Arrhythmia classification for cardiac mapping

Abstract

The present invention is entitled "Arrhythmia Classification for Cardiac Mapping". The present invention discloses systems and methods for cardiac mapping. The technology includes extracting beat segments from biometric data obtained from a patient during an electrophysiological procedure, and classifying the beat segments into clusters, each cluster representing a type of arrhythmia. Maps are generated to visualize the biometric data. Each map is generated based on data associated with a beat segment in one of the clusters.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 073,217 filed on September 1, 2020 and U.S. Provisional Patent Application No. 63 / 090,494 filed on October 12, 2020. Both disclosures are hereby incorporated by reference herein in their entirety. Background Art

[0003] Electrophysiology (EP) procedures are assessments of electrical activity in the heart used to diagnose abnormal heartbeats or arrhythmias. EP procedures can be performed using surface electrodes or intracardiac electrodes (where a catheter is inserted into the heart through a blood vessel to measure electrical activity). EP procedures provide cardiac images generated based on the measured electrical activity, including images of cardiac tissue, chambers, veins, arteries, and / or pathways. Conventional cardiac images can visualize electrical activity in the heart by measuring electrical potentials, thereby presenting the voltage of the beats (propagating pulses generated by arrhythmias) at various tissue locations, i.e., voltage maps. Cardiac images can also visualize electrical activity by measuring local activation times (LATs), thereby presenting the arrival times of the beats to various tissue locations, i.e., LAT maps.

[0004] An inherent assumption of cardiac imaging is that the type of arrhythmia that generates the electrical activity captured by cardiac imaging does not change rapidly. However, in practice, during an EP procedure, patients can tolerate arrhythmias that change their nature rapidly and spontaneously. Therefore, cardiac mapping (voltage mapping or LAT mapping) may involve visualizing data from beats caused by different arrhythmia types. Such erroneous cardiac mapping affects the clinical interpretation of arrhythmia conditions. Reliable techniques are needed to ensure that each cardiac image during an EP procedure visualizes the electrical activity generated by one class of arrhythmias. Summary of the invention

[0005] Aspects of the present application disclose methods for cardiac mapping. The methods disclosed herein include: receiving biometric data obtained from a patient; extracting beat segments from the biometric data; classifying the beat segments into clusters, each cluster representing a type of arrhythmia; and in response to the number of clusters in which the beat segments are classified being below a threshold number, generating at least one map based on data associated with a beat segment in one of the clusters.

[0006] Aspects of the present application also disclose a system for cardiac mapping. The system disclosed herein includes at least one processor and a memory storing instructions. These instructions, when executed by the at least one processor, cause the system to: receive biometric data obtained from a patient; extract beat segments from the biometric data; classify the beat segments into clusters, each cluster representing a type of arrhythmia; and in response to the number of clusters in which the beat segments are classified as being below a threshold number, generate at least one mapping diagram based on data associated with a beat segment in one of the clusters.

[0007] In addition, aspects of the present application disclose a non-transitory computer-readable medium including instructions executable by at least one processor to perform a method for cardiac mapping. The method disclosed herein includes: receiving biometric data obtained from a patient; extracting beat segments from the biometric data; classifying the beat segments into clusters, each cluster representing a type of arrhythmia; and in response to the beat segments being classified into a number of clusters below a threshold number, generating at least one map based on data associated with the beat segments in one of the clusters. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] A more detailed understanding may be obtained from the following detailed description provided by way of example in conjunction with the accompanying drawings, in which like reference numerals indicate like elements, and in which:

[0009] Figure 1 is a diagram of an exemplary cardiac system upon which one or more features of the present disclosure may be implemented;

[0010] Figure 2 It can be Figure 1 A block diagram of an exemplary system of an exemplary cardiac system deployment based on which one or more features of the present disclosure may be implemented;

[0011] Figure 3 is a functional block diagram of an exemplary system for cardiac mapping of data based on clustering, based on which one or more features of the present disclosure may be implemented;

[0012] Figure 4 is a flow chart of an exemplary method for cardiac mapping of data based on clustering, based on which one or more features of the present disclosure may be implemented;

[0013] Figure 5 is a flow chart of an exemplary method for classifying beat segments into clusters based on beat features, based on which one or more features of the present disclosure may be implemented;

[0014] Figure 6 is a diagram of an exemplary clustering method based on which one or more features of the present disclosure may be implemented;

[0015] FIG. 7 is a flow chart of an exemplary method for classifying beat segments into clusters based on predictions of arrhythmia types, including a method for training a predictor ( Fig. 7A ) and the application method of the trained predictor ( Figure 7B ), based on which one or more features of the present disclosure can be implemented; and

[0016] Figure 8 is a functional block diagram of an exemplary machine learning system based on which one or more features of the present disclosure may be implemented. DETAILED DESCRIPTION

[0017] Disclosed herein are systems and methods for cardiac mapping of data based on clustering. For example, clusters may be formed based on arrhythmia types or electrocardiogram (ECG) data features. Data associated with the clusters may then be used to create a cardiac map that visualizes electrical activity corresponding to the arrhythmia types or ECG data features associated with the clusters. In various aspects of the present invention, biometric data measured relative to a patient during an EP procedure (e.g., including body surface (BS) ECG data, intracardiac electrocardiogram (IC) ECG data, ablation data, and catheter electrode position data) is processed. Beat segments extracted from the ECG data are classified into clusters based on the type of arrhythmia that produces the arrhythmia. Beat segments may be classified into clusters based on predicted arrhythmia types or based on beat features. Thus, a cardiac map corresponding to arrhythmia clusters may be generated, i.e., biometric data associated with the clusters may be visualized in each cardiac map.

[0018] Figure 1 1 is an illustration of an exemplary cardiac system 100 upon which one or more features of the present disclosure may be implemented. System 100 may be used to collect, process, and visualize biometric data associated with a heart 120 of a patient 125, which is shown as being located on a surface 130, during a cardiac procedure performed by a physician (or medical professional) 115. System 100 may include a probe 110 and a display 165 connected to a console 160. Probe 110 may include a catheter 105 (having at least one electrode 106), a shaft 112, a sheath 113, and a manipulator 114. Inset 150 shows catheter 105 in an enlarged view and inset 140 shows catheter 105 within a cardiac chamber of heart 120. Note that each element and / or item of system 100 represents one or more of that element and / or item. Figure 1The example of system 100 shown can be modified to implement the aspects disclosed herein. The aspects disclosed herein can be similarly applied using other system components and settings.

[0019] According to various aspects disclosed herein, system 100 can be used to detect, diagnose and treat cardiac diseases. Cardiac diseases such as arrhythmias have always been common and dangerous medical conditions, especially in the elderly population. For patients with normal sinus rhythm, the heart (including atria, ventricles and excitatory conduction tissues) beats in a synchronous, patterned manner under the action of electrical excitation. This electrical excitation can be detected as an intracardiac signal. For patients with arrhythmias, abnormal areas of cardiac tissue do not follow the synchronous beating cycle associated with normal conduction tissues like patients with normal sinus rhythm. For those patients with arrhythmias, abnormal areas of cardiac tissue conduct abnormally to adjacent tissues, thereby disrupting the cardiac cycle into an asynchronous rhythm. This asynchronous rhythm can also be detected by an intracardiac signal. It was previously known that such abnormal conduction occurs in various areas of the heart, such as in the sinoatrial (SA) node area, along the conduction pathway of the atrioventricular (AV) node, or in the myocardial tissue that forms the walls of the ventricular and atrial heart chambers.

[0020] The catheter 105 may be configured to obtain biometric data including electrical signals of an organ in the body (e.g., heart 120) and / or be configured to ablate tissue regions of a cardiac chamber of the heart 120. The electrodes 106 of the catheter may represent any element capable of being configured to ablate a tissue region or obtain biometric data associated with the heart, such as a tracking coil, a piezoelectric transducer, an electrode, or a combination of elements. For example, the catheter 105 may use the electrodes 106 to generate images based on intravascular ultrasound and / or MRI. As another example, the catheter 105 may be used to ablate cardiac tissue by targeting those tissues with energy. The energy may be thermal energy and may cause damage to these tissue regions starting from the surface of the tissue region and extending into the thickness of the tissue region.

[0021] The console 160 of the system 100 may include a processor 161, a memory 162, and an I / O interface 163. According to various aspects described herein, the processor 161 may represent one or more processors 161 configured to execute software modules associated with training and application of an arrhythmia predictor. The memory 162 may represent any non-transitory tangible medium capable of facilitating the storage of computer instructions and data associated with executing the software modules. In one aspect, one or more of the software modules associated with training and application of an arrhythmia predictor may be executed external to the console 160, such as in the catheter 105 or other external device (e.g., a mobile device, a cloud-based device, or an independent processor). In this case, one or more of these software modules may be transmitted over a network. The I / O interface 163 may enable data to be sent to and received from the catheter 105, as well as control messages to be sent and received between components of the system 100. For example, the I / O interface 163 may enable the console 160 to receive signals from and / or transmit signals to at least one electrode 106 of the catheter 105. The 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) electrocardiogram or electromyogram (EMG) signal conversion integrated circuit. The console 160 may process and / or store signals from the A / D ECG or EMG circuitry, or may send the signals to an external device for processing and / or storage.

[0022] The display 165 of the system 100 may be connected to the console 160. During a procedure, the console 160 may facilitate visualization (rendering) of a body part on the display 165 for viewing by the physician 115, and may store the rendered body part data in the memory 162. In one aspect, the physician 115 may be able to manipulate the rendered body part using one or more input devices, such as a touch pad, a mouse, a keyboard, or a gesture recognition device. For example, the input device may be used to change the position of the catheter 105 so that the rendering of the body part is updated. The display 165 may include a touch screen that may be configured to accept other inputs from the medical professional 115 in addition to the input for controlling the rendering of the body part. It is noted that the display 165 may be located locally or remotely from the console 160, such as at another hospital or healthcare provider site. In addition, the system 100 may be part of a surgical system that is configured to obtain anatomical measurements and electrical measurements of a patient's organ, such as the heart, and to perform a cardiac ablation procedure. An example of such a surgical system is the Carto Surgical System sold by Biosense Webster. ® system.

[0023] Figure 2 It can be Figure 1 2 is a block diagram of an example system 200 for an example cardiac ablation system deployment of an example cardiac ablation system of the present disclosure, based on which one or more features of the present disclosure may be implemented. System 200 may include a monitoring and processing system 205, a local system 280, and a remote system 290. In an alternative form, monitoring and processing system 205 may represent console 160 of system 100. Monitoring and processing system 205 may include patient biometric sensor 210, processor 220, memory 230, input device 240, output device 250, and transceiver 260 (i.e., a transmitter-receiver that communicates with network 270). System 205 may continuously or periodically monitor, store, process, and transmit various patient biometrics via network 270. Examples of patient biometrics include electrical signals (e.g., ECG signals), anatomical images, blood pressure data, blood glucose data, and temperature data. Patient biometrics may be monitored and may be transmitted to treat various diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathy, and coronary artery disease) and autoimmune diseases (e.g., type I and type II diabetes).

[0024] The monitoring and treatment system 205 can be in vivo in the patient's body—for example, the system 205 can be implanted subcutaneously, inserted orally or surgically, inserted intravenously or intraarterially, inserted via an endoscopic or laparoscopic procedure. Alternatively, the system 205 can be external to the patient, for example attached to the patient's skin. In one aspect, the system 205 can include both components that are in vivo in the patient's body and components that are external to the patient's body.

[0025] The monitoring and processing system 205 may represent multiple monitoring and processing systems 205 that may process the patient's biometric data in parallel and / or in communication with each other or with a server via a network. One or more systems 205 may acquire or receive all or part of the patient's biometric data (e.g., electrical signals, anatomical images, blood pressure, temperature, blood sugar levels, or other biometric data). The one or more systems 205 may also acquire or receive additional information associated with the acquired or received biometric data of the patient from one or more other systems 205. The additional information may be, for example, diagnostic information and / or information obtained from a device such as a wearable device. Each monitoring and processing system 205 may process data acquired by itself and may process data received from another system 205.

[0026] Patient biometric sensor 210 may be one or more sensors that can be configured to sense biometric data. For example, sensor 210 may be an electrode, temperature sensor, blood pressure sensor, blood glucose sensor, blood oxygen sensor, pH sensor, accelerometer, or microphone configured to acquire electrical signals (e.g., bioelectric signals originating from the heart). In one aspect, system 205 may be an ECG monitor that measures ECG signals originating from the heart. In such cases, sensor 210 may be one or more electrodes that can be configured to acquire ECG signals. ECG signals can be used to treat various cardiovascular diseases. In one aspect, patient biometric sensor 210 may also include a catheter, a probe, a blood pressure cuff, a weight scale, a bracelet (e.g., a smart watch biometric tracker), a glucose monitor, a continuous positive airway pressure (CPAP) machine, or any other device that provides biometric data or other data about the patient's health.

[0027] The transceiver 260 may include a transmitter component and a receiver component. These transmitter and receiver components may be integrated into a single device or implemented separately. The transceiver may provide a connection between the system 205 and other systems or servers via a communication network 270. The network 270 may be a wired network, a wireless network, or a combination of wired and / or wireless networks. The network 270 may be a short-range network (e.g., a local area network (LAN) or a personal area network (PAN)). Various short-range communication protocols (such as Bluetooth, Wi-Fi, Zigbee, Z-Wave, near field communication (NFC), ultra-band, Zigbee, or infrared (IR)) may be used to send or receive information via the short-range network. The network 270 may also be a long-range network (e.g., a wide area network (WAN), the Internet, or a cellular network). Various long-range communication protocols (such as TCP / IP, HTTP, 3G, 4G / LTE, or 5G / new radio) may be used to send or receive information via the long-range network.

[0028] The processor 220 may be configured to process biometric data of a patient, such as obtained by the sensor 210, and store the biometric data and / or processed biometric data in the memory 230. The processor 220 may also be configured to transmit the biometric data over the network 270 via the transmitter of the transceiver 260. Biometric data from one or more other monitoring and processing systems 205 may be received by the receiver of the transceiver 260. The processor 220 may employ a machine learning algorithm (e.g., based on a neural network), or alternatively, the machine learning algorithm may be employed by another processor, such as at the local system 280 or the remote system 290. In various aspects, the processor 220 may include one or more CPUs, one or more GPUs, or one or more FPGAs. In these aspects, the machine learning algorithm may be executed on one or more of these processing units. Similarly, the processor 220 may include an ASIC (such as an Intel FPGA) dedicated to performing deep learning calculations. ® Nervana ™ The processing unit executing the machine learning algorithm may be located in the medical procedure room or in another location (e.g., another medical facility or the cloud).

[0029] The input device 240 of the monitoring and processing system 205 can be used as a user interface. The input device 240 can include, for example, a piezoelectric sensor or a capacitive sensor configured to receive user input (such as a tap or touch). Therefore, the input device 240 can be configured to implement capacitive coupling in response to a user tapping or touching the surface of the system 205. Gesture recognition can be implemented through various capacitive couplings, such as resistive capacitance, surface capacitance, projected capacitance, surface acoustic wave, piezoelectric, or infrared touch. The capacitive sensor can be placed on the surface of the input device 240 so that a tap or touch of the surface activates the system 205. The processor 220 can be configured to selectively respond to different tap patterns of the capacitive sensor (e.g., a single click or double click on the input device 240) so that different functions of the system 205 (e.g., acquisition, storage, or transmission of data) can be activated based on the detected pattern. In one aspect, for example, when a gesture is detected and recognized, audible feedback can be given to the user from the system 205.

[0030] In one aspect, a local system 280 that can communicate with the monitoring and processing system 205 via the network 270 can be configured to act as a gateway to the remote system 290 through another network 285 accessible to the local system 280. The local system 280 can be, for example, a smart phone, a smart watch, a tablet computer, or other portable smart device. Alternatively, the local system 280 can be a fixed or stand-alone device. Patient biometric data can be transmitted between the local system 280 and the monitoring and processing system 205. In one aspect, the local system 280 can also be configured to display the acquired patient biometric data and associated information.

[0031] In one aspect, the remote system 290 can be configured to receive at least a portion of the monitored patient biometric data and associated information via the network 285, which can be a remote network. For example, if the local system 280 is a mobile phone, the network 285 can be a wireless cellular network. Information can be transmitted between the local system 280 and the remote system 290 via wireless technology standards (such as any of the wireless technologies described above). The remote system 290 can be configured to present the received patient biometric data and associated information to a healthcare professional (e.g., a physician) visually on a display or audibly through a speaker.

[0032] As reference Figure 1 and Figure 2 As described, the system 100, 200 may process 161, 220 biometric data associated with the patient. The system 100, 200 may receive 163, 260 biometric data from measurements performed on the patient 125 during the EP procedure. The system 100 may also and optionally use ultrasound, computed tomography (CT), MRI, or other medical imaging techniques known in the art to obtain biometric data, such as anatomical measurements of the heart 120. The system 100 may use a catheter or other sensor that measures the electrical properties of the heart 120 to obtain ECG or electrical measurements. The biometric data, including the anatomical and electrical measurements, may then be stored in a memory 162 of the console 160. The biometric data may be sent to the console 160 from a non-transitory tangible medium. Alternatively or in addition, the biometric data may be transmitted to a server, which may be local or remote, using a network as otherwise described herein.

[0033] According to one aspect, the console 160 may be connected to body surface electrodes via cables, which may include adhesive skin patches attached to the patient 125. The body surface electrodes may obtain / generate biometric data in the form of BS ECG data. For example, the processor 161 in conjunction with the current tracking module may determine the position coordinates of the catheter 105 inside a body part (e.g., the heart 120) of the patient 125. These position coordinates may be based on the impedance or electromagnetic field measured between the body surface electrodes and the electrodes 106 or other electromagnetic components of the catheter 105. Additionally or alternatively, a positioning pad may be located on the surface of the bed 130 and may be detachable from the bed 130.

[0034] According to various aspects, the catheter 105 can be configured to ablate a tissue region of a cardiac chamber of the heart 120. Inset 150 shows the catheter 105 in a magnified view within the cardiac chamber of the heart 120. According to various aspects disclosed herein, an ablation electrode such as at least one electrode 106 can be configured to provide energy to a tissue region of an internal organ such as the heart 120. The energy can be thermal energy and can cause damage to the tissue region starting from the surface of the tissue region and extending into the thickness of the tissue region. Biometric data relative to the ablation procedure (e.g., ablated tissue, ablation location, etc.) can be considered as ablation data.

[0035] According to one or more aspects, a catheter containing a position sensor can be used to determine the trajectory of points on the surface of the heart. These trajectories can be used to infer motion characteristics, such as the contractility of the tissue. When trajectory information is sampled at a sufficient number of points in the heart 120, a map depicting such motion characteristics can be constructed.

[0036] Typically, a catheter 105 containing an electrical sensor at or near its distal tip (at least one electrode 106) is advanced to a point in the heart 120, where the sensor contacts the tissue and data is acquired at that point to measure electrical activity at that point in the heart 120. One disadvantage of using a catheter 105 containing only a single distal tip electrode to map a cardiac chamber is the time required to acquire data point by point at the necessary number of points required for a detailed map of the chamber as a whole. Therefore, multi-electrode catheters have been developed to measure electrical activity at multiple points in a cardiac chamber simultaneously.

[0037] According to one example, a multi-electrode catheter may be advanced into a chamber of the heart 120. An anteroposterior fluorogram (AP) and a lateral fluorogram may be obtained to establish the position and orientation of each electrode. An ECG relative to a time reference (such as, starting from the P wave in sinus rhythm from a BS ECG) may be recorded by each of the electrodes in contact with the surface of the heart. As further disclosed herein, the system may distinguish between those electrodes that record electrical activity and those electrodes that do not record electrical activity due to not being in close proximity to the endocardial wall. After recording the initial ECG, the catheter may be repositioned, and the fluorogram and ECG may be recorded again. An electrical mapping map may then be constructed according to iterations of the above process.

[0038] According to one example, cardiac mapping (e.g., which is an example of IC ECG data) can be generated based on the detection of intracardiac electrical potential fields. Non-contact techniques for simultaneously acquiring a large amount of cardiac electrical information can be implemented. For example, a catheter having a distal end portion can be provided with a series of sensor electrodes distributed on its surface and connected to an insulated electrical conductor for connection to a signal sensing and processing device. The size and shape of the end portion can be such that the electrodes are substantially spaced apart from the wall of the heart chamber. The intracardiac electrical potential field can be detected during a single heartbeat. According to one example, the sensor electrodes can be distributed on a series of circumferences located in planes spaced apart from each other. These planes can be perpendicular to the long axis of the end portion of the catheter. At least two additional electrodes can be provided adjacent to the end of the long axis of the end. As a more specific example, the catheter may include four circumferences, wherein eight electrodes are equiangularly spaced apart on each circumference. Therefore, in this specific implementation, the catheter may include at least 34 electrodes (32 circumferential electrodes and 2 end electrodes).

[0039] According to another example, an electrophysiological cardiac mapping system and technique based on a non-contact and non-expanding multi-electrode catheter can be implemented. An ECG can be obtained through a catheter having multiple electrodes (e.g., 42 to 122 electrodes). According to this specific implementation, knowledge of the relative geometry of the probe and the endocardium can be obtained, such as through an independent imaging modality (such as transesophageal echocardiography). After independent imaging, the non-contact electrodes can be used to measure the surface potential of the heart and construct a map therefrom. The technology may include the following steps (after the independent imaging step): (a) measuring the potential using multiple electrodes set on a probe positioned on the heart 120; (b) determining the geometric relationship between the probe surface and the endocardial surface; (c) generating a coefficient matrix representing the geometric relationship between the probe surface and the endocardial surface; and (d) determining the endocardial potential based on the electrode potential and the coefficient matrix.

[0040] According to another example, techniques and apparatus for mapping the electrical potential distribution of a cardiac chamber may be implemented. An intracardiac multi-electrode mapping catheter assembly may be inserted into the heart 120. The mapping catheter assembly may include a multi-electrode array with an integral reference electrode, or preferably, a matching reference catheter. The electrodes may be deployed in a substantially spherical array. The electrode array may be spatially referenced to a point on the endocardial surface by a reference electrode or by a reference catheter in contact with the endocardial surface. A preferred electrode array catheter may carry a plurality of individual electrode sites (e.g., at least 24). In addition, the exemplary technique may be implemented by knowing the location of each of the electrode sites on the array and knowing the geometry of the heart. These locations are preferably determined by the technique of impedance plethysmography.

[0041] According to another example, a cardiac mapping catheter assembly may include an electrode array defining a plurality of electrode sites. The mapping catheter assembly may also include an inner cavity to receive a reference catheter having a distal tip electrode assembly that can be used to detect a heart wall. The mapping catheter may include a braid of insulated wires (e.g., having 24 to 64 wires in the braid), and each wire may be used to form an electrode site. The catheter may be positioned at a first site in the heart 120 to obtain a first set of electrical activity information from the non-contact electrodes, and then may be positioned at another site in the heart 120 to obtain another set of electrical activity information from the non-contact electrodes.

[0042] According to another example, another catheter for mapping electrophysiological activity within the heart can be implemented. The catheter body may include a distal tip adapted to deliver stimulation pulses for cardiac pacing or an ablation electrode for ablating tissue in contact with the tip. The catheter may also include at least one pair of orthogonal electrodes to generate a difference signal indicative of local cardiac electrical activity adjacent to the orthogonal electrodes.

[0043] According to another example, a process for measuring electrophysiological data in a heart chamber may be implemented. The method may include, in part, positioning a set of active electrodes and passive electrodes into the heart 120, supplying current to the active electrodes to generate an electric field in the heart chamber, and measuring the electric field at the passive electrode sites. The passive electrodes are contained in an array positioned on an inflatable balloon of a balloon catheter. In a preferred aspect, the array is said to have 60 to 64 electrodes.

[0044] According to another example, cardiac mapping can be implemented using one or more ultrasound transducers. The ultrasound transducer can be inserted into the patient's heart 120, and multiple ultrasound slices (e.g., two-dimensional or three-dimensional slices) can be collected at various positions and orientations within the heart 120. The position and orientation of a given ultrasound transducer can be known, and the collected ultrasound slices can be stored so that they can be displayed at a later time. One or more ultrasound slices corresponding to the position of a probe (e.g., a treatment catheter) can be displayed after a period of time, and the probe can be overlaid on one or more ultrasound slices.

[0045] According to other examples, the body patch and / or body surface electrodes may be positioned on or near the patient's body. A catheter having one or more electrodes may be positioned within the patient's body (e.g., within the patient's heart 120), and the position of the catheter may be determined by the system based on signals transmitted and received between the one or more electrodes of the catheter and the body patch and / or body surface electrodes. In addition, the catheter electrodes may sense biometric data (e.g., LAT values) from within the body of the patient 125 (e.g., within the heart 120). The biometric data may be associated with the determined position of the catheter so that a rendering of a body part of the patient (e.g., heart 120) may be displayed, and the biometric data overlaid on the body shape may be displayed.

[0046] In view of system 100, it is noted that arrhythmias, including atrial arrhythmias, can be of the multi-wavelet reentry type, characterized by multiple asynchronous loops of electrical impulses dispersed around the atrial chambers and generally self-propagating (e.g., another example of IC ECG data). Alternatively, or in addition to the multi-wavelet reentry type, arrhythmias can also have a focal origin, such as when an isolated area of ​​tissue within the atrium beats autonomously in a rapid, repetitive manner (e.g., another example of IC ECG data). Ventricular tachycardia (V-tach or VT) is a tachycardia or rapid heart rhythm that originates in one of the ventricles. This is a potentially life-threatening arrhythmia as it can lead to ventricular fibrillation and sudden death.

[0047] For example, aFib occurs when normal electrical impulses generated by the sinoatrial node (e.g., another example of IC ECG data) are overwhelmed by chaotic electrical impulses originating from the atrial veins and PVs that cause irregular pulses to be transmitted to the ventricles. Irregular heartbeats occur and may last from minutes to weeks, or even years. aFib is typically a chronic condition that is usually associated with a slightly increased risk of death due to stroke. The first line of treatment for aFib is medication that can slow the heart rate or restore the heart rhythm to normal. In addition, people with aFib are often given anticoagulants to prevent them from being at risk of stroke. The use of such anticoagulants comes with its own risk of internal bleeding. For some patients, drug therapy is not enough, and their aFib is considered drug-refractory, that is, it cannot be cured with standard drug interventions. Synchronized cardioversion can also be used to convert aFib to a normal heart rhythm. Alternatively, aFib patients are treated by catheter ablation.

[0048] Therapy based on catheter ablation can include mapping the electrical properties of cardiac tissue (particularly the endocardium and cardiac volume), and selectively ablating cardiac tissue by applying energy. Cardiac mapping, which is an example of cardiac imaging, includes creating, for example, a map of electrical potentials propagating along the cardiac tissue (e.g., a voltage map) or a map of arrival times to various tissue locations (e.g., a LAT map). Cardiac mapping (e.g., a cardiac map) can be used to detect localized cardiac tissue dysfunction. Ablation, such as ablation based on cardiac mapping, can stop or alter the propagation of unwanted electrical signals from one part of the heart 120 to another.

[0049] The ablation process damages unwanted electrical pathways by forming non-conductive lesions. A variety of energy delivery modalities have been disclosed for forming lesions, and include the use of microwaves, lasers, and more commonly radiofrequency energy to form conduction blocks along the walls of cardiac tissue. In a two-step procedure (e.g., mapping followed by ablation), electrical activity at various points within the heart 120 is typically sensed and measured by advancing a catheter 105 containing one or more electrical sensors (or electrodes 106) into the heart 120 and obtaining / acquiring data (e.g., ECG data) at multiple points. This ECG data is then used to select an endocardial target area where ablation will be performed.

[0050] Cardiac ablation and other cardiac electrophysiology procedures are becoming increasingly complex as clinicians treat increasingly challenging conditions such as atrial fibrillation and ventricular tachycardia. Treatment of complex arrhythmias may rely solely on the use of a three-dimensional (3D) mapping system to reconstruct the anatomy of the heart chamber of interest. In this regard, the classification engine 101 employed by the system 100 herein manipulates and evaluates ECG data to produce improved tissue data that enables more accurate diagnosis, images, scans, and / or mapping for treating abnormal heartbeats or arrhythmias.

[0051] Electrode catheters (e.g., catheter 105) are used in medical practice. The electrode catheters are used to stimulate and map electrical activity in the heart, as well as to ablate sites of abnormal electrical activity. When used, the electrode catheter is inserted into a major vein or artery, such as the femoral artery, and then guided into the heart chamber of interest. A typical ablation procedure involves inserting a catheter having at least one electrode at its distal end into a heart chamber. A reference electrode, which is usually taped to the patient's skin, is provided, or a second catheter disposed in or near the heart can be used to provide the reference electrode. Radiofrequency (RF) current is applied to the tip electrode of the ablation catheter, and the current flows to the reference electrode through the medium surrounding it (i.e., blood and tissue). The distribution of the current depends on the amount of contact between the electrode surface and the tissue compared to the blood, which has a higher conductivity than the tissue. Due to the resistance of the tissue, heating of the tissue occurs. The tissue is heated sufficiently to cause cell destruction in the heart tissue, resulting in the formation of non-conductive ablation lesions in the heart tissue. In this process, heating of the electrode also occurs due to conduction from the heated tissue to the electrode itself. If the electrode temperature becomes high enough, perhaps above 60 degrees Celsius, a thin transparent coating of dehydrated blood proteins may form on the surface of the electrode. If the temperature continues to rise, this dehydrated layer may become increasingly thicker, causing blood coagulation on the electrode surface. Because the dehydrated biomaterial has a higher electrical resistance than the endocardial tissue, the impedance to the flow of electrical energy into the tissue also increases. If the impedance increases sufficiently, impedance rise occurs, and the catheter must be removed from the body and the tip electrode cleaned.

[0052] Treatment of cardiac disorders (such as arrhythmias) often requires obtaining detailed mapping of cardiac tissue, chambers, veins, arteries and / or electrical pathways. For example, a prerequisite for successfully performing catheter ablation is that the cause of the arrhythmia is accurately located in the heart chamber. Such positioning can be accomplished via an electrophysiological study, during which electrical potentials are spatially resolved using a mapping catheter introduced into the heart chamber. This electrophysiological study (so-called electroanatomical mapping) therefore provides 3D mapping data that can be displayed on a monitor. In many cases, the mapping function and the treatment function (e.g., ablation) are provided by a single catheter or a group of catheters, so that the mapping catheter also operates simultaneously as a treatment (e.g., ablation) catheter. In this case, the modules performed by systems 100, 200 can be performed by catheter 105.

[0053] Mapping of cardiac regions, such as cardiac regions, tissues, veins, arteries, and / or electrical pathways of the heart (e.g., 120), can result in identification of problem areas such as scar tissue, sources of arrhythmias (e.g., electrical rotors), healthy areas, and the like. The cardiac region can 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 an example of cardiac imaging, can include mapping based on one or more modalities, such as, but not limited to, local activation time (LAT), electrical activity, topology, bipolar mapping, dominant frequency, or impedance. Data corresponding to multiple modalities can be captured using a catheter inserted into a patient, and data corresponding to multiple modalities can be provided for rendering simultaneously or non-simultaneously based on corresponding settings and / or preferences of a medical professional.

[0054] Cardiac mapping can be implemented using one or more techniques. As an example of a first technique, cardiac mapping can be implemented by sensing the electrical properties of cardiac tissue (e.g., LAT) according to precise locations within the heart. The corresponding data can be acquired by one or more catheters that are advanced into the heart using catheters having electrical sensors and position sensors in their distal ends. For example, position and electrical activity can initially be measured at about 10 to about 20 points on the inner surface of the heart. These data points are generally sufficient to generate a preliminary reconstruction or mapping map of satisfactory quality of the heart surface. The preliminary map can be combined with data taken from additional points to produce a more comprehensive map of the heart's electrical activity. In a clinical setting, it is not uncommon to accumulate data at 100 or more sites to generate a detailed and comprehensive mapping map of the electrical activity of the heart chambers. The detailed map generated can then be used as a basis for deciding on a course of therapeutic action, such as tissue ablation, to change the propagation of the heart's electrical activity and restore normal heart rhythm.

[0055] Figure 3300 based on the exemplary system for cardiac mapping of data based on clusters 300, based on which one or more features of the present disclosure can be implemented. According to various aspects disclosed herein, the system 300 can classify ECG data relative to biometric data measured by a patient into clusters and map the biometric data associated with each cluster. The system 300 may include a data processor 320, an evaluation engine 340, and a mapper 360. The components 320, 340, 360 of the system 300 may be implemented by one or more software modules, which may be provided by reference to the above Figure 1 and Figure 2 The data processor 320 may receive as input biometric data 310 including data collected from a patient during a medical procedure. The data processor 320 may process the received biometric data 310, for example, to improve the discriminative properties of the data and / or reduce the data size. The data processor 320 may feed the evaluation engine 340 with beat segments 335.1-335.M extracted from the ECG data of the biometric data 310. Each beat segment (e.g., including an ECG signal 335.m) indicates the type of arrhythmia generated thereby.

[0056] The evaluation engine 340 may classify the beat segments 330 into clusters (e.g., cluster A 352 and cluster B 354). Classification of the beat segments into clusters may be based on beat characteristics of the segments and / or may be based on a prediction of the type of arrhythmia that produced the biometric data 310 associated with the beat segments. Thus, the output 350 of the evaluation engine 340 may be segments classified into clusters based on beat characteristics of the segments (e.g., the origin of the beat (the location of focal arrhythmic activity in the heart), the propagation velocity of the beat, and the shape descriptor of the beat). Alternatively or in addition, the output 350 of the evaluation engine 340 may be segments classified into clusters based on the predicted type of arrhythmia represented by the segments (e.g., a specific arrhythmia type, normal sinus rhythm (NSR), or mixed arrhythmia). The mapper 360 may then generate a map (e.g., a voltage map or a LAT map). Each map visualizes data associated with segments from one cluster (eg, map 372 visualizes data associated with segments in cluster B 354 ).

[0057] The biometric data 310 provided to the system 300 may include data measured by the system 100, 200 relative to the patient during the EP procedure. The biometric data may include BS ECG data, IC ECG data, ablation data, and catheter electrode position data. In one aspect, the BS ECG data may include signals collected from electrodes positioned on the surface of the patient's body; the IC ECG data may include signals collected from electrodes within the patient's body; and the ablation data may include data collected from tissue that has been ablated. Therefore, a beat segment 330 may be extracted from a BS ECG signal or an IC ECG signal containing at least one heartbeat according to a time window. It should be understood that any of a variety of different instruments for measuring electrical activity in the patient's body may be used to collect signals from the patient's body. As described above, the classification of the beat segments 330 into clusters may be based on arrhythmia types, such as specific arrhythmia types, NSR, mixed arrhythmias, or combinations thereof. For example, a specific arrhythmia type may include atrial fibrillation, flutter, or atrial tachycardia. NSR may be the rhythm of a healthy heart, ie, correctly sent electrical impulses from the sinoatrial node. Mixed arrhythmias may include two or more types of arrhythmias as well as one or more types of arrhythmias and NSR.

[0058] Figure 4 4 is a flow chart of an exemplary method 400 for cardiac mapping of data based on clustering, based on which one or more features of the present disclosure may be implemented. In step 410, biometric data measured by the system 100, 200 during a medical procedure for a patient is obtained. The biometric data may include any data related to a cardiac condition, including, for example, BS ECG data, IC ECG data, ablation data, and catheter electrode position data. The method 400 may extract beat segments from the biometric data in step 420. In one aspect, the segments may overlap in time, or may be extracted within a rolling time window across the time dimension of the BS ECG data and / or the IC ECG data. In step 430, the segments are classified into clusters. As described above, the classification of the beat segments into clusters may be based on the beat characteristics of the segments and / or may be based on a prediction of the type of arrhythmia based on the biometric data 310 associated with the beat segments. Next, if the segments are clustered into less than a threshold number of beats, the segments are classified into clusters. T If the number of clusters is 440, cardiac maps may be generated in step 450. Each generated map may visualize data associated with segments from one cluster. However, if the segments are clustered to be equal to or above a threshold number T If multiple clusters 440 are identified, it can be concluded in step 460 that the beat segment represents a complex arrhythmia, which conclusion can affect the treatment process.

[0059] Classifying the beat segments into clusters (in step 430 of method 400 or by evaluation engine 340 of system 300) may be accomplished based on a clustering algorithm or based on a machine learning algorithm. Figure 5 to Figure 6 The use of a clustering algorithm to classify beat segments into clusters based on beat features is described. Figure 8 The use of a machine learning algorithm to classify beat segments into clusters based on the segments associated with biometric data is described.

[0060] Figure 5 is a flow chart of an exemplary method 500 for classifying beat segments into clusters based on beat characteristics, based on which one or more features of the present disclosure may be implemented. Method 500 may estimate characteristics (origin and velocity) of beats represented in a subset of beat segments 335 captured by electrodes of a multi-electrode catheter. Method 500 begins at step 510, where time measurements of the electrodes are obtained. The time measurements of the electrodes indicate the time of the beat in the segment (e.g., 335.m) that the electrodes measured. Then, in step 520, position measurements of the electrodes are obtained. The position measurements of the electrodes indicate the position of the electrodes in the heart when the electrodes measured the beat in the segment (e.g., 335.m). Based on these time measurements and position measurements, method 500 estimates the origin (position in the heart) and beat propagation velocity of the beat in step 530, as described in detail below. If the estimation error is above a threshold T 540, the measurements with high error contributions may be eliminated in step 550, and the estimation in step 530 may be repeated 555 using only the remaining measurements. If the estimated error is equal to or below the threshold T 540, the beat origin estimate and the velocity estimate can be used to classify subsets of beat segments captured by the multi-electrode catheter into clusters, as shown in reference Figure 6 described.

[0061] Next, a technique for estimating the origin and velocity of a beat is described (step 530). The technique estimates the location (i.e., origin) of focal arrhythmic activity in the heart and its conduction velocity (i.e., velocity). The system 100, 200 may be used with a multi-electrode catheter (e.g., Pentaray ® Electrodes of a coronary catheter (a catheter, a constellation catheter, or a coronary sinus catheter) acquire multiple signals from the region of the heart where the electrodes are located. In one aspect, a coronary sinus catheter can be used to acquire reference measurements. Such reference measurements can be used to correlate (or calibrate) measurements acquired, for example, by a Pentaray catheter. That is, measurements made by a Pentaray catheter (at different times and at different locations in the atrium) can be measured relative to corresponding measurements made by a coronary sinus catheter, so that the measurements acquired by the Pentaray catheter can be correlated to create, for example, a LAT map.

[0062] A segment including atrial activation (beat) (ie, a beat segment 330, 420) is extracted from the signal acquired by the electrodes of the multi-electrode. It's time that matters (electrode i time of atrial activation) and the time at which the electrode Location ( ). The activation time of the beat is determined by , and the origin of the pulsation is given by ( , ) indicates the position of the electrode ( ) and the origin of the pulsation ( , ) is usually defined relative to a cardiac reference location (e.g., a region of interest within the heart). Thus, the beat can be Location in the heart , ) starts at the speed v (i.e., conduction velocity) and can be By location ( ) i Measurement.

[0063] Therefore, relative to the electrode i , the pulsation can be along the distance (Depend on The travel time of a beat can be defined as ,in Representation and electrode i The associated measurement error can then be calculated based on m The measured values ​​of the electrodes are calculated by taking the mean square error Minimize to calculate the origin of the pulsation ( , ) and the speed of the pulsation v The estimate is as follows:

[0064] , (1)

[0065] in is measured from the distance (or equivalent position measurement ) and from m Time measurement value of each electrode The estimated parameter vector. In one aspect, the regularization term :

[0066] . (2)

[0067] For example, the regularization term Set to The region of interest closer to the origin of the catheter and possibly within the cardiac anatomy can be obtained. The cost function (At the origin of the beating , ) estimate and the jump propagation speed estimate) can be minimized by an optimization algorithm (such as gradient descent based optimization). Based on these estimates, the mean square error can be calculated: If the mean square error is higher than the threshold T (Step 540), the error above the predetermined error level can be eliminated The associated electrode measurements are taken (step 550), and the estimation (step 530) may be repeated including only the measurements 555 of the remaining electrodes.

[0068] Figure 6 6 is a diagram of an exemplary clustering method 600 based on which one or more features of the present disclosure may be implemented. Method 600 may be used to classify beat segments into clusters based on beat characteristics of the segments—that is, based on the beat origin and beat velocity of the segments in the heart (e.g., estimated using method 500) and / or based on other descriptors (such as shape descriptors). Clusters may be represented by corresponding centroids in a space defined by the data on which the classification is performed. For example, the beat origin may be represented by the centroids of the segments. and pulse rate v Limited four-dimensional space.

[0069] exist Figure 6, the classification of data points in a two-dimensional space according to the K-means clustering algorithm is shown. As shown, the data points will be classified into two clusters (K=2)—Cluster A and Cluster B 610. In the K-means algorithm, the number of clusters should be predetermined. In one aspect, the number of clusters can be learned by a machine learning algorithm based on training data (e.g., training data of a beat segment), and the physician can verify the number of clusters for the training data. In order to initialize the K-means algorithm, two initial centroids set apart from each other are determined for each cluster. These centroids are represented by hollow circles 620, 630. Then, in the first iteration, the data points can be classified into two clusters 640 based on the similarity of the data points to each centroid. Therefore, the data points on the left side of the boundary line can be assigned to Cluster A 642, and the data points on the right side of the boundary line can be classified to Cluster B 644. Next, the centroids 650 of the clusters are calculated based on the data points within each cluster 652, 654. In a second iteration, the data points may again be reclassified into two clusters based on their similarity to each of the centroids 660. Thus, data points to the left of the boundary may be assigned to cluster A 662, and data points to the right of the boundary may be assigned to cluster B 664. Next, the centroids 670 of the clusters are recalculated based on the data points within each cluster 672, 674. The process of assigning data points to clusters 640, 660 and recalculating the centroids 650, 670 of the clusters may be repeated until a maximum number of iterations is reached or until there is no change in the assignment of data points to clusters.

[0070] FIG. 7 is a flow chart of an exemplary method for classifying beat segments into clusters based on predictions of arrhythmia types, including a training method 700A for a predictor ( Fig. 7A ) and applying the trained predictor method 700B ( Figure 7B ), based on which one or more features of the present disclosure may be implemented. Methods 700A-B may be employed by an evaluation engine 340, the execution of which may be described in detail in this document. Figure 1 or Figure 2The method 700A may be performed by any processor of the system 100 or 200 described above. In step 710 of the method 700A, a training data set may be received, including training pairs. Each training pair includes biometric data associated with a patient suffering from an arrhythmia and a corresponding classification of the type of arrhythmia of the patient. The biometric data of the training pair may include a beat segment representing the type of arrhythmia. In step 720, the biometric data of the training data set may be processed to improve its predictive value and / or reduce its size. In one aspect, step 720 is not applied to the biometric data. Based on the training data set provided by step 720 (or step 710), the arrhythmia prediction model may learn the correlation between the training pairs of biometric data and their corresponding classifications, that is, in step 730, the model is trained to predict the type of arrhythmia when it is presented together with the biometric data of a new patient.

[0071] The received training data set 710 may include biometric data measured by the system 100 or 200, as described herein with respect to Figure 1 or Figure 2 For example, the training data set 710 may include biometric data derived from measurements obtained during surgical procedures and corresponding classifications associated with the results of those surgical procedures. For example, the patient's biometric data may include BS ECG data, IC ECG data, ablation data, and catheter electrode position data, and may be manually annotated (classified) by a physician as corresponding to a specific arrhythmia type, NSR, mixed arrhythmia, or a combination thereof. Figure 8 As explained, the results of training the model (step 730) are model parameters (weights) that are used when applying the model to make predictions. In one aspect, the arrhythmia prediction model can be updated (weights can be recalculated) in real time as more training data becomes available (and added to the training data set 710), e.g., after a surgical procedure.

[0072] Thus, in step 750 of method 700B, the trained arrhythmia prediction model may be applied to biometric data 750 measured from a patient currently undergoing a medical procedure, for example, biometric data measured during a surgical procedure. Biometric data 750 may include BS ECG data, IC ECG data, and catheter electrode location data. In step 760, the trained arrhythmia prediction model may be applied to biometric data 750 measured from a patient currently undergoing a medical procedure, for example, biometric data measured during a surgical procedure. Biometric data 750 may include BS ECG data, IC ECG data, and catheter electrode location data. Fig. 7A The patient's biometric data is processed in the same manner as the training biometric data in step 720 of the embodiment. In one aspect, steps 720 and 760 are not applied. Then, in step 770, the trained arrhythmia prediction model may be applied to predict the patient's arrhythmia type, i.e., a specific arrhythmia type, NSR, mixed arrhythmia, or a combination thereof. The predicted arrhythmia type may be used to predict the patient's arrhythmia type according to the embodiment of the present invention. Figure 4Step 430 classifies the corresponding beat segments into clusters.

[0073] Figure 8 is a functional block diagram of an exemplary machine learning system 800, based on which one or more features of the present disclosure can be implemented. Various machine learning systems 800 can be used to train and apply Figure 3 The arrhythmia predictor employed by the evaluation engine 340 of the invention. For example, the machine learning system 800 may be based on an ANN of various architectures, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), an example of which is an LSTM network. Generally speaking, a neural network is trained to predict information of interest based on observations. The neural network is trained via a supervised learning process by which correlations between pairs of examples (i.e., observations and corresponding information of interest) are learned.

[0074] In one aspect, ANN 810 may be a CNN. A CNN may be used to learn patterns from data provided in a spatiotemporal format, such as ECG data. Generally, a CNN may employ convolution operations across several layers using kernels. Each layer in the network (e.g., layer n 840) can process data from an image at its input and can generate data to be used by the next layer (e.g., layer m 850). Convolution kernels applied in earlier layers in the network can integrate information from neighboring data elements more effectively than convolution kernels applied in later layers in the network. Therefore, correlations between data elements that are closely located in the image can be better learned in the CNN.

[0075] Typically, neural network 810 includes nodes ("neurons") connected according to a given architecture. For example, in a given architecture, these nodes may be arranged in layers, i.e., a layer (e.g., a layer n 840) feeds the output of the node to which it is connected (e.g., layer m 850) in the input of the node. m 850 nodes j 855 (i.e. m j ) are usually connected to the layer with a certain strength or a certain weight n 8 40 nodes i 845 (i.e. n i ): w ( m j , n i ) 860. Therefore, the weights associated with the inter-node connections of the network { w ( mj , n i )} (“synaptic weights”) parameterize the neural network model. Training the neural network can then be viewed as specifying the network by determining the weights (parameters) of the network, i.e., determining the model parameters 830.

[0076] The manner in which the neural network 810 processes data can be described as follows. Input data can be fed to nodes in the first layer of the neural network so that each node in the first layer receives a weighted combination of the input data (or a weighted combination of a subset of the input data). Then, the weighted combination of the inputs of each node is converted according to the activation function of the node, thereby obtaining the output data of the node. Next, the output data from each node in the first layer can be fed to nodes in the second layer of the neural network so that each node in the second layer receives a weighted combination of the outputs of the nodes in the first layer (or a weighted combination of the outputs of a subset of the nodes in the first layer). Then, the weighted combination of the inputs of each node is converted according to the activation function of the node, thereby obtaining the output data of the node. The output data from the nodes in the second layer are then propagated and similarly processed in other intermediate layers of the network, wherein the last layer provides the output data of the network. Therefore, a neural network is generally characterized by the structure of its nodes and the activation functions of these nodes. The weights associated with the connections between nodes (network parameters or model parameters 830) are learned through an iterative training process (e.g., a backpropagation algorithm) based on training parameters (e.g., a learning rate and a cost function) and based on a training data set 820.

[0077] The training data set 820 that can be used to train the neural network model 810 can include exemplary data pairs, such as observation data (e.g., measurements collected during a surgical procedure) and corresponding information of interest to be predicted by the model (e.g., the outcome of the surgical procedure). For example, temperature data of the heart (observation data) can be collected and can be associated (through a training process) with the outcome of a cardiac procedure (the information of interest to be predicted). Once the model parameters are determined through the training process, the model can be applied to predict the information of interest based on new observations. For example, in the case of the heart, based on the temperature input during the procedure (e.g., between 97.7 degrees Celsius and 100.2 degrees Celsius), the output of the model can be a prediction of the outcome of the procedure. The prediction is based on a correlation between temperature and the outcome of the procedure, which is learned by the neural network model based on the training data set.

[0078] According to aspects of the present disclosure, the assessment engine 340 can train a machine learning model 810 and can apply the trained model to predict the classification of the patient's arrhythmic condition. The algorithm disclosed herein can be applied to train the model based on a training data set 820 (obtained from patients experiencing arrhythmic conditions through various modalities) and the corresponding classification of the patient's arrhythmic condition.

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the possible specific implementation architecture, functions and operations of the system, method and computer program product according to various aspects of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, section or part of an instruction, which includes one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions indicated in the box may not occur in the order indicated in the accompanying drawings. For example, depending on the functions involved, the two boxes shown in succession may actually be executed substantially simultaneously, or the boxes may sometimes be executed in reverse order. It should also be noted that each box in the block diagram and / or flowchart illustration and the combination of boxes in the block diagram and / or flowchart illustration can be implemented by a system based on dedicated hardware that performs a specified function or action or by a combination of dedicated hardware and computer instructions.

[0080] Although the features and elements are described above in detail, it will be appreciated by those skilled in the art that each feature or element may be used alone or in any combination with other features and elements. In addition, the methods described herein may be implemented in a computer program, software, or firmware incorporated in a computer-readable medium for execution by a computer or processor. As used herein, a computer-readable medium should not be understood as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electrical signal transmitted by wire.

[0081] Examples of computer-readable media include electronic 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 associated with software may be used to implement a radio frequency transceiver for use in a WTRU, UE, terminal, base station, RNC, or any host computer.

[0082] It should be understood that the terms used herein are only for the purpose of describing specific aspects and are not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the / said" include plural references. It should also be understood that the terms "include" and / or "comprise" when used in this specification specify the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0083] The description of various aspects herein is presented for the purpose of illustration, but is not intended to be exhaustive or limited to the disclosed aspects. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and essence of the described aspects. The terminology used herein is selected to best explain the principles of the described aspects, practical applications or technical improvements over existing technologies on the market, or to enable other persons of ordinary skill in the art to understand the aspects disclosed herein.

Claims

1. A system for cardiac mapping, comprising: at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the system to: receiving biometric data obtained from a patient, extracting beat segments from the biometric data, classifying the beat segments into clusters, each cluster representing a type of arrhythmia, and In response to the beat segments being classified into a number of clusters below a threshold number, at least one map is generated based on data associated with beat segments in one of the clusters.

2. The system of claim 1, wherein the biometric data comprises at least one of surface electrocardiogram data, intracardiac electrocardiogram data, or ablation data.

3. The system of claim 1, wherein the biometric data comprises catheter electrode position data.

4. The system of claim 1, wherein the biometric data comprises measurements acquired by a catheter and corresponding reference measurements acquired by a coronary sinus catheter, and wherein the reference measurements are used to correlate the measurements acquired by the catheter.

5. The system of claim 1, wherein the arrhythmia type comprises a specific arrhythmia type, normal sinus rhythm, mixed arrhythmia, or a combination thereof.

6. The system of claim 1, wherein the classification comprises: estimating one or more beat characteristics for each of the beat segments; as well as The beat segments are classified into the clusters based on their respective beat features.

7. The system of claim 6, wherein the pulsation characteristics include one or more of a shape descriptor, an origin, or a propagation velocity.

8. The system of claim 6, wherein: The subset of beat segments represents beats characterized by an origin and a propagation velocity in the heart, each beat segment in the subset being captured by a corresponding electrode of a multi-electrode catheter.

9. The system of claim 8, wherein: The estimation includes estimating the origin and the propagation speed of the beat based on time measurements and based on position measurements, each time measurement indicating the time when an electrode of the multi-electrode catheter measured the beat in a corresponding beat segment of the subset, and each position measurement indicating the position of the electrode when the beat was measured by the electrode.

10. The system of claim 1, wherein the classification comprises: For each of the beat segments, using a machine learning model, predicting a corresponding arrhythmia type based on biometric data associated with the beat segment; as well as The beat segments are classified into the clusters based on their respective predicted arrhythmia types.

11. The system of claim 10, further comprising instructions that cause the system to: Receiving a training data set associated with past patients, wherein the training data set for each past patient comprises: beat segments extracted from biometric data obtained with respect to said past patient, and Classification of arrhythmia type for each beat segment; as well as The machine learning model is trained based on the training data set to predict arrhythmia types associated with beat segments obtained from the patient.

12. A non-transitory computer readable medium comprising instructions executable by at least one processor to perform a method for cardiac mapping, the method comprising: receiving biometric data obtained from a patient; extracting beat segments from the biometric data; classifying the beat segments into clusters, each cluster representing a type of arrhythmia; as well as In response to the beat segments being classified into a number of clusters below a threshold number, at least one map is generated based on data associated with beat segments in one of the clusters.

Images