P-wave detection using intracardiac electrodes

Abstract

The method includes acquiring intracardiac unipolar and intracardiac bipolar signals at a given region of the patient's heart. The unipolar signals are pruned by removing those unipolar signals that correspond in time to the respective bipolar signals. One or more unipolar signals are identified from among the pruned unipolar signals that are associated with far-field P-waves. Using the identified P-waves, a window of interest (WOI) is established on an electrogram acquired within the atrium of the heart, and the electrogram with the established WOI is used to generate an electrophysiological (EP) map of the atrium indicative of atrial tachycardia (AT) tissue location therein.

Description

[Technical field]

[0001] The present disclosure relates generally to electrophysiological (EP) maps, and more particularly to cardiac EP mapping. [Background technology]

[0002] Methods for detecting specific cardiac activation have been previously proposed in the patent literature. For example, U.S. Patent No. 7,174,210 describes how a relative refractory window is opened within the refractory period of both the atrium and ventricle for the purpose of determining the atrial rate. In this manner, T waves occurring during the relative refractory window are excluded from the atrial rate calculation, but P waves occurring during the relative refractory window are counted, thereby achieving a more accurate atrial rate calculation, especially at high atrial rates.

[0003] As another example, U.S. Patent No. 5,078,133 describes how electrical cardiogenic cardiac depolarizations are detected on a multi-polar single probe with individual electrodes. A bipolar electrode in the atrium allows for detection of intra-atrial activity (P-waves) as a first rate control signal for controlling the pacemaker. A second rate control signal other than the P-waves that correlates with the patient's activity is determined in parallel with the P-wave control signal. The two control signals are compared to determine whether the intra-atrial activity (P-waves) is the appropriate control signal. The pace rate control is switched between the two signals to generate the most beneficial pacing mode for the patient. The control system can respond to unreliability or instability of the intrinsic atrial P-wave signal, e.g., fibrillation, and transition control to another appropriate rate response mode.

[0004] The present disclosure will become more fully understood from the following detailed description of the embodiments thereof, taken in conjunction with the drawings, in which: [Brief description of the drawings]

[0005] The present disclosure will become more fully understood from the following detailed description of the embodiments thereof, taken in conjunction with the drawings, in which: [Figure 1]FIG. 1 is a schematic depiction of a system for electrophysiological (EP) mapping, according to one embodiment of the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram of an EP mapping catheter of the system of FIG. 1 for three configurations (I) P wave, to enable P wave discrimination, (II) for EP mapping the right atrium (RA), and (III) for EP mapping the left atrium (LA), according to one example of the present disclosure. [Diagram 3] 1 is a flow chart that generally illustrates a method for detecting P-waves using intracardiac electrodes and automatically setting a time window of interest (WOI) for an EP map, according to an example of the present disclosure. [Figure 4] 4 is a local activation time (LAT) map of the right atrium (RA) visualizing tissue locations likely to cause AT using the method of FIG. 3 according to an example of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0006] overview Atrial tachycardia (AT) is a cardiac arrhythmia that occurs when cardiac tissue is induced by a cause other than a normally functioning sinoatrial node. One possible method of electrophysiologically (EP) mapping AT using a mapping catheter relies on the physician identifying P waves in an electrocardiogram (ECG) acquired by body surface (BS) electrodes and accurately setting the relevant window of interest (WOI) on the map. Identifying AT arrhythmogenic tissue regions using the EP map allows the physician to ablate atrial tissue to stop AT from occurring.

[0007] However, it is difficult, and sometimes impossible, to localize P waves within the BS signal because, for example, P waves have a low signal-to-noise ratio, high interpatient variability, and may be missing or hidden within the QRS complex or T wave. The difficulty in localizing P waves increases the likelihood of erroneous WOI leading to erroneous EP maps.

[0008] Furthermore, other problems in identifying P waves are common, for example the presence of complex split EP signals preceding the P waves. These signals are considered crucially related to the AT mechanism because they are observed to be located in the "exit zone" from the isthmus of scar tissue that is most likely to cause the tachycardia. It is useful to accurately identify the isthmus (e.g., on an EP map) since the physician can ablate it to stop the tachycardia.

[0009] Examples of the present disclosure described below provide methods and systems for accurately identifying and annotating P-waves during EP mapping. Rather than using BS signals, the disclosed techniques use intracardiac signals. In some embodiments, the intracardiac signals are acquired using the mapping catheter itself, which is first deflected toward the inferior vena cava (IVC) or superior vena cava (SVC) during EP mapping, to acquire far-field P-wave unipolar signals therein, and since these regions usually do not have any local activity, local signals that obscure the P-wave far-field activation can be easily removed.

[0010] In one example, unipolar and bipolar signals are acquired from intracardiac electrodes on the catheter, and a processor analyzes the signals (also called "electrograms" or EGMs) to identify far-field P-waves. Because the IVC and SVC tissues are less active electrophysiologically, acquisition in the IVC or SVC minimizes the presence of inhibitory local activation (detected as a bipolar signal). Alternatively, the catheter can acquire far-field signals and eliminate local signals by being located in the RA or LA blood pool (e.g., rather than in contact with the SVC / IVC tissue).

[0011] To detect the far-field unipolar signal associated with the far-field P-wave, the processor removes the dominant far-field QRS complex signal from the acquired waveform. The remaining unipolar signal is further analyzed by the processor to detect unipolar activation (corresponding to a P-wave), for example, by finding the time when the negative unipolar voltage derivative exceeds a predetermined threshold.

[0012] The remaining bipolar signal is then further analyzed to find bipolar activations. During occurrences where unipolar and bipolar activations correspond in time to one another, i.e., near-field activity is detected, the disclosed method assumes that the activation is not caused by P-waves but by near-field activation. Thus, further analysis of the remaining unipolar signal removes (e.g., prunes) unipolar activations that correspond in time to the respective bipolar activations.

[0013] The remaining unipolar activations are assumed to be P-waves. The processor identifies one or more unipolar signals among the pruned unipolar signals that are associated with far-field P-waves. To this end, further confirmation is typically provided by considering corresponding signals from other electrodes and / or signals from the last N heartbeats and selecting those that are stable over a duration comparable to the cycle length of the tachycardia. The different signals are weighted to estimate P-wave activation with higher consistency. Examples of weights include giving higher weight to signals from electrodes that do not contact cardiac tissue (e.g., in the blood pool). Alternatively, weights can be assigned to the votes according to their timing relative to the QRS peak, with weights increasing in the vicinity of the QRS peak.

[0014] Typically, the processor is programmed with software that contains specific algorithms that enable the processor to perform each of the processor-related steps and functions outlined above.

[0015] System Description FIG. 1 is a schematic depiction of an electrophysiological (EP) mapping system 21, according to one embodiment of the present disclosure.

[0016] 1 shows a physician 27 performing EP mapping of a chamber (e.g., the right atrium (RA) and / or the left atrium (LA)) of a heart 23 of a patient 25 using an EP mapping Pentaray® catheter 29. It should be noted that other catheters may be utilized.

[0017] The catheter 29 includes an electrode array 50 at its distal end that includes one or more arms 20 with a mapping electrode 22 disposed along each arm. During a mapping procedure, the electrodes 22 acquire signals from and / or inject signals into tissue of the heart 23. In particular, the electrodes 22 acquire intracardiac signals, such as atrial electrograms.

[0018] The location of each of the mapping electrodes 22 within the heart 23 (i.e., if an electrogram is measured) is also tracked so that the processor 28 can link each acquired IEGM with the location where the signal was acquired. The system 21 externally senses electrical position signals, such as an electrocardiogram (ECG), and EP data using a number of external electrodes 24 coupled to the body surface of the patient 25. For simplicity, three external electrodes 24 may be coupled to the patient's chest and another three external electrodes may be coupled to the patient's back. For ease of illustration, only one external electrode is shown in FIG. 1.

[0019] One example of a system that can use sensed electrical position signals to track the position of the mapping electrodes 22 within the patient's heart 23 is the CARTO® 3 system (manufactured by Biosense Webster Inc., Irvine, California). The CARTO® 3 system uses a tracking method called Advanced Current Location (ACL), described in detail in U.S. Pat. No. 8,456,182, the disclosure of which is incorporated herein by reference. According to this method, the processor 28 measures the electrical impedance between at least a portion of the mapping electrodes 22 and each of the external electrodes 24 and uses these impedances to find the location coordinates of the mapping electrodes. Alternatively or additionally, the system 21 can apply other location sensing methods known in the art, such as magnetic position sensing, in finding these location coordinates.

[0020] The intracardiac signals captured by the mapping electrodes 22 are transmitted via wire links (not shown) extending through the catheter 29 to a data acquisition module 33 via an electrical interface 35. By establishing spatiotemporal correlations between electrograms using the sensed locations, the processor 28 of the system 21 generates an EP map, such as a LAT map. The processor stores the EP map in memory 31. In parallel, the processor 28 can present electrogram traces 40 on the display 26 of the system 20.

[0021] In particular, inset 45 shows an electrogram trace 40 characteristic of AT in which the P-wave is inverted.

[0022] During and / or following the treatment, processor 28 may display the EP map on display 26, which may be a touch screen that allows physician 27 to mark clinical inputs on the EP map or electrogram traces 40 (such as activated pathways and / or scar regions), as well as to command detection of P-waves and set windows of interest (WOIs) for the EP map based on P-wave occurrence, as described below. Alternatively or additionally, physician 27 may mark clinical inputs using any other suitable input device, for example in the form of a mouse or trackball.

[0023] The exemplary illustration shown in FIG. 1 is chosen solely for conceptual clarity. Other types of multi-electrode sensing geometries, such as the Lasso® catheter (Biosense Webster), may also be used. Additionally, contact sensors may be attached to the distal end of the catheter 29 to transmit data indicative of the physical quality of electrode contact with the tissue. In one example, measurements of some electrodes 22 may be discarded due to poor quality of their physical contact, while measurements of other electrodes may be considered valid due to good quality of their contact.

[0024] Although examples of the present disclosure are described above with particular reference to elements of system 21 for purposes of specificity and clarity, the principles of the present disclosure may be applied to other EP mapping systems having suitable sensing capabilities as well, and all such alternatives are considered to be within the scope of the present disclosure.

[0025] Processor 28 typically comprises a general-purpose computer that is programmed with software to perform the functions described herein. The software may be downloaded to the computer in electronic form, for example over a network, or alternatively or additionally may be provided and / or stored on a non-transitory tangible medium, such as magnetic, optical, or electronic memory. In particular, processor 28 executes dedicated algorithms that enable processor 28 to perform each of the steps described in FIG.

[0026] P-wave detection using intracardiac electrodes FIG. 2 is a schematic diagram of an EP mapping catheter of the system of FIG. 1 in three locations within the heart 23: (I) to enable identification of P waves, (II) for EP mapping the right atrium (RA), and (III) for EP mapping the left atrium (LA), in accordance with an example of the present disclosure.

[0027] In configuration I, the catheter's electrode array 50 is seen in contact with the SVC tissue to acquire far-field P-wave signals therein. This initial step may last for a few seconds, after which the physician moves the catheter to perform EP mapping of one or two of the atria. Configuration II in FIG. 2 represents an EP mapping session of the RA, and configuration III represents an EP mapping session of the LA.

[0028] The processor analyzes the acquisition in the SVC (or in the IVC, not shown) to set the correct WOI for the electrograms used to generate the EP map so that the abnormal tissue in which AT occurs is visible on the EP map.

[0029] The diagram in FIG. 2 is provided as an example. In practice, other catheters can be used to acquire P waves. The catheter can acquire far-field signals by being located in the blood pool of the RA or LA, rather than in contact with the SVC / IVC tissue.

[0030] 3 is a flow chart that illustrates a schematic of a method for detecting P-waves using intracardiac electrodes and automatically setting a time window of interest (WOI) for an EP map, according to an example of the present disclosure. According to the example presented, the algorithm executes a process that begins with the physician 27 acquiring unipolar and bipolar signals, for example from the SVC or IVC tissue, using the electrode array 50, in a signal acquisition step 302. Although the SVC or IVC tissue is not particularly EP active, some interfering local bipolar signals may still be present.

[0031] Next, in a remove QRS complex step 304, processor 28 removes the dominant QRS complexes from the unipolar and bipolar signals.

[0032] In a next activation detection step 306, the processor 28 analyzes the remaining unipolar signal to detect unipolar activation (corresponding to P-waves), for example, by finding the time point when the negative voltage derivative exceeds a predefined threshold. The threshold can be either a constant or a dynamic number. Calculating the absolute value of the amplitude requires high-pass filtering, for example by subtracting the signal after a median filter or an FIR or IIR filter from the signal itself. Calculating the negative derivative requires a low-pass filter, such as a Gaussian filter, which does not introduce ripple. The remaining bipolar signal is analyzed in a similar manner to find intruding bipolar activation. Activation in the bipolar electrogram can be defined as the time point when the absolute value of the negative derivative and / or the amplitude exceeds a certain threshold.

[0033] Processor 28 then removes unipolar signals that correspond to (e.g., coincide with) the bipolar signals in an extraneous unipolar signal removal step 308. Activation that appears in a bipolar electrogram is likely to be near-field activation rather than P-waves.

[0034] In the P-wave consistency test step 310, the processor 28 considers all activations that appear on the unipolar signal and do not appear on the bipolar signal as votes, and the processor can calculate a majority vote to detect a P-wave with a high probability. Additionally, the last N heartbeats can contribute to the vote. The consistency of the votes can be weighted according to the atrial reference cycle length. Certain unipolar deflections are ranked higher if they are consistent with their temporal distance from the atrial reference signal. All votes can be either 0 or 1, or the votes can be real numbers between 0 and 1. For example, the unipolar activation level can contribute to the vote as a positive component to move it closer to 1, and the strength of the bipolar activation can contribute to the vote as a negative component to move it closer to 0. The majority vote can then be calculated as the sum of the votes.

[0035] Voting may be performed between each of the intracardiac electrodes, including when the electrodes are in the blood pool. In the presence of a "tissue proximity detection" algorithm or a "force measurement" mechanism, electrodes that are not in contact with RA or LA cardiac tissue (i.e., in the blood pool) may have a higher weight in the majority voting algorithm.

[0036] Alternatively, votes can be assigned weights according to their timing relative to the QRS peak.

[0037] Alternatively, P-waves may be manually tagged on multiple occasions during development. The intracardiac unipolar and bipolar signals and the manually tagged P-wave timings may be fed into a supervised machine learning algorithm. Using such training, the algorithm learns to detect segments with strong and sufficient unipolar activation without strong and sufficient bipolar activation. The output of the machine learning algorithm is the P-wave timing.

[0038] Finally, in an automatic WOI setting step 312, processor 28 uses the detected (e.g., annotated) P-wave occurrences to accurately set the WOI for an EP map, such as a local activation time (LAT) map, to visualize tissue locations where AT occurs so that a physician can ablate such tissue locations to remove the AT.

[0039] The above process can be automatic or semi-automatic. For example, to perform steps 302 et seq., a physician can click a button on a user interface to instruct the system to attempt to detect P-waves. The system's processor responds with a progress indicator on the display 26 while it processes the signal for a few seconds (e.g., up to 10). Once the calculations are complete, the processor will light a P-wave indicator on a display, such as an annotation viewer, and the signal will continue to update in real time.

[0040] The flow chart of Figure 3 is an example. Additional or alternative algorithm steps may be included, such as for removal of interfering far-field signals and noise.

[0041] 4 is a right atrium (RA) local activation time (LAT) map 400 visualizing tissue locations 402 likely causing AT using the method of FIG. 3 according to an example of the present disclosure. The LAT map 400 has an asymmetric time scale of [-255, 65] mSec, which is a result of a selected WOI based on detected P-waves. Using the LAT map 400, a physician can identify atrial tissue locations 402 causing AT. The physician can then ablate the tissue locations 402 to prevent AT from occurring. EXAMPLES

[0042] The method includes acquiring intracardiac unipolar and intracardiac bipolar signals in a given region of a heart (23) of a patient (25). The unipolar signals are pruned by removing those unipolar signals that correspond in time to the respective bipolar signals. One or more unipolar signals are identified from among the pruned unipolar signals that are associated with far-field P-waves. Using the identified P-waves, a window of interest (WOI) is placed on an electrogram (40) acquired in an atrium of the heart (23), and an atrial electrophysiological (EP) map (400) is generated that indicates atrial tachycardia (AT) tissue location therein using the electrogram with the established WOI. EXAMPLES

[0043] The method of example 1, wherein the given region is one of the superior vena cava (SVC) and the inferior vena cava (IVC). EXAMPLES

[0044] The method of example 1, wherein the given region is the atrial blood pool. EXAMPLES

[0045] 4. The method of any one of claims 1 to 3, wherein identifying the unipolar signal associated with a far-field P-wave comprises weighting the unipolar signal based on at least one of: (i) the number of electrodes (22) used to acquire the unipolar signal; (ii) the number of cardiac cycles during which the unipolar signal was acquired; and (iii) the timing of occurrence of the unipolar signal relative to the QRS complex. EXAMPLES

[0046] The method according to any of the preceding claims, wherein setting the WOI comprises adding a P-wave annotation onto the electrogram (40) and using the annotation as a time reference for the WOI. EXAMPLES

[0047] The method according to any of the preceding claims, wherein the acquisition of the unipolar and bipolar signals is performed using a catheter (29) equipped with an electrode (22). EXAMPLES

[0048] The method according to any one of Examples 1 to 6, wherein the EP map is a local activation time (LAT) map (400). EXAMPLES

[0049] The method includes acquiring intracardiac unipolar and intracardiac bipolar signals at a given region of a heart (23) of a patient (25). A supervised machine learning algorithm is trained to identify P-waves in the acquired unipolar signals by manually tagging the unipolar signals indicative of P-waves due to low amplitude in the respective bipolar signals. Using the trained machine learning algorithm, one or more unipolar signals are identified from among the newly acquired unipolar and bipolar signals that are associated with far-field P-waves. The identified P-waves are used to establish a window of interest (WOI) on an electrogram (40) acquired in an atrium of the heart (23), and the electrogram (40) with the established WOI is used to generate an atrial electrophysiological (EP) map (400) indicative of atrial tachycardia (AT) tissue location therein. EXAMPLES

[0050] The system includes a memory (31) and a processor (28). The memory (31) is configured to store intracardiac unipolar and bipolar signals acquired in a given region of the heart (23) of the patient (25). The processor (28) is configured to (i) prune the unipolar signals by removing those unipolar signals that correspond in time to respective bipolar signals, (ii) identify, from among the pruned unipolar signals, one or more unipolar signals associated with far-field P-waves, (iii) use the identified P-waves to define a window of interest (WOI) on an electrogram (40) acquired in an atrium of the heart (23), and generate an atrial electrophysiological (EP) map (400) indicative of atrial tachycardia (AT) tissue locations therein using the electrogram (40) with the defined WOI.

[0051] It will be understood that the above described embodiments are given by way of example, and the present disclosure is not limited to what is particularly shown and described herein above. Rather, the scope of the present disclosure includes both combinations and subcombinations of the various features described above, as well as variations and modifications thereof that would occur to a person skilled in the art upon reading the foregoing description and that are not disclosed in the prior art. Documents incorporated into this patent application by reference shall be considered as an integral part of this application, provided that, to the extent that any term is defined in these incorporated documents in a manner that is inconsistent with the definition expressly or implicitly made herein, only the definition in this specification shall be considered.

[0052] [Embodiment] (1) A method for identifying and annotating P waves during EP mapping, comprising: acquiring intracardiac unipolar and intracardiac bipolar signals in a given region of a patient's heart; pruning the unipolar signals by removing ones of the unipolar signals that correspond in time to respective bipolar signals; identifying, from among the pruned unipolar signals, one or more unipolar signals associated with far-field P-waves; using the identified P-waves to define a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and using the electrogram having the defined WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein; A method comprising: (2) The method of embodiment 1, wherein the given region is one of the superior vena cava (SVC) and the inferior vena cava (IVC). (3) The method of embodiment 1, wherein the given region is the blood pool of the atrium. (4) The method of embodiment 1, wherein identifying the unipolar signal associated with the far-field P-wave comprises weighting the unipolar signal based on at least one of: (i) a number of electrodes used to acquire the unipolar signal; (ii) a number of cardiac cycles during which the unipolar signal was acquired; and (iii) a timing of occurrence of the unipolar signal relative to a QRS complex. (5) The method of embodiment 1, wherein setting the WOI includes adding an annotation of the P wave on the electrogram and using the annotation as a time reference for the WOI.

[0053] (6) The method of embodiment 1, wherein acquiring the unipolar signal and the bipolar signal is performed using a catheter having electrodes attached thereto. (7) The method of embodiment 1, wherein the EP map is a local activation time (LAT) map. (8) A method for identifying and annotating P waves during EP mapping, comprising: acquiring intracardiac unipolar and intracardiac bipolar signals in a given region of a patient's heart; training a supervised machine learning algorithm to identify P-waves in the acquired unipolar signals by manually tagging the unipolar signals indicative of P-waves due to low amplitudes in respective bipolar signals; using the trained machine learning algorithm to identify one or more unipolar signals associated with far-field P-waves from among the newly acquired unipolar and bipolar signals; using the identified P-waves to define a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and using the electrogram having the defined WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein; A method comprising: (9) A system for identifying and annotating P waves during EP mapping, comprising: a memory configured to store intracardiac unipolar and bipolar signals acquired at a given region of the patient's heart; a processor, the processor comprising: pruning the unipolar signal by removing those of the unipolar signal that correspond in time to each bipolar signal; identifying, from among the pruned unipolar signals, one or more unipolar signals associated with far-field P-waves; The system is configured to use the identified P-waves to set a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and to use the electrogram having the set WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein. (10) The system of embodiment 9, wherein the given region is one of the superior vena cava (SVC) and the inferior vena cava (IVC).

[0054] (11) The system of embodiment 9, wherein the given region is the blood pool of the atrium. (12) The system of embodiment 9, wherein the processor is configured to identify the unipolar signal associated with the far-field P wave by weighting the unipolar signal based on at least one of: (i) a number of electrodes used to acquire the unipolar signal, (ii) a number of cardiac cycles during which the unipolar signal was acquired, and (iii) a timing of occurrence of the unipolar signal relative to a QRS complex. (13) The system of embodiment 9, wherein the processor is configured to set the WOI by adding an annotation of the P wave on the electrogram and using the annotation as a time reference for the WOI. (14) The system of embodiment 9, wherein the unipolar signal and the bipolar signal are acquired using a catheter having electrodes attached thereto. (15) The system described in embodiment 9, wherein the EP map is a local activation time (LAT) map.

[0055] (16) A system for identifying and annotating P waves during EP mapping, comprising: a memory configured to store intracardiac unipolar and bipolar signals acquired at a given region of the patient's heart; a processor, the processor comprising: training a supervised machine learning algorithm to identify P-waves in the acquired unipolar signals by manually tagging the unipolar signals indicative of P-waves due to low amplitudes in respective bipolar signals; using the trained machine learning algorithm to identify, from among the newly acquired unipolar and bipolar signals, one or more unipolar signals associated with far-field P-waves; The system is configured to use the identified P-waves to set a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and to use the electrogram having the set WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein.

Claims

1. 1. A system for identifying and annotating P-waves during EP mapping, comprising: a memory configured to store intracardiac unipolar and bipolar signals acquired at a given region of the patient's heart; a processor, the processor comprising: pruning the unipolar signal by removing those of the unipolar signal that correspond in time to each bipolar signal; identifying, from among the pruned unipolar signals, one or more unipolar signals associated with far-field P-waves; The system is configured to use the identified P-waves to set a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and to use the electrogram having the set WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein.

2. The system of claim 1 , wherein the given region is one of a superior vena cava (SVC) and an inferior vena cava (IVC).

3. The system of claim 1 , wherein the given region is the atrial blood pool.

4. 2. The system of claim 1, wherein the processor is configured to identify the unipolar signal associated with the far-field P-wave by weighting the unipolar signal based on at least one of: (i) a number of electrodes used to acquire the unipolar signal, (ii) a number of cardiac cycles during which the unipolar signal was acquired, and (iii) a timing of occurrence of the unipolar signal relative to a QRS complex.

5. The system of claim 1 , wherein the processor is configured to set the WOI by adding an annotation of the P-wave onto the electrogram and using the annotation as a time reference for the WOI.

6. The system of claim 1 , wherein the unipolar and bipolar signals are acquired using a catheter having electrodes attached thereto.

7. The system of claim 1 , wherein the EP map is a local activation time (LAT) map.

8. 1. A system for identifying and annotating P-waves during EP mapping, comprising: a memory configured to store intracardiac unipolar and bipolar signals acquired at a given region of the patient's heart; a processor, the processor comprising: training a supervised machine learning algorithm to identify P-waves in the acquired unipolar signals by manually tagging the unipolar signals indicative of P-waves due to low amplitudes in respective bipolar signals; using the trained machine learning algorithm to identify, from among the newly acquired unipolar and bipolar signals, one or more unipolar signals associated with far-field P-waves; The system is configured to use the identified P-waves to set a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and to use the electrogram having the set WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein.

9. 1. A method for identifying and annotating P-waves during EP mapping, comprising: acquiring intracardiac unipolar and intracardiac bipolar signals in a given region of a patient's heart; pruning the unipolar signals by removing ones of the unipolar signals that correspond in time to respective bipolar signals; identifying, from among the pruned unipolar signals, one or more unipolar signals associated with far-field P-waves; using the identified P-waves to define a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and using the electrogram having the defined WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein; A method comprising:

10. 10. The method of claim 9, wherein the given region is one of the superior vena cava (SVC) and the inferior vena cava (IVC).

11. The method of claim 9 , wherein the given region is the atrial blood pool.

12. 10. The method of claim 9, wherein identifying the unipolar signal associated with the far-field P-wave comprises weighting the unipolar signal based on at least one of: (i) a number of electrodes used to acquire the unipolar signal, (ii) a number of cardiac cycles during which the unipolar signal was acquired, and (iii) a timing of occurrence of the unipolar signal relative to a QRS complex.

13. 10. The method of claim 9, wherein setting the WOI comprises adding an annotation of the P-wave onto the electrogram and using the annotation as a time reference for the WOI.

14. The method of claim 9 , wherein acquiring the unipolar and bipolar signals is performed using a catheter having electrodes attached thereto.

15. The method of claim 9 , wherein the EP map is a local activation time (LAT) map.

16. 1. A method for identifying and annotating P-waves during EP mapping, comprising: acquiring intracardiac unipolar and intracardiac bipolar signals in a given region of a patient's heart; training a supervised machine learning algorithm to identify P-waves in the acquired unipolar signals by manually tagging the unipolar signals indicative of P-waves due to low amplitudes in respective bipolar signals; using the trained machine learning algorithm to identify, from among the newly acquired unipolar and bipolar signals, one or more unipolar signals associated with far-field P-waves; using the identified P-waves to define a window of interest (WOI) on an electrogram acquired within an atrium of the heart, and using the electrogram having the defined WOI to generate an electrophysiological (EP) map of the atrium indicating atrial tachycardia (AT) tissue location therein; A method comprising:

Images