Abstract: Machine-learned computational models can be trained to estimate echocardiogram parameters (as conventionally measured by echocardiography) from electrocardiograms and/or electrocardiogram-derived time-domain and/or time-frequency features. In some embodiments, a multi-level model architecture includes a level to derive the echocardiogram parameter estimate(s), with input features to that level being computed in a preceding level, and/or with one or more echocardiogram parameter estimate(s) flowing into a subsequent layer to compute downstream qualitative or quantitative indicators of heart function.

Abstract: Diastolic function may be assessed by operating one or more machine-learned computational models on electrocardiograms or electrocardiogram-derived features to compute quantitative diastolic indicators, including estimates of echocardiography parameters conventionally measured by echocardiography. In various embodiments, parameters derived from time-frequency transforms of the electrocardiograms are used as input to the model(s) and/or computed within the model(s).

Abstract: Heart condition and function can be quantified using repolarization measures and/or repolarization indices derived from a time-frequency transform of an electrocardiogram, e.g., based on points in time associated with the T wave. The electrocardiograms, time-frequency maps derived therefrom, and/or indices obtained by analysis of the time-frequency maps and electrocardiograms may be assembled into a user interface. Further embodiments are described.

Abstract: Diastolic function may be assessed by operating one or more machine-learned computational models on electrocardiograms or electrocardiogram-derived features to compute quantitative diastolic indicators, including estimates of echocardiography parameters conventionally measured by echocardiography. In various embodiments, parameters derived from time-frequency transforms of the electrocardiograms are used as input to the model(s) and/or computed within the model(s).

Abstract: Electrocardiograms can be analyzed in the time-frequency domain, following conversion into time-frequency maps, to determine characteristics or features of various waveforms, such as waveform morphology and/or the amplitude(s) and location(s) (in time and/or frequency) of one or more extrema of the waveform. Based on comparison of the extrema against thresholds and/or against each other, disease conditions may be determined.

Abstract: Heart condition and function can be quantified using repolarization measures and/or repolarization indices derived from a time-frequency transform of an electrocardiogram, e.g., based on points in time associated with the T wave. The electrocardiograms, time-frequency maps derived therefrom, and/or indices obtained by analysis of the time-frequency maps and electrocardiograms may be assembled into a user interface. Further embodiments are described.

Abstract: Heart condition and function can be quantified using repolarization measures and/or repolarization indices derived from a time-frequency transform of an electrocardiogram, e.g., based on points in time associated with the T wave. The electrocardiograms, time-frequency maps derived therefrom, and/or indices obtained by analysis of the time-frequency maps and electrocardiograms may be assembled into a user interface. Further embodiments are described.

Abstract: Electrocardiograms can be analyzed in the time-frequency domain, following conversion into time-frequency maps, to determine characteristics or features of various waveforms, such as waveform morphology and/or the amplitude(s) and location(s) (in time and/or frequency) of one or more extrema of the waveform. Based on comparison of the extrema against thresholds and/or against each other, disease conditions may be determined.

Abstract: Heart condition and function can be quantified using repolarization measures and/or repolarization indices derived from a time-frequency transform of an electrocardiogram, e.g., based on points in time associated with the T wave. The electrocardiograms, time-frequency maps derived therefrom, and/or indices obtained by analysis of the time-frequency maps and electrocardiograms may be assembled into a user interface. Further embodiments are described.

Abstract: Described are systems, devices, and methods for deriving quantitative metrics of heart condition and function from one or more electrocardiograms or time-frequency maps derived therefrom. In various embodiments, repolarization indices for the left and right ventricles are determined from the T wave in respective electrocardiograms. An overall heart-health index may be determined based on a comparison between the left and right ventricular repolarization indices.

Abstract: Heart condition and function can be quantified using repolarization measures and/or repolarization indices derived from a time-frequency transform of an electrocardiogram, e.g., based on points in time associated with the T wave. The electrocardiograms, time-frequency maps derived therefrom, and/or indices obtained by analysis of the time-frequency maps and electrocardiograms may be assembled into a user interface. Further embodiments are described.

Abstract: Heart condition and function can be quantified using repolarization measures and/or repolarization indices derived from a time-frequency transform of an electrocardiogram, e.g., based on points in time associated with the T wave. The electrocardiograms, time-frequency maps derived therefrom, and/or indices obtained by analysis of the time-frequency maps and electrocardiograms may be assembled into a user interface. Further embodiments are described.