep neural system includes a trained representation neural network and a trained classifier neural network. A processing system is communicatively connected to the storage system and configured to receive cardiac waveform data for a patient, identify a time segment in the cardiac waveform data, and transform the time segment into a spectrum image. The processing system is further configured to generate, with the representation neural network, a latent representation from the spectrum image, and then to generate, with the classifier neural network, an arrhythmia classifier from the latent representation.

Abstract: A system for identifying arrhythmias based on cardiac waveforms includes a storage system storing a trained deep neural network system, wherein the trained deep neural system includes a trained representation neural network and a trained classifier neural network. A processing system is communicatively connected to the storage system and configured to receive cardiac waveform data for a patient, identify a time segment in the cardiac waveform data, and transform the time segment into a spectrum image. The processing system is further configured to generate, with the representation neural network, a latent representation from the spectrum image, and then to generate, with the classifier neural network, an arrhythmia classifier from the latent representation.

Abstract: A system for processing ECG to detect atrial fibrillation includes three software modules. A beat module is executable on a processor to receive a time series of ECG data, identify heart beats, and determine a beat AFIB value based on a timing of each identified heart beat. The beat AFIB value represents a presence or absence of AFIB based on variability in the timing of each identified heart beat. A segment module is executable to receive the time series of ECG data, divide the time series of ECG data into two or more time segments, and determine a segment AFIB value for each time segment. The segment AFIB value indicates a presence or absence of AFIB in the time segment based on whether any of a set of rhythms are identified. The AFIB detection module is executable to determine an AFIB identification value for each time segment based on the beat AFIB value during that time segment and the segment AFIB value for that time segment.

Abstract: A system for processing ECG to detect atrial fibrillation includes three software modules. A beat module is executable on a processor to receive a time series of ECG data, identify heart beats, and determine a beat AFIB value based on a timing of each identified heart beat. The beat AFIB value represents a presence or absence of AFIB based on variability in the timing of each identified heart beat. A segment module is executable to receive the time series of ECG data, divide the time series of ECG data into two or more time segments, and determine a segment AFIB value for each time segment. The segment AFIB value indicates a presence or absence of AFIB in the time segment based on whether any of a set of rhythms are identified. The AFIB detection module is executable to determine an AFIB identification value for each time segment based on the beat AFIB value during that time segment and the segment AFIB value for that time segment.

Abstract: A method is provided for determining cellular electrical potentials using a state estimator. The state estimator is generated using at least an electrical source model and an electrical conduction model. One or more parameters or states of the state estimator are adjusted based on a measured electrocardiographic and/or a measured body-surface-potential signal. The electrical potential of one or more cells is determined based on the one or more adjusted parameters or states. In one aspect of the present technique, one or more representations of an organ comprising the one or more cells is generated such that the electrical potential or its deriving characteristic of the one or more cells is visually indicated.

Abstract: The present disclosure includes a system and method of detecting LQTS in a patient by comparing a collected set of ECG data from the patient to a plurality of databases of collected ECG data. The plurality of databases will include a database containing previous ECGs from the patient, a known acquired LQTS characteristics database, and a known genetic LQTS characteristics database. Comparing the patients ECG to these databases will facilitate the detection of such occurrences as changes in QT interval from success of ECGs, changes in T-wave morphology, changes in U-wave morphology and can match known genetic patterns of LQTS. The system and method is sensitive to patient gender and ethnicity, as these factors have been shown to effect LQTS, and is furthermore capable of matching a QT duration to a database of drug effects. The system and method is also easily integrated into current ECG management systems and storage devices.

Abstract: The present disclosure includes a system and method of detecting LQTS in a patient by comparing a collected set of ECG data from the patient to a plurality of databases of collected ECG data. The plurality of databases will include a database containing previous ECGs from the patient, a known acquired LQTS characteristics database, and a known genetic LQTS characteristics database. Comparing the patients ECG to these databases will facilitate the detection of such occurrences as changes in QT interval from success of ECGs, changes in T-wave morphology, changes in U-wave morphology and can match known genetic patterns of LQTS. The system and method is sensitive to patient gender and ethnicity, as these factors have been shown to effect LQTS, and is furthermore capable of matching a QT duration to a database of drug effects. The system and method is also easily integrated into current ECG management systems and storage devices.

Abstract: A method is provided for determining cellular electrical potentials using a state estimator. The state estimator is generated using at least an electrical source model and an electrical conduction model. One or more parameters or states of the state estimator are adjusted based on a measured electrocardiographic and/or a measured body-surface-potential signal. The electrical potential of one or more cells is determined based on the one or more adjusted parameters or states. In one aspect of the present technique, one or more representations of an organ comprising the one or more cells is generated such that the electrical potential or its deriving characteristic of the one or more cells is visually indicated.

Abstract: The present disclosure includes a system and method of detecting LQTS in a patient by comparing a collected set of ECG data from the patient to a plurality of databases of collected ECG data. The plurality of databases will include a database containing previous ECGs from the patient, a known acquired LQTS characteristics database, and a known genetic LQTS characteristics database. Comparing the patients ECG to these databases will facilitate the detection of such occurrences as changes in QT interval from success of ECGs, changes in T-wave morphology, changes in U-wave morphology and can match known genetic patterns of LQTS. The system and method is sensitive to patient gender and ethnicity, as these factors have been shown to effect LQTS, and is furthermore capable of matching a QT duration to a database of drug effects. The system and method is also easily integrated into current ECG management systems and storage devices.

Abstract: A method and apparatus for analyzing the QT interval characteristics of ECG signal data having a succession of waveforms produced by the beating of the heart. ECG signal data is obtained from a patient. The R-R interval and the QT intervals of the waveforms of the ECG signal data are determined. Waveforms of the ECG signal data having a stable heart rate are selected for use in determining the QT interval characteristics. Preferably, the waveforms selected are those having minimum R-R interval standard deviation and minimum R-R interval dispersion. The QT correction (QTc) is computed from the ECG signal data waveforms selected in the foregoing manner or on the basis of clinician editing. The R-R intervals, the QT intervals, and QTc for the heart beats of the selected waveforms are displayed for analysis and diagnosis purposes. The invention can also be used, in an analogous manner, to obtain and display other cardiac data from the ECG waveforms.

Abstract: In a multi-tier patient monitoring data analysis system, an algorithm server is positioned as a middle tier between an acquisition device, such as a cardiograph or patient monitor that can be seen as a lower tier, and a storage device for a database, such as that of a central computer for a hospital or clinic that can be seen as an upper tier. The algorithm server gathers current data from the real time acquisition device and obtains previously stored ECG signal data from the database. The algorithm server contains ECG analysis algorithm(s) and runs one or more algorithms using the current and previously acquired ECG signal data. Analysis algorithms may also be run on the acquisition device. The system provides the rapid, extensive, and thorough ECG analysis that is critical to patient welfare.

Abstract: Method and apparatus for determining alternans data of an ECG signal. The method can include determining at least one value representing at least one morphology feature of each beat of the ECG signal and generating a set of data points based on a total quantity of values and a total quantity of beats. The data points can each include a first value determined using a first mathematical function and a second value determined using a second mathematical function. The method can also include several preprocessing algorithms to improve the signal to noise ratio. The method can also include separating the data points into a first group of points and a second group of points and generating a feature map by plotting the first group of points and the second group of points in order to assess an alternans pattern of variation. The feature map can be analyzed by statistical tests to determine the significance difference between groups and clusters.

Abstract: Method and apparatus for determining alternans data of an ECG signal. The method can include determining at least one value representing at least one morphology feature of each beat of the ECG signal and generating a set of data points based on a total quantity of values and a total quantity of beats. The data points can each include a first value determined using a first mathematical function and a second value determined using a second mathematical function. The method can also include several preprocessing algorithms to improve the signal to noise ratio. The method can also include separating the data points into a first group of points and a second group of points and generating a feature map by plotting the first group of points and the second group of points in order to assess an alternans pattern of variation. The feature map can be analyzed by statistical tests to determine the significance difference between groups and clusters.

Abstract: Method and apparatus for determining alternans data of an ECG signal. The method can include determining at least one value representing at least one morphology feature of each beat of the ECG signal and generating a set of data points based on a total quantity of values and a total quantity of beats. The data points can each include a first value determined using a first mathematical function and a second value determined using a second mathematical function. The method can also include several preprocessing algorithms to improve the signal to noise ratio. The method can also include separating the data points into a first group of points and a second group of points and generating a feature map by plotting the first group of points and the second group of points in order to assess an alternans pattern of variation. The feature map can be analyzed by statistical tests to determine the significance difference between groups and clusters.

Abstract: Method and apparatus for assessing a patient's cardiac vulnerability to sudden cardiac death. The method can include defining a relationship between depolarization and repolarization, determining a first value representative of the relationship for a first beat, determining a second value representative of the relationship for a second beat, and analyzing variation of the first value and the second value to assess the patient's cardiac vulnerability to sudden cardiac death.

Abstract: Method and apparatus for detecting cardiac repolarization abnormality using at least one electrocardiogram signal. The at least one electrocardiogram signal can be obtained from any number of continuous or non-continuous windows. The method can include deriving a total quantity of representative beats of the at least one electrocardiogram signal. At least one morphology shape descriptor can be used to determine a total quantity of values representing the total quantity of representative beats. Data corresponding to at least some of the total quantity of values can be used to assess cardiac repolarization abnormality.

Abstract: A system and method is provided for registering a representation of a probe with an image. One embodiment of a method comprises acquiring an image of or pertaining to a heart and registering a representation of a probe which is in or adjacent to the heart with the image using a heart vector of the heart.

Abstract: A system and method is provided for registering a representation of a probe with an image. One embodiment of a method comprises locating a feature of or relating to a heart with a probe which is inside the body and registering a representation of the probe with an image of the heart using the feature.

Abstract: A system and method is provided for registering a representation of a probe with an image. One embodiment of a method comprises acquiring an image pertaining to an organ or structure inside a body and registering a representation of a probe which is inside the body with the image, the representation of the probe and the image being registered to substantially the same point in a bodily cycle.

Abstract: A method of displaying a representation of a physiological signal produced by a patient. The method includes the acts of obtaining a portion of at least one physiological signal acquired from the patient, determining an area to display, and constructing a virtual image representing at least a portion of the patient. The virtual image including (M) polygonal areas. The method further includes transforming the obtained signal to a plurality of values, assigning each value to one of the (M) polygonal areas, assigning a visual characteristic to each polygonal area based in part on the assigned values, and displaying at least a portion of the virtual image including the assigned visual characteristics. The invention further provides a method of optimal feature selection for the classification of the physiological signals produced by a patient.