Automatic detection and logging of surgical stages and risk estimation during surgery

Abstract

Certain aspects of the present disclosure provide techniques for automated risk assessment during surgery on a patient. A method includes determining one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient. The method includes automatically collecting procedural data during the surgery. The method includes automatically collecting physiological data of the patient during the surgery. The method includes automatically collecting neurological response waveform data of the patient. The method includes automatically providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system. The method includes comparing, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform. The method includes assessing a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data.

Description

[0001] AUTOMATIC DETECTION AND LOGGING OF SURGICAL STAGES AND RISK ESTIMATION DURING SURGERY

[0002] CLAIM FOR PRIORITY

[0003] This application claims the benefit of and priority to U.S. Provisional App. No. 63 / 605,074 filed on December 1, 2023 and entitled, “AUTOMATIC DETECTION AND LOGGING OF SURGICAL STAGES AND RISK ESTIMATION DURING SURGERY.” The entire contents of the 63 / 605,074 application are hereby incorporated by reference.

[0004] BACKGROUND

[0005] Field of the Disclosure

[0006] Aspects of the present disclosure relate to neurophysiological monitoring, and more particularly, to techniques for monitoring of the nervous system in the operating room during surgeries where the nervous system may be at risk.

[0007] Description of Related Art

[0008] Certain surgeries, such as lumbar surgery or cervical surgery, risk damage to the patient’s nervous system. Lumbar surgery, also known as lumbar spine surgery or lower back surgery, refers to surgical procedures performed on the lumbar region of the spine. The lumbar region is the lower part of the spine, consisting of the five vertebrae (LI to L5) between the thoracic spine (upper back) and the sacrum (pelvic region). Lumbar surgery is typically considered when conservative treatments such as medication, physical therapy, and lifestyle changes have failed to alleviate severe or chronic back pain, instability, or other symptoms associated with conditions affecting the lumbar spine. Examples of lumbar surgical procedures include discectomy, spinal fusion such as lateral lumbar interbody fusion (LLIF) and transforaminal lumbar interbody fusion (TLIF), laminectomy, foraminotomy, posterior transpsoas procedures (PTP), and artificial disc replacement surgeries. In order to mitigate the risks of damage during such surgeries, it is helpful to perform neurophysiological monitoring of the motor pathways during such surgeries to detect early changes in neurological dysfunction that if left un-mitigated might lead to transient or permanent injury or dysfunction post operatively.

[0009] During surgical procedures requiring anesthesia, patients may be monitored using neurophysiological techniques or modalities which record various biological signals from the patient to detect changes in those signals which suggest neurological dysfunction. Such changes and dysfunction, if left un-addressed, might lead to transient or permanent neurological injury or dysfunction post operatively. Detection of these changes presents an opportunity to intervene and mitigate or avoid those injuries.

[0010] Such neurophysiological monitoring may include a wide range of modalities and techniques including, for example, short latency Somatosensory Evoked Potentials (SSEP), Trans-Cranial Electrical Motor Evoked Potentials (TceMEP), Direct Waves (D-Waves), Electroencephalography (EEG), Hoffman waves (H waves), near nerve stimulation and recording from nerve and / or muscle electromyography (triggered EMG), and neuromuscular junction testing for paralytic effect (e.g., Train of Four (TOF) nerve stimulation and muscle recording).

[0011] The signals generated by each modality generally have one or more allowed characteristic variations. For example changes in latency or amplitude or other properties which, if exceeded, lead to a concern of impending or transpired tissue injury and require timely action for a mitigation to be effective. These allowed characteristic variations are often generated by expert opinion, are assigned by modality, and do not consider any confounding factors.

[0012] Interpretation of the individual modality monitoring may be further complicated or affected by type, dose, and duration of the anesthesia used on the patient, by patient systemic factors and patient co-morbidities. For example, SSEPs and Motor Evoked Potentials (MEPs) are strongly affected by gas anesthetic agents in varying degrees according to their doses and the cadence of their delivery. Also, neuromuscular junction testing, MEPs, and EMG are affected by the use of paralytic agents, and EEG is affected by the use of both anesthetic and hypnotic agents. In addition, several of these modalities are affected by changes in patient body temperature, blood pressure, local perfusion, and co-morbidities.

[0013] When used together, the results of some monitoring modalities may affect the interpretation of other modalities. For example, a neuromuscular junction test showing strong paralytic effect may suggest a reduced ability to acquire MEPs, alter the reliability of MEPs, and complicate the process for predicting an injury. Likewise, a change in EEG may reflect a change in anesthesia effect on SSEPs or MEPs with similar consequences.

[0014] In addition, the degree of noise injected into the various signals may vary due to nearby surgical machinery including lights, patient warmers, fluid warmers, surgical tools, or other monitoring devices. The surgical bed itself may confound recording of the signals in varying degrees over time. Electrode or device malfunction may increase noise or reduce signal clarity reducing the reliability of a recording to predict injury. Further, the stage of the surgery (such as the ongoing surgical tasks or events that change during the surgery duration) may affect the ongoing degree or location of risk to the patient and the consequence of any particular signal change in one or more modalities in predicting tissue dysfunction and / or a need for intervention. For example, changes during or within a specific period after insertion of a spinal cage or de-rotation of a spinal deformity are generally treated with more seriousness due to the higher risk of injury to the spinal cord during those time periods.

[0015] The above factors complicate the interpretation of changes in the modality related signals. Interpretation thus requires knowledge of the various surgical stages, anesthesia types and doses, physiological factors, modality interdependencies, etc., that are occurring in the operating room to accurately gauge the immediate degree of risk and the significance of any signal changes. For these reasons, monitoring is typically performed by a highly trained technologist overseen by a physician or senior clinician (the monitoring team). The integrated data is qualitatively analyzed by the monitoring team and when changes in integrated data suggest a risk to the patient, the monitoring team delivers an alert to the surgical staff so that mitigations can be considered.

[0016] The monitoring team personnel and the monitoring devices are expensive, require pre-booking, and are often not readily available. Training and knowledge are also widely variable. Interpretation may be further affected by human factors such as fatigue and inattention. Delays or failures in manually logging events into the record due to the demands on the technologist may make the logs less reliable. The monitoring personnel may be biased to deliver alerts to the surgical staff even when the risk to the patient is low and / or the data is poor to avoid medico-legal liability. The monitoring personnel may also be biased not to deliver alerts when the situation is tense or the surgical staff are preoccupied. This may lead to under, over, or delayed reporting of alerts, variability in recording of events, and differences in the utility of monitoring within or between cases or monitoring teams in predicting when mitigations are warranted.

[0017] Consequently, there exists a need for further improvements in neurophysiological monitoring and alerting that need no expertise or oversight, are always available, and allow for automated determination of appropriate monitoring.

[0018] SUMMARY

[0019] One aspect provides a method for automated risk assessment during surgery on a patient. A method includes determining one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient. The method includes automatically collecting procedural data during the surgery. The method includes automatically collecting physiological data of the patient during the surgery. The method includes automatically collecting neurological response waveform data of the patient. The method includes automatically providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system. The method includes comparing, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform. The method includes assessing a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data. In some embodiments, the method includes one more automated steps or stages — such as collecting physiological data, collecting neurological data — combined with one or more user inputs — such as procedural data or an indication of the current procedural stage — which inputs are used by a monitoring system to properly assess the collected physiological and neurological data.

[0020] Other aspects provide: an apparatus operable, configured, or otherwise adapted to perform any one or more of the aforementioned methods and / or those described elsewhere herein; a system for performing the aforementioned methods as well as those described elsewhere herein; a non-transitory, computer-readable media comprising instructions that, when executed by a processor of an apparatus, cause the apparatus to perform the aforementioned methods as well as those described elsewhere herein; a computer program product embodied on a computer-readable storage medium comprising code for performing the aforementioned methods as well as those described elsewhere herein; and / or an apparatus comprising means for performing the aforementioned methods as well as those described elsewhere herein. By way of example, an apparatus may comprise a processing system, a device with a processing system, or processing systems cooperating over one or more networks.

[0021] The following description and the appended figures set forth certain features for purposes of illustration.

[0022] BRIEF DESCRIPTION OF DRAWINGS

[0023] The appended figures depict certain features of the various aspects described herein and are illustrative and exemplary in nature and not to be considered limiting of the scope of this disclosure. The following detailed description of the illustrative aspects can be better understood when read in conjunction with the following drawings wherein like structure is indicated with like reference numerals and in which: Figure 1 is a block diagram depicting major components of an example system for automatically collecting and logging surgical stages, events, and actions, and estimating and assessing patient injury risk during surgery.

[0024] Figure 2 depicts an example process for automatically collecting and logging surgical stages, events, and actions and estimating and assessing patient injury risk during surgery.

[0025] Figure 3 is a block diagram depicting an example system for automatically collecting surgical stages, events, and actions, and estimating and assessing injury risk during surgery.

[0026] Figure 4 depicts an example artificial intelligence (Al) / machine learning (ML) functional framework.

[0027] Figure 5 is a flow diagram depicting an example method for automatically collecting and logging surgical stages, events, and actions, and estimating and assessing patient injury risk during surgery.

[0028] Figure 6 depicts a block diagram illustrating an apparatus for automatically collecting and logging surgical stages, events, and actions, and estimating and assessing patient injury risk during surgery.

[0029] DETAILED DESCRIPTION

[0030] Aspects of the present disclosure provide apparatuses, methods, processing systems, and computer-readable mediums for monitoring of the nervous system in the operating room during surgeries where the nervous system may be at risk.

[0031] Current neurological monitoring procedures may involve collecting baseline response waveforms from a patient and then monitoring response waveforms from the patient during surgery and comparing the monitored response waveforms to the baseline waveforms to assess whether there is an injury or risk of injury to the patient. In some cases, the response waveforms are interpreted by a human operator to assess the risk. Such interpretation may be subjective, subject to human error, and requires a skilled operator. In addition, current alerting systems may be inaccurate because they do not account for all data that may affect the interpretation of the response waveforms. For example, physiological data of the patient (e.g., temperature, blood pressure, etc.), procedural data (e.g., associated with the ongoing surgical stage), procedures performed by the anesthesiologist, dosing and dosing rate of certain drugs (e.g., propofol), the surgical stage and the risks associated with the stage (e.g., placing an insert is a dangerous part of the surgery), positioning of the patient (e.g., for risk of positional nerve injury), alertness of the technologist, the technologist’s age and experience, the technologist’s relationship with the surgeon (e.g., an inexperienced technologist might be hesitant to alert the surgeon) impacts the interpretation and response to the waveforms.

[0032] Described herein is an automated monitoring and logging system and device for risk estimation during surgeries. The automated monitoring and logging system or device may be used by persons without expertise and without oversight. In some aspects, the automated monitoring and logging system or device may collect procedural data related to on-going surgical stages and events, as well as data associated with physiological states of the patient and neurological response monitoring data and uses the procedural data, physiological data, and neurological monitoring data, as well as potentially additional data, in objectively interpreting monitoring waveforms for assessing risk. In some aspects, a machine learning model may log the collected data, interpret the monitoring waveforms based on collected procedural, physiological, and neurological monitoring data, and perform risk assessment.

[0033] In some aspects, with the collected data, the automated monitoring and logging system or device may take one or more actions in response to collected procedure and physiological data. For example, the automated monitoring and logging system or device may temporally assign a relative risk to the patient dependent upon various factors; the automated monitoring and logging system or device may inform the surgical staff of the ongoing risk level; the automated monitoring and logging system or device may adjust a type, a location, and a frequency of the monitoring to address the risk; the automated monitoring and logging system or device may adjust alerting criteria accordingly to the risk level; the automated monitoring and logging system or device may deliver alerts to the operating room staff when a significant change in the monitoring data is detected.

[0034] In some aspects, a system, method, device, apparatus, and / or computer program for automated risk assessment during surgery on a patient is disclosed. This system, method, device, apparatus, and / or computer program may automatically detect and identify surgical stages, events, and actions during surgery, though, in some embodiments, at least some of this information may be supplied by a user. For example, in some embodiments, a user may be able to input the surgical stage or, in response to a prompt from the system, indicate the surgical stage based on a pre-arranged procedural plan. In some embodiments, a procedural plan will have been established or accepted by a surgeon. The plan may include each stage of the procedural plan along with an estimated duration for each so that as the procedure progresses, the system may advance automatically from one stage to the next or may prompt a user asking if a given stage has been completed or if the subsequent stage has begun. Such prompts may be triggered by the system as it monitors various aspects of the surgery, such as the use of certain instruments, changes in physiological and / or neurological data from the patient, the position or change of position of the patient, and / or the actions of at least some of the individuals involved in the surgery.

[0035] The detected or registered surgical stages, events, and actions during surgery may then be integrated with other available neuromonitoring results. In some aspects, the detected or registered surgical stages, events, and actions during surgery may be integrated with physiological and / or anesthesia information. The system, method, device, apparatus, and / or computer program is configured to identify changes in the neuromonitoring results and / or physiological and anesthesia information, calculate the ongoing degree and location of risk to the patient, and adjust type, location, and frequency of monitoring testing to address such calculated risk. The system, method, device, apparatus, and / or computer program may be configured to adjust alerting criteria accordingly to the calculated risk level. In some aspects, some or all of the information is displayed to the user. In some aspects, the information is logged contemporaneously.

[0036] In some aspects, a method for integrating neuromonitoring, physiological monitoring, anesthesia data, and navigation system or robotic camera data during surgery is disclosed. The integrated data may be utilized to estimate ongoing risk, and adjust further neuromonitoring to address the ongoing risk.

[0037] In some aspects, a method for incorporating and integrating the surgical planning and procedural workflow outputs of the robotic or navigation system is disclosed. In some aspects, the method may estimate the ongoing risk to the patient and adjust the neuromonitoring to address that risk. For example, neuromonitoring that may be adjusted include navigation systems for determining the placement of the lumbar screws and at which spinal level the surgery is occurring, monitoring systems configured to determine which instrument is in use (e.g., an awl, a tap, or a screwdriver), monitoring systems for determining where the instrument is located in relation to boney architecture, and monitoring systems for determining expected locations of neural structures.

[0038] In some aspects, the method may further include displaying the neuromonitoring results on a display unit.

[0039] In some aspects, the neuromonitoring results may be returned to the monitoring systems as electrical signals recorded by the recording electrodes. In some aspects, the method may utilize one or more of electric stimulators, preamplifiers, amplifiers, and / or computer components to control stimulation and process return signals.

[0040] In some aspects, the stimuli responses may be averaged together to reduce noise and produce a cleaner signal. In some aspects, software may be used in the signal processing to improve the signal-to-noise ratio.

[0041] While aspects are described herein for intra-operative monitoring, the techniques and apparatus described herein can also be used outside of the operating room in nonoperative use cases.

[0042] Intra-Operative Monitoring System

[0043] Figure l is a block diagram depicting major components of an example system 100 for automatically collecting and logging data associated with surgical stages, events, and actions, and estimating and assessing risk of patient injury during surgery.

[0044] In some aspects, the system 100 includes devices for collecting neurological monitoring data. As shown in Figure 1, the system may include stimulating electrodes 120. The stimulating electrodes 120 may include stimulating cathode electrodes, stimulating anode electrodes, and / or peripheral stimulating electrodes. The stimulating electrodes 120 may be placed on the body of a patient 180. The stimulating electrodes 120 may be configured to provide electrical stimulation of one or more muscles of the patient 180 (e.g., in a supine, lateral, or prone positioning). In some aspects, the electrodes are secured to the patient 180 cutaneously (e.g. surface electrodes) or subdermal (e.g. needle electrodes). Cutaneous electrodes are non-invasive electrodes placed on the skin of the patient 180. Subdermal electrodes are invasive electrodes that penetrate the skin of the patient 180. In some aspects, the stimulating electrodes 120 may include one or more probe(s) / clips 122. In some aspects, the stimulating electrodes 120 are inserted into the skin of the patient 180 subcutaneously (e.g. subdermal electrodes). In some aspects, the location that stimulating electrodes 120 are placed on the body of the patient 180 is dependent on the areas of the body to be monitored and / or the type of monitoring to be performed (e.g., the type of response waveform to be evoked).

[0045] Anode electrodes of the stimulating electrodes 120 provide the conductive pathway for electrical current. For example, the anode electrodes of the stimulating electrodes 120 provide the positive electrodes where the electrical current enters the body of the patient 180, while the cathode electrodes of the stimulating electrodes 120 provide the negative electrodes where the electrical current exits the body of the patient 180, with the cathode(s) acting as the stimulating source.

[0046] The electrical stimulations provided by the stimulating electrodes 120 may cause one or more muscles of the body of the patient 180 to provide responses. The muscle responses may be detected as resultant electrical waveforms from depolarized supplying motor nerves of those muscles. The muscle responses may be reflexive, direct, or both. The resultant electrical waveforms from the stimulated muscles are collected by recording electrodes 170.

[0047] In some aspects, the stimulating electrodes 120 may include electrodes for evoking sensory responses and / or other cranial responses. For example, the stimulating electrodes may include electrodes 124 for evoking Trans-Cranial Electrical Motor Evoked Potentials (TceMEP). TceMEP is a technique used to assess the integrity of the motor pathways in the brain and spinal cord through the application of electrical stimulation to the motor cortex of the brain, such as through scalp electrodes, while monitoring the electrical responses in the muscles of the body. During a TceMEP procedure, electrical pulses are delivered to the motor cortex through the cranium, which activate the motor neurons responsible for controlling specific muscles. The electrical signals generated by these neurons travel down the spinal cord and peripheral nerves, causing muscle contractions. These muscle contractions produce electrical activity, which can be recorded using electrodes placed near, on or in the muscles. By analyzing the recorded electrical responses, neurophysiologists can evaluate the time it takes for the electrical signals to travel from the motor cortex to the muscles, as well as the amplitude and waveform characteristics of the evoked potentials. Any abnormalities or delays in the response can provide insights into the functional status of the motor pathways and help diagnose conditions such as spinal cord injury. TceMEP helps surgeons avoid damaging critical motor pathways and provides real-time feedback on the functional integrity of these pathways. Other examples of cranial response waveforms that may be monitored include Direct Waves (D-Waves), electroencephalography (EEG), anesthesia effect, and brainstem auditory evoked response (BAER). EEG is a test that measures electrical activity in the brain. BAER is a test that is utilized to measure the brain wave activity that occurs in response to clicks or tones. BAER may be utilized during surgery to monitor and decrease the risk of damage to the brain or nervous system.

[0048] The stimulating electrodes 120 may include electrodes 126 for evoking short latency Somatosensory Evoked Potentials (SSEP). SSEP utilizes a series of waves that reflect sequential activation of neural structures along the somatosensory pathways. SSEP may be utilized for intraoperative neurophysiological monitoring for spinal, central nervous system (CNS), and vascular surgeries. SSEPs may be utilized to determine the potential for or actual nerve injury and avoid morbidity associated with surgery.

[0049] A probe or clip electrode 122 may be used to evoke triggered electromyography (tEMG). tEMG is a method of intraoperative neuromonitoring used to assist in the placement of pedicle screws (PS), which may compromise the adjacent neural structures.

[0050] In some aspects, the stimulating electrodes 120 may be used for neuromuscular junction testing, spinal reflex test, electroencephalography, brainstem auditory evoked potentials, electromyography, triggered electromyography, and other testing of patient 180. In some aspects, the stimulating electrodes 120 include electrodes for evoking muscle responses. For example, the stimulating electrodes 120 may be used to evoke Direct Waves (D-Waves), evoke surface electromyography (sEMG), Motor Evoked Potentials (MEPs), or other muscle response waveforms. sEMG provides a global view of skeletal muscle function and allows for the study of features of multiple muscle systems. MEPs provide electrical signals recorded from muscle tissue in response to stimulation in the motor cortex. D-Waves provide electrical signals recorded from spinal cord in response to stimulation of the motor cortex. In MEPs and D-Waves, magnetic or electrical stimulation may be applied directly to the motor cortex or transcranially.

[0051] The resultant electrical waveforms from the stimulated muscles are collected by recording electrodes 170. For example, the recording electrodes may record the response waveforms resulting from any of the stimulating electrodes 120, such the tEMG, TceMEP, SSEP, EEG, BAER, anesthesia effect, sEMG, MEP, or any of the resulting waveform. In some aspects, the recording electrodes 170 for recording resulting muscle waveforms are attached, connected, and / or coupled over one or more muscles of the upper or lower extremities of the patient 180. For example, the recording electrodes 170 may be positioned at one or more leg muscles of either or both legs of the patient 180 and / or the recording electrodes 170 may be positioned at one or more upper extremities of the patient 180, such as on both arms of the patient 180, such as on the wrists or near the ulnar nerve.

[0052] In addition, the recording electrodes 170 may measure physiological parameters of the patient 180 such as blood pressure (BP), pulse oximetry, etc.

[0053] According to certain aspects of the disclosure, the system 100 further collects procedural data, for example, associated with surgical stages. As shown in Figure 1, the system 100 may include a navigation and / or robotics device 110. In some aspects, the navigation or robotics device 110 uses an imaging device, such as a camera 112. In some aspects, the camera 112 may be an infrared camera, visible-light camera, x-ray imaging device, or other imaging device that collects procedural data. It should be understood that while Figure 1 illustrates a navigation device, robotics device, and / or camera to collect procedural data, that different types of devices may be used collect procedural data.

[0054] In some aspects, the navigation or robotics device 110 may utilize fiducials or radio frequency identification circuits on the surgical instruments and devices and the other equipment and items within an operating theater.

[0055] In some aspects, the navigation or robotics device 110 may perform real-time intraoperative nerve location and assessment. In some aspects, the navigation or robotics device 110 may be configured to reduce noise and amplify the signal.

[0056] In some aspects, the navigation or robotics device 110 is a platform configured to improve image quality, reduce radiation dosage, and accommodate a wider range of patients to provide pre-operative images.

[0057] In some aspects, the navigation or robotics device 110 is a visualization device configured to receive input from a C-arm in conjunction with spatial tracking and image processing technology for intra-operative imaging.

[0058] In some aspects, the navigation or robotics device 110 is a table-mounted navigation system configured to guide instrumentation and implants via robotic assistance when placing pedicle screws. In some aspects, the navigation or robotics device 110 utilizes a 3D imaging scan or 2D fluoroscopic images of the patient.

[0059] In some aspects, the outputs of the navigation or robotics device 110 may provide, for instance, navigation for lumbar screws that includes at which spinal level the surgery is occurring, which instrument is in use such as awl, tap, or screwdriver or the like, where the instrument is located in relation to boney architecture, expected location of neural structures, etc.

[0060] In some aspects, the procedural data includes images or video within the operating theater. For example, such images may include x-ray images, 3D imaging, 2D fluoroscopic images, or other imaging formats. The images may be of the patient, the process, the equipment, the surgical team, or other objects within the operating theatre. Such procedural data can indicate the surgical stage. For example, the procedure data may show that patient is still in pre-operation, when the surgeon is placing an insert, or that the surgery has begun. In addition, the procedural data can indicate other actions / events associated with the surgery. In some aspects, the actions of the surgeon or other members of the surgery team may be indicated, imaged, or recorded. For example, when the anesthesiologist is adjusting drug dosage or when the surgeon is utilizing a slap hammer. In some aspects, the equipment is captured, such as the anesthesia machine (e.g., what physiological parameters were entered into the system), the positioning of the surgical instruments, and what equipment is in the room. In some aspects, the patient is captured, for example, for monitoring the patient’s position.

[0061] According to certain aspects, the system 100 collects the procedural data from the camera 112 and / or the navigation or robotics device 110 (or any device used to collect procedural data) and the system 100 collects the physiological data and the neurological monitoring data (e.g., including muscle response data, sensory response data, spinal cord response data and / or cranial response data) from the recording electrodes 170. According to some aspects, the system 100 — based on the data already collected by the system 100 — prompts a user to determine if the procedure has in fact advanced from a given stage to a subsequent stage or the system 100 may be configured to receive an input from a user as to a given stage irrespective of whether the user is responding to a prompt. For example, in some embodiments, the system 100 may — after performing a given step — pause until receiving input from a user to proceed to the next step, which next step may be an adjustment in the type of monitoring performed or a change in the thresholds applicable to the monitoring.

[0062] As discussed in more detail below with respect to Figure 2, the system 100 may use the collected and / or inputted data to automatically determine baseline response waveforms, interpret ongoing collected monitoring waveforms and assess ongoing risk of injury to the patient 180.

[0063] As shown in Figure 1, the system 100 includes a response processing device 130, a surgical instrument, stage, event, and / or action identification device 140, a risk assessment, logging, alerting, and modulating device 150, and a display 160. It should be understood that while illustrated as separate devices in Figure 1, any of the response processing device 130, surgical instrument, stage, event, and / or action identification device 140, risk assessment, logging, alerting, and modulating device 150, and / or display 160 may be combined in a single device. In some aspects, the response processing device 130, the surgical instrument, stage, event, and / or action identification device 140, and / or the risk assessment, logging, alerting, and modulating device 150 may be a computer or any other device configured to receive, process, and transmit data. In the example illustrated in Figure 1, the stimulating electrodes 120 and the recording electrodes 170 may communicate with the response processing device 130. For example, the stimulating electrodes 120 may provide the response processing device 130 with data associated with the stimulating. The recording electrodes 170 may provide the collected physiological data and the collected neurological monitoring response waveform data to the response processing device 130.

[0064] In some aspects, the response processing device 130 may identify the presence or absence of various electrophysiological signals. In some aspects, the response processing device 130 may detect and / or identify changes in the various electrophysiological signals. In some aspects, the response processing device 130 may control the stimulating electrodes 120, for example, the frequency, location, and / or amplitude of the stimulating. In some aspects, the response processing device 130 may control the recording electrodes 170

[0065] In some aspects, the response processing device 130 provides the physiological data and / or the neurological monitoring response waveform data to surgical instrument, stage, event, and / or action identification device 140, risk assessment, logging, alerting, and modulating device 150, and / or display 160.

[0066] As shown in Figure 1, the navigation or robotics device 110 and / or the camera 112 (or other device used to collect procedural data) provides the collected procedural data to the surgical instrument, stage, event, and / or action identification device 140. Based on the procedural data, the surgical instrument, stage, event, and / or action identification device 140 may identify information about the surgical instruments being used, the current surgical stage, the event transpiring during the surgical stage, and / or the action being performed during the surgical stage. In some aspects, the surgical instrument, stage, event, and / or action identification device 140 may collect the physiological data and / or the neurological monitoring data and results (modalities) from the response processing device 130. In some aspects, the surgical instrument, stage, event, and / or action identification device 140 may receive inputs from a user to help identify the appropriate surgical instrument, stage, event, and / or action, which input may be the result of a prompt to which the user is responding, which prompt may have been triggered by procedural information gathered by the surgical instrument, stage, event, and / or action identification device 140 and / or by the progress of time as measured against a pre-accepted surgical plan complete with estimated durations of each surgical instrument, stage, event, and / or action.

[0067] The surgical instrument, stage, event, and / or action identification device 140 may provide the information about the surgical instruments, current surgical stage, events, and / or actions to the response processing device 130, the risk assessment, logging, alerting, and modulating device 150, and / or the display 160. In some aspects, the surgical instrument, stage, event, and / or action identification device 140 incorporates as an input the patient’ s risk of getting an injury (e.g., a patient with a tight stenosis would be at greater risk than a patient with a large canal). In some aspects, the surgical instrument, stage, event, and / or action identification device 140 is configured to recognize and identify the instruments in the field. In some aspects, the surgical instrument, stage, event, and / or action identification device 140 is configured to identify the action that the surgeon is performing (e.g., if the surgeon is utilizing a slap hammer). In some aspects, the surgical instrument, stage, event, and / or action identification device 140 — after recognizing and identifying instruments in the field or after identifying an action of the surgeon or after identifying some other indication of an advancement of the surgical procedure from one surgical instrument, stage, event, and / or action to another — prompts a user for confirmation that the surgical instrument, stage, event, and / or action has in fact occurred and / or advanced appropriately.

[0068] In some aspects, the risk assessment, logging, alerting, and modulating device 150 obtains both the procedural data information from the surgical instrument, stage, event, action identification device 140 and also the physiological and neurological monitoring response waveform data from the response processing device 130. According to certain aspects, the risk assessment, logging, alerting, and modulating device 150 may use the procedure information and the physiological information to interpret the neurological monitoring response waveform data. For example, as described in more detail below with respect to Figure 2, the risk assessment, logging, alerting, and modulating device 150 may use the procedure information, the physiological information, and the neurological monitoring response waveform information in assessing the ongoing level of risk and the structures at risk, in assigning monitoring frequency and location, in modulating ongoing alerting criteria, in delivering alerts, and / or in logging data. In some aspects, the structures at risk may be determined based on the type of the surgery and the clinical state of the patient. In some aspects, the structures at risk may be anatomical locations of the risk to the patient. In some aspects, the structures at risk may be the entirety of or specific portions of the spinal column, the blood vessels that supply the spinal cord with blood, or the nerves. In some aspects, risks to the structures at risk include bleeding inside the spinal column, leaking of spinal fluid, damage to the blood vessels that supply the spinal cord with blood, or nerve damage. In some aspects, the risk assessment, logging, alerting, and modulating device 150 may monitor and log changes in neuromonitoring resulting from one or more modalities. For example, the risk assessment, logging, alerting, and modulating device 150 may monitor and log changes in information from other neuromonitoring modalities to determine when changes in the resultant neuromonitoring results are due to anesthesia or the presence of paralytic or other pharmaceutical agents. In some aspects, the risk assessment, logging, alerting, and modulating device 150 may monitor and log changes in information based on one or more modalities to information from physiological parameters, for example, but not limited to, a blood pressure, temperature or pulse oximeter to determine when changes in the resultant electrical waveforms are due to changes in those physiological parameters. In some aspects, the risk assessment, logging, alerting, and modulating device 150 may monitor and log changes in information based on the camera 112 or data collected by the navigation or robotics device 110 to determine when changes in the neuromonitoring results are due to stages, events, and actions during surgery. According to some aspects, the risk assessment, logging, alerting, and modulating device 150 may prompt a user to confirm a change based on information collected from the camera 112 or data collected by the navigation or robotics device 110. According to some aspects, a user may indicate a change even without a prompt.

[0069] Display 160 may receive and display information from the response processing device 130, the surgical instrument, stage, event, action identification device 140, and / or the risk assessment, logging, alerting, modulating device 150. The display 160 may be a computer, a tablet, a monitor, or other device configured to present data. In some aspects, the display 160 may include a display which may display various types of information, such as areas being stimulated and recorded from, baseline and current neuromonitoring results, trends in signals, relevant changes in signals, location of signal changes, quality of recorded signals, position of electrodes, surgical stages, events or actions, surgical instrument positions, level or location of ongoing surgical risk. In some aspects, the display 160 may display physiological parameters such as blood pressure, temperature, pulse oximetry, estimates of anesthetic effect, and alerts due to significant changes in one or more neuromonitoring signals. In some aspects, the display 160 may include audio, visual, and / or tactical alerts based on data transmitted from the risk assessment, logging, alerting, and modulating device 150. In some aspects, the display 160 may be configured to alert a user to changes in the neuromonitoring results using one or more of a notification, an alert, a communication, an indication, and / or an alarm. In some aspects, the risk assessment, logging, alerting, and modulating device 150 is configured to take a baseline risk, modulate the baseline risk according to the surgical procedure and physiological data, and produce an alert accordingly. In some aspects, the risk assessment, logging, alerting, and modulating device 150 is configured to have varying degrees of sensitivity based on the risk of the surgery. In some aspects, the risk assessment, logging, alerting, and modulating device 150 is configured to produce an alert when a high risk patient is at a high risk portion of a surgery. In some aspects, the risk assessment, logging, alerting, and modulating device 150 is configured to produce an alert that is displayed on a user’s phone.

[0070] In some aspects, the display 160 may include one or more buttons or control inputs. In some aspects, the one or more buttons or inputs may allow an operator to set up an initial neuromonitoring layout and interact with the display 160 during monitoring to add additional information or respond to alerts. In some aspects, display 160 may allow override of a change in signal by an anesthesiologist, or other medical personnel, such as when a signal change is related to an event unrelated to nerve injury.

[0071] In some aspects, the system 100 or portions thereof may be implemented using hardware, software, firmware, or a combination thereof. The system 100 or portions thereof may be implemented in one or more computer systems or other processing systems. In some aspects, the system 100 may be directed toward one or more computer systems capable of carrying out the functionality described herein.

[0072] Figure 2 depicts an example process 200 for automatically collecting and logging surgical stages, events, and actions and estimating and assessing patient injury risk during surgery. According to some aspects of process 200, one or more stages of process 200 are not performed automatically. For example, one or more operations may involve manual input from a user, which may be the result of a prompt from one or more aspects of the system 100.

[0073] In operation 205, a type of surgery is input. The type of surgery may be input manually (e.g., by the surgeon nurse, operating room staff, or other operator). In some aspects, the type of surgery may be automatically detected by the system. In some aspects, the system may automatically detect the type of surgery based on the collected procedural data. In some aspects, the system may utilize artificial intelligence and / or machine learning (AI / ML), for example, via a trained model for the detecting the surgery type. In some aspects, operation 205 may be performed by the surgical instrument, stage, event, action identification device 140 described in Figure 1. In operation 210, the baseline risk level and structures at risk are set. In some aspects, the baseline risk level and the structures at risk may be input manually to the system or the base risk level and structures at risk may be automatically detected by the system (e.g., based on the type of surgery, data about the patient physiology, and / or other data). In some aspects, operation 210 may be performed by the risk assessment, logging, alerting, modulating device 150 described in Figure 1.

[0074] In operation 215, a surgical monitoring plan is assigned. The surgical monitoring plan may be input to the system manually or the surgical monitoring plan may be automatically determined by the system (e.g., based on the type of surgery, the risk assessment, and the structures at risk). The surgical monitoring plan may include the types of monitoring to be performed, the placement of stimulating electrodes 120 and recording electrodes 170, the frequency of the monitoring, the operation of navigation or robotics device 110, estimated durations of each step of the plan, intervals for prompting a user for updates on the status of at least some steps of the plan, the collection of physiological data, and / or other parameters associated with the monitoring.

[0075] In operation 220, a baseline modality data is collected. For example, based on the monitoring plan assigned in operation 215, baseline response waveforms can be collected for the patient 180 for the types of monitoring to be performed during the surgery so that these baseline response waveforms can be compared to response waveforms collected during the surgery in order to assess risk to the patient 180 based on changes in the response waveforms. The collection of the modality data is discussed in relation to Figure 1. For example, operation 220 may be performed by stimulating electrodes 120, recording electrodes 170, and response processing device 130 described in Figure 1.

[0076] In operation 225, the baseline physiological, anesthesia, and surgical state data are collected. For example, baseline physiological, anesthesia, and surgical state data may be collected as discussed in relation to Figure 1. For example, operation 225 may be performed by recording electrodes 170, navigation or robotics device 110, camera 112, response processing device 130, and surgical instrument, stage, event, action identification device 140 described in Figure 1.

[0077] In some aspects, operations 205-225 occur pre-operatively. After operations 205- 225, the surgical procedure may begin and operations 230-255 may be performed until the surgery is completed. In some embodiments, at least some of operations 205-225 are performed manually by one or more users while operations 230-255 are performed automatically by the system 100. In some embodiments, at least some of operations 205- 255 are performed manually where all non-manual operations are performed automatically by the system 100. In some embodiments, all of operations 205-255 are performed automatically by the system 100, and manual input or override may be an option though not a requirement as the operations progress.

[0078] In operation 230, ongoing modality, physiological, anesthesia, and procedural data (e.g., surgical state data) are collected during the surgical procedure. In some aspects, the ongoing modality, physiological, anesthesia, and procedural data may be collected periodically, intermittently, or continuously during the surgical procedure. In some aspects, the ongoing modality, physiological, anesthesia, and procedural data may be collected according to the monitoring plan assigned at operation 215. In some aspects, the monitoring plan may be manually or automatically adjusted during the surgical procedure as discussed in more detail below with respect to operation 245. The method of collecting of the ongoing modality, physiological, anesthesia, and procedural data may be as discussed in relation to Figure 1. For example, operation 230 may be performed by stimulating electrodes 120, recording electrodes 170, navigation or robotics device 110, camera 112, response processing device 130, and surgical instrument, stage, event, action identification device 140 described in Figure 1.

[0079] In operation 235, the ongoing risk level and structures at risk are assessed based on the ongoing modality, physiological, anesthesia, and procedural data collected in operation 230. The method of assessing the ongoing risk level and structures at risk based on collected ongoing data is discussed in relation to Figure 1. For example, operation 235 may be performed by the risk assessment, logging, alerting, modulating device 150 described in Figure 1. According to certain aspects, the risk assessment, logging, alerting, modulating device 150 uses a trained AI / ML model to assess the risk and structures at risk using the ongoing modality, physiological, anesthesia, and procedural data.

[0080] As discussed herein, the system uses the procedural data, including surgical stage data, in interpreting the collected ongoing data, in order to provide a comprehensive automated system that uses not only the modality, physiological, and anesthesia data, but also uses procedural data to improve the interpretation of the modality, physiological, and anesthesia data. As discussed in more detail below with respect to the operations 240-260, the system can use the risk assessment, automatically assessed and accounting for the procedural data, to display information to a surgeon, adjust the monitoring, modulate alerting criteria, provide alerts, and log data. In some aspects, depending on the surgical stage, the system may ignore certain changes in the monitored response waveforms, adjust the alert threshold based on the surgical stage, or adjust the waveforms. In some aspects, the system may be utilized for surgical case review and medicolegal requirements.

[0081] In operation 240, the ongoing risk and structures at risk may be displayed. In some aspects, information associated with the ongoing risk and structures at risk, and / or other information associated with the collected data, may be displayed on the display 160 depicted in Figure 1.

[0082] In operation 245, the ongoing monitoring location and frequency may be automatically adjusted based on the ongoing risk and structures at risk assessment. Operation 245 may be performed by the risk assessment, logging, alerting, modulating device 150 described in Figure 1.

[0083] In operation 250, the ongoing alerting criteria may be automatically modulated based on the ongoing risk and structures at risk assessment. Operation 250 may be performed by the risk assessment, logging, alerting, modulating device 150 described in Figure 1.

[0084] In operation 255, an alert is automatically delivered if the collected data meets the alerting criteria. Operation 255 may be performed by the risk assessment, logging, alerting, modulating device 150 described in Figure 1.

[0085] In operation 260, the data is automatically logged. According to certain aspects, the system performs automated logging of data that includes procedural data, such as surgical stage data. In some aspects, the surgical stage data is logged in response to detection of a particular action or event. Operation 260 may be performed by the risk assessment, logging, alerting, modulating device 150, described in Figure 1. In some aspects, the logged data is utilized to improve (e.g., train) machine learning models, facilitate case review, and satisfy regulatory requirements and medicolegal purposes.

[0086] Figure 3 is a block diagram depicting example components of a system 300 for automatically collecting surgical stages, events, and actions, and estimating and assessing injury risk during surgery.

[0087] The system 300 may include a network 320. The network 320 may provide communication between the various components of the system 300. In some aspects, the connections may be hard-wired, wireless, or a combination of hard-wired and wireless. The network 320 may be the Internet, a wireless wide area network (WWAN), a wireless peer- to-peer network, a local area network (LAN), a wireless LAN (WLAN), a wide area network (WAN), a Wi-Fi network, a cloud, a Bluetooth connection, or other connected network. As shown, the system 300 may include the response processing device 130, the surgical event / stage / action identification system 140, the risk assessment, logging, alerting, modulating device 150, the navigation or robotics device 110, camera 112, and the display 160. As shown in Figure 3, the system 300 may further include an identification controller 304, a client device 308, a sensory acquisition system 310, a motor acquisition system 312, a physiological parameter acquisition system 314, a surgical planning system 324, a surgical planning system 324, and / or database 332 on one or more servers 330.

[0088] In some aspects, the database 322 may store logging data, AI / ML model and / or training data used by the system, and / or other data. In some aspects, the database 332 may store some or all of the surgical cases. As shown, the database 322 may be connected to a business inventory or operations system 302. In some aspects, the business inventory or operations system 302 is configured to allow calculation of instrumentation usage, implant usage, surgical variability, and other information useful for business, inventory, or operations management.

[0089] As shown, the surgical event / stage / action identification system 140 may be connected to the camera 112 (and / or a radio frequency identification (RFID) reader) that collects procedural data. As shown, the surgical event / stage / action identification system 140 may be connected to the navigation or robotics device 110. Thus, the surgical event / stage / action identification system 140 may collect procedural data from the camera 112 (or RFID reader) and / or the navigation and robotics device 110 and may share the procedural data with the other components via the network 320.

[0090] The surgical planning system 324 may be configured to input the selection of the surgery type, set baseline risk level and structures at risk, and assign a surgical monitoring (e.g., as shown in operations 205-215 of Figure 2), as well other planning of a surgical procedure.

[0091] In some aspects, the sensory acquisition system 310 is configured to collect sensory response data of the patient 180. The sensory acquisition system 310 may include one or more of the stimulating electrodes 120 and recording electrodes 170. The sensory acquisition system 310 may share the collected sensory response data with the other components of the system 300 via the network 320.

[0092] In some aspects, the motor acquisition system 312 is configured to collect motor response data of the patient 180. The motor acquisition system 312 may include one or more of the stimulating electrodes 120 and recording electrodes 170. The motor acquisition system 312 may share the collected motor response data with the other components of the system 300 via the network 320.

[0093] In some aspects, the physiological parameter acquisition system 314 is configured to collect physiological data of the patient 180. The physiological parameter acquisition system 314 may include one or more of the recording electrodes 170. The physiological parameter acquisition system 314 may share the collected physiological parameter data with the other components of the system 300 via the network 320.

[0094] Identification controller 304 may control one or more components of the system 300 via the network 320. In some aspects, identification controller 304 may receive data from one or more of the components of the system 300 via the network 320 and control the components based on the data.

[0095] Client device 308 may be a mobile device, smart phone, tablet, laptop, wearable smart device, or other client device. In some aspects, the client device 308 may receive and display data from one or more components of the system 300, via the network 320, to a user of the client device 308. In some aspects, the client device 308 may receive user input for the system 300.

[0096] In some aspects, the system 300 may further include one or more processors, memory, storage devices, and / or computers (not shown).

[0097] Figure 4 depicts an example AI / ML functional framework 400, in which aspects described herein may be implemented.

[0098] The AI / ML functional framework 400 includes a data collection function 402, a model training function 404, a model inference function 406, and an actor function 408, which interoperate to provide a platform for collaboratively applying AI / ML to various procedures within the methods and systems described herein.

[0099] The data collection function 402 generally provides input data to the model training function 404 and the model inference function 406. AI / ML algorithm specific data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) may not be carried out in the data collection function 402. Examples of input data to the data collection function 402 (or other functions) may include measurements from the recording electrodes 170, the navigation / robotics device 110, feedback from the actor function 408, and output from an AI / ML model. The data collection function 402 may analyze what data to input to the model training function 404 and the model inference function 406. The data collection function 402 may deliver training data to the model training function 404 and inference data to the model inference function 406. The model training function 404 may perform AI / ML model training, validation, and testing, which may generate model performance metrics as part of the model testing procedure. The model training function 404 may also be responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on the training data delivered by the data collection function 402.

[0100] The model training function 404 may provide model deployment / update data to the model interface function 406. The model deployment / update data may be used to initially deploy a trained, validated, and tested AI / ML model to the model inference function 406 or to deliver an updated model to the model inference function 406. The model may be trained to predict risk to a patient based on input including surgical stage data.

[0101] In some examples, the model training function 404 uses machine learning algorithm, a reinforcement learning algorithm, a deep learning algorithm, a continuous infinite learning algorithm, or a policy optimization reinforcement learning algorithm (e.g., a proximal policy optimization (PPO) algorithm, a policy gradient, a trust region policy optimization (TRPO) algorithm, or the like) to generate a model to predict risk to a patient based on surgical stage data. In some examples, model is implemented by an artificial neural network (e.g., a deep Q network (DQN) including one or more deep neural networks (DNNs)).

[0102] In some examples, the model training function 404 generates a neural network model to predict risk to a patient based on surgical stage data. Neural networks may be designed with a variety of connectivity patterns. In feed-forward networks, information is passed from lower to higher layers, with each neuron in a given layer communicating to neurons in higher layers. A hierarchical representation may be built up in successive layers of a feed-forward network. Neural networks may also have recurrent or feedback (also called top-down) connections. In a recurrent connection, the output from a neuron in a given layer may be communicated to another neuron in the same layer. A recurrent architecture may be helpful in recognizing patterns that span more than one of the input data chunks that are delivered to the neural network in a sequence. A connection from a neuron in a given layer to a neuron in a lower layer is called a feedback (or top-down) connection. A network with many feedback connections may be helpful when the recognition of a high-level concept may aid in discriminating the particular low-level features of an input.

[0103] In some examples, the model training function 404 generates a deep belief network (DBN) model to predict risk to a patient based on surgical stage data. DBNs are probabilistic models comprising multiple layers of hidden nodes. DBNs may be used to extract a hierarchical representation of training data sets. A DBN may be obtained by stacking up layers of Restricted Boltzmann Machines (RBMs). An RBM is a type of artificial neural network that can learn a probability distribution over a set of inputs. Because RBMs can learn a probability distribution in the absence of information about the class to which each input could be categorized, RBMs are often used in unsupervised learning. Using a hybrid unsupervised and supervised paradigm, the bottom RBMs of a DBN may be trained in an unsupervised manner and may serve as feature extractors, and the top RBM may be trained in a supervised manner (on a joint distribution of inputs from the previous layer and target classes) and may serve as a classifier.

[0104] In some examples, the model training function 404 generates a deep convolutional network (DCN) model to predict risk to a patient based on surgical stage data. DCNs are networks of convolutional networks, configured with additional pooling and normalization layers. DCNs have achieved state-of-the-art performance on many tasks. DCNs can be trained using supervised learning in which both the input and output targets are known for many exemplars and are used to modify the weights of the network by use of gradient descent methods. DCNs may be feed-forward networks. In addition, as described above, the connections from a neuron in a first layer of a DCN to a group of neurons in the next higher layer are shared across the neurons in the first layer. The feed-forward and shared connections of DCNs may be exploited for fast processing. The computational burden of a DCN may be much less, for example, than that of a similarly sized neural network that comprises recurrent or feedback connections.

[0105] An artificial neural network, which may be composed of an interconnected group of artificial neurons (e.g., neuron models), is a computational device or represents a method performed by a computational device. Individual nodes in the artificial neural network may emulate biological neurons by taking input data and performing simple operations on the data. The results of the simple operations performed on the input data are selectively passed on to other neurons. Weight values are associated with each vector and node in the network, and these values constrain how input data is related to output data. For example, the input data of each node may be multiplied by a corresponding weight value, and the products may be summed. The sum of the products may be adjusted by an optional bias, and an activation function may be applied to the result, yielding the node’ s output signal or “output activation.” The weight values may initially be determined by an iterative flow of training data through the network (e.g., weight values are established during a training phase in which the network learns how to identify particular classes by their typical input data characteristics).

[0106] In some aspects, the model training function 404 can generate various types of artificial neural networks to predict risk to a patient based on surgical stage data, such as recurrent neural networks (RNNs), multilayer perceptron (MLP) neural networks, convolutional neural networks (CNNs), and the like. RNNs work on the principle of saving the output of a layer and feeding this output back to the input to help in predicting an outcome of the layer. In MLP neural networks, data may be fed into an input layer, and one or more hidden layers provide levels of abstraction to the data. Predictions may then be made on an output layer based on the abstracted data. MLPs may be particularly suitable for classification prediction problems where inputs are assigned a class or label. Convolutional neural networks (CNNs) are a type of feed-forward artificial neural network. Convolutional neural networks may include collections of artificial neurons that each has a receptive field (e.g., a spatially localized region of an input space) and that collectively tile an input space. Convolutional neural networks have numerous applications. In particular, CNNs have broadly been used in the area of pattern recognition and classification. In layered neural network architectures, the output of a first layer of artificial neurons becomes an input to a second layer of artificial neurons, the output of a second layer of artificial neurons becomes an input to a third layer of artificial neurons, and so on. Convolutional neural networks may be trained to recognize a hierarchy of features. Computation in convolutional neural network architectures may be distributed over a population of processing nodes, which may be configured in one or more computational chains. These multi-layered architectures may be trained one layer at a time and may be fine-tuned using back propagation.

[0107] In some examples, when using AI / ML, the model training function 404 generates vectors from the information in a training repository. In some examples, the training repository stores vectors. In some examples, the vectors map one or more features to a label. For example, the features may correspond to various deployment scenario patterns discussed herein, such as the UE mobility, speed, rotation, channel conditions, BS deployment / geometry in the network, etc. The label may correspond to the predicted optimal beam selection (e.g., of RX beams) associated with the features for performing a beam management procedure. The predictive model function 404 may use the vectors to train the predictive model. As discussed above, the vectors may be associated with weights in the adaptive learning algorithm. As the learning algorithm adapts (e.g., updates), the weights applied to the vectors can also be changed. Thus, when the beam management procedure is performed again, under the same features (e.g., under the same set of conditions), the model may give a different result (e.g., a different beam selection).

[0108] The model inference function 406 may provide AI / ML model inference output (e.g., predictions or decisions) to the actor function 408 and may also provide model performance feedback to the model training function 404, at times. The model inference function 406 may also be responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on inference data delivered by the data collection function 402, at times.

[0109] The inference output of the AI / ML model may be produced by the model inference function 406. The model performance feedback may be used for monitoring the performance of the AI / ML model. The model performance feedback may be delivered to the model training function 404, for example, if certain information derived from the model inference function is suitable for improvement of the AI / ML model trained in the model training function 404. In some aspects, feedback is used by the model training function 404 to adjust one or more weights in the model.

[0110] The model inference function 406 may signal the outputs of the model to nodes that have requested them (e.g., via subscription), or nodes that take actions based on the output from the model inference function. An AI / ML model used in a model inference function 406 may need to be initially trained, validated and tested by a model training function before deployment. The model training function 404 and model inference function 406 may be able to request specific information to be used to train or execute the AI / ML algorithm and to avoid reception of unnecessary information. The nature of such information may depend on the use case and on the AI / ML algorithm.

[0111] The actor function 408 may receive the output from the model inference function 406, which may trigger or perform corresponding actions. The actor function 408 may trigger actions directed to other entities or to itself. The feedback generated by the actor function 408 may provide information used to derive training data, inference data or to monitor the performance of the AI / ML Model. As noted above, input data for a data collection function 402 may include this feedback from the actor function 408. The feedback from the actor function 408 or other network entities (e.g., via data collection function 402) may also be used at the model inference function 406.

[0112] Example Method Figure 5 is a flow diagram depicting an example method 500 for automatically collecting and logging surgical stages, events, and actions, and estimating and assessing patient (e.g., patient 180) injury risk during surgery (e.g., a lumbar surgery).

[0113] In one aspect, the method 500 optionally begins at operation 502 with determining one or more baseline neurological response waveforms of the patient 180 prior to performing surgery on the patient 180. In some aspects, operation 502 may be performed by the risk assessment, logging, alerting, modulating device 150 described in Figure 1.

[0114] In one aspect, the method 500 optionally includes, at operation 504, automatically collecting procedural data during the surgery. In some aspects, operation 504 is performed by the stimulating electrodes 120, the recording electrodes 170, and / or the navigation / robotics device 110 described in Figure 1. In some aspects, operation 504 is performed at least in part by collecting user input in response to a prompt from the system 100.

[0115] In one aspect, the method 500 optionally includes, at operation 506, automatically collecting physiological data of the patient 180 during the surgery. In some aspects, operation 506 is performed by the stimulating electrodes 120, the recording electrodes 170, and / or the navigation / robotics device 110 described in Figure 1.

[0116] In one aspect, the method 500 optionally includes, at operation 508, automatically collecting neurological response waveform data of the patient 180. In some aspects, operation 508 is performed by the stimulating electrodes 120, the recording electrodes 170, and / or the navigation / robotics device 110 described in Figure 1.

[0117] In one aspect, the method 500 optionally includes, at operation 510, automatically providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system. In some aspects, operation 510 is performed by the stimulating electrodes 120, the recording electrodes 170, the navigation / robotics device 110, the response processing device 130, the surgical instrument / stage / event / action identification device 140, and / or the risk assessment, logging, alerting, modulating device 150 described in Figure 1.

[0118] In one aspect, the method 500 optionally includes, at operation 512, comparing, by the risk assessment system, logging, alerting, modulating device 150, the neurological response waveform with the baseline neurological response waveform. In some aspects, operation 512 is performed by the risk assessment, logging, alerting, modulating device 150, the response processing device 130, and / or the surgical instrument / stage / event / action identification device 140 described in Figure 1. In one aspect, the method 500 optionally includes, at operation 514, assembling a level of risk of injury to the patient 180 based on the comparison and further based on the procedural data and the physiological data.

[0119] Example Apparatus

[0120] Figure 6 depicts a block diagram illustrating an apparatus 600 for automatically collecting and logging surgical stages, events, and actions, and estimating and assessing patient injury risk during surgery. As shown, the apparatus 600 includes a processing system 605 with a number of input / output interfaces 610, processors 615, and computer- readable memory 620. While shown as a single device, in some embodiments, functions of the apparatus 600 may be distributed across multiple physical devices. The apparatus 600 may include functions of one or more of response processing device 130, surgical instrument, stage, event, action identification device 140, and / or risk assessment, logging, alerting, and / or modulating device 150. In some aspects, the apparatus 600 is connected or, or in communication with, one or more of display 160, stimulating electrodes 120, recording electrodes 170, and / or navigation / robotics device 110. In some aspects, the apparatus includes the functionality of the display 160 and / or navigation / robotics device 110.

[0121] I / O interfaces 610 may connect the apparatus 600, wired or wirelessly, to recording electrodes 170 to enable apparatus 600 to obtain resulting muscle response electrical waveforms from recording electrodes 170 and / or to provide control to recording electrodes 170.

[0122] I / O interfaces 610 may connect the apparatus 600, wired or wirelessly, to stimulating electrodes 120 to enable apparatus 600 to control the stimulating electrodes 120.

[0123] I / O interfaces 610 may connect the apparatus 600, wired or wirelessly, to display 160 to enable apparatus 600 to display neurophysical monitoring information generated based on processing the resulting muscle response electrical waveforms to the stimulation.

[0124] I / O interfaces 610 may provide one or more user interfaces enabling a user to interact with the apparatus 600, such as buttons, touch screens, switches, keyboards, mouse, or other user interfaces.

[0125] As shown in Figure 6, the processing system 605 includes one or more processors 615 and computer-readable media / memory 620. The processor(s) 615 may include circuitry for performing one or more of the operations of method 500. The computer- readable media / memory 620 may include instructions, executable by the one or more processor(s) 615 to perform the operations of method 500. The computer-readable media / memory 620 may store other information, such as collected data (e.g., resulting muscle response electrical waveform data) and information generated from the data.

[0126] In some aspects, the processor(s) 615 include circuitry 625 for obtaining resulting signals from recording electrodes 170. In some aspects, the processor(s) 615 include circuitry 630 for processing the resulting signals. In some aspects, processing the resulting signals includes averaging the muscle response electrical waveforms to several stimuli together to reduce noise, improve the signal-to-noise ratio, and produce a cleaner signal. In some aspects, the processing the resulting signals includes automatically determining adequacy of the resulting signals.

[0127] In some aspects, software may also be used to compare neuromonitoring results between modalities. In some aspects, the software may be utilized to compare neuromonitoring results with physiological results, surgical stages, surgical events, and surgical actions. In some aspects, the software may be utilized to compare neuromonitoring results with anesthesia information to dynamically adjust alerting criteria based on changes in signals due to systemic effects of paralytic use, anesthesia, blood pressure changes, or other non- surgery related events.

[0128] In some aspects, the processor(s) include circuitry 635 for controlling the stimulating electrodes based on the processing of the resulting signals. In some aspects, the apparatus 600 controls the stimulation by optimizing the stimulation pulses. The apparatus 600 may optimize the stimulation intensity responses by adjusting the latency, amplitude, and response of the stimulating pulses.

[0129] In some aspects, the processor(s) 615 include circuitry 640 for outputting information, generated based on processing the resulting signals, to the display 160.

[0130] In some aspects, the apparatus 600 automatically detects and identifies impending neural injury based on changes in the resulting muscle response electrical waveform signals. The apparatus 600 may identify changes in neural function by comparing baseline muscle responses (e.g., based on resultant electrical waveforms obtained pre-surgery or at the beginning of the surgical procedure) to those obtained during surgery. For example, the apparatus 600 may compare the amplitude, latency, morphology, and / or area under the curve of the baseline and intra-operative muscle response electrical waveforms. The apparatus 600 may further identify changes in neural function by taking into account information from an anesthesia machine or a neuromuscular testing machine. Based on the comparison, the apparatus 600 can determine whether changes in the resulting electrical waveforms are due to anesthesia or the presence of paralytic agents. The apparatus 600 may further identify changes in neural function by taking into account information from a blood pressure machine and / or a pulse oximetry machine to determine whether changes in the resulting muscle response electrical waveforms are due to blood pressure or perfusion. The apparatus 600 may further identify changes in neural function by taking into account surgical stage data (e.g., images from camera 112).

[0131] In some aspects, the apparatus 600 outputs an alert to a use when changes are identified in the resulting muscle response electrical waveforms. For example, the alert may output to the display 160, output directly from the response processing devices, or output to another device. The alert may be a visual alert, a text alert, an audible sound or message, an alarm, a light, a color coding, or other type of alert.

[0132] In some aspects, the apparatus 600 generates and outputs a recommendation for action to ameliorate the identified neural dysfunction.

[0133] In some aspects, apparatus 600 accounts for changes in the resulting muscle response electrical waveforms that are due to systemic effects of paralytic use, anesthesia, or blood pressure changes to eliminate alerts that are false positives.

[0134] In some aspects, the apparatus 600 includes one or more other components (not shown), such as electric stimulators, pre-amplifies, amplifiers, and / or computer components.

[0135] In some aspects, a non-transitory storage medium including instructions to enable one or more machines (e.g., computers, etc.) to implement or signal the need to implement one or more of the described features is disclosed. Similarly, computer systems configured to implement the described methods that may include one or more processors and one or more memories coupled to the one or more processors are disclosed. A memory, which can include a non-transitory computer-readable or machine-readable storage medium, may include, encode, or store one or more programs that cause one or more processors to perform the one or more of the operations described herein is disclosed. Computer- implemented methods consistent with one or more implementations of the current subject matter may be implemented by one or more data processors residing in a single computing system or multiple computing systems. In some aspects, the multiple computing systems may be connected and may exchange data, commands, or other instructions via the one or more connections. In some aspects, the connections may include a connection over a network or via a direct connection between the one or more of the multiple computing systems. In some aspects, implementations may account for or further utilize other methods of producing optimized motor or sensory responses including multi-polar stimulation or recordings.

[0136] Embodiments

[0137] The following are contemplated by the authors of this disclosure as possible, nonlimiting embodiments of the inventive concepts discussed herein:

[0138] Embodiment 1. A method for automated risk assessment during surgery on a patient, the method comprising: determining one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient; automatically collecting procedural data during the surgery; automatically collecting physiological data of the patient during the surgery; automatically collecting neurological response waveform data of the patient; automatically providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system; comparing, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform; and assessing a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data.

[0139] Embodiment 2. The method of embodiment 1, wherein the procedural data is provided by a surgical navigation system.

[0140] Embodiment 3. The method of embodiment 2, wherein the procedural data provided by the surgical navigation system comprises at least one of procedure workflow, instrument selection, and instrument tracking.

[0141] Embodiment 4. The method of any combination of embodiments 1-3, wherein automatically collecting the procedural data comprises collecting imaging data from at least one of: an infrared camera, a visible-light camera, an x-ray imaging device, a radio frequency identification (RFID) reader, a surgical navigation system, or a surgical robotic system.

[0142] Embodiment 5. The method of any combination of embodiments 1-4, wherein automatically collecting the procedural data comprises automatically identifying a presence or an absence of one or more surgical instruments based on the imaging data.

[0143] Embodiment 6. The method of any combination of embodiments 1-5, wherein automatically collecting the procedural data comprises automatically identifying a presence or an absence of one or more operating room personnel based on the imaging data.

[0144] Embodiment 7. The method of any combination of embodiments 1-6, wherein automatically collecting the procedural data comprises automatically identifying a presence or an absence of one or more surgical equipment based on the imaging data. Embodiment 8. The method of any combination of embodiments 1-7, wherein automatically collecting the procedural data comprises automatically identifying occurrence of one or more surgical actions or events based on the imaging data.

[0145] Embodiment 9. The method of any combination of embodiments 1-8, wherein automatically collecting the procedural data comprises automatically identifying a surgical stage based on the imaging data.

[0146] Embodiment 10. The method of any combination of embodiments 1-9, wherein assessing the level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data includes adjusting an alert threshold, or adjusting the collected neurological response waveforms, based on the procedural data, wherein the alert threshold is a threshold difference between the baseline neurological response waveform and the collected neurological response waveform.

[0147] Embodiment 11. The method of any combination of embodiments 1-10, further comprising automatically logging, by the risk assessment system, at least one of: the collected procedural data, the collected physiological data, or the collected neurological response waveform data.

[0148] Embodiment 12. The method of any combination of embodiments 1-11, further comprising, prior to performing the surgery on the patient: setting a baseline risk level based on a type of the surgery and a clinical state of the patient; and determining one or more baseline patient structures at risk based on the type of the surgery and the clinical state of the patient.

[0149] Embodiment 13. The method of embodiment 12, further comprising, prior to performing the surgery on the patient, determining a monitoring plan based on the baseline risk level and the one or more baseline patient structures at risk, wherein the monitoring plan specifies a frequency and location of monitoring for collection of at least one of: the procedural data, the physiological data, or the neurological response waveform data.

[0150] Embodiment 14. The method of any combination of embodiments 1-13, wherein assessing the level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data includes adjusting an alert threshold, or adjusting the collected neurological response waveforms, based on at least one of: collected anesthesia data or the collected physiological data.

[0151] Embodiment 15. The method of any combination of embodiments 1-14, further comprising estimating, by the risk assessment system, one or more patient structures at risk based on the comparison and further based on the procedural data and the physiological data, wherein the patient structures at risk comprise one or more anatomical locations of the risk to the patient.

[0152] Embodiment 16. The method of embodiment 15, further comprising, in response to the level of risk and the one or more patient structures at risk, automatically adjusting, by the risk assessment system, at least one of: one or more monitoring locations, one or more types of monitoring, and one or more monitoring frequencies for collecting at least one of: additional procedural data, additional physiological data, or additional neurological response waveform data.

[0153] Embodiment 17. The method of any combination of embodiments 15-16, further comprising, in response to the level of risk and the one or more patient structures at risk, automatically adjusting one or more alerting criteria of one or more monitoring modalities.

[0154] Embodiment 18. The method of any combination of embodiments 1-17, further comprising activating an alert, to a user of the risk assessment system, in response to the level of risk exceeding an alert threshold.

[0155] Embodiment 19. A non-transitory computer-readable medium comprising executable instructions that, when executed by a processor of an apparatus, cause the apparatus to perform a method in accordance with any one of embodiments 1-18.

[0156] Embodiment 20. A system for automated risk assessment during surgery on a patient, the system comprising: one or more stimulating electrodes; one or more recording electrodes; a computing device configured to: determine one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient; automatically collect procedural data during the surgery; automatically collect physiological data of the patient during the surgery; automatically collect neurological response waveform data of the patient; automatically provide the procedural data, the physiological data, and neurological response waveform data to a risk assessment system; compare, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform; and assess a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data.

[0157] Embodiment 21. The system of embodiment 20, further comprising one or more robotics devices.

[0158] Embodiment 22. The system of any combination of embodiments 20-21, further comprising one or more cameras. Embodiment 23. An apparatus for automated risk assessment during surgery on a patient, the system comprising: means for determining one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient; means for automatically collecting procedural data during the surgery; means for automatically collecting physiological data of the patient during the surgery; means for automatically collecting neurological response waveform data of the patient; means for automatically providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system; means for comparing, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform; and means for assessing a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data.

[0159] Embodiment 24. A method for risk assessment during surgery on a patient, the method comprising: determining one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient; collecting procedural data during the surgery; collecting physiological data of the patient during the surgery; collecting neurological response waveform data of the patient; providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system; comparing, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform; and assessing a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data; wherein at least one of the above method steps is performed automatically.

[0160] Embodiment 25. The method of embodiment 24, further comprising receiving input from a user as to a type of surgery to be performed on the patient.

[0161] Embodiment 26. The method of embodiment 25, wherein the type of surgery to be performed on the patient comprises at least two stages, each having an estimated duration, and each stage being distinct in at least one of risk level, expected neurological response waveforms, and expected physiological data.

[0162] Embodiment 27. The method of embodiment 26, wherein the collecting physiological data and the collecting neurological response waveform data occurs automatically as the surgery progresses from one stage to the next.

[0163] Embodiment 28. The method of embodiment 26, wherein a user provides an update on the progress of the surgery from one stage to the next. Embodiment 29. The method of embodiment 28, wherein the user update is provided in response to a prompt that is automatically generated based on at least one of passage of time as measured against the estimated duration of a stage of the surgery, a change in the collected physiological data, a change in the collected neurological response waveform data, and the collected procedural data.

[0164] Embodiment 30. The method of any one of embodiments 24-29, wherein the procedural data is provided by a surgical navigation system.

[0165] Embodiment 31. The method of embodiment 30, wherein the procedural data provided by the surgical navigation system comprises at least one of procedure workflow, instrument selection, and instrument tracking.

[0166] Embodiment 32. The method of any one of embodiments 24-31, wherein collecting the procedural data comprises automatically collecting imaging data from at least one of: an infrared camera, a visible-light camera, an x-ray imaging device, a radio frequency identification (RFID) reader, a surgical navigation system, or a surgical robotic system.

[0167] Embodiment 33. The method of any one of embodiments 24-32, wherein collecting the procedural data comprises automatically identifying a presence or an absence of one or more surgical instruments based on the imaging data.

[0168] Embodiment 34. The method of any one of embodiments 24-33, wherein collecting the procedural data comprises automatically identifying a presence or an absence of one or more operating room personnel based on the imaging data.

[0169] Embodiment 35. The method of any combination of embodiments 24-34, wherein collecting the procedural data comprises automatically identifying a presence or an absence of one or more surgical equipment based on the imaging data.

[0170] Embodiment 36. The method of any one of embodiments 24-35, wherein collecting the procedural data comprises automatically identifying occurrence of one or more surgical actions or events based on the imaging data.

[0171] Embodiment 37. The method of any one of embodiments 24-36, wherein collecting the procedural data comprises automatically identifying a surgical stage based on the imaging data.

[0172] Embodiment 38. The method of any one of embodiments 24-37, further comprising prompting a user for confirmation of the collected procedural data, which confirmation is provided to the risk assessment system. Embodiment 39. The method of embodiment 38, wherein the confirmation affects at least one of an expected risk level, an expected physiological data of the patient, and an expected neurological response waveform of the patient.

[0173] Embodiment 40. The method of any one of embodiments 24-39, wherein assessing the level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data includes adjusting an alert threshold, or adjusting the collected neurological response waveforms, based on the procedural data, wherein the alert threshold is a threshold difference between the baseline neurological response waveform and the collected neurological response waveform.

[0174] Embodiment 41. The method of any one of embodiment 24-40, further comprising automatically logging, by the risk assessment system, at least one of: the collected procedural data, the collected physiological data, or the collected neurological response waveform data.

[0175] Embodiment 42. The method of any one of embodiments 24-41, further comprising, prior to performing the surgery on the patient: setting a baseline risk level based on a type of the surgery and a clinical state of the patient; and determining one or more baseline patient structures at risk based on the type of the surgery and the clinical state of the patient.

[0176] Embodiment 43. The method of embodiment 42, further comprising, prior to performing the surgery on the patient, determining a monitoring plan based on the baseline risk level and the one or more baseline patient structures at risk, wherein the monitoring plan specifies a frequency and location of monitoring for collection of at least one of: the procedural data, the physiological data, or the neurological response waveform data.

[0177] Embodiment 44. The method of any one of embodiments 24-43, wherein assessing the level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data includes adjusting an alert threshold, or adjusting the collected neurological response waveforms, based on at least one of: collected anesthesia data or the collected physiological data.

[0178] Embodiment 45. The method of any one of embodiments 24-44, further comprising estimating, by the risk assessment system, one or more patient structures at risk based on the comparison and further based on the procedural data and the physiological data, wherein the patient structures at risk comprise one or more anatomical locations of the risk to the patient. Embodiment 46. The method of embodiment 45, further comprising, in response to the level of risk and the one or more patient structures at risk, automatically adjusting, by the risk assessment system, at least one of: one or more monitoring locations, one or more types of monitoring, and one or more monitoring frequencies for collecting at least one of: additional procedural data, additional physiological data, or additional neurological response waveform data.

[0179] Embodiment 47. The method of either one of embodiments 45 or 46, further comprising, in response to the level of risk and the one or more patient structures at risk, automatically adjusting one or more alerting criteria of one or more monitoring modalities.

[0180] Embodiment 48. The method of any one of embodiments 24-47, further comprising activating an alert, to a user of the risk assessment system, in response to the level of risk exceeding an alert threshold.

[0181] Embodiment 49. A non-transitory computer-readable medium comprising executable instructions that, when executed by a processor of an apparatus, cause the apparatus to perform a method in accordance with any one of embodiments 24-48.

[0182] Embodiment 50. A system for automated risk assessment during surgery on a patient, the system comprising: one or more stimulating electrodes; one or more recording electrodes; a computing device configured to perform a method in accordance with any of embodiments 24-48.

[0183] Embodiment 51. A system for automated risk assessment during surgery on a patient, the system comprising: one or more stimulating electrodes; one or more recording electrodes; a computing device configured to: determine one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient; collect procedural data during the surgery; collect physiological data of the patient during the surgery; collect neurological response waveform data of the patient; provide the procedural data, the physiological data, and neurological response waveform data to a risk assessment system; compare, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform; and assess a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data.

[0184] Embodiment 52. The system of embodiment 51, wherein at least one of the determining one or more baseline neurological response waveforms, the collecting procedural data, the collecting physiological data, the collecting neurological response waveform data, the providing, the comparing, and the assessing is performed automatically without user input.

[0185] Embodiment 53. The system of embodiment 52, wherein at least some of the collected procedural data is received from a user.

[0186] Embodiment 54. The system of either one of embodiments 51 or 52, wherein the collecting procedural data comprises prompting a user to confirm one or more aspects of the procedural data.

[0187] Embodiment 55. The system of any one of embodiments 51-54, further comprising one or more robotics devices.

[0188] Embodiment 56. The system of any one of embodiments 51-55, further comprising one or more cameras.

[0189] Embodiment 57. An apparatus for risk assessment during surgery on a patient, the system comprising: means for automatically determining one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient; means for collecting procedural data during the surgery; means for automatically collecting physiological data of the patient during the surgery; means for automatically collecting neurological response waveform data of the patient; means for automatically providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system; means for comparing, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform; and means for assessing a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data.

[0190] Additional Considerations

[0191] The preceding description is provided to enable any person skilled in the art to practice the various aspects described herein. The examples discussed herein are not limiting of the scope, applicability, or aspects set forth in the claims. While particular aspects have been illustrated and described herein, it should be understood that various other changes and modifications may be made without departing from the spirit and scope of the claimed subject matter. Moreover, although various aspects of the claimed subject matter have been described herein, such aspects need not be utilized in combination. Also, features described with respect to some examples may be combined in some other examples. For example, an apparatus may be implemented or a method may be practiced using any number of the aspects set forth herein. In addition, the scope of the disclosure is intended to cover such an apparatus or method that is practiced using other structure, functionality, or structure and functionality in addition to, or other than, the various aspects of the disclosure set forth herein. It should be understood that any aspect of the disclosure disclosed herein may be embodied by one or more elements of a claim.

[0192] Some of the aspects disclosed herein may have been disclosed in relation to a particular approach (e.g., lateral); however, other approaches (e.g., anterior, posterior, transforaminal, etc.) are also contemplated.

[0193] The aspects disclosed herein (or any part(s) or function(s) thereof) may be implemented using hardware, software, firmware, or a combination thereof and may be implemented in one or more computer systems or other processing systems. In fact, one example aspects may be directed toward one or more computer systems capable of carrying out the functionality described herein

[0194] The various illustrative logical blocks, modules and circuits described in connection with the present disclosure may be implemented or performed with a general purpose processor, a digital signal processor (DSP), an ASIC, a field programmable gate array (FPGA) or other programmable logic device (PLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any commercially available processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, a system on a chip (SoC), or any other such configuration.

[0195] As used herein, “a processor,” “at least one processor” or “one or more processors” generally refers to a single processor configured to perform one or multiple operations or multiple processors configured to collectively perform one or more operations. In the case of multiple processors, performance of the one or more operations could be divided amongst different processors, though one processor may perform multiple operations, and multiple processors could collectively perform a single operation. Similarly, “a memory,” “at least one memory” or “one or more memories” generally refers to a single memory configured to store data and / or instructions, multiple memories configured to collectively store data and / or instructions.

[0196] Unless otherwise indicated, all numbers expressing quantities of ingredients, properties such as molecular weight, reaction conditions, and so forth used in the specification and claims are to be understood as being modified in all instances by the term “about.” Accordingly, unless indicated to the contrary, the numerical parameters set forth in the specification and attached claims are approximations that may vary depending upon the desired properties sought to be obtained by the aspects of the present disclosure. At the very least, and not as an attempt to limit the application of the doctrine of equivalents to the scope of the claims, each numerical parameter should at least be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the present disclosure are approximations, the numerical values set forth in the specific examples are reported as precisely as possible. Any numerical value, however, inherently contains certain errors necessarily resulting from the standard deviation found in their respective testing measurements. In one aspect, the terms “about” and “approximately” refer to numerical parameters within 10% of the indicated range.

[0197] As used herein, a phrase referring to “at least one of’ a list of items refers to any combination of those items, including single members. As an example, “at least one of: a, b, or c” is intended to cover a, b, c, a-b, a-c, b-c, and a-b-c, as well as any combination with multiples of the same element (e.g., a-a, a-a-a, a-a-b, a-a-c, a-b-b, a-c-c, b-b, b-b-b, b-b-c, c-c, and c-c-c or any other ordering of a, b, and c).

[0198] As used herein, the terms “a,” “an,” “the,” and similar referents used in the context of describing the aspects of the present disclosure (especially in the context of the following claims) are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. Recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g., “such as”) provided herein is intended merely to better illuminate the aspects of the present disclosure and does not pose a limitation on the scope of the present disclosure. No language in the specification should be construed as indicating any nonclaimed element essential to the practice of the aspects of the present disclosure.

[0199] As used herein, the term “determining” encompasses a wide variety of actions. For example, “determining” may include calculating, computing, processing, deriving, investigating, looking up (e.g., looking up in a table, a database or another data structure), ascertaining and the like. Also, “determining” may include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory) and the like. Also, “determining” may include resolving, selecting, choosing, establishing and the like.

[0200] Groupings of alternative elements or aspects disclosed herein are not to be construed as limitations. Each group member may be referred to and claimed individually or in any combination with other members of the group or other elements found herein. It is anticipated that one or more members of a group may be included in, or deleted from, a group for reasons of convenience and / or patentability. When any such inclusion or deletion occurs, the specification is deemed to contain the group as modified thus fulfilling the written description of all Markush groups used in the appended claims.

[0201] Certain aspects are described herein, including the best mode known to the author(s) of this disclosure for carrying out the aspects disclosed herein. Variations on these described aspects will become apparent to those of ordinary skill in the art upon reading the foregoing description. The author(s) expects skilled artisans to employ such variations as appropriate, and the author(s) intends for the aspects of the present disclosure to be practiced otherwise than specifically described herein. Accordingly, this disclosure includes all modifications and equivalents of the subject matter recited in the claims appended hereto as permitted by applicable law. Moreover, any combination of the abovedescribed elements in all possible variations thereof is encompassed by the present disclosure unless otherwise indicated herein or otherwise clearly contradicted by context.

[0202] Specific aspects disclosed herein may be further limited in the claims using consisting of or consisting essentially of language. When used in the claims, whether as filed or added per amendment, the transition term “consisting of’ excludes any element, step, or ingredient not specified in the claims. The transition term “consisting essentially of’ limits the scope of a claim to the specified materials or steps and those that do not materially affect the basic and novel characteristic(s). Aspects of this disclosure so claimed are inherently or expressly described and enabled herein.

[0203] Within a claim, reference to an element in the singular is not intended to mean “one and only one” unless specifically so stated, but rather “one or more.” Unless specifically stated otherwise, the term “some” refers to one or more. No claim element is to be construed under the provisions of 35 U.S.C. §112(f) unless the element is expressly recited using the phrase “means for”. All structural and functional equivalents to the elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the claims.

Claims

WHAT IS CLAIMED IS:

1. A system for automated risk assessment during surgery on a patient, the system comprising: one or more stimulating electrodes; one or more recording electrodes; a computing device configured to perform a method for risk assessment during surgery on a patient, the method comprising: determining one or more baseline neurological response waveforms of the patient prior to performing a surgery on the patient; collecting procedural data during the surgery; collecting physiological data of the patient during the surgery; collecting neurological response waveform data of the patient; providing the procedural data, the physiological data, and neurological response waveform data to a risk assessment system; comparing, by the risk assessment system, the neurological response waveform with the baseline neurological response waveform; and assessing a level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data; wherein at least one of the above method steps is performed automatically.

2. The system of claim 1, further comprising receiving input from a user as to a type of surgery to be performed on the patient.

3. The system of claim 2, wherein the type of surgery to be performed on the patient comprises at least two stages, each having an estimated duration, and each stage being distinct in at least one of risk level, expected neurological response waveforms, and expected physiological data.

4. The system of claim 3, wherein the collecting physiological data and the collecting neurological response waveform data occurs automatically as the surgery progresses from one stage to the next.

5. The system of claim 3, wherein a user provides an update on the progress of the surgery from one stage to the next.

6. The system of claim 5, wherein the user update is provided in response to a prompt that is automatically generated based on at least one of passage of time as measured against the estimated duration of a stage of the surgery, a change in the collectedphysiological data, a change in the collected neurological response waveform data, and the collected procedural data.

7. The system of any one of claims 1-6, wherein the procedural data is provided by a surgical navigation system.

8. The system of claim 7, wherein the procedural data provided by the surgical navigation system comprises at least one of procedure workflow, instrument selection, and instrument tracking.

9. The system of any one of claims 1-8, wherein collecting the procedural data comprises automatically collecting imaging data from at least one of: an infrared camera, a visible-light camera, an x-ray imaging device, a radio frequency identification (RFID) reader, a surgical navigation system, or a surgical robotic system.

10. The system of any one of claims 1-9, wherein collecting the procedural data comprises automatically identifying a presence or an absence of one or more surgical instruments based on the imaging data.

11. The system of any one of claims 1-10, wherein collecting the procedural data comprises automatically identifying a presence or an absence of one or more operating room personnel based on the imaging data.

12. The method of any combination of claims 1-11, wherein collecting the procedural data comprises automatically identifying a presence or an absence of one or more surgical equipment based on the imaging data.

13. The method of any one of claims 1-12, wherein collecting the procedural data comprises automatically identifying occurrence of one or more surgical actions or events based on the imaging data.

14. The method of any one of claims 1-13, wherein collecting the procedural data comprises automatically identifying a surgical stage based on the imaging data.

15. The method of any one of claims 1-14, further comprising prompting a user for confirmation of the collected procedural data, which confirmation is provided to the risk assessment system.

16. The method of claim 15, wherein the confirmation affects at least one of an expected risk level, an expected physiological data of the patient, and an expected neurological response waveform of the patient.

17. The method of any one of claims 1-16, wherein assessing the level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data includes adjusting an alert threshold, or adjusting the collectedneurological response waveforms, based on the procedural data, wherein the alert threshold is a threshold difference between the baseline neurological response waveform and the collected neurological response waveform.

18. The method of any one of claims 1-17, further comprising automatically logging, by the risk assessment system, at least one of: the collected procedural data, the collected physiological data, or the collected neurological response waveform data.

19. The method of any one of claims 1-18, further comprising, prior to performing the surgery on the patient: setting a baseline risk level based on a type of the surgery and a clinical state of the patient; and determining one or more baseline patient structures at risk based on the type of the surgery and the clinical state of the patient.

20. The method of embodiment 19, further comprising, prior to performing the surgery on the patient, determining a monitoring plan based on the baseline risk level and the one or more baseline patient structures at risk, wherein the monitoring plan specifies a frequency and location of monitoring for collection of at least one of: the procedural data, the physiological data, or the neurological response waveform data.

21. The method of any one of claims 1-20, wherein assessing the level of risk of injury to the patient based on the comparison and further based on the procedural data and the physiological data includes adjusting an alert threshold, or adjusting the collected neurological response waveforms, based on at least one of: collected anesthesia data or the collected physiological data.

22. The method of any one of claims 1-21, further comprising estimating, by the risk assessment system, one or more patient structures at risk based on the comparison and further based on the procedural data and the physiological data, wherein the patient structures at risk comprise one or more anatomical locations of the risk to the patient.

23. The method of claim 22, further comprising, in response to the level of risk and the one or more patient structures at risk, automatically adjusting, by the risk assessment system, at least one of: one or more monitoring locations, one or more types of monitoring, and one or more monitoring frequencies for collecting at least one of: additional procedural data, additional physiological data, or additional neurological response waveform data.

24. The method of either one of claims 22 or 23, further comprising, in response to the level of risk and the one or more patient structures at risk, automatically adjusting one or more alerting criteria of one or more monitoring modalities.

25. The method of any one of claims 1-24, further comprising activating an alert, to a user of the risk assessment system, in response to the level of risk exceeding an alert threshold.

Images