| CPC G16H 50/20 (2018.01) [A61B 5/349 (2021.01); G16H 50/30 (2018.01)] | 19 Claims |

|
1. A method for non-invasively assessing a cardiac disease state or abnormal condition of a subject, the method comprising:
obtaining, by one or more processors, a biophysical signal data set of the subject comprising a plurality of cardiac signals;
generating, by the one or more processors, a high-energy subspace model of the plurality of cardiac signals, wherein the high-energy subspace model is generated from a signal-modeling algorithm that generates an energy subspace that includes only a top percentile of energy of each signal through a selection of one or more candidate signals;
determining, by the one or more processors, a residue model from the high-energy subspace model;
determining, by the one or more processors and based, at least in part, on the residue model, values of one or more conduction deviation properties associated with ventricular depolarization within the plurality of cardiac signals; and
determining, by the one or more processors, an estimated value for a presence of a metric associated with the cardiac disease state or abnormal condition based, in part, on an application of the determined values of the one or more conduction deviation properties to an estimation model for the metric,
wherein the estimated value for of the presence of the metric is used in the estimation model to non-invasively estimate the presence or non-presence of the cardiac disease state or condition for use in a diagnosis of the cardiac disease state or condition or to direct treatment of the cardiac disease state or condition.
|