Stimulation system

Abstract

A method for detecting and identifying a patient's physiological response includes stimulating one or more nerves of the patient via stimulating electrodes coupled to the patient. The method includes recording a plurality of derived electrical waveforms via recording electrodes coupled to the patient. The method includes determining, based on the plurality of derived electrical waveforms, whether at least a subset of the plurality of derived electrical waveforms includes the patient's physiological response. The determining includes comparing the subset of derived electrical waveforms of the plurality of derived electrical waveforms to a model waveform from a database of a plurality of model waveforms. The determining includes determining a comparison characteristic based on the comparison. The comparison characteristic is indicative of whether the patient's physiological response is present within the subset. The method includes displaying, via the display, an indication that the patient's physiological response is present within the subset of derived electrical waveforms.

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims priority to U.S. Provisional Patent Application No. 63 / 160,605, filed on March 12, 2021, entitled "Stimulation System", the entire disclosure of which is incorporated herein by reference.

[0002] The subject matter described herein generally relates to patient monitoring and clinical neurophysiology, and more specifically to a stimulation system for detecting and discriminating a patient's physiological responses.

Background Art

[0003] Monitoring a patient by recording waveforms in response to stimuli delivered to the patient during surgery makes it possible to identify and prevent impending injuries such as nerve damage. Generally, a highly trained technician under a physician's supervision may monitor a patient during surgery using sophisticated multi - channel amplifiers and display devices. Unfortunately, such staff and equipment are costly, may have limited availability, and / or may require advance reservation. Such staff may also subjectively analyze waveforms under stressful conditions, resulting in reduced accuracy, speed, and efficiency in detecting physiological responses, and thus an increased risk of injury to the patient during surgery. Detecting a patient's physiological response and changes in the response within the recorded waveforms can also be difficult when such responses are small, and the waveforms may contain a large amount of ongoing noise signals.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Therefore, it can be difficult for technicians to recognize a patient's physiological responses and to issue appropriate warnings for changes in those responses. This can lead to an increase in injuries sustained by patients during surgery. [Means for solving the problem]

[0006] Systems, methods, and articles of manufacture, including computer program products, are provided to constitute medical devices and to recommend drug dosages based at least partially on a patient's health condition. For example, the system may treat patients more effectively, efficiently, and quickly by providing patients with more accurate drug preparation and delivery configurations and / or dosages.

[0007] A method for detecting and identifying a patient's physiological response is provided, according to several embodiments. This method may include stimulating one or more nerves of the patient via stimulating electrodes coupled to the patient. The method may also include recording a plurality of obtained electrical waveforms via recording electrodes coupled to the patient. The method may also include determining, based on the plurality of obtained electrical waveforms, whether at least a subset of the plurality of obtained electrical waveforms contains the patient's physiological response. Determining this may include comparing the subset of obtained electrical waveforms from the plurality of obtained electrical waveforms with an induced model waveform from a database of a plurality of template waveforms, possibly in real time. Determining this may also include determining one or more comparison features based on the comparison. One or more comparison features may indicate whether the patient's physiological response is present within the subset of obtained electrical waveforms. The method may further include displaying, via a display, an indication that the patient's physiological response is present within the subset of obtained electrical waveforms.

[0008] In some embodiments, the model waveform includes predicted physiological responses and multiple anthropogenic signaling phenomena.

[0009] In some embodiments, one or more comparison features further indicate whether or not artificial phenomenon signals are present within the subset of the resulting electrical waveforms.

[0010] In some embodiments, the method also includes displaying, via a display, an indication that an artificial phenomenon signal is present within a subset of the resulting electrical waveforms.

[0011] In some embodiments, determining whether at least a subset of multiple obtained electrical waveforms contains a patient's physiological response further includes labeling the subset of multiple obtained electrical waveforms with a positive or negative label based on one or more comparative features. A positive label indicates the presence of a patient's physiological response, and a negative label indicates the absence of a patient's physiological response.

[0012] In some embodiments, determining whether multiple obtained electrical waveforms include a patient's physiological response further includes determining that a patient's physiological response is present if one or more comparison features of a subset of electrical waveforms fall within a threshold range of the threshold of one or more comparison features.

[0013] In some embodiments, one or more comparison features include the mean squared error between the obtained subset of electrical waveforms and the model waveform, the correlation between the obtained subset of electrical waveforms and the model waveform, the amplitude of the physiological coefficients, the power of the fundamental harmonic noise, the THP of the harmonic noise, the ratio of the physiological coefficients of the obtained subset of electrical waveforms to the power of the harmonic noise, and the variance ratio of the patient's physiological response to the model's predicted physiological response to the obtained subset of electrical waveforms.

[0014] In some embodiments, the determination of whether multiple obtained electrical waveforms include a patient's physiological response further includes determining that a patient's physiological response is present if the polarity of each electrical waveform in the subset of obtained electrical waveforms is the same.

[0015] In some embodiments, the comparison feature represents a comparison of the form of the model waveform with the form of a subset of the obtained electrical waveforms.

[0016] In some embodiments, the comparison feature includes a plurality of comparison features, and the labeling is further based on a mathematical representation of the plurality of comparison features.

[0017] In some embodiments, the labeling includes comparing the comparison feature with a plurality of previously generated comparison features.

[0018] In some embodiments, a time window is applied to a subset of the plurality of obtained electrical waveforms.

[0019] In some embodiments, the model waveform is generated using an integrated high-speed orthogonal search method. The integrated high-speed orthogonal search method can generate a model waveform using the following equation,

Equation

Equation

[0020] In some embodiments, stimulating includes transmitting a plurality of electrical stimuli. The stimulation electrodes are in communication with an evoked potential detection device configured to monitor one or more peripheral nerves of a patient.

[0021] In some embodiments, a plurality of obtained electrical waveforms are received by an evoked potential detection device. The obtained electrical waveforms can be generated by a patient in response to an electrical stimulus.

[0022] Embodiments of the present subject matter may include articles that include a method according to the description provided herein, and a specifically embodied machine-readable medium operable to cause a machine (e.g., a computer, etc.) to perform one or more of the features described or signals necessary to perform the one or more of the features described. Similarly, a computer system may also be described that may include one or more processors and one or more memories connected to the one or more processors. A memory that may include a non-transitory computer-readable or machine-readable storage medium may include, encode, store, etc., one or more programs that cause the one or more processors to perform one or more of the operations described herein. A computer-implemented method according to one or more embodiments of the present subject matter may be implemented by one or more data processors resident in a single computing system or multiple computing systems. Such multiple computing systems may be connected and may exchange data and / or commands or other instructions, etc., via one or more connections including, for example, a connection via a network (e.g., the Internet, a wireless wide area network, a local area network, a wide area network, a wired network, etc.), a direct connection between one or more of the multiple computing systems, etc.

[0023] Details regarding one or more variations of the subject matter described herein are set forth in the accompanying drawings and the following description. Other features and advantages of the subject matter described herein will be apparent from the description and drawings, and from the claims. The claims that follow this disclosure are intended to define the scope of the protected subject matter.

Brief Description of the Drawings

[0024] The following attached drawings, which are incorporated in and form a part of this specification, illustrate specific aspects of the subject matter disclosed herein and, together with the description, serve to explain some of the principles associated with the disclosed embodiments. [Figure 1]This diagram shows a system diagram illustrating a stimulation system according to an embodiment of the subject matter. [Figure 2] This shows a functional block diagram of a system for monitoring nerve function, according to an embodiment of this subject. [Figure 3] This represents an exemplary user interface following the embodiment of this subject. [Figure 4] This represents an exemplary user interface following the embodiment of this subject. [Figure 5] This represents an exemplary user interface following the embodiment of this subject. [Figure 6] This represents an exemplary user interface following the embodiment of this subject. [Figure 7] This represents an exemplary user interface following the embodiment of this subject. [Figure 8] This represents an exemplary user interface following the embodiment of this subject. [Figure 9] This represents an exemplary user interface following the embodiment of this subject. [Figure 10] This flowchart shows a process for identifying and labeling a patient's physiological responses according to an embodiment of this subject. [Figure 11] This is a flowchart showing the process for generating a physiological template according to an embodiment of this subject. [Figure 12] This is a flowchart showing the process for generating a model waveform according to an embodiment of this subject. [Figure 13] This flowchart shows a process for identifying and labeling a patient's physiological responses according to an embodiment of this subject. [Figure 14] This is a block diagram illustrating a computing system according to several exemplary embodiments. In actual cases, similar reference numbers indicate similar structures, features, or elements. [Modes for carrying out the invention]

[0025] Monitoring patients during surgery by recording waveforms or signals in response to stimuli delivered to them allows for the early identification and prevention of impending injuries, such as nerve damage. These waveforms may be generated by the patient in response to nerve stimulation, such as in peripheral nerves or other parts of the patient's nervous system.

[0026] Monitoring and identifying patient physiological responses within recorded waveforms can be difficult due to the small size of these responses, such as evoked potentials, and the large amount of continuous noise or artificial signals. This makes it difficult to recognize physiological responses and determine when to issue alarms, especially in the stressful environment of surgery. While some systems generate alarms automatically, considerable noise and fluctuations can cause false alarms. For example, the generated signals may be pre-processed and / or noise may not be accurately measured or accounted for. In other systems, highly trained technicians, such as those trained under the supervision of a physician, may monitor patients during surgery using sophisticated multi-channel amplifiers and displays. Such personnel and equipment are costly, have limited availability, or may require prior booking. Personnel may also subjectively analyze waveforms under stressful conditions, which can reduce the accuracy, speed, and efficiency of physiological response detection, potentially leading to increased injury to patients during surgery. Subjective real-time monitoring of signals can lead to false alarms and / or inaccurate identification of a patient's physiological response, potentially increasing the risk of injury to the patient during surgery.

[0027] The stimulation systems described herein can accurately and automatically detect and / or identify a patient's physiological responses, such as electrophysical evoked potentials. The stimulation systems described herein may accurately detect a patient's physiological responses, for example, by comparing a subset of recorded waveforms with model waveforms generated by the system and stored in a database of model waveforms. Thus, the stimulation systems described herein may automatically and more accurately identify a patient's physiological responses in real time from recorded waveforms that also include unwanted artificial phenomena and noise signals. In some embodiments, the stimulation system may detect physiological responses without a technician or another staff member monitoring the recorded signals or subjectively evaluating the recorded waveforms in real time. Therefore, the stimulation systems described herein may reduce misinterpretation of signals during surgery, reduce the risk of causing injury to the patient, and reduce errors in the evaluation of recorded waveforms caused by noise or artificial phenomena signals. The stimulation systems described herein may be implemented as part of and / or in combination with a response identification device. The stimulation systems described herein, when used additionally and / or as an alternative during any surgery or in situations where the patient is in a critical condition, may detect and / or identify the patient's physiological response, and indicate whether or not a physiological response has been found, thereby improving positioning effects or other nerve damage or abnormalities.

[0028] As described above, electrical noise interference or artificial phenomena signals that may arise from electrical noise generators such as power cables, patient warming devices, and other electronic surgical instruments, electrode placement, patient movement, etc., can significantly alter the electrical waveforms recorded during surgery. Since recorded physiological response signals of the patient, such as evoked potentials, may be particularly small, even a few abnormal waveforms greatly affected by noise can significantly alter the apparent amplitude (height) or latency (onset time) of the waveform in question. In some cases, noise or artificial phenomena signals may be prevented at least partially by carefully selecting the stimulation frequency and filtering the waveform. For example, such methods may function in several ways, such as (1) by limiting the frequency range of the recorded waveform, (2) by rejecting recording periods in which high-amplitude signals containing clear artificial phenomena exist, and (3) by expanding the number of averages included in the averaged signal. However, standard filters that limit the frequency range of recordings (e.g., frequency filters, rejection threshold filters, etc.), or waveform classifiers that remove raw recordings exceeding a specific amplitude threshold, may fail to adequately remove noise or artificial signals from evoked potential recordings, resulting in inaccurate detection of physiological responses. Furthermore, these methods may be insufficient because physiological responses may fall within the frequency range of the noise, and the noise frequency may change. As a result, noise signals can make it difficult for even highly trained and skilled technicians to interpret waveforms recorded during surgery, leading to misassessments and misidentifications of physiological responses, and ultimately, harm to the patient.

[0029] The stimulation system described herein can accurately detect physiological responses, for example, by comparing a subset of recorded waveforms with model waveforms generated by the system and stored in a database of model waveforms. Thus, the system can automatically and more accurately identify physiological responses in real time from waveforms that include unwanted artificial phenomena signals and noise signals, without significantly altering the characteristics of the recorded waveforms. As an addition and / or alternative, the stimulation system described herein issues alarms regarding the identification of consistent and accurate physiological responses. Such a configuration allows for automated determination of alarms, and / or more accurate automated prediction and indication of alarms. Therefore, the system described herein can identify physiological responses and generate alarms without being affected by the subjective analysis of the technician during surgery, and by fluctuating noise and bias, while minimizing or eliminating false negative and false positive errors.

[0030] As described herein, a stimulation system may identify one or more patient physiological responses from recorded waveforms. These physiological responses may include, among others, one or more evoked potentials (EPs), such as somatosensory evoked potentials (SSEPs), auditory evoked potentials (AERs), motor evoked potentials (MEPs), brainstem auditory evoked potentials (BAEPs), and / or visual evoked potentials (VERs). SSEPs may include electrical signals generated by the patient's nervous system in response to electrical stimulation applied to the patient's peripheral nerves. EPs may include any potentials recorded from the nervous system as a result of stimulation applied to a part of the patient's body. For example, EPs may include voltage-versus-time signals obtained by harmonically averaging the electrophysiological responses to repeated stimulation of a particular sensory nervous system, detected using appropriate electrodes.

[0031] Figure 1 shows a system diagram illustrating a stimulation system 100 according to several exemplary embodiments. Referring to Figure 1, the stimulation system 100 may include a display 54, a client device 99, an identification controller 102, and / or a database 125. In some exemplary embodiments, the display 54, the client device 99, the identification controller 102, and / or the database 125 may form part of a response identification device 101 and / or be located within the housing of the response identification device 101.

[0032] Referring to Figure 1, the response identification device 101, the display 54, the client device 99, the identification controller 102, and / or the database 125 may be connected communicably via a network 150 as described herein and / or via direct inter-device connections. The network 150 may be a wired and / or wireless network including, for example, a public land mobile network (PLMN), a local area network (LAN), a virtual local area network (VLAN), a wide area network (WAN), the Internet, a short-range wireless connection such as Bluetooth, a peer-to-peer mesh network, etc.

[0033] The client device 99 may be a mobile device such as a smartphone, tablet computer, or wearable device. However, it should be understood that the client device 99 may be any processor-based device, including, for example, a desktop computer, laptop or mobile computer, or workstation. For example, via the client device 99, a clinician may configure specific parameters of the response identification device 101, such as a stimulus sequence or stimulus intensity, or a response recording procedure. In some implementations, the client device 99 forms part of the response identification device 101. In addition, in some examples, the user may configure various stimuli or procedures via the client device 99.

[0034] Referring to Figure 2, the stimulation system 100 may include a response identification device 101, one or more recording electrodes 110 and / or one or more stimulating electrodes 120 coupled to the patient 10, and a display 54.

[0035] The stimulating electrode 120 may be positioned on or near the patient's arm or leg, above peripheral nerve structures such as the ulnar nerve, median nerve, peroneal nerve, saphenous nerve, and / or posterior tibial nerve. The stimulating electrode 120 may also be positioned on or near the ulnar nerve and posterior tibial nerve by placing it on the patient's skin at the wrist and / or ankle. These configurations enable complete patient monitoring of peripheral nerves, such as monitoring nerves in all of the patient's limbs. In some embodiments, the stimulation system 100 may be used for upper limb monitoring. In such embodiments, the stimulating electrode 120 may be positioned on the patient's wrist, for example, above or near the ulnar nerve.

[0036] The recording electrodes 110 may be positioned on the torso, spine, neck, and / or head of the patient 10. The recording electrodes 110 are intended to be positioned on the patient 10, on the cervical vertebra 5 (C5) just below the hairline, on the forehead, midway between the left and right sternocleidomastoid muscles near the clavicle, and / or on the skin above or just above the left and right popliteal fossae just above the knees.

[0037] As shown in Figure 2, the response identification device 101 may be coupled to the recording electrode 110 and the stimulation electrode 120 via a plurality of cables 130, etc. The response identification device 101 may also be electrically, electronically, and / or mechanically coupled to the display 52 via a link 150, etc. The link 150 may include internal wiring and / or external cables. In some embodiments, the link 150 is a wireless communication link. For example, the response identification device 101 may be wirelessly connected to the display 52 via Bluetooth® or another radio frequency signal, or via short-range wireless communication or a cellular signal.

[0038] The response identification device 101 can apply electrical stimulation to the peripheral nerves of a patient by sending electrical signals to stimulating electrodes 120 located on part or all of the patient's limbs. Repeated stimulation induces a response in the patient's nervous system in the form of a physiological response such as an epiphysical puncture (EP), which travels up the peripheral nerves, through the posterior column of the spinal cord, and to the brain. The EP can be detected, and changes in the monitored EP may indicate changes in nerve function. For example, the recording electrode 110 may receive one or more obtained electrical waveforms in response to the stimulation delivered to the patient 10 via the stimulating electrode 120. The response identification device 101 may detect changes in the EP, such as changes in latency, amplitude, or morphology. Based on the observed changes, the response identification device 101 may identify potential injuries caused by the physical location of the patient's body, the stimulation being delivered to the patient, etc. In some embodiments, the response identification device 101 identifies specific nerve structures or body regions affected by the positioning effect or stimulation based on the EP. The reaction identification device 101 may, as an addition and / or alternative, improve damage by recommending a change of position via a display 54 or the like.

[0039] As described above, the stimulation system 100 may include one or more stimulation electrodes 120. The response identification device 101 may continuously stimulate the peripheral nerves of the patient 10 via the stimulation electrodes 120 while recording the EP via the recording electrodes 110. Thus, in some embodiments, the stimulation electrodes 120 are coupled to the response identification device 101 as an output, and the recording electrodes 110 are coupled to the response identification device 101 as an input.

[0040] The response identification device 101 can control stimuli and process feedback signals by including various circuit components such as an electrical stimulator, a preamplifier, an amplifier, and / or other components. In some embodiments, the response identification device 101 may average responses to several stimuli together to reduce noise in the signal.

[0041] As described herein, the response identification device 101 may analyze signals via the response identification controller 102, etc., to determine when a warning and / or alarm are appropriate. For example, the response identification device 101 may display a warning and / or alarm by sending a signal to the display 54 when a stimulus is approaching a patient's nerve.

[0042] The display 54 may form part of the reaction identification device 101 and / or the client device 99, and / or may be separately coupled to the reaction identification device 101 and / or the client device 99. The display 54 may also include a user interface. The user interface may form part of the display screen of the display 54 that presents information to a user (e.g., a clinician, patient, technician, etc.), and / or the user interface may be separate from the display screen. For example, the user interface may include one or more buttons, or a portion of the display screen configured to receive input from the user.

[0043] The display 54 may display various information such as patient history information, recommended electrode placement, stimulation parameters, stimulation and recorded areas, baseline and current signal traces, historical signal trends, associated signal changes, location of signal changes, quality of recorded signals, electrode placement, alarms due to significant signal changes, suggested movements to mitigate harmful signal changes, and recorded obtained electrical waveforms. The display 54 may allow the operator to set an initial monitoring layout and interact with the display 54 during monitoring to add additional information, view information in different formats, and / or respond to alarms. In some embodiments, the display 54 allows an anesthesiologist or other medical staff member to ignore signal changes, for example, if the signal changes are related to changes in anesthetic dosage or some other event unrelated to stimulation of the patient's nerves.

[0044] Figure 3 shows an example of a display 54 consistent with the embodiments of this subject. In some embodiments, the stimulation system 100 facilitates the setup of the stimulation procedure by clinicians and / or non-experts by providing visual cues and instructions during the setup process. For example, as shown in Figure 3, the display 54 may display pictorial instructions on where to place stimulation electrodes and / or recording electrodes, such as stimulation electrodes 120 and / or recording electrodes 110, on the patient's body. Such images may appear when the response identification device 101 is activated, indicating that monitoring of a new patient has begun or when it receives a signal that a cable has been connected to the response identification device 101. In Figure 3, each circle represents a recommended position for the electrode.

[0045] In general, the display 54 (e.g., a dynamic display) also improves how the client device 99 and / or the response identification device 101 display information and interact with the user. By dynamically generating values ​​based on input, the client device 99 and / or the response identification device 101 can reduce the need to render additional complex data input elements to complete programming. For example, the graphical user interface presented by the display 54 may include graphical elements for increasing or decreasing the values ​​of displayed parameters, rather than presenting a full keypad for data input. The client device 99 and / or the response identification device 101 can process and verify these input signals, which may be more than input from free-form text or numeric data input fields, more efficiently. The use of smaller input elements also saves display area on the client device 99 and / or the response identification device 101. This allows for the presentation of more programming parameters during data input, thereby further reducing the possibility of programming errors.

[0046] Figures 4-9 show examples of displays 54 according to embodiments of this subject. As shown in Figure 4, waveforms received by the recording electrode 110 may be presented via the display 54. As an addition and / or alternative, Figures 5 and 6 show examples of displays 54 presenting historical records. For example, the provided history spans specific durations, such as 10 minutes, 15 minutes, 30 minutes, 60 minutes, or 2 hours for surgical procedures. Trends may become visible based on the historical records shown by the display 54. For example, an increase in signal latency is seen in the waveform shown by the display 54 in Figure 5, and a decrease in amplitude is seen in the waveform shown by the display 54 in Figure 6. As an addition and / or alternative, the display 54 displays a real-time summary of the acquired data in pictorial form. For example, as shown in Figure 7, the display 54 uses color and / or pictures to indicate whether the signal received from a particular limb or body part is good, bad, indeterminate / boundary, or unreliable. In some embodiments, the system 100 identifies impending peripheral nerve injury by automatically determining whether the signal is good, bad, uncertain / borderline, or unreliable, without real-time monitoring by users such as anesthesiologists or nurses.

[0047] Figures 8 and 9 also show examples of displays 54 according to embodiments of the subject. For example, in Figure 8, the display 54 displays an exemplary waveform having a positive physiological response. In this example, the waveform is positively labeled when it contains a patient's physiological response. As shown in Figure 8, the recorded waveform has an amplitude (A 21 , A 23 This includes changes in ) and latency (T1, T2, T3). In Figure 9, display 54 displays an exemplary waveform that is negatively labeled. In other words, the exemplary waveform displayed by display 54 in Figure 9 does not include the patient's physiological response.

[0048] Referring back to Figure 1, the database 125 may include one or more databases that provide physical data storage within a dedicated facility and / or are stored locally on the reaction identification device 101 and / or client device 99. Additionally and / or alternatively, the database 125 may include a cloud-based system that provides remote data storage, for example, within a multi-tenant computing environment. The database 125 may also include non-temporary computer-readable media. The database 125 may store data recorded from and / or calculated from waveforms recorded by the recording electrode 110 and / or received by the reaction identification device 101. Additionally and / or alternatively, the database 125 may store one or more predicted physiological response or waveform models generated by the identification controller 102, as described herein.

[0049] The database 125 includes and / or may be coupled to a server 126, which may be a server connected to a network, cloud server, etc. The response identification device 101 and / or client device 99 may communicate wirelessly with the server 126. The server 126, which may include a cloud-based server, may implement one or more features of the stimulation system 100 consistent with the embodiment of this subject by providing and / or receiving data and / or commands from the data system 125 to the response identification device 101 and / or client device 99. As an addition and / or alternative, the server 126 may receive data from the response identification device 101 and / or client device 99 (e.g., one or more waveform signals, patient information, information characterizing one or more waveform signals, etc.).

[0050] The identification controller 102 may be at least partially incorporated into and / or implemented within the response identification device 101 and / or the client device 99. The controller 102 may help prevent or reduce the risk of nerve damage to the patient during surgery by detecting and identifying the patient's physiological response based on recorded waveforms.

[0051] Figure 10 shows a flowchart illustrating a method 1000 for identifying and labeling a patient's physiological responses, according to an embodiment of this subject. During surgery or another procedure performed on the patient, the identification controller 102 may cause one or more of the stimulating electrodes 120 to stimulate one or more nerves of the patient, such as the tibia (e.g., posterior tibial nerve), saphenous nerve, or ulnar nerve. In some embodiments, the identification controller 102 causes one or more of the stimulating electrodes 120 to stimulate the patient's nerves during surgery, such as during lumbar spine surgery.

[0052] In 1002, the identification controller 102 may record multiple obtained electrical waveforms, such as multiple time-locked obtained electrical waveforms, via one or more of the recording electrodes 110. For example, the recording electrode 110 may record 1, 2, 3, 4, 5, 6, 7, 8, 9, or 10 or more electrical waveforms obtained in response to the delivered electrical stimulus. In some embodiments, the recording electrode 110 continuously detects and / or records electrical waveforms at set time intervals (e.g., every second, every 15 seconds, every 30 seconds, every minute, every 5 minutes, every 15 minutes, every 30 minutes, and / or every other range including ranges in between) after each stimulus has been delivered to a patient or the like.

[0053] Based on the multiple obtained electrical waveforms, the identification controller 102 may determine whether at least a subset of the multiple obtained electrical waveforms includes the patient's physical response. Determining whether at least a subset of the multiple obtained electrical waveforms includes the patient's physiological response may help detect whether the surgeon or surgical instrument is approaching the patient's nerves and may help mitigate or prevent injuries to the patient during surgery, such as patient positional impairment. The subset of multiple obtained electrical waveforms may include at least two electrical waveforms from multiple recorded obtained electrical waveforms. In some embodiments, the subset of multiple obtained electrical waveforms includes at least two consecutive and / or discontinuous obtained electrical waveforms. In some embodiments, the subset of multiple obtained electrical waveforms includes at least three, four, five, six, seven, eight, nine, or ten or more electrical waveforms from multiple recorded electrical waveforms.

[0054] To determine whether at least a subset of the obtained electrical waveforms contains the patient's physiological response, the identification controller 102 may compare a subset of the obtained electrical waveforms with model waveforms that can be stored in a database of multiple model waveforms. The subset of obtained electrical waveforms may be averaged and then compared with the model waveforms, and / or each obtained electrical waveform in the subset may be compared individually with the model waveforms. Based on this comparison, the identification controller 102 may determine comparison features that indicate whether the patient's physiological response is present in the subset of obtained electrical waveforms.

[0055] In some embodiments, the identification controller 102 includes a predicted response model 106 and / or a classification machine learning model 104. In 1008, the predicted response model 106 may generate a model waveform. The model waveform may include and / or be defined by a harmonic mean of a predicted physiological response and a plurality of artificial phenomena or noise signals. By comparing the model waveform with a subset of obtained electrical waveforms (e.g., automatically), it is possible to accurately, quickly, and efficiently identify whether a patient's physiological response is present within the subset of obtained electrical waveforms. As described above, the model waveforms may be stored in a database 125. In some embodiments, the database 125 stores multiple model waveforms. Each of the multiple model waveforms may be generated by the identification controller 102, for comparison with a subset of obtained electrical waveforms, such as the predicted response model 106.

[0056] Model waveforms may be generated by a predicted response model 106 based on non-patient and / or non-treatment data. In other words, model waveforms may be generated based on data such as clinical data and / or previously acquired data from prior to the current treatment being performed on the patient and / or from previous treatments in that patient or another patient.

[0057] The predicted response model 106 may be defined using an integrated fast orthogonal search method. In another embodiment, the predicted response model 106 may be defined by using, among other things, a fast orthogonal search method and / or another method such as supervised machine learning topology. The predicted response model 106 may also be defined using clinical data collected from previous surgeries, such as previous lumbar spine surgery, performed on a patient, and such patients include the patient undergoing the current surgery and / or another patient undergoing a different surgery. The clinical data may include one or more obtained electrical waveforms from one or more nerves of the patient (e.g., the saphenous nerve, the posterior tibial nerve, etc.) and / or one or more corresponding parameters such as latency, amplitude, quality factor, offset latency, and whether or not a physiological response of the patient was present. In some embodiments, an expert may characterize and / or annotate each obtained electrical waveform collected as part of the clinical data. For example, an expert may characterize and / or annotate each obtained electrical waveform by indicating the ideal placement of markers for the start and peak points.

[0058] As shown in Figures 1004 and 1006, and in Figure 12, the predicted response model 106 incorporates one or more physiological templates 112 and one or more noise candidates 114. Figure 11 shows an exemplary method 1100 for generating one or more physiological templates 112 according to an embodiment of the subject. In some embodiments, the identification controller 102 may generate one or more physiological templates 112 using characterized and / or annotated clinical data. In doing so, the identification controller 102 may identify the minimum number of templates that can represent all positively labeled physiological responses (e.g., the resulting electrical waveforms labeled as containing the patient's physiological response). The physiological templates 112 may form a pool of physiological response candidates (e.g., one or more inputs) for use when the predicted response model 106 generates the model waveform 116 via an integrated fast orthogonal search method.

[0059] In some embodiments, in 1102, the identification controller 102 may receive clinical data, including the obtained electrical waveforms, in order to create a physiological template. In 1104, the identification controller 102 may extract one or more patterns from the obtained electrical waveforms. For example, samples before and after the physiological response from each obtained electrical waveform are removed so that only the morphology of interest (e.g., pattern) remains. In 1106, the patterns are clustered into groups of similar morphologies using k-means. The pattern with the minimum Euclidean distance to the centroid of each cluster is selected to become the physiological template 112. Each physiological template 112 can be shifted within a wide range of latencies to create a candidate pool for use in generating the model waveform 116. The candidate pool may represent a large population of the obtained electrical waveforms. In some embodiments, k=8 in k-means provides a desirable balance between obtaining a unique and diverse set of morphologies for the candidate pool and reducing computational processing requirements. In another embodiment, k = 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, or more. In 1108, the physiological template 112 is generated as output.

[0060] As described above, the predicted response model 106 may be defined using an integrated fast orthogonal search method. The integrated fast orthogonal search method is an extension of the fast orthogonal search method. In some cases, the fast orthogonal search method may be used to generate the predicted response model 106, but the integrated fast orthogonal search method may take into account one or more noise candidates 114, such as a pool of noise and / or anthropogenic signals, when generating a waveform model (e.g., a predicted physiological response), which the fast orthogonal search method may not take into account. Thus, the integrated fast orthogonal search method may generate a more accurate and time-reproducible waveform model because it incorporates noise generated by major noise sources as described herein. One or more noise candidates 114 may be generated by incorporating a combination of 60, 120, and / or 180 Hz harmonic noise and / or by adding white noise of a desired signal-to-noise ratio.

[0061] As an addition and / or alternative, the integrated fast orthogonal search method can minimize errors in predicted responses across multiple waveforms simultaneously, rather than just one waveform (as used in the fast orthogonal search method). This configuration also improves the accuracy and reproducibility of the generated waveform model. As shown in Figure 12, using the integrated fast orthogonal search method, the predicted response model 106 may take one or more inputs, such as physiological candidates 112 and noise candidates 114, and output one or more model waveforms 116 corresponding to one or more of the following equations, where the equations represent the following multiple waveform models that can be compared with the obtained electrical waveforms or a subset of the obtained electrical waveforms to determine whether the patient's physiological response lies within a subset of multiple obtained electrical waveforms:

number

number

number

number

[0062] Referring to Figure 10, in 1010, the identification controller 102 may compare a subset of the obtained electrical waveforms with a model waveform. The identification controller 102 may, in addition and / or alternative, determine one or more comparison features based on the comparison. One or more comparison features may indicate whether the patient's physiological response is present in the subset of the obtained electrical waveforms. In addition and / or alternative, the comparison features may indicate whether artificial phenomena signals or noise signals are present in the subset of the obtained electrical waveforms, and / or whether a portion of the subset of the obtained electrical waveforms contains the patient's physiological response and / or artificial phenomena signals.

[0063] In some embodiments, one or more comparison features may include one or more of the following: the mean squared error between the obtained subset of electrical waveforms and the model waveform; the correlation between the obtained subset of electrical waveforms and the model waveform; the amplitude of the physiological coefficients; the power of the fundamental harmonic noise; the THP of the harmonic noise; the ratio of the physiological coefficients of the obtained subset of electrical waveforms to the power of the harmonic noise; and the variance ratio of the patient's physiological response to the model's predicted physiological response to the obtained subset of electrical waveforms. In some embodiments, the comparison features may, in addition to and / or as an alternative, represent a comparison between the morphology of the obtained subset of electrical waveforms and the morphology of the model waveform.

[0064] As described above, the comparison features may include the mean squared error between the obtained subset of electrical waveforms and the model waveform. A small mean squared error indicates that the obtained subset of electrical waveforms is likely to include the patient's physiological response. A small mean squared error may, for example, include a mean squared error close to zero for at least two identical waveforms. A large mean squared error indicates that the obtained subset of electrical waveforms is unlikely to include the patient's physiological response. A large mean squared error may include a mean squared error approaching infinity for at least two different waveforms (for example, indicating that at least two waveforms are infinitely different).

[0065] In some embodiments, one or more comparison features include the variance ratio of the patient's physiological response to a subset of obtained electrical waveforms relative to the waveform model's predicted physiological response. A low variance ratio indicates a high probability that the subset of obtained electrical waveforms contains the patient's physiological response. A low variance ratio may, for example, include a variance ratio close to zero for at least two identical waveforms. A high variance ratio indicates a low probability that the subset of obtained electrical waveforms contains the patient's physiological response. A high variance ratio may include a variance ratio close to infinity for at least two different waveforms (for example, indicating that at least two waveforms are infinitely different).

[0066] In some embodiments, one or more comparison features include the polarity of each electrical waveform in the obtained subset of electrical waveforms. In some embodiments, if each electrical waveform in the obtained subset of electrical waveforms has the same polarity (e.g., positive or negative), the identification controller 102 may indicate that the obtained subset of electrical waveforms is likely to contain a patient's physiological response. In some embodiments, if at least one of the electrical waveforms in the obtained subset of electrical waveforms has a different polarity (e.g., positive or negative) from another electrical waveform in the subset, the identification controller 102 may indicate that the obtained subset of electrical waveforms is unlikely to contain a patient's physiological response.

[0067] In some embodiments, the identification controller 102 determines that a patient's physiological response is present or likely to be present if the comparison features of a subset of electrical waveforms fall within a threshold range of the comparison feature threshold. The threshold range may be approximately 1 to 5%, 5 to 10%, 10 to 20%, 20 to 30%, and / or other ranges.

[0068] Referring again to Figure 10, in 1014, the identification controller 102 may classify or label the obtained subset of electrical waveforms with positive or negative labels based on the comparison features. In addition and / or alternative, the classification may be based on a mathematical representation of the comparison features and / or on a comparison between the comparison features and one or more previously generated comparison features. A positive label may indicate that the patient's physiological response is present in the obtained subset of electrical waveforms, while a negative label may indicate that the patient's physiological response is not present in the obtained subset of electrical waveforms.

[0069] In 1012, the discrimination controller 102 may classify or label the obtained subset of electrical waveforms using a classification machine learning model 104 (also referred to herein as the “Classification ML Model 104”). The Classification ML Model 104 may include a support vector machine (“SVM”) learning model trained for the purpose of predicting whether to assign positive and / or negative labels to the obtained subset of electrical waveforms. The classification or labeling may be determined based on comparative features. As described above, a positive label for the obtained subset of electrical waveforms indicates that a patient’s physiological response is present or likely to be present within that subset, while a negative label for the obtained subset of electrical waveforms indicates that a patient’s physiological response is not present or likely to be present within that subset.

[0070] In some embodiments, the classification ML model 104 may be trained using training data. The training data may include features (e.g., physiological responses, model errors, correlations, and / or other parameters) extracted from model waveforms generated by a predicted response model 106 based on simulated baseline waveforms and physiological templates 112. The simulated baseline waveforms may be generated by receiving and / or accessing physiological templates 112. Based on the accessed physiological templates 112, the discrimination controller 102 may add variance to one or more physiological templates 112 by extending or compressing response initiation to offset the time to a desired period, shifting the template peak to a time within the analysis range, adding a combination of harmonic noise, and / or adding white noise at a desired signal-to-noise ratio. This process may be repeated to create a set of simulated baseline waveforms (e.g., 1, 2, 3, 4, 5, or more sets) for use in training the classification ML model 104. These simulated baseline waveforms have known labels that form at least one portion of the training data used to train the classification ML model 104. Once the classification ML model 104 is trained, the trained classification ML model 104 may, in 1016, indicate whether a patient's physiological response is present or likely to be present within the subset of the obtained electrical waveforms by classifying or labeling at least a subset of the obtained electrical waveforms with positive or negative labels.

[0071] In some embodiments, the identification controller 102 may cause the display 54 to display an indication that the patient's physiological response is present in the obtained subset of electrical waveforms, for example, when the classification ML model 104 labels the obtained subset of electrical waveforms with a positive label, and the display 54 may display this indication. As an addition and / or alternative, the identification controller 102 may cause the display 54 to display an indication that the patient's physiological response is not present in the obtained subset of electrical waveforms, or that only artificial phenomenon signals or noise signals are present in the obtained subset of electrical waveforms, for example, when the classification ML model 104 labels the obtained subset of electrical waveforms with a negative label, or the display 54 may display this indication. Thus, by automatically, accurately, and effectively identifying and determining whether the recorded waveforms contain the patient's physiological response, the stimulation system 100 can help reduce or eliminate the risk of causing injury to the patient during surgery or another procedure.

[0072] In some embodiments, methods for performing surgery or other procedures as described herein include, among other things, performing robot-assisted surgical procedures such as robot-assisted hysterectomy, other gynecological surgery, prostatectomy, urological surgery, general laparoscopic surgery, thoracoscopic surgery, valve replacement, other cardiac surgery, bariatric surgery, other gastrointestinal surgery, or tumor surgery. Methods in some embodiments further include delivering electrical stimulation to peripheral nerves in the body, recording the resulting electrical waveforms generated by the body's nervous system in response to the electrical stimulation, and monitoring the resulting electrical waveforms to detect changes indicating potential nerve damage. As an addition or alternative, in some embodiments, methods for performing surgery may include any of the methods for detecting the function of one or more nerves described elsewhere herein. Methods for detecting the function of one or more nerves or using the response identification device 101 may be incorporated into any connection of robotic surgery. For example, such methods may be performed only multiple times in a series in pre-selected circumstances (including any of the above), such as when a particular type of procedure is initiated or terminated. The methods of various embodiments further include adjusting the patient's position when potential nerve damage or abnormalities are detected.

[0073] Figure 13 shows a method 1300 for identifying and labeling a patient's physiological response, according to an embodiment of this subject.

[0074] In 1302, the system (e.g., via the identification controller 102) may stimulate one or more nerves of the patient via stimulating electrodes coupled to the patient. For example, the system may stimulate the patient's tibial nerve (e.g., posterior tibial nerve), saphenous nerve, ulnar nerve, etc., during surgery or another procedure. The stimulating electrodes may include one or more electrodes that communicate with a response identification device (e.g., response identification device 101) configured to monitor one or more nerves of the patient. In some embodiments, the stimulation is delivered to the patient continuously at various time intervals according to a stimulation procedure, etc. The stimulation may include the transmission of multiple electrical stimuli.

[0075] In 1304, the system may record multiple obtained electrical waveforms via recording electrodes coupled to the patient, such as via the identification controller 102. The multiple obtained electrical waveforms may include 1, 2, 3, 4, 5, or more obtained electrical waveforms. The multiple obtained electrical waveforms may be received by a response identification device. The obtained electrical waveforms may be generated by the patient in response to delivered electrical stimuli.

[0076] In 1306, the system may determine whether at least one subset of multiple obtained electrical waveforms includes a physiological response. This determination may help prevent injury to the patient during surgery or another procedure. For example, in 1308, a subset of obtained electrical waveforms from multiple obtained electrical waveforms may be compared with model waveforms from a database of multiple model waveforms. The model waveforms may include the harmonic mean of the predicted physiological response and multiple anthropogenic or noise signals. The model waveforms may be generated using an integrated high-speed orthogonal search method that incorporates both a physiological template (e.g., a predicted physiological response) and candidate anthropogenic or noise (e.g., by a predicted response model 106), as described herein.

[0077] As described herein, multiple model waveforms may be generated based on clinical data including non-treatment or non-patient information. In other words, multiple template waveforms stored in the database may be generated based on treatments and / or information collected from patients that are not currently being treated or from patients. The database may also store clinical data and / or be loaded with clinical data collected before the current surgery, which is not based on the surgery the patient is currently undergoing.

[0078] In 1310, the comparison features may be determined based on a comparison. The comparison features may indicate whether or not a patient's physiological response is present in the subset of the obtained electrical waveforms. The comparison features may, in addition and / or alternatively, indicate whether or not the subset of the obtained electrical waveforms contains only artificial phenomenon signals or noise signals. In some embodiments, one or more comparison features may include one or more of the following: the mean squared error between the subset of the obtained electrical waveforms and the model waveform; the correlation between the subset of the obtained electrical waveforms and the model waveform; the amplitude of the physiological coefficients; the power of the fundamental harmonic noise; the THP of the harmonic noise; the ratio of the physiological coefficients of the subset of the obtained electrical waveforms to the power of the harmonic noise; and the variance ratio of the patient's physiological response in the subset of the obtained electrical waveforms to the predicted physiological response of the model. In addition and / or alternatively, the comparison features may represent a comparison of the morphology of the subset of the obtained electrical waveforms to the morphology of the model waveform. The comparison features may include multiple comparison features.

[0079] In 1312, the obtained subset of electrical waveforms may be labeled as positive or negative, based at least on comparative features. A positive label indicates that the patient's physiological response is present or likely to be present within the subset of recorded electrical waveforms. A negative label indicates that the patient's physiological response is not present or likely to be present within the subset of recorded electrical waveforms. Labeling and / or classification of the obtained subset of electrical waveforms may be performed by a machine learning model (e.g., a support vector machine learning model), such as the trained classification ML model 104 described herein.

[0080] In 1314, an indication that a physiological response is present within a subset of the obtained electrical waveforms may be displayed on a display (e.g., display 54). The display may be coupled to a response identification device 101. The indication may include one or more alarms, such as one or more audible, visual, and / or tactile alarms or signals. This indication may indicate that the surgeon is approaching the patient's nerves. In some embodiments, the indication may, in addition and / or alternative thereto, indicate that the subset of the obtained electrical waveforms does not contain a physiological response or contains only noise or artificial phenomenon signals. Thus, the stimulation system 100 may help reduce or eliminate the risk of causing injury to the patient during surgery or another procedure by automatically, accurately, and effectively identifying and determining whether the recorded waveforms contain the patient's physiological response.

[0081] Figure 14 is a block diagram showing a computing system 500 according to an embodiment of the subject. Referring to Figures 1 and 14, the computing system 500 may be used to implement the stimulation system 100 and / or any other components therein.

[0082] As shown in Figure 14, the computing system 500 may include a processor 510, memory 520, storage device 530, and input / output device 540. The processor 510, memory 520, storage device 530, and input / output device 540 may be interconnected via a system bus 550. The processor 510 may process instructions for execution within the computing system 500. Such instructions for execution may implement, for example, one or more components of the configuration engine 110. In some exemplary embodiments, the processor 510 may be a single-threaded processor. Alternatively, the processor 510 may be a multi-threaded processor. The processor 510 may process instructions stored in memory 520 and / or storage device 530 to present graphic information for a user interface provided via the input / output device 540.

[0083] Memory 520 is a computer-readable medium, such as a volatile or non-volatile medium, that stores information within the computing system 500. Memory 520 may store, for example, a data structure representing a configuration object database. Storage device 530 may provide persistent storage for the computing system 500. Storage device 530 may be a floppy disk device, a hard disk device, an optical disk device, a tape device, or another suitable persistent storage means. Input / output device 540 provides input / output operations to the computing system 500. In some exemplary embodiments, the input / output device 540 includes a keyboard and / or a pointing device. In various embodiments, the input / output device 540 includes a display unit for displaying a graphical user interface.

[0084] According to some exemplary embodiments, the input / output device 540 may provide input / output operation to a network device. For example, the input / output device 540 may include an Ethernet port or another networking port for communicating with one or more wired and / or wireless networks (e.g., a local area network (LAN), a wide area network (WAN), the Internet).

[0085] In some exemplary embodiments, the computing system 500 may be used to run various interactive computer software applications that can be used to organize, analyze, and / or store data in various formats. Alternatively, the computer system 500 may be used to run software applications. These applications may be used to perform various functions, such as planning functions (e.g., generating, managing, and editing spreadsheet documents, word processor documents, and / or any other objects), computing functions, communication functions, etc. The applications may include various add-in functions or standalone computing products and / or functions. When activated within an application, these functions may be used to generate a user interface provided via the input / output device 540. The user interface may be generated by the computing system 500 (e.g., on a computer screen monitor) and presented to the user.

[0086] One or more aspects or features of the subject matter described herein may be realized in digital electronic circuits, integrated circuits, specially designed ASICs, field-programmable gate array (FPGA) computer hardware, firmware, software, and / or combinations thereof. These various aspects or features may include embodiments in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, the programmable processor may be dedicated or general-purpose and may be coupled to receive data and instructions from a storage system, at least one input device, and at least one output device, and to transmit data and instructions to them. The programmable system or computing system may include clients and servers. The clients and servers are geographically separated from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on each computer that have a client-server relationship with each other.

[0087] These computer programs, also called programs, software, software applications, applications, components, or code, may also contain machine instructions for programmable processors and may be implemented in high-level procedural and / or object-oriented programming languages ​​and / or assembly / machine language. As used herein, the term “machine-readable medium” means any computer program product, apparatus, and / or device, such as magnetic disks, optical disks, memory, and programmable logic devices (PLDs), which are used to provide machine instructions and / or data to programmable processors and include machine-readable mediums that receive machine instructions as machine-readable signals. The term “machine-readable signals” means any signals used to provide machine instructions and / or data to programmable processors. Machine-readable medium may store such machine instructions non-temporarily, which may be, for example, non-temporarily solid-state memory, magnetic hard drives, or any equivalent storage medium. Machine-readable medium may, as an alternative or addition, store such machine instructions in a temporary manner, which may be, for example, a processor cache associated with one or more physical processor cores or another random-access memory.

[0088] To provide user interaction, one or more aspects or features of the subject matter described herein may be implemented on a computer having, for example, a display device such as a cathode ray tube (CRT), liquid crystal display (LCD), or light-emitting diode (LED) monitor for displaying information to the user, one or more hardware buttons such as a mouse or trackball by which the user can provide input to the computer, a keyboard, and / or a pointing device. Other types of devices may be used to similarly provide user interaction. For example, the feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback, and input from the user may be received in any form, including acoustic, linguistic, or tactile input. Other possible input devices include touchscreens or other touch sensor devices such as single or multipoint resistive or capacitive trackpads, speech recognition hardware and software, optical scanners, optical pointers, digital image capture devices, hardware buttons, and associated interpretation software.

[0089] While the disclosures, including the figures described herein, may individually describe and / or illustrate different modifications, it should be understood that all or part of them, or their components, may be combined.

[0090] While various exemplary embodiments have been described above, any of the many modifications may be made to various embodiments. For example, the order in which various described method steps are performed may often be changed in alternative embodiments, and in other alternative embodiments, one or more method steps may be skipped as a whole. Optional features of various device and system embodiments may be included in some embodiments and not in others. Therefore, the foregoing descriptions are provided primarily for illustrative purposes and should not be construed as limiting the scope of the claims.

[0091] Where a feature or element is referred to herein as being "on top of" another feature or element, it may be directly on top of the other feature or element, or there may be intervening features and / or elements. In contrast, where a feature or element is referred to as being "directly on top of" another feature or element, there are no intervening features or elements. Also, where a feature or element is referred to as being "connected," "attached," or "joined" to another feature or element, it should be understood that it may be directly connected, attached, or joined to the other feature or element, or there may be intervening features or elements. In contrast, where a feature or element is referred to as being "directly connected," "directly attached," or "directly joined" to another feature or element, there are no intervening features or elements. Although described or illustrated in relation to one embodiment, features and elements described or illustrated in this way may also apply to other embodiments. A reference to a structure or feature positioned "adjacent to" another feature may have a portion that overlaps with or lies beneath the adjacent feature.

[0092] The terminology used herein is intended solely to describe specific embodiments and is not intended to limit them. For example, as used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, as used herein, the terms "include" and / or "contain" identify the presence of the described features, steps, actions, elements, and / or components, but will not be understood to exclude the presence or addition of one or more other features, steps, actions, elements, components, and / or groups thereof. As used herein, the terms "and / or" may be abbreviated as " / " to include combinations of some and all of one or more of the related enumerated items.

[0093] For example, spatial relative terms such as "below," "downward," "below," "above," and "on top" may be used herein to describe the relationship of one element or feature to another single or multiple element or feature, as shown in the diagram, for the sake of clarity. It should be understood that spatial relative terms are intended to include different orientations of the device in use or operation, in addition to the orientation shown in the diagram. For example, if the device in the diagram is inverted, an element described as "below" or "downward" of another element or feature will be oriented "above" of the other element or feature. Thus, the exemplary term "below" may include both up and down orientations. The device may also be in a different orientation (rotated by 90 degrees or in a different orientation), and the spatial relative descriptors used herein will be interpreted accordingly. Similarly, terms such as "above," "downward," "perpendicular to," and "horizontal" are used herein for descriptive purposes only, unless otherwise noted.

[0094] The terms “first” and “second” may be used herein to describe various features / elements (including steps), but unless the context indicates otherwise, these features / elements should not be limited by these terms. These terms may be used to distinguish one feature / element from another. Thus, without deviating from the teachings provided herein, the first feature / element discussed below may be called the second feature / element, and similarly, the second feature / element discussed below may be called the first feature / element.

[0095] Throughout this specification and the subsequent claims, unless the context requires otherwise, the words “include” and “contains,” and their variations thereof, may be used jointly in reference to methods and articles (e.g., components and apparatus including devices and methods). For example, it will be understood that the term “contains” means to include any described element or step, but not to exclude any other element or step.

[0096] As used herein and in the claims, including as used in the examples, all numbers may be read as if preceded by the words “about” or “approximately,” even if the terms do not explicitly appear. The words “about” or “approximately” may be used when describing size and / or location to indicate that the described value and / or location is within a reasonable expected range of the value and / or location. For example, a number may have a value that is + / -0.1% of the stated value (or range of value), + / -1% of the stated value (or range of value), + / -2% of the stated value (or range of value), + / -5% of the stated value (or range of value), + / -10% of the stated value (or range of value), etc. Furthermore, any number given herein is understood to include approximately or nearly that value unless the context otherwise indicates.

[0097] The examples and figures included herein are illustrative, not limiting, and illustrate specific embodiments in which the subject matter may be put into practice. As stated, other embodiments may be used and derived therefrom, and structural and logical substitutions and modifications may be made without departing from the scope of this disclosure. Although specific embodiments have been illustrated and described herein, any configuration calculated to achieve the same objective may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all adaptations or variations of various embodiments. Combinations of the embodiments described above with other embodiments not specifically described herein are possible.

[0098] In the above description and claims, a combined enumeration of elements or features may follow phrases such as "at least one" or "one or more." The term "and / or" may appear within an enumeration of two or more elements or features. Unless implicitly or explicitly contradicted by the context in which it is used, such phrases are intended to mean any of the enumerated elements or features individually, or any of the elements or features listed in combination with other enumerated elements or features. For example, the phrases "at least one of A and B," "one or more of A and B," and "A and / or B" are intended to mean "A only, B only, or A and B together," respectively. A similar interpretation is also intended for enumerations containing three or more items. For example, “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, and / or C” are intended to mean “A only, B only, C only, A and B together, A and C together, B and C together, or A, B, and C together.” The use of the term “based on” in the foregoing and in the claims is intended to mean “at least partially based,” so as to allow for features or elements that are not listed.

[0099] As used herein, “User Interface” (also known as an interactive user interface, graphic user interface, or UI) may refer to a network-based interface that includes data fields and / or other control elements for receiving input signals or providing electronic information and / or providing information to the user in response to any received input signals. Control elements may include dials, buttons, icons, selectable areas, or other perceptible indicators presented via the UI, which, when interacted with (e.g., clicked, touched, selected, etc.), initiate data exchange with the device presenting the UI. The UI may be implemented entirely or partially using technologies such as Hypertext Markup Language (HTML), FLASH®, JAVA®, .NET®, C, C++, web services, or Rich Site Summary (RSS). In some embodiments, the UI may be contained within a standalone client (e.g., a thick client, a fat client) configured to communicate (e.g., send or receive data) according to one or more of the embodiments described. Communication may take place between a medical device or a server communicating with it.

[0100] As used herein, the terms “determine” or “decide” encompass a broad range of actions. For example, “decide” may include, through hardware elements without user intervention, calculating, computing, processing, deriving, generating, obtaining, examining (e.g., examining within a table, database, or other data structure), confirming, etc. “Determine” may also include, through hardware elements without user intervention, receiving (e.g., receiving information), accessing (e.g., accessing data in memory), etc. “Determine” may also include, through hardware elements without user intervention, resolving, selecting, choosing, establishing, etc.

[0101] As used herein, the terms “provide” or “to provide” encompass a wide variety of actions. For example, “to provide” may include storing a value in a location in a storage device for subsequent retrieval, directly transmitting a value to a recipient via at least one wired or wireless communication medium, or transmitting or storing a reference to a value. “To provide” may also include encoding, decrypting, encrypting, deciphering, verifying, or inspecting via hardware elements.

[0102] As used herein, the term “message” encompasses a wide variety of formats for conveying (e.g., transmitting or receiving) information. A message may include machine-readable information sets such as XML documents, fixed-field messages, comma-separated messages, JSON, and custom protocols. In some embodiments, a message may also include signals used to transmit one or more representations of information. While listed in the singular, it should be understood that a message may consist of multiple parts, may be transmitted, may be stored, may be received, etc.

[0103] As used herein, the terms “selectively” or “selective” can encompass a wide variety of actions. For example, a “selective” process may include deciding on one option from several options. A “selective” process may include one or more dynamically determined inputs, pre-configured inputs, or user-initialized inputs for making a decision. In some embodiments, n input switches may be included to provide the selection function, where n is the number of inputs used to make the selection.

[0104] For users as defined herein, the terms “correspond” or “correspond” encompass structural, functional, quantitative, and / or qualitative correlations or relationships between two or more objects, datasets, information, etc., preferably such correspondences or relationships are used to transform one or more of the two or more objects, datasets, information, etc., so that they appear to be the same or equivalent. Correspondence relationships may be evaluated using one or more of the following: thresholds, value ranges, fuzzy logic, pattern matching, machine learning evaluation models, or a combination thereof.

[0105] In any embodiment, the generated or detected data may be transferred to a “remote” device or location, where “remote” means a location or device other than the location or device on which the program is executed. For example, a remote location could be another location within the same city (e.g., an office, laboratory, etc.), another location within a different city, another location within a different state, another location within a different country, etc. Thus, when one item is indicated as “remote” from another item, it means that the two items may be in the same room but separated, or at least in different rooms or buildings, and may be at least 1 mile, 10 miles, or at least 100 miles apart. To “communicate” information means to transmit data representing that information as electrical signals over an appropriate communication channel (e.g., a private or public network). To “transfer” an item means any means of transporting the item from one location to another, whether by physical transport or by another means (if possible), which includes, at least in the case of data, physically transporting the medium carrying the data, or communicating the data. Examples of communication media include wireless or infrared transmission channels, network connections to other computers or network devices, and the internet, or email transmissions and information recorded on websites.

[0106] The examples and figures included herein illustrate, not limiting, specific embodiments in which the subject matter may be implemented. As stated, structural and logical substitutions and modifications may be made without departing from the scope of this disclosure by utilizing and deriving from other embodiments. Such embodiments of the subject matter of the present invention may be referred to individually or collectively by the term “invention” without merely convenience, without the intention of spontaneously limiting the scope of this application to a single invention or, in fact, an inventive concept if more than one is disclosed. Thus, while a particular implementation has been illustrated and described herein, any configuration estimated to achieve the same objective may be substituted for the specific embodiment shown. This disclosure is intended to cover all applications or variations of various embodiments. Combinations of the embodiments described above, and other embodiments not specifically described herein, will be apparent to those skilled in the art by considering the above description.

Claims

1. A stimulation system for detecting and identifying a patient's physiological response, wherein the stimulation system is At least one processor, When executed by the aforementioned at least one processor, it includes at least one memory that stores instructions that result in an action, Equipped with, The aforementioned operation is, The steps of stimulating one or more nerves of the patient via stimulating electrodes attached to the patient, The steps include recording multiple obtained electrical waveforms via recording electrodes attached to the patient, A step of determining whether at least a subset of the obtained electrical waveforms includes the patient's physiological response, based on the plurality of obtained electrical waveforms. The steps include: displaying instructions via a display if the patient's physiological response is present within the subset of the obtained electrical waveforms; Includes, The aforementioned step of making a decision is, The process involves comparing a subset of the obtained electrical waveforms with model waveforms from a database of multiple model waveforms, Based on the above comparison, a comparative feature is determined that indicates whether or not the patient's physiological response is present within the subset of the obtained electrical waveforms. Includes, The aforementioned model waveform includes the harmonic mean of the predicted physiological response and multiple artificial phenomenon signals. A stimulation system characterized by the following features.

2. The aforementioned comparative features further indicate whether or not the artificial phenomenon signal is present within the subset of electrical waveforms obtained. The aforementioned artificial phenomenon signal is generated by noise. The system according to feature 1.

3. The operation further includes the step of displaying, via the display, an indication that the artificial phenomenon signal is present within the subset of the obtained electrical waveforms. The system according to claim 2.

4. The step of determining whether at least the subset of the plurality of obtained electrical waveforms includes the physiological response of the patient further includes labeling the subset of the plurality of obtained electrical waveforms with a positive or negative label based on the comparison features, The aforementioned positive label indicates the presence of a physiological response in the patient. The aforementioned negative label indicates the absence of a physiological response in the patient. The system according to any one of claims 1 to 3.

5. The determination of whether the plurality of obtained electrical waveforms include the patient's physiological response further includes determining that the patient's physiological response exists if the comparison features of a subset of the electrical waveforms fall within the threshold range of the comparison feature threshold. The system according to any one of claims 1 to 4.

6. The comparison features include one or more of the following: the mean squared error between the obtained subset of electrical waveforms and the model waveform; the correlation between the obtained subset of electrical waveforms and the model waveform; the amplitude of the physiological coefficients; the power of the fundamental harmonic noise; the THP of the harmonic noise; the ratio of the physiological coefficients of the obtained subset of electrical waveforms to the power of the harmonic noise; and the variance ratio of the patient's physiological response to the obtained subset of electrical waveforms to the predicted physiological response of the model waveform. The system according to claim 5, characterized in that it is the same as described in claim 5.

7. The determination of whether the plurality of obtained electrical waveforms include the patient's physiological response further includes determining that the patient's physiological response exists if the polarity of each electrical waveform in the subset of obtained electrical waveforms is the same. The system according to any one of claims 1 to 6.

8. The comparison feature represents a comparison of the form of the obtained subset of electrical waveforms with the form of the model waveform. The system according to any one of claims 1 to 7.

9. The aforementioned comparison feature includes multiple comparison features, The labeling is further based on the mathematical representation of the multiple comparison features. The system according to feature 4.

10. The labeling includes comparing the comparison feature with a plurality of previously generated comparison features. The system according to feature 4.

11. The subset of the multiple obtained electrical waveforms is locked with a time lock. The system according to any one of claims 1 to 10.

12. The stimulating step includes transmitting multiple electrical stimuli, The stimulating electrode communicates with an evoked potential detection device configured to monitor one or more peripheral nerves of the patient. The system according to any one of claims 1 to 11.

13. The plurality of obtained electrical waveforms are received by the evoked potential detection device, The obtained electrical waveform is generated by the patient in response to the electrical stimulation. The system according to feature 12.

Images