EP4651937A1

EP4651937A1 - Systems for capturing neural responses

Info

Publication number: EP4651937A1
Application number: EP24706189.8A
Authority: EP
Inventors: Aleksandra Pavlovna KHARAM; Robert A. Corey
Original assignee: Medtronic Inc
Current assignee: Medtronic Inc
Priority date: 2023-01-20
Filing date: 2024-01-12
Publication date: 2025-11-26
Also published as: WO2024154028A1

Abstract

Systems and methods for capturing early neural responses are provided. An input waveform that includes a stimulation portion and a neural response portion may be captured. A stimulation artifact template may be applied to the input waveform to create a modified input waveform. The modified input waveform may be analyzed to retrieve information about the neural response portion of the input waveform and the information may include a first response peak created as a response to the stimulation portion.

Description

SYSTEMS AND METHODS FOR CAPTURING NEURAL RESPONSES

[0001] This Application claims priority from U.S. Provisional Patent Application 63/440,252, filed 20 January 2023, the entire content of which is incorporated herein by reference.

BACKGROUND

[0002] The present disclosure is generally directed to capturing neural responses, and relates more particularly to capturing early neural responses.

[0003] Closed-loop therapeutic neuromodulation may be carried out by sending an electrical signal generated by a pulse generator to a stimulation target (e.g., nerves, non-neuronal cells, etc.), which may provide a stimulating or blocking therapy to the stimulation target. In such closed-loop neuromodulation therapies, one or more signals resulting from the stimulating or blocking therapy may be recorded and the therapy may be adjusted based on the recorded signals.

BRIEF SUMMARY

[0004] Example aspects of the present disclosure include:

[0005] A method according to at least one embodiment of the present disclosure comprises capturing an input waveform that includes a stimulation portion and a neural response portion; applying a stimulation artifact template to the input waveform to create a modified input waveform; and analyzing the modified input waveform in a digital domain to retrieve information about the neural response portion of the input waveform, wherein the information about the neural response portion includes a first response peak created as a response to the stimulation portion.

[0006] Any aspect herein, further comprising: stimulating, using a pulse generator, an anatomical element with one or more electrical pulses, wherein the one or more electrical pulses contribute to the stimulation portion.

[0007] Any aspect herein, wherein the neural response portion comprises a response of the anatomical element to the one or more electrical pulses and wherein the first response peak in the neural response portion coincides with the one or more electrical pulses.

[0008] Any aspect herein, wherein the stimulation artifact template comprises a predicted version of the stimulation portion.

[0009] Any aspect herein, wherein the stimulation artifact template comprises a post stimulation artifact.

[0010] Any aspect herein, wherein the stimulation artifact template comprises a stimulus artifact obtained from the stimulation portion. [0011] Any aspect herein, wherein the stimulation artifact template comprises a combination of a post stimulation artifact and a stimulus artifact obtained from the stimulation portion.

[0012] Any aspect herein, wherein the stimulation artifact template is generated from a machine learning model based on the machine learning model processing the input waveform.

[0013] Any aspect herein, wherein the stimulation artifact template is generated using an accumulator.

[0014] Any aspect herein, wherein applying the stimulation artifact template to the input waveform comprises subtracting the stimulation artifact template from the input waveform. [0015] Any aspect herein, further comprising: passing the modified input waveform through an analog-to-digital converter prior to analyzing the modified input waveform in the digital domain. [0016] Any aspect herein, further comprising: amplifying the modified input waveform prior to passing the modified input waveform through the analog-to-digital converter; and filtering the modified input waveform prior to passing the modified input waveform through the analog-to-digital converter.

[0017] Any aspect herein, further comprising: passing a digital version of the stimulation artifact template through a digital-to-analog converter to obtain an analog version of the stimulation artifact template, wherein the analog version of the stimulation artifact template is applied to the input waveform.

[0018] A system according to at least one embodiment of the present disclosure comprises an input to receive an input waveform that includes a stimulation portion and a neural response portion; a summer circuit that applies a stimulation artifact template to the input waveform to create a modified input waveform; and a waveform analytics engine that analyzes the modified input waveform to retrieve information about the neural response portion of the input waveform, wherein the information about the neural response portion includes a first response peak created as a response to the stimulation portion.

[0019] Any aspect herein, further comprising: an analog-to-digital converter positioned between the summer circuit and the waveform analytics engine.

[0020] Any aspect herein, further comprising: one or more leads positioned near an anatomical element, wherein the one or more leads deliver a stimulation pulse to the anatomical element and capture the neural response to the stimulation pulse.

[0021] Any aspect herein, wherein the anatomical element comprises a nerve.

[0022] Any aspect herein, wherein the input waveform comprises an Evoked Compound Action Potential (eCAP) signal. [0023] Any aspect herein, wherein the neural response portion comprises a response of the anatomical element to the stimulation pulse, wherein a first response peak in the neural response portion coincides with the stimulation pulse, and wherein the stimulation artifact template comprises a predicted version of the stimulation portion.

[0024] A circuit according to at least one embodiment of the present disclosure comprises an input to receive an input waveform that includes a stimulation portion and a neural response portion; a summation node that applies a stimulation artifact template to the input waveform to create a modified input waveform; and an analog-to-digital converter that transforms the modified input waveform from an analog version thereof to a digital version thereof.

[0025] Any aspect in combination with any one or more other aspects.

[0026] Any one or more of the features disclosed herein.

[0027] Any one or more of the features as substantially disclosed herein.

[0028] Any one or more of the features as substantially disclosed herein in combination with any one or more other features as substantially disclosed herein.

[0029] Any one of the aspects/features/embodiments in combination with any one or more other aspects/ features/ embodiments .

[0030] Use of any one or more of the aspects or features as disclosed herein.

[0031] It is to be appreciated that any feature described herein can be claimed in combination with any other feature(s) as described herein, regardless of whether the features come from the same described embodiment.

[0032] The details of one or more aspects of the disclosure are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the techniques described in this disclosure will be apparent from the description and drawings, and from the claims. [0033] The phrases “at least one”, “one or more”, and “and/or” are open-ended expressions that are both conjunctive and disjunctive in operation. For example, each of the expressions “at least one of A, B and C”, “at least one of A, B, or C”, “one or more of A, B, and C”, “one or more of A, B, or C” and “A, B, and/or C” means A alone, B alone, C alone, A and B together, A and C together, B and C together, or A, B and C together. When each one of A, B, and C in the above expressions refers to an element, such as X, Y, and Z, or class of elements, such as XI -Xn, Yl-Ym, and Zl-Zo, the phrase is intended to refer to a single element selected from X, Y, and Z, a combination of elements selected from the same class (e.g., XI and X2) as well as a combination of elements selected from two or more classes (e.g., Y1 and Zo). [0034] The term “a” or “an” entity refers to one or more of that entity. As such, the terms “a” (or “an”), “one or more” and “at least one” can be used interchangeably herein. It is also to be noted that the terms “comprising”, “including”, and “having” can be used interchangeably.

[0035] The preceding is a simplified summary of the disclosure to provide an understanding of some aspects of the disclosure. This summary is neither an extensive nor exhaustive overview of the disclosure and its various aspects, embodiments, and configurations. It is intended neither to identify key or critical elements of the disclosure nor to delineate the scope of the disclosure but to present selected concepts of the disclosure in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other aspects, embodiments, and configurations of the disclosure are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.

[0036] Numerous additional features and advantages of the present disclosure will become apparent to those skilled in the art upon consideration of the embodiment descriptions provided hereinbelow.

BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are incorporated into and form a part of the specification to illustrate several examples of the present disclosure. These drawings, together with the description, explain the principles of the disclosure. The drawings simply illustrate preferred and alternative examples of how the disclosure can be made and used and are not to be construed as limiting the disclosure to only the illustrated and described examples. Further features and advantages will become apparent from the following, more detailed, description of the various aspects, embodiments, and configurations of the disclosure, as illustrated by the drawings referenced below. [0038] Fig. 1 is a diagram of a system according to at least one embodiment of the present disclosure;

[0039] Fig. 2 is a diagram of a pulse generator with leads connected to nerves according to at least one embodiment of the present disclosure;

[0040] Fig. 3 A is a diagram of a stimulation waveform and a neural response according to at least one embodiment of the present disclosure;

[0041] Fig. 3B is a diagram of a system according to at least one embodiment of the present disclosure;

[0042] Fig. 3C is an example circuit according to at least one embodiment of the present disclosure; [0043] Fig. 4 is a flowchart according to at least one embodiment of the present disclosure;

[0044] Fig. 5 is a flowchart according to at least one embodiment of the present disclosure;

[0045] Fig. 6 is a diagram of a system according to at least one embodiment of the present disclosure; and

[0046] Fig. 7 is a flowchart according to at least one embodiment of the present disclosure.

DETAILED DESCRIPTION

[0047] It should be understood that various aspects disclosed herein may be combined in different combinations than the combinations specifically presented in the description and accompanying drawings. It should also be understood that, depending on the example or embodiment, certain acts or events of any of the processes or methods described herein may be performed in a different sequence, and/or may be added, merged, or left out altogether (e.g., all described acts or events may not be necessary to carry out the disclosed techniques according to different embodiments of the present disclosure). In addition, while certain aspects of this disclosure are described as being performed by a single module or unit for purposes of clarity, it should be understood that the techniques of this disclosure may be performed by a combination of units or modules associated with, for example, a computing device and/or a medical device.

[0048] In one or more examples, the described methods, processes, and techniques may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a computer-readable medium and executed by a hardware-based processing unit. Alternatively or additionally, functions may be implemented using machine learning models, neural networks, artificial neural networks, or combinations thereof (alone or in combination with instructions). Computer- readable media may include non-transitory computer-readable media, which corresponds to a tangible medium such as data storage media (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer).

[0049] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors (e.g., Intel Core i3, i5, i7, or i9 processors; Intel Celeron processors; Intel Xeon processors; Intel Pentium processors; AMD Ryzen processors; AMD Athlon processors; AMD Phenom processors; Apple A10 or 10X Fusion processors; Apple Al l, A12, A12X, A12Z, or Al 3 Bionic processors; or any other general purpose microprocessors), graphics processing units (e.g., Nvidia GeForce RTX 2000-series processors, Nvidia GeForce RTX 3000-series processors, AMD Radeon RX 5000-series processors, AMD Radeon RX 6000-series processors, or any other graphics processing units), application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Accordingly, the term “processor” as used herein may refer to any of the foregoing structure or any other physical structure suitable for implementation of the described techniques. Also, the techniques could be fully implemented in one or more circuits or logic elements.

[0050] Before any embodiments of the disclosure are explained in detail, it is to be understood that the disclosure is not limited in its application to the details of construction and the arrangement of components set forth in the following description or illustrated in the drawings. The disclosure is capable of other embodiments and of being practiced or of being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of “including,” “comprising,” or “having” and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. Further, the present disclosure may use examples to illustrate one or more aspects thereof. Unless explicitly stated otherwise, the use or listing of one or more examples (which may be denoted by “for example,” “by way of example,” “e.g.,” “such as,” or similar language) is not intended to and does not limit the scope of the present disclosure.

[0051] The terms proximal and distal are used in this disclosure with their conventional medical meanings, proximal being closer to the operator or user of the system, and further from the region of surgical interest in or on the patient, and distal being closer to the region of surgical interest in or on the patient, and further from the operator or user of the system.

[0052] During therapeutic neuromodulation, early neural responses may occur simultaneously or near a stimulation pulse based on a variety of factors such as, for example, stimulation parameters, a location of a sense electrode, and/or a position and/or type of a neural target. The stimulation pulse may result in early neural responses being obscured out due to artifacts that arise during and/or after the stimulation superimposed on top of the early neural responses. For example, electrically Evoked Compound Action Potential (eCAP) responses occur within a stimulation recharge when electrodes for stimulation and electrodes or sensors for sensing neural response are closely spaced to each other. In such configurations, the early eCAP responses may happen concurrently with a stimulation artifact and are thus difficult to sense. More specifically, the eCAP responses may be challenging to sense during stimulation as the sensing may require a large dynamic range of a sensing channel. Thus, an earlier eCAP response (e.g., a “Pl” response) cannot be sensed due to the stimulus artifact. [0053] It is desirable to be able to sense the earlier portion of the eCAP response (or any neural response) to provide more flexibility in leads and/or electrode configurations. For example, electrodes positioned laterally on the spinal cord will activate larger fiber nerves with faster conduction velocities. Such faster conduction velocities will cause the eCAP response to pass by one or more recording electrodes at a fixed distance from the stimulation electrodes in a shorter amount of time. Because stimulation artifact time constants are invariant to the lead in a lateral direction, a faster eCAP conduction velocity will cause the eCAP to overlay onto a larger stimulation artifact, thereby making eCAP detection and amplitude estimation more difficultln another example, peripheral applications such as, for example, peripheral nerve stimulation are constrained by limited electrode options wherein the electrodes may be positioned near each other. Further, other leads have configurations in which the electrodes are spaced closely together. Additionally, some physiological signals may be of interest and they can potentially modulate a stimulation signal (e.g., respiration) and it may be desirable to be able to sense responses during a stimulation pulse.

[0054] At least one embodiment of the present disclosure provides for systems and methods for enabling the capture of early neural responses using estimative stimulation artifact template(s) such that the early neural responses can be captured with, for example, electrodes that are positioned close to each other. The template(s) may be a direct measurement of an artifact or may be obtained using, for example, impedance information and/or current information. The stimulation artifact template may be used to remove the artifact from input sense signals via a front-end feedback in a way that maximizes a dynamic range of sense signal and accuracy of the physiological signal of interest. [0055] Thus, embodiments of the present disclosure provide technical solutions to one or more of the problems of (1) measuring early neural responses regardless of electrode spacing, (2) removing artifact(s) resulting from a stimulation from input waveforms, and (3) improving therapeutic neuromodulation.

[0056] Turning to Figs. 1-2, diagrams of aspects of a system 100 according to at least one embodiment of the present disclosure are shown. The system 100 may be used to provide therapeutic neuromodulation in the form of electric signals to a patient and/or carry out one or more other aspects of one or more of the methods disclosed herein. For example, the system 100 may include at least a device 102 that is capable of providing a stimulation applied to an anatomical element such as, for example, the spinal cord 108 of the patient and/or to one or more nerve endings for a patient. In some examples, the device 102 may be referred to as a pulse generator, an implantable neural stimulator, an internal neural stimulator, or the like, which may be implantable in some embodiments. In other embodiments, the device 102 may not be implanted in the patient and may be, for example, external to the patient. The device 102 may be configured to generate a current or electrical signal, such as a signal capable of stimulating one or more neural responses such as, for example, eCAP responses in the spinal cord 108 or from one or more nerves. Additionally, the system 100 may include one or more leads 104 (e.g., electrical leads) that provide a connection between the device 102 and the spinal cord or nerves of the patient for enabling, for example, stimulation. In some embodiments, the leads 104 may be implanted wholly or partially within the patient.

[0057] Neurostimulation techniques (e.g., technologies that act directly upon nerves of a patient, such as the alteration, or “modulation,” of nerve activity by delivering electrical impulses directly to a target area) may be used for assisting in treatments for different diseases, disorders, or ailments (e.g., chronic pain) of a patient. As discussed herein, neuromodulation techniques may be used to block, modulate, or alter pain signals (or, more generally, other signals) sent to a patient’s brain to relieve or modulate chronic pain. Additionally or alternatively, neuromodulation techniques may be used to stimulate or prevent other neurological signals from traveling to or from the patient’s brain for the purposes of assisting with patient treatment. In some embodiments, the device 102 may provide electrical stimulation of the spinal cord 108 of the patient (or one or more nerves therein) to alter or block signals from reaching the patient’s brain.

[0058] In some embodiments, the one or more leads 104 may include a first lead 104A disposed on or connected to a first side of the spinal cord 108 of the patient and a second lead 104B disposed on or connected to a second side of the spinal cord 108 of the patient. For example, the first lead 104A may be connected to the righthand side of the spinal cord 108, while the second lead 104B may be connected to the lefthand side of the spinal cord 108. However, the position and/or orientation of each lead relative to the spinal cord 108 may vary depending on, for example, the type of treatment, the type of lead, combinations thereof, and the like.

[0059] In some examples, the leads 104 may provide the electrical signals to the spinal cord or nerve via electrodes or electrode devices that extend from the leads 104 and connect to the spinal cord or nerve (e.g., sutured in place, wrapped around the nerves, etc.). In some examples, the leads 104 may be referenced as cuff electrodes or may otherwise include cuff electrodes (e.g., at an end of the leads 104 not connected or plugged into the device 102).

[0060] In other examples, the leads 104 may be or comprise linear spinal cord stimulation (SCS) leads capable of delivering one or more stimulation signals to the spinal cord 108, as discussed in further detail below. The leads 104 may comprise a plurality of electrodes disposed along the length of the lead 104, such that the leads 104 contact the spinal cord 108 at multiple points along a length of the spinal cord 108. A first set of the electrodes on each lead 104 may pass an electrical signal into the spinal cord 108, while a second set of the electrodes on each lead 104 may sense one or more signals generated in response by the spinal cord 108. In one embodiment, the electrodes may be able to sense, measure, or otherwise collect data related to neural responses (e.g., eCAP responses).

[0061] Fig. 2 depicts at least one embodiment of the device 102 and the leads 104 connected to the spinal cord 108 of the patient. The leads 104 include one or more electrodes 208, 210 that receive a current or other stimulant instructions from the device 102 (e.g., via the leads 104). In some examples, the electrodes 208, 210 may each include a body and a plurality of electrodes 208A-208D, 210A-210D that are disposed on respective first and second sides 204A, 204B of the spinal cord 108, where the plurality of electrodes 208A-208D, 210A-210D are configured to apply the current generated by the device 102 to the spinal cord 108. As shown, a first electrode 208 may be configured for placement on the spinal cord 108 to apply a current to the spinal cord 108 (e.g., carried via a second lead 104B and emitted from one or more of the electrodes 208A-208D), and a second electrode 210 may also be configured for placement on the spinal cord 108 to apply a current to the spinal cord (e.g., carried via a first lead 104 A and emitted from one or more of the electrodes 210A-210D). In some examples, the electrodes 208, 210 may be referred to as cuff electrodes.

[0062] The application of current to the spinal cord 108 may stimulate a neural response such as an eCAP response in the spinal cord or nerve of the patient, and data or information associated with the eCAP response may be captured using, for example, one or more sensors 620 (shown in Fig. 6) or the one or more of the electrodes 208A-208D, 210A-210D. In some embodiments, an input waveform 306 (discussed in Figs. 3B-5 and 7) having a stimulation portion and a neural response portion may be recorded so as to capture an early neural response. For example, one or more of the electrodes 208A-208D, 210A-210D may generate an electric signal that stimulates the spinal cord 108. The stimulation may cause one or more neural responses such as, for example, eCAP responses, which may be sensed, detected, and/or measured together with the stimulation by the electrodes 208A-208D, 210A-210D that were not used to stimulate the spinal cord. In some embodiments, the electrodes 208A-208D may stimulate the spinal cord 108, while the electrodes 210A-210D sense or record the eCAP response and the stimulation. In other embodiments, a first set of electrodes (e.g., the electrodes 208A, 208B, 210A, 210B) may stimulate the spinal cord 108, while a second set of electrodes (e.g., the electrodes 208C, 208D, 210C, 210D) may measure the spinal cord 108 response and stimulation, including capturing the eCAP response or waveform data. [0063] The system 100 or similar systems may be used, for example, to carry out one or more aspects of the methods 400, 500, 700 described herein. The system 100 or similar systems may also be used for other purposes. It will be appreciated that the human body has many nerves and the stimulation and/or measurement described herein may be applied to one or more nerves, which may reside at any location of a patient (e.g., lumbar, thoracic, peripheral nerve stimulation, pelvic health (e.g., sacral nerve or tibial nerve) etc.). Further, the use of the leads 104 to stimulate and/or measure neural responses such as eCAP responses may occur with different portions of the nervous system. For example, the leads 104 may be connected to one or more of nerve endings in the spinal cord, the brain or portions thereof, combinations thereof, and the like.

[0064] Additionally, while not shown in Figs. 1-2, the system 100 may include one or more processors (e.g., one or more DSPs, general purpose microprocessors, graphics processing units, ASICs, FPGAs, or other equivalent integrated or discrete logic circuitry) shown and described in Fig. 7 that are programmed to carry out one or more aspects of the present disclosure. In some examples, the one or more processors may include a memory or may be otherwise configured to perform the aspects of the present disclosure. For example, the one or more processors may provide instructions to the device 102 or other components of the system 100 not explicitly shown or described with reference to Fig. 1 for generating stimulations of one or more nerves, measuring eCAP responses, stimulation, and/or adjusting provided therapies based on the measured eCAP responses, as described herein. In some examples, the one or more processors may be part of the device 102 or part of a control unit for the system 100 (e.g., where the control unit is in communication with the device 102 and/or other components of the system 100).

[0065] Turning to Fig. 3A, a chart 360 showing a neural response 362 superimposed on a stimulation response 364 is shown. A y-axis 366 of the chart 360 represents amplitude and the x-axis 368 of the chart represents time. As shown, an early response or a Pl response 370 of the neural response 362 is obscured by the stimulation waveform 364. Thus, it may be difficult to obtain or retrieve the early response or the Pl response 370. Thus, one or more circuits, as described below, may facilitate retrieval of the early response or the Pl response 370.

[0066] Turning to Fig. 3B, a neural response system 300 having a circuit 302 and a waveform analytics engine 304 are shown. The neural response system 300 may be configured to capture and retrieve an early neural response during therapeutic neuromodulation. The circuit 302 may be configured to receive or sense an input waveform 306 and to convert the input waveform 306 into a format that can be analyzed by the waveform analytics engine 304. The waveform analytics engine 304 may be configured to retrieve or obtain the early neural response from the input waveform 306. [0067] The circuit 302 includes an input 310 configured to receive the input waveform 306 and a summation node 312 configured to apply a stimulation artifact template such as a stimulation artifact template 324 (also discussed in Figs. 5 and 7 below) to the input waveform 306 to create a modified input waveform. As previously described, the input waveform 306 may include a stimulation portion and a neural response portion. The neural response portion of the input waveform 306 includes a response of an anatomical element (such as, for example, a nerve) to a stimulation pulse or one or more electric pulses delivered by, for example, the device 102 to the anatomical element. The neural response portion may comprise an eCAP response. The neural response portion may also include a first response peak created as a response to the stimulation portion of the input waveform 306. In such embodiments, the first response peak in the neural response portion may coincide with the stimulation pulse or the pose-stimulus artifact, which may obscure or block the first response peak. As previously described, the stimulation pulse may block an early portion of the neural response portion or the first response peak when, for example, the leads 104A, 104B are positioned near each other. Thus, the neural response system 300 may be utilized to retrieve or obtain the neural response portion - and more specifically, the first response peak - from the input waveform 306.

[0068] The neural response system 300 also includes a template generator 308 configured to generate the stimulation artifact template 324. The stimulation artifact template 324 may comprise a predicted version of the stimulation portion. In other embodiments, the stimulation artifact template 324 may comprise a post stimulation artifact, a stimulus artifact obtained from the stimulation portion, or a combination thereof. Prior to applying the stimulation artifact template 324 to the input waveform 306, the stimulation artifact template 324 may be passed through a digital-to-analog converter 318 to obtain an analog version of the stimulation artifact template 324. The digital-to- analog converter 318 may be any digital-to-analog converter configured to convert binary or digital code into an analog signal using any circuit or method such as, for example, a weighted resistor method, a R-2R ladder circuit, and/or a pulse width modulation method. The stimulation artifact template 324 may then be applied to the input waveform 306 in the analog version. In some embodiments, applying the stimulation artifact template 324 to the input waveform 306 by the summation node 312 may comprise subtracting the stimulation artifact template 324 from the input waveform 306 to create the modified input waveform 306.

[0069] Turning to Fig. 3C, a circuit 322 comprising a feedback loop is shown. The circuit 322 is configured to apply a stimulation waveform to match or control a ground voltage of a body (e.g., the patient) 328 with a voltage of the device 102 applying the simulation. In other words, the circuit 322 keeps the common mode input voltage of the input waveform 306 within the input range of the amplifier 310. Thus, the feedback loop can be used to control a body voltage (e.g., of the patient) and therefore, control a common mode voltage of the input waveform 306. Limiting the input voltage requirement beneficially enables the use of higher performance, low voltage components in the amplifier 310.

[0070] More specially in at least one embodiment, the common mode voltage level at the electrodes (body) can be biased at a common mode level of the applied stimulus pulse (as applied by the device 102) via the feedback loop as illustrated. In the illustrated feedback loop, CHOLD/2 330A is a mid-rail voltage of the stimulus when the stimulus pulse is applied to the patient and CHOLD 330B is a power rail of the stimulus. The voltage of the body 328 may be biased around the CHOLD/2 330A using the feedback loop. As the result, when the stimulus is applied, there may be no change or minimal change of the common mode level at the electrodes which would allow a simplified design for the amplifier 310 and can also enable sensing during the stimulus or shortly thereafter. It will be appreciated that in some embodiments, CHOLD/2 can be replaced with other forms of bias such as, for example, Vstim or Vcm stim (e.g., a common mode bias from the stimulation)..

[0071] The modified input waveform 306 can be received as input by the waveform analytics engine 304, which is configured to retrieve information about the neural response portion of the input waveform 306. In some instances, the modified input waveform is analyzed in the digital domain. In such instances, the modified input waveform 306 may be passed through an analog-to- digital converter 316 prior to being analyzed. The analog-to-digital converter 316 may be any analog-to-digital converter configured to convert an analog signal into binary or digital code using any circuit or method such as, for example, a successive approximation analog-to-digital converter, a delta-sigma analog-to-digital converter, a dual slope analog-to-digital converter, a pipelined analog- to-digital converter, and/or a flash analog-to-digital converter. It will be appreciated that in the illustrated embodiment the analog-to-digital converter 316 may comprise an analog-to-digital converter 316A. Further, prior to passing the modified input waveform 306 through the analog-to- digital converter 316, the modified input waveform may be amplified and/or filtered by an active filter 314. The active filter 314 may be any active filter 314 configured to allow certain frequency components and/or reject other frequency components. The active filter 314 may comprise an active low pass filter, an active high pass filter, an active band pass filter, or an active band stop filter.

[0072] The neural response system 300 also includes an artifact input 332 As shown in the illustrated embodiment, the neural response system 300 may be configured to capture an early neural response and to estimate the stimulation artifact during therapeutic neuromodulation. It will be appreciated that in some embodiments the artifact input 332 may be a separate signal path that can be connected to a separate or the same set of electrodes as the input waveform 306. In such embodiments, the separate signal path can be used to estimate the stimulus or post-stimulus artifact and to generate the stimulation artifact template 324.

[0073] The artifact input 332 may receive the input waveform 306 and estimate the stimulus artifact from the input waveform 306. As shown in the illustrated embodiment, once the stimulus artifact is measured, the stimulus artifact may be passed through an amplifier 320. The amplifier 320 may be any amplifier configured to increase a magnitude of the signal and filter the signal (of, for example, the stimulus artifact) in order to derive a template of the stimulus or post-stimulus artiface. In some embodiments, the amplifier 320 is a low gain amplifier. In other embodiments, the stimulus artifact may be estimated from, for example, impedance, current information, and/or direct artifact measurements (in embodiments where access to the one or more electrodes 208, 210 is provided via a high-input impedance connection). The stimulus artifact may then be passed through an analog-to- digital converter 316B (which may be the same as or similar to the analog-to-digital converter 316A) to obtain a digital version of the stimulus artifact. The digital stimulus artifact may then be used to create or generate the stimulation artifact template 324 by the template generator 308. In some embodiments, as also described below in Fig. 5, the stimulus artifact obtained from the input waveform 306 may be used to generate or update the stimulation artifact template 324 by the template generator 308 using a machine learning model 408. In other embodiments, the stimulation artifact template 324 may be generated by the template generator 308 using an accumulator. The stimulation artifact template 324 may be updated by the template generator 308 periodically or continuously throughout the therapeutic neuromodulation. For example, the stimulation artifact template 324 may be updated at least once a day. In other embodiments, the stimulation artifact template 324 may be updated based on user input. Further, one or more stimulation artifact templates 324 may be stored in, for example, memory such as the memory 606, a database such as the database 630, or a cloud such as the cloud 632.

[0074] Turning to Fig. 4, an example of a model architecture 400 that supports methods and systems (e.g., Artificial Intelligence (Al)-based methods and/or system) for generating the stimulation artifact template 324 using the machine learning model 408 is provided. It will be appreciated that the machine learning model 408 may be used in some embodiments to generate the stimulation artifact template 324 and in other embodiments the stimulation artifact template 324 may be generated using an accumulator. [0075] An input waveform 306 may be used by a processor such as the processor 604 as input for a machine learning model 408. The machine learning model 408 may output a stimulation artifact template 324. In some embodiments, the input waveform 306 may be received from a sensor such as the sensor 620 (shown in Fig. 6) and/or one or more electrodes 208, 210 (shown in Fig. 2), or any other component of the systems 100, 300, 600. The input waveform 306 includes a stimulation portion and a neural response portion. The stimulation portion is formed by stimulating an anatomical element using, for example, the device 102 with one or more electrical pulses or stimulation pulses. The neural response portion is created as a response to the stimulation portion. In some embodiments, the neural response portion comprises an eCAP response having a first response peak. The stimulation artifact template 324 may be used to remove the stimulus artifact from the input waveform 306 prior to processing the input waveform 306 in, for example, the analog domain to obtain the neural response portion.

[0076] The machine learning model 408 may be trained using historical input waveforms, historical stimulus artifacts, and/or historical stimulus portions. In other embodiments, the machine learning model 408 may be trained using the input waveform 306. In such embodiments, the machine learning model 408 may be trained prior to inputting the input waveform 306 into the machine learning model 408 or may be trained in parallel with inputting the input waveform 306 into the machine learning model 408.

[0077] Fig. 5 depicts a method 500 that may be used, for example, for generating a model is provided.

[0078] The method 500 comprises generating a model (step 504). The model may be the machine learning model 408. A processor such as the processor 604 may generate the model. The model may be generated to facilitate and enable, for example, generating the stimulation artifact template 324. [0079] The method 500 also comprises training the model (step 508). In embodiments where the model is trained prior to therapeutic neuromodulation, the model may be trained using historical data from a number of patients. In some embodiments, the historical data may be obtained from patients that have similar patient data to a patient on which the therapeutic neuromodulation is to be applied. In other embodiments, the historical data may be obtained from any patient.

[0080] In other embodiments, the model may be trained in parallel with use of another model. Training in parallel may, in some embodiments, comprise training a model using input received during, for example, or prior to a therapeutic neuromodulation, while also using a separate model to receive and act upon the same input. Such input may be specific to a patient undergoing the therapeutic neuromodulation. In some instances, when the model being trained exceeds the model in use (whether in efficiency, accuracy, or otherwise), the model being trained may replace the model in use. Such parallel training may be useful, for example, in situations, where a model is continuously in use (for example, when an input (such as, for example, an image) is continuously updated) and a corresponding model may be trained in parallel for further improvements.

[0081] In some embodiments, it will be appreciated that the model trained using historical data may be initially used as a primary model at a start of the therapeutic neuromodulation. A training model may also be trained in parallel with the primary model using patient-specific input until the training model is sufficiently trained. The primary model may then be replaced by the training model.

[0082] The method 500 also comprises storing the model (step 512). The model may be stored in memory such as the memory 606 and/or a database such as the database 630 for later use. In some embodiments, the model is stored in the memory when the model is sufficiently trained. The model may be sufficiently trained when the model produces an output that meets a predetermined threshold, which may be determined by, for example, a user, or may be automatically determined by a processor such as the processor 604.

[0083] The present disclosure encompasses embodiments of the method 500 that comprise more or fewer steps than those described above, and/or one or more steps that are different than the steps described above.

[0084] Turning to Fig. 6, a block diagram of a system 600 according to at least one embodiment of the present disclosure is shown. The system 600 may be used with the system 100 or the system 300 or components thereof, and/or may carry out one or more other aspects of one or more of the methods disclosed herein. The system 600 comprises the device 102, the neural response system 300, a computing device 602, a database 630, and/or a cloud or other cloud network 634. Systems according to other embodiments of the present disclosure may comprise more or fewer components than the system 600. For example, the system 600 may not include one or more components of the computing device 602, the database 630, and/or the cloud network 634. While the computing device 602 of the system 600 is illustrated as being in communication with the device 102, it is to be understood that the computing device 602 may be disposed as a sub-component within the device 102, or may alternatively be an external device that communicates with the device 102 using, for example, a communication interface 608, or through the cloud 634 or other network. In some embodiments, the device 102 may include any one or more components of the system 600 including, but not limited to, the computing device 602, the processor 604, the memory 606, the communication interface 608, the database 630, combinations thereof, and the like. [0085] The device 102 may comprise the leads 104, the electrodes 208, 210, and one or more sensors 620. As previously described, the leads 104 and the electrodes 208, 210 may be configured to apply the current to an anatomical element (e.g., the spinal cord, one or more nerves, etc.). The device 102 may communicate with the computing device 602 to receive instructions such as instructions for applying a current to the anatomical element. The device 102 may also provide data (such as data received from or measured by the electrodes 208, 210 or measured by the sensors 620), which may be used to determine whether overstimulation is occurring or has occurred. The determination of overstimulation may enable the system 600 to adjust the therapy applied by the device 102, beneficially resulting in improved patient treatment.

[0086] The neural response system 300 may be configured to capture an early neural response and/or to estimate the stimulation artifact during therapeutic neuromodulation. The neural response system 300 may comprise an input such as the input 310, a summation node such as the summation node 312, and a waveform analytics engine such as the waveform analytics engine 304. The neural response system 300 may also comprise additional components such as, for example, a digital-to- analog converter such as the digital -to-analog converter 318, an analog-to-digital converter such as the analog-to-digital converter 316, an active filter such as the active filter 314, an artifact input such as the artifact input 332, and/or an amplifier such as the amplifier 320.

[0087] The one or more sensors 620 may be or comprise sensors capable of capturing data and/or information related to stimulation and/or neural response(s) such as eCAP waveforms. For example, the one or more sensors 620 may be or comprise one or more voltmeters or ammeters capable of respectively detecting voltages and currents generated during an eCAP response. In some embodiments, the sensors 620 may be directly or proximally attached to the leads 104 to capture data associated with the eCAPs. In some embodiments, the sensors 620 may communicate with the device 102, the computing device 602, and/or the database 630. The communication may enable the sensors 620 to receive instructions from the computing device 602 (e.g., instructions to begin or stop capturing data) and transmit recorded data to, for example, the database 630. In some embodiments, the electrodes 208, 210 may include the one or more sensors 620, or may act themselves as sensors, for measuring the eCAPs.

[0088] The computing device 602 comprises a processor 604, a memory 606, a communication interface 608, and a user interface 610. Computing devices according to other embodiments of the present disclosure may comprise more or fewer components than the computing device 602.

[0089] The processor 604 of the computing device 602 may be any processor described herein or any similar processor. The processor 604 may be configured to execute instructions stored in the memory 606, which instructions may cause the processor 604 to carry out one or more computing steps utilizing or based on data received from the device 102, the database 630, and/or the cloud network 634. Additionally or alternatively, the processor 604 may be configured to perform tasks, computations, or the like associated with one or more waveform analytics engine(s) 304, one or more template generator(s) 308, one or more stimulation artifact template(s) 324, and/or one or more machine learning model(s) 408, and the like.

[0090] The memory 606 may be or comprise RAM, DRAM, SDRAM, other solid-state memory, any memory described herein, or any other tangible, non-transitory memory for storing computer- readable data and/or instructions. The memory 606 may store information or data useful for completing, for example, one or more steps of the methods 400, 500, 700 described herein, or of any other methods. The memory 606 may store, for example, instructions and/or machine learning models (e.g., neural networks) that support one or more functions of the device 102 and/or the system 300. For instance, the memory 606 may store content (e.g., instructions and/or machine learning models) that, when executed by the processor 604, enable determinations of whether a patient is experiencing overstimulation.

[0091] Content stored in the memory 606, if provided as in instruction, may, in some embodiments, be organized into one or more applications, modules, packages, layers, or engines. Alternatively or additionally, the memory 606 may store other types of content or data (e.g., machine learning models, artificial neural networks, deep neural networks, etc.) that can be processed by the processor 604 to carry out the various method and features described herein. For example, the memory 606 may store the one or more stimulation artifact templates 324, the machine learning model 408, or other data such as the input waveform 306. Thus, although various contents of memory 606 may be described as instructions, it should be appreciated that functionality described herein can be achieved through use of instructions, algorithms, and/or machine learning models. The data, algorithms, and/or instructions may cause the processor 604 to manipulate data stored in the memory 606 and/or received from or via the device 102, the database 630, and/or the cloud network 634.

[0092] The computing device 602 may also comprise a communication interface 608. The communication interface 608 may be used for receiving data (for example, data from the device 102 or the system 300) or other information from an external source (such as the device 102, the system 300, the database 630, the cloud network 634, and/or any other system or component not part of the system 600), and/or for transmitting instructions, images, or other information to an external system or device (e.g., another computing device 602, the device 102, the system 300, the database 630, the cloud network 634, and/or any other system or component not part of the system 600). The communication interface 608 may comprise one or more wired interfaces (e.g., a USB port, an Ethernet port, a Firewire port) and/or one or more wireless transceivers or interfaces (configured, for example, to transmit and/or receive information via one or more wireless communication protocols such as 602.11a/b/g/n, Bluetooth, NFC, ZigBee, and so forth). In some embodiments, the communication interface 608 may be useful for enabling the computing device 602 to communicate with one or more other processors 604 or computing devices 602, whether to reduce the time needed to accomplish a computing-intensive task or for any other reason.

[0093] The computing device 602 may also comprise one or more user interfaces 610. The user interface 610 may be or comprise a keyboard, mouse, trackball, monitor, television, screen, touchscreen, and/or any other device for receiving information from a user and/or for providing information to a user. The user interface 610 may be used, for example, to receive a user selection or other user input regarding any step of any method described herein. Notwithstanding the foregoing, any required input for any step of any method described herein may be generated automatically by the system 600 (e.g., by the processor 604 or another component of the system 600) or received by the system 600 from a source external to the system 600. In some embodiments, the user interface 610 may be useful to allow a surgeon or other user to modify instructions to be executed by the processor 604 according to one or more embodiments of the present disclosure, and/or to modify or adjust a setting of other information displayed on the user interface 610 or corresponding thereto. [0094] Although the user interface 610 is shown as part of the computing device 602, in some embodiments, the computing device 602 may utilize a user interface 610 that is housed separately from one or more remaining components of the computing device 602. In some embodiments, the user interface 610 may be located proximate one or more other components of the computing device 602, while in other embodiments, the user interface 610 may be located remotely from one or more other components of the computing device 602.

[0095] The database 630 may store information such as patient data, lead parameters, input waveforms data, eCAP waveform data or similar data, electrode parameters, threshold values, etc. The database 630 may be configured to provide any such information to the computing device 602 or to any other device of the system 600 or external to the system 600, whether directly or via the cloud network 634. In some embodiments, the database 630 may be or comprise part of a hospital storage system, such as a picture archiving and communication system (PACS), a health information system (HIS), and/or another system for collecting, storing, managing, and/or transmitting electronic medical records. [0096] The cloud network 634 may be or represent the Internet or any other wide area network. The computing device 602 may be connected to the cloud network 634 via the communication interface 608, using a wired connection, a wireless connection, or both. In some embodiments, the computing device 602 may communicate with the database 630 and/or an external device (e.g., a computing device) via the cloud network 634.

[0097] The system 600 or similar systems may be used, for example, to carry out one or more aspects of the methods 400, 700 described herein. The system 600 or similar systems may also be used for other purposes.

[0098] Fig. 7 depicts a method 700 that may be used, for example, for measuring an input waveform having a neural response such as, for example, an eCAP response.

[0099] The method 700 (and/or one or more steps thereof) may be carried out or otherwise performed, for example, by at least one processor. The at least one processor may be the same as or similar to the processor(s) 604 of the computing device 602 described above. A processor other than any processor described herein may also be used to execute the method 700. The at least one processor may perform the method 700 by executing elements stored in a memory such as the memory 606. The elements stored in memory and executed by the processor may cause the processor to execute one or more steps of a function as shown in method 700. One or more portions of a method 700 may be performed by the processor executing any of the contents of memory, such as a machine learning model such as the machine learning model 408, a template generator such as a template generator 308, and/or an analytics waveform engine such as the waveform analytics engine 304.

[0100] The method 700 comprises stimulating an anatomical element (step 704). The anatomical element may be, for example, one or more nerves. The anatomical element may be stimulated using, for example, a device such as the device 102. The device may include one or more leads such as the leads 104A, 104B that are configured to deliver a stimulation pulse or one or more electrical pulses to the anatomical element. In some embodiments, the lead may comprise one or more electrodes such as the electrodes 208, 210 that may be used to deliver the stimulation pulse. In such embodiments, some of the one or more electrodes may be configured to deliver the stimulation pulse and other electrodes may be configured to record a response to the stimulation pulse.

[0101] The method 700 also comprises capturing an input waveform (step 708). The input waveform may be the same as or similar to the input waveform 306 and may be received by an input such as the input 310 of a circuit such as the circuit 302. The input waveform may be recorded or captured by the one or more electrodes or by one or more sensors such as the one or more sensors 620. As previously described, the input waveform includes a stimulation portion and a neural response portion. The neural response portion may be, for example, an eCAP response. The neural response portion may include a first response peak created as a response to the stimulation portion. However, the stimulation portion may block or obscure the first response peak, thus, the method 700 may be utilized to retrieve or obtain the first response peak as described below.

[0102] The method 700 also comprises passing a digital version of a stimulation artifact template through a digital-to-analog converter (step 712). The stimulation artifact template may be the same as or similar to the stimulation artifact template 324 and may be generated by a template generator such as the template generator 308. The stimulation artifact template may be passed through a digital-to-analog converter such as the digital-to-analog converter 318 to obtain an analog version of the stimulation artifact template. As previously described, the stimulation artifact template may comprise a predicted version of the stimulation portion, a post stimulation artifact, a stimulus artifact obtained from the stimulation portion, or a combination thereof. In some embodiments, the stimulation artifact template may be generated by the template generator using a machine learning model such as the machine learning model 408 using the input waveform as an input. In other embodiments, the stimulation artifact template may be generated by the template generator using an accumulator. The stimulation artifact template can also be estimated by the template generator from impedance, current information, or a direct artifact measurement from the one or more electrodes. One or more stimulation artifact templates may be stored in memory such as the memory 606, a database such as the database 630, and/or a cloud such as the cloud 632.

[0103] It will be appreciated that the method 700 may not include the step 712.

[0104] The method 700 also comprises applying the stimulation artifact template to the input waveform to create a modified input waveform (step 716). The stimulation artifact template may be applied to the input waveform by a summation node such as the summation node 312. Applying the stimulation artifact template to the input waveform may comprise subtracting the simulation artifact template from the input waveform. In other words, the modified input waveform may comprise the input waveform without at least a portion of the stimulation artifact, thereby enabling processing or retrieval of, for example, the first response peak from the modified input waveform.

[0105] The method 700 also comprises amplifying the modified input waveform (step 720). The modified input waveform may be amplified by passing the modified input waveform through an active filter such as the active filter 314.

[0106] It will be appreciated that the method 700 may not include the step 720. [0107] The method 700 also comprises filtering the modified input waveform (step 724). The modified input waveform may be filtered by passing the modified input waveform through the active filter.

[0108] It will be appreciated that the method 700 may not include the step 724. It will also be appreciated that the steps 720 and 724 may occur simultaneously.

[0109] The method 700 also comprises passing the modified input waveform through an analog- to-digital converter (step 728). The modified input waveform may be passed through an analog-to- digital converter such as the analog-to-digital converter 316 to obtain a digital version of the modified input waveform.

[0110] The method 700 also comprises analyzing the modified input waveform (step 732). The modified input waveform may be analyzed by a waveform analytics engine such as the waveform analytics engine 304. The waveform analytics engine is configured to analyze the modified input waveform to retrieve information about the neural response portion of the input waveform. The information may include the first response peak created as a response to the stimulation portion of the input waveform.

[0111] In some embodiments, the method may also include alternating a polarity of another stimulation pulse generated by the device to cancel a residual error of the summation node 312 and the digital-to-analog converter 318 upon addition of two waveforms originating from different stimulus polarities.

[0112] The present disclosure encompasses embodiments of the method 700 that comprise more or fewer steps than those described above, and/or one or more steps that are different than the steps described above.

[0113] As noted above, the present disclosure encompasses methods with fewer than all of the steps identified in Figs. 4, 5 and 7 (and the corresponding description of the methods 400, 500, 700), as well as methods that include additional steps beyond those identified in Figs. 4, 5 and 7 (and the corresponding description of the methods 400, 500 and 700). The present disclosure also encompasses methods that comprise one or more steps from one method described herein, and one or more steps from another method described herein. Any correlation described herein may be or comprise a registration or any other correlation.

[0114] The foregoing is not intended to limit the disclosure to the form or forms disclosed herein. In the foregoing Detailed Description, for example, various features of the disclosure are grouped together in one or more aspects, embodiments, and/or configurations for the purpose of streamlining the disclosure. The features of the aspects, embodiments, and/or configurations of the disclosure may be combined in alternate aspects, embodiments, and/or configurations other than those discussed above. This method of disclosure is not to be interpreted as reflecting an intention that the claims require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed aspect, embodiment, and/or configuration. Thus, the following claims are hereby incorporated into this Detailed Description, with each claim standing on its own as a separate preferred embodiment of the disclosure.

[0115] Moreover, though the foregoing has included description of one or more aspects, embodiments, and/or configurations and certain variations and modifications, other variations, combinations, and modifications are within the scope of the disclosure, e.g., as may be within the skill and knowledge of those in the art, after understanding the present disclosure. It is intended to obtain rights which include alternative aspects, embodiments, and/or configurations to the extent permitted, including alternate, interchangeable and/or equivalent structures, functions, ranges or steps to those claimed, whether or not such alternate, interchangeable and/or equivalent structures, functions, ranges or steps are disclosed herein, and without intending to publicly dedicate any patentable subject matter.

Claims

CLAIMS What is claimed is:

1. A method, comprising: capturing an input waveform that includes a stimulation portion and a neural response portion; applying a stimulation artifact template to the input waveform to create a modified input waveform; and analyzing the modified input waveform in a digital domain to retrieve information about the neural response portion of the input waveform, wherein the information about the neural response portion includes a first response peak created as a response to the stimulation portion.

2. The method of claim 1, further comprising: stimulating, using a pulse generator, an anatomical element with one or more electrical pulses, wherein the one or more electrical pulses contribute to the stimulation portion.

3. The method of claim 2, wherein the neural response portion comprises a response of the anatomical element to the one or more electrical pulses and wherein the first response peak in the neural response portion coincides with the one or more electrical pulses.

4. The method of claim 1, wherein the stimulation artifact template comprises a predicted version of the stimulation portion.

5. The method of claim 4, wherein the stimulation artifact template comprises a post stimulation artifact.

6. The method of claim 4, wherein the stimulation artifact template comprises a stimulus artifact obtained from the stimulation portion.

7. The method of claim 4, wherein the stimulation artifact template comprises a combination of a post stimulation artifact and a stimulus artifact obtained from the stimulation portion.

8. The method of claim 4, wherein the stimulation artifact template is generated from a machine learning model based on the machine learning model processing the input waveform.

9. The method of claim 4, wherein the stimulation artifact template is generated using an accumulator.

10. The method of claim 1, wherein applying the stimulation artifact template to the input waveform comprises subtracting the stimulation artifact template from the input waveform.

11. The method of claim 1, further comprising: passing the modified input waveform through an analog-to-digital converter prior to analyzing the modified input waveform in the digital domain.

12. The method of claim 11, further comprising: amplifying the modified input waveform prior to passing the modified input waveform through the analog-to-digital converter; and filtering the modified input waveform prior to passing the modified input waveform through the analog-to-digital converter.

13. The method of claim 11, further comprising: passing a digital version of the stimulation artifact template through a digital-to-analog converter to obtain an analog version of the stimulation artifact template, wherein the analog version of the stimulation artifact template is applied to the input waveform.

14. A system, comprising: an input to receive an input waveform that includes a stimulation portion and a neural response portion; a summer circuit that applies a stimulation artifact template to the input waveform to create a modified input waveform; and a waveform analytics engine that analyzes the modified input waveform to retrieve information about the neural response portion of the input waveform, wherein the information about the neural response portion includes a first response peak created as a response to the stimulation portion.

15. The system of claim 14, further comprising: an analog-to-digital converter positioned between the summer circuit and the waveform analytics engine.

16. The system of claim 14, further comprising: one or more leads positioned near an anatomical element, wherein the one or more leads deliver a stimulation pulse to the anatomical element and capture the neural response to the stimulation pulse.

17. The system of claim 16, wherein the anatomical element comprises a nerve.

18. The system of claim 16, wherein the input waveform comprises an Evoked

Compound Action Potential (eCAP) signal.

19. The system of claim 16, wherein the neural response portion comprises a response of the anatomical element to the stimulation pulse, wherein a first response peak in the neural response portion coincides with the stimulation pulse, and wherein the stimulation artifact template comprises a predicted version of the stimulation portion.

20. A circuit, comprising: an input to receive an input waveform that includes a stimulation portion and a neural response portion; a summation node that applies a stimulation artifact template to the input waveform to create a modified input waveform; and an analog-to-digital converter that transforms the modified input waveform from an analog version thereof to a digital version thereof.