Method and system to assess disease using phase space tomography and machine learning

A system for non-invasively assessing presence or non-presence of significant coronary artery disease, the system comprising:

• one or more processors;
• and
• a non-transitory computer-readable medium storing computer-executable instructions that when executed by the one or more processors cause the system to:
• obtain acquired data from a measurement of one or more biophysical signals of a subject, wherein the acquired data are derived from measurements acquired via noninvasive equipment configured to measure properties of a heart;
• generate a plurality of low-energy subspace parameters from the acquired data;
• generate a three-dimensional model defining a volume and a surface based on a residual analysis of the low-energy subspace parameters generated from the acquired data;
• generate a set of two-dimensional images derived from the three-dimensional model, including a first and a second two-dimensional image, wherein each two-dimensional image of the set of two-dimensional images is a different view of the three-dimensional model, wherein each two-dimensional image of the set of two-dimensional images synthesizes and displays the electrical and functional characteristics of the heart;
• and
• determine an output indicating the presence or non-presence of significant coronary artery disease, using an output of a trained neural network, wherein the trained neural network comprises a neural network trained using two-dimensional images of the set of two-dimensional images that are paired with coronary angiography results assessed for the presence or non-presence of significant coronary artery disease,
• wherein the output of the trained neural network is subsequently used for an assessment of presence and/or non-presence of significant coronary artery disease.

A non-transitory computer-readable medium storing computer-executable instructions that when executed by one or more processors cause a system to:

• obtain acquired data from a measurement of one or more biophysical signals of a subject, wherein the acquired data are derived from measurements acquired via noninvasive equipment configured to measure properties of a heart;
• generate a plurality of low-energy subspace parameters from the acquired data;
• generate a three-dimensional model defining a volume and a surface based on a residual analysis of the low-energy subspace parameters generated from the acquired data;
• generate a set of two-dimensional images derived from the three-dimensional model, including a first and a second two-dimensional image, wherein each two-dimensional image of the set of two-dimensional images is a different view of the three-dimensional model, wherein each two-dimensional image of the set of two-dimensional images synthesizes and displays the electrical and functional characteristics of the heart;
• and
• determine an output indicating the presence or non-presence of significant coronary artery disease, using an output of a trained neural network, wherein the trained neural network comprises a neural network trained using two-dimensional images of the set of two-dimensional images that are paired with coronary angiography results assessed for the presence or non-presence of significant coronary artery disease,
• wherein the output of the trained neural network is subsequently used for an assessment of presence and/or non-presence of significant coronary artery disease.