Intelligent real-time nerve monitoring and early warning system and method based on spinal surgery robot

Abstract

The application belongs to the field of spinal surgery equipment, and discloses an intelligent real-time nerve monitoring and early warning system and method based on a spinal surgery robot. The system comprises a spinal surgery robot body, the spinal surgery robot body is integrated with a processor and a mechanical arm execution unit, the mechanical arm execution unit is electrically connected with the processor, an electromyographic signal acquisition unit is electrically connected with the processor, when performing spinal surgery on a patient, the electromyographic signal acquisition unit is used for acquiring the electromyographic signal of the patient and uploading the electromyographic signal to the processor, the processor is used for risk identification on the electromyographic signal, obtaining a surgery risk result, generating a risk warning and a surgery action adjustment instruction based on the surgery risk result, sending the surgery action adjustment instruction to the mechanical arm execution unit, and the mechanical arm execution unit adjusts the surgery action parameter when responding to the surgery action adjustment instruction. The application can improve the use safety and reliability of the spinal surgery robot.

Description

Intelligent Real-Time Neurological Monitoring and Early Warning System and Method Based on Spinal Surgery Robot Technical Field

[0001] This invention belongs to the field of spinal surgery equipment, specifically relating to an intelligent real-time nerve monitoring and early warning system and method based on a spinal surgery robot. Background Technology

[0002] Spinal surgery is a surgical procedure used to treat spinal-related diseases, including those of the cervical, thoracic, and lumbar spine. The goals of spinal surgery include relieving pain, repairing or stabilizing spinal structures, relieving nerve compression, correcting spinal deformities, or treating spinal infections and tumors.

[0003] Traditional spinal surgery is typically performed manually by a doctor. However, with the development of intelligent technologies, spinal surgery robots have emerged. These high-tech medical devices are designed to assist or perform precise procedures during spinal surgery. These robotic systems are usually controlled by a doctor to improve surgical accuracy, reduce complications, shorten recovery time, and enhance overall surgical outcomes.

[0004] Spinal surgery robots mainly consist of a robotic arm, a navigation system, and a control interface. The robotic arm is primarily used to perform surgical procedures, such as drilling and implant placement. The navigation system is mainly used to provide a three-dimensional view of the spine using advanced imaging technologies (such as CT or MRI), helping surgeons plan the surgical path.

[0005] Spinal surgery robots can operate with millimeter-level precision, reducing the risk of damage to surrounding healthy tissues. Furthermore, the robotic arms are more stable than human hands, reducing vibration and errors during surgery.

[0006] Because there is still a risk of nerve damage to the patient during surgery, and existing spinal surgery robots do not have patient monitoring capabilities, the safety and reliability of existing spinal surgery robots are relatively low, and there is a need to improve the safety and reliability of spinal surgery robots. Summary of the Invention

[0007] The purpose of this invention is to provide an intelligent real-time nerve monitoring and early warning system and method based on a spinal surgery robot, in order to solve the problem that existing spinal surgery robots do not have the function of monitoring patients, which leads to low safety and reliability of existing spinal surgery robots because there is still a risk of nerve damage to patients during surgery.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] In a first aspect, the present invention provides an intelligent real-time neural monitoring and early warning system based on a spinal surgery robot, the system comprising:

[0010] A spinal surgery robot body, wherein the spinal surgery robot body integrates a processor and a robotic arm execution unit, and the robotic arm execution unit is electrically connected to the processor;

[0011] An electromyography (EMG) signal acquisition unit is electrically connected to a processor; during spinal surgery, the EMG signal acquisition unit is used to acquire the patient's EMG signals and upload them to the processor.

[0012] The processor is used to: identify risks from electromyographic signals, obtain surgical risk results, generate risk warnings and surgical action adjustment instructions based on the surgical risk results, send the surgical action adjustment instructions to the robotic arm execution unit, and adjust the surgical action parameters in response to the surgical action adjustment instructions. The surgical action parameters include at least: surgical force, surgical path, or action pause.

[0013] Preferably, the system further includes a display unit electrically connected to the processor, the display unit being used to visually display surgical risk results, risk warnings, and surgical action parameters.

[0014] Preferably, the electromyographic signal includes: electromyographic signal and evoked potential signal; the electromyographic signal acquisition unit includes: electromyographic signal acquisition subunit and evoked potential signal acquisition subunit;

[0015] The electromyography signal acquisition subunit includes: a first surface electrode, a first amplifier, a first filter, and a first analog-to-digital converter. The output terminal of the first surface electrode is electrically connected to the input terminal of the first amplifier, the output terminal of the first amplifier is electrically connected to the input terminal of the first filter, the output terminal of the first filter is electrically connected to the input terminal of the first analog-to-digital converter, and the output terminal of the first analog-to-digital converter is electrically connected to the I / O port of the processor.

[0016] The evoked potential signal acquisition subunit includes: a stimulator, a second surface electrode, a second amplifier, a second filter, an averager, and a second analog-to-digital converter. The controlled terminal of the stimulator is electrically connected to the I / O port of the processor. The output terminal of the second surface electrode is electrically connected to the input terminal of the second amplifier. The output terminal of the second amplifier is electrically connected to the input terminal of the averager. The output terminal of the averager is electrically connected to the input terminal of the second analog-to-digital converter. The output terminal of the second analog-to-digital converter is electrically connected to the I / O port of the processor.

[0017] Preferably, the electromyography signal acquisition unit is further used to: acquire electromyography reference samples of the patient before performing spinal surgery on the patient;

[0018] The processor performs the following steps to identify surgical risks from electromyographic signals and obtain surgical risk results:

[0019] A classification set is constructed based on electromyographic reference samples and electromyographic signals;

[0020] The K-means clustering algorithm is used to cluster the set to be classified, resulting in several clusters and the cluster center of each cluster.

[0021] Within each cluster, calculate the distance between all electromyographic signals in that cluster and the cluster center of that cluster;

[0022] When the distance between any electromyographic signal and the cluster center of the classification cluster exceeds a preset distance, the electromyographic signal is marked as abnormal, and several abnormal electromyographic signals are obtained; wherein, the preset distance is determined by the average intra-cluster distance of the classification cluster;

[0023] The abnormal electromyographic (EMG) signals were classified into different levels to obtain the abnormality level of each EMG signal. The abnormal EMG signals and their corresponding abnormality levels were used as the surgical risk results.

[0024] Secondly, the present invention provides an intelligent real-time neural monitoring and early warning method based on a spinal surgery robot, implemented based on the aforementioned intelligent real-time neural monitoring and early warning system based on a spinal surgery robot, the method comprising:

[0025] Acquire electromyographic signals during spinal surgery on a patient;

[0026] Risk identification is performed on electromyographic signals to obtain surgical risk results;

[0027] Based on the surgical risk results, a risk warning and surgical action adjustment instructions are generated. The surgical action adjustment instructions are sent to the robotic arm execution unit of the intelligent real-time neural monitoring and early warning system based on the spinal surgery robot. When responding to the surgical action adjustment instructions, the robotic arm execution unit adjusts the surgical action parameters. The surgical action parameters include at least: surgical force, surgical path, or action pause.

[0028] The surgical risk outcomes, risk warnings, and surgical procedure parameters are visualized.

[0029] Preferably, before risk identification of the electromyographic signals, the method further includes: preprocessing the electromyographic signals, the preprocessing including at least: data cleaning, standardization and normalization.

[0030] Preferably, the electromyographic signals are used for risk identification to obtain surgical risk results, including:

[0031] Obtain electromyography (EMG) reference samples before performing spinal surgery on patients, and construct a classification set based on the EMG reference samples;

[0032] The acquired electromyographic signals are added to the classification set to obtain the set to be classified;

[0033] The K-means clustering algorithm is used to cluster the set to be classified, resulting in several clusters and the cluster center of each cluster.

[0034] Within each cluster, calculate the distance between all electromyographic signals in that cluster and the cluster center of that cluster;

[0035] When the distance between any electromyographic signal and the cluster center of the classification cluster exceeds a preset distance, the electromyographic signal is marked as abnormal, and several abnormal electromyographic signals are obtained; wherein, the preset distance is determined by the average intra-cluster distance of the classification cluster;

[0036] The abnormal electromyographic (EMG) signals were classified into different levels to obtain the abnormality level of each EMG signal. The abnormal EMG signals and their corresponding abnormality levels were used as the surgical risk results.

[0037] Preferably, the anomaly levels include: Level 1 anomaly, Level 2 anomaly, and Level 3 anomaly, wherein the severity of the anomaly decreases progressively from Level 1 to Level 2 to Level 3.

[0038] Preferably, the abnormal electromyographic signals are classified into different abnormality levels to obtain the abnormality level of each abnormal electromyographic signal, including:

[0039] Extract the sampling time corresponding to each abnormal electromyographic signal;

[0040] Determine whether the sampling times corresponding to each abnormal electromyographic signal are continuous. If so, classify the abnormality level of each abnormal electromyographic signal as Level 1 abnormality.

[0041] If the sampling times corresponding to each abnormal electromyographic signal are not continuous, calculate the interval between two adjacent abnormal electromyographic signals.

[0042] Determine whether all intervals are the same. If not, classify each abnormal electromyographic signal as a level 2 abnormality. If so, classify each abnormal electromyographic signal as a level 3 abnormality.

[0043] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described intelligent real-time neural monitoring and early warning method based on a spinal surgery robot.

[0044] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described intelligent real-time neural monitoring and early warning method based on a spinal surgery robot.

[0045] Beneficial effects:

[0046] The spinal robot of this invention is equipped with an electromyography (EMG) signal acquisition unit, which can be used to acquire the patient's EMG signals in real time and then upload the EMG signals to the spinal robot's processor. The processor analyzes the EMG signals, identifies risky EMG signals, and generates risk warnings and surgical action adjustment instructions. It can promptly warn of abnormal EMG signals. Furthermore, the robotic arm execution unit adjusts the surgical action parameters in response to the surgical action adjustment instructions to avoid damage to the patient's nerves, thereby improving the safety and reliability of the spinal surgery robot. Attached Figure Description

[0047] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0048] Figure 1 is a block diagram of an intelligent real-time nerve monitoring and early warning system based on a spinal surgery robot provided in one embodiment of the present invention;

[0049] Figure 2 is a flowchart of an intelligent real-time neural monitoring and early warning method based on a spinal surgery robot provided by one embodiment of the present invention. Detailed Implementation

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0051] Example 1

[0052] Figure 1 is a block diagram of an intelligent real-time neural monitoring and early warning system based on a spinal surgery robot according to one embodiment of the present invention. As shown in Figure 1, the intelligent real-time neural monitoring and early warning system based on a spinal surgery robot includes: a spinal surgery robot body and an electromyography signal acquisition unit.

[0053] The spinal surgery robot body integrates a processor and a robotic arm execution unit. The robotic arm execution unit is electrically connected to the processor. The hardware structure of the spinal surgery robot body is existing technology and is not described in detail in this embodiment.

[0054] The electromyography (EMG) signal acquisition unit is electrically connected to the processor; during spinal surgery, the EMG signal acquisition unit is used to acquire the patient's EMG signals and upload them to the processor.

[0055] The processor is used to: identify risks from electromyographic signals, obtain surgical risk results, generate risk warnings and surgical action adjustment instructions based on the surgical risk results, send the surgical action adjustment instructions to the robotic arm execution unit, and adjust the surgical action parameters in response to the surgical action adjustment instructions. The surgical action parameters include at least: surgical force, surgical path, or action pause.

[0056] As a further optimization of this embodiment, the electromyographic signal includes: electromyography signal and evoked potential signal; the electromyographic signal acquisition unit includes: electromyography signal acquisition subunit and evoked potential signal acquisition subunit;

[0057] The electromyography signal acquisition subunit includes: a first surface electrode, a first amplifier, a first filter, and a first analog-to-digital converter. The output terminal of the first surface electrode is electrically connected to the input terminal of the first amplifier, the output terminal of the first amplifier is electrically connected to the input terminal of the first filter, the output terminal of the first filter is electrically connected to the input terminal of the first analog-to-digital converter, and the output terminal of the first analog-to-digital converter is electrically connected to the I / O port of the processor.

[0058] In this embodiment, during the surgery, if the patient experiences muscle spasms, cramps, or increased muscle fatigue, the frequency or amplitude of the electromyographic signal will change. For example:

[0059] 1. During muscle twitching or spasms, the frequency of electromyographic signals increases because muscle fibers are rapidly and frequently activated in a short period of time.

[0060] 2. As muscle fatigue increases, in order to maintain power output, muscles may recruit more motor units at a higher frequency;

[0061] 3. Neuromuscular diseases may reduce the frequency of muscle activation due to decreased recruitment of motor units or slowed conduction speed of muscle fibers.

[0062] Therefore, the patient's electromyography (EMG) signal can be acquired through the first surface electrode. Then, the EMG signal is amplified and filtered using the first amplifier and the first filter. The processed signal is then converted from an analog signal to a digital signal by the first analog-to-digital converter, i.e., a digital EMG signal. After the digital EMG signal is sent to the processor, the processor analyzes and processes it to obtain the patient's EMG signal map.

[0063] The evoked potential signal acquisition subunit includes: a stimulator, a second surface electrode, a second amplifier, a second filter, an averager, and a second analog-to-digital converter. The controlled terminal of the stimulator is electrically connected to the I / O port of the processor. The output terminal of the second surface electrode is electrically connected to the input terminal of the second amplifier. The output terminal of the second amplifier is electrically connected to the input terminal of the averager. The output terminal of the averager is electrically connected to the input terminal of the second analog-to-digital converter. The output terminal of the second analog-to-digital converter is electrically connected to the I / O port of the processor.

[0064] In this embodiment, the stimulator is used to apply electrical stimulation to the nervous system to induce a response; the second surface electrode can record the patient's electromyographic response, i.e., the evoked potential signal, which is also amplified and filtered by the second amplifier and the second filter; since the evoked potential signal is usually very weak, it is necessary to superimpose and average the signal through multiple stimulations and recordings in order to extract a clear waveform of the evoked potential signal; therefore, the averager superimposes and averages the signal through multiple stimulations and recordings to obtain the processed evoked potential signal; the second analog-to-digital converter then performs analog-to-digital conversion on the processed evoked potential signal, converting the analog evoked potential signal into a digital evoked potential signal, and sends the digital evoked potential signal to the processor, which analyzes and processes the digital evoked potential signal to obtain the patient's evoked potential signal map.

[0065] As a further optimization of this embodiment, the electromyography (EMG) signal acquisition unit is also used to: acquire EMG reference samples of the patient before performing spinal surgery on the patient; therefore, the steps of the processor to perform risk identification on EMG signals and obtain surgical risk results include: constructing a set to be classified based on the EMG reference samples and EMG signals; clustering the set to be classified based on the K-means clustering algorithm to obtain several classification clusters and the cluster center corresponding to each classification cluster; calculating the distance between all EMG signals in the classification cluster and the cluster center of the classification cluster in each classification cluster; when the distance between any EMG signal and the cluster center of the classification cluster exceeds a preset distance, marking the EMG signal as abnormal, and obtaining several abnormal EMG signals; wherein, the preset distance is determined by the average intra-cluster distance of the classification cluster; classifying each abnormal EMG signal into an abnormality level to obtain the abnormality level of each abnormal EMG signal, and using each abnormal EMG signal and the abnormality level corresponding to each abnormal EMG signal as the surgical risk result.

[0066] As a further optimization of this embodiment, the system further includes a display unit, which is electrically connected to the processor and is used to visualize surgical risk results, risk warnings, and surgical action parameters.

[0067] In this embodiment, the display unit can be a liquid crystal display (LCD) to visualize surgical risk outcomes, risk warnings, and surgical action parameters, making it easier for medical staff to view relevant parameters during the surgical process.

[0068] In this embodiment, the spinal robot is equipped with an electromyography (EMG) signal acquisition unit. This unit can collect the patient's EMG signals in real time and then upload them to the spinal robot's processor. The processor analyzes the EMG signals, identifies risky EMG signals, and generates risk warnings and surgical action adjustment commands. This allows for timely warnings of abnormal EMG signals. Furthermore, the robotic arm execution unit adjusts surgical action parameters in response to surgical action adjustment commands to avoid damage to the patient's nerves, thereby improving the safety and reliability of the spinal surgery robot.

[0069] Example 2

[0070] Figure 2 is a flowchart of an intelligent real-time neural monitoring and early warning method based on a spinal surgery robot according to an embodiment of the present invention. As shown in Figure 2, this embodiment provides an intelligent real-time neural monitoring and early warning method based on a spinal surgery robot. The method is implemented based on the intelligent real-time neural monitoring and early warning system based on a spinal surgery robot in Embodiment 1. The method mainly runs in a processor and includes:

[0071] Step S10: Acquire electromyographic signals during spinal surgery on the patient; In this embodiment, an electromyographic signal acquisition unit can be used to acquire electromyographic signals of the patient during spinal surgery.

[0072] Step S20: Perform risk identification on electromyographic signals to obtain surgical risk results.

[0073] In this embodiment, before risk identification of the electromyographic signal, the method further includes: preprocessing the electromyographic signal, the preprocessing including at least: data cleaning, standardization and normalization. Through preprocessing, high-frequency and low-frequency noise unrelated to nerve signals in the electromyographic signal can be removed, and the signal can be standardized to a uniform range to facilitate comparison and analysis.

[0074] After preprocessing the electromyographic (EMG) signals, the risk identification process begins. The specific identification steps are as follows:

[0075] Step S201: Obtain electromyography (EMG) reference samples before spinal surgery on the patient, and construct a classification set based on the EMG reference samples. In this embodiment, since the actual EMG signals of each patient are different, the traditional method of directly classifying EMG signals using a fixed threshold indicates that the patient's physical condition is abnormal. However, in practice, due to the differences in patients' bodies, the muscle structure and size of each person are different, and the EMG signals of each person are different. Therefore, the traditional fixed threshold cannot accurately judge the EMG signals of each patient. Therefore, this application collects the patient's EMG signals before surgery as reference samples. At this time, the EMG reference samples are sample data collected when the patient's physical characteristics are relatively good.

[0076] Step S202: Add the acquired electromyographic signals to the classification set to obtain the set to be classified.

[0077] Step S203: Cluster the set to be classified based on the K-means clustering algorithm to obtain several clusters and the cluster center of each cluster.

[0078] Step S204: In each cluster, calculate the distance between all electromyographic signals in that cluster and the cluster center of that cluster.

[0079] Step S205: When the distance between any electromyographic signal and the cluster center of the classification cluster exceeds a preset distance, the electromyographic signal is marked as abnormal, and several abnormal electromyographic signals are obtained; wherein, the preset distance is determined by the average intra-cluster distance of the classification cluster.

[0080] Step S206: Classify the abnormal electromyographic signals into different levels to obtain the abnormality level of each abnormal electromyographic signal. Use each abnormal electromyographic signal and its corresponding abnormality level as the surgical risk result.

[0081] In this embodiment, the set to be classified contains electromyographic (EMG) signals before surgery and EMG signals during surgery. The EMG signals from the two different surgical processes are mixed together and clustered using the K-means clustering algorithm to determine a threshold for judging whether the EMG signals are abnormal. This threshold is not fixed but dynamically adjusted according to the differences among patients, which improves the flexibility, practicality and accuracy of abnormality judgment.

[0082] In this embodiment, the abnormalities in electromyographic signals vary in severity, and different degrees of severity require different adjustments to the surgical procedures of the spinal robot. Therefore, as a further optimization of this embodiment, the abnormality levels include: Level 1 abnormality, Level 2 abnormality, and Level 3 abnormality, wherein the severity of Level 1, Level 2, and Level 3 abnormalities gradually decreases.

[0083] Therefore, for step S206, the specific steps for classifying the abnormality level of each abnormal electromyographic signal are as follows:

[0084] Step a10: Extract the sampling time corresponding to each abnormal electromyographic signal.

[0085] Step a20: Determine whether the sampling time corresponding to each abnormal electromyographic signal is continuous. If so, classify the abnormality level of each abnormal electromyographic signal into Level 1 abnormality. In the case of Level 1 abnormality, it indicates that the patient's vital signs are deteriorating rapidly and the surgery needs to be suspended in time.

[0086] Step a30: If the sampling times corresponding to each abnormal electromyographic signal are not continuous, calculate the interval between two adjacent abnormal electromyographic signals.

[0087] Step a40: Determine whether all interval durations are the same. If not, classify the abnormality level of each abnormal electromyographic signal as Level II abnormality; if yes, classify the abnormality level of each abnormal electromyographic signal as Level III abnormality. In this embodiment, when all interval durations are the same, it indicates that the patient's electromyographic signal fluctuations are stable, and it is necessary to pay close attention to the patient's surgical process. If abnormalities occur, the surgery should be suspended or the surgical intensity and surgical path should be adjusted in time. When the interval durations are not the same, it indicates that the patient's characteristics are continuously deteriorating, and it is necessary to adjust the surgical intensity and surgical path in time.

[0088] Step S30: Generate risk warning and surgical action adjustment instructions based on surgical risk results, and send the surgical action adjustment instructions to the robotic arm execution unit of the intelligent real-time neural monitoring and early warning system based on the spinal surgery robot. When responding to the surgical action adjustment instructions, the robotic arm execution unit adjusts the surgical action parameters, which include at least: surgical force, surgical path or action pause.

[0089] Step S40: Visualize the surgical risk results, risk warnings, and surgical action parameters.

[0090] This invention uses an electromyography (EMG) signal acquisition unit to collect the patient's EMG signals in real time, and then uploads the EMG signals to the processor of the spinal robot. The processor analyzes the EMG signals, identifies risky EMG signals, and generates risk warnings and surgical action adjustment instructions. It can promptly warn of abnormal EMG signals. Furthermore, the robotic arm execution unit adjusts the surgical action parameters in response to the surgical action adjustment instructions to avoid damage to the patient's nerves, thereby improving the safety and reliability of the spinal surgery robot.

[0091] Example 3

[0092] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent real-time neural monitoring and early warning method based on a spinal surgery robot in Embodiment 2.

[0093] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the intelligent real-time neural monitoring and early warning method based on a spinal surgery robot in Embodiment 2.

[0094] This invention uses an electromyography (EMG) signal acquisition unit to collect the patient's EMG signals in real time, and then uploads the EMG signals to the processor of the spinal robot. The processor analyzes the EMG signals, identifies risky EMG signals, and generates risk warnings and surgical action adjustment instructions. It can promptly warn of abnormal EMG signals. Furthermore, the robotic arm execution unit adjusts the surgical action parameters in response to the surgical action adjustment instructions to avoid damage to the patient's nerves, thereby improving the safety and reliability of the spinal surgery robot.

[0095] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.

[0097] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An intelligent real-time neural monitoring and early warning system based on a spinal surgery robot, characterized in that, The system includes: a spinal surgery robot body, which integrates a processor and a robotic arm execution unit, the robotic arm execution unit being electrically connected to the processor; and an electromyography (EMG) signal acquisition unit, electrically connected to the processor. During spinal surgery, the EMG signal acquisition unit acquires the patient's EMG signals in real time and uploads them to the processor. The processor is used to: identify risks in the EMG signals, obtain surgical risk results, generate risk warnings and surgical action adjustment commands based on the surgical risk results, and send the surgical action adjustment commands to the robotic arm execution unit. The robotic arm execution unit adjusts the surgical action parameters in response to the surgical action adjustment commands, the surgical action parameters being at least... This includes: surgical force, surgical path, or pause in movement; the electromyographic signals include: electromyography (EMG) signals and evoked potential (EP) signals; the EMG signal acquisition unit includes: an EMG signal acquisition subunit and an EEG signal acquisition subunit; the EMG signal acquisition subunit includes: a first surface electrode, a first amplifier, a first filter, and a first analog-to-digital converter (ADC), wherein the output terminal of the first surface electrode is electrically connected to the input terminal of the first amplifier, the output terminal of the first amplifier is electrically connected to the input terminal of the first filter, the output terminal of the first filter is electrically connected to the input terminal of the first ADC, and the output terminal of the first ADC is electrically connected to the I / O port of the processor; the evoked potential signal acquisition... The subunit includes: a stimulator, a second surface electrode, a second amplifier, a second filter, an averager, and a second analog-to-digital converter. The controlled terminal of the stimulator is electrically connected to the I / O port of the processor. The output terminal of the second surface electrode is electrically connected to the input terminal of the second amplifier. The output terminal of the second amplifier is electrically connected to the input terminal of the averager. The output terminal of the averager is electrically connected to the input terminal of the second analog-to-digital converter. The output terminal of the second analog-to-digital converter is electrically connected to the I / O port of the processor. The electromyography (EMG) signal acquisition unit is also used to: acquire EMG reference samples from the patient before performing spinal surgery; and the processor performs risk identification on the EMG signals to obtain surgical risk results. The steps include: constructing a set to be classified based on electromyographic reference samples and electromyographic signals; clustering the set to be classified using the K-means clustering algorithm to obtain several clusters and the cluster center of each cluster; calculating the distance between all electromyographic signals in each cluster and the cluster center of that cluster; marking any electromyographic signal as abnormal when the distance between any electromyographic signal and the cluster center of that cluster exceeds a preset distance, thus obtaining several abnormal electromyographic signals; wherein, the preset distance is determined by the average intra-cluster distance of the clusters; classifying each abnormal electromyographic signal into an abnormality level to obtain the abnormality level of each abnormal electromyographic signal, and using each abnormal electromyographic signal and its corresponding abnormality level as the surgical risk result.

2. The intelligent real-time neural monitoring and early warning system based on a spinal surgery robot according to claim 1, characterized in that, The system further includes a display unit, which is electrically connected to the processor and is used to visualize surgical risk results, risk warnings, and surgical action parameters.

3. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by a processor to implement an intelligent real-time neural monitoring and early warning method based on a spinal surgery robot. The method is implemented based on the intelligent real-time neural monitoring and early warning system described in any one of claims 1-2. The method includes: acquiring electromyography (EMG) signals during spinal surgery on a patient; preprocessing the EMG signals, the preprocessing including at least: data cleaning, standardization, and normalization; and identifying surgical risks from the EMG signals to obtain surgical risk results, including: acquiring EMG reference samples before spinal surgery on the patient, constructing a classification set based on the EMG reference samples; and adding the acquired EMG signals to the classification set to obtain the surgical risk result. The dataset is classified using the K-means clustering algorithm to obtain several clusters and their corresponding cluster centers. Within each cluster, the distance between all electromyographic (EMG) signals and the cluster center is calculated. If the distance between any EMG signal and the cluster center exceeds a preset distance, the EMG signal is marked as abnormal, resulting in several abnormal EMG signals. The preset distance is determined by the average intra-cluster distance of the clusters. Each abnormal EMG signal is then classified into an abnormality level, and the abnormality level and corresponding abnormality level are used to determine the abnormality level of each signal. As a surgical risk outcome, the abnormality levels include: Level 1, Level 2, and Level 3, with the severity of abnormalities decreasing progressively from Level 1 to Level 3. The abnormality level of each abnormal electromyographic (EMG) signal is determined by classifying the abnormal EMG signal into three levels: extracting the sampling time corresponding to each abnormal EMG signal; determining whether the sampling times corresponding to each abnormal EMG signal are continuous; if so, classifying each abnormal EMG signal as Level 1; if the sampling times corresponding to each abnormal EMG signal are not continuous, calculating the interval duration between two adjacent abnormal EMG signals; and determining the duration of all intervals. If the lengths are all the same, the abnormality level of each abnormal electromyographic signal is classified as Level II; if so, the abnormality level of each abnormal electromyographic signal is classified as Level III. Based on the surgical risk results, risk warnings and surgical action adjustment instructions are generated, and the surgical action adjustment instructions are sent to the robotic arm execution unit of the intelligent real-time nerve monitoring and early warning system based on the spinal surgery robot. When responding to the surgical action adjustment instructions, the robotic arm execution unit adjusts the surgical action parameters, which include at least: surgical force, surgical path, or action pause. The surgical risk results, risk warnings, and surgical action parameters are visualized.

Images