Disclosed herein, in some aspects, are systems and methods for detecting, monitoring, and managing a cardiac health status for a subject using ECG data. In some embodiments, the system receives health parameter measurements from one or more devices that are then used by a cardiac health tool (CHT) to determine a cardiac health status. Exemplary health parameter measurements include electrocardiogram (ECG) data from an ECG device and/or weight (from a weight scale for example). As described herein, in some embodiments, determining the cardiac health status includes a) detecting a cardiac condition in the subject, b) predicting a risk of a subject developing a cardiac condition (cardiac condition risk), and/or c) temporal monitoring of a cardiac health status for a subject. In some embodiments, the cardiac health tool is configured to determine the efficacy of a treatment or therapy applied to reduce the severity and/or risk of a cardiac condition.

An ECG system identifies and annotates cardiac electrophysiological signals in an ECG waveform from harmonic waveforms. Electrical impulses are received from a beating heart. The electrical impulses are converted to an ECG waveform. The ECG waveform is converted to a frequency domain waveform, which, in turn, is separated into two or more different frequency domain waveforms, which, in turn, are converted into a plurality of time domain cardiac electrophysiological subwaveforms and discontinuity points between these subwaveforms. The plurality of subwaveforms and discontinuity points are compared to a database of subwaveforms and discontinuity points for normal and abnormal patients. At least one subwaveform or one or more discontinuity points are identified as a normal or abnormal electrophysiological signal of the ECG waveform from the comparison. The ECG waveform is displayed along with one or more markers at a location of the at least one subwaveform or one or more discontinuity points.

The present disclosure encompasses an artifact score derived from the signal characteristics of an acquired 12-lead ECG, (2) a patient context score derived from key elements of the patient's history, presentation, and prehospital emergency care, and (3) techniques for integrating these scores into an emergency medical care system.

The present technology is an automated method for determining whether a patient-specific electrocardiogram (ECG) is either (a) Normal and can be excluded from manual review or (b) Abnormal and included for manual review. In one embodiment, the method comprises comparing a plurality of characteristics of the ECG with predetermined subthreshold levels that are set less than clinically significant levels of abnormality of the characteristics, wherein the characteristics of the ECG are selected from the group including T-Wave inversion, ST-Depression, QT segment duration, delta wave character, anterior S-wave character and ectopic or pre-mature beats. The method continues by selecting the ECG for manual review if the plurality of selected characteristics exceed the predetermined subthreshold levels yet are below the corresponding clinically significant threshold levels of abnormality of the characteristics.

A system automatically detects and measures ST deviation of a heart wave ECG signal in the presence of noise and accommodates baseline variation of the signal and other artifacts. A system identifies a particular point in an electrophysiological signal representing heart electrical activity using an interface for receiving an electrical signal waveform comprising an R-wave and including an ST segment portion associated with heart electrical activity of a patient over a heart beat cycle. A signal processor processes data representing the electrical signal waveform by identifying an S point and T point in the electrical signal waveform and determining a first candidate J point in the electrical signal waveform having substantially a maximum distance from a line between the identified S and T points, the distance being measured perpendicularly to the line.

According to an embodiment of the present disclosure, there is provided a method of diagnosing left ventricular systolic dysfunction based on an electrocardiogram, the method being performed by a computing device including at least one processor, the method including: acquiring electrocardiogram data; and estimating the probability of occurrence of left ventricular systolic dysfunction for the subject of measurement of the electrocardiogram data based on the electrocardiogram data by using a pre-trained neural network model; wherein the neural network model has been trained based on the correlations between left ventricular systolic dysfunction and changes in electrocardiogram characteristics.

According to an embodiment of the present disclosure, there is provided a method of diagnosing left ventricular systolic dysfunction based on an electrocardiogram, the method being performed by a computing device including at least one processor, the method including: acquiring electrocardiogram data; and estimating the probability of occurrence of left ventricular systolic dysfunction for the subject of measurement of the electrocardiogram data based on the electrocardiogram data by using a pre-trained neural network model; wherein the neural network model has been trained based on the correlations between left ventricular systolic dysfunction and changes in electrocardiogram characteristics.

A method of detection of a recurrent feature of interest within a signal including: obtaining evidence, based on a signal, the evidence including a probability density function for each of a plurality of parameters for parameterizing the signal, including at least one probability density function for a parameter, of the plurality of parameters, that positions a feature of interest within signal data of the signal; parameterizing a portion of the signal data from the signal based upon a hypothesis that a point of interest in the signal data is a position of the feature of interest; determining a posterior probability of the hypothesis being true given the portion of the signal data by combining a prior probability of the hypothesis and a conditional probability of observing the portion of the signal data given the hypothesis.

A method of detection of a recurrent feature of interest within a signal including: obtaining evidence, based on a signal, the evidence including a probability density function for each of a plurality of parameters for parameterizing the signal, including at least one probability density function for a parameter, of the plurality of parameters, that positions a feature of interest within signal data of the signal; parameterizing a portion of the signal data from the signal based upon a hypothesis that a point of interest in the signal data is a position of the feature of interest; determining a posterior probability of the hypothesis being true given the portion of the signal data by combining a prior probability of the hypothesis and a conditional probability of observing the portion of the signal data given the hypothesis.

A method for early detection of a heart attack in a subject. The method includes acquiring a plurality of clinical symptoms from the subject, acquiring a gender of the subject, acquiring an age of the subject, acquiring a raw ECG signal from the subject, generating an averaged ECG signal from the raw ECG signal, acquiring a plurality of ECG features from the averaged ECG signal, designing a fuzzy inference system based on a set of rules associated with the plurality of clinical symptoms, the gender, the age, and the plurality of ECG features, and determining an occurrence of the heart attack utilizing the fuzzy inference system.