Determining repolarization waves using a simulated heart model

Abstract

An example method can use simulation data of a virtual heart model to measure characteristics including cell potential and determine repolarization timing while collecting accurate simulated intracardiac signals. The determined characteristics (e.g., repolarization timing) can be annotated for reference. The collected signals in combination with the annotated timing can be used to train an AI model. The AI model can be configured to determine characteristics such as repolarization timing based on input of one or more intracardiac signals. The AI model can be tested by inputting a dataset including intracardiac signals from other heart models and receiving a predicted ARP from the AI model. The predicted ARP can be compared to a known ARP to determine the accuracy of the AI model. The other heart models can be associated with heart conditions and / or complications such as tachycardia.

Description

[0001] Cross-references to related applications This application is a non-provisional application and claims the benefit of Provisional Application No. 63 / 782,332, filed on 2 April 2025, which is incorporated herein by reference in its entirety for any and all purposes. Background Technology

[0002] Detecting atrial repolarization waves can aid in the diagnosis of atrial tachycardia and / or atrial fibrillation. However, detecting repolarization waves within intracardiac signals is a complex task. Repolarization waves may often be subtle or masked by low signal-to-noise ratios (SNR) (such as respiration) and / or by other far-field signals.

[0003] Therefore, other methods for identifying repolarization waves are needed. Furthermore, perhaps even more interesting questions relate to the repolarization state of cells, and the recorded electrode potentials are merely substitutes for this situation, rather than precise measurements. Summary of the Invention

[0004] It should be understood that the following general description and detailed description are exemplary and illustrative only, and do not constitute a limitation. Methods and systems for detecting repolarization waves using a simulated cardiac model are described.

[0005] A system having one or more computers may be configured to perform specific operations or actions by installing software, firmware, hardware, or combinations thereof on the system, which, in operation, causes the system to perform these actions. One or more computer programs may be configured to perform specific operations or actions by including instructions that, when executed by a data processing device, cause the device to perform these actions.

[0006] In one general aspect, the method may include determining first data indicating one or more of a unipolar intracardiac signal, a bipolar intracardiac signal, or a multipolar intracardiac signal of the heart. The method may also include determining second data indicating one or more action potential signals of the heart having an action recovery period (ARP). The method may further include training an artificial intelligence (AI) model based on the first and second data, wherein the AI ​​model is configured to determine a predicted ARP based on one or more of the unipolar intracardiac signal, a bipolar intracardiac signal, or a multipolar intracardiac signal of the heart. The method may additionally include receiving third data indicating one or more of the unipolar intracardiac signal, a bipolar intracardiac signal, or a multipolar intracardiac signal of the heart. Furthermore, the method may include determining the predicted ARP from the third data. Other embodiments of this aspect include corresponding computer systems, devices, and computer programs recorded on one or more computer storage devices, each computer program configured to perform actions of these methods.

[0007] These and other features and advantages will be described in more detail below. Attached Figure Description

[0008] Some features are shown in the accompanying drawings by way of example rather than limitation. In the drawings, the same reference numerals refer to similar elements.

[0009] Figure 1 An example image of the example model described in this article is shown.

[0010] Figure 2 An example model described in this article is shown.

[0011] Figure 3 An example diagram described in this article is shown.

[0012] Figure 4 An example method for training the example model disclosed in this paper is shown.

[0013] Figure 5 An example method for testing the example model disclosed in this paper is shown.

[0014] Figure 6 A flowchart illustrating an example method according to this disclosure is provided.

[0015] Figure 7 A flowchart illustrating an example method according to this disclosure is provided.

[0016] Figure 8 A flowchart illustrating an example method according to this disclosure is provided.

[0017] The accompanying drawings illustrate examples of this disclosure. It should be understood that the examples shown in the drawings and / or discussed herein are non-exclusive, and there are other examples of how this disclosure can be practiced. Detailed Implementation

[0018] This disclosure relates to detecting one or more repolarization waves from a simulated cardiac model that includes cell potentials and simulated additional cell potentials.

[0019] This disclosure relates to systems and / or methods for modeling repolarization in cardiac cells. Example methods may use virtual heart models comprising multiple cells (e.g., 10 million), cell interactions, conduction systems, myocardial layers, and cardiac anatomy and pathology to simulate cardiac activity. The models can be configured to exhibit a variety of simulated cardiac activities under various conditions. By utilizing such heart models, one can generate any number of simulated scenarios and collect output data associated with the modeled scenarios. For example, the methods of this disclosure can combine electrophysiology and artificial intelligence (AI) to accurately study and track cellular repolarization and its effects on measured intracardiac signals.

[0020] In a healthy heart, cardiomyocytes are electrically stimulated to contract in a sequential, synchronous manner. The propagation begins in the sinoatrial node in the right atrium and spreads throughout the heart as each cell stimulates its neighboring cells. After activation of each cardiomyocyte comes a period in which the cell cannot be stimulated again. This period is called the refractory period, and its function is to ensure smooth muscle contraction and efficient blood flow through the chambers of the heart. In patients with arrhythmias, the propagation of electrical stimulation of the muscle does not proceed as it should. The heart rate may be too fast or too slow, or the electrical stimulation of the heart may occur through abnormal pathways, initiating elsewhere or becoming self-sustaining (as in macroreentry or atrial fibrillation). Abnormal pathways can be fixed, or they can be functional, i.e., without a fixed circuit or focus. They can occur in the atria or ventricles, or both; they can originate from the epicardium or endocardium, or both, and can include structures other than the four main chambers.

[0021] To identify electrical activation sequences in the heart, local electrical activity is acquired at locations within the heart chambers using a manipulable catheter, the location of which is assessed through radiographic images of the heart chambers that are not visible within them. Local electrical activation time (measured as the time elapsed from a common reference event in the cardiac cycle to a baseline during electrical systole) represents the local activation time (LAT) required to construct activation mapping data points at a single location.

[0022] Typically, to generate a complete activation map of the heart, several data points can be sampled. The catheter can be moved to different locations within the heart chambers and electrical activation can be acquired again. The mapping electrode positions are used to establish and correlate LATs within the anatomical structures. The resulting activation map can be used to identify electrical pathways that may be the cause of a patient's arrhythmias.

[0023] As an example, the method according to this disclosure can generate simulated data from a virtual heart model. Such data can include characteristics such as the electrical potential of cells in the modeled heart, and determine the timing of cell depolarization and repolarization (e.g., recovery timing—the time it takes for a cell to be ready to reactivate), while collecting accurate simulated signals. The signals and corresponding recovery timings can be used to train an AI model to learn how recovery timings relate to a large set of recorded signals. As an example, a model (e.g., an AI model) can be trained using one or more of unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals, along with action potentials or groups of action potentials. The model can be trained on one or more datasets simulated using the heart model. Action potential outputs (e.g., cellular action potentials as a function of time) can indicate the action recovery period (ARP) of cellular activity from the heart model. Therefore, patterns in one or more of the unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals can be correlated with action potentials, and particularly with timing characteristics of action potentials, such as ARP or repolarization timing. Multiple timing parameters or characteristics of the waveform can be trained for detection, such as the maximum action potential (AP), a function or derivative of the AP waveform (e.g., dv / dt, or the percentage change from the maximum AP value). By developing an AI model in this way, the model can then receive one or more of unipolar, bipolar, or multipolar intracardiac signals without benefiting from the action potential and can still predict reliable ARP.

[0024] AI models can be trained and / or tested on different cardiac models and datasets exhibiting the same or different design characteristics, such as modeling age, size, biological condition, or other cardiac properties. AI models can be trained and / or tested on different cardiac models and datasets involving cardiac conditions with different rhythms, pacing, and tachycardias. The predicted recovery timing determined by the AI ​​model can be compared with known recovery timings to examine the accuracy of the AI ​​model. Example methods can use cardiac models, physiological modeling, anatomical modeling, and / or physical modeling, and / or AI models to accurately detect one or more repolarization waves within intracardiac signals.

[0025] The example method uses simulated data from a virtual heart model to measure cell potential and determine repolarization timing, while simultaneously collecting accurate simulated intracardiac signals. The determined repolarization timing can be annotated for reference. The collected signals, combined with the annotated timing, can be used to train an AI model. The AI ​​model can be configured to determine repolarization timing based on inputs from one or more intracardiac signals. The AI ​​model can be trained on a large set of intracardiac signals.

[0026] The AI ​​model can be trained on unipolar intracardiac signals and known ARPs. Known ARPs can be determined by cellular activity associated with the cardiac model. The data used to train the AI ​​model can be augmented to simulate real cardiac conditions or activity. Augmentation of the data can include adding noise, respiratory modulation, mechanical heartbeat position changes, and / or adding far-field signals, such as ventricular far-field signals. Once the AI ​​model is trained, it can be tested by inputting a dataset including intracardiac signals from other cardiac models and receiving predicted ARPs from the AI ​​model. The predicted ARPs can be compared to known ARPs to determine the accuracy of the AI ​​model. Other cardiac models can be associated with cardiac conditions and / or complications, such as various tachycardias, such as microreentry, macroreentry, AFib, NSR, or pacing.

[0027] Figure 1 Example image 100 of the example model described herein is shown. The example model can simulate the motion of a heart including similar structures. The example model can include multiple simulated cells, such as ten million or more simulated cells. The example model can simulate various waveform propagations. The state of the action potential in the cells can be measured using a modeled heart or by actual measurement using simulated electrodes. Other simulations can be used as described herein.

[0028] Figure 2 An example model 200 described herein is shown. As illustrated, the example model may include one or more electrodes (202a-202d), and may also simulate non-conductive elements of a duct element. The electrodes may be used to generate signals for creating the model or supplementing modeling data. The signals and / or the data represented by such signals may include various properties, including tissue properties, parameters of cells or cell populations, properties of regions of interest in the tissue, and / or other parameters that can be measured or modeled.

[0029] Figure 3Example Figure 300 described herein is shown. Example Figure 300 can illustrate the relationship between detected / measured or modeled signals. As shown, Figure 300 represents a comparison of a unipolar signal 302, an action potential signal 304, and a bipolar signal 306. As an example, a model (e.g., an AI model) can be trained using one or more of the unipolar intracardiac signal 302, the bipolar intracardiac signal 306, or the multipolar intracardiac signal, along with the action potential signal 304. Example action potential signal 304 illustrates a spike in the potential followed by a decay of the potential. The repolarization time and / or ARP can be determined from the action potential signal 304. The repolarization time and / or ARP can be compared with one or more of the unipolar intracardiac signal 302, the bipolar intracardiac signal 306, or the multipolar intracardiac signal within the same time frame to determine the correlation between the signals. Therefore, the patterns in one or more of the unipolar intracardiac signal 302, bipolar intracardiac signal 306, or multipolar intracardiac signal can be correlated with the action potential signal 302, and in particular with the timing characteristics of the action potential, such as ARP or repolarization timing. A dataset including data indicating Figure 300 can be used to train / test models such as AI models. By developing an AI model in this way, the model can then receive one or more of the unipolar intracardiac signal, bipolar intracardiac signal, or multipolar intracardiac signal without benefiting from the action potential, and can still reliably predict ARP or other characteristics, such as the features or morphology of the AP waveform.

[0030] Figure 4 An example method 400 for training the example artificial intelligence (AI) model disclosed herein is illustrated. Example method 400 may include training the AI ​​model on unipolar and / or bipolar intracardiac signals and a known ARP. The known ARP can be determined by cellular activity associated with the cardiac model and / or may include action potential data (e.g., simulated or measured). As an illustrative example, cells within a defined proximity of the electrode (e.g., a radius of 3 mm from the center of the electrode) can be studied and measured or simulated. The data used to train the AI ​​model may be augmented to simulate real-world conditions. Augmenting the data used to train the AI ​​model may include adding real noise to the data and / or adding far-field ventricular signals to the data. The AI ​​model may be configured to determine repolarization timing (ARP) based on inputs of one or more unipolar and / or bipolar intracardiac signals.

[0031] Figure 5 Example method 500 is shown for testing the example artificial intelligence (AI) model disclosed herein. Example method 500 can test models created by… Figure 4Example method 400 described herein trains an AI model. Example method 500 may include inputting a dataset of unipolar and / or bipolar intracardiac signals into the AI ​​model and may receive predicted ARPs as output from the AI ​​model. Example method 500 may include comparing the predicted ARPs with the actual ARPs to determine a performance evaluation associated with the AI ​​model. Other outputs may be provided from the trained AI model. For example, the morphology of the AP waveform may be trained for other parameters (such as unipolar signals, bipolar signals, multipolar signals) so that predictive characteristics of the AP morphology can be output from the trained AI model.

[0032] Figure 6 A flowchart illustrating a method 600 for using an artificial intelligence (AI) model to determine repolarization waves in data from a model heart is shown. One or more processors may execute method 600.

[0033] The first data can be determined at 602. The first data can indicate one or more of the following: a unipolar intracardiac signal, a bipolar intracardiac signal, or a multipolar intracardiac signal. The first data can be simulated or measured. As further described herein, the first data can be simulated from a model of the heart.

[0034] The second data can be determined at 604. The second data may indicate one or more action potential signals of the heart, including the action recovery period (ARP). The second data may include repolarization waves. The second data may be simulated or measured. As further described herein, the second data can be simulated from a model of the heart.

[0035] An artificial intelligence (AI) model can be trained at point 606. The AI ​​model can be trained based on both the first and second data sets. The AI ​​model can be configured to determine predicted ARP based on one or more of the following: unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals. As described herein, the AI ​​model can be trained / tested to determine predicted ARP based solely on unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals.

[0036] Third data can be received at 608. The third data can indicate one or more of the following: unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals. The third data can be analog or measured. As an example, the third data can be measured from the patient's physical heart.

[0037] At point 610, using an AI model, the predicted ARP can be determined from third-party data. By developing an AI model in this way, the model can then receive one or more of unipolar, bipolar, or multipolar intracardiac signals without benefiting from the action potential, and can still predict characteristics such as reliable ARP, AP, or characteristics of AP, such as waveform morphology. The AI ​​model can be used to predict other characteristics, including, for example, various predicted attributes, measured attributes, or extracted attributes.

[0038] Although example boxes are shown, some specific implementations may include additional boxes, fewer boxes, different boxes, or boxes with different arrangements compared to those depicted. Additionally or alternatively, two or more boxes within a frame may be executed in parallel.

[0039] Figure 7 A flowchart illustrating a method 700 for determining repolarization waves in data from a model heart using an artificial intelligence (AI) model is shown. One or more processors may execute method 700. Data may be received from the heart model (box 702). This data may be simulated data. In one example, the heart model may include more than ten million cells. However, any number of cells may be represented in a heart model. The heart model may include a combination of physiological, anatomical, and physical models. The data may include one or more intracardiac signals. The data may include one or more unipolar signals. The data may include one or more bipolar signals. Repolarization waves may be determined in the data based on the AI ​​model (box 704). The AI ​​model can be evaluated (e.g., verified, checked, confirmed, etc.) by comparing the determined repolarization waves with associated known repolarization waves. The AI ​​model may have been trained (e.g., fine-tuned, etc.) on one or more datasets that associate repolarization waves with data from one or more heart models, such as a heart model.

[0040] Figure 8 This is the flowchart for example process 800. In some specific implementations, Figure 8 One or more process frames can be executed by one or more devices.

[0041] like Figure 8 As shown, process 800 may include determining first data (block 802) indicating one or more of a unipolar intracardiac signal, a bipolar intracardiac signal, or a multipolar intracardiac signal indicating at least the first heart. For example, the device may determine first data indicating one or more of a unipolar intracardiac signal, a bipolar intracardiac signal, or a multipolar intracardiac signal indicating at least the first heart, as described above.

[0042] For example Figure 8As shown, process 800 may include receiving second data (block 804) indicating one or more action potential (AP) signals of at least a first heart having an action recovery period (ARP). For example, the device may receive second data indicating one or more action potential (AP) signals of at least a first heart having an action recovery period (ARP), as described above.

[0043] like Figure 8 As further shown, process 800 may include training an artificial intelligence (AI) model based on the first and second data, wherein the AI ​​model is configured to determine the predicted AP characteristics based solely on one or more of the heart's unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals (box 806). For example, the device may train the AI ​​model based on the first and second data, wherein the AI ​​model is configured to determine the predicted AP characteristics based solely on one or more of the heart's unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals, as described above.

[0044] although Figure 8 An example block diagram of process 800 is shown, but in some specific implementations, process 800 may include... Figure 8 The boxes depicted in the diagram are compared to additional boxes, fewer boxes, different boxes, or boxes with different arrangements. Alternatively or additionally, two or more boxes of process 800 can be executed in parallel.

[0045] Although example boxes are shown, some specific implementations may include additional boxes, fewer boxes, different boxes, or boxes with different arrangements compared to those depicted. Additionally or alternatively, two or more boxes within a frame may be executed in parallel. Example

[0046] This disclosure includes at least the following embodiments: Example Clause A: A method for determining one or more predicted action potential characteristics of a patient's heart, the method comprising: determining first data indicating one or more of a unipolar intracardiac signal, a bipolar intracardiac signal, or a multipolar intracardiac signal of a first heart; determining second data indicating one or more action potential (AP) signals of the first heart that may include at least an action recovery period (ARP); training an artificial intelligence (AI) model based on the first data and the second data, wherein the AI ​​model is configured to determine a predicted ARP based on one or more of the unipolar intracardiac signal, the bipolar intracardiac signal, or the multipolar intracardiac signal of the first heart; receiving third data indicating one or more of the unipolar intracardiac signal, the bipolar intracardiac signal, or the multipolar intracardiac signal of the patient's heart; and determining the predicted ARP of the patient's heart by the AI ​​model and based on the third data.

[0047] Example Clause B: The method described in Example Clause A, wherein the first data is simulated data.

[0048] Example Clause C: The method described according to Example Clause A or Example Clause B, wherein the first data may include simulated data.

[0049] Example Clause D: The method according to any one of Example Clauses A to C, wherein the first data may include simulation data generated from at least a portion of a simulated heart model.

[0050] Example Clause E: The method according to any one of Example Clauses A to D, wherein the heart model may include a combination of physiological models, anatomical models and physical models.

[0051] Example Clause F: The method according to any one of Example Clauses A to E, wherein the second data is simulated data.

[0052] Example Clause G: The method according to any one of Example Clauses A to F, wherein the second data may include simulation data.

[0053] Example Clause H: The method according to any one of Example Clauses A to G, wherein the second data may include simulation data generated from at least a portion of the simulated heart model.

[0054] Example Clause I: The method according to any one of Example Clauses A to H, wherein the first data and the second data represent different signals within the same time period.

[0055] Example Clause J: The method according to any one of Example Clauses A to I, wherein the third data is measured from the patient's heart.

[0056] Example Clause K: A method for determining one or more predicted action potential characteristics of a patient's heart, the method comprising: determining first data indicating one or more of a unipolar intracardiac signal of at least a first heart, a bipolar intracardiac signal of at least a first heart, or a multipolar intracardiac signal of at least a first heart; receiving second data indicating one or more action potential (AP) signals of at least the first heart, including an action recovery period (ARP); and training an artificial intelligence (AI) model based on the first data and the second data, wherein the AI ​​model is configured to determine the predicted AP characteristics based solely on one or more of the unipolar intracardiac signal of the heart, the bipolar intracardiac signal of the heart, or the multipolar intracardiac signal of the heart.

[0057] Example Clause L: The method described according to Example Clause K, wherein the first data is simulated data.

[0058] Example Clause M: The method described according to Example Clause K or Example Clause L, wherein the first data may include simulated data.

[0059] Example Clause N: The method according to any one of Example Clauses K to M, wherein the first data may include simulation data generated from at least a portion of a simulated heart model.

[0060] Example Clause O: The method according to any one of Example Clauses K to N, wherein the heart model may include a combination of physiological models, anatomical models and physical models.

[0061] Example Clause P: The method according to any one of Example Clauses K to O, wherein the second data is simulated data.

[0062] Example Clause Q: In any one of Example Clauses K to P, the second data may include simulation data.

[0063] Example Clause R: The method according to any one of Example Clauses K to Q, wherein the second data may include simulation data generated from at least a portion of the simulated heart model.

[0064] Example Clause S: ​​The method according to any one of Example Clauses K to R, wherein the predicted AP characteristics may include one or more of the predicted ARP or predicted morphology of the AP waveform.

[0065] Example Clause T: A method for determining one or more predicted action potential characteristics of a patient’s heart, the method may include: receiving simulation data from at least a portion of a cardiac model; and using an artificial intelligence (AI) model and based on the simulation data to determine a repolarization wave indicative of a predicted action recovery period (ARP) of the patient’s heart.

[0066] Example Clause U: The method described according to Example Clause T, wherein the heart model may include a combination of physiological models, anatomical models and physical models.

[0067] Example Clause V: The method described according to Example Clause T or Example Clause U, wherein the simulated data may include one or more intracardiac signals.

[0068] Example Clause W: The method according to any one of Example Clauses T to V, wherein the analog data may include one or more unipolar signals.

[0069] Example Clause X: The method according to any one of Example Clauses T to W, wherein the analog data may include one or more bipolar signals.

[0070] The foregoing disclosure provides examples and descriptions, but is not intended to be exhaustive or to limit specific implementations to the exact forms disclosed. Modifications may be made based on the foregoing disclosure, or modifications may be derived from the practice of specific implementations. As used herein, the term "component" is intended to be interpreted broadly as hardware, firmware, or a combination of hardware and software. It will be apparent that the systems and / or methods described herein can be implemented in various forms of hardware, firmware, and / or combinations of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit specific implementations. Therefore, the operation and behavior of these systems and / or methods are described herein without reference to specific software code; it should be understood that software and hardware can be used to implement these systems and / or methods based on the description herein. As used herein, satisfying a threshold may refer to a value greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, etc., depending on the context. Although specific combinations of features are recited in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various specific implementations. In fact, many of these features can be combined in ways not specifically described in the claims and / or not disclosed in the specification.

[0071] Although each dependent claim listed below may directly depend on only one claim, the disclosure of various specific embodiments includes a combination of each dependent claim with each other claim in the claim set. Unless expressly stated otherwise, no element, action, or instruction used herein should be construed as critical or necessary. Furthermore, as used herein, the articles “a” and “an” are intended to include one or more items and may be used interchangeably with “one or more.” Furthermore, as used herein, the article “the” is intended to include one or more items referenced in combination with the article “the” and may be used interchangeably with “one or more.” Furthermore, as used herein, the term “set” is intended to include one or more items (e.g., related items, unrelated items, a combination of related and unrelated items, etc.) and may be used interchangeably with “one or more.” Where only one item is intended to be described, the phrase “only one” or similar language is used. Furthermore, as used herein, the terms “having,” “comprising,” “containing,” etc., are intended as open-ended terms. Furthermore, unless expressly stated otherwise, the phrase “based on” is intended to mean “at least partially based on.” Furthermore, as used herein, the term “or” is intended to be inclusive when used in enumeration and may be used interchangeably with “and / or” unless otherwise expressly stated (e.g., if used in conjunction with “any” or “only one of them”).

Claims

1. A method for determining one or more predicted action potential characteristics of a patient's heart, the method comprising: First data indicating one or more of the following: a unipolar intracardiac signal of the first heart, a bipolar intracardiac signal of the first heart, or a multipolar intracardiac signal of the first heart; Second data indicating at least one or more action potential (AP) signals of the first heart including the action recovery period (ARP); An artificial intelligence (AI) model is trained based on the first data and the second data, wherein the AI ​​model is configured to determine the predicted ARP based on one or more of the unipolar intracardiac signal of the first heart, the bipolar intracardiac signal of the first heart, or the multipolar intracardiac signal of the first heart. Receive third data indicating one or more of the following: a unipolar intracardiac signal of the patient's heart, a bipolar intracardiac signal of the patient's heart, or a multipolar intracardiac signal of the patient's heart; as well as The AI ​​model and the third data are used to determine the predicted ARP of the patient's heart.

2. The method according to claim 1, wherein, The first data is simulated data.

3. The method according to claim 1, wherein, The first data includes simulation data.

4. The method according to claim 1, wherein, The first data includes simulation data generated from at least a portion of a simulated heart model.

5. The method according to claim 4, wherein, The heart model comprises a combination of physiological, anatomical, and physical models.

6. The method according to claim 1, wherein, The second data is simulated data.

7. The method according to claim 1, wherein, The second data includes simulation data.

8. The method according to claim 1, wherein, The second data includes simulation data generated from at least a portion of the simulated heart model.

9. The method according to claim 1, wherein, The first data and the second data represent different signals within the same time period.

10. The method according to claim 1, wherein, The third data was measured from the patient's heart.

11. A method for determining one or more predicted action potential characteristics of a patient's heart, the method comprising: First data indicating one or more of the following: a unipolar intracardiac signal of at least the first heart, a bipolar intracardiac signal of at least the first heart, or a multipolar intracardiac signal of at least the first heart; The receiving indication includes second data including one or more action potential (AP) signals from at least the first heart during the action recovery period (ARP); An artificial intelligence (AI) model is trained based on the first data and the second data, wherein the AI ​​model is configured to determine the predicted AP characteristics based solely on one or more of the following: unipolar intracardiac signals, bipolar intracardiac signals, or multipolar intracardiac signals.

12. The method according to claim 11, wherein, The first data includes simulation data generated from at least a portion of a simulated heart model.

13. The method according to claim 12, wherein, The heart model comprises a combination of physiological, anatomical, and physical models.

14. The method according to claim 11, wherein, The second data includes simulation data generated from at least a portion of the simulated heart model.

15. The method according to claim 11, wherein, The predicted AP characteristics include one or more of the predicted ARP or AP waveform morphology.

16. A method for determining one or more predicted action potential characteristics of a patient's heart, the method comprising: Receive simulation data from at least a portion of the heart model; as well as Artificial intelligence (AI) models are used and the simulation data is used to determine the repolarization wave that indicates the predicted action recovery period (ARP) of the patient's heart.

17. The method according to claim 16, wherein, The heart model comprises a combination of physiological, anatomical, and physical models.

18. The method according to claim 16, wherein, The simulation data includes one or more intracardiac signals.

19. The method of claim 16, wherein, The simulation data includes one or more unipolar signals.

20. The method of claim 16, wherein, The analog data includes one or more bipolar signals.

Images