Gap finder index for high power short duration (HPSD) RF ablation lesion

Abstract

A method is described herein. The method is implemented by an optimization engine executed by a processor. The optimization engine receives data including performance metrics for mapping and ablation procedures. In turn, the optimization engine generates procedure expectations for the mapping and ablation procedure based on the data, and generates a successful prediction for the current ablation procedure using the procedure expectations. And calculating a gap index. The optimization engine also outputs an ablation suggestion based on the success prediction and the gap index.

Description

Technical Field

[0001] The disclosure herein relates to a gap finder index for radiofrequency (RF) ablation lesions. For example, the gap finder index can be applied in high power short duration (HPSD). The gap finder index can be applied to other energy sources delivered within the heart, such as cryoablation and pulsed field ablation (sometimes referred to as PFA or interchangeably referred to as irreversible electroporation (IRE)). Background Art

[0002] The pulmonary vein isolation (PVI) procedure involves ablating a series of adjacent locations on the PV to create a ring or line of ablated tissue. If the procedure is successful, the ablation ring or line acts as a barrier to the transmission of electrical waves. However, the rate of creating successful rings can be improved, and recent data indicate that approximately 21% of 179 cases of certain very high power short duration temperature controlled ablation procedures found gaps in the barrier after the first pass of ring creation.

[0003] The present method for checking a successful procedure (such as first pass isolation criteria) includes manually searching for gaps in the ring or line by cardiac signal mapping, such as ablation indications such as those provided by VISITAG from Biosense Webster, Inc. TM The distance between the indications provided by the module (these indications are referred to herein as "VisiTags"). As will be appreciated, cardiac signal mapping is provided as an example, and any other verification method for the block may be used. This is not always reliable, given the low first pass success rate, and is time consuming for the physician performing the ablation. Summary of the invention

[0004] According to an exemplary embodiment, a method is provided. The method is implemented by an optimization engine executed by one or more processors. The method includes: receiving data including performance metrics of mapping and ablation procedures; generating procedure expected results for mapping and ablation procedures based on the data; generating one or more success predictions for the current ablation procedure using the procedure expected results; and outputting an ablation recommendation based on one or more success predictions including a gap index. The present method for checking successful procedures (such as first pass isolation criteria) includes: manually searching for gaps in a ring or line, such as the distance between VisiTags, by cardiac signal mapping. As will be understood, cardiac signal mapping is provided as an example, and any other verification method for a block may be used.

[0005] According to one or more embodiments, the above exemplary method embodiments may be implemented as an apparatus, system, and / or computer program product. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] A more detailed understanding may be obtained from the following detailed description provided by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate like elements, and in which:

[0007] Figure 1 Diagrams showing exemplary systems that may implement one or more features of the disclosed subject matter according to one or more embodiments;

[0008] Figure 2 A block diagram illustrating an exemplary system for anatomically correct reconstruction of a heart atrium according to one or more embodiments is shown;

[0009] Figure 3 A method according to one or more embodiments is shown;

[0010] Figure 4 shows a graphical depiction of an AI system according to one or more embodiments;

[0011] Figure 5A An example of a neural network according to one or more embodiments is shown;

[0012] Figure 5B A block diagram illustrating a method performed in a neural network according to one or more embodiments;

[0013] Figure 6 A method according to one or more embodiments is shown;

[0014] Figure 7 shows a diagram according to one or more embodiments;

[0015] Figure 8 A method of a gap finder according to one embodiment is shown; and

[0016] Figures 9 to 14 Plots associated with the parameters are provided to demonstrate the importance and relationships associated with the parameter. DETAILED DESCRIPTION

[0017] A system and method for utilizing a gap finder index for high power short duration (HPSD) RF ablation lesions is provided. The system and method may be implemented by a computer. The system and method may include an input / output (I / O) device for receiving data from a catheter configured to perform ablation on a patient's heart. The system and method may include a memory and a processor, which is operable to perform a method including processing the received data. The system and method include: an optimization engine executed by one or more processors receives data including performance metrics of mapping and ablation procedures; the optimization engine generates a procedure expected result of the mapping and ablation procedures based on the data; the optimization engine generates one or more success predictions of the current ablation procedure using the procedure expected result; performs ablation and calculates a gap index for the ablation; and outputs the gap index for the ablation. Performing ablation may include ablating a series of adjacent locations to produce a ring or line of ablated tissue. The ablation performed may include providing one or more ablations to prevent the transmission of electrical waves. The one or more success predictions may include searching for gaps in the ablation ring or ablation line. The higher the gap index, the higher the probability of a gap in the ablation. The data may include at least an ablation index derived from at least one of force, power and time of ablation of the site. The data may include at least an average temperature or a maximum temperature of ablation of the site. The data may include at least a stability quality derived from a site stability algorithm. The data may include at least a distance to the nearest stable site derived using a site stability algorithm. The gap index for the ablation may be a function of at least the ablation index, the average temperature of the ablation, the stability quality and the distance to the nearest stable site. The gap index may be calculated for each location where ablation is performed. The system and method may include outputting a map of ablation sites that highlights ablation locations with high gap indices. A high gap index may be determined by thresholding the gap index.

[0018] Figure 1 1 is a diagram of an example system (e.g., a medical device arrangement) illustrated as system 100 in which one or more features of the subject matter herein may be implemented according to one or more embodiments. All or part of system 100 may be used to collect information (e.g., data / input, such as biometric data and / or training data sets) and / or to implement an optimization engine 101 (e.g., an ML / AI algorithm or model thereof). Optimization engine 101 may be defined as an optimization in which model parameters that best fit data and prior statistical knowledge are estimated in an iterative process to identify ablation gaps and predict successful optimization.

[0019] As shown, system 100 includes a probe 105 having a catheter 110 (including at least one electrode 111), a shaft 112, a sheath 113, and a manipulator 114. As shown, system 100 also includes a physician 115 (or medical professional, technician, clinician), a heart 120, a patient 125, and a bed 130 (or table). Illustrations 140 and 150 show the heart 120 and catheter 110 in more detail. As shown, system 100 also includes a console 160 (including one or more processors 161 and a memory 162) and a display 165. Each element and / or item of system 100 represents one or more of the element and / or the item. Figure 1 The example of the system 100 shown can be modified to implement the embodiments disclosed herein. The embodiments disclosed in the present invention can be similarly applied using other system components and settings. In addition, the system 100 can include additional components, such as elements for sensing electrical activity, wired or wireless connectors, processing and display devices, etc.

[0020] System 100 can be used to detect, diagnose and / or treat cardiac conditions (e.g., using optimization engine 101). Cardiac conditions such as arrhythmias continue to be common and dangerous medical conditions, especially in the elderly. For example, system 100 can be a surgical system (e.g., sold by Biosense Webster). The present invention is a part of a surgical system configured to obtain biometric data (e.g., anatomical measurements and electrical measurements of a patient's organ (such as heart 120)) and perform a cardiac ablation procedure. According to one or more embodiments, the biometric data may include anatomical and electrical measurements acquired in a significant portion of the atrium during mapping and ablation procedures.

[0021] More specifically, treatment of cardiac conditions such as arrhythmias typically requires obtaining detailed mapping of cardiac tissue, chambers, veins, arteries, and / or electrical pathways. For example, a prerequisite for successfully performing catheter ablation (as described herein) is that the cause of the arrhythmia is accurately located in a chamber of the heart 120. Such positioning can be accomplished via an electrophysiological study, during which a mapping catheter (e.g., catheter 110) introduced into a chamber of the heart 120 is used to spatially resolve electrical potentials. The electrophysiological study (so-called electroanatomical mapping) therefore provides 3D mapping data that can be displayed on a monitor. In many cases, the mapping function and the therapeutic function (e.g., ablation) are provided by a single catheter or a group of catheters, so that the mapping catheter also operates as a therapeutic (e.g., ablation) catheter at the same time. In this case, the optimization engine 101 can be directly stored and executed by the catheter 110.

[0022] In a patient with normal sinus rhythm (NSR) (e.g., patient 125), the heart (e.g., heart 120) including the atria, ventricles, and excitatory conduction tissue is electrically stimulated to beat in a synchronized patterned manner. This electrical stimulation can be detected as intracardiac electrocardiogram (IC ECG) data, etc.

[0023] In a patient (e.g., patient 125) with an arrhythmia (e.g., atrial fibrillation or aFib), an abnormal region of cardiac tissue does not follow the synchronous beating cycle associated with normal conducting tissue, in contrast to a patient with NSR. Instead, the abnormal region of cardiac tissue conducts abnormally to adjacent tissue, disrupting the cardiac cycle into an asynchronous rhythm. This asynchronous rhythm may also be detected as IC ECG data. Such abnormal conduction has previously been known to occur at various regions of the heart 120, such as in the sinoatrial (SA) node region, along the conduction pathway of the atrioventricular (AV) node, or in the myocardial tissue that forms the walls of the ventricular and atrial heart chambers. There are other conditions (such as fibrillation) in which the pattern of abnormal conducting tissue results in a reentrant pathway that causes the chambers to beat in a regular pattern that may be a multiple of the sinus rhythm.

[0024] To support the system 100 in detecting, diagnosing and / or treating cardiac conditions, the probe 105 may be navigated by a physician 115 into the heart 120 of a patient 125 lying on a bed 130. For example, the physician 115 may insert the shaft 112 through the sheath 113 while manipulating the distal end of the shaft 112 using a manipulator 114 near the proximal end of the catheter 110 and / or deflecting from the sheath 113. As shown in inset 140, a basket catheter 110 may be mounted at the distal end of the shaft 112. The basket catheter 110 may be inserted through the sheath 113 in a collapsed state and may then be deployed within the heart 120.

[0025] Typically, a catheter 110 containing an electrical sensor (e.g., at least one electrode 111) at or near its distal tip is advanced to a point in the heart 120, where the sensor contacts tissue and data is acquired at that point to measure electrical activity at that point in the heart 120. One disadvantage of using a catheter containing only a single distal tip electrode to map a heart chamber is the time required to accumulate data point by point at the necessary number of points required for a detailed map of the chamber as a whole. Therefore, multi-electrode catheters (e.g., catheter 110) have been developed to simultaneously measure electrical activity at multiple points in a heart chamber.

[0026] The catheter 110, which may include at least one electrode 111 and a portion coupled to its body, may be configured to obtain biometric data, such as electrical signals of an organ in the body (e.g., heart 120), and / or ablate a tissue region thereof (e.g., a cardiac chamber of heart 120). Electrode 111 represents any similar element, such as a tracking coil, a piezoelectric transducer, an electrode, or a combination of elements configured to ablate a tissue region or obtain biometric data. According to one or more embodiments, the catheter 110 may include one or more positioning sensors for determining trajectory information. For example, trajectory information and other information including force data and temperature sensors may be used to infer motion characteristics, such as the contractility of tissue.

[0027] Biometric data (e.g., patient biometrics, patient data, or patient biometric data) may include one or more of local activation time (LAT), electrical activity, topology, bipolar mapping, reference activity, ventricular activity, dominant frequency, impedance, and the like. The LAT may be a time point corresponding to a threshold activity of local activation calculated based on a normalized initial starting point. The electrical activity may be any applicable electrical signal that may be measured based on one or more thresholds and may be sensed and / or enhanced based on a signal-to-noise ratio and / or other filters. The topology may correspond to a physical structure of a body part or a portion of a body part, and may correspond to changes in the physical structure relative to different portions of a body part or relative to different body parts. The dominant frequency may be a frequency or frequency range that is prevalent at a portion of a body part, and may be different in different portions of the same body part. For example, the dominant frequency of the PV of a heart may be different from the dominant frequency of the right atrium of the same heart. Impedance may be a resistance measurement at a given area of ​​a body part.

[0028] Examples of biometric data include, but are not limited to, patient identification data, IC ECG data, bipolar intracardiac reference signals, anatomical and electrical measurements, trajectory information, body surface (BS) ECG data, historical data, brain biometrics, blood pressure data, ultrasound signals, radio signals, audio signals, two-dimensional or three-dimensional image data, blood glucose data, and temperature data. Biometric data can be used to monitor, diagnose, and treat any number of various diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathy, and coronary artery disease) and autoimmune diseases (e.g., type I and type II diabetes). BS ECG data can include data and signals collected from electrodes on the surface of the patient, IC ECG data can include data and signals collected from electrodes inside the patient, and ablation data can include data and signals collected from tissue that has been ablated. In addition, BS ECG data, IC ECG data, and ablation data, along with catheter electrode positioning data, can be derived from one or more procedure records.

[0029] For example, catheter 110 may use electrodes 111 to enable intravascular ultrasound and / or MRI catheterization to image (e.g., obtain and process biometric data) heart 120. Illustration 150 shows catheter 110 in a magnified view within a heart chamber of heart 120. Although catheter 110 is shown as a pointed catheter, it should be understood that any shape including one or more electrodes 111 may be used to implement the exemplary embodiments disclosed herein.

[0030] Examples of catheter 110 include, but are not limited to, a linear catheter with multiple electrodes, a balloon catheter including electrodes dispersed on multiple ridges that shape the balloon, a lasso or loop catheter with multiple electrodes, a contact force sensing catheter, or any other applicable shape or type. The linear catheter may be fully or partially elastic so that it can twist, bend, and / or otherwise change its shape based on received signals and / or based on applying an external force (e.g., heart tissue) on the linear catheter. The balloon catheter may be designed so that when deployed into the patient, its electrodes can remain in close contact against the endocardial surface. As will be appreciated, although a balloon catheter is described to aid in understanding the present invention, a spherical or grid-shaped catheter or a catheter with multiple ridges may also be used. For example, a balloon catheter may be inserted into an inner cavity, such as a PV. The balloon catheter may be inserted into the PV in a deflated state so that the balloon catheter does not occupy its maximum volume when inserted into the PV. The balloon catheter may be expanded inside the PV so that those electrodes on the balloon catheter are in contact with the entire circular segment of the PV. Such contact with the entire circular segment of the PV or any other lumen may enable effective imaging and / or ablation.

[0031] According to other examples, the body patch and / or body surface electrodes may also be positioned on or near the body of the patient 125. The catheter 110 having the one or more electrodes 111 may be positioned within the body (e.g., within the heart 120), and the position of the catheter 110 may be determined by the system 100 based on signals transmitted and received between the one or more electrodes 111 of the catheter 110 and the body patch and / or body surface electrodes. In addition, the electrodes 111 may sense biometric data from within the body of the patient 125 (such as within the heart 120) (e.g., the electrodes 111 sense the electrical potential of the tissue in real time). The biometric data may be associated with the determined positioning of the catheter 110, so that a rendering of the patient's body part (e.g., the heart 120) may be displayed, and the biometric data may be displayed overlaid on the shape of the body part.

[0032] The probe 105 and other items of the system 100 may be connected to the console 160. The console 160 may include any computing device that employs an ML / AI algorithm or model (represented as the optimization engine 101). According to an exemplary embodiment, the console 160 includes one or more processors 161 (any computing hardware) and a memory 162 (any non-transitory tangible medium), wherein the one or more processors 161 execute computer instructions relative to the optimization engine 101, and the memory 162 stores these instructions for execution by the one or more processors 161. For example, the console 160 may be configured to receive and / or store biometric data on a database in the memory 162, process the biometric data, and determine whether a given tissue region is conductive.

[0033] According to one or more embodiments, the console 160 may also be programmed by the optimization engine 101 (in software) to perform the following functions: receive data including performance metrics of mapping and ablation procedures, generate procedure expected results for the mapping and ablation procedures based on the data, generate a success prediction for the current ablation procedure, and output a probability of redoing the procedure based on the success prediction. In this regard, the optimization engine 101 may include, implement and / or incorporate unsupervised and / or supervised ML / AI algorithms (hereinafter referred to as Figure 3 and Figure 6 In generating the expected results of the mapping and ablation procedures, the present systems and methods operate using various measurement data collected during the procedures to classify the results based on known data from other procedures. In this way, the system and method predicts the results of the ablation procedure via the optimization engine 101 using the ablation index and its related parameters as described below. In this way, the system and method can indicate to the medical professional or identify on the display of the system that additional corrective actions need to be taken in order to improve the success rate of the procedure. One such additional action can be to re-perform the ablation.

[0034] Generally speaking, the optimization engine 101 can provide one or more user interfaces, such as representing an operating system or other application and / or directly providing as needed. User interfaces include, but are not limited to, an Internet browser, a graphical user interface (GUI), a window interface, and / or other visual interfaces for applications, operating systems, folders, etc. According to one or more embodiments, the optimization engine 101 can be located outside the console 160, and can be located, for example, in the catheter 110, in an external device, in a mobile device, in a cloud-based device, or can be an independent processor. In this regard, the optimization engine 101 can be transmitted / downloaded over a network in electronic form.

[0035] In one example, the console 160 can be any computing device (such as a general purpose computer) as described herein including software (e.g., optimization engine 101) and / or hardware (e.g., processor 161 and memory 162) with suitable front-end and interface circuitry for transmitting and receiving signals to and from the probe 105, as well as for controlling other components of the system 100. For example, the front-end and interface circuitry include an input / output (I / O) communication interface that enables the console 160 to receive and / or transmit signals to at least one electrode 111. The console 160 can include real-time noise reduction circuitry, typically configured as a field programmable gate array (FPGA), followed by an analog-to-digital (A / D) ECG or electrocardiograph or electromyogram (EMG) signal conversion integrated circuit. The console 160 can pass signals from the A / D ECG or EMG circuitry to another processor and / or can be programmed to perform one or more functions disclosed herein.

[0036] The display 165 may be any electronic device for visual presentation of biometric data, which is connected to the console 160. According to an exemplary embodiment, during a procedure, the console 160 may facilitate presenting a body part rendering to the physician 115 on the display 165, and storing data representing the body part rendering in the memory 162. For example, a map depicting motion characteristics may be rendered / constructed based on trajectory information sampled at a sufficient number of points in the heart 120. As an example, the display 165 may include a touch screen, which may be configured to accept input from the physician 115 in addition to presenting the body part rendering.

[0037] In some embodiments, the physician 115 can manipulate elements of the system 100 and / or the body part rendering using one or more input devices, such as a touch pad, a mouse, a keyboard, a gesture recognition device, etc. For example, an input device can be used to change the positioning of the catheter 110 so that the rendering is updated. The display 165 can be located in the same location or a remote location, such as a separate hospital or in a separate healthcare provider network.

[0038] According to one or more embodiments, the system 100 may also use ultrasound, computed tomography (CT), MRI or other medical imaging techniques using the catheter 110 or other medical equipment to obtain biometric data. For example, the system 100 may use one or more catheters 110 or other sensors to obtain ECG data and / or anatomical and electrical measurements (e.g., biometric data) of the heart 120. More specifically, the console 160 may be connected to a BS electrode via a cable, the BS electrode comprising an adhesive skin patch attached to the patient 125. The BS electrode may obtain / generate biometric data in the form of BS ECG data. For example, the processor 161 may determine the position coordinates of the catheter 110 within a body part (e.g., the heart 120) of the patient 125. These position coordinates may be based on impedance or electromagnetic fields measured between the surface electrodes and the electrodes 111 or other electromagnetic components of the catheter 110. Additionally or alternatively, a positioning pad generating a magnetic field for navigation may be located on the surface of the bed 130 and may be separated from the bed 130. The biometric data may be transmitted to the console 160 and stored in the memory 162. Alternatively or additionally, the biometric data may be transmitted to a server, which may be local or remote, using a network as otherwise described herein.

[0039] According to one or more exemplary embodiments, the catheter 110 may be configured to ablate a tissue region of a cardiac chamber of the heart 120. Illustration 150 shows the catheter 110 in a cardiac chamber of the heart 120 in an enlarged view. For example, an ablation electrode such as at least one electrode 111 may be configured to provide energy to a tissue region of an organ (e.g., the heart 120) within the body. The energy may be thermal energy and may cause damage to the tissue region starting from the surface of the tissue region and extending into the thickness of the tissue region. Biometric data relative to the ablation procedure (e.g., ablated tissue, ablation location, etc.) may be considered as ablation data.

[0040] According to one example, with respect to obtaining biometric data, a multi-electrode catheter (e.g., catheter 110) may be advanced into a chamber of the heart 120. Anterior-posterior fluorograms (AP) and lateral fluorograms may be obtained to establish the location and orientation of each electrode. An ECG may be recorded from each of the electrodes 111 in contact with the surface of the heart relative to a time reference (such as the start of a P wave in sinus rhythm from a BS ECG and / or a signal from an electrode 111 of the catheter 110 placed in the coronary sinus). As further disclosed herein, the system may distinguish between those electrodes that record electrical activity and those electrodes that do not record electrical activity due to not being in close proximity to the endocardial wall. After recording the initial ECG, the catheter may be repositioned, and the fluorogram and ECG may be recorded again. An electrical map may then be constructed (e.g., via cardiac mapping) according to iterations of the above process.

[0041] Cardiac mapping can be accomplished using one or more techniques. In general, mapping of cardiac regions (such as cardiac areas, tissues, veins, arteries, and / or electrical pathways of the heart 120) can enable identification of problem areas (such as scar tissue), sources of arrhythmias (e.g., electrical rotors), healthy areas, and the like. A cardiac region can be mapped such that a visual rendering of the mapped cardiac region is provided using a display, as further disclosed herein. In addition, cardiac mapping (which is an example of cardiac imaging) can include mapping based on one or more modalities, such as, but not limited to, LAT, local activation velocity, electrical activity, topology, bipolar mapping, dominant frequency, or impedance. A catheter (e.g., catheter 110) inserted into a patient's body can be used to capture data corresponding to multiple modalities (e.g., biometric data), and the data can be provided for rendering simultaneously or at different times based on corresponding settings and / or preferences of the physician 115.

[0042] As an example of a first technique, cardiac mapping may be achieved by sensing electrical properties of cardiac tissue (e.g., LAT) according to precise locations within the heart 120. Corresponding data (e.g., biometric data) may be acquired by one or more catheters (e.g., catheter 110) that are advanced into the heart 120 and have electrical sensors and position sensors (e.g., electrodes 111) in their distal tips. As a specific example, position and electrical activity may initially be measured at about 10 to about 20 points on the inner surface of the heart 120. These data points may generally be sufficient to generate a preliminary reconstruction or map of satisfactory quality of the heart surface. The preliminary map may be combined with data taken from additional points to produce a more comprehensive map of cardiac electrical activity. In a clinical setting, it is not uncommon to accumulate data at 100 or more sites (e.g., thousands) to generate a detailed and comprehensive map of cardiac chamber electrical activity. The generated detailed map may then serve as a basis for deciding a course of therapeutic action, such as tissue ablation as described herein, to alter the propagation of cardiac electrical activity and restore normal heart rhythm.

[0043] In addition, cardiac mapping can be generated based on the detection of an intracardiac potential field (e.g., an example of an IC ECG data and / or a bipolar intracardiac reference signal). A non-contact technique for simultaneously acquiring a large amount of cardiac electrical information can be implemented. For example, a catheter type having a distal end portion may be provided with a series of sensor electrodes distributed on its surface and connected to an insulated electrical conductor for connection to a signal sensing and processing device. The size and shape of the end portion may be such that the electrode is substantially spaced apart from the wall of the heart chamber. The intracardiac potential field may be detected during a single heartbeat. According to one example, the sensor electrodes may be distributed on a series of circumferences located in planes spaced apart from each other. These planes may be perpendicular to the long axis of the end portion of the catheter. At least two additional electrodes may be provided adjacently at the end of the long axis of the end. As a more specific example, the catheter may include four circumferences, wherein eight electrodes are equiangularly spaced apart on each circumference. Therefore, in this specific implementation, the catheter may include at least 34 electrodes (32 circumferential electrodes and 2 end electrodes). As another more specific example, the catheter may include other multi-spline catheters, such as five soft flexible branches, eight radial splines, or a parallel spline spatula type (eg, any of which may have a total of 42 electrodes).

[0044] As an example of electrical mapping or cardiac mapping, an electrophysiological cardiac mapping system and technique based on a non-contact and non-expanding multi-electrode catheter (e.g., catheter 110) can be implemented. ECG can be obtained using one or more catheters 110 having multiple electrodes (e.g., such as between 42 and 122 electrodes). According to this specific implementation, knowledge of the relative geometry of the probe and the endocardium can be obtained by an independent imaging modality such as transesophageal echocardiography. After independent imaging, the non-contact electrodes can be used to measure the cardiac surface potential and construct a map therefrom (e.g., in some cases, using a bipolar intracardiac reference signal). The technique may include the following steps (after the independent imaging step): (a) measuring the potential using multiple electrodes disposed on a probe positioned in the heart 120; (b) determining the geometric relationship of the probe surface to the endocardial surface and / or other references; (c) generating a coefficient matrix representing the geometric relationship of the probe surface and the endocardial surface; and (d) determining the endocardial potential based on the electrode potential and the coefficient matrix.

[0045] According to another example of electrical mapping or cardiac mapping, techniques and apparatus for mapping the electrical potential distribution of a cardiac chamber may be implemented. An intracardiac multi-electrode mapping catheter assembly may be inserted into the heart 120. The mapping catheter (e.g., catheter 110) assembly may include a multi-electrode array or a matching reference catheter having one or more integral reference electrodes (e.g., one or more electrodes 111).

[0046] According to one or more exemplary embodiments, the electrodes can be deployed in a substantially spherical array that can be spatially referenced to a point on the endocardial surface by a reference electrode or by a reference catheter in contact with the endocardial surface. A preferred electrode array catheter can carry a plurality of individual electrode sites (e.g., at least 24). In addition, the exemplary technique can be implemented by knowing the location of each of the electrode sites on the array and knowing the geometry of the heart. These locations are preferably determined by the technique of impedance plethysmography.

[0047] In view of electrical mapping or cardiac mapping and according to another example, the catheter 110 may be a cardiac mapping catheter assembly, which may include an electrode array defining a plurality of electrode sites. The cardiac mapping catheter assembly may also include an inner cavity to receive a reference catheter having a distal tip electrode assembly, which can be used to detect the heart wall. The cardiac mapping catheter assembly may include a braid of insulated wires (e.g., having 24 to 64 wires in the braid), and each of the wires may be used to form an electrode site. The cardiac mapping catheter assembly may be easily positioned in the heart 120 for obtaining electrical activity information from a first set of non-contact electrode sites and / or a second set of contact electrode sites.

[0048] In addition, according to another example, the catheter 110 that can achieve mapping of electrophysiological activities in the heart may include a distal tip suitable for delivering stimulation pulses for cardiac pacing or an ablation electrode for ablating tissue contacted with the tip. The catheter 110 may also include at least one pair of orthogonal electrodes to generate a difference signal indicating local cardiac electrical activity adjacent to the orthogonal electrodes.

[0049] As described herein, the system 100 can be used to detect, diagnose and / or treat cardiac conditions. In an example operation, a process for measuring electrophysiological data in a heart chamber can be implemented by the system 100. The process can include, in part, positioning a set of active electrodes and passive electrodes into the heart 120, supplying current to the active electrodes, thereby generating an electric field in the heart chamber, and measuring the electric field at the passive electrode sites. The passive electrodes are contained in an array positioned on an inflatable balloon of a balloon catheter. In a preferred embodiment, the array is said to have from 60 to 64 electrodes.

[0050] As another example operation, cardiac mapping may be implemented by the system 100 using one or more ultrasound transducers. The ultrasound transducer may be inserted into the patient's heart 120, and multiple ultrasound slices (e.g., two-dimensional or three-dimensional slices) may be collected at various positions and orientations within the heart 120. The position and orientation of a given ultrasound transducer may be known, and the collected ultrasound slices may be stored so that they may be displayed at a later time. One or more ultrasound slices corresponding to the position of the probe 105 (e.g., a treatment catheter shown as catheter 110) at a later time may be displayed, and the probe 105 may be overlaid on the one or more ultrasound slices.

[0051] In view of system 100, it is noted that arrhythmias, including atrial arrhythmias, may be of the multi-wavelet reentrant type, characterized by multiple asynchronous loops of electrical impulses dispersed around the atrial chambers and typically self-propagating (e.g., another example of ICECG data). Alternatively, or in addition to the multi-wavelet reentrant type, arrhythmias may also have a focal origin, such as when an isolated tissue region within the atrium beats autonomously in a rapid, repetitive manner (e.g., another example of IC ECG data). Ventricular tachycardia (V-tach or VT) is a tachycardia or rapid heart rhythm originating from one of the ventricles. This is a potentially life-threatening arrhythmia as it can lead to ventricular fibrillation and sudden death.

[0052] For example, aFib occurs when normal electrical impulses generated by the sinoatrial node (e.g., another example of IC ECG data) are overwhelmed by chaotic electrical impulses originating from the atrial veins and PVs that cause irregular pulses to be transmitted to the ventricles. Irregular heartbeats occur and may last from minutes to weeks, or even years. aFib is typically a chronic condition that is usually caused by a stroke, with a slightly increased risk of death. The first-line treatment for aFib is medication that slows the heart rate or restores the heart rhythm to normal. In addition, people with aFib are usually given anticoagulants to prevent them from having a risk of stroke. The use of such anticoagulants is accompanied by its own risk of internal bleeding. For some patients, drug therapy is not enough, and their aFib is considered drug-refractory, that is, it cannot be cured with standard drug interventions. Synchronized cardioversion can also be used to convert aFib to a normal heart rhythm. Alternatively, aFib patients are treated by catheter ablation.

[0053] Treatment based on catheter ablation can include mapping the electrical properties of cardiac tissue (particularly the endocardium and cardiac volume), and selectively ablating cardiac tissue by applying energy. Electrical mapping or cardiac mapping (e.g., implemented by any of the electrophysiology cardiac mapping systems and techniques described herein) includes creating a map of electrical potentials propagating along the cardiac tissue (e.g., a voltage map) or a map of arrival times to various tissue locations (e.g., a LAT map). Electrical mapping or cardiac mapping (e.g., a cardiac map) can be used to detect local cardiac tissue dysfunction. Ablation (such as ablation based on cardiac mapping) can stop or alter the propagation of unwanted electrical signals from one part of the heart 120 to another.

[0054] The ablation process damages unwanted electrical pathways by forming non-conductive lesions. A variety of energy delivery modalities for forming lesions have been disclosed, and include the use of microwaves, lasers, and more commonly radiofrequency energy to form conduction blocks along the walls of cardiac tissue. Another example of an energy delivery technique includes pulsed field ablation (PFA) to achieve irreversible electroporation (IRE) by providing a pulsed high voltage electric field that damages cell membranes. In a two-step procedure (e.g., mapping followed by ablation), electrical activity at various points within the heart 120 is typically sensed and measured by advancing a catheter 110 containing one or more electrical sensors (or electrodes 111) into the heart 120 and obtaining / acquiring data at multiple points (e.g., generally such as biometric data, or specifically such as ECG data). The ECG data is then used to select an endocardial target area where ablation is to be performed.

[0055] Cardiac ablation and other cardiac electrophysiology procedures have become increasingly complex as clinicians treat increasingly challenging conditions such as atrial fibrillation and ventricular tachycardia. Treatment of complex arrhythmias may rely solely on the use of a three-dimensional (3D) mapping system to reconstruct the anatomy of the heart chamber of interest. In this regard, the optimization engine 101 employed by the system 100 herein manipulates and evaluates biometric data in general or ECG data in particular to produce improved tissue data that enables more accurate diagnosis, images, scans, and / or maps for treating abnormal heartbeats or arrhythmias. For example, cardiologists rely on software such as the 3D Imager software produced by Biosense Webster, Inc. (Diamond Bar, Calif.). The 3D mapping system's Complex Fractionated Atrial Electrogram (CFAE) module generates and analyzes ECG data. The optimization engine 101 of the system 100 enhances the software to generate and analyze improved biometric data, which further provides multiple pieces of information about the electrophysiological properties of the heart 120 (including scar tissue) that represent the cardiac substrate (anatomy and function) of aFib.

[0056] Thus, system 100 can implement a 3D mapping system such as 3 3D mapping system to locate potential arrhythmogenic substrates of cardiomyopathies in terms of abnormal ECG detection. The substrate associated with these cardiac disorders is associated with the presence of fragmented and prolonged ECG in the endocardial layer and / or epicardial layer of the ventricular chambers (right and left). For example, areas of low or medium voltage may exhibit ECG fragmentation and prolonged activity. In addition, during sinus rhythm, areas of low or medium voltage may correspond to key isthmuses identified during sustained and organized ventricular arrhythmias (e.g., applicable to non-tolerant ventricular tachycardia, as well as in the atria). In general, abnormal tissue is characterized by a low voltage ECG. However, initial clinical experience in endocardial-epicardial mapping indicates that low voltage areas are not always present in such patients as the only arrhythmogenic mechanism. In fact, areas of low or medium voltage may exhibit ECG fragmentation and prolonged activity during sinus rhythm, which corresponds to key isthmuses identified during sustained and organized ventricular arrhythmias, for example, applicable only to non-tolerant ventricular tachycardia. Furthermore, in many cases, ECG fragmentation and prolonged activity are observed in areas showing normal or near-normal voltage amplitudes (>1mV-1.5mV). Although the latter areas can be assessed based on voltage amplitude, they cannot be considered normal based on the intracardiac signal and therefore represent a true arrhythmogenic substrate. 3D mapping enables localization of the arrhythmogenic substrate on the endocardial and / or epicardial layers of the right / left ventricle, which can vary in distribution depending on the extension of the primary disease.

[0057] As another example operation, cardiac mapping can be implemented by the system 100 using one or more multi-electrode catheters (e.g., catheter 110). The multi-electrode catheter is used to stimulate and map electrical activity in the heart 120 and to ablate sites of abnormal electrical activity. When used, the multi-electrode catheter is inserted into a major vein or artery (e.g., femoral vein) and then guided into the chamber of the heart 120 of interest. A typical ablation procedure involves inserting a catheter 110 having at least one electrode 111 at its distal end into a cardiac chamber. A reference electrode is provided that is glued to the patient's skin, or a reference electrode is provided by a second catheter positioned in or near the heart or selected from one or other electrodes 111 of the catheter 110. A radio frequency (RF) current is applied to the tip electrode 111 of the ablation catheter 110, and the current flows to the reference electrode through the medium (e.g., blood and tissue) surrounding the tip electrode. The distribution of the current depends on the amount of contact between the electrode surface and the tissue compared to the blood, which has a higher conductivity than the tissue. Due to the resistance of the tissue, heating of the tissue occurs. The tissue is heated sufficiently to cause cell destruction in the cardiac tissue, resulting in the formation of non-conductive ablation lesions within the cardiac tissue. During this process, heating of the tip electrode 111 also occurs due to conduction from the heated tissue to the electrode itself. If the electrode temperature becomes high enough (perhaps above 60° C.), a thin transparent coating of dehydrated blood protein may form on the surface of the electrode 111. If the temperature continues to rise, the dehydrated layer may become thicker and thicker, causing blood coagulation on the electrode surface. Because the dehydrated biomaterial has a higher electrical resistance than the endocardial tissue, the impedance to the flow of electrical energy into the tissue also increases. If the impedance increases sufficiently, an impedance rise occurs, and the catheter 110 must be removed from the body and the tip electrode 111 cleaned.

[0058] Figure 2 A diagram of a system 200 is shown in which one or more features of the disclosed subject matter may be implemented, according to one or more exemplary embodiments. Figure 1 ), the system 200 includes a device 204, a local computing device 206, a remote computing system 208, a first network 210, and a second network 211. In addition, the device 204 may include a biometric sensor 221 (e.g., Figure 1 10 ), a processor 222, a user input (UI) sensor 223, a memory 224, and a transceiver 225. For ease of explanation and brevity, Figure 1 Optimization Engine 101 Figure 2 was reused.

[0059] According to one embodiment, device 204 may be Figure 1An example of a system 100 is provided, wherein the device 204 may include both components that are internal to the patient and components that are external to the patient. According to another embodiment, the device 204 may be a device external to the patient 202 that includes an attachable patch (e.g., attached to the patient's skin). According to another embodiment, the device 204 may be internal to the body of the patient 202 (e.g., implanted subcutaneously), wherein the device 204 may be inserted into the patient 202 via any suitable means, including oral injection, surgical insertion via a vein or artery, endoscopic procedures, or laparoscopic procedures. According to one embodiment, although in Figure 2 A single device 204 is shown in FIG. 2 , but the example system may include multiple devices.

[0060] Thus, the device 204, the local computing device 206, and / or the remote computing system 208 may be programmed to execute computer instructions relative to the optimization engine 101. For example, the memory 223 stores these instructions for execution by the processor 222 so that the device 204 can receive and process biometric data via the biometric sensor 201. As such, the processor 222 and the memory 223 represent the processor and memory of the local computing device 206 and / or the remote computing system 208.

[0061] The device 204, local computing device 206, and / or remote computing system 208 may be any combination of software and / or hardware that, alone or in combination, stores, executes, and implements the optimization engine 101 and its functions. In addition, the device 204, local computing device 206, and / or remote computing system 208 may be an electronic computer framework that includes and / or employs any number and combination of computing devices and networks utilizing various communication technologies, as described herein. The device 204, local computing device 206, and / or remote computing system 208 may be easily scalable, extensible, and modular, with the ability to change to different services or reconfigure some features independently of other features.

[0062] Networks 210 and 211 may be wired networks, wireless networks, or include one or more wired and wireless networks. According to one embodiment, network 210 is an example of a short-range network (e.g., a local area network (LAN) or a personal area network (PAN)). Any of a variety of short-range wireless communication protocols (such as Bluetooth, Wi-Fi, Zigbee, Z-Wave, near field communication (NFC), ultra-band, Zigbee, or infrared (IR)) may be used to send information between device 204 and local computing device 206 via network 210. In addition, network 211 is an example of one or more of the following: an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or a series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between local computing device 206 and remote computing system 208. Any of a variety of long-range wireless communication protocols (e.g., TCP / IP, HTTP, 3G, 4G / LTE, or 5G / new radio) may be used to send information via network 211. For either of networks 210 and 211, wired connections may be implemented using Ethernet, Universal Serial Bus (USB), RJ-11, or any other wired connection and wireless connections may be implemented using Wi-Fi, WiMAX, as well as Bluetooth, infrared, cellular networks, satellite, or any other wireless connection method.

[0063] In operation, device 204 may continuously or periodically obtain, monitor, store, process biometric data associated with patient 202, and transmit the biometric data via network 210. In addition, device 204, local computing device 206, and / or remote computing system 208 communicate via networks 210 and 211 (e.g., local computing device 206 may be configured as a gateway between device 204 and remote computing system 208). For example, device 204 may be Figure 1 The system 100 is configured to communicate with a local computing device 206 via a network 210. The local computing device 206 may be, for example, a fixed / standalone device, a base station, a desktop / laptop computer, a smart phone, a smart watch, a tablet computer, or other device configured to communicate with other devices via networks 211 and 210. A public cloud computing provider (e.g., Amazon Web Services ) implemented as a physical server on or connected to the network 211 or a network 210 ) can be configured to communicate with the local computing device 206 via the network 211. Thus, biometric data associated with the patient 202 can be transmitted throughout the system 200.

[0064] The elements of the device 204 are now described. The biometric sensor 221 may include, for example, one or more transducers configured to convert one or more environmental conditions into electrical signals so that different types of biometric data can be observed / obtained / acquired. For example, the biometric sensor 221 may include one or more of the following: electrodes (e.g., Figure 1 electrodes 111), a temperature sensor (e.g., a thermocouple), a blood pressure sensor, a blood glucose sensor, a blood oxygen sensor, a pH sensor, an accelerometer, and a microphone.

[0065] When executing the optimization engine 101, the processor 222 can be configured to receive, process and manage biometric data acquired by the biometric sensor 221, and transmit the biometric data to the memory 224 via the transceiver 225 for storage (e.g., on a database therein) and / or across the network 210 (e.g., to its database). Biometric data from one or more other devices 204 can also be received by the processor 222 via the transceiver 225. As described in more detail below, the processor 222 can be configured to selectively respond to different tap patterns (e.g., single or double taps) received from the UI sensor 223, so that different tasks of the patch (e.g., acquisition, storage or transmission of data) can be activated based on the detected pattern. In some embodiments, the processor 222 can generate audible feedback about the detected gesture.

[0066] UI sensor 223 includes, for example, a piezoelectric sensor or a capacitive sensor configured to receive user input such as a tap or touch. For example, in response to patient 202 tapping or contacting the surface of device 204, UI sensor 223 can be controlled to achieve capacitive coupling. Gesture recognition can be achieved via any of a variety of capacitance types, such as resistive capacitance, surface capacitance, projected capacitance, surface acoustic wave, piezoelectric, and infrared touch. Capacitive sensors can be set at a small area or over the length of a surface so that a tap or touch of the surface activates the monitoring device.

[0067] Memory 224 is any non-transitory tangible medium such as magnetic, optical, or electronic memory (e.g., any suitable volatile and / or non-volatile memory such as random access memory or a hard drive). Memory 224 stores computer instructions for execution by processor 222.

[0068] The transceiver 225 may include a separate transmitter and a separate receiver. Alternatively, the transceiver 225 may include a transmitter and a receiver integrated into a single device.

[0069] In operation, the device 204 utilizes the optimization engine 101 to observe / obtain biometric data of the patient 202 via the biometric sensor 221, stores the biometric data in a memory, and shares the biometric data across the system 200 via the transceiver 225. The optimization engine 101 can then utilize models, algorithms (e.g., unsupervised and / or supervised ML / AI algorithms), neural networks to identify ablation gaps and provide a success prediction to the physician 1515 to transform the operation of the system 100, which increases the probability of success of the next procedure and / or eliminates unnecessary subsequent procedures.

[0070] Figure 3 According to one or more exemplary embodiments (for example, by Figure 1 and / or Figure 2 The method 300 is performed by the optimization engine 101 of the embodiment of the present invention. The method 300 identifies ablation gaps and provides success predictions by providing multi-step manipulation of data that improves arrhythmia diagnosis and treatment. The method 300 is described in an exemplary and explanatory manner with respect to an ablation procedure.

[0071] The method begins at block 320 where the optimization engine 101 receives data including performance metrics of mapping and ablation procedures. The data may be considered one or more inputs to the optimization engine 101, which is executed by one or more processors 161 or 222.

[0072] The data / inputs typically represent biometric data (as described herein), patient parameters, procedure parameters, and / or performance metrics. For example, biometric data may include, for example, anatomical and electrical measurements obtained in significant portions of the atrium during mapping and ablation procedures, as well as other sensor measurements including temperature and impedance. In addition, patient and / or procedure parameters may be related to the mapping and ablation procedures, such as patient characteristics, tissue characteristics, and other data points in the indexing procedure, as well as patient demographics, information / data related to previous electrophysiological procedures, and acute / long-term results of the patient. In general, patient parameters or patient-specific information may include body temperature, irrigation temperature, tissue and surface temperature before ablation, tissue and surface temperature during ablation, and tissue and surface temperature after ablation. In addition, patient parameters or patient-specific information may also include surface ECG, patient prior medical history, patient demographics, IC ECG, voltage mapping, type of equipment used, time and date of procedure, and anatomical structure of the patient's heart. In general, procedure parameters or procedure-specific information may include catheter stability during ablation procedures and other patient historical results. In addition, the data / inputs may include performance metrics, including any information indicating or identifying the results during and / or the results of mapping and ablation procedures. Using these inputs, the optimization engine 101 initiates the technical effects and benefits of identifying ablation gaps and providing successful predictions for each patient based on circumstances (e.g., time and location).

[0073] The optimization engine 101 receives one or more previous medical records (such as previous or old ablation procedures) stored in the system 100 (e.g., a database therein) or received by the system 100. Based on these previous medical records, data / input can be derived / obtained via a map having a chain of ablation lesions, an anatomical map, and / or an electrical map thereof. Based on these previous medical records, data / input can be derived / obtained from its sensor data, which is generated by one or more sensors (e.g., from the catheter 110 and / or surface electrodes). For example, an ablation catheter (e.g., catheter 110) can be used to form tissue necrosis in the cardiac tissue of the heart 120 to correct arrhythmias. In an exemplary ablation procedure, ablation lesions are created in the cardiac tissue of the heart 120 of the patient 125 when the catheter 110 is inserted into the heart 120 to contact the cardiac tissue and electromagnetic RF energy is injected into the cardiac tissue from one or more electrodes 111 to cause ablation and create ablation lesions. The coordinates of the ablation lesion and the parameters of the electromagnetic RF energy may be included in the data / input of the ablation procedure.

[0074] At block 340, the optimization engine 101 generates one or more procedure expected outcomes for the mapping and ablation procedure based on the data. Generally, the one or more procedure expected outcomes identify the performance of the mapping and ablation procedure, such as acute success or long-term success in preventing aFib recurrence (i.e., acute or long-term failure of ablation).

[0075] In order to determine / generate one or more expected results of the procedure, the optimization engine 101 analyzes the data to build and train the model. The optimization engine 101 can inject data into the model, such as a gold standard, where the user has identified gaps and good ablations, and the model outputs the most prominent parameters that predict gaps / good ablations. The optimization engine 101 can use supervised methods, unsupervised methods, and / or deep learning solutions to build and train the model, as described herein. That is, the optimization engine 101 considers all available data / inputs when building and training the model (as described in box 320). Building / training can be considered as the ML stage of the optimization engine 101. For example, the optimization engine 101 collects 10,000 cases with twelve (12) months of follow-up information, each of which is associated with a single class of redo / long-term success, and the back propagation algorithm (as described herein) minimizes the loss function to train and learn all weights in the neural network. Then, the optimization engine 101 uses the model to analyze the data / input (e.g., whether there is an ablation gap) to determine whether the mapping and ablation procedures are successful. The model may analyze success across one or more scenarios, such as different patient groupings (eg, based on age, gender, health, etc.) and different procedure groupings (eg, based on type of procedure).

[0076] For example, the optimization engine 101 is trained by using previous or old ablation procedures to learn different scenarios over time. In this regard, the optimization engine 101 generates training data sets (from previous or old ablation procedures) for different patient / procedure groupings corresponding to one or more scenarios. Previous or old ablation procedures include previous ablation treatments, locations, etc., as well as cardiac information from subsequent mapping procedures. Patient / procedure groupings include similar cases such as alignment with similar patient demographics (e.g., patients with the same age or blood pressure) and / or procedure conditions (e.g., procedures in the same atrial region). The generated training data set provides for each patient or procedure grouping whether an ablation gap occurs and whether a redo operation is performed, which are incorporated into the optimization engine 101.

[0077] According to one or more embodiments, the optimization engine 101 utilizes the long-term results of the patient 125 to train the model (and the system 100) by informing / guiding / telling the model which ECG data, etc. (e.g., any biometric data relative to the long-term results) may or may not be healthy. In addition, the ECG data, etc. can be used to train the weights of the neural network using a back-propagation method (e.g., a back-propagation algorithm as described herein).

[0078] For ease of understanding, Figures 4 to 5A , Figure 5B The construction and training of the optimization engine 101 and its models are described. Where appropriate, reference is made to Figures 1 to 3 conduct Figures 4 to 5A , Figure 5B Description.

[0079] Figure 4 An ML / AI system 400 is shown according to one or more embodiments. The ML / AI system 400 includes data 410, machines 420, models 430, results 440, and (underlying) hardware 450.

[0080] Machine 420, model 430, and hardware 450 may represent Figure 1 to Figure 2 The hardware 450 may also represent aspects of the optimization engine 101 (e.g., the ML / AI algorithms therein). Figure 1 The catheter 110, Figure 1 Console 160 and / or Figure 2 device 204. Generally speaking, the ML / AI algorithm of the ML / AI system 400 (e.g., Figure 1 to Figure 2 4) uses data 410 to operate relative to hardware 450 to train machine 420, build model 430, and predict results 440. For example, machine 420 operates or is associated with a controller or data collection associated with hardware 450.

[0081] Data 410 may be data being generated, or output data associated with hardware 450. For example, data 410 may include biometric data from previous medical records, such as anatomical data (e.g., anatomical reconstruction, CT, MRI, ultrasound, etc.), electrical data (e.g., body surface and IC ECG signals), contact force data, ablation parameter data, tissue touch data, respiratory data, fluid data, case-specific data, location, time between original case and redo data, and other determining factors. Data 410 may also include currently collected data, historical data, or other data from hardware 450; a case summary by physician 115; additional imaging data; may include measurements during a surgical procedure (e.g., an ablation procedure) and may be associated with the results of the surgical procedure; may include data collected and associated with the results of a cardiac procedure. Figure 1 and may be associated with hardware 450. According to one or more embodiments, data 410 may include patient and / or procedure parameters associated with mapping and ablation procedures (e.g., patient characteristics, tissue characteristics, and other data points in the indexing procedure), patient demographics, information / data associated with prior electrophysiology procedures, and acute / long-term outcomes for patient 125. Data 410 may be divided by machine 420 into one or more subsets.

[0082] Model 430 is built on data 410. Building model 430 may include physical hardware or software modeling, algorithmic modeling, etc. that attempts to represent data 410 (or a subset thereof). In some aspects, the building of model 430 is part of a self-training operation performed by machine 420. Model 430 may be configured to model the operation of hardware 450 and to model data 410 collected from hardware 450 to predict an outcome 440 achieved by hardware 450. Predicted outcome 440 may utilize a trained version of model 430. For example and to increase understanding of the present disclosure, in the case of a heart, if a temperature between 36.5°C and 37.89°C (i.e., 97.7 degrees Fahrenheit and 100.2 degrees Fahrenheit) during a procedure produces a positive outcome from a cardiac procedure, the outcome 440 may be predicted using these temperatures in a given procedure. Thus, using the predicted outcome 440, machine 420, model 430, and hardware 450 may be constructed accordingly.

[0083] The machine 420 trains the model 430, such as with respect to the hardware 450 and the data 410. The training may also include analyzing and correlating the collected data 410. For example, the machine 420 may train the model 430 to determine the Figure 1 According to another embodiment, the training machine 420 and the model 430 may include a Figure 1 The optimization engine 101 utilizes one or more subsets for self-training. In this regard, Figure 1 The optimization engine 101 learns point-by-point detection case classification.

[0084] In order for the ML / AI system 400 to operate with respect to the hardware 450, analyze the data 410, perform the build / training, and predict the results 440, the ML / AI algorithms therein may include a neural network, an autoencoder, and a back-propagation algorithm. A neural network is a network or circuit of neurons, or in the modern sense, an artificial neural network (ANN) composed of artificial neurons or nodes or cells. An autoencoder is an automatic self-training algorithm. The back-propagation algorithm is used to train a feed-forward neural network for supervised learning.

[0085] At decision box 360, the optimization engine 101 generates one or more predictions of success for the current procedure (e.g., the current ablation procedure). For example, the optimization engine 101 includes receiving current of the current ablation procedure and executing the generated model to predict success. Generally speaking, the present procedure or the current ablation procedure can be a current or real-time ablation procedure. The execution can be considered as the AI ​​phase of the optimization engine 101. The one or more predictions of success may include the acute and / or long-term results of the current ablation procedure and the necessity of a redo procedure relative to one or more ablation gaps. According to one or more embodiments, the optimization engine 101 generates a score at the end of the current ablation procedure. The score can be in the range of 0 to 1, where one is the best. Then, based on the score (e.g., the optimization engine 101 outputs 0.8), the physician can search again around the PV, provide additional ablations, and run the optimization engine 101 again. The optimization engine 101 generates a second score (e.g., a score of 0.89) at the end of the second iteration of the current ablation procedure, and the physician 115 decides whether to stop or perform additional ablations, tests, and / or challenges (e.g., adenosine challenges). Thus, the technical effects, advantages, and benefits of the optimization engine 101 include the ability to inform the physician 115 of the possibility that the current ablation procedure can be ended without redoing, thereby reducing the risk to the patient 125 by increasing the probability of success of the current ablation procedure and / or eliminating unnecessary subsequent procedures.

[0086] According to one or more embodiments, the optimization engine 101 analyzes the biometric data of the current ablation procedure using the model and the expected results of the mapping and ablation procedures to determine one or more predictions of success. That is, the optimization engine 101 can be used during the current ablation procedure to receive inputs that are unique to the patient 125 undergoing the current ablation procedure. Since the model of the optimization engine 101 has been built and trained at box 340, the optimization engine 101 can process the model and these current patient inputs to identify ablation gaps and generate new ablation targets (e.g., potential locations for the physician 115 to consider to prevent acute or long-term failure and the probability of success). The optimization engine 101 can also generate predictions about the success and / or necessity of these new ablation targets.

[0087] According to one or more embodiments, Figure 5A An example of a neural network 500 is shown, and Figure 5B A block diagram of a method 501 performed in a neural network 500 is shown. The neural network 500 operates to support the implementation of the ML / AI algorithms described herein (e.g., as described by Figure 1 to Figure 2 The neural network 500 may be implemented in hardware (such as Figure 4 implemented in machine 420 and / or hardware 450).

[0088] In an exemplary operation, Figure 1 The optimization engine 101 includes collecting data 410 from hardware 450. In the neural network 500, the input layer 510 is composed of multiple inputs (e.g., Figure 5A 410 ). With respect to block 520 of method 501 , input layer 510 receives inputs 512 and 514 . Inputs 512 and 514 may include biometric data. For example, the collection of inputs 512 and 514 may be aggregating biometric data (e.g., BS ECG data, IC ECG data, and ablation data, along with catheter electrode position data) recorded from one or more procedures of hardware 450 into a data set (as represented by data 410 ). According to one or more embodiments, inputs 512 and 514 may include twelve (12) input ECG leads of system 100 .

[0089] In accordance with one or more embodiments, inputs 512 and 514 may include a BS ECG before a first procedure, a twelve (12) lead BS ECG after the procedure (e.g., if in NSR), categorical / numeric information about the patient (e.g., gender, left atrial volume, age, body mass index, as described herein), and outcomes (e.g., acute and / or long-term), such as categorical / numeric information indicated by an ECG recording or an actual ECG signal from a link or other device, relative to feature extraction of a training set.

[0090] At block 525 of method 501, neural network 500 encodes inputs 512 and 514 using any portion of data 410 and one or more expected results of procedures generated by ML / AI system 400 to produce a latent representation or data encoding. The latent representation includes one or more intermediate data representations derived from multiple inputs. According to one or more embodiments, the latent representation is composed of Figure 1 The element-level activation function (e.g., sigmoid function or trimmed linear unit) of the optimization engine 101 is generated. Figure 5A As shown, inputs 512 and 514 are provided to a hidden layer 530 depicted as including nodes 532, 534, 536, and 538. Neural network 500 performs processing via hidden layer 530 of nodes 532, 534, 536, and 538 to exhibit complex global behavior determined by the connections between processing elements and element parameters. Thus, the transition between layers 510 and 530 can be considered an encoder stage that takes inputs 512 and 514 and transmits them to the deep neural network (within layer 530) to learn some smaller representation of the inputs (e.g., a resulting latent representation).

[0091] The deep neural network can be a CNN, a long short-term memory neural network, a fully connected neural network or a combination thereof. The encoding provides a dimensionality reduction of inputs 512 and 514. Dimensionality reduction is a process of reducing the number of random variables (of inputs 512 and 514) considered by obtaining a set of primary variables. For example, dimensionality reduction can be a feature extraction of data (e.g., inputs 512 and 514) from a high-dimensional space (e.g., more than 10 dimensions) to a low-dimensional space (e.g., 2 to 3 dimensions). The technical effects and benefits of reducing the dimensions include reducing the time and storage space requirements of inputs 512 and 514, improving the visualization of inputs 512 and 514, and improving the parameter interpretation for machine learning. The data conversion can be linear or nonlinear. The operations of receiving (box 520) and encoding (box 525) can be considered as the data preparation part of the multi-step data manipulation performed by the optimization engine 101.

[0092] At block 545 of method 510, neural network 500 decodes the latent representation. The decoding stage takes the encoder output (e.g., the resulting latent representation) and attempts to reconstruct some form of input 512 and 514 using another deep neural network. In this regard, nodes 532, 534, 536, and 538 are combined to produce output 552 in output layer 550, as shown in block 560 of method 510. That is, output layer 590 reconstructs inputs 512 and 514 in a reduced dimension, but without signal interference, signal artifacts, and signal noise. Examples of output 552 include cleaned biometric data (e.g., a cleaned / denoised version of IC ECG data, etc.). According to one or more embodiments, a CNN autoencoder for twelve (12) lead BS ECG is used as neural network 500 relative to the deep learning solution of optimization engine 101. The CNN autoencoder can be a deep CNN that is pre-trained or trained as described herein. Thus, according to one or more embodiments, output 552 includes an ECG reconstructed from data provided by a twelve (12) lead BS ECG. Technical effects and benefits of cleaned biometric data include the ability to more accurately monitor, diagnose, and treat any number of various diseases.

[0093] At box 380, the optimization engine outputs an ablation recommendation based on one or more predictions of success. According to one or more embodiments, the optimization engine 101 provides one or more user interfaces on the display 165 showing mapping of the current ablation procedure and the ablation recommendation. The ablation recommendation includes an area for ablation based on one or more predictions of success and the probability of redoing the procedure. In this way, the optimization engine 1010 provides the physician 115 with whether redoing any procedure is likely to have a positive outcome, and provides the correct / suggested course of action for such determination. Therefore, the technical effects, advantages and benefits of the optimization engine include reducing risks to the patient by increasing the probability of success of the next procedure and / or eliminating unnecessary subsequent procedures.

[0094] Figure 6 A method 600 according to one or more exemplary embodiments is shown. Figure 1 and / or Figure 2 The method 600 is described by way of example and for ease of explanation with respect to an ablation procedure. The method 600 identifies ablation gaps and provides predictions of success through multi-step manipulation of data that improves arrhythmia diagnosis and treatment.

[0095] In general, the success rate of atrial arrhythmia treatment via catheter ablation is not always completely successful. For example, a certain portion of patients (e.g., 5%-40%) experience atrial arrhythmias in the subsequent year. These patients may suffer from reconnections in the ablation chain, which requires repeat ablation at a location that was ablated in the past, or may suffer from disease recurrence, which originates from drivers that were not targeted for ablation in the first procedure. Method 600 attempts to avoid unnecessary subsequent procedures while identifying ablation gaps and recommendations to increase the probability of success of necessary subsequent procedures.

[0096] The method 600 begins at block 605, where the optimization engine 101 receives input from prior medical records (eg, prior mapping and ablation procedures). In one practical example, the optimization engine 101 analyzes prior medical records with and without redo procedures to derive data 410 and performance metrics as input.

[0097] According to one or more embodiments, in the treatment of atrial or ventricular arrhythmias, the optimization engine 101 places ablation applications adjacent to each other in a continuous manner to create a continuous ablation line, wherein gaps in the line due to ablation lesions not being deep enough or close enough to each other create disruptions in the flow of electricity through the ablation chain, thereby rendering the ablation chain ineffective. These disrupted areas are very difficult to find and identify manually, which results in longer procedures with lower success rates.

[0098] According to one or more embodiments, data 410 and performance metrics can be obtained via a map with ablation lesion chains, an anatomical map with wall depth information or an anatomical reconstruction and / or an electrical map. In order to support the prediction of method 600, the optimization engine 101 can utilize data from previous ablations, such as ablation sites, ablation indices, and anatomical maps from both the initial ablation study and any redo procedures. Data 410 and performance metrics can also be derived and collected using backup studies. The data 410 and performance metrics can be compared with the redo position before redoing. In some embodiments, data 410 and performance metrics (e.g., for training) can be obtained from the magnetic field around the patient 125 from the magnetic sensor included in the catheter 110. Data 410 and performance metrics can also be obtained using ACL features, electrode sensors using signal filter algorithms, grids / images, registration algorithms, and ablation index parameters and algorithms.

[0099] At block 610, the optimization engine 101 is trained. In this regard, the optimization engine 101 creates / builds a model that can be used in real-time protocols to identify potential areas where the physician 115 should take a second look and revalidate those areas to avoid protocol failure, protocol extension, or redoing the protocol.

[0100] According to one or more embodiments, the acquired data 410 and performance metrics (e.g., original case data, IC ECG and location, additional imaging data, and physician 115's case summary) can be input into an unsupervised algorithm, a deep learning algorithm, an autoencoder, and / or a back-propagation algorithm for analysis by the optimization engine 101. The data 410 and performance metrics can be pre-processed to extract relevant features for the task of predicting the success rate of redoing both for a specific patient and a subgroup of similar patients, and assessing the risk of a patient needing a redo procedure. The optimization engine 101 can analyze the data of potentially missing ablation steps in an attempt to determine whether the ablation will need to be redone. That is, by having data 410 and performance metrics about the results, as well as the procedures that require a redo procedure, and the location in the redo procedure where the ablation is placed to treat the patient, the optimization engine 101 can know whether a particular ablation procedure will need to be redone.

[0101] Figure 7 A graph 700 is shown that includes one or more aspects of an ML / AI algorithm of the optimization engine 100. As shown, data 712, 714, and 716 may be input into one or more autoencoders 722 and 724 and trees 730 and 750 (which represent one or more ML / AI algorithms) to output a probability of redo 780. According to one or more embodiments, additional inputs may include results (e.g., acute and / or long-term), such as categorical / numeric information indicated from an ECG recording or an actual ECG signal from a link or other device.

[0102] Data 712 may include a baseline recording of a twelve (12) lead ECG and / or a signal from a fixed catheter (such as a coronary sinus (CS) catheter). Data 714 may include post-ablation procedure data. According to one or more embodiments, data 712 and data 714 are fed through a pre-trained CNN autoencoder (e.g., autoencoders 714 and 716 to provide a training data set).

[0103] At block 620, the optimization engine 101 receives data relative to the performance of the ablation procedure for the current patient (e.g., patient 125). The optimization engine 101 presents data relative to the performance of the current ablation procedure as described below. For example, during a PV isolation procedure, anatomical data and electrical data are acquired in a significant portion of the atrium. This information may provide an indication to estimate whether additional ablation steps will be needed based on the model and optimization engine 101 analysis of block 630.

[0104] At block 630, the optimization engine 101 is executed. For example, the optimization engine 101 compares the current data to the model to predict the success (acute or long-term) of the current ablation procedure. Block 630 may include sub-blocks 640 and 650. At sub-block 640, the optimization engine 101 analyzes the data to determine the ablation gap. At sub-block 650, the optimization engine 650 utilizes the ablation gap to predict the success of the ablation procedure.

[0105] According to one or more embodiments, the optimization engine 101 analyzes the current data relative to the data 410, the performance metrics, and the model to determine potential ablation gaps. Figure 7 , data 716 may be current data including classification information such as gender, weight, body mass index (BMI), atrial volume, left atrial volume, CHADS or CHADS2 (i.e., a score for determining treatment of atrial fibrillation patients at risk of stroke), etc. Thus, data 712, 714, and 716 are analyzed together by trees 730 and 750. Tree 730 may be a fully connected neural network with ten (10) hidden layers to which such pre-ablation procedure and post-ablation procedure data 712 and 714 and classification data 716 are fed. The output of tree 730 may then be fed to tree 750 with a single hidden layer (which has a single neuron) at the output of redo probability 780.

[0106] Once the current data is analyzed, the optimization engine 101 uses the determination and model of potential ablation gaps to predict the acute and long-term success of the ablation procedure. For example, a prediction of whether a re-procedure may be necessary may be obtained by learning the parameters of the current patient 125 (e.g., learning patient and tissue characteristics through an indexing procedure), comparing procedure cases for similar patients, such as via an unsupervised algorithm, a deep learning algorithm, an autoencoder, and / or a back-propagation algorithm of the optimization engine. In addition to patient and tissue characteristics, the optimization engine 101 may also learn additional ablations added to close acute reconnections, data points for corresponding re-procedures performed, and locations where ablations were performed in the re-procedure to terminate arrhythmias, as well as other data points. Once learned, the optimization engine 101 may predict which are the locations that may cause acute or long-term failures. The optimization engine 101 may suggest resolving any failures in the re-procedure and / or specifically emphasize any failures in the current ablation procedure. In this regard, the optimization engine 101 may identify ablation areas outside of the vein or areas that are susceptible to reconnection. The optimization engine 101 may be applicable to arrhythmias other than aFib.Analyzing data from a redo procedure may help understand whether a real-time ablation of a gap may be formed later (eg, tissue recovery), and may visually indicate to the physician 115 at that location.

[0107] At box 670, the optimization engine 101 provides an output. The output can be provided on a display 165 or the like via one or more user interfaces described herein. The output can include one or more ablation recommendations based on the success of each ablation procedure for the patient 125. For example, the optimization engine 101 outputs to the physician 115 potential locations that may need to be ablated based on the prediction to avoid electrical reconnection in the ablation chain. The optimization engine 101 can also output additional potential locations to be ablated in order to avoid electrical reconnection.

[0108] According to one or more embodiments, the optimization engine 101 provides the physician 115 with the likelihood of needing to redo the procedure based on the prediction as an output. Figure 7 , the redo probability 780 can be a percentage, a fraction, a value expressed on a scale (e.g., from 0 to 1, where 0 is the lowest probability of redo). According to one or more embodiments, the optimization engine 101 can infer the likelihood of redo for the patient based on the results of an ablation set (e.g., a training data set). As described herein, an exemplary training data set may include records of patients undergoing a first ablation treatment, as well as optional clinical category patient information, and / or status of aFib without subsequent mapping procedures. That is, the optimization engine 101 provides the physician with an indication 115 of whether the current ablation is good enough or whether the current ablation may have potential gaps that will result in a redo based on previous medical records, and indicates where these gaps may be located on the patient's 3D cardiac map.

[0109] At box 690, the optimization engine 101 receives feedback. In general, the feedback may include any information provided directly to the optimization engine 101 by the physician 115 before, during, or after the current ablation procedure. The feedback may be provided on the display 165, etc. via one or more user interfaces described herein. According to one or more embodiments, when the physician 115 begins an ablation procedure, the information obtained before and during the procedure may be used to determine whether a redo procedure may be necessary. This information may be used to further train the model and the optimization engine 101. The ML / AI of the optimization engine 101 may also be used to analyze this information in real time to indicate to the physician 115 whether additional ablations or redo procedures may be necessary or likely to occur during the current ablation procedure. That is, because it is desired to prevent redos based on previous study cases, any real-time indication may help the physician 115 focus on specific areas to examine and verify these areas to observe that the ablation is sufficient.

[0110] According to one or more embodiments, the optimization engine 101 can track the procedure workflow (e.g., in atrial fibrillation), identify the anatomical reconstruction and mapping phase, the insertion of the catheter 110 into the pulmonary veins, the ablation phase, the wait time for verification, repeated ablations in position, etc., and learn the workflow and process patterns. In an embodiment specific to aFib, the optimization engine 101 can identify the insertion of the catheter 110 into the pulmonary veins for the purpose of verifying isolation, and identify whether an active signal is measured on the catheter 110.

[0111] If an active signal is measured, the optimization engine 101 can identify and alert the earliest activation on the DX catheter that may be related to electrical damage. The optimization engine 101 can then The area most likely to be the cause of the damage is marked on the system (e.g., marked with an arrow, via coloring on the map according to the likelihood of the area causing the damage, or in any other manner, or any other possible presentation). Thus, through ML / AI, the optimization engine 101 enables the ability to identify the workflow stage, the stage at which the operator wishes to verify the acute success of the ablation, and / or the link between the earliest signal on the catheter 110 and a specific location on the anatomy.

[0112] Additionally, during the triangulation process, any acquired data may indicate where the source point of the arrhythmia may be and which points are most informative for validating and finding the source point in the most valid data. The optimization engine 101 learns from previous maps, anatomy, and mapping sequences to recommend the best course of action at each point.

[0113] Thus, during an ablation procedure, the optimization engine 101 can utilize any acquired data to present areas for ablation to the physician 115 where the physician 115 can have a greater chance of success and less need to redo the procedure. For example, the optimization engine 101 can read the location of the catheter 110 in the heart 120 from the moment the catheter 110 is inserted into the vein, and generate locations on the screen for recommended ablations based on the executed ML algorithm and the prediction of the results. Thus, the optimization engine 101 knows where to perform ablation during the current procedure based on the ablation gaps from the previous case history and the current data used to project the location for the physician 115, which will have less need to redo the procedure.

[0114] With reference to the ML / AI algorithms described in this article, neural networks, autoencoders, and back-propagation algorithms are now described.

[0115] ANN involves a network of processing elements (artificial neurons) that can exhibit complex global behaviors determined by the connections between the processing elements and the element parameters. These connections of a network or circuit of neurons are modeled as weights. Positive weights reflect excitatory connections, while negative values ​​represent inhibitory connections. The input is modified by the weights and summed using linear combinations. The activation function can control the amplitude of the output. For example, the acceptable output range is typically between 0 and 1, or the range can be between -1 and 1. In most cases, ANN is an adaptive system that changes its structure based on external or internal information flowing through the network.

[0116] In more practical terms, a neural network is a nonlinear statistical data modeling or decision-making tool that can be used to model complex relationships between inputs and outputs or to find patterns in data. Therefore, ANNs can be used for predictive modeling and adaptive control applications while being trained via a data set. Self-learning resulting from experience can occur within the network, which can draw conclusions from complex and seemingly unrelated groups of information. The practicality of artificial neural network models lies in that they can be used to infer functions from observations and can also be used to use the functions. Unsupervised neural networks can also be used to learn representations of inputs that capture significant features of the input distribution, and recent deep learning algorithms can implicitly learn distribution functions of observed data. Learning in neural networks is particularly useful in applications where the complexity of the data (e.g., biometric data) or tasks (e.g., monitoring, diagnosing, and treating any number of various diseases) makes it impractical to manually design such functions.

[0117] Neural networks can be used in different fields. Therefore, the ML / AI algorithms therein may include neural networks, which are usually divided according to the tasks to which they are applied. These divisions tend to belong to the following categories: regression analysis (e.g., function approximation), including time series prediction and modeling; classification, including pattern and sequence recognition; novelty detection and sequential decision making; data processing, including filtering; clustering; blind signal separation and compression. For example, application areas of ANNs include nonlinear system identification and control (vehicle control, process control), game playing and decision making (backgammon, chat, competition), pattern recognition (radar systems, facial recognition, object recognition), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis and treatment, financial applications, data mining (or knowledge discovery in databases, "KDD"), visualization, and email spam filtering. For example, semantic features of patient biometric data emerging from medical procedures can be created.

[0118] According to one or more embodiments, the neural network can implement a long short-term memory neural network architecture, a convolutional neural network architecture (CNN), or other similar architectures. The neural network can be configured with respect to: multiple layers, multiple connections (e.g., encoder / decoder connections), regularization techniques (e.g., dropout); and optimization features.

[0119] The LSTM neural network architecture includes feedback connections and can process single data points (e.g., such as images) as well as entire data sequences (e.g., such as speech or video). A unit of the LSTM neural network architecture can consist of a unit, an input gate, an output gate, and a forget gate, where the unit remembers a value over an arbitrary time interval and the gate regulates the flow of information into and out of the unit.

[0120] The CNN architecture is a shared weight architecture with translation invariance characteristics, where each neuron in one layer is connected to all neurons in the next layer. The regularization techniques of the CNN architecture can exploit hierarchical patterns in the data and use smaller and simpler patterns to assemble more complex patterns. If a neural network implements a CNN architecture, other configurable aspects of the architecture may include the number of filters at each level, kernel size, and the number of kernels per layer.

[0121] The autoencoder is an automatic self-training algorithm. In some cases, the autoencoder includes a training algorithm that implements a deep learning training loss function (and more specifically, an autoencoder clinical weighted MSE loss function). In addition, the autoencoder can be executed in one or more modes. For example, the first mode may include building a dedicated graphical user interface including one or more filters. The dedicated GUI provides the ability to manually filter out noise components based on a set of predefined filters (the original data signal is usually recorded with noise). In this way, the autoencoder undergoes at least two groups of signals, such as the original signal containing noise and the noise reduction signal for training the autoencoder. The second mode may include recording noise in a controlled environment and adding noise to clean signal data (e.g., a clean version from a previous stage). Noise may include at least one of power line noise, contact noise, deflection noise, Fluro noise, and ventricular far field.

[0122] An autoencoder can reconstruct an input from a corrupted version of itself by forcing the hidden layers to discover more robust features and prevent relearning a particular identity. In this regard, the autoencoder forces the hidden layers therein to discover more robust features (i.e., useful features that will constitute a better high-level representation of the input) and prevents them from learning characteristics (i.e., always returning to the same value). In addition, the autoencoder encodes the input (e.g., to preserve information about the input) and reverses the effects of a corrupting process that is randomly applied to the input of the autoencoder. For example, the autoencoder clinically weighted MSE loss function is a multi-step data manipulation of an electrical signal to detect or quantify or detect high frequency regions in the signal, and then uses the autoencoder clinically weighted MSE loss function to enhance signal reconstruction around atrial activity.

[0123] In deep learning, the backpropagation algorithm is used to train a feed-forward neural network for supervised learning. The adjective "deep" in deep learning comes from the use of multiple layers in the network. The backpropagation algorithm works by calculating the gradient of the loss function with respect to each weight via the chain rule. The weights are updated to minimize the loss function. Additionally, gradient descent or variants such as stochastic gradient descent can be used.

[0124] Figure 8 A method 800 of a gap finder according to one embodiment is shown. The parameters of each ablation site acquired during the ablation procedure can be used to generate a gap index (GI) for that site. A high GI indicates a high probability of a gap. The site parameters are the ablation index (AI), average temperature (T), quality of stability (QS), and distance to the nearest stable site (DS).

[0125] The ablation index (AI) can be derived from the force, power and time of ablation of a site. The AI ​​is defined in Equation 1:

[0126]

[0127] QS can be derived from a site stability algorithm. The site stability algorithm is explained in more detail in U.S. patent application 17 / 188,844, "PROBE-CAVITY MOTION MODELING," filed on March 1, 2021, by Meir Bar-Tal, Erez Silberschein, Liron Shmuel Mizrahi, Alona Sigal, and Aharon Turgeman, which is incorporated herein by reference. DS can be determined using a site stability algorithm. The stability quality index is a function of the average distance of the catheter from the center of mass of the site. Very stable ablations may provide low stability index values, and less stable ablations may provide high stability index values.

[0128] The gap index at the ablation site is given by Equation 2:

[0129] GI = f(AI, T, QS, DS) Equation 2

[0130] Where f() is a function of the parameters listed above. ML can be used to determine the probability of a gap and / or to determine the relationship between the above parameters and the probability of a gap.

[0131] like Figure 8 As shown, the method includes: after inserting an ablation catheter into a desired area at 810, using the ablation catheter to ablate multiple locations at the area at 820. Once all or desired locations have been ablated, data for ablation is collected at each location at 830, and a processor calculates a GI for each location at 840. The processor highlights ablation locations with high GI (i.e., those sites with a high probability of becoming gaps) on a map or depiction of the ablation at 850. Displaying high-probability gap locations to the physician reduces the time required for the physician to search for gaps.

[0132] As will be appreciated, relationships between various site parameters may be important. Specifically, relationships may exist within and between various parameters of AI, T, QS, and DS. The present systems and methods involve using parameters to verify or validate other parameters to ensure high quality ablation and calculation of GI. Details regarding the combination of important parameters and how these inferences are made are presented below. For example, the set of parameters (position, contact force, temperature, impedance) may all need to be met in order for the ablation to be considered successful. In the following Figures 10 to 14 In the examples of , various combinations of these four parameters are lacking and this results in poor or questionable ablations as described.

[0133] Figures 9 to 14Graphs of data associated with the above parameters are provided to demonstrate the importance and relationships associated with the parameters. Fig. 9 This provides a general framework for describing the data and provides a basis for future Figures 10 to 14 The framework for the analysis provided in .

[0134] Specifically, Fig. 9 A set of general graphs 900 are shown. In the first graph in the set, the left axis plots the location of the XYZ position 910 as seen in the CARTO system. For example, the data may include filtering, such as heartbeat filtering. The right axis of the first graph in the set represents the respiration signal of the reference plot 920.

[0135] As shown in the second graph, the left axis includes temperature referenced to the plot of maximum temperature 930 and referenced to the plot of six temperatures of the QDOT 940. The right axis of the second graph provides an impedance scale referenced to the plot of impedance 950.

[0136] As shown in the third graph in the set of graphs, the power scale is set on the left and the current scale is set on the right. As shown, the traces of current and power have only slight deviations.

[0137] As shown in the fourth graph in the set of graphs, the force scale for the plot of reference force 960 is on the left.

[0138] Usually, if Fig. 9 The above parameters are included in the curve graphs of the data to demonstrate the importance and relationship associated with the parameter.

[0139] Fig.10 As shown above relative to Fig. 9 A set of graphs 1000 of parameters during an ablation procedure as described. The set of graphs 1000 shows a configuration in which position is stable and contact force is stable. Specifically, with respect to position, the first graph in the set of graphs provides a graph of positioning that indicates small changes of a few millimeters during the plot. With respect to contact force, the fourth graph in the set of graphs indicates that the contact force varies slightly on the scale of a few grams. The third graph in the set of graphs shows a graph of contact force with respect to position. Fig. 9 1010. The substantially consistent power and current provided in the catheter. With respect to the second portion of the set of graphs, a temperature drop and impedance rise are shown. The temperature drops 1010 by more than about 5°C for a short period of time, and at the same time the impedance rises 1020 by more than about 5Ω. This combination of a temperature drop and impedance rise may indicate that the catheter is not heating the same point on the tissue.

[0140] Fig.11 Shows Fig. 9A set of graphs 1100 of parameters of the present invention are shown. The set of graphs 1100 shows stable positions. In particular, the first graph in the set of graphs provides a graph of positioning relative to position, which indicates small changes of a few millimeters during the plotting period. The set of graphs 1100 indicates that low applied contact forces 1110 applied to the tissue result in low temperature rise and associated impedance drop.

[0141] Fig.12 Shows Fig. 9 A set of graphs 1200 of parameters of the catheter. The set of graphs 1200 indicates that sliding of the catheter during the ablation procedure resulted in low stability quality 1210. Specifically, the first graph in the set of graphs provides a graph of positioning with respect to position that indicates large changes during the plot. While the force in the fourth graph in the set of graphs 1200 proved to be acceptable, the temperature rise 1220 in the second graph in the set of graphs 1200 was of poor quality, which may be a result of poor positional stability.

[0142] Fig.13 Shows Fig. 9 A set of graphs 1300 of parameters. The force in the fourth graph in the set of graphs 1200 is shown to be acceptable. The power and current in the third graph in the set of graphs 1300 represent a duration of approximately four seconds. The set of graphs 1300 shows that there was sufficient average force during the ablation procedure (the fourth graph in the set of graphs) and an ablation duration of four seconds (the third graph in the set of graphs), but the indicated site stability algorithm indicates that only 2.5 of the four seconds were sufficiently stable 1310. From this information, it can be seen that even if the duration of the ablation is appropriate, the smaller amount of mass stability for 2.5 seconds is not sufficient for successful ablation. This is further illustrated in the effect of instability on temperature increase 1320.

[0143] Fig.14 Shows Fig. 9 A set of graphs 1400 of parameters of the ablation protocol. A set of graphs 1400 shows stable position (within thresholds) and stable contact force during an ablation procedure. Specifically, the first graph in the set of graphs provides a graph of positioning relative to position, which indicates small changes of a few millimeters during the plot. The force in the fourth plot in the set of graphs 1400 is shown to be acceptable. A temperature drop 1410 and an impedance increase 1420 are shown in the second graph in the set of graphs 1400. This temperature drop and impedance increase may indicate that the ablation is not heating the same point on the tissue.

[0144] Figures 9 to 14The relationship between various site parameters within and between various parameters of AI, T, QS and DS is shown. It should be understood that other parameters may also be used.

[0145] Especially in Fig.11 In FIG. 1 , the graph indicates that an ablation duration of 4 seconds can be governed using other parameters to achieve an actual (or effective time) of 2.5 seconds of ablation, which is lower than the time required for ablation. Fig.10 and Fig.14 Cases are further illustrated where position and force are stable, but temperature drops and impedance rises indicating that ablation is occurring at different points.

[0146] Logistic regression may be performed. As will be appreciated, other analyses and regressions described with respect to modeling may be used. Using the input of data calculated on the multiple variables described, using criteria, parameters with significance and their corresponding weights may be determined to predict gaps as described above.

[0147] The flow charts and block diagrams in the accompanying drawings illustrate the possible specific implementation architecture, functions and operations of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram may represent a module, fragment or part of an instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the function indicated in the box may not occur in the order indicated in the accompanying drawings. For example, depending on the function involved, the two boxes shown in succession may actually be executed substantially simultaneously, or the box may sometimes be executed in the opposite order. It should also be noted that each box in the block diagram and / or the flow chart diagram and the combination of the boxes in the block diagram and / or the flow chart diagram can be implemented by a system based on dedicated hardware that performs a specified function or action or by a combination of dedicated hardware and computer instructions.

[0148] Although the features and elements are described above in detail, it will be appreciated by those skilled in the art that each feature or element may be used alone or in any combination with other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. As used herein, a computer-readable medium should not be understood as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electrical signal transmitted by wire.

[0149] Examples of computer-readable media include electronic signals (transmitted via a wired or wireless connection) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, registers, cache memories, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, optical media such as compact disks (CDs) and digital versatile disks (DVDs), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), static random access memories (SRAMs), and memory sticks. A processor associated with software can be used to implement a radio frequency transceiver used in a terminal, a base station, or any host computer.

[0150] The terms used herein are only for the purpose of describing specific embodiments and are not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms "a", "a", and "the / said" include plural references. It should also be understood that the terms "comprise" and / or "comprising" when used in this specification specify the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0151] The description of various embodiments herein is presented for the purpose of illustration, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and essence of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, practical applications or technical improvements over technologies available on the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A computer-implemented method, the computer-implemented method comprising: An optimization engine executed by one or more processors receives data including performance metrics of mapping and ablation procedures; generating, by the optimization engine, an expected outcome of a procedure for the mapping and ablation procedure based on the data; generating, by the optimization engine, one or more predictions of success for a current ablation procedure using the expected outcome of the procedure; performing an ablation and calculating a gap index for the ablation; as well as The gap index of the ablation is output.

2. The method according to claim 1, wherein: Performing an ablation involves ablating a series of adjacent locations to create a ring or line of ablated tissue.

3. The method according to claim 1, wherein: The ablation performed includes providing one or more ablations to prevent the transmission of electrical waves.

4. The method according to claim 1, wherein: The one or more successful predictions search for gaps in the ablation ring or ablation line.

5. The method according to claim 1, wherein: The higher the gap index, the higher the probability that a gap exists in the ablation.

6. The method according to claim 1, wherein: The data includes at least an ablation index derived from at least one of force, power and time of ablation of the site.

7. The method according to claim 1, wherein: The data include at least a mean temperature or a maximum temperature of the ablation at a site.

8. The method according to claim 1, wherein: The data includes at least a stability quality derived from a site stability algorithm.

9. The method according to claim 1, wherein: The data includes at least the distance to the nearest stable site using a site stability algorithm.

10. The method according to claim 1, wherein: The gap index of the ablation is a function of at least the ablation index, an average temperature of the ablation, a stability quality, and a distance to a nearest stable site.

11. The method according to claim 1, wherein: A gap index is calculated for each location where ablation is performed.

12. The method of claim 1, further comprising outputting a map of ablation sites, the map highlighting ablation locations having a high gap index.

13. The method according to claim 1, wherein: A high gap index is determined by thresholding the gap index.

14. A system, comprising: an input / output (I / O) device for receiving data from a catheter configured to perform ablation on a patient's heart; and a memory and a processor operable to process the received data and to: An optimization engine executed by one or more processors receives data including performance metrics of mapping and ablation procedures; generating, by the optimization engine, an expected outcome of a procedure for the mapping and ablation procedure based on the data; generating, by the optimization engine, one or more predictions of success for a current ablation procedure using the expected outcome of the procedure; performing an ablation and calculating a gap index for the ablation; as well as The gap index of the ablation is output.

15. The system of claim 14, wherein: Performing an ablation involves ablating a series of adjacent locations to create a ring or line of ablated tissue.

16. The system of claim 14, wherein: The ablation performed includes providing one or more ablations to prevent the transmission of electrical waves.

17. The system of claim 14, wherein: The one or more successful predictions search for gaps in the ablation ring or ablation line.

18. The system of claim 14, wherein: The higher the gap index, the higher the probability that a gap exists in the ablation.

19. The system of claim 14, wherein: The data includes at least an ablation index derived from at least one of force, power and time of ablation of the site.

20. The system of claim 14, wherein: The data include at least a mean temperature or a maximum temperature of the ablation at a site.

21. The system of claim 14, wherein: The data includes at least a stability quality derived from a site stability algorithm.

22. The system of claim 14, wherein: The data includes at least the distance to the nearest stable site using a site stability algorithm.

23. The system of claim 14, wherein: The gap index of the ablation is a function of at least the ablation index, an average temperature of the ablation, a stability quality, and a distance to a nearest stable site.

24. The system of claim 14, wherein: A gap index is calculated for each location where ablation is performed.

25. The system of claim 14, further comprising outputting a map of ablation sites, the map highlighting ablation locations having a high gap index.

26. The system of claim 14, wherein: A high gap index is determined by thresholding the gap index.

Images