Computational cardiac depolarization and repolarization simulation library mapping for non-invasive arrhythmia risk stratification
A non-invasive method for cardiac arrhythmia risk stratification may include identifying, based at least on an electrical recording of a patient, a cardiac depolarization simulation and a cardiac repolarization simulation corresponding to an electrical recording of a patient. One or more regions of increased spatial repolarization gradient in which a first area of a myocardium of the patient exhibits a first repolarization rate that differs from a second repolarization rate of a second area of the myocardium by an amount then divided by the spatial distance between the two regions, by a threshold value may be determined based on the cardiac depolarization simulation and the cardiac repolarization simulation. A risk of cardiac arrhythmia for the patient may be determined based a magnitude of the increased spatial repolarization gradient. Moreover, a treatment plan for the patient may be determined based on the magnitude and/or location of the increased spatial repolarization gradient.
1. A system, comprising:
at least one processor; and
at least one memory including program code which when executed by the at least one processor provides operations comprising:
generating a computational library that includes, for each of a plurality of cardiac geometries, a cardiac repolarization simulation;
accessing an electrical recording of a patient;
identifying, within the computational library, a cardiac repolarization simulation corresponding to the electrical recording of the patient;
determining, based at least on the cardiac repolarization simulation, one or more regions exhibiting an increased spatial repolarization gradient in which a ratio of a difference between a first repolarization rate of a first area of a myocardium of the patient a second repolarization rate of a second region of the myocardium, and a spatial distance between the first region and the second region exceeds a threshold value;
determining, based at least on a magnitude of the increased spatial repolarization gradient, a risk of cardiac arrhythmia for the patient; and
determining, based at least on the magnitude of the increased spatial repolarization gradient, a treatment plan for the patient.
2. The system of claim 1 , wherein the treatment plan is determined to include, based at least the magnitude of the increased spatial repolarization gradient, a cardioverter-defibrillator implantation or an invasive electrophysiology study and ablation.
3. The system of claim 1 , wherein the treatment plan includes determining, based at least on a location of the one or more regions of increased spatial repolarization gradient, a location for a targeted therapy.
4. The system of claim 3 , wherein the targeted therapy includes catheter ablation and/or stereotactic ablative radiotherapy (SAbR).
5. The system of claim 1 , wherein the operations further comprise:
identifying, based at least on clinical data associated with the patient, a subset of simulations from the computational library that correspond to an anatomy of the patient wherein the identifying of the cardiac repolarization simulation is based on the subset of simulations.
6. The system of claim 5 , wherein the clinical data includes cardiac imaging data indicating one or more locations of scar tissue, borderzone tissue, and normal tissue, cardiac chamber size, the presence of hypertrophy or dilation, locations of fibrosis, regions of normal and abnormal contractility, or regions of wall thinning.
7. The system of claim 5 , wherein the operations further comprise: in response to failing to identify the subset of simulations corresponding to the anatomy of the patient, generating, based at least on the clinical data of the patient, a custom computational library that includes one or more cardiac repolarization simulations specific to the anatomy of the patient.
8. The system of claim 1 , wherein the operations further comprise applying a machine learning model trained to determine that the cardiac repolarization simulation matches the electrical recording of the patient.
9. The system of claim 8 , wherein the machine learning model comprises a neural network, a regression model, an instance-based model, a regularization model, a decision tree, a random forest, a Bayesian model, a clustering model, an associative model, a dimensionality reduction model, and/or an ensemble model.
10. The system of claim 1 , wherein the electrical recording comprises one or more of an electrogram, a vectorcardiogram, an electrocardiogram, an electroencephalogram, or a vectorcardiogram.
11. The system of claim 10 , wherein the electrical recording further includes one or more body surface potential recordings.
12. The system of claim 1 , wherein the electrical recording comprises an electrocardiographic imaging (ECGi) recording system including one or more body surface potential recordings.
13. The system of claim 1 , wherein the operations further comprise:
determining, based at least on the cardiac repolarization simulation, one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block; and
determining, based at least on a presence and/or an absence of the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block, the risk of cardiac arrhythmia for the patient.
14. The system of claim 13 , wherein the operations further comprise:
determining, based at least on the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block, the treatment plan for the patient.
15. The system of claim 14 , wherein the treatment plan targets, individually or in groups, the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block.
16. The system of claim 14 , wherein the treatment plan is determined to include one or more drug therapies based at least on the presence and/or the absence of the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block.
17. A computer-implemented method, comprising:
generating a computational library that includes, for each of a plurality of cardiac geometries, a cardiac depolarization simulation and repolarization simulation;
accessing an electrical recording of a patient;
identifying, within a computational library, a cardiac depolarization simulation and a cardiac repolarization simulation corresponding to the electrical recording of the patient;
determining, based at least on the cardiac depolarization simulation and the cardiac repolarization simulation, one or more regions exhibiting an increased spatial repolarization gradient in which a ratio of a difference between a first repolarization rate of a first area of a myocardium of the patient a second repolarization rate of a second area of the myocardium, and a spatial distance between the first region and the second region exceeds a threshold value; and
determining, based at least on a magnitude of the increased spatial repolarization gradient, a risk of cardiac arrhythmia for the patient.
18. The method of claim 17 , further comprising determining, based at least on the magnitude of the increased spatial repolarization gradient, a treatment plan for the patient.
19. The method of claim 18 , wherein the treatment plan is determined to include, based at least the magnitude of the increased spatial repolarization gradient, a cardioverter-defibrillator implantation or an invasive electrophysiology study and ablation.
20. The method of claim 18 , wherein the treatment plan includes determining, based at least on a location of the one or more regions of increased spatial repolarization gradient, a location for a targeted therapy.
21. The method of claim 20 , wherein the targeted therapy includes catheter ablation and/or stereotactic ablative radiotherapy (SAbR).
22. The method of claim 17 , wherein the cardiac depolarization simulation comprises a ventricular activation simulation, and wherein the cardiac repolarization simulation comprises a ventricular recovery simulation.
23. The method of claim 17 , further comprising:
identifying, based at least on clinical data associated with the patient, a subset of simulations from the computational library that correspond to an anatomy of the patient; and
identifying, within the subset of simulations corresponding to the anatomy of the patient, the cardiac depolarization simulation and the cardiac repolarization simulation corresponding to the electrical recording of the patient.
24. The method of claim 23 , wherein the clinical data includes patient demographics.
25. The method of claim 23 , wherein the clinical data includes cardiac imaging data indicating one or more locations of scar tissue, borderzone tissue, and normal tissue, cardiac chamber size, the presence of hypertrophy or dilation, locations of fibrosis, regions of normal and abnormal contractility, and/or regions of wall thinning.
26. The method of claim 23 , further comprising:
in response to failing to identify the subset of simulations corresponding to the anatomy of the patient, generating, based at least on the clinical data of the patient, a custom computational library that includes one or more cardiac depolarization simulations and/or cardiac repolarization simulations specific to the anatomy of the patient.
27. The method of claim 17 , further comprising applying a machine learning model trained to determine that the cardiac repolarization simulation and the cardiac depolarization simulation match the electrical recording of the patient.
28. The method of claim 27 , wherein the machine learning model comprises a neural network, a regression model, an instance-based model, a regularization model, a decision tree, a random forest, a Bayesian model, a clustering model, an associative model, a dimensionality reduction model, and/or an ensemble model.
29. The method of claim 17 , further comprising:
determining, based at least on the cardiac depolarization simulation and the cardiac repolarization simulation, one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block; and
determining, based at least on a presence and/or an absence of the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block, the risk of cardiac arrhythmia for the patient.
30. The method of claim 29 , further comprising:
determining, based at least on the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block, a treatment plan for the patient.
31. The method of claim 30 , wherein the treatment plan targets, individually or in groups, the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block.
32. The method of claim 30 , wherein the treatment plan is determined to include one or more drug therapies based at least on the presence and/or the absence of the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block.
33. An apparatus, comprising:
means for generating a computational library that includes, for each of a plurality of cardiac geometries, a cardiac depolarization simulation and repolarization simulation;
means for accessing an electrical recording of a patient;
means for identifying, within a computational library, a cardiac depolarization simulation and a cardiac repolarization simulation corresponding to an electrical recording of a patient;
means for determining, based at least on the cardiac depolarization simulation and the cardiac repolarization simulation, one or more regions of increased spatial repolarization gradient in which a first area of a myocardium of the patient exhibits a first repolarization rate that differs from a second repolarization rate of a second area of the myocardium by an amount then divided by the spatial distance between the two regions, by a threshold value; and
means for determining, based at least on a magnitude of the increased spatial repolarization gradient, a risk of cardiac arrhythmia for the patient.
34. A method, comprising:
performing by a system that includes at least one processor and a memory including program code which when executed by the at least one processor provides operations comprising:
identifying, within a computational library, a cardiac repolarization simulation corresponding to an electrical recording of a patient;
determining, based at least on the cardiac repolarization simulation, one or more regions exhibiting an increased spatial repolarization gradient in which a ratio of a difference between a first repolarization rate of a first region of a myocardium of the patient a second repolarization rate of a second region of the myocardium, and a spatial distance between the first region and the second region exceeds a threshold value;
determining, based at least one a magnitude of the increased spatial repolarization gradient, a risk of cardiac arrhythmia for the patient; and
determining, based at least on the magnitude of the increased spatial repolarization gradient, a treatment plan for the patient that includes performing an ablation to treat a source of a cardiac arrhythmia; and
performing the ablation on the patient in accordance with the treatment plan.
35. The method of claim 34 wherein the identifying includes applying a neural network that is trained to identify the cardiac repolarization simulation that match electrical recording of the patient.
36. The method of claim 35 wherein the electrical recording is an electrocardiogram that includes a voltage recorded at every millisecond.
37. The method of claim 35 wherein the electrical recording is an electrocardiogram that includes 500 voltages per second.
38. The system of claim 1 wherein the system further includes an ablation device and the operations comprise identifying a source of a cardiac arrhythmia and controlling the performing of an ablation targeting the source of the cardiac arrhythmia.
39. The system of claim 38 wherein the ablation is performed using stereotactic ablative radiotherapy.
40. The system of claim 38 wherein the ablation is performed using an ablation catheter.
41. The method of claim 34 wherein the ablation is a pulsed field ablation.
42. The method of claim 34 wherein the ablation is performed using stereotactic ablative radiotherapy.
43. The method of claim 34 wherein the ablation is performed using a catheter.
44. The method of claim 34 wherein the program code when executed by the at least one processor further provides operations comprising:
determining, based at least on the cardiac repolarization simulation, one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block and
determining, based at least on a presence and/or an absence of the one or more regions of early activation, slow conduction, independent activation pathways, late activation, protected conduction isthmuses, and/or conduction block, the risk of cardiac arrhythmia for the patient.
45. The method of claim 34 wherein the program code when executed by the at least one processor provides operations further comprising generating a computational library that includes, for each of a plurality of cardiac geometries, a cardiac depolarization simulation.
46. A method, comprising:
performing by a system that includes at least one processor and a memory including program code which when executed by the at least one processor provides operations comprising:
identifying, within a computational library, a cardiac repolarization simulation corresponding to an electrical recording of a patient;
determining, based at least one the cardiac repolarization simulation, one or more regions exhibiting an increased spatial repolarization gradient in which a ratio of a difference between a first repolarization rate of a first region of a myocardium of the patient a second repolarization rate of a second region of the myocardium, and a spatial distance between the first region and the second region exceeds a threshold value;
determining, based at least on a magnitude of the increased spatial repolarization gradient, a risk of cardiac arrhythmia for the patient; and
determining, based at least on the magnitude of the increased spatial repolarization gradient, a treatment plan for the patient that includes a cardioverter-defibrillator implantation to treat a cardiac arrhythmia; and
implanting a cardioverter defibrillator in the patient in accordance with the treatment plan.
47. The method of claim 46 wherein the program code when executed by the at least one processor provides operations further comprising generating a computational library that includes, for each of a plurality of cardiac geometries, a cardiac depolarization simulation and repolarization simulation.
48. A method, comprising:
performing by a system that includes at least one processor and a memory including program code which when executed by the at least one processor provides operations comprising:
identifying, within a computational library, a cardiac repolarization simulation corresponding to an electrical recording of a patient;
determining, based at least one the cardiac repolarization simulation, one or more regions exhibiting an increased spatial repolarization gradient in which a ratio of a difference between a first repolarization rate of a first region of a myocardium of the patient a second repolarization rate of a second region of the myocardium, and a spatial distance between the first region and the second region exceeds a threshold value;
determining, based at least on a magnitude of the increased spatial repolarization gradient, a risk of cardiac arrhythmia for the patient; and
determining, based at least on the magnitude of the increased spatial repolarization gradient, a treatment plan for the patient that includes one or more of a cardiac ablation, a cardioverter-defibrillator implantation, a drug therapy, or an invasive electrophysiology study to treat a cardiac arrhythmia; and
treating the patient in accordance with the treatment plan, the treating including one or more of performing a cardiac ablation, implanting a cardioverter defibrillator, administering the drug therapy, and performing the invasive electrophysiology study.
49. The method of claim 48 wherein the program code when executed by the at least one processor provides operations further comprising generating a computational library that includes, for each of a plurality of cardiac geometries, a repolarization simulation.