阅读说明：本技术 使用相干算法的局部噪声识别 (Local noise identification using coherent algorithms ) 是由 I·多伦 M·齐-瓦里 A·科恩 于 2021-06-04 设计创作，主要内容包括：本发明题为“使用相干算法的局部噪声识别”。本发明公开了用于自动检测心律失常位置的系统、装置和技术。该系统、装置和技术包括被配置成感测心电图(ECG)数据的多个体表电极。该系统、装置和技术包括处理器,该处理器包括神经网络,该处理器被配置成接收多个历史ECG数据和基于多个历史ECG数据中的每个历史ECG数据确定的对应的心律失常位置,基于多个历史ECG数据和对应的心律失常位置来训练学习系统,基于该学习系统生成模型。可从多个体表电极接收新的ECG数据,并且处理器可基于新的ECG数据来提供新的心律失常位置。另外,可基于使用历史相干标测调整训练的模型来提供新的相干标测调整。(The invention relates to local noise identification using a coherent algorithm. Systems, devices, and techniques for automatically detecting the location of an arrhythmia are disclosed. The systems, devices, and techniques include a plurality of body surface electrodes configured to sense Electrocardiogram (ECG) data. The systems, apparatuses, and techniques include a processor including a neural network configured to receive a plurality of historical ECG data and a corresponding arrhythmia location determined based on each of the plurality of historical ECG data, train a learning system based on the plurality of historical ECG data and the corresponding arrhythmia location, generate a model based on the learning system. New ECG data may be received from the plurality of sets of table electrodes and the processor may provide a new arrhythmia location based on the new ECG data. Additionally, a new coherent mapping adjustment may be provided based on the model trained using the historical coherent mapping adjustment.)

1. A system for automatically detecting the location of an arrhythmia, comprising:

a plurality of body surface electrodes configured to sense Electrocardiogram (ECG) data;

a display; and

a processor comprising a neural network and configured to:

receiving a plurality of historical ECG data and a corresponding arrhythmia location determined based on each of the plurality of historical ECG data;

training a learning system based on the plurality of historical ECG data and corresponding arrhythmia locations;

generating a model based on the learning system;

receiving new ECG data from the plurality of body surface electrodes;

providing a new arrhythmia location based on the new ECG data and the model; and

presenting the new arrhythmia location on the display.

2. The system of claim 1, wherein the received plurality of historical ECG data and corresponding arrhythmia locations correspond to arrhythmias successfully treated at the corresponding arrhythmia locations.

3. The system of claim 1, further comprising an ablation catheter.

4. The system of claim 3, wherein the ablation catheter is located at the new arrhythmia location and is configured to treat the arrhythmia.

5. The system of claim 1, wherein the learning system is trained using at least one selected from the group consisting of classification, regression, and clustering algorithms.

6. The system of claim 1, wherein the processor comprising a neural network is further configured to:

receiving a patient characteristic;

training the learning system based on the patient characteristics; and

the model is generated based on a further trained learning system.

7. The system of claim 1, wherein the processor comprising a neural network is further configured to:

receiving catheter position data;

training the learning system based on the catheter position data; and

the model is generated based on a further trained learning system.

8. The system of claim 1, wherein the processor comprising a neural network is further configured to assign a score to at least one of the corresponding arrhythmia locations, wherein the score corresponds to a noise probability of the at least one of the corresponding arrhythmia locations.

9. The system of claim 8, wherein the score is in the range of 0 to 1.

10. The system of claim 8, wherein the processor comprising a neural network is further configured to filter out locations that score 0.

11. A method for generating an arrhythmia prediction model, the method comprising:

receiving a plurality of historical ECG data and a corresponding arrhythmia location determined based on each of the plurality of historical ECG data;

training a learning system based on a first set of historical ECG data from the plurality of historical ECG data and corresponding arrhythmia locations such that a combination of ECG attributes from the ECG correlates with a first set of corresponding arrhythmia locations;

updating the learning system based on a second set of historical ECG data from the plurality of historical ECG data and corresponding arrhythmia locations such that a combination of ECG attributes from the ECG correlates with a second set of corresponding arrhythmia locations; and

generating a model based on the first set of corresponding arrhythmia locations and the second set of corresponding arrhythmia locations.

12. The method of claim 11, wherein the second set of corresponding arrhythmic locations is an improved first set of corresponding arrhythmic locations.

13. The method of claim 11, further comprising assigning a score to at least one of the corresponding arrhythmia locations, wherein the score corresponds to a noise probability of the at least one of the corresponding arrhythmia locations.

14. The method of claim 13, wherein the score is in the range of 0 to 1.

15. The method of claim 13, further comprising filtering out locations with a score of 0.

16. A system for automatically applying coherent mapping, comprising:

an intrabody catheter configured to detect a location within a heart;

a processor comprising a neural network and configured to:

receiving a plurality of historical coherent mapping data for a plurality of patients, the historical coherent mapping data comprising patient-specific data and a plurality of coherent mapping adjustments;

training a learning system based on the historical coherent mapping data;

generating a model based on the learning system;

receiving new mapping data using the intra-body catheter; and

providing a new coherent mapping adjustment based on the new mapping data and the model.

17. The system of claim 16, wherein the coherent mapping adjustments include at least any one or a combination of changes in respiration, mechanical effects of the catheter on the chamber wall, and changes in chamber dynamics during arrhythmias.

18. The system of claim 16, wherein the new mapping data includes an input to the model and the new coherent mapping adjustment is an output of the model.

19. The system of claim 16, wherein the processor comprising a neural network is further configured to assign a score to at least a portion of the new mapping data, wherein the score corresponds to a noise probability of the at least a portion of the new mapping data.

20. The system of claim 19, wherein the score is in a range of 0 to 1, and wherein the processor comprising a neural network is further configured to filter out at least one new coherent mapping adjustment of the model due to a score of 0.

Technical Field

The present teachings relate to artificial intelligence and machine learning associated with optimizing mapping and identifying optimal regions for conducting cardiac protocols.

Background

Medical conditions such as cardiac arrhythmias (e.g., Atrial Fibrillation (AF)) are typically diagnosed and treated by in vivo procedures. For example, pulmonary venous electrical isolation (PVI) from the Left Atrial (LA) body is performed using ablation for treating AF. PVI and many other minimally invasive catheterization procedures require real-time visualization and mapping of the internal body surface.

Visualization and mapping of an intracorporeal site may be performed by mapping propagation of activation waves, fluoroscopy, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI), as well as other techniques that may require more than a desired amount of time or resources to provide visualization and mapping.

In addition, medical professionals often observe an Electrocardiogram (ECG) in an attempt to locate the site of the arrhythmia. Successful identification of such arrhythmias may often require years of medical training and may still lead to human error.

Disclosure of Invention

Systems, devices, and techniques for automatically detecting the location of an arrhythmia are disclosed. The systems, devices, and techniques may include a plurality of body surface electrodes configured to sense Electrocardiogram (ECG) data. The systems, apparatuses, and techniques may include a processor including a neural network configured to receive a plurality of historical ECG data and corresponding arrhythmia locations determined based on each of the plurality of historical ECG data, train a learning system based on the plurality of historical ECG data and corresponding arrhythmia locations, and generate a model based on the learning system. New ECG data may be received from the plurality of sets of table electrodes and the processor may provide a new arrhythmia location based on the new ECG data. Additionally, a new coherent mapping adjustment may be provided based on the model trained using the historical coherent mapping adjustment.

Drawings

A more particular understanding can be obtained by reference to the following detailed description, which is provided by way of example in connection with the accompanying drawings, wherein like reference numbers refer to like elements, and in which:

FIG. 1 is a block diagram of an exemplary system for remotely monitoring and transmitting a patient biometric;

FIG. 2 is a system diagram of an example of a computing environment in communication with a network;

FIG. 3 is a block diagram of an exemplary apparatus that may implement one or more features of the present disclosure;

FIG. 4 depicts a graphical depiction of an artificial intelligence system incorporating the exemplary apparatus of FIG. 3;

FIG. 5 illustrates a method performed in the artificial intelligence system of FIG. 4;

FIG. 6 shows an example of a probability of a naive Bayes calculation;

FIG. 7 illustrates an exemplary decision tree;

FIG. 8 illustrates an exemplary random forest classifier;

FIG. 9 illustrates an exemplary logistic regression;

FIG. 10 illustrates an exemplary support vector machine;

FIG. 11 illustrates an exemplary linear regression model;

FIG. 12 illustrates exemplary K-means clustering;

FIG. 13 illustrates an exemplary ensemble learning algorithm;

FIG. 14 illustrates an exemplary neural network;

FIG. 15 illustrates a hardware-based neural network;

fig. 16A to 16D show examples of cardiomyopathies with different etiologies;

FIG. 17 is an illustration of an exemplary system in which one or more features of the disclosed subject matter can be implemented;

FIG. 18A shows an example of a linear catheter comprising a plurality of electrodes;

fig. 18B shows an example of a balloon catheter comprising a plurality of elongate strips;

FIG. 18C shows an example of a ring catheter including multiple electrodes;

FIG. 19 is a flow chart for identifying heart location based on ECG data and a model;

FIG. 20A shows exemplary ECG data and associated heart locations;

FIG. 20B shows another exemplary ECG data and associated heart location;

FIG. 21 illustrates an exemplary logistic regression graph for predicting whether certain ECG characteristics are likely to correspond to a given heart location with arrhythmia;

fig. 22 shows a flow chart for applying coherent mapping adjustments based on patient-specific data; and

fig. 23A-C illustrate inherent limitations associated with chamber reconstruction and data projection.

Detailed Description

According to exemplary embodiments of the disclosed subject matter, a medical procedure may be optimized by applying historic Electrocardiogram (ECG) data that is successfully used to map the location of an arrhythmia to predict the location of the arrhythmia such that the arrhythmia may be treated.

In addition, according to exemplary embodiments of the presently disclosed subject matter, cardiac mapping/rendering may be improved based on a number of factors in addition to location-based mapping. Such factors may be improved based on the assessment of a given patient and corresponding mapping over an external time period (e.g., 30 seconds) that is not needed for correction from a given cardiac mapping. Such unwanted external factors may be, but are not limited to, noise, cycle data (e.g., breathing), position correction, and the like. As disclosed herein, the training data may include a plurality of such corrections that may be provided such that a given model is trained to automatically correct such unwanted external features for new cardiac mapping without requiring evaluation of a new patient over a period of time (e.g., 30 seconds).

Fig. 1 is a block diagram of an exemplary system 100 for remotely monitoring and transmitting patient biometrics (i.e., patient data). In the example shown in fig. 1, the system 100 includes a patient biometric monitoring and processing device 102 associated with a patient 104, a local computing arrangement 106, a remote computing system 108, a first network 110, and a second network 120.

According to an embodiment, the monitoring and processing device 102 may be a (e.g., subcutaneously implantable) device within the patient. The monitoring and processing device 102 may be inserted into the patient via any suitable means, including oral injection, surgical insertion via veins or arteries, endoscopic or laparoscopic procedures.

According to an embodiment, the monitoring and processing device 102 may be a device external to the patient. For example, as described in more detail below, the monitoring and processing device 102 may include an attachable patch (e.g., that attaches to the skin of a patient). The monitoring and processing device 102 may also include a catheter having one or more electrodes, a probe, a blood pressure cuff, a weight scale, a bracelet or smart watch biometric tracker, a glucose monitor, a Continuous Positive Airway Pressure (CPAP) machine, or virtually any device that can provide input related to the health or biometrics of a patient.

According to an embodiment, the monitoring and processing device 102 may include both patient-internal components and patient-external components.

A single monitoring and processing device 102 is shown in fig. 1. However, an exemplary system may include a plurality of patient biometric monitoring and processing devices. The patient biometric monitoring and processing device may be in communication with one or more other patient biometric monitoring and processing devices. Additionally or alternatively, the patient biometric monitoring and processing device may be in communication with the network 110.

The one or more monitoring and processing devices 102 may acquire patient biometric data (e.g., electrical signals, blood pressure, temperature, blood glucose level, or other biometric data) and receive at least a portion of the patient biometric data representing the acquired patient biometric and additional information associated with the acquired patient biometric from the one or more other monitoring and processing devices 102. The additional information may be, for example, diagnostic information and/or additional information obtained from an additional device, such as a wearable device. Each monitoring and processing device 102 may process data, including its own acquired patient biometric as well as data received from one or more other monitoring and processing devices 102.

In fig. 1, network 110 is an example of a short-range network, such as a Local Area Network (LAN) or a Personal Area Network (PAN). Information may be sent between the monitoring and processing device 102 and the local computing arrangement 106 via the short-range network 110 using any 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).

Network 120 may be a wired network, a wireless network, or include one or more wired and wireless networks. For example, the network 120 may be a remote network (e.g., a Wide Area Network (WAN), the internet, or a cellular network). Information may be transmitted via network 120 using any of a variety of long-range wireless communication protocols (e.g., TCP/IP, HTTP, 3G, 4G/LTE, or 5G/new radio).

The patient monitoring and processing device 102 may include a patient biometric sensor 112, a processor 114, a User Input (UI) sensor 116, a memory 118, and a transmitter-receiver (i.e., transceiver) 122. The patient monitoring and processing device 102 may continuously or periodically monitor, store, process, and transmit any number of various patient biometrics via the network 110. Examples of patient biometrics include electrical signals (e.g., ECG signals and brain biometrics), blood pressure data, blood glucose data, and temperature data. Patient biometrics can be monitored and communicated in order to treat any number of a variety of diseases, such as cardiovascular diseases (e.g., arrhythmias, cardiomyopathy, and coronary artery disease) and autoimmune diseases (e.g., type I and type II diabetes).

Patient biometric sensor 112 may include, for example, one or more sensors of a type configured to sense a biometric patient biometric. For example, patient biometric sensor 112 may include electrodes configured to acquire electrical signals (e.g., cardiac signals, brain signals, or other bioelectrical signals), temperature sensors, blood pressure sensors, blood glucose sensors, blood oxygen sensors, pH sensors, accelerometers, and microphones.

As described in more detail below, the patient biometric monitoring and processing device 102 may be an ECG monitor for monitoring ECG signals of the heart. The patient biometric sensor 112 of the ECG monitor may include one or more electrodes for acquiring ECG signals. The ECG signal can be used to treat various cardiovascular diseases.

In another example, the patient biometric monitoring and processing device 102 may be a Continuous Glucose Monitor (CGM) for continuously monitoring the blood glucose level of a patient to treat various diseases, such as type I and type II diabetes. CGM may include subcutaneously placed electrodes that can monitor blood glucose levels from interstitial fluid of a patient. The CGM may be a component of, for example, a closed loop system, where blood glucose data is sent to an insulin pump for calculating the delivery of insulin without user intervention.

The transceiver 122 may include separate transmitters and receivers. Alternatively, the transceiver 122 may include a transmitter and a receiver integrated into a single device.

The processor 114 may be configured to store patient data, such as patient biometric data acquired by the patient biometric sensor 112, in the memory 118 and to transmit the patient data across the network 110 via the transmitter of the transceiver 122. Data from one or more other monitoring and processing devices 102 may also be received by a receiver of transceiver 122, as described in more detail below.

According to an embodiment, the monitoring and processing device 102 includes a UI sensor 116, which may be, for example, a piezoelectric sensor or a capacitive sensor configured to receive user input (such as a tap or touch). For example, in response to the patient 104 tapping or touching a surface of the monitoring and processing device 102, the UI sensor 116 may be controlled to enable capacitive coupling. Gesture recognition may be accomplished via any of a variety of capacitance types, such as resistive-capacitive, surface-capacitive, projected-capacitive, surface acoustic wave, piezoelectric, and infrared touch. The capacitive sensor may be disposed at a small area or over the length of the surface such that a tap or touch of the surface activates the monitoring device.

As described in more detail below, the processor 114 may be configured to selectively respond to different tap patterns (e.g., single or double tap) of the capacitive sensor (which may be the UI sensor 116) such that different tasks (e.g., acquisition, storage, or transmission of data) of the patch may be activated based on the detected patterns. In some implementations, when a gesture is detected, audible feedback may be given to the user from the processing device 102.

The local computing device 106 of the system 100 is in communication with the patient biometric monitoring and processing device 102 and may be configured to act as a gateway to the remote computing system 108 over the second network 120. For example, the local computing device 106 may be a smart phone, smart watch, tablet computer, or other portable smart device configured to communicate with other devices via the network 120. Alternatively, the local computing device 106 may be a fixed or stand-alone device, such as a fixed base station including, for example, modem and/or router capabilities, a desktop or laptop computer that uses executable programs to transfer information between the processing device 102 and the remote computing system 108 via the PC's radio module, or a USB dongle. Patient biometrics may be communicated between the local computing device 106 and the patient biometric monitoring and processing device 102 via a short-range wireless network 110, such as a Local Area Network (LAN) (e.g., a Personal Area Network (PAN)), using short-range wireless technology standards (e.g., bluetooth, Wi-Fi, ZigBee, Z-wave, and other short-range wireless standards). In some embodiments, the local computing device 106 may also be configured to display the acquired patient electrical signals and information associated with the acquired patient electrical signals, as described in more detail below.

In some embodiments, the remote computing system 108 may be configured to receive at least one of the monitored patient biometric and information associated with the monitored patient via the network 120 as a remote network. For example, if the local computing device 106 is a mobile telephone, the network 120 may be a wireless cellular network and may communicate information between the local computing device 106 and the remote computing system 108 via a wireless technology standard, such as any of the wireless technologies described above. As described in more detail below, the remote computing system 108 may be configured to provide (e.g., visually display and/or audibly provide) at least one of patient biometrics and related information to a healthcare professional (e.g., a physician).

Fig. 2 is a system diagram of an example of a computing environment 200 in communication with network 120. In some cases, the computing environment 200 is incorporated into a public cloud computing platform (such as Amazon Web Services or Microsoft Azure), a hybrid cloud computing platform (such as HP Enterprise oneserver), or a private cloud computing platform.

As shown in FIG. 2, the computing environment 200 includes a remote computing system 108 (hereinafter computer system), which is one example of a computing system on which embodiments described herein may be implemented.

The remote computing system 108 may perform various functions via a processor 220, which may include one or more processors. The functions may include analyzing monitored patient biometrics and related information, and providing (e.g., via display 266) alarms, additional information or instructions in accordance with physician-determined or algorithm-driven thresholds and parameters. As described in more detail below, the remote computing system 108 may be used to provide a patient information dashboard (e.g., via the display 266) to healthcare personnel (e.g., physicians) so that such information may enable the healthcare personnel to identify and prioritize patients with more critical needs than others.

As shown in FIG. 2, computer system 210 may include a communication mechanism (such as a bus 221) or other communication mechanism for communicating information within computer system 210. Computer system 210 also includes one or more processors 220 coupled with bus 221 for processing information. Processor 220 may include one or more CPUs, GPUs, or any other processor known in the art.

Computer system 210 also includes a system memory 230 coupled to bus 221 for storing information and instructions to be executed by processor 220. The system memory 230 may include computer-readable storage media in the form of volatile and/or nonvolatile memory such as read only system memory (ROM)231 and/or Random Access Memory (RAM) 232. The system memory RAM 232 may include other dynamic storage devices (e.g., dynamic RAM, static RAM, and synchronous DRAM). The system memory ROM 231 may include other static storage devices (e.g., programmable ROM, erasable PROM, and electrically erasable PROM). In addition, system memory 230 may be used to store temporary variables or other intermediate information during execution of instructions by processor 220. A basic input/output system 233(BIOS), containing the basic input/output system 233(BIOS), may be included between elements within the computer system 210, such as routines to transfer information during start-up, which may be stored in system memory ROM 231. RAM 232 may contain data and/or program modules that are immediately accessible to and/or presently being operated on by processor 220. System memory 230 may additionally include, for example, an operating system 234, application programs 235, other program modules 236, and program data 237.

The illustrated computer system 210 also includes a disk controller 240 coupled to the bus 221 to control one or more storage devices for storing information and instructions, such as a magnetic hard disk 241 and a removable media drive 242 (e.g., a floppy disk drive, an optical disk drive, a tape drive, and/or a solid state drive). Storage devices may be added to computer system 210 using an appropriate device interface (e.g., Small Computer System Interface (SCSI), Integrated Device Electronics (IDE), Universal Serial Bus (USB), or firewire).

Computer system 210 may also include a display controller 265 coupled to bus 221 to control a monitor or display 266, such as a Cathode Ray Tube (CRT) or Liquid Crystal Display (LCD), to display information to a computer user. The illustrated computer system 210 includes a user input interface 260 and one or more input devices, such as a keyboard 262 and a pointing device 261, for interacting with a computer user and providing information to the processor 220. Pointing device 261 may be, for example, a mouse, a trackball, or a pointing stick for communicating direction information and command selections to processor 220 and for controlling cursor movement on display 266. The display 266 may provide a touch screen interface that may allow input to supplement or replace the communication of direction information and command selections by the pointing device 261 and/or the keyboard 262.

Computer system 210 may perform a portion of, or each of, the functions and methods described herein in response to processor 220 executing one or more sequences of one or more instructions contained in a memory, such as system memory 230. Such instructions may be read into system memory 230 from another computer-readable medium, such as hard disk 241 or removable media drive 242. Hard disk 241 may contain one or more data stores and data files used by embodiments described herein. The data store contents and data files may be encrypted to improve security. Processor 220 may also be employed in a multi-processing arrangement to execute one or more sequences of instructions contained in system memory 230. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions. Thus, embodiments are not limited to any specific combination of hardware circuitry and software.

As described above, computer system 210 may include at least one computer-readable medium or memory for holding instructions programmed according to embodiments described herein and for containing data structures, tables, records, or other data described herein. The term computer-readable medium as used herein refers to any non-transitory tangible medium that participates in providing instructions to processor 220 for execution. Computer-readable media can take many forms, including but not limited to, non-volatile media, and transmission media. Non-limiting examples of non-volatile media include optical, solid state, magnetic disks, and magneto-optical disks, such as the hard disk 241 or the removable media drive 242. Non-limiting examples of volatile media include dynamic memory, such as system memory 230. Non-limiting examples of transmission media include coaxial cables, copper wire and fiber optics, including the wires that comprise bus 221. Transmission media can also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

Computing environment 200 may also include a computer system 210 that operates in a networked environment using logical connections to local computing device 106 and one or more other devices, such as a personal computer (laptop or desktop), a mobile device (e.g., a patient mobile device), a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above relative to computer system 210. When used in a networking environment, the computer system 210 can include a modem 272 for establishing communications over the network 120, such as the Internet. The modem 272 may be connected to the system bus 221 via the network interface 270, or via another appropriate mechanism.

As shown in fig. 1 and 2, network 120 may be any network or system known in the art, including the internet, an intranet, a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a direct connection or a series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between computer system 610 and other computers (e.g., local computing device 106).

Fig. 3 is a block diagram of an example apparatus 300 that may implement one or more features of the present disclosure. For example, the device 300 may be a local computing device 106. The device 300 may comprise, for example, a computer, a gaming device, a handheld device, a set-top box, a television, a mobile phone, or a tablet. The device 300 includes a processor 302, a memory 304, a storage device 306, one or more input devices 308, and one or more output devices 310. The apparatus 300 may also optionally include an input driver 312 and an output driver 314. It should be understood that the apparatus 300 may include additional components not shown in FIG. 3, including an artificial intelligence accelerator.

In various alternatives, processor 302 includes a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a CPU and a GPU located on the same die, or one or more processor cores, where each processor core may be a CPU or a GPU. In various alternatives, the memory 304 is located on the same die as the processor 302 or is located separately from the processor 302. The memory 304 includes volatile or non-volatile memory, such as Random Access Memory (RAM), dynamic RAM, or cache.

Storage 306 includes fixed or removable storage, such as a hard disk drive, solid state drive, optical disk, or flash drive. Input device 308 includes, but is not limited to, a keyboard, keypad, touch screen, touch pad, detector, microphone, accelerometer, gyroscope, biometric scanner, or a network connector (e.g., a wireless local area network card for transmitting and/or receiving wireless IEEE802 signals). Output devices 310 include, but are not limited to, a display, a speaker, a printer, a haptic feedback device, one or more lights, an antenna, or a network connection (e.g., a wireless local area network card for transmitting and/or receiving wireless IEEE802 signals).

The input driver 312 is in communication with the processor 302 and the input device 308 and allows the processor 302 to receive input from the input device 308. The output driver 314 communicates with the processor 302 and the output device 310 and allows the processor 302 to send output to the output device 310. Note that the input driver 312 and the output driver 314 are optional components, and if the input driver 312 and the output driver 314 are not present, the apparatus 300 will operate in the same manner. The output driver 316 includes an accelerated processing device ("APD") 316 coupled to a display device 318. The APD accepts compute commands and graphics rendering commands from processor 302, processes those compute and graphics rendering commands, and provides pixel outputs to display device 318 for display. As described in further detail below, APD316 includes one or more parallel processing units to perform computations according to a single instruction multiple data ("SIMD") paradigm. Thus, while various functions are described herein as being performed by APD316 or in conjunction with APD316, in various alternatives, the functions described as being performed by APD316 are additionally or alternatively performed by other computing devices with similar capabilities that are not driven by a host processor (e.g., processor 302) and that provide graphical output to display device 318. For example, any processing system that performs processing tasks according to the SIMD paradigm is contemplated to perform the functions described herein. Alternatively, computing systems that do not perform processing tasks according to the SIMD paradigm are contemplated to perform the functions described herein.

FIG. 4 shows a graphical depiction of an artificial intelligence system 200 incorporating the example apparatus of FIG. 3. The system 400 includes data 410, a machine 420, a model 430, a plurality of results 440, and underlying hardware 450. The system 400 operates in the following manner: the data 410 is used to train the machine 420 while the model 430 is built to enable prediction of multiple results 440. System 400 may operate with respect to hardware 450. In such a configuration, data 410 may be related to hardware 450 and may originate, for example, from device 102. For example, data 410 may be data being generated or output data associated with hardware 450. The machine 420 may operate as or be associated with a controller or data collection associated with the hardware 450. Model 430 may be configured to model the operation of hardware 450 and to model data 410 collected from hardware 450 in order to predict the results achieved by hardware 450. Using the predicted outcome 440, the hardware 450 may be configured to provide some desired outcome 440 from the hardware 450.

FIG. 5 illustrates a method 500 performed in the artificial intelligence system of FIG. 4. The method 500 includes collecting data from hardware at step 510. The data may include data currently collected from the hardware, historical data from the hardware, or other data. For example, the data may include measurements during a surgical procedure and may be associated with the results of the procedure. For example, the temperature of the heart may be collected and correlated with the results of a cardiac procedure.

At step 520, the method 500 includes training a machine on hardware. The training may include analysis and correlation of the data collected in step 510. For example, in the case of a heart, the temperature and outcome data may be trained to determine whether there is a correlation or link between the temperature of the heart and the outcome during the procedure.

At step 530, the method 500 includes building a model on data associated with hardware. Building a model may include physical hardware or software modeling, algorithmic modeling, and the like, as will be described below. The modeling may attempt to represent collected and trained data.

At step 540, the method 500 includes predicting an outcome of a model associated with the hardware. Such prediction of the outcome may be based on a trained model. For example, in the case of the heart, if a temperature between 97.7-100.2 degrees f during the procedure produces a positive result by the procedure, the result may be predicted in a given procedure based on the temperature of the heart during the procedure. While this model is basic, it is provided for exemplary purposes and to enhance understanding of the present teachings.

The system and method of the present invention are used to train machines, build models, and predict results using algorithms. These algorithms can be used to solve the trained model and predict the results associated with the hardware. These algorithms can generally be divided into classification, regression and clustering algorithms.

For example, classification algorithms are used to classify dependent variables (which are predicted variables) into multiple classes and predict the class (dependent variable) under a given input. Thus, classification algorithms are used to predict outcomes from a set number of fixed, predefined outcomes. The classification algorithms may include a naive bayes algorithm, a decision tree, a random forest classifier, logistic regression, a support vector machine, and k nearest neighbors.

Generally speaking, naive bayes algorithms follow bayesian theorems and follow probabilistic methods. It should be understood that other probability-based algorithms may also be used, and that these algorithms generally operate using probability principles similar to those described below for the exemplary naive bayes algorithm.

Fig. 6 shows an example of a probability of a na iotave bayes calculation. The probabilistic approach of bayesian theorem essentially means that the algorithm has a set of prior probabilities for each class of target, rather than hopping directly into the data. After inputting the data, the naive bayes algorithm can update the prior probabilities to form posterior probabilities. This is given by the following equation:

such a naive bayes algorithm, as well as a bayes algorithm, may often be useful when it is desired to predict whether your input belongs to n categories for a given list. A probabilistic approach may be used because the probability of all n classes will be rather low.

For example, as shown in FIG. 6, a person may play golf balls depending on factors including the outside weather shown in the first data set 610. The first data set 610 shows the weather in a first column and the results of a ball hit associated with the weather in a second column. In frequency table 620, the frequency at which certain events occur is generated. In the frequency table 620, the frequency of a person playing golf or not playing golf in each weather condition is determined. Thus, a likelihood table for generating initial probabilities is compiled. For example, the probability of the weather being cloudy is 0.29, while the general probability of playing a ball is 0.64.

A posterior probability may be generated from likelihood table 630. These posterior probabilities may be configured to answer questions about weather conditions and whether to play golf in those weather conditions. For example, the probability of a fair and golf shot outdoors may be illustrated by a bayesian formula:

p (clear) ═ P (clear) × P (yes)/P (clear)

From likelihood table 630:

p (clear | is) 3/9 0.33,

p (clear) 5/14 0.36,

p (yes) ═ 9/14 ═ 0.64.

Thus, P (is | clear) ═ 0.33 × 0.64/0.36 or about 0.60 (60%).

Generally, a decision tree is a tree structure similar to a flow chart, where each external node represents a test on an attribute and each branch represents the result of the test. Leaf nodes contain actual prediction tags. The decision tree starts at the tree root where the attribute values are compared until the leaf nodes are reached. The decision tree may be used as a classifier when processing high dimensional data and when it has taken little time after data preparation. The decision tree may take the form of a simple decision tree, a linear decision tree, an algebraic decision tree, a deterministic decision tree, a stochastic decision tree, a non-deterministic decision tree, and a quantum decision tree. An exemplary decision tree is provided below in fig. 7.

Fig. 7 shows a decision tree for deciding whether to play golf, which follows the same structure as the bayesian example described above. In the decision tree, a first node 710 checks the weather, choosing sunny 712, cloudy 714 and rainy 716 days to progress down the decision tree. If the weather is not clear, the legs of the tree are followed to a second node 720 where the temperature is checked. In this example, the temperature at node 720 may be high 722 or normal 724. If the temperature at node 720 is high 722, a "no" (no play) 723 golf ball prediction occurs. If the temperature at node 720 is normal 724, then a "yes" (play) 725 golf ball prediction occurs.

Further, starting at the first node 710, a result of cloudy day 714 occurs, and yes 715 is reached.

Starting from the first node weather 710, the result of the rainy day 716 results in a third node 730 that (again) checks the temperature. If the temperature at the third node 730 is normal 732, then "yes" (play) 733 golf. If the temperature at the third node 730 is low 734, then "no" (no play) 735 is true for the golf ball.

According to the decision tree, if the weather is cloudy 715, under normal temperature sunny weather 725, and under normal temperature rainy weather 733, the golfer plays golf, and if it is sunny high temperature 723 or rainy low temperature 735, the golfer does not play golf.

A random forest classifier is a committee of decision trees in which each decision tree has been fed a subset of the attributes of the data and predictions are made based on that subset. The mode of the actual predicted values of the decision tree is considered to provide the final random forest answer. Random forest classifiers generally mitigate overfitting that exists in independent decision trees, resulting in more robust and accurate classifiers.

Fig. 8 shows an exemplary random forest classifier for classifying colors of clothing. As shown in fig. 8, the random forest classifier includes five decision trees 8101, 8102, 8103, 8104, and 8105 (collectively or generally referred to as decision trees 810). Each tree is designed to classify the color of the garment. A discussion of each tree and the decisions made is not provided, as each individual tree typically operates as the decision tree of fig. 7. In this example, three of the five trees (8101, 8102, 8104) determine the garment to be blue, while one tree determines the garment to be green (8103), and the remaining trees determine the garment to be red (8105). The random forest takes these actual predictions of the five trees and calculates the mode of these actual predictions to provide a random forest answer with clothing in blue.

Logistic regression is another algorithm used for binary classification tasks. Logistic regression is based on logistic functions (also called sigmoid functions). The sigmoid curve may take any real number of values and map it between 0 and 1, asymptotically approaching those limits. The logical model may be used to model the probability of a certain category or event of presence such as pass/fail, win/loss, survival/death, or health/illness. This may be extended to modeling several types of events, such as determining whether a cat, dog, lion, etc. is contained in the image. Each object detected in the image will be assigned a probability between 0 and 1, with the sum of the probabilities being 1.

In the logical model, the log probability (log of probability) of a value labeled "1" is a linear combination of one or more arguments ("predictor"); these arguments may each be binary variables (two classes, encoded by indicator variables) or continuous variables (any real value). The corresponding probability of a value marked as "1" may vary between 0 (affirmatively value "0") and 1 (affirmatively value "1"), and is therefore marked; the function that converts log probability to probability is a logical function, so this name is used. The unit of measure of the log probability scale is called the log fraction, from the logical unit, and therefore this alternative name is used. Similar models with different sigmoid functions rather than logistic functions may also be used, such as probabilistic models; the defining property of the logical model is to increase the probability that one of the arguments, each with its own parameters, multiplicatively scales a given result at a constant rate; for a binary dependent variable, this summarizes the probability ratio.

In the binary logistic regression model, the dependent variable has two levels (on the class). The output having more than two values is modeled by multiple logistic regression, and if the multiple classes are ordered, then modeled by sequential logistic regression (e.g., a proportional-dominant sequential logistic model). The logistic regression model itself simply models the probability of an output from an input and does not perform statistical classification (which is not a classifier), but it can be used to act as a classifier, for example, by selecting a cutoff value and classifying inputs with probabilities greater than the cutoff value into one class, and inputs with probabilities lower than the cutoff value into another analogy; this is a common way to make binary classifiers.

FIG. 9 illustrates an exemplary logistic regression. This exemplary logistic regression enables the prediction of results based on a set of variables. For example, based on an average school performance of an individual, results accepted by a school may be predicted. The past history of the average score performance and the relationship to the acceptance enables the prediction to occur. The logistic regression of fig. 9 enables analysis of the average credit performance variables 920 to predict a result 910 defined by 0 to 1. At the low end 930 of the sigmoid curve, the average credit performance point 920 predicts an unacceptable result 910. While at the high end 940 of the sigmoid curve, the average credit performance point 920 predicts an accepted result 910. Logistic regression can be used to predict house value, customer life values in the insurance industry, and the like.

A Support Vector Machine (SVM) can be used to classify data with a margin between two classes spaced as far apart as possible. This is called the maximum margin interval. The SVM may consider support vectors when rendering the hyperplane, as opposed to linear regression, which uses a dataset for this purpose.

FIG. 10 illustrates an exemplary support vector machine. In the exemplary SVM 1000, data may be classified into two different categories, represented as squares 1010 and triangles 1020. The SVM 1000 operates by plotting a random hyperplane 1030. The hyperplane 1030 is monitored by comparing the distance (shown by line 1040) between the hyperplane 1030 and the nearest data point 1050 from each category. The data points 1050 closest to the hyperplane 1030 are referred to as support vectors. Hyperplane 1030 is drawn based on these support vectors 1050, and the best hyperplane has the largest distance from each of these support vectors 1050. The distance between the hyperplane 1030 and the support vector 1050 is referred to as margin.

The SVM 1000 may be used to classify data by using the hyperplane 1030 such that the distance between the hyperplane 1030 and the support vector 1050 is maximized. For example, such SVM 1000 may be used to predict heart disease.

The K nearest neighbor points (KNN) refer to a set of algorithms that typically make no assumptions about the underlying data distribution and perform a fairly short training phase. Generally, KNN uses a number of data points divided into several categories to predict the classification of a new sample point. Operationally, KNN specifies an integer N with a new sample. The N entries in the model of the system closest to the new sample are selected. The most common classification of these entries is determined and assigned to the new sample. KNN generally requires that memory space increases as the training set increases. This also means that the estimation time increases in proportion to the number of training points.

In the regression algorithm, the output is a continuous quantity, and therefore the regression algorithm may be used in the case where the target variable is a continuous variable. Linear regression is a general example of a regression algorithm. Linear regression can be used to estimate the true quality (house cost, number of impressions, all buy-out transactions, etc.) from one or more consistent variables. The connection between the variables and the results is created by fitting the best line (and thus the linear regression). This best fit line is called the regression line and is expressed by the direct condition Y ═ a × X + b. Linear regression is best used in methods involving low dimensional numbers.

FIG. 11 illustrates an exemplary linear regression model. In this model, predictor variables 1110 are modeled relative to measured variables 1120. A cluster of instances of predictor variables 1110 and measure variables 1120 is plotted as data points 1130. Data points 1130 are then fitted with a best fit line 1140. The best fit line 1140 is then used for subsequent predictions given the measured variables 1120, and this line 1140 is used to predict the predicted variables 1110 for this instance. Linear regression can be used to model and predict aspects of financial portfolio, revenue forecasting, real estate, and traffic at the time of arrival estimate arrival.

Clustering algorithms can also be used to model and train the data set. In clustering, the inputs are assigned to two or more clusters based on feature similarity. Clustering algorithms typically learn patterns and useful insights from data without any guidance. For example, clustering viewers into similar groups based on their interests, age, geography, etc. may be performed using unsupervised learning algorithms such as K-means clustering.

K-means clustering is generally considered to be a simple unsupervised learning method. In K-means clustering, similar data points may be clustered together and bound in clusters. One method for binding data points together is by calculating the centroid of the set of data points. In determining the active clusters, in K-means clustering, the distance between each point and the centroid of the cluster is evaluated. Data is assigned to the closest cluster according to the distance between the data point and the centroid. The goal of clustering is to determine the eigen-groupings in a set of unlabeled data. "K" in the K-means represents the number of clusters formed. The number of clusters (essentially the number of categories into which new data instances can be classified) can be determined by the user. For example, the determination may be performed during training using feedback and looking at the size of the cluster.

K-means is mainly used where the data sets have distinct and well-spaced points, otherwise modeling may render the clusters inaccurate if they are not spaced. In addition, the K-means can be avoided in cases where the data set contains a large number of outliers or where the data set is non-linear.

Fig. 12 shows K-means clustering. In K-means clustering, data points are plotted and assigned K values. For example, for K — 2 in fig. 12, the data points are plotted as shown in plot 1210. These points are then assigned to similar centers at step 1220. Cluster centroids are identified as shown at 1230. Once the centroids are identified, the points are reassigned to the clusters to provide the minimum distance between the data point to the corresponding cluster centroid, as shown at 1240. A new centroid for the cluster can then be determined, as shown in depiction 1250. When reassigning data points to clusters, a new cluster centroid formation, iteration, or series of iterations may occur to minimize the size of the cluster and determine the centroid of the optimal centroid. Then, when a new data point is measured, the new data point can be compared to the centroid and cluster to identify with the cluster.

An ensemble learning algorithm may be used. These algorithms use multiple learning algorithms to achieve better prediction performance than can be achieved from any constituent learning algorithm alone. Ensemble learning algorithms perform the task of searching through a hypothesis space to find suitable hypotheses that will predict well for a particular problem. Even if the hypothesis space contains hypotheses that fit well into a particular problem, finding a good hypothesis may be very difficult. The integration algorithm combines multiple hypotheses to form a better hypothesis. The term integration is generally reserved for methods that use the same underlying learner to generate multiple hypotheses. The broader term of the multiple classifier system also encompasses a mixture of hypotheses that are not induced by the same base learner.

Evaluating the integrated predictions typically requires more computations than evaluating the predictions of a single model, and thus integration can be considered a way to compensate for poor learning algorithms by performing a large number of additional computations. Fast algorithms such as decision trees are often used in integration methods, e.g. random forests, although slower algorithms may also benefit from integration techniques.

The integration itself is a supervised learning algorithm, as the integration can be trained and then used to make predictions. Thus, the trained ensemble represents a single hypothesis. However, the assumption is not necessarily accommodated within the assumption space that the assumed model is built. Thus, integration can be shown with greater flexibility in the functionality that it can represent. In theory, this flexibility may enable these integrations to be more suitable for training data than a single model, but in practice, some integration techniques (especially bagging) tend to reduce problems associated with over-fitting training data.

Empirically, integrated algorithms tend to produce better results when there is significant diversity between models. Thus, many integration methods attempt to promote diversity between the models they combine. Although non-intuitive, a more random algorithm (e.g., a random decision tree) may be used to produce a stronger integration than a very intentional algorithm (e.g., an entropy-reducing decision tree). However, using a variety of brute force learning algorithms has been shown to be more efficient than using techniques that attempt to discard models to promote diversity.

The number of component classifiers integrated has a large impact on the accuracy of the prediction. Predetermining the integrated size and volume and speed of large data streams makes this even more important for online integrated classifiers. The theoretical framework suggests that there are an ideal number of component classifiers for integration, so having more or less than this number of classifiers will reduce accuracy. The theoretical framework shows that using the same number of independent component classifiers as class labels gives the highest accuracy.

Some common types of integration include bayesian-best classifiers, bootstrap aggregation (bagging), boosting, bayesian model averaging, bayesian model combining, model storage, and stacking. Fig. 13 shows an exemplary ensemble learning algorithm, where bagging is performed 1310 in parallel and boosting is performed 1320 sequentially.

A neural network is a network or circuit of neurons, or in a modern sense, an artificial neural network consisting of artificial neurons or nodes. The connections of biological neurons are modeled as weights. Positive weights reflect excitatory connections, while negative values indicate inhibitory connections. The inputs are modified by weights and summed using linear combinations. The activation function may control the amplitude of the output. For example, an acceptable output range is typically between 0 and 1, or the range may be between-1 and 1.

These artificial networks can be used for predictive modeling, adaptive control, and applications, and can be trained via a data set. Empirically generated self-learning can occur within a network, which can be concluded from a complex and seemingly unrelated set of information.

For completeness, a biological neural network consists of one or more groups of chemically linked or functionally related neurons. A single neuron may be connected to many other neurons, and the total number of neurons and connections in a network may be extensive. Connections (called synapses) are typically formed from axons to dendrites, but dendritic synapses and other connections are also possible. In addition to electrical signals, there are other forms of signals caused by neurotransmitter diffusion.

Artificial intelligence, cognitive modeling, and neural networks are information processing paradigms evoked by the way biological nervous systems process data. Artificial intelligence and cognitive modeling attempt to model some of the characteristics of biological neural networks. In the field of artificial intelligence, artificial neural networks have been successfully applied to speech recognition, image analysis, and adaptive control to build software agents or autonomous robots (in computers and video games).

In the case of artificial neurons, called Artificial Neural Networks (ANN) or Simulated Neural Networks (SNN), a Neural Network (NN) is a set of interconnected natural or artificial neurons that use mathematical or computational models for information processing based on computational methods of connection. In most cases, an ANN is an adaptive system that changes its structure based on external or internal information flowing through the network. The more realistic term neural network is a non-linear statistical data modeling or decision-making tool. These terms neural networks can be used to model complex relationships between inputs and outputs or to find patterns in data.

Artificial neural networks involve networks of simple processing elements (artificial neurons) that can exhibit complex global behavior determined by the connections between the processing elements and the element parameters.

One classic type of artificial neural network is the recurrent hopfield network. Artificial neural network models are useful in that they can be used to infer a function from observations and can also be used to use that function. Unsupervised neural networks can also be used to learn representations of inputs that capture salient features of the input distribution, and recent deep learning algorithms can implicitly learn the distribution function of the observed data. Learning in neural networks is particularly useful in applications where the complexity of the data or tasks makes it impractical to manually design such functions.

Neural networks are used in different fields. Tasks applied by artificial neural networks tend to fall within the following broad categories: functional approximation or regression analysis, including time series prediction and modeling; classification, including pattern and sequence recognition, novelty detection, and order decision; and data processing, including filtering, clustering, blind signal separation, and compression.

The application areas of ANN include nonlinear system recognition and control (vehicle control, process control), game play and decision making (checkers, chat, competition), pattern recognition (radar systems, facial recognition, object recognition), sequence recognition (gesture, voice, handwritten text recognition), medical diagnostics, financial applications, data mining (or knowledge discovery in databases, "KDD"), visualization, and email spam. For example, a semantic feature map of user interest may be created from a picture trained for object recognition.

Fig. 14 illustrates an exemplary neural network. In the neural network, there is a plurality of inputs such as 1410₁And 1410₂The input layer of the representation. Input 1410₁、1410₂Is provided to be depicted as including node 1420₁、1420₂、1420₃、1420₄The hidden layer of (1). These nodes 1420₁、1420₂、1420₃、1420₄Are combined to produce an output 1430 in the output layer. Neural networks via a hidden layer of simple processing elements (node 1420)₁、1420₂、1420₃、1420₄) Performing simple processing, the neural network may exhibit complex global behavior determined by the connections between processing elements and element parameters.

The neural network of fig. 14 may be implemented in hardware. As shown in fig. 15, a hardware-based neural network is shown.

Cardiac arrhythmias, and specifically atrial fibrillation, have long been a common and dangerous medical condition, especially in the elderly population. For patients with normal sinus rhythm, the heart, consisting of the atria, ventricles and excitatory conducting tissue, beats in a synchronized, patterned manner under the influence of electrical stimulation. For patients with cardiac arrhythmias, the abnormal region of cardiac tissue does not follow the synchronous beat cycle associated with normal conductive tissue as does a patient with a normal sinus rhythm. In contrast, abnormal regions of cardiac tissue are abnormally conducted to adjacent tissue, thereby disrupting the cardiac cycle to an asynchronous rhythm. It is previously known that such abnormal conduction occurs at various regions of the heart, such as in the Sinoatrial (SA) junction region, in the conduction pathways along the Atrioventricular (AV) node and the his bundle, or in the myocardial tissue forming the walls of the ventricular and atrial chambers.

Arrhythmias, including atrial arrhythmias, may be of the multi-wavelet reentrant type, characterized by multiple asynchronous loops of electrical impulses dispersed around the atrial chamber and generally self-propagating. Alternatively, or in addition to the multi-wavelet reentry type, arrhythmias may also have a focal source, such as when isolated tissue regions within the atrium beat autonomously in a rapidly repeating manner. Ventricular tachycardia (V-tach or VT) is a tachycardia or tachyarrhythmia that originates in one of the ventricles. This is a potentially life-threatening arrhythmia, as it can lead to ventricular fibrillation and sudden death.

One type of arrhythmia, atrial fibrillation, occurs when the normal electrical impulses generated by the sinoatrial node are overwhelmed by the disorganized electrical impulses originating in the atria and pulmonary veins, which result in irregular impulses being transmitted to the ventricles. Thereby producing an irregular heartbeat and may last from minutes to weeks, or even years. Atrial Fibrillation (AF) is generally a chronic condition that slightly increases the risk of death usually caused by stroke. The risk increases with age. Approximately 8% of people over the age of 80 have some degree of AF. Atrial fibrillation is usually asymptomatic and not itself generally life threatening, but it can cause palpitations, weakness, fainting, chest pain, and congestive heart failure. The risk of stroke increases during AF because blood can pool and form blood clots in the poorly contracting atria and left atrial appendage. First line treatment of AF is a drug therapy that can slow or normalize heart rhythm. In addition, people with AF are often given anticoagulants to prevent them from being at risk for stroke. The use of such anticoagulants is associated with its own risk of internal bleeding. For some patients, drug treatment is insufficient and their AF is considered drug refractory, i.e. no treatment is available with standard drug intervention. Synchronous electrical cardioversion may also be used to restore AF to a normal heart rhythm. Alternatively, AF patients are treated by catheter ablation.

Catheter ablation-based therapies may include mapping electrical properties of cardiac tissue (particularly endocardium and heart volume), and selectively ablating cardiac tissue by applying energy. Cardiac mapping, for example, creating a map of electrical potentials propagating along waves of cardiac tissue (voltage map) or a map of arrival times to various tissue locations (local time activation (LAT) maps) may be used to detect local cardiac tissue dysfunction ablation, such as those based on cardiac mapping, which may stop or modify the propagation of unwanted electrical signals from one portion of the heart to another.

The ablation process damages the unwanted electrical pathways by forming electrically non-conductive lesions. Various forms of energy delivery for forming lesions have been disclosed and include the use of microwaves, lasers and more commonly radio frequency energy to form conduction blocks along the walls of cardiac tissue. In a two-step procedure of mapping and then ablation, electrical activity at various points in the heart is typically sensed and measured by inserting a catheter containing one or more electrical sensors (or electrodes) into the heart and acquiring data at the various points. These data are then used to select an endocardial target area to be ablated.

Cardiac ablation and other cardiac electrophysiology protocols become increasingly complex as clinicians treat increasingly challenging conditions such as atrial fibrillation and ventricular tachycardia. Treatment of complex arrhythmias currently relies on the use of three-dimensional (3D) mapping systems in order to reconstruct the anatomy of the heart chamber of interest.

For example, cardiologists rely on software, such as that produced by Biosense Webster, Inc. (Diamond Bar, Calif.)A Complex Fractionated Atrial Electrogram (CFAE) module of the 33D mapping system analyzes intracardiac EGM signals and determines ablation points for treating a wide range of cardiac disorders, including atypical atrial flutter and ventricular tachycardia.

The 3D map may provide a variety of information about the electrophysiological properties of the tissue that represent these challenging arrhythmic anatomical and functional substrates.

Cardiomyopathies of different etiologies (hypoxia, Dilated (DCM), Hypertrophic Cardiomyopathy (HCM), Arrhythmogenic Right Ventricular Dysplasia (ARVD), left ventricular incompetence (LVNC), etc.) have identifiable substrates characterized by regions of unhealthy tissue surrounded by normal functioning cardiomyocytes.

Fig. 16A to 16D show examples of cardiomyopathies with different etiologies. As a first example, fig. 16A and 16B show an exemplary rendering of a heart 1600 with post-ischemic Ventricular Tachycardia (VT) characterized by an endocardial-epicardial low or intermediate voltage region 1602 in which signaling is slowed. This shows that measuring any prolonged electrical potential inside or around the dense scar region can help identify potential isthmuses that maintain VT. The post-ischemic VT shown in fig. 16A is characterized by an endocardial-epicardial low or intermediate voltage region of slowed signaling. This shows that measuring any prolonged electrical potential inside or around the dense scar region can help identify potential isthmuses that maintain VT. Fig. 16A shows bipolar signal amplitude (Bi) changes in various sectors of the heart 1600. FIG. 16A shows that Bi ranges from 0.5mV to 1.5 mV. Fig. 16B shows the Shortex Composite Interval (SCI) variation in various sectors of the heart. For example, the SCI ranges from 15.0 milliseconds to 171.00 milliseconds, with the SCI of interest ranging between 80 milliseconds and 170 milliseconds.

Fig. 16C and 16D show exemplary renderings of a heart 1610 that has experienced left ventricular incompetent cardiomyopathy. More specifically, fig. 16C shows an epicardial voltage map, and fig. 16D shows a Potential Duration Map (PDM). In fig. 16C and 16D, the three black circles in 1612 are marked as abnormally extended potentials, e.g., potentials above 200 milliseconds.

Abnormal tissue is generally characterized by a low voltage EGM. However, initial clinical experience in intracardiac-epicardial mapping indicates that the low voltage region is not always present as the only arrhythmogenic mechanism in such patients. Indeed, regions of low or medium voltage may exhibit EGM fragmentation and prolonged activity during sinus rhythm, which corresponds to a critical isthmus identified during persistent and tissue ventricular arrhythmias, e.g., applicable to intolerant ventricular tachycardia. Furthermore, in many cases, EGM fragmentation and prolonged activity were observed in regions exhibiting normal or near normal voltage amplitudes (> 1-1.5 mV). While a region can then be evaluated in terms of voltage amplitude, they cannot be considered normal in terms of intracardiac signals, and thus represent a true arrhythmogenic substrate. The 3D mapping can localize the proarrhythmic matrix on the endocardial and/or epicardial layers of the right/left ventricle, which can vary in distribution according to the spread of the primary disease.

The stroma associated with these cardiac conditions is associated with the presence of fragmented and prolonged EGMs in the endocardial and/or epicardial layers of the ventricular chambers (right and left). 3D mapping systems such asCan localize the underlying proarrhythmic substrate of cardiomyopathy in terms of abnormal EGM detection.

Electrode catheters have been commonly used in medical practice for many years. They are used to stimulate and map electrical activity in the heart, and to ablate sites of abnormal electrical activity. In use, an electrode catheter is inserted into a main vein or artery, such as the femoral artery, and then introduced 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 is provided, typically taped to the patient's skin, or may be provided using a second catheter placed in or near the heart. RF (radio frequency) current is applied to the tip electrode of the ablation catheter and the current flows through the surrounding medium (i.e., blood and tissue) to the reference electrode. The distribution of the current depends on the amount of contact of the electrode surface with the tissue compared to blood, which has a higher conductivity than the tissue. Heating of the tissue occurs due to the electrical resistance of the tissue. The tissue is heated sufficiently to cause cell destruction in the heart tissue, resulting in the formation of non-conductive foci within the heart tissue. During 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, possibly above 60 ℃, a thin transparent coating of dehydrated blood proteins can form on the surface of the electrode. If the temperature continues to rise, the dehydrated layer may become thicker, resulting in blood clotting on the electrode surface. Because dehydrated biological material has a higher electrical resistance than endocardial tissue, the impedance to the flow of electrical energy into the tissue also increases. If the impedance increases sufficiently, an impedance rise occurs and the catheter can be removed from the body and the tip electrode cleaned.

Fig. 17 is an illustration of an example system 1720 that can implement one or more features of the presently disclosed subject matter. All or a portion of the system 1720 may be used to collect information for a training data set and/or all or a portion of the system 1720 may be used to implement a trained model. The system 1720 may include a component, such as a catheter 1740, configured to damage a tissue region of an internal organ. The catheter 1740 may also be further configured to obtain biometric data. Although the catheter 1740 is shown as a pointed catheter, it should be understood that any shape catheter including one or more elements (e.g., electrodes) may be used to implement the embodiments disclosed herein. The system 1720 includes a probe 1721 having an axis that can be navigated by a physician 1730 into a body part of a patient 1728 lying on a table 1729, such as a heart 1726. According to an embodiment, multiple probes may be provided, however, for the sake of brevity a single probe 1721 is described herein, but it should be understood that the probe 1721 may represent multiple probes. As shown in fig. 17, the physician 1730 can insert the shaft 1722 through the sheath 1723 while manipulating the distal end of the shaft 1722 using the manipulator 1732 near the proximal end of the catheter 1740 and/or deflecting from the sheath 1723. As shown in fig. 1725, a catheter 1740 may be fitted at the distal end of the shaft 1722. The catheter 1740 may be inserted through the sheath 1723 in a collapsed state, and may then be deployed within the heart 1726. As further disclosed herein, the catheter 1740 can include at least one ablation electrode 1747 and a catheter needle 1748.

According to an exemplary embodiment, catheter 1740 may be configured to ablate a tissue region of a heart cavity of heart 1726. Inset 1745 shows the catheter 1740 in an enlarged view within the heart cavity of the heart 1726. As shown, the catheter 1740 can include at least one ablation electrode 1747 coupled to the body of the catheter. According to other exemplary embodiments, multiple elements may be connected via an elongate strip forming the shape of the catheter 1740. One or more other elements (not shown) may be provided, which may be any element configured to ablate or obtain biometric data, and may be an electrode, a transducer, or one or more other elements.

In accordance with embodiments disclosed herein, an ablation electrode, such as electrode 1747, may be configured to provide energy to a tissue region of an internal body organ, such as heart 1726. The energy may be thermal energy and may cause damage to the tissue region starting at a surface of the tissue region and extending into a thickness of the tissue region.

According to example embodiments disclosed herein, biometric data may include one or more of Local Activation Time (LAT), electrical activity, topology, bipolar maps, dominant frequency, impedance, and the like. The LAT may be a point in time corresponding to a locally activated threshold activity calculated based on a normalized initial starting point. The electrical activity may be any suitable electrical signal that may be measured based on one or more thresholds and may be sensed and/or enhanced based on a signal-to-noise ratio and/or other filters. The topology may correspond to the physical structure of a body part or a portion of a body part, and may correspond to a change in the physical structure relative to a different portion of the body part or relative to a different body part. The dominant frequency may be a frequency or range of frequencies that are ubiquitous at one part of the body part and may be different in different parts of the same body part. For example, the dominant frequency of the pulmonary veins of a heart may be different from the dominant frequency of the right atrium of the same heart. The impedance may be a measure of the resistance at a given region of the body part.

As shown in fig. 17, the probe 1721 and catheter 1740 may be connected to a console 1724. The console 1724 may include a processor 1741 (such as a general purpose computer) with suitable front end and interface circuits 1738 for transmitting signals to and receiving signals from the catheter, and for controlling other components of the system 1720. In some embodiments, the processor 1741 may be further configured to receive biometric data, such as electrical activity, and determine whether a given tissue region is conductive. According to one embodiment, the processor may be located external to the console 1724, and may be located, for example, in a catheter, in an external device, in a mobile device, in a cloud-based device, or may be a stand-alone processor.

As noted above, the processor 1741 may comprise a general purpose computer, which may be programmed with software to perform the functions described herein. The software may be downloaded to the general purpose computer in electronic form, over a network, for example, or it may alternatively or additionally be provided and/or stored on a non-transitory tangible medium, such as magnetic, optical, or electronic memory. The exemplary configuration shown in fig. 17 may be modified to implement the embodiments disclosed herein. The disclosed embodiments of the invention may be similarly applied using other system components and arrangements. Additionally, system 1620 may include additional components, such as elements for sensing electrical activity, wired or wireless connectors, processing and display devices, and the like.

According to one embodiment, the display connected to the processor (e.g., processor 1741) may be located at a remote location such as at a separate hospital or in a separate healthcare provider network. Additionally, the system 1720 may be of a surgical systemIn part, the surgical system is configured to obtain anatomical and electrical measurements of a patient organ (such as the heart) and perform a cardiac ablation procedure. An example of such a surgical system is marketed by Biosense WebsterProvided is a system.

The system 1720 may also, and optionally does, use ultrasound, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), or other medical imaging techniques known in the art to obtain biometric data, such as anatomical measurements of the patient's heart. The system 1720 may use a catheter, an Electrocardiogram (EKG), or other sensor that measures an electrical characteristic of the heart to obtain an electrical measurement. As shown in fig. 17, the biometric data including the anatomical measurements and the electrical measurements may then be stored in a memory 1742 of the mapping system 1720. Biometric data may be transferred from the memory 1742 to the processor 1741. Alternatively or in addition, the biometric data can be transmitted using a network 1662 to a server 1760, which can be local or remote.

The network 1762 may be any network or system known in the art, such as 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 the mapping system 1720 and the server 1760. The network 1662 may be wired, wireless, or a combination thereof. The wired connection may be implemented using ethernet, Universal Serial Bus (USB), RJ-11, or any other wired connection known in the art. The wireless connection may be implemented using Wi-Fi, WiMAX and bluetooth, infrared, cellular networks, satellite or any other wireless connection method known in the art. In addition, several networks may operate alone or in communication with each other to facilitate communication within the network 1762.

In some cases, the server 1762 may be implemented as a physical server. In other cases, the server 1762 may be implemented as a public cloud computing provider (e.g., Amazon Web Services)The virtual server of (1).

The console 1724 may be connected to a body surface electrode 1743, which may include an adhesive skin patch attached to the patient 1730, by a cable 1739. The processor, in conjunction with the current tracking module, may determine positional coordinates of the catheter 1740 within a body part of the patient, such as the heart 1726. The position coordinates may be based on impedance or electromagnetic fields measured between the body surface electrode 1743 and the electrode 1748 or other electromagnetic components of the catheter 1740. Additionally or alternatively, the placemat may be located on the surface of the bed 1729 and may be separate from the bed 1729.

The processor 1741 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 (electrocardiogram) or EMG (electromyogram) signal conversion integrated circuit. Processor 1741 may transfer 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.

The console 1724 can also include an input/output (I/O) communication interface that enables the console to communicate signals from and/or to the electrode 1747.

During the procedure, processor 1741 may facilitate presenting body part renderings 1735 to physician 1730 on display 1727 and storing data representing body part renderings 1735 in memory 1742. Memory 1742 may include any suitable volatile and/or nonvolatile memory, such as random access memory or a hard disk drive. In some embodiments, medical professional 1730 may be able to manipulate body part rendering 1735 using one or more input devices (such as a touchpad, mouse, keyboard, gesture recognition device, etc.). For example, an input device may be used to change the position of the catheter 1740 such that the rendering 1735 is updated. In an alternative embodiment, display 1727 may include a touch screen that may be configured to accept input from medical professional 1730 in addition to presenting body part renderings 1735.

Treatment of cardiac disorders such as arrhythmias often requires obtaining a detailed map of the cardiac tissue, chambers, veins, arteries, and/or electrical pathways. For example, a prerequisite for successful catheter ablation is that the cause of the arrhythmia is located exactly in the heart chamber. Such localization can be accomplished via electrophysiological studies during which electrical potentials are spatially resolved detected with a mapping catheter introduced into the heart chamber. This electrophysiological study (so-called electroanatomical mapping) thus provides 3D mapping data that can be displayed on a monitor. In many cases, mapping and treatment functions (e.g., ablation) are provided by a single catheter or a set of catheters, such that the mapping catheter also operates simultaneously as a treatment (e.g., ablation) catheter.

Mapping of cardiac regions such as cardiac regions, tissue, veins, arteries, and/or electrical pathways may result in identifying problem areas such as scar tissue, arterial blood sources (e.g., electrical rotors), healthy areas, and the like. The cardiac region 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 may include mapping based on one or more modalities, such as, but not limited to, LAT, electrical activity, topology, bipolar maps, dominant frequency, or impedance. Data corresponding to multiple modalities may be captured using a catheter inserted into a patient's body, and rendering may be provided simultaneously or at different times based on corresponding settings and/or preferences of a medical professional.

Cardiac mapping may be accomplished using one or more techniques. As an example of the first technique, cardiac mapping may be achieved by sensing electrical properties (e.g., LAT) of cardiac tissue from precise locations within the heart. Corresponding data may be acquired by one or more catheters advanced into the heart using a catheter having an electrical sensor and a position sensor in its distal tip. As a specific example, the location and electrical activity may be initially measured at about 10 to about 20 points on the inner surface of the heart. These data points may generally be sufficient to generate a satisfactory quality preliminary reconstruction or map of the cardiac surface. The preliminary map may be combined with data taken from additional points to produce a more comprehensive map of cardiac electrical activity. In a clinical setting, it is not uncommon to accumulate data at 100 or more sites to generate a detailed and comprehensive map of the heart chamber electrical activity. The detailed map generated can then be used as a basis for deciding on the course of therapeutic action, such as tissue ablation, to alter the propagation of cardiac electrical activity and restore a normal heart rhythm.

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 tissue. When trajectory information is sampled at a sufficient number of points in the heart, a map depicting such motion characteristics may be constructed.

The electrical activity at a point in the heart may be measured by advancing a catheter containing an electrical sensor at or near its distal tip, typically to the point in the heart, contacting the tissue with the sensor and acquiring data at that point. One disadvantage of using a catheter containing a single distal tip electrode to map a heart chamber is the long time required to acquire data point-by-point over the necessary number of points required for a detailed view of the chamber population. Accordingly, multi-electrode catheters have been developed to measure electrical activity at multiple points in the heart chamber simultaneously.

The multi-electrode catheter may be implemented using any suitable shape, such as a linear catheter with multiple electrodes, a balloon catheter including electrodes dispersed over multiple ridges that shape the balloon, a lasso or loop catheter with multiple electrodes, or any other suitable shape. Fig. 18A shows an example of a linear catheter 1802 including a plurality of electrodes 1804, 1805, and 1806 that may be used to map a cardiac region. The linear catheter 1802 may be fully or partially elastic such that it may twist, bend, and/or otherwise change its shape based on the received signals and/or based on the application of an external force (e.g., cardiac tissue) on the linear catheter 1802.

Fig. 18B shows an example of a balloon catheter 1812 that includes a plurality of elongate strips. In the example shown in fig. 18B, there are 12 strips, including strips 1814, 1815, 1816, and the plurality of electrodes on each strip includes electrodes 1821, 1822, 1823, 1824, 1825, and 1826, as shown. The balloon catheter 1812 may be designed such that when deployed into a patient, the balloon catheter 1812 electrodes may remain in intimate contact against the endocardial surface. For example, the balloon catheter 1812 may be inserted into a lumen, such as a Pulmonary Vein (PV). The balloon catheter 1812 may be inserted into the PV in a deflated state such that the balloon catheter does not occupy its maximum volume when inserted into the PV. The balloon catheter 1812 may be inflated inside the PV such that the electrodes on the balloon catheter are in contact with the entire circular section of the PV. Such contact with the entire circular segment of the PV or any other lumen may enable effective mapping and/or ablation.

Fig. 18C shows an example of a loop catheter 1830 (also referred to as a lasso catheter) including a plurality of electrodes 1832, 1834, and 1836 that may be used to map a region of the heart. The loop catheter 1830 may be fully or partially elastic such that it may twist, bend, and/or otherwise change its shape based on the received signals and/or based on the application of an external force (e.g., cardiac tissue) on the loop catheter 1830.

According to one example, a multi-electrode catheter such as linear catheter 1802, balloon catheter 1812, and loop catheter 1830 may be advanced into a chamber of the heart. Anteroposterior (AP) and lateral fluorescence maps can be obtained to establish the position and orientation of each electrode. An electrogram may be recorded by each of the electrodes in contact with the surface of the heart relative to a time reference, such as starting from a P-wave in a sinus rhythm from a body surface ECG. As further disclosed herein, the system can distinguish between those electrodes that record electrical activity and those electrodes that do not record electrical activity. The failure to record electrical activity may be due to a lack of close proximity to the endocardial wall. After the initial electrogram is recorded, the multi-electrode catheter may be repositioned, and the fluorescence and electrogram may be recorded again. The electrical map may be constructed according to iterations of the above process. .

According to one example, a cardiac map may be generated based on the detection of the intracardiac potential field. Non-contact techniques for simultaneously acquiring large amounts of electrical information of the heart may be implemented. For example, a catheter having a distal end portion may be provided with a series of sensor electrodes distributed over its surface and connected to insulated electrical conductors for connection to a signal sensing and processing device. The end portion may be sized and shaped such that the electrode is substantially spaced from the wall of the heart chamber. The intracardiac potential field may be detected during a single heartbeat. According to one example, the sensor electrodes may be distributed over a series of circumferences lying in planes spaced apart from each other. These planes may be perpendicular to the long axis of the end portion of the catheter. At least two additional electrodes may be provided adjacent at the ends of the long axis of the end. As a more specific example, the catheter may include four circumferences, with eight electrodes equiangularly spaced on each circumference. Thus, in this implementation, the catheter may include at least 34 electrodes (32 circumferential electrodes and 2 end electrodes).

According to another example, electrophysiology cardiac mapping systems and techniques based on non-contact and non-expanding multi-electrode catheters may be implemented. An electrogram may be obtained with a catheter having multiple electrodes (e.g., between 42 and 122 electrodes). According to this implementation, knowledge of the relative geometry of the probe and endocardium may be obtained, such as by a separate imaging modality, such as transesophageal echocardiography. After independent imaging, the non-contact electrodes may be used to measure cardiac surface potentials and construct a map therefrom. The technique may include the following steps (after the separate imaging step): (a) measuring electrical potentials with a plurality of electrodes disposed on a probe positioned in the heart; (b) determining a geometric relationship between the probe surface and the endocardial surface; (c) generating a coefficient matrix representing a geometric relationship of the probe surface and the endocardial surface; and (d) determining the endocardial potential based on the electrode potential and the coefficient matrix.

According to another example, techniques and devices for mapping electrical potential distributions of a heart chamber may be implemented. An intracardiac multi-electrode mapping catheter assembly may be inserted into a heart of a patient. The mapping catheter assembly may include a multi-electrode array with an integral reference electrode, or alternatively, a mating 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. The electrode array catheter may carry a plurality of individual electrode sites (e.g., at least 24). In addition, the exemplary technique can be implemented by knowing the location of each of the electrode sites on the array and knowing the geometry of the heart. These locations may be determined by techniques of impedance plethysmography.

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 a lumen to receive a reference catheter having a distal tip electrode assembly that may be used to probe the heart wall. The mapping catheter may include a braid of insulated wires (e.g., 24 to 64 wires in the braid), and each wire may be used to form an electrode site. The catheter may be readily positioned in the heart for acquiring electrical activity information from the first set of non-contact electrode sites and/or the second set of contact electrode sites.

According to another example, another catheter for mapping electrophysiological activity within the heart may be implemented. The catheter body 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. The catheter may also include at least one pair of orthogonal electrodes to generate a difference signal indicative of local cardiac electrical activity of adjacent orthogonal electrodes.

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 and passive electrodes into a heart, providing a current to the active electrodes to generate an electric field in a chamber of the heart, and measuring the electric field at a location of the passive electrodes. The passive electrodes may be included in an array positioned on an inflatable balloon of the balloon catheter. In embodiments, the array may have 60 to 64 electrodes.

According to another example, cardiac mapping may be accomplished using one or more ultrasound transducers. An ultrasound transducer may be inserted into a patient's heart and a plurality of ultrasound slices (e.g., 2D or 3D slices) may be collected at various locations and orientations within the heart. The position and orientation of a given ultrasound transducer may be recorded and the collected ultrasound slices may be stored so that they may be displayed at a later time. One or more ultrasound slices corresponding to the position of the probe (e.g., treatment catheter) at a later time may be displayed, and the probe may be overlaid on the one or more ultrasound slices.

According to other examples, the body patch and/or the body surface electrodes may be positioned on or near the patient's body. A catheter having one or more electrodes may be positioned within a body of a patient (e.g., within a heart of a patient), and a 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 patient's body (e.g., within the heart). The biometric data may be associated with the determined position of the catheter such that a rendering of a body part (e.g., the heart) of the patient may be displayed and the biometric data overlaid on the body part shape may be displayed, as determined by the position of the catheter.

According to an exemplary embodiment, the medical procedure may be optimized by predicting the location of the arrhythmia by applying historical ECG data used to map the location of the arrhythmia such that the arrhythmia may be effectively treated. For clarity, many examples of historical ECG data used to identify ablations that successfully treated arrhythmias may be used as training data to generate models according to the figures as provided herein. The model may be trained so that a new ECG may be fed into the model, and based on the trained components of the model, arrhythmic sites may be identified. Such implementations may alleviate or eliminate the need to manually identify arrhythmic sites to reduce human error, and may allow for higher confidence ablation.

FIG. 19 is a flow chart 1900 for identifying a heart location based on ECG data and a model. As shown in the flowchart 1900 of fig. 19, historical ECG data and corresponding heart locations may be collected at step 1902. The corresponding cardiac location may be a cardiac location identified as causing an arrhythmia based on the ECG data. As further disclosed herein, the ECG data and corresponding locations collected at step 1902 may correspond to a protocol in which the arrhythmia was successfully treated (e.g., via ablation). In step 1902, data of unsuccessful procedures may be discarded or not collected. Alternatively, data of unsuccessful procedures may be provided as negative data and considered accordingly.

At step 1904 of the process 1900 of fig. 19, the ECG data and corresponding location collected at step 1902 may be used as training data for the learning system. At step 1904, the training data can be used to train the learning system based on a given algorithm. At step 1906 of the process 1900 of FIG. 19, the trained learning system can be used to generate a model. A model may be generated such that given a new ECG input, the model is configured to provide as an output a new cardiac location corresponding to the predicted arrhythmia location predicted by the model.

At step 1908 of the process 1900 of fig. 19, new ECG data for the patient may be received by or provided as input to the model generated at step 1906. At step 1910, the model may output arrhythmia locations for treatment (e.g., by ablation).

As shown in the flowchart 1900 of fig. 19, historical ECG data and corresponding heart locations may be collected at step 1902. ECG data may be obtained using a multi-lead ECG (e.g., a 12-lead ECG) such that cardiac signals and electrical activity of the heart are recorded and can be observed to identify a condition of the heart, such as an arrhythmia. The ECG may be based on Body Surface (BS) electrode patches that may be placed at locations on the body surface of the patient. While the present disclosure generally relates to BS electrode-based ECGs, it should be understood that intracardiac electrodes may alternatively be used to obtain cardiac signals to generate an ECG. The data may be obtained using one or more magnetic sensors, electrode sensors, signal filtering algorithms, advanced catheter position (ACL) techniques, and the like.

As further disclosed herein, historical ECG data can be provided for a large number of patients. The large number of patients may be, for example, more than 100 patients, more than 1000 patients, more than 10,000 patients, etc. The number of patients using historical ECG data may depend on one or more of the quality of the ECG, the degree of success of the corresponding ablation, the variability of ECG readings in the historical ECG data set, and the like.

Depending on the implementation, the ECG data provided for a large number of patients may correspond to a protocol for successfully treating an arrhythmia by identifying the location of the arrhythmia using a corresponding ECG. For example, a set of 100 ECGs may be used to train the system, as further disclosed herein. From the 100 available ECGs, 70 ECGs may correspond to a protocol in which the ECGs are used to identify the location of the arrhythmia, which is then successfully treated (e.g., via ablation). 70 ECGs may be used as training data for embodiments disclosed herein. In contrast, 30 ECGs that are not used to identify the location of the arrhythmia or that identify the location of the arrhythmia but for which treatment was unsuccessful based on the identified location may not be included as training data.

Depending on the implementation, the ECG may be used to identify the location of a cardiac disorder, such as an arrhythmia. For example, QRS complexes during Ventricular Tachycardia (VT) can be generated from a given site of origin of focal VT or from a site of exit of the constrained diastolic isthmus during reentry VT. The ventricular geometry and activation of a given patient may dominate the ECG pattern seen in VT. For example, a left ventricular free wall VT may exhibit a Right Bundle Branch Block (RBBB) configuration, while a VT exiting from the intervening septum or right ventricle exhibits a Left Bundle Branch Block (LBBB) configuration. As another example, a septal exit may be associated with a narrower QRS complex consistent with synchronous activation rather than sequential ventricular activation. As another example, the basal site may show positive centripetal anterior coordination, while negative coordination may be seen in the apical site of origin. The QRS axis may vary primarily with outlet offset along the lower axis, but may also occur with right shifting. Even in the presence of significant structural heart disease, such distinguishing attributes can be applied, but significant scarring from previous infarcts, cardiomyopathies and congenital heart diseases can reduce the accuracy of the ECG as a locating tool.

As another example, anatomical changes may be a factor that may cause an interruption in the expected pattern of ECG vectors for a given arrhythmia origin. This may result from translational, rotational, or lateral shifting of the normal relationship of the heart to the chest wall, or from changes within the heart mediastinal anatomy itself. Antiarrhythmic drugs can be expected to affect the appearance of a surface ECG in VT by affecting myocardial conduction properties.

As an example of ECG data for identifying potential arrhythmia locations for treatment, fig. 20A shows an example of correlating an ECG with potential arrhythmia locations. In particular, fig. 20A shows a base view of the annulus and outflow tract regions after removal of the two atrial chambers. The close three-dimensional anatomical relationship of the various outflow tracts to the annular structure surrounding the central fibrous cardiac skeleton is shown. The Pulmonary Artery (PA), Right Ventricular Outflow Tract (RVOT), left coronary valve (LCC), right coronary valve (RCC), Left Coronary Artery (LCA), and Right Coronary Artery (RCA) are shown. In fig. 20A, 2002 shows an exemplary surface ECG appearance of VT caused by the back of the free wall of RVOT. See LBBB configuration with lower axis with late pre-cardiac transition after V3 and notch formed in lower lead. Positive force in lead I means posterior (or right) focus. At 2004, an example of the appearance of a surface ECG with VT of septal RVOT origin is shown. The early precordial transition before V3 is considered to have a negative lead I morphology. At 2004, the multiphasic notch configuration in lead V1 can be seen in the outflow tract VT, which originates from the left coronary valve of the valsalva aortic sinus. At 2008, an example of VT produced by the epicardium of the left ventricular outflow tract is mapped to the anterior interventricular vein region (where activation occurs 45ms before QRS onset). The ECG shows the lower axis configuration of the Left Bundle Branch Block (LBBB), with a 149ms wide QRS complex and intrinsic deflection of the pulposus.

Fig. 20B illustrates an example of ECG criteria that identify locations that can be used to identify potential arrhythmias. In particular, fig. 20B shows that the reporting interval and morphological ECG criteria used to identify the site of origin of left ventricular Epicardium (EPI) VT are evaluated by two different observers for fast VT 2022 and slow VT 2024. Notably, for fast VT 2022, QRS is defined differently from the beginning, thereby affecting the measurement of the interval criterion. As applied in fig. 20B, CL indicates the cycle length; IDT, intrinsic deflection time; MDI, maximum deflection index; PDW, pseudo delta wave; and SRS, shortest RS complex.

It should be understood that fig. 1 and 2 illustrate one embodiment. 20A and 20B are provided as examples and one or more other techniques may be used to identify potential arrhythmia sites based on ECG data. Such ECG data may be filtered based on the respective successful treatment of the arrhythmia such that ECG data corresponding to the unsuccessful treatment is filtered out.

At step 1904 of the process 1900 of fig. 19, the filtered ECG data can be used to train a learning system. The training may be performed using hardware, software, and/or firmware. The training may include analysis and correlation of the ECG data collected in step 1902. Attributes of a given ECG (e.g., such as those shown in fig. 20B) can be used to determine whether a correlation or link exists between a given aspect and a corresponding arrhythmia location.

Features of the ECG data collected at step 1902 can be extracted and can include ECG attributes (e.g., such as those shown in fig. 20B), patient history, scar information, catheter location, ablation tags (e.g., visitags), and the like. A feature matrix may be generated based on the extracted features and a learning system may be trained at step 1904. According to one implementation, the learning system may be trained based on a machine learning algorithm such as described herein.

At step 1906, the learning system can be trained using an algorithm to generate a model. The algorithm may be, for example, a classification algorithm, a regression algorithm, a clustering algorithm, or any suitable algorithm capable of generating a model that predicts the location of an arrhythmia using ECG data.

For example, fig. 21 shows a logistic regression graph to predict whether certain ECG features are likely to correspond to a given heart location with arrhythmia. The logistic regression enables prediction of arrhythmia location based on ECG attributes. For example, based on the plurality of QRS onsets, cycle lengths, and maximum deflection indices, it may be determined whether the arrhythmia originated from the results of the left atrium. Given the past history of the combination of QRS onset, cycle length, and maximum deflection index, and the relationship to cardiac arrhythmias originating from the left atrium, enables predictions to occur. The logistic regression of fig. 21 enables analysis of the combination of a given QRS onset, cycle length, and maximum deflection index variable 2120 to predict whether an arrhythmia is originating from the left atrium, with probabilities 2110 defined by 0 to 1. At the lower end 2130 of the S-shaped curve, a given combined prediction 2110 of QRS onset, cycle length, and maximum deflection index 2120 is not in the left atrium. While at the high end 2140 of the S-shaped curve, the combined 2120 prediction 2110 is in the left atrium.

As described above, a large variety of combinations of such features (e.g., ECG attributes, patient history, scar information, etc.) may be used to generate a plurality of logistic regression-based results, each predicting the likelihood of the location of an arrhythmia at a different location based on the features. Combinations of such logistic regression-based results may be used to generate a logistic regression model at step 1906 that is generated based on training of the learning system at step 1904.

It should be appreciated that although a logistic regression-based model is provided as an example, any suitable algorithm (e.g., classification, regression clustering, etc.) may be used to generate the corresponding model at step 1906.

Once sufficient training data (e.g., features) is used to train the learning system and generate a suitable model, the model can be used with the new data. At step 1908, a new ECG can be applied to the model, and the model can extract features from the new ECG and/or external features (e.g., patient history, scar information, etc.). Feature vectors may be generated and input into the model generated at 1906. At step 1910, the model may use the feature vectors as inputs (e.g., as shown in fig. 15) and may predict arrhythmia locations based on the inputs. According to one implementation, a plurality of potential arrhythmia locations may be provided such that each potential arrhythmia location is given a score (e.g., a correlation score) that indicates a probability of an arrhythmia at a predicted location as determined by the model.

In accordance with implementations of the presently disclosed subject matter, the predicted location of the arrhythmia may be confirmed via a pacing protocol. The pacing process may be an artificially induced electrical signal that serves as a source of potential arrhythmia.

The pacing catheter may be used at one or more arrhythmic locations, and may induce artificially generated electronic signals at each of the one or more predicted arrhythmic locations. The resulting ECG pattern can be viewed to confirm whether a given site is the source of an arrhythmia. According to a specific implementation, pacing catheters may be used at two or more potential arrhythmia locations identified by the model generated at step 1906. As disclosed herein, the model may provide two or more potential arrhythmia locations, and may provide a score (e.g., a correlation score) for each of these locations. A medical professional or automated system may then use the pacing catheter at these two or more locations and observe the corresponding ECG signal patterns to confirm which of these locations corresponds to the arrhythmic location.

In accordance with implementations of the presently disclosed subject matter, at step 1902, patient characteristics may be used to enhance the training of the learning system. The patient characteristic may be a characteristic other than patient specific ECG data. Patient characteristics may include, but are not limited to, patient age, gender, height, weight, and may also include any additional information about the patient, such as medical history, cardiac structure (e.g., based on MRI or CT scans), and the like. For example, a child's heart may be smaller than a growing adult, and thus, identifying arrhythmia locations may be supported by such additional information.

According to this implementation, the patient characteristics may supplement the ECG data in addition to the ECG data associated with the confirmed arrhythmia location, such that the learning system trained at step 1902 is trained by associating the patient characteristics with the confirmed arrhythmia location, as disclosed herein. Thus, the model generated at step 1906 may allow patient characteristics as input in addition to the ECG data.

For example, the subset of training data collected at step 1902 may correspond to a child. Thus, when the learning system is trained at 1904, the corresponding ECG data of the subset of training data may also be related to the child. Thus, the model may be trained to recognize that training applied to historical pediatric ECG data is more highly applicable than adult ECG data when providing new ECG data for children.

According to another implementation, the location of the catheter at the time the ECG data is collected may be used to enhance the training of the learning system at step 1902. The location of the catheter may correspond to a location within the heart, heart chamber, vein, and/or may correspond to proximity to tissue or another location-based feature.

According to this implementation, the location of the catheter may be supplemented with ECG data such that the learning system trained at step 1902 is trained by associating the location of the catheter with a confirmed arrhythmia location, in addition to ECG data associated with the confirmed arrhythmia location, as disclosed herein. Thus, the model generated at step 1906 may allow the location of the catheter as an input in addition to the ECG data. In addition, the ECG data and the position of the catheter can be used together with the catheter position (such as CT/MRI/grid) on the image as an additional input to the training model by normalizing the anatomy in such a way that the catheter position is located in the "same region" of the 3D model.

For example, the subset of training data collected at step 1902 may correspond to a catheter located in a Pulmonary Vein (PV). Thus, when the learning system is trained at 1904, the corresponding ECG data of the subset of training data may also be correlated with the PV. Thus, the model may be trained to recognize that training applied to historical PV ECG data is more highly applicable than non-PV ECG data when providing new ECG data collected in the patient's PV.

As disclosed, one or more potential arrhythmia locations may be identified at step 1910. The rendering or mapping of the heart (collectively, "mapping") may be used to identify one or more heart locations. For example, one or more identified cardiac locations may be displayed or highlighted on a map of the heart. A map of the heart may be generated external to the process 1900 of fig. 19 and may be generated using location tracking with electromagnetic signals (e.g., using one or more catheters, location pads, BS electrodes, etc., or a combination thereof).

In accordance with implementations of the presently disclosed subject matter, improved mappings may be generated using historical improvements to the mappings based on algorithmic solutions that account for inaccuracies associated with electrogram timing and presentation of complex activation patterns, as well as inaccuracies associated with projection of data into rigid chamber reconstructions. This improved mapping is referred to herein as coherent mapping. As further disclosed herein, coherent mapping may be achieved by improving conventional mapping, which may be achieved using electromagnetic signals to identify catheter locations (e.g., based on electromagnetic catheters, location pads, BS patches, etc.), cardiac boundaries (e.g., tissue proximity indications), ultrasound imaging, etc. Coherent mapping may improve traditional mapping based on time-based data collection (e.g., noise, chronic signals such as respiration, inaccuracies associated with electrogram timing and presentation of complex activation patterns, and inaccuracies associated with projection of data into rigid chamber reconstructions) collected over a period of time (e.g., 30 seconds).

As shown in the flowchart 2200 of fig. 22, historical coherent mapping data may be collected at step 2202. The coherent mapping data may include patient-specific data and coherent mapping adjustments made based on the patient-specific data. For clarity, coherent mapping data enhances conventional electromagnetic mapping, as disclosed herein.

At step 2204 of the process 2200 of fig. 22, the coherent mapping data collected at step 2202 may be used as training data for a learning system. At step 2204, the training data may be used to train the learning system based on a given algorithm. At step 2206 of the process 2200 of FIG. 22, the trained learning system may be used to generate a model. A model may be generated such that given new patient-specific data, mapping may be provided, and the model may be configured to provide coherent mapping (i.e., improved mapping) without having to recalculate such coherent mapping data for a given new patient.

At step 2208 of the process 2200 of fig. 22, new patient-specific data may be received by or provided as input to the model generated at step 2206. At step 2210, the model may output coherent mapping data based on the new patient-specific data, such that coherent mapping data is obtained without collecting coherent mapping data based on the patient-specific data (e.g., over a time period such as 30 seconds), but rather output by the model.

Historical coherent mapping data may be collected, as shown at step 2202. The data may be collected using one or more magnetic sensors, electrode sensors, signal filtering algorithms, Advanced Catheter Location (ACL) techniques, coherent mapping algorithms, and the like. The coherent mapping data may include patient-specific data and coherent mapping adjustments made based on the patient-specific data. Coherent mapping adjustments can be an improvement over traditional mapping and can better represent activation waves in complex matrices, with the limitations set forth in the introduction being most evident. As described herein, coherent mapping algorithm solutions account for inaccuracies associated with electrogram timing and presentation of complex activation patterns, as well as inaccuracies associated with projection of data into rigid chamber reconstructions.

LAT assays and their representation on 3D chamber reconstruction are disclosed herein. The electrogram temporal annotation may be determined by conventional mapping algorithms. According to this algorithm, LAT is determined by analyzing each bipolar electrogram and its corresponding unipolar electrogram, such that local temporal annotations are marked at the component with the greatest unipolar-dV/dt. However, in complex matrices with multiple potentials of relatively similar-dV/dt values, annotation of a single potential can be misleading and lead to LAT inconsistencies. To address this issue, coherent mapping can be designed to identify the possible potentials for each individual electrogram and chamber data. Once the chamber data is obtained, the algorithm utilizes the likelihood of each individual electrogram to determine the most coherent global propagation under physiological conduction.

The reconstruction chamber is a static and rigid representation of the dynamic anatomy. The activation map is created by sampling the LATs from various locations in the chamber. These measurements rarely fall on rigid reconstructions due to changes in respiration, mechanical effects of the catheter on the chamber wall (stretching), or changes in chamber dynamics during arrhythmias. Current mapping algorithms project these points onto the nearest surface, but the nearest location on the reconstruction is usually different from the sampling location. Further, samples from different locations and different LATs are associated with similar locations of reconstruction using the nearest location, as shown in fig. 23A.

According to an exemplary embodiment of the disclosed subject matter, coherent mapping data may be collected by dividing the surface into meshes with small triangles, thereby reducing the magnitude of interpolation related to errors in the projections, as shown in fig. 23B. Furthermore, the effect of each individual data point on the activation map can be designed to be proportional to its distance from the nearest triangle, so that data points further from the surface get lower weights than data points closer to the surface, as shown in FIG. 23C. The coherent mapping solution may reduce active mapping inaccuracies associated with projections of data points collected during different beats.

Fig. 23A-23C illustrate inherent limitations associated with chamber reconstruction and data projection. Fig. 23A includes a display of the association of different LAT measurements with the same location. FIG. 23B shows the reconstruction chamber divided into a triangular mesh consisting of small triangles (. apprxeq.0.5 mm), allowing more accurate assignment of measurements. Figure 23C shows a sagittal section of a reconstruction chamber with lines based on calculated LAT staining, where each individual measurement affects the calculated LAT in proportion to its distance (halo represents the attenuation effect with distance).

The coherent mapping algorithm assigns, for example, 3 descriptors to each triangle on the reconstructed mesh: LAT values, conduction vectors, and non-conductivity probabilities. The conduction velocity is calculated using the LAT values and the known distance and direction between the triangles. These descriptor values are initially known for triangles with direct measurements, but are unknown for other triangles on the reconstructed mesh. To address this issue, the following physiological-based assumptions apply: (1) speed continuity: in the region of conduction continuity, the conduction velocity remains as similar as possible to the adjacent triangle and is allowed to vary gradually. This relationship between triangles is performed by finding the mathematical formula of the minimum mean square error of the above relationship. The best solution produces the smallest difference at most locations, allowing for larger differences in areas of sufficient measurement contradictory continuity; and (2) identifying a non-conductive region by multiple measurements at the same location, indicating that the electrode resides in a region having at least 2 different waves. In these regions, the probability of conduction slowing or complete blockage is determined by the propagation vector and the calculated conduction velocity. In areas with structural obstacles for conduction, the propagation vector may bypass the obstacle or conduct through the obstacle at a slow rate. Conduction block is defined as a value below the lowest physiological conduction velocity (10cm/s) in the human atrium. The above criteria are used to set the probability that a triangle is in a non-conductive area. The equations are solved until the resulting LAT, conduction velocity and dielectric probability stabilize without further change, which represents the optimal solution.

The LAT, vector data, and identification of non-conductive or slowly conductive regions are used to generate an integrated coherent activation map. The coherent activation map is displayed as a vector map.

The techniques described above may be implemented such that coherent mapping data corresponding to a large number of patients (e.g., 100 patients, 1000 patients, 10,000 patients, etc.) is provided at step 2202. The coherent mapping data may include patient-specific data (e.g., cardiac structures, respiratory changes, mechanical effects of the catheter on the chamber wall (stretching), changes in chamber dynamics during arrhythmias, etc.) and corresponding coherent mapping adjustments made according to the data.

At step 2204, a learning system may be trained based on the coherent mapping data collected at step 2202. Training may include extracting features from the coherent mapping data to create a feature matrix. The feature matrix may be applied to the algorithm used to generate the model at step 2206. The algorithm may be, for example, a classification algorithm, a regression algorithm, a clustering algorithm, or any suitable algorithm capable of using coherent mapping data to generate a model that predicts coherent mapping adjustments based on patient-specific data of a new patient.

For example, fig. 13 illustrates an exemplary neural network that can be implemented to train the model at step 2206. In the neural network, there is a plurality of inputs such as 1410₁And 1410₂The input layer of the representation. The input may include patient specific data (e.g., cardiac structure, respiratory changes, mechanical effects of the catheter on the chamber wall (stretching), changes in chamber dynamics during arrhythmias, etc.). Will be input 1410₁、1410₂The provisioning is depicted as including node 1420₁、1420₂、1420₃、1420₄The hidden layer of (1). These nodes 1420₁、1420₂、1420₃、1420₄Combine to produce an output 1430 in the output layer. The output may be, for example, the historical coherent mapping adjustments provided at step 2202 of fig. 22, and may be the target targeted by the hidden layer of the neural network. The neural network may be via a hidden layer of simple processing elements (node 1420)₁、1420₂、1420₃、1420₄) Execute the treatment ofComplex global behavior determined by the connections between processing elements and element parameters may be exhibited over the network.

At step 2206, the resulting model may be generated such that the new set of patient-specific data received at step 2208 may be applied to the model, and at 2210, a coherent mapping adjustment may be automatically output based on the model. Notably, by using the model, coherent mapping adjustments can be provided without the time and resources expended to measure and calculate such coherent mapping adjustments during the procedure.

The system may also provide local noise identification using a coherent algorithm once the model is created and the coherent mapping adjustments are provided, or as an alternative path in creating the coherent model. As described herein, there are various types of measurements used to construct anatomical heart models. These measurements include, for example, CT, MRI and ultrasound measurements. These measurements may be provided by intracardiac catheters (proximity, impedance, temperature, etc.) and other sources. As described above, a 3D model may be constructed and displayed based on these measurements (tissue and volume) of the heart.

In addition, the surface ECG measurements as well as the measurements from the inserted catheter are input to an existing system that calculates an average signal flow over location and time and displays the flow vectors in coherent mapping/coloring. The system requires approximately 20 minutes of recorded signal as input. Taking into account the duration of the input, it takes about 30-60 seconds to produce the output. Thus, the process does not provide real-time indications to the user.

To provide a more real-time indication to the user, the system may provide some preliminary, approximately coherent mapping to the user based on the partial measurements. For example, these partial measurements may include two minutes of data instead of the traditional 20 minutes of data. Partial measurements may be provided prior to calculating the precise map, or in addition. While partial measurements may not be an accurate mapping for the current patient, partial measurements may save time by giving early feedback and guiding the user to move the catheter to a more relevant area for further measurements.

The system may provide feedback on the accuracy of measurements taken by the catheter at a particular location at a particular point in time.

Measurements taken by the catheter at a particular location at a particular point in time are used, along with previous measurements from the patient, to calculate the LAT for that location, as described above. Providing a score (such as between 0 and 1) on the accuracy of the LAT value, for example, may provide additional benefits in view of various noise sources within the body and from instruments that provide errors in the LAT.

As described herein, each patient's data contains a patient ID and associated patient parameters such as age, gender, some body size, and the like. The data may also include measurements from the instruments (ECG and catheter) over time and position. The output of the system may include the existing coherent mapping described herein.

A neural network may be trained based on the data. The inputs to the NN may include patient parameters, instrument measurements, and specific location points of interest for which LAT values are calculated. The NN may output a score between 0 and 1 indicating the accuracy of the LAT value for the input location point. The output score may provide feedback to a user and may provide measured real-time noise filtering as an input to a coherent mapping system.

On data for a particular past patient, the known coherently mapped LAT values for each particular location point are used as the expected output ("signature") for supervised training of the NN. The error that is minimized is the difference between the output of the NN at the location point and the correct known LAT value. Thus, no manual marking is required. The NN may be provided with measurements of the new patient as well as specific location points of interest and calculated LAT values, and output as a score of 0 to 1 indicating the accuracy of the LAT values. Unlike systems that take 30-60 seconds to produce output, data collected from previous cases can be used to train a NN, which can then produce a map in a much shorter amount of time. The input to the NN is the measurements taken from the patient and the output is the complete coherent mapping.

An indirect way to approximate mapping is to retrieve cases from previous patients that are similar to the current patient and display some aggregation (e.g., average) of their coherent mappings. Each unhealthy heart behaves slightly differently and arrhythmias may be located at different locations within the heart. This change may show the benefit of finding data from previous cases that is most similar to measurements from the current patient. Therefore, it may be important to retrieve similar cases given the partial measurements of the current patient.

This process may be implemented by defining a distance function between representations of cases. The representation of the patient may include measurements of the patient. The distance function may be, for example, a simple distance measure in vector space, such as euclidean distance, cosine similarity, etc., or a more complex function defined by an expert. The distance function can be used to provide the most similar previous cases by using an algorithm such as the k-nearest neighbor method described above.

Alternatively, the neural network may be trained to calculate the distance function. The input to the NN is a pair of two representations, and the output is a score between 0 and 1, indicating the similarity of the two representations. Given N previously represented datasets, a similarity table of size N2 may be prepared, where entry (i, j) contains 0 if the representations i and j are the same, and 1 (or, alternatively, a score between 0 and 1 indicating their similarity) if the representations i and j are different. The similarity table may be populated by an expert indicating which cases are similar, or automatically (or semi-automatically) by calculating a similarity value between the relevant maps associated with the representation.

The shape of each heart is slightly different. Therefore, the 3D position needs to be normalized so that the current measurement position on the grid can be compared with the previous data. A 3D model of a "standard heart" may be created. A projection algorithm may be used to modify the original locations and project the original locations onto standard locations in the 3D model. This is done in a preprocessing stage on the locations measured by the instrument and on the coherently mapped data.

The accuracy of the system may be improved by using a classifier that indicates which type of cardiac abnormality (e.g., fibrillation, VT, micro-orientation, etc.) is associated with the current patient. The classifier can be used in a pre-processing stage in a system. In particular, both prior data and current patient data may be classified to detect relevant categories. Rather than creating only one model to explain all cases, a separate model may be built for each class. Each model may be specific to only one (or a few) specific categories to improve the accuracy of the results.

Alternatively, data from previous patients may contain relevant classifications assigned by physicians. Supervised learning can be used to build classifiers based on this data, where the input is the patient's data and the output is the assigned abnormality category.

Additional data may be accumulated even after the system is ready and deployed in a hospital. Accumulated data may be added to the training data set and the system may be retrained to continually improve the accuracy of the system.

Although features and elements are described above with particularity, those of ordinary skill in the art will recognize that each feature or element can be used alone or in any combination with the other features and elements. Furthermore, 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. Examples of computer readable media include electronic signals (transmitted over a wired or wireless connection) and computer readable storage media. Examples of the computer readable storage medium include, but are not limited to, Read Only Memory (ROM), Random Access Memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM disks and Digital Versatile Disks (DVDs). 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.