Gap finder index for high power short duration (HPSD) RF damage.

Abstract

A method is described herein. The method is performed by an optimization engine executed by a processor. The optimization engine receives data including performance metrics of mapping and ablation procedures. The optimization then utilizes predicted treatment outcomes to generate predicted treatment outcomes for the mapping and ablation procedures based on the data and success prediction for the current ablation procedure. A gap index is calculated. The optimization engine also outputs an ablation recommendation based on the success prediction and the gap index.

Description

[Technical Field]

[0001] The present disclosure relates to a Gap Finder Index for radiofrequency (RF) lesions. The Gap Finder Index may be applied, for example, in High Power Short Duration (HPSD) procedures. The Gap Finder Index may also be applied to other energy sources delivered into the heart, such as cryoablation and pulsed field ablation (sometimes referred to interchangeably as PFA or irreversible electroporation (IRE)). [Background technology]

[0002] Pulmonary vein isolation (PVI) procedures involve 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 radio wave transmission. However, the speed at which a successful ring is created can be improved—recent data suggest that approximately 21% of 179 cases of a specific ultra-high-power, short-duration, temperature-controlled ablation procedure found gaps in the barrier after the first pass of ring creation.

[0003] Methods for confirming successful treatment, such as first-pass separation criteria, include manually searching for gaps in the rings or lines, such as the distance between ablation indicators, such as indicators provided by the VISITAG™ module from Biosense Webster, Inc. (indicators are referred to herein as "VisiTags"), via cardiac signal mapping. As will be appreciated, cardiac signal mapping is provided as an example, and any other verification method for blockage may be used. This, combined with low first-pass success rates, is not always reliable and is time-consuming for the physician performing the ablation. Summary of the Invention [Means for solving the problem]

[0004] An exemplary embodiment provides a method, 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 predicted treatment outcomes for the mapping and ablation procedures based on the data, generating one or more success predictions for the current ablation procedure using the predicted treatment outcomes, calculating a gap index for the performed ablation, and outputting an ablation recommendation based on the one or more success predictions including the gap index. The method for confirming successful treatment, such as first-pass separation criteria, includes manually searching for gaps in rings or lines, such as distances between VisiTags, via cardiac signal mapping. It should be understood that cardiac signal mapping is provided as an example, and any other verification method for blockages may be used.

[0005] According to one or more embodiments, the exemplary method embodiments described above may be implemented as an apparatus, a system, and / or a computer program product. [Brief explanation of the drawings]

[0006] A more detailed understanding may be had from the following description, given by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate similar elements and in which: [Figure 1] 1 illustrates a diagram of an example system that may implement one or more features of the presently disclosed subject matter, according to one or more embodiments. [Figure 2] 1 illustrates a block diagram of an exemplary system for anatomically accurate reconstruction of the atria of the heart, according to one or more embodiments. [Figure 3] 1 illustrates a method according to one or more embodiments. [Figure 4] 1 illustrates a graphical depiction of an AI system, according to one or more embodiments. [Figure 5A] 1 illustrates an example of a neural network, according to one or more embodiments. [Figure 5B] 1 illustrates a block diagram of a method implemented in a neural network, according to one or more embodiments. [Figure 6] 1 illustrates a method according to one or more embodiments. [Figure 7] 1 illustrates a graph according to one or more embodiments. [Figure 8] 1 illustrates a gap finder method, according to one embodiment. [Figure 9] Plots associated with the parameters are provided to demonstrate the significance and relationships associated with the parameters. [Figure 10] Plots associated with the parameters are provided to demonstrate the significance and relationships associated with the parameters. [Figure 11] Plots associated with the parameters are provided to demonstrate the significance and relationships associated with the parameters. [Figure 12] Plots associated with the parameters are provided to demonstrate the significance and relationships associated with the parameters. [Figure 13] Plots associated with the parameters are provided to demonstrate the significance and relationships associated with the parameters. [Figure 14] Plots associated with the parameters are provided to demonstrate the significance and relationships associated with the parameters. DETAILED DESCRIPTION OF THE INVENTION

[0007] Systems and methods are provided for utilizing a gap finder index for high power short duration (HPSD) RF lesions. The systems and methods may be implemented using a computer. The systems and methods may include an input / output (I / O) device for receiving data from a catheter configured to perform ablation on a patient's heart. The systems and methods may include a memory and a processor operable to perform a method including processing the received data. The systems and methods include receiving, by an optimization engine executed by one or more processors, data including performance metrics of the mapping and ablation procedure; generating, by the optimization engine, predicted treatment outcomes for the mapping and ablation procedure based on the data; generating, by the optimization engine, one or more success predictions for the current ablation procedure using the predicted treatment outcomes; performing the ablation; calculating an ablation gap index; and outputting the ablation gap index. Performing the ablation may include ablating a series of adjacent locations to generate a ring or line of ablated tissue. The ablation performed may include providing one or more ablations to prevent radio wave transmission. 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 at a site. The data may include at least an average or maximum temperature of ablation at a 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 using the site stability algorithm.The ablation gap index may be a function of at least the ablation index, the average temperature of the ablation, the quality of stability, and the distance to the nearest stable site. A gap index may be calculated for each location where an ablation is performed. The system and method may include outputting a map of the ablation site that highlights ablation locations with a high gap index. A high gap index may be determined by thresholding the gap index.

[0008] 1 is a diagram of an exemplary system (e.g., a medical device instrument) shown 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 a portion of system 100 may be used to collect information (e.g., data / inputs such as biometric data and / or training data sets) and / or may be used to implement optimization engine 101 (e.g., an ML / AI algorithm or model thereof). Optimization engine 101 may be defined as optimization in which model parameters that best fit the data and prior statistical knowledge are estimated in an iterative process to identify ablation gaps and predict success.

[0009] The illustrated system 100 includes a probe 105 with a catheter 110 (including at least one electrode 111), a shaft 112, a sheath 113, and a manipulator 114. As shown, the system 100 also includes a physician 115 (or medical professional, technician, clinician, etc.), a heart 120, a patient 125, and a bed 130 (or table). Insets 140 and 150 show the heart 120 and catheter 110 in more detail. The system 100 also includes a console 160 (including one or more processors 161 and memory 162) and a display 165, as illustrated. Each element and / or item of the system 100 represents one or more of that element and / or item. The example system 100 illustrated in FIG. 1 may be modified to implement the embodiments disclosed herein. The embodiments of the present disclosure may be similarly applied using other system components and configurations. Furthermore, the system 100 may include additional components, such as elements for sensing electrical activity, wired or wireless connectors, processing units, and display devices.

[0010] System 100 may be utilized to detect, diagnose, and / or treat cardiac conditions (e.g., using optimization engine 101). Cardiac conditions, such as cardiac arrhythmias, remain common and dangerous medical ailments, particularly in the aging population. For example, system 100 may be part of a surgical system (e.g., the CARTO® system sold by Biosense Webster, Inc.) configured to acquire biometric data (e.g., anatomical and electrical measurements of a patient's organs, such as heart 120) and perform cardiac ablation procedures. According to one or more embodiments, the biometric data may include anatomical and electrical measurements acquired on a substantial portion of the atria during mapping and ablation procedures.

[0011] More specifically, treatment of cardiac conditions, such as cardiac arrhythmias, often requires 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 source of the cardiac arrhythmia be accurately localized in a chamber of heart 120. Such localization may be performed by an electrophysiological study, during which spatially resolved electrical potentials are detected by a mapping catheter (e.g., catheter 110) introduced into a chamber of heart 120. This electrophysiological study, or so-called electroanatomical mapping, thus provides 3D mapping data that may be displayed on a monitor. In many cases, mapping and therapy functions (e.g., ablation) are provided by a single catheter or a group of catheters, with the mapping catheter simultaneously acting as a therapy (e.g., ablation) catheter. In this case, optimization engine 101 may be stored and executed directly by catheter 110.

[0012] In a patient (e.g., patient 125) having normal sinus rhythm (NSR), the heart (e.g., heart 120), including the atria, ventricles, and excitable conductive tissue, is electrically excited to beat in a synchronized, patterned manner, which can be detected, for example, as intracardiac electrocardiogram (IC ECG) data.

[0013] In patients (e.g., patient 125) with cardiac arrhythmias (e.g., atrial fibrillation or aFib), abnormal regions of cardiac tissue do not follow the synchronous beating cycle associated with normal conductive tissue, in contrast to patients with NSR. In contrast, abnormal regions of cardiac tissue conduct abnormally to adjacent tissue, disrupting the cardiac cycle and resulting in asynchronous cardiac rhythms. This asynchronous cardiac rhythm can also be detected in IC ECG data. Such abnormal conduction has previously been known to occur in various regions of the heart 120, such as in the region of the sinoatrial (SA) node along the atrioventricular (AV) node's conductive pathways, or in the myocardial tissue forming the walls of the ventricles and atria. Other conditions, such as atrial flutter, exist in which abnormal conductive tissue patterns lead to reentry pathways, causing the heart chambers to beat in a regular pattern that can be multiples of sinus rhythm.

[0014] To assist system 100 in detecting, diagnosing, and / or treating a cardiac condition, physician 115 may guide probe 105 into heart 120 of patient 125 reclining on bed 130. For example, physician 115 may insert shaft 112 through sheath 113 while manipulating the distal end of shaft 112 using manipulator 114 near the proximal end of catheter 110 and / or deflection from sheath 113. As shown in inset 140, catheter 110 may be attached to the distal end of shaft 112. Catheter 110 may be inserted through sheath 113 in a collapsed state and then expanded within heart 120.

[0015] In general, electrical activity at a point within the heart 120 may be measured by advancing a catheter 110 (e.g., at least one electrode 111), typically containing an electrical sensor at or near its distal tip, to the point within the heart 120, contacting tissue with the sensor, and acquiring data at the point. One difficulty with mapping a heart chamber using a catheter type containing only a single distal tip electrode is that it can take a long time to collect data for each point across the necessary number of points required for a detailed map of the entire heart chamber. Therefore, multi-electrode catheters (e.g., catheter 110) have been developed to simultaneously measure electrical activity at multiple points within a heart chamber.

[0016] 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 internal organ (e.g., the heart 120) and / or ablate a tissue region thereof (e.g., a chamber of the heart 120). The electrode 111 represents any similar element, such as a tracking coil, piezoelectric transducer, electrode, or 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 position sensors used to determine trajectory information. For example, the trajectory information and other information, including force data and temperature sensors, may be used to infer motion characteristics, such as tissue contractility.

[0017] The 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, baseline activity, ventricular activity, dominant frequency, impedance, etc. LAT may be a time point of threshold activity corresponding to local activation calculated based on a normalized initial starting point. Electrical activity may be any applicable electrical signal that can be measured based on one or more thresholds and may be sensed and / or enhanced based on signal-to-noise ratio and / or other filters. Topology may correspond to the physical structure of a body part or portion of a body part and may correspond to changes in the physical structure for different parts of the body part or for different body parts. The dominant frequency may be a frequency or range of frequencies commonly found in a portion of a body part and may differ in different parts of the same body part. For example, the dominant frequency of the PVs of a heart may differ from the dominant frequency of the right atrium of the same heart. Impedance may be a resistance measurement in a particular region of a body part.

[0018] 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 may generally be used to monitor, diagnose, and treat any number of various diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathies, and coronary artery disease) and autoimmune diseases (e.g., type I and type II diabetes). BS ECG data may include data and signals collected from electrodes on the patient's surface, while IC ECG data may include data and signals collected from electrodes inside the patient's body, and ablation data may include data and signals collected from ablated tissue. Furthermore, BS ECG data, IC ECG data, and ablation data, along with catheter electrode position data, may be derived from one or more treatment records.

[0019] For example, catheter 110 may use electrodes 111 to implement intravascular ultrasound and / or MRI catheterization to image (e.g., acquire and process biometric data) heart 120. Inset 150 shows a close-up of catheter 110 within a chamber of heart 120. While catheter 110 is shown as a point catheter, it will be understood that any shape that includes one or more electrodes 111 may be used to implement the exemplary embodiments disclosed herein.

[0020] Examples of the catheter 110 include, but are not limited to, a straight catheter with multiple electrodes, a balloon-type catheter including electrodes distributed on multiple spines forming a balloon, a lasso or loop catheter with multiple electrodes, a force-sensing catheter, or any other applicable shape or type. The straight 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 the action of an external force (e.g., cardiac tissue) on the straight catheter. The balloon-type catheter may be designed to hold its electrodes in intimate contact with the endocardial surface when deployed within a patient's body. It should be understood that, although a balloon-type catheter is described to aid in understanding the present invention, spherical or lattice-shaped catheters or catheters with multiple spines may also be used. As an example, a balloon-type catheter may be inserted into a lumen such as the PV. The balloon-type catheter may be inserted into the PV in a deflated state, thereby preventing the balloon-type catheter from occupying its maximum volume while inserted into the PV. The balloon catheter can be expanded while inside the PV so that the electrodes on the balloon catheter contact the entire circular portion of the PV, which allows for efficient imaging and / or ablation.

[0021] According to other embodiments, body patches and / or body surface electrodes may similarly be positioned on or adjacent to the body of the patient 125. A catheter 110 having 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 patches and / or body surface electrodes. Additionally, 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 tissue electrical potentials in real time). The biometric data may be associated with the determined position of the catheter 110, thereby displaying a rendering of the patient's body part (e.g., the heart 120) and showing the biometric data superimposed on the shape of the body part.

[0022] The probe 105 and other items of the system 100 may be connected to a console 160. The console 160 may include any computing device that employs ML / AI algorithms or models (represented as the optimization engine 101). According to an exemplary embodiment, the console 160 includes one or more processors 161 (any computing hardware) and memory 162 (any non-transitory tangible medium), where the one or more processors 161 execute computer instructions for 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 conducts electricity.

[0023] According to one or more embodiments, the console 160 may be further programmed by an optimization engine 101 (in software) to perform the functions of receiving data including performance metrics of the mapping and ablation procedures, generating predicted treatment outcomes for the mapping and ablation procedures based on the data, generating a success prediction for the current ablation procedure, and outputting a probability of a repeat treatment 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 (described herein in connection with FIGS. 3 and 6 ). In generating predicted treatment outcomes for the mapping and ablation procedures, the system and method operates using various measurement data collected during the treatment and classifies the outcome based on known data from other treatments. In this manner, the system and method, via the optimization engine 101, utilizes the Ablation Index and its associated parameters, as described below, to predict the outcome of the ablation procedure. In this manner, the system and method may indicate to a medical professional or identify on a system display that additional corrective actions need to be taken to improve treatment success. One such additional measure may be to re-perform the ablation.

[0024] In general, the optimization engine 101 may provide one or more user interfaces, such as in place of an operating system or other application and / or directly as needed. User interfaces include, but are not limited to, an internet browser, a graphic user interface (GUI), a windowing interface, and / or other visual interfaces for applications, operating systems, file folders, etc. According to one or more embodiments, the optimization engine 101 may be external to the console 160 and may be located, for example, within the catheter 110, an external device, a mobile device, a cloud-based device, or may be a stand-alone processor. In this regard, the optimization engine 101 may be transferable / downloadable in electronic form over a network.

[0025] In one example, console 160 may be any computing device including hardware (e.g., processor 161 and memory 162), such as a general-purpose computer, with software (e.g., optimization engine 101) and / or front-end and interface circuitry suitable for transmitting and receiving signals to and from probe 105, as well as for controlling other components of system 100, as described herein. For example, the front-end and interface circuitry may include an input / output (I / O) communication interface that allows console 160 to receive signals from and / or transfer signals to at least one electrode 111. Console 160 may 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 electrocardiogram / electromyogram (EMG) signal conversion integrated circuit. The console 160 may communicate signals from the A / D ECG or EMG circuitry to another processor and / or may be programmed to perform one or more of the functions disclosed herein.

[0026] A display 165, which may be any electronic device for visually presenting biometric data, is connected to the console 160. According to an exemplary embodiment, during a procedure, the console 160 may facilitate the presentation of a rendering of the body part to the physician 115 on the display 165 and store data representing the rendering of the body part in the memory 162. For example, a map indicative of motion characteristics may be rendered / constructed based on trajectory information sampled at a sufficient number of points within the heart 120. As one example, the display 165 may include a touch screen, which may be configured to receive input from the physician 115 in addition to presenting the rendering of the body part.

[0027] In some embodiments, physician 115 may use one or more input devices, such as a touchpad, mouse, keyboard, gesture recognizer, etc., to manipulate elements of system 100 and / or renderings of body parts. For example, the input device may be used to change the position of catheter 110 so that the renderings are updated. Display 165 may be located at the same location or at a remote location, such as a remote hospital, or within a separate healthcare provider network.

[0028] According to one or more embodiments, the system 100 may also obtain biometric data using ultrasound, computed tomography (CT), MRI, or other medical imaging techniques utilizing the catheter 110 or other medical equipment. For example, the system 100 may obtain ECG data and / or anatomical and electrical measurements (e.g., biometric data) of the heart 120 using one or more catheters 110 or other sensors. More specifically, the console 160 may be connected by a cable to BS electrodes, including adhesive skin patches, attached to the patient 125. The BS electrodes may acquire / generate biometric data in the form of BS ECG data. For example, the processor 161 may determine position coordinates of the catheter 110 within a body part (e.g., the heart 120) of the patient 125. The position coordinates may be based on impedance or electromagnetic fields measured between body surface electrodes and electrodes 111 of the catheter 110 or other electromagnetic component. Additionally or alternatively, location pads that generate the magnetic fields used for steering may be located on the surface of bed 130 or may be separate from bed 130. The biometric data may be transmitted to console 160 and stored in memory 162. Alternatively or additionally, the biometric data may be transmitted to a server, which may be local or remote, using a network as further described herein.

[0029] According to one or more exemplary embodiments, catheter 110 may be configured to ablate a tissue region of a chamber of heart 120. Inset 150 shows an enlarged view of catheter 110 within a chamber of heart 120. For example, an ablation electrode, such as at least one electrode 111, may be configured to apply energy to a tissue region of an internal organ (e.g., heart 120). The energy may be thermal energy and may cause damage to the tissue region starting from the surface of the tissue region and extending through the thickness of the tissue region. Biometric data related to the ablation procedure (e.g., ablated tissue, ablation location, etc.) may be considered ablation data.

[0030] According to one embodiment, with respect to acquiring biometric data, a multi-electrode catheter (e.g., catheter 110) may be advanced into a chamber of heart 120. Anteroposterior (AP) and lateral fluoroscopic photographs may be acquired to establish the position and orientation of each of the electrodes. An ECG may be recorded from each of the electrodes 111 in contact with the subject's cardiac surface relative to a time reference, such as the occurrence of P waves in sinus rhythm from a BS ECG and / or a signal from an electrode 111 of catheter 110 positioned within the coronary sinus. Systems further disclosed herein may distinguish between electrodes that record electrical activity and electrodes that do not record electrical activity due to their lack of proximity to the endocardial wall. After the initial ECG is recorded, the catheter may be repositioned, and fluoroscopic photographs and an ECG may be recorded again. An electrical map may then be constructed from an iteration of the above process (e.g., via cardiac mapping).

[0031] Cardiac mapping may be implemented using one or more techniques. Generally, mapping of cardiac regions, such as the cardiac regions, tissues, veins, arteries, and / or electrical pathways of the heart 120, may lead to the identification of problem areas, such as scar tissue, arrhythmia sources (e.g., electrical rotors), healthy regions, etc. Cardiac regions may be mapped such that a visual rendering of the mapped cardiac region is provided using a display, as further disclosed herein. Additionally, cardiac mapping (which is one example of cardiac imaging) may include mapping based on one or more modalities, such as, but not limited to, LAT, regional activation rate, electrical activity, topology, bipolar mapping, dominant frequency, or impedance. Data (e.g., biometric data) corresponding to multiple modalities may be acquired using a catheter (e.g., catheter 110) inserted into the patient's body and provided for rendering simultaneously or at different times based on corresponding settings and / or physician 115 preferences.

[0032] As an example of the first technique, cardiac mapping may be implemented by sensing electrical properties of cardiac tissue, such as LAT, as a function of precise location within the heart 120. Corresponding data (e.g., biometric data) may be acquired by one or more catheters (e.g., catheter 110) advanced into the heart 120 and having electrical and position sensors (e.g., electrodes 111) at their distal tips. By way of example, position and electrical activity may initially be measured at approximately 10 to approximately 20 points on the interior surface of the heart 120. These data points may generally be sufficient to generate a preliminary reconstruction or map of the cardiac surface with satisfactory quality. This preliminary map may often be combined with data measured at additional points to generate a more comprehensive map of the cardiac electrical activity. In clinical practice, it is not uncommon to collect data from 100 or more sites (e.g., several thousand) to generate a detailed, comprehensive map of the cardiac chamber's electrical activity. The detailed maps generated can then serve as the basis for making decisions about therapeutic action courses, such as tissue ablation as described herein, to alter the propagation of electrical activity in the heart and restore normal cardiac rhythm.

[0033] Furthermore, cardiac mapping may be generated based on detection of intracardiac potential fields (e.g., IC ECG data and / or bipolar intracardiac reference signals, which are examples). Non-contact methods may be implemented to simultaneously acquire large amounts of cardiac electrical information. For example, a catheter type having a distal end portion may include a series of sensor electrodes distributed over its surface and connected to insulated conductors for connection to signal sensing and processing means. The size and shape of the end portion may be such that the electrodes are substantially spaced apart from the walls of the cardiac chambers. The intracardiac potential fields may be detected during a single cardiac beat. According to one embodiment, the sensor electrodes may be distributed on a series of circumferences located in spaced-apart planes. These planes may be perpendicular to the longitudinal axis of the catheter end. At least two additional electrodes may be disposed adjacent to each end of the longitudinal axis of the end portion. As a more specific example, the catheter may include four circumferences with eight electrodes equiangularly spaced apart on each circumference. Thus, in this particular 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 a five soft flexible branch, eight radial splines, or a turner-type catheter with parallel splines (e.g., any of which may have a total of 42 electrodes).

[0034] As an example of electrical or cardiac mapping, electrophysiological cardiac mapping systems and techniques based on non-contact and non-expandable multi-electrode catheters (e.g., catheter 110) may be implemented. An ECG may be acquired using one or more catheters 110 with multiple electrodes (e.g., 42-122 electrodes, etc.). This implementation allows knowledge of the relative geometric relationship of the probe and endocardium to be obtained through an independent imaging modality, such as transesophageal echocardiography. After the independent imaging, cardiac surface potentials may be measured using non-contact electrodes, and a map may be constructed from these surface potentials (e.g., possibly using a bipolar intracardiac reference signal). This technique may include (after the independent imaging step): (a) measuring potentials using multiple electrodes disposed on a probe placed within heart 120; (b) determining the geometric relationship between the probe surface and the endocardial surface and / or other fiducials; (c) generating a matrix of coefficients representing the geometric relationship between the probe surface and the endocardial surface; and (d) determining the endocardial potentials based on the electrode potentials and the matrix of coefficients.

[0035] As another example of electrical or cardiac mapping, techniques and devices may be implemented for mapping the electrical potential distribution of a heart chamber. An intracardiac multi-electrode mapping catheter assembly may be inserted into heart 120. The mapping catheter (e.g., catheter 110) assembly may include a multi-electrode array or companion reference catheter having one or more integrated reference electrodes (e.g., one or more electrodes 111).

[0036] According to one or more exemplary embodiments, the electrodes may be deployed in a generally spherical array, which may be spatially referenced to points on the endocardial surface by a reference electrode or by a reference catheter that is brought into contact with the endocardial surface. A preferred electrode array catheter may carry a large number of individual electrode sites (e.g., at least 24). Additionally, this exemplary technique may be implemented by knowing the location of each of the electrode sites on the array and by knowing the cardiac geometry. These locations are preferably determined by impedance plethysmography.

[0037] From an electrical or cardiac mapping perspective, and according to another embodiment, the catheter 110 may be a cardiac mapping catheter assembly that may include an electrode array defining multiple electrode sites. The cardiac mapping catheter assembly also includes a lumen for receiving a reference catheter having a distal tip electrode assembly that may be used to probe the heart wall. The cardiac mapping catheter assembly may include a braid of insulated wires (e.g., having 24-64 wires within the braid), each of which may be used to form an electrode site. The cardiac mapping catheter assembly may be easily positionable within the heart 120 to be used to acquire electrical activity information from a first set of non-contact electrode sites and / or a second set of contact electrode sites.

[0038] Furthermore, according to another embodiment, a catheter 110 capable of mapping electrophysiological activity within the heart may include a distal tip adapted to deliver stimulation pulses for pacing the heart or an ablation electrode for ablating tissue in contact with the tip, and may further include at least one pair of orthogonal electrodes for generating a differential signal indicative of local cardiac electrical activity in the vicinity of the orthogonal electrodes.

[0039] As described herein, system 100 may be used to detect, diagnose, and / or treat cardiac conditions. In an exemplary operation, system 100 may implement a process for measuring electrophysiological data within a heart chamber. This process may include, in part, positioning a set of active and passive electrodes within heart 120, applying current to the active electrodes to thereby generate an electric field within the heart chamber, and measuring the electric field at the passive electrode sites. The passive electrodes are included in an array disposed on an inflatable balloon of a balloon-type catheter. In a preferred embodiment, the array is said to have 60 to 64 electrodes.

[0040] As another exemplary operation, cardiac mapping may be performed by system 100 using one or more ultrasound transducers. The ultrasound transducers may be inserted into a patient's heart 120 and may acquire multiple ultrasound slices (e.g., two-dimensional or three-dimensional slices) at various positions and orientations within heart 120. The position and orientation of a particular ultrasound transducer may be known, and the acquired ultrasound slices may be stored for later display. One or more ultrasound slices corresponding to the position of probe 105 (e.g., a treatment catheter shown as catheter 110) may be displayed, and probe 105 may be superimposed on one or more ultrasound slices.

[0041] Considering the system 100, it can be seen that cardiac arrhythmias, including atrial arrhythmias, can be of the multiwavelet reentrant type, characterized by multiple asynchronous loops of electrical impulses that scatter, often self-propagating, around the atria (e.g., another example of IC ECG data). Alternatively or in addition to the multiwavelet reentrant type, cardiac arrhythmias can also have focal sources of excitation, such as when isolated regions of atrial tissue are spontaneously excited in a rapid and repetitive manner (e.g., another example of IC ECG data). Ventricular tachycardia (V-tach or VT) is a tachycardia or fast cardiac rhythm that originates from one of the ventricles. It is a potentially fatal arrhythmia because it can lead to ventricular fibrillation and sudden death.

[0042] 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 (e.g., signal interference) originating in the atrial veins and PVs, causing irregular impulses to be conducted to the ventricles. This results in an irregular heartbeat that may persist for minutes to weeks, or even years. In many cases, aFib is a chronic condition that often carries a small increase in the risk of death from a heart attack. The treatment approach for aFib is medication to reduce the heart rate or restore normal heart rhythm. Additionally, patients with aFib are often given anticoagulants to protect against the risk of heart attack. The use of such anticoagulants carries its own risks: internal bleeding. In some patients, medication is insufficient, and their aFib is deemed drug-refractory, i.e., untreatable with standard pharmacological interventions. Synchronized cardioversion may also be used to convert aFib to a normal heart rhythm. Alternatively, patients with aFib may be treated with catheter ablation.

[0043] Catheter ablation-based therapy may involve mapping the electrical properties of cardiac tissue, particularly the endocardium and cardiac volumes, and selectively ablating the cardiac tissue through the application of energy. Electrical or cardiac mapping (e.g., implemented by any of the electrophysiological cardiac mapping systems and techniques described herein) involves creating an electrical potential map (e.g., a voltage map) of wave propagation along cardiac tissue or a map of arrival times (e.g., a LAT map) to points located within various tissues. Electrical or cardiac mapping (e.g., a cardiac map) may be used to detect localized cardiac tissue dysfunction. Ablation, such as cardiac mapping-based ablation, may stop or alter the propagation of unwanted electrical signals from one portion of the heart 120 to another.

[0044] Ablation techniques disrupt unwanted electrical pathways by creating non-conductive lesions. Various energy delivery modalities have been previously disclosed for creating lesions, including the use of microwave, laser, and more generally, radiofrequency energy to create conductive interruptions along cardiac tissue walls. Another example of an energy delivery technique includes pulsed field ablation (PFA), which produces irreversible electroporation (IRE) by providing a pulsed high-voltage electric field that damages cell membranes. In a two-stage procedure (mapping followed by ablation), electrical activity at points within the heart 120 is typically sensed and measured by advancing a catheter 110 containing one or more electrical sensors (e.g., electrodes 111) into the heart 120 and acquiring / capturing data (e.g., biometric data generally or ECG data specifically) at multiple points. The ECG data is then used to select a target region of the endocardium where ablation will be performed.

[0045] Cardiac ablations and other cardiac electrophysiology procedures are becoming increasingly complex as physicians treat challenging conditions such as atrial fibrillation and ventricular tachycardia. Treatment of refractory arrhythmias may now rely on the use of three-dimensional (3D) mapping systems to reconstruct the anatomical structure of the target heart chamber. In this regard, the optimization engine 101 used by the system 100 herein manipulates and evaluates biometric data in general, or ECG data in particular, to generate improved tissue data that enables more accurate diagnoses, images, scans, and / or maps for treating abnormal heart rhythms or arrhythmias. For example, cardiologists rely on software such as the Complex Fractionated Atrial Electrograms (CFAE) module of the CARTO® 3 3D mapping system, manufactured by Biosense Webster, Inc. (Diamond Bar, California), to generate and analyze ECG data. The optimization engine 101 of the system 100 enhances this software to generate and analyze improved biometric data and further provides multiple pieces of information regarding the electrophysiological properties of the heart 120 (including scar tissue) that represent the cardiac substrate (anatomical and functional) of the aFib.

[0046] Thus, the system 100 may implement a 3D mapping system, such as the CARTO® 3 3D mapping system, to identify potential arrhythmogenic substrates for cardiomyopathies in terms of detecting abnormal ECGs. Substrates related to these cardiac conditions have been associated with the presence of fragmented and delayed ECG activity in the endocardial and / or epicardial layers of the ventricular chambers (right and left). For example, low- or medium-voltage regions may indicate fragmented and delayed ECG activity. Furthermore, low- or medium-voltage regions during sinus rhythm may correspond to critical isthmuses identified in sustained, coherent ventricular arrhythmias (e.g., non-permissive ventricular tachycardia and intra-atrial tachycardia). Generally, abnormal tissue is characterized by low-voltage ECG activity. However, early clinical experience with endocardial-epicardial mapping has demonstrated that low-voltage regions are not always present as the sole arrhythmogenic mechanism in these patients. In fact, areas of low or medium voltage may show ECG fragmentation and delayed activity during sinus rhythm, corresponding to critical isthmuses identified during sustained, coherent ventricular arrhythmias (e.g., only applicable to nonpermissive ventricular tachycardia). Furthermore, ECG fragmentation and delayed activity are often observed in areas showing normal or near-normal voltage amplitudes (>1-1.5 mV). These latter areas can be evaluated according to voltage amplitude but are not considered normal according to the intracardiac signal and therefore represent true arrhythmogenic substrates. 3D mapping may also be able to identify the location of arrhythmogenic substrates on the endocardial and / or epicardial layers of the right and / or left ventricles, whose distribution may vary depending on the primary disease progression.

[0047] As another exemplary operation, cardiac mapping may be implemented by system 100 using one or more multi-electrode catheters (e.g., catheter 110). Multi-electrode catheters are used to stimulate and map electrical activity within heart 120 and to ablate sites of abnormal electrical activity. In use, the multi-electrode catheter is inserted into a major vein or artery, such as the femoral vein, and then guided into a target chamber of heart 120. A typical ablation procedure involves inserting catheter 110 having at least one electrode 111 at its distal end into a cardiac chamber. A reference electrode is provided by taping to the patient's skin, by a second catheter placed in or near the heart, or by selecting one or other of the electrodes 111 on catheter 110. Radio frequency (RF) current is applied to the tip electrode 111 of ablation catheter 110, causing current to flow through the medium surrounding the tip electrode (i.e., blood and tissue) toward the reference electrode. The current distribution is determined by the amount of electrode surface in contact with the tissue compared to blood, which has a higher electrical conductivity than tissue. Tissue heating occurs due to its electrical resistance. Sufficient tissue heating induces cellular destruction in the cardiac tissue, resulting in the formation of electrically non-conductive lesions within the cardiac tissue. This process also heats the tip electrode 111 through conduction from the heated tissue to the electrode itself. If the electrode temperature becomes high enough, potentially exceeding 60°C, a thin, transparent film of dehydrated blood proteins can form on the surface of the electrode 111. As the temperature continues to rise, this dehydrated layer can gradually thicken, causing blood to coagulate on the electrode surface. Because dehydrated biological materials have a higher electrical resistance than endocardial tissue, the impedance to the flow of electrical energy into the tissue also increases. If the impedance becomes high enough, the catheter 110 must be removed from the body and the tip electrode 111 must be cleaned.

[0048] 2 illustrates a diagram of a system 200 that may implement one or more features of the subject matter of this disclosure, according to one or more exemplary embodiments. System 200 includes, in association with a patient 202 (e.g., an example of patient 125 of FIG. 1 ), an apparatus 204, a local computing device 206, a remote computing system 208, a first network 210, and a second network 211. Additionally, apparatus 204 may include a biometric sensor 221 (e.g., an example of catheter 110 of FIG. 1 ), a processor 222, a user input (UI) sensor 223, a memory 224, and a transceiver 225. Note that for ease of explanation and brevity, optimization engine 101 of FIG. 1 is reused in FIG. 2 .

[0049] According to one embodiment, device 204 may be an implementation of system 100 of FIG. 1 , and device 204 may include both patient-internal and patient-external components. According to another embodiment, device 204 may be a patient 202-external device including an attachable patch (e.g., attached to the patient's skin). According to another embodiment, device 204 may be internal to the body of patient 202 (e.g., subcutaneously implantable), and device 204 may be inserted into the body of patient 202 by any applicable method, including oral infusion, surgical insertion via a vein or artery, endoscopic surgery, or laparoscopic surgery. According to one embodiment, while a single device 204 is shown in FIG. 2 , an exemplary system may include multiple devices.

[0050] Accordingly, apparatus 204, local computing device 206, and / or remote computing system 208 may be programmed to execute computer instructions related to optimization engine 101. As one example, memory 223 stores these instructions for execution by processor 222 such that apparatus 204 may receive and process biometric data via biometric sensor 201. In this manner, processor 222 and memory 223 are representative of the processor and memory of local computing device 206 and / or remote computing system 208.

[0051] The apparatus 204, the local computing device 206, and / or the remote computing system 208 may be any combination of software and / or hardware that individually or collectively stores, executes, and implements the optimization engine 101 and its functions. Furthermore, the apparatus 204, the local computing device 206, and / or the remote computing system 208 may be an electronic computer framework that includes and / or uses any number and combination of computing devices and networks utilizing various communication technologies, as described herein. The apparatus 204, the local computing device 206, and / or the remote computing system 208 may be easily scalable, extensible, and modular, capable of being tailored for different services or reconfigured with some functions independent of others.

[0052] Networks 210 and 211 may be wired networks, wireless networks, or may 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)). Information may be transmitted over network 210 between apparatus 204 and local computing device 206 using any one of a variety of short-range wireless communication protocols, such as Bluetooth, Wi-Fi, Zigbee, Z-Wave, Near Field Communication (NFC), Ultraband, Zigbee, or infrared (IR). Furthermore, network 211 is an example of one or more of an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or 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. Information may be transmitted over network 211 using any one of a variety of long-range wireless communication protocols (e.g., TCP / IP, HTTP, 3G, 4G / LTE, or 5G / New Radio). In both networks 210 and 211, wired connections may be implemented using Ethernet, Universal Serial Bus (USB), RJ-11, or any other wired connection, while wireless connections may be implemented using Wi-Fi, WiMAX, Bluetooth, infrared, cellular networks, satellite communications, or any other wireless connection method.

[0053] During operation, device 204 may continuously or periodically acquire, monitor, store, process, and communicate biometric data related to patient 202 via network 210. Additionally, 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 an embodiment of system 100 of FIG. 1 configured to communicate with local computing device 206 via network 210. Local computing device 206 may be, for example, a fixed / standalone device, a base station, a desktop / laptop computer, a smartphone, a smartwatch, a tablet, or any other device configured to communicate with other devices via networks 211 and 210. A remote computing system 208, implemented as a physical server on or connected to the network 211 or as a virtual server within a public cloud computing provider of the network 211 (e.g., Amazon Web Services (AWS)®), may be configured to communicate with the local computing device 206 over the network 211. Thus, biometric data related to the patient 202 may be communicated throughout the system 200.

[0054] The elements of device 204 are now described. 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 may be observed / acquired / obtained. For example, biometric sensor 221 may include one or more of an electrode (e.g., electrode 111 of FIG. 1 ), 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.

[0055] In executing optimization engine 101, processor 222 may be configured to receive, process, and manage biometric data acquired by biometric sensor 221 and communicate the biometric data to memory 224 for storage (e.g., on a database therein) and / or across network 210 (e.g., to the database) via transceiver 225. Biometric data from one or more other devices 204 may also be received by processor 222 via transceiver 225. As described in more detail below, processor 222 may also be configured to selectively respond to different tapping patterns (e.g., single tap or double tap) received from UI sensor 223 such that different tasks of the patch (e.g., data acquisition, storage, or transmission) are initiated based on the detected pattern. In some embodiments, processor 222 may generate audible feedback regarding detection of the gesture.

[0056] The UI sensor 223 includes, for example, a piezoelectric or capacitive sensor configured to receive user input, such as a tap or touch. For example, the UI sensor 223 may be controlled to implement capacitive coupling in response to the patient 202 tapping or touching the surface of the device 204. Gesture recognition may be implemented by any one of a variety of capacitive types, such as resistive capacitive, surface capacitive, projected capacitive, surface acoustic wave, piezoelectric, and infrared touch. The capacitive sensor may be disposed over a small area or length of the surface, such that a tap or touch on the surface activates the monitoring device.

[0057] The 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 disk drive). The memory 224 stores computer instructions that are executed by the processor 222.

[0058] The transceiver 225 may include a separate transmitter and a separate receiver, or alternatively, the transceiver 225 may include a transmitter and receiver integrated into a single device.

[0059] During operation, the device 204 utilizing the optimization engine 101 observes / acquires biometric data of the patient 202 via the biometric sensor 221, stores the biometric data in memory, and shares this biometric data throughout the system 200 via the transceiver 225. The optimization engine 101 may 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 to increase the success probability of the next procedure and / or eliminate unnecessary subsequent procedures.

[0060] 3 illustrates a method 300 (e.g., implemented by optimization engine 101 of FIGS. 1 and / or 2) and is illustrated in accordance with one or more exemplary embodiments. Method 300 provides a success prediction by providing multi-stage manipulation of data to identify ablation gaps and improve the diagnosis and treatment of cardiac arrhythmias. Method 300 is described with respect to an ablation procedure, by way of example and ease of explanation.

[0061] The method begins at block 320, where the optimization engine 101 receives data including performance metrics of the mapping and ablation procedures. The data may be considered an input or inputs to the optimization engine 101, which is being executed by one or more processors 161 or 222.

[0062] The data / inputs generally represent biometric data (as described herein), patient parameters, treatment parameters, and / or performance metrics. For example, biometric data may include anatomical and electrical measurements, as well as other sensor measurements, including temperature and impedance, acquired across a significant portion of the atrium during the mapping and ablation procedure. Additionally, patient and / or treatment parameters may be related to patient characteristics, tissue characteristics, and other data points in the index procedure, as well as mapping and ablation procedures, such as patient demographic characteristics, information / data related to conventional electrophysiology procedures, and short-term / long-term patient outcomes. Generally, patient parameters or patient-specific information may include pre-ablation body temperature, irrigation temperature, tissue and surface temperature, tissue and surface temperature during ablation, and tissue and surface temperature after ablation. Additionally, patient parameters or patient-specific information may also include a body surface ECG, the patient's prior medical history, the patient's demographic characteristics, IC ECG, voltage maps, the type of equipment used, the time and date of the procedure, and the patient's cardiac anatomy. In general, the procedure parameters or procedure-specific information may include catheter stability during the ablation procedure and other patient historical outcomes. Additionally, the data / inputs may include performance metrics, including any information indicative of or specific to the mapping and ablation procedure and / or its results. Utilizing these inputs, the optimization engine 101 initiates technical effects and benefits that identify ablation gaps and provide success predictions for each patient situation (e.g., time and location).

[0063] The optimization engine 101 receives one or more previous cases, such as previous or older ablation procedures, stored in the system 100 (e.g., in a database therein) or received by the system 100. From these previous cases, data / inputs may be derived / obtained via a series of lesion-bearing maps, anatomical maps, and / or electrical maps thereof. From these previous cases, data / inputs may be derived / obtained from sensor data generated by one or more sensors (e.g., from the catheter 110 and / or body surface electrodes). For example, an ablation catheter (e.g., the catheter 110) may be used to cause tissue necrosis in cardiac tissue of the heart 120 to correct a cardiac arrhythmia. In an exemplary ablation procedure, damage occurs to 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 from one or more electrodes 111 into the cardiac tissue to cause ablation and the creation of lesions. The coordinates of the lesion and the parameters of the electromagnetic RF energy may be included in the data / input for the ablation procedure.

[0064] In block 340, the optimization engine 101 generates one or more predicted treatment outcomes for the mapping and ablation procedure based on the data. Generally, the one or more predicted treatment outcomes identify the performance of the mapping and ablation procedure, such as short-term or long-term success in preventing aFib recurrence (i.e., short-term or long-term failure of the ablation).

[0065] To determine / generate one or more predicted treatment outcomes, the optimization engine 101 analyzes the data to build and train a model. The optimization engine 101 may inject data into a model, such as a gold standard, in which a user has identified gaps and successful ablations, and the model outputs the most significant parameters that predict gaps / successful ablations. The optimization engine 101 may build and train the model using supervised approaches, unsupervised approaches, and / or deep learning solutions, as described herein. That is, the optimization engine 101 considers all available data / inputs (described in block 320) when building and training the model. The building / training can be considered the ML stage of the optimization engine 101. For example, the optimization engine 101 collects 10,000 cases with 12-month follow-up information, each case associated with a single-class rerun / long-term success, and a backpropagation algorithm (as described herein) minimizes a loss function to train all weights in the neural network. The optimization engine 101 then utilizes the model to analyze the data / inputs (e.g., whether an ablation gap exists) to determine whether the mapping and ablation procedure was successful. The model may analyze success across one or more scenarios, such as different patient groupings (e.g., based on age, gender, health, etc.) and different treatment groupings (e.g., based on treatment type).

[0066] For example, the optimization engine 101 trains by using previous or older ablation procedures to learn different scenarios over time. In this regard, the optimization engine 101 generates training datasets (from previous or older ablation procedures) for different patient / procedure classifications corresponding to one or more scenarios. The previous or older ablation procedures may include previous ablation procedures, locations, etc., as well as cardiac information from follow-up mapping procedures after the ablation procedures. The patient / procedure classifications may include similar cases with similar patient demographic characteristics (e.g., patients of the same age and blood pressure) and / or adjustments to treatment conditions (e.g., treatments in the same atrium area). The generated training datasets may provide information on whether an ablation gap occurred and whether a rerun operation was performed for each patient or procedure grouping, which are incorporated into the optimization engine 101.

[0067] According to one or more embodiments, the optimization engine 101 trains the model by utilizing the patient's 125 long-term outcomes to inform / teach / tell the model (and the system 100) which ECG data, etc. (e.g., any biometric data for long-term outcomes) are likely to be healthy or not. This ECG data, etc. may then be used to train the weights of the neural network using a back-propagation approach (e.g., the back-propagation algorithm described herein).

[0068] For ease of understanding, the optimization engine 101 and the construction and training of its models will be described with reference to Figures 4-5A and 5B. Where appropriate, the description of Figures 4-5A and 5B will be made with reference to Figures 1-3.

[0069] 4 illustrates an ML / AI system 400 according to one or more embodiments. The ML / AI system 400 includes data 410, a machine 420, a model 430, an outcome 440, and (underlying) hardware 450.

[0070] 1-2 (e.g., the ML / AI algorithms therein), while hardware 450 may also represent catheter 110 of FIG. 1, console 160 of FIG. 1, and / or device 204 of FIG. 2. In general, the ML / AI algorithms of ML / AI system 400 (e.g., implemented by optimization engine 101 of FIG. 1-2) operate on hardware 450 using data 410 to train machine 420, build model 430, and predict outcome 440. For example, machine 420 acts as a controller or data collector associated with hardware 450 and / or is associated with hardware 450.

[0071] Data 410 may be ongoing data or output data associated with hardware 450. For example, data 410 may include 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, respiration data, fluid data, case-specific data, location, time data from the original case to the rerun, and other determinants. Data 410 may also include currently collected data, historical data, or other data from hardware 450, case summaries by physician 115, additional imaging data, measurements during a surgical procedure (e.g., an ablation procedure) that may be associated with the outcome of the surgical procedure, and temperatures of heart 140 of FIG. 1 that are collected and correlated with the outcome of the cardiac procedure and associated with hardware 450. According to one or more embodiments, the data 410 may include patient and / or procedure parameters related to the mapping and ablation procedure (e.g., patient characteristics, tissue characteristics, and other data points at the index procedure), patient demographic characteristics, information / data about previous electrophysiology procedures, and short-term / long-term outcome results for the patient 125. The data 410 may be divided into one or more subsets by the machine 420.

[0072] A model 430 is constructed on the data 410. Constructing the model 430 may include physical hardware or software modeling, algorithmic modeling, and / or similar modeling intended to represent the data 410 (or a subset thereof). In some aspects, constructing the model 430 is part of a self-training operation by the machine 420. The model 430 may be configured to model the operation of the hardware 450 and to model the data 410 collected from the hardware 450 to predict an outcome 440 obtained by the hardware 450. Predicting the outcome 440 may utilize a trained version of the model 430. For example, and to further understand the present disclosure, in the case of the heart, if temperatures during treatment between 36.5°C and 37.89°C (i.e., 97.7°F and 100.2°F) result in a positive outcome from a cardiac treatment, then the outcome 440 may be predicted for a given treatment using these temperatures. Thus, the predicted outcome 440 may be used to construct the machine 420, model 430, and hardware 450 accordingly.

[0073] Machine 420 trains model 430, such as on hardware 450 and data 410. This training may also include analysis and correlation of collected data 410. For example, machine 420 may train model 430 to determine whether a correlation or association exists between the temperature of heart 140 of FIG. 1 during a cardiac procedure and an outcome. According to another embodiment, training machine 420 and model 430 may include self-training by optimization engine 101 of FIG. 1 with one or more subsets. In this regard, optimization engine 101 of FIG. 1 learns to detect pointwise case classifications.

[0074] The ML / AI algorithms in the ML / AI system 400 may include neural networks, autoencoders, and backpropagation algorithms to operate on hardware 450, analyze data 410, build / train, and predict outcomes 440. 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. A backpropagation algorithm is used in training feedforward neural networks for supervised learning.

[0075] At decision block 360, the optimization engine 101 generates one or more success predictions for the current procedure (e.g., the current ablation procedure). For example, the optimization engine 101 may receive a current for the current ablation procedure and execute the generated model to predict success. Generally, the procedure or current ablation procedure may be a current or real-time ablation procedure. The execution may be considered the AI ​​stage of the optimization engine 101. The one or more success predictions may include short-term and / or long-term consequences for the current ablation procedure, as well as the need for re-administration of 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 may range from 0 to 1, with 1 being the best. Then, based on the score (e.g., the optimization engine 101 outputs 0.8), the physician may search around the PV again, provide additional ablation, 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 likelihood that the current ablation procedure can be terminated without re-runs, which may increase the probability of success of the current ablation procedure and / or reduce risk to the patient 125 by eliminating unnecessary subsequent procedures.

[0076] According to one or more embodiments, the optimization engine 101 utilizes the model and the mapping and predicted treatment outcomes of the ablation procedure to analyze the biometric data of the current ablation procedure to determine one or more success predictions. That is, the optimization engine 101 may be utilized during the current ablation procedure to receive input specific to the patient 125 undergoing the current ablation procedure. Because the optimization engine 101 model has been constructed and trained in block 340, the optimization engine 101 may process the model and these current patient inputs to identify ablation gaps and generate new ablation targets (e.g., potential locations and success probabilities for consideration by the physician 115 to prevent short-term or long-term impairments). The optimization engine 101 may further generate predictions regarding the success and / or necessity of these new ablation targets.

[0077] 5A illustrates an example of a neural network 500, and FIG. 5B illustrates a block diagram of a method 501 implemented within the neural network 500, according to one or more embodiments. The neural network 500 operates to assist in the implementation of the ML / AI algorithms described herein (e.g., as implemented by the optimization engine 101 of FIGS. 1-2). The neural network 500 may be implemented in hardware, such as the machine 420 and / or hardware 450 of FIG. 4.

[0078] In exemplary operation, optimization engine 101 of FIG. 1 includes collecting data 410 from hardware 450. In neural network 500, input layer 510 is represented by multiple inputs (e.g., inputs 512 and 514 of FIG. 5A ). With reference to block 520 of method 501, input layer 510 receives inputs 512 and 514. Inputs 512 and 514 may include biometric data. For example, collecting 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) from one or more treatment records of hardware 450 into a dataset (represented by data 410). According to one or more embodiments, inputs 512 and 514 may include the 12 input ECG leads of system 100.

[0079] According to one or more embodiments, with respect to feature extraction for the training set, inputs 512 and 514 may include (e.g., short-term and / or long-term) outcomes, such as a pre-first procedure BS ECG, a 12-lead BS ECG post-procedure (e.g., as in NSR), patient categorical / numerical information (e.g., gender, left atrial volume, age, body mass index as described herein), and categorical / numerical information indicated from ECG recordings or real-time ECG signals from a link or other means.

[0080] In block 525 of method 501, neural network 500 encodes inputs 512 and 514 using any portion of data 410 and one or more expected action outcomes generated by ML / AI system 400 to generate 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 generated by an element-wise activation function (e.g., a sigmoid function or a rectified linear function) of optimization engine 101 of FIG. 1. As shown in FIG. 5A, inputs 512 and 514 are provided to hidden layer 530, which is shown to include nodes 532, 534, 536, and 538. Neural network 500 executes processing through 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 layer 510 and layer 530 can be viewed as an encoder stage that takes input 512 and input 514 and forwards them to a deep neural network (in layer 530) to learn smaller representations of some of the inputs (e.g., resulting latent representations).

[0081] The deep neural network may be a CNN, a long-short-term memory neural network, a fully connected neural network, or a combination thereof. This encoding results in dimensionality reduction of the inputs 512 and 514. Dimensionality reduction is the process of reducing the number of random variables being considered (in the inputs 512 and 514) by obtaining a set of key variables. For example, dimensionality reduction may be feature extraction, which transforms data (e.g., the inputs 512 and 514) from a high-dimensional space (e.g., greater than 10 dimensions) to a low-dimensional space (e.g., two to three dimensions). Technical effects and advantages of dimensionality reduction include reducing the time and storage space requirements of the inputs 512 and 514, improving the visualization of the inputs 512 and 514, and improving parameter interpretability for machine learning. This data transformation may be linear or nonlinear. The receiving (block 520) and encoding (block 525) operations may be considered the data preparation portion of a multi-stage data manipulation by the optimization engine 101.

[0082] At block 545 of method 510, neural network 500 decodes the latent representation. The decoding stage receives the encoder output (e.g., the resulting latent representation) and attempts to reconstruct a particular form of input 512 and input 514 using another deep neural network. In this regard, nodes 532, 534, 536, and 538 are combined to generate output 552 at output layer 550, as shown at block 560 of method 510. That is, output layer 590 reconstructs input 512 and input 514 with reduced dimensionality but without signal interference, signal artifacts, and signal noise. An example of output 552 includes cleaned biometric data (e.g., a clean / denoised version of IC ECG data, etc.). According to one or more embodiments, a 12-lead BS ECG CNN autoencoder is utilized as neural network 500 for 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, the output 552 includes a reconstructed ECG from data provided by a 12-lead BS ECG. Technical effects and benefits of the cleaned biometric data include enabling more accurate monitoring, diagnosis, and treatment of any number of various disorders.

[0083] At block 380, the optimization engine outputs an ablation recommendation based on one or more success predictions. According to one or more embodiments, the optimization engine 1010 provides one or more user interfaces on the display 165 showing a mapping of the current ablation procedure and the ablation recommendation. The ablation recommendation includes areas for ablation based on one or more success predictions and the probability of a repeat procedure. In this manner, the optimization engine 1010 provides the physician 115 with an indication of whether repeating any procedure is likely to have a positive outcome and provides a correct / suggested course of action for such a decision. Thus, technical effects, advantages, and benefits of the optimization engine include increasing the probability of success of the next procedure and / or reducing risk to the patient by eliminating unnecessary subsequent procedures.

[0084] 6 illustrates a graph 600 according to one or more exemplary embodiments. A method 600 (e.g., a method implemented by optimization engine 101 of FIGS. 1 and / or 2 ) according to one or more exemplary embodiments is illustrated. Method 600 is described with respect to an ablation procedure by way of example and ease of explanation. Method 600 identifies ablation gaps and provides a success prediction through multi-stage manipulation of data to improve the diagnosis and treatment of cardiac arrhythmias.

[0085] In general, the success rate of treating atrial arrhythmias with catheter ablation is not always completely successful. For example, a portion of patients (e.g., 5-40%) experience atrial arrhythmias one year later. These patients may suffer from reconnections in the ablation chain, which may require repeat ablation at a previously ablated location, or may suffer from disease recurrence within a driver not targeted by ablation in the first procedure. Method 600 attempts to avoid unnecessary subsequent procedures while identifying ablation gaps and making recommendations to increase the success rate of necessary subsequent procedures.

[0086] Method 600 begins at block 605, where optimization engine 101 receives input from previous cases (e.g., previous mapping and ablation procedures). In an actual embodiment, optimization engine 101 analyzes the previous cases with and without re-run procedures to derive data 410 and performance metrics as input.

[0087] According to one or more embodiments, in treating atrial or ventricular arrhythmias, the optimization engine 101 places ablation applications next to each other in an adjacent fashion to create adjacent ablation lines, where gaps in the lines due to lesions not being deep enough or close enough together would likely cause electrical breaches through the ablation chain, rendering the ablation chain ineffective. These areas of breach are very difficult to manually locate and identify, leading to longer procedures with lower success rates.

[0088] According to one or more embodiments, the data 410 and performance metrics may be obtained via maps with injury chains, anatomical maps with wall depth information, or anatomical reconstructions and / or electrical maps. To support the predictions of method 600, the optimization engine 101 may utilize data from previous ablations, such as ablation sites, ablation indexes, and anatomical maps, both from the initial ablation study and any rerun procedures. The data 410 and performance metrics may also be obtained using backup studies. This data 410 and performance metrics may be compared to the rerun locations before reruns. In some embodiments, the data 410 and performance metrics (e.g., for training) may be obtained from the magnetic field around the patient 125 through magnetic sensors included in the catheter 110. The data 410 and performance metrics may also be obtained using ACL features, electrode sensors using signal filter algorithms, meshes / images, registration algorithms, and ablation index parameters and algorithms.

[0089] Block 610 trains the optimization engine 101. In this regard, the optimization engine 101 creates / builds a model that can be used in real-time procedures to identify potential areas for the physician 115 to revisit and revalidate these areas to avoid treatment failure, treatment extension, or re-run procedures.

[0090] 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 case summary by physician 115) may be input into unsupervised algorithms, deep learning algorithms, autoencoders, and / or backpropagation algorithms for analysis by optimization engine 101. The data 410 and performance metrics may be preprocessed to extract relevant features for the task of predicting rerun success rates and assessing the patient's risk of needing a rerun procedure, both for specific patients and similar subgroups of patients. The optimization engine 101 may analyze data regarding potential lost ablation procedures to attempt to determine whether the ablation will require reruns. That is, by having the data 410 and performance metrics regarding outcomes, and which procedures required rerun procedures and where ablations were placed to treat patients in the rerun procedures, the optimization engine 101 can learn whether a particular ablation procedure will require reruns.

[0091] 7 illustrates a graph 700 that includes one or more aspects of the ML / AI algorithms of optimization engine 100. As shown, data 712, 714, and 716 may be input to one or more autoencoders 722 and 724 and trees 730 and 750 representing one or more ML / AI algorithms, outputting probabilities of rerun 780. According to one or more embodiments, additional inputs may include outcomes (e.g., short-term and / or long-term), such as categorical / numerical information indicated from ECG recordings or real-time ECG signals from a link or other means.

[0092] Data 712 may include a baseline recording of a 12-lead ECG and / or signals from a stationary catheter, such as a coronary sinus (CS) catheter. Data 714 may include data after an ablation procedure. According to one or more embodiments, data 712 and data 714 are fed through pre-trained CNN autoencoders (e.g., autoencoders 714 and 716 to provide a training data set).

[0093] In block 620, the optimization engine 101 receives data regarding the performance of the ablation procedure for the current patient (e.g., patient 125). The optimization engine 101 presents the data, as described below, regarding the performance of the current ablation procedure. For example, during a PV isolation procedure, anatomical and electrical data is acquired over a significant portion of the atrium. This information can provide an indication of whether additional ablation steps will be required based on the model and optimization engine 101 analysis in block 630.

[0094] Block 630 executes the optimization engine 101. For example, the optimization engine 101 compares current data with a model to predict success, whether short-term or long-term, for the current ablation procedure. Block 630 may include sub-blocks 640 and 650. In sub-block 640, the optimization engine 101 analyzes the data to determine an ablation gap. In sub-block 650, the optimization engine 650 uses the ablation gap to predict the success of the ablation procedure.

[0095] According to one or more embodiments, optimization engine 101 analyzes this data with respect to data 410, performance metrics, and models to determine potential ablation gaps. Returning to FIG. 7 , data 716 may represent data including categorical information such as gender, weight, Body Mass Index (BMI), atrial volume, left atrial volume, CHADS or CHADS2 (i.e., scores used to determine treatment for atrial fibrillation patients at risk for heart attack). In this manner, data 712, 714, and 716 are analyzed together via trees 730 and 750. Tree 730 may be a fully connected neural network with 10 hidden layers, to which, for example, pre-ablation procedure and post-ablation procedure data 712 and 714, as well as categorical data 716, are fed. The output of tree 730 may then be fed to tree 750, which has a single hidden layer with a single neuron, with an output for probability of rerun 780.

[0096] Once the current data is analyzed, the optimization engine 101 utilizes the potential ablation gap and model determination to predict the short-term and long-term success of the ablation procedure. For example, predictions of whether a repeat procedure is necessary can be obtained by learning parameters of the current patient 125 (e.g., learning patient and tissue characteristics through index procedures) comparing procedure cases of similar patients, e.g., via unsupervised algorithms, deep learning algorithms, autoencoders, and / or the optimization engine's backpropagation algorithm. In addition to patient and tissue characteristics, the optimization engine 101 can learn additional ablations to be added to close abrupt reconnections, data points from each repeat procedure performed, and locations ablated to terminate arrhythmias in the repeat procedure, as well as other data points. Once learned, the optimization engine 101 can predict which locations are likely to be involved in short-term or long-term failures. The optimization engine 101 can recommend addressing any failures in the repeat procedure and / or placing special emphasis on any failures in the current ablation procedure. In this regard, the optimization engine 101 may identify regions for ablation outside of veins or areas prone to reconnection. The optimization engine 101 may accommodate arrhythmias other than aFib. Analyzing data from repeat procedures may contribute to understanding real-time ablation, whether gaps can be formed later (e.g., tissue healing), and at that location may visualize instructions to the physician 115.

[0097] At block 670, the optimization engine 101 provides output. The output may be provided to the display 165, via one or more user interfaces described herein, or the like. The output may 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 for potentially necessary ablations based on predictions to avoid electrical reconnections within the ablation chain. The optimization engine 101 may also output additional potential locations for ablations to avoid electrical reconnections.

[0098] According to one or more embodiments, the optimization engine 101 provides the physician 115 with an output indicating the likelihood of a retry based on the prediction. Returning to FIG. 7 , the probability of retry 780 can be a percentage, a score, or a value expressed on a scale (e.g., 0 to 1, with 0 being the lowest probability of retry). According to one or more embodiments, the optimization engine 101 can conclude the likelihood of retry for this patient based on the results of an ablation set (e.g., a training dataset). As described herein, an exemplary training dataset can include records of patients undergoing a first ablation procedure, as well as any clinical classification patient information and / or aFib status without a follow-up mapping procedure. That is, the optimization engine 101 provides the physician with an indication 115 of whether the current ablation is sufficiently good based on previous cases, or whether the current ablation may have potential gaps that would result from a retry, and suggests possible locations on the patient's cardiac 3D map.

[0099] In block 690, the optimization engine 101 receives feedback. Generally, feedback may include any information provided directly by the physician 115 before, during, or after the current ablation procedure to the optimization engine 101. The feedback may be provided to the display 165, etc., via one or more user interfaces described herein. According to one or more embodiments, if the physician 115 initiates an ablation procedure, there is information obtained before and during the procedure that can be used to determine whether a rerun procedure may be necessary. This information can be used to further train the model and optimization engine 101. This information can also be analyzed in real time using the ML / AI of the optimization engine 101 to instruct the physician 115 during the current ablation procedure if additional ablation or a rerun procedure is required or likely. That is, because it is desirable to prevent reruns based on previous study cases, a real-time display can help the physician 115 focus on specific areas and confirm and verify these areas to determine if ablation is sufficient.

[0100] According to one or more embodiments, the optimization engine 101 may track a treatment workflow (e.g., in atrial fibrillation) and learn this workflow and process pattern, identifying the anatomical reconstruction and mapping phase, insertion of the catheter 110 into the pulmonary vein, ablation phase, wait times for verification, repeat ablation in place, etc. In an aFib-specific embodiment, the optimization engine 101 may identify insertion of the catheter 110 into the pulmonary vein and whether an activity signal is measured on the catheter 110 for the purpose of verification of isolation.

[0101] If an activity signal is measured, the optimization engine 101 may identify and suggest the earliest activation on the Dx catheter that is likely to correlate with an electrical breach. The optimization engine 101 may then mark on the CARTO® system the most likely area causing the breach (marked with an arrow according to the likelihood of the area causing a breach, or by coloring on the map in any other way, or with any other potential indication). Thus, via ML / AI, the optimization engine 101 enables the identification of workflow steps where the operator intends to verify the short-term success of the ablation and / or the ability to link between the earliest signal on the catheter 110 and a specific location on the anatomy.

[0102] Furthermore, during the triangulation process, any acquired data may indicate a possible location of the arrhythmia origin, which is the most useful information for validating and finding the origin in the most effective data. The optimization engine 101 learns from previous maps, anatomy, and mapping sequences to recommend the best course of action at each point.

[0103] Thus, during the ablation procedure, any acquired data can be utilized by the optimization engine 101 to suggest areas for ablation to the physician 115 where the physician 115 will have more success and less chance of needing a re-run procedure. For example, the optimization engine 101 can read the position of the catheter 110 within the heart 120 from the moment the catheter 110 is inserted into the vein and generate on the screen a recommended ablation location based on the implemented ML algorithm and outcome prediction. Thus, the optimization engine 101 estimates ablation gaps from previous cases and locations where the physician 115 should perform ablation during the current procedure, learning from current data, with less need for a re-run procedure.

[0104] With reference to the ML / AI algorithms described herein, we now describe neural networks, autoencoders, and backpropagation algorithms.

[0105] An ANN contains a network of processing elements (artificial neurons) that can exhibit complex global behavior determined by the connections between the processing elements and element parameters. These connections in a neuronal network or circuit are modeled as weights. Positive weights reflect excitatory connections, while negative values ​​represent inhibitory connections. Inputs are modified by the weights and summed using linear combinations. An activation function may control the amplitude of the output. For example, the acceptable range of the output is typically 0 to 1, but can also be -1 to 1. ANNs are often adaptive systems that change their structure based on external or internal information flowing through the network.

[0106] In more practical terms, neural networks are nonlinear statistical data modeling or decision-making tools 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 through a data set. Self-learning arising from experience can occur within ANNs, allowing them to draw conclusions from complex and seemingly unrelated sets of information. The usefulness of artificial neural network models lies in the fact that they can be used to estimate and use functions from observations. Unsupervised neural networks can also be used to learn representations of inputs that capture salient features of the input distribution and, more recently, in deep learning algorithms that can implicitly learn distribution functions for observed data. Training with neural networks is particularly useful in applications where the complexity of the data (e.g., biometric data) or the task (e.g., monitoring, diagnosing, and treating any number of different diseases) makes the design of such functions impractical.

[0107] Neural networks can be used in a variety of fields. Therefore, internal ML / AI algorithms may generally include neural networks, divided according to the tasks to which they are applied. These divisions tend to fall into the categories of regression analysis (e.g., function approximation), including time series prediction and modeling; classification, including pattern and sequence recognition; novelty detection and continuous 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, chess, racing), pattern recognition (radar systems, face identification, object recognition), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis and treatment, financial applications, data mining (or knowledge discovery in databases, i.e., "Knowledge Discovery in Databases"), visualization, and email spam filtering. For example, it is possible to create semantic profiles of patient biometric data obtained from medical procedures.

[0108] According to one or more embodiments, the neural network may implement a long-short-term memory neural network architecture, a convolutional neural network (CNN) architecture, or the like. The neural network may be configurable with respect to multiple layers, multiple connections (e.g., encoder / decoder connections), regularization techniques (e.g., dropout), and optimization features.

[0109] Long-short-term memory neural network architectures include feedback connections and can process a single data point (e.g., an image) along with an entire sequence of data (e.g., speech or video). The units of a long-short-term memory neural network architecture can consist of a cell, an input gate, an output gate, and a forget gate; the cell remembers a value over any time interval, and the gates regulate the flow of information into and out of the cell.

[0110] A CNN architecture is a shared weight architecture with translational invariance properties, where each neuron in one layer is connected to every neuron in the next layer. Regularization techniques in CNN architectures can exploit hierarchical patterns in the data and organize more complex patterns using smaller, simpler patterns. When a neural network implements a CNN architecture, other configurable aspects of the architecture can include the number of filters in each stage, kernel size, and number of kernels per layer.

[0111] An autoencoder is an automatic, self-training algorithm. In some cases, the autoencoder includes a training algorithm that implements a deep learning training loss function, more specifically, an autoencoder clinically weighted MSE loss function. Furthermore, the autoencoder may operate in one or more modes. For example, a first mode may include building a dedicated graphic user interface that includes one or more filters. The dedicated GUI provides the ability to manually filter out noise components based on a set of predefined filters (raw data signals are typically recorded with noise). In this way, the autoencoder experiences at least two sets of signals, such as the original signal containing noise and the denoised signal used to train the autoencoder. A 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). The noise may include at least one of power line noise, contact noise, deflection noise, fluorescence noise, and ventricular far field noise.

[0112] An autoencoder can reconstruct an input from a corrupted version of itself by forcing hidden layers to find more robust features and, in particular, prevent relearning discriminatory information. In this regard, the autoencoder forces hidden layers to find more robust features (i.e., useful features that will constitute a better, higher-level representation of the input) and prevent the input from learning a particular identity (i.e., always reverting to the same value). Additionally, the autoencoder encodes the input (e.g., to preserve information about the input) to reverse the effects of a corrupting process that was probabilistically applied to the autoencoder's input. For example, an autoencoder clinical-weighted MSE loss function is a multi-stage data manipulation of an electrical signal to detect or quantify or detect high-frequency zones within the signal, and then uses the autoencoder clinical-weighted MSE loss function to enhance the reconstruction of the signal around atrial activity.

[0113] The backpropagation algorithm is used in deep learning for supervised learning, training feedforward neural networks. 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 a chain rule. The weights are updated to minimize the loss function. Additionally, gradient descent or variants such as stochastic gradient descent may be used.

[0114] 8 illustrates a gap finder method 800 according to one embodiment. 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 Ablation Index (AI), Average Temperature (T), Quality of Stability (QS), and Distance to Nearest Stable Site (DS).

[0115] The ablation index (AI) may be derived from the force, power, and time of ablation of a site. AI is defined by Equation 1:

[0116]

number

[0117] QS may be derived from a site stability algorithm. The site stability algorithm described in detail in U.S. Patent Application No. 17 / 188,844, filed March 1, 2021, by Meir Bar-Tal, Erez Silberschein, Liron Shmuel Mizrahi, Alona Sigal, and Aharon Turgeman, entitled "PROBE-CAVITY MOTION MODELING," is incorporated herein by reference. DS may be determined using the 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. A very stable ablation may provide a low stability index value, while a less stable ablation may provide a high stability index value.

[0118] The gap index for the ablation site is given by Equation 2: GI=f(AI,T,QS,DS) Equation 2 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.

[0119] As shown in Figure 8, the method includes inserting an ablation catheter into a desired region at 810, followed by ablating multiple locations in the region using the ablation catheter at 820. Once all or the desired locations have been ablated, ablation data is collected at each location at 830, and a processor calculates the GI for each location at 840. The processor highlights ablation locations with high GI, i.e., sites with a high probability of being gaps, on the map or depiction at 850. By indicating high probability gap locations to the physician, the time required for the physician to search for gaps is reduced.

[0120] As will be appreciated, relationships between various site parameters can be important. Specifically, relationships may exist within and between various parameters: AI, T, QS, and DS. The present systems and methods relate to using parameters to verify or validate other parameters to ensure high-quality ablations and calculations within the GI. Details of important parameter combinations and how these inferences are made are provided below. For example, a set of parameters (position, contact force, temperature, impedance) may all need to be met for an ablation to be considered successful. In the examples of FIGS. 10-14 below, various combinations of these four parameters are missing, which, as will be explained, leads to insufficient or questionable ablations.

[0121] Figures 9-14 provide graphs of data related to the above-mentioned parameters to demonstrate the significance and relationships associated with the parameters. Figure 9 generally provides a framework for the interpretation of the data and for the analysis that will be provided in the other Figures 10-14.

[0122] Specifically, Figure 9 shows a set of generic graphs 900. In the first graph of the set, the left axis plots the location of xyz locations 910 as seen in a CARTO system. The data may include filtering, such as heart rate filtering. The right axis of the first graph of the set represents the respiration signal, with reference to plot 920.

[0123] As shown in the second graph, the left axis includes temperature, referenced to the plot of maximum temperature 930, and temperature, referenced to the plot of six temperatures of QDOT 940. The right axis of the second graph provides a scale of impedance, referenced to the plot of impedance 950.

[0124] As shown in the third graph, the left side provides a set scale for power, and the right side provides a scale for current. As shown, the current is a power track with only a small deviation.

[0125] As shown in the fourth plot of the set, on the left there is a force scale referenced to the force 960 plot.

[0126] Generally, the above parameters are included in a graph of the data to demonstrate the significance and relationships associated with the parameters, as provided in FIG.

[0127] FIG. 10 shows a set of parameter graphs 1000 during an ablation procedure such as that described above with respect to FIG. 9. The set of graphs 1000 illustrates a configuration in which position is stable and contact force is stable. Specifically, for position, the first graph in the set provides a position curve showing small variations in the plot over a few millimeters. For contact force, the fourth plot in the set shows that contact force fluctuates slightly over the scale of a few grams. The third plot in the set shows power and current generally consistent with those provided in FIG. 9. For the second portion of the set of graphs, a temperature drop and impedance rise are illustrated. The temperature drops by more than about 5° C. in a short period of time (1010), while the impedance rises by more than about 5 Ω (1020). This combination of temperature drop and impedance rise may indicate that the catheter is not heating the same spot on the tissue.

[0128] 11 shows a set of graphs 1100 of the parameters of FIG. 9. The set of graphs 1100 shows stable positions. Specifically, with respect to position, the first graph in the set provides a position curve showing small variations in the plot of a few millimeters. The set of graphs 1100 shows a low applied contact force 1110 applied to tissue, resulting in a low temperature rise and associated impedance drop.

[0129] FIG. 12 illustrates a set of graphs 1200 of the parameters of FIG. 9. The set of graphs 1200 shows that a sliding catheter results in poor stability quality 1210 during an ablation procedure. Specifically, with respect to position, the first graph in the set provides a position curve that exhibits greater variation in the plot. While force proves acceptable in the fourth plot in the set of graphs 1200, the temperature rise 1220 in the second graph in the set of graphs 1200 is not of good quality, which may be the result of insufficient positional stability.

[0130] FIG. 13 illustrates a set of graphs 1300 of the parameters of FIG. 9 . Force proves acceptable in the fourth plot of set of graphs 1200. Power and current represent a duration of approximately 4 seconds in the third graph of set of graphs 1300. Set of graphs 1300 illustrates that adequate average force was present during the ablation procedure (fourth graph of set) and ablation occurred over a 4-second duration (third graph of set), but the site stability algorithm shown indicates that only 2.5 seconds of the 4 seconds were sufficiently stable (1310). From this information, even if the ablation was of adequate duration, a lesser amount of quality stability over 2.5 seconds is not sufficient for successful ablation. This is further illustrated in the effect of instability on temperature rise 1320.

[0131] FIG. 14 illustrates a set of graphs 1400 of the parameters of FIG. 9. The set of graphs 1400 shows stable position (within threshold) and stable contact force during the ablation procedure. Specifically, with respect to position, the first graph in the set provides a position curve showing small variations in the plot of a few millimeters. Force proves acceptable in the fourth plot of the set of graphs 1400. A temperature drop 1410 and impedance rise 1420 are shown in the second graph in the set of graphs 1400. This temperature drop and impedance rise may indicate that the ablation is not heating the same spot on the tissue.

[0132] 9-14 show the relationship between various site parameters for various parameters of AI, T, QS, and DS. As will be appreciated, other parameters may also be used.

[0133] In particular, in Figure 11, the graph shows that a 4 second ablation duration can be nulled using other parameters to arrive at a real ablation (or effective time) of 2.5 seconds, which is less than the time required for ablation. This "second order" is further illustrated in Figures 10 and 14, where position and force are stable, but temperature drops and impedance increases indicate that ablation is occurring at different spots.

[0134] 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 across multiple variables as described above, standards may be used to determine significance parameters and their respective weights to predict gaps as described above.

[0135] The flowcharts and block diagrams in the figures illustrate the structure, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the depicted logical function(s). In some alternative implementations, the functions shown in the blocks may occur out of the order shown in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, may be implemented by a dedicated hardware-based system that performs the specified function or operation, or may operate or be executed by a combination of dedicated hardware and computer instructions.

[0136] Although features and elements have been described above in particular combinations, those skilled in the art will understand that each feature or element can be used alone or in combination with other features and elements. It should be noted that the methods described herein may be implemented in a computer program, software, or firmware embodied in a computer-readable medium for execution on a computer or processor. Computer-readable medium, as used herein, should not be construed as a signal that is itself ephemeral, such as an electric 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 through a current line.

[0137] Examples of computer-readable media include electrical signals (transmitted via wired or wireless connections) and computer-readable storage media. Examples of computer-readable storage media include, but are not limited to, registers, cache memory, 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 memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random-access memory (SRAM), and memory sticks. A processor together with software may implement a radio frequency transceiver for use in a terminal, base station, or any host computer.

[0138] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a," "an," and "the" are intended to include the plural unless the context clearly dictates otherwise. It is further understood that the terms "comprise" and / or "comprising," when used herein, indicate the presence of stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0139] The description of different embodiments herein is provided for illustrative purposes, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles, practical applications, or technical improvements of the embodiments compared to technologies found on the market, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0140] [Embodiment] (1) A computer-implemented method, the computer-implemented method comprising: receiving, by an optimization engine executed by one or more processors, data including performance metrics of the mapping and ablation procedures; generating, by the optimization engine, predicted treatment outcomes for the mapping and the ablation procedure based on the data; generating, by the optimization engine, one or more success predictions for the current ablation procedure using the predicted treatment outcomes; performing an ablation and calculating a gap index of said ablation; and outputting the gap index of the ablation. (2) The method of embodiment 1, wherein performing ablation includes ablating a series of adjacent locations to create a ring or line of ablated tissue. (3) The method of embodiment 1, wherein the ablation performed includes providing one or more ablations to prevent transmission of radio waves. (4) The method of embodiment 1, wherein the one or more success predictions search for gaps in the ablation ring or ablation line. (5) The method described in embodiment 1, wherein the higher the gap index, the higher the probability of a gap in the ablation.

[0141] (6) The method of embodiment 1, wherein the data includes at least an ablation index derived from at least one of the force, power, and time of ablation of the site. (7) The method of embodiment 1, wherein the data includes at least the average or maximum temperature of the ablation at the site. (8) The method of embodiment 1, wherein the data includes at least a stability quality derived from a site stability algorithm. (9) The method of embodiment 1, wherein the data includes at least the distance to the nearest stable site using a site stability algorithm. (10) The method of embodiment 1, wherein the gap index of the ablation is a function of at least the ablation index, the average temperature of the ablation, the quality of stability, and the distance to the nearest stable site.

[0142] (11) The method of embodiment 1, wherein a gap index is calculated for each position where ablation is performed. (12) The method of embodiment 1, further comprising outputting a map of the ablation site highlighting ablation locations with high gap indices. (13) The method of embodiment 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 an ablation on a patient's heart; a memory and a processor for processing the received data; and receiving, by an optimization engine executed by one or more processors, data including performance metrics of the mapping and ablation procedures; generating, by the optimization engine, predicted treatment outcomes for the mapping and the ablation treatment based on the data; generating, by the optimization engine, one or more success predictions for the current ablation procedure using the predicted treatment outcomes; performing an ablation and calculating a gap index for said ablation; a memory and a processor operatively configured to output the gap index of the ablation. (15) The system of embodiment 14, wherein performing ablation includes ablating a series of adjacent locations to generate a ring or line of ablated tissue.

[0143] (16) The system of embodiment 14, wherein the ablation performed includes providing one or more ablations to prevent transmission of radio waves. (17) The system of embodiment 14, wherein the one or more success predictions search for gaps in the ablation ring or ablation line. (18) The system described in embodiment 14, wherein the higher the gap index, the higher the probability of a gap in the ablation. (19) The system of embodiment 14, wherein the data includes at least an ablation index derived from at least one of the force, power, and time of ablation of the site. (20) The system of embodiment 14, wherein the data includes at least an average or maximum temperature of the ablation at the site.

[0144] (21) The system of embodiment 14, wherein the data includes at least a stability quality derived from a site stability algorithm. (22) The system of embodiment 14, wherein the data includes at least the distance to the nearest stable site using a site stability algorithm. (23) The system of embodiment 14, wherein the gap index of the ablation is a function of at least the ablation index, the average temperature of the ablation, the quality of stability, and the distance to the nearest stable site. (24) The system of embodiment 14, wherein a gap index is calculated for each position where ablation is performed. (25) The system of embodiment 14, further comprising outputting a map of the ablation site highlighting ablation locations with high gap indices.

[0145] (26) The system of embodiment 14, wherein a high gap index is determined by thresholding the gap index.

Claims

1. 1. A system, comprising: an input / output (I / O) device for receiving data from a catheter configured to perform ablation on a patient's heart; a memory and a processor for processing the received data; and receiving, by an optimization engine executed by one or more processors, data including performance metrics of the mapping and ablation procedures; generating, by the optimization engine, predicted treatment outcomes for the mapping and the ablation treatment based on the data; generating, by the optimization engine, one or more success predictions for the current ablation procedure using the predicted treatment outcomes; performing an ablation and calculating a gap index for said ablation; a memory and a processor operatively configured to output the gap index of the ablation.

2. The system of claim 1 , wherein performing ablation comprises ablating a series of adjacent locations to create a ring or line of ablated tissue.

3. The system of claim 1 , wherein the ablation performed comprises providing one or more ablations to prevent transmission of radio waves.

4. The system of claim 1 , wherein the one or more success predictions look for gaps in an ablation ring or ablation line.

5. The system of claim 1 , wherein the higher the gap index, the higher the probability of a gap in the ablation.

6. The system of 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 system of claim 1 , wherein the data includes at least an average or maximum temperature of the ablation at the site.

8. The system of claim 1 , wherein the data includes at least a stability quality derived from a site stability algorithm.

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

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

11. The system of claim 1 , wherein a gap index is calculated for each location at which ablation is performed.

12. The system of claim 1 , further comprising outputting a map of the ablation site highlighting ablation locations with high gap indices.

13. The system of claim 1 , wherein a high gap index is determined by thresholding the gap index.

14. 1. A computer-implemented method, the computer-implemented method comprising: receiving, by an optimization engine executed by one or more processors, data including performance metrics of the mapping and ablation procedures; generating, by the optimization engine, predicted treatment outcomes for the mapping and the ablation procedure based on the data; generating, by the optimization engine, one or more success predictions for the current ablation procedure using the predicted treatment outcomes; performing an ablation and calculating a gap index for said ablation; and outputting the gap index of the ablation.

15. 15. The method of claim 14, wherein performing ablation comprises ablating a series of adjacent locations to create a ring or line of ablated tissue.

16. 15. The method of claim 14, wherein the ablation performed comprises providing one or more ablations to prevent transmission of radio waves.

17. The method of claim 14 , wherein the one or more success predictions look for gaps in an ablation ring or ablation line.

18. The method of claim 14, wherein the higher the gap index, the higher the probability of a gap in the ablation.

19. The method 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 method of claim 14 , wherein the data includes at least an average or maximum temperature of the ablation at the site.

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

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

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

24. The method of claim 14 , wherein a gap index is calculated for each location at which ablation is performed.

25. The method of claim 14 , further comprising outputting a map of ablation sites highlighting ablation locations with high gap indices.

26. The method of claim 14 , wherein a high gap index is determined by thresholding the gap index.

Images