Machine learning for identifying characteristics of a reentrant circuit

One or more computing systems for identifying an entrance site, a common pathway, and an exit site of a reentrant circuit of a heart, the one or more computing systems comprising:

• one or more computer-readable storage mediums that store computer-executable instructions for controlling the one or more computing systems to:
• access subject tissue characteristics of a subject reentrant circuit of a subject, the subject tissue characteristics includes a specification of scar tissue and border zone tissue;
• access a reentry machine learning (RML) model for identifying an entrance site, a common pathway, and an exit site of the reentrant circuit, the RML model being trained using training data that includes, for each of a plurality of simulated reentrant circuits, information relating to simulated scar tissue and simulated border zone tissue of that simulated reentrant circuit that is labeled with information relating to a simulated entrance site, a simulated common pathway, and a simulated exit site of that simulated reentrant circuit;
• apply the RML model to the subject tissue characteristics to identify subject information relating to an entrance site, a common pathway, and an exit site for the subject reentrant circuit;
• and
• output an indication of the identified subject information;
• and
• one or more processors for controlling the one or more computing systems to execute the computer-executable instructions.

A method performed by one or more computing systems for simulating electrical activity of a reentrant circuit of a heart, the method comprising:

• generating a plurality of sets of simulation parameters that each specify areas of normal tissue, scar tissue, and border zone tissue;
• and
• for each set of simulation parameters,
• simulating electrical activity of a heart having areas of scar tissue and border zone tissue as specified by the set of simulation parameters;
• and
• when a simulated arrhythmia has stabilized,
• generating a simulated cardiogram based on the simulated electrical activity during a simulated cardiac cycle;
• analyzing the simulated electrical activity to identify a loop near scar tissue based on flow of simulated action potential that loops back to itself during the simulated cardiac cycle;
• identifying an entrance site of the loop based on simulated conduction velocity;
• identifying an exit site of the loop based on the simulated cardiogram;
• and
• storing a mapping of one or more of the simulation parameters to one or more of the identified entrance site, the identified loop, and the identified exit site.

A method performed by one or more computing systems for identifying a reentrant circuit characteristic of a reentrant circuit of a heart, the method comprising:

• accessing a subject image of a subject reentrant circuit of a subject;
• accessing a reentry machine learning (RML) model for identifying a reentrant circuit characteristic based on tissue characteristics relating to scar tissue and border zone tissue identified from the subject image, the RML model being trained using training data that includes, for each of a plurality of simulated reentrant circuits, simulated tissue characteristics relating to simulated scar tissue and simulated border zone tissue of that simulated reentrant circuit that is labeled with a simulated reentrant circuit characteristic of that simulated reentrant circuit;
• applying the RML model to subject tissue characteristics of the subject to identify a subject reentrant circuit characteristic for the subject reentrant circuit;
• and
• outputting an indication of the identified subject reentrant circuit characteristic.