Intraoperative neurological status monitoring report generation system

Abstract

This invention proposes a system for generating intraoperative neurological status monitoring reports. It utilizes automated algorithms to process and analyze data in real time, generating reports based on electromyographic signals during and before surgery, as well as nerve confirmation and comparative analysis. The system eliminates the need for manual report writing, significantly improving report generation efficiency. Furthermore, the system eliminates the need for specialized technicians to manually monitor and capture signals and perform extensive subsequent data analysis; the processing center automatically interprets the signals in real time, alleviating the burden of manual data processing.

Description

Technical Field

[0001] This invention relates to the field of medical data processing and report generation technology, and in particular to a method and system for generating intraoperative neurological status monitoring reports. Background Technology

[0002] With the continuous advancement of medical data processing technology, intraoperative neurological status monitoring has become an indispensable technique in neurosurgery, spinal surgery, and other procedures. By monitoring the patient's neurophysiological signals in real time during surgery, surgeons can assess the impact of surgical procedures on the nervous system, thereby reducing the risk of intraoperative nerve injury. Advanced algorithms are used to process and analyze the data in real time to generate accurate and detailed monitoring reports.

[0003] Existing monitoring reports are typically written manually, which is time-consuming and error-prone, impacting the efficiency of the surgical procedure and resulting in low report generation efficiency. Intraoperative neurological status monitoring generates a massive amount of data, requiring real-time interpretation by specialized technicians, which places high demands on medical resources. Summary of the Invention

[0004] The purpose of this invention is to provide a system for generating intraoperative neurological status monitoring reports to alleviate the technical problems existing in the prior art.

[0005] In a first aspect, the present invention provides a system for generating intraoperative neurological status monitoring reports, comprising:

[0006] The startup module generates a report and sends a report generation instruction to the data processing center based on the user's first operation, and obtains relevant data on the current doctor and patient, as well as information on intraoperative consumables.

[0007] The condition judgment module, after receiving the report generation instruction, obtains the impedance data of the connecting wires and inserted catheters, and judges whether the impedance is lower than the set value based on the impedance data. If it is lower than the set value, the intraoperative data processing steps are performed.

[0008] The first data processing module triggers intraoperative data processing instructions based on the user's second operation. The intraoperative data includes at least the first electromyography (EMG) signal pattern, the corresponding stimulation current magnitude, the corresponding current time scale and amplitude scale, and the maximum amplitude adjustment of the EMG signal. The time scale, amplitude scale, and stimulation current parameters can be set in advance. The specific EMG signal pattern is obtained by using a stimulation probe to collect the EMG response signal corresponding to the surgical target area.

[0009] Furthermore, the nerves near the target surgical object are determined by the first electromyographic signal pattern, and the electromyographic signal pattern at this time is recorded as the second electromyographic signal pattern. The nerve processing unit for determining the nerves near the target surgical object includes the following processing procedures:

[0010] Step 1: Receive intraoperative muscle stimulation and acquire the corresponding electromyographic signal S. Decompose the signal S to obtain multiple sets of different signal curves.

[0011] Step 2: Perform periodic segmentation on multiple sets of different signals, and obtain the electromyographic signal representation Fi for each period based on the following feature extraction algorithm:

[0012] For the two maximum abrupt change points Q1 and Q2 within each period, calculate the distances L1 and L2 from the abrupt change points to the beginning of the corresponding period, respectively; simultaneously, convert the signal within each period into a rectangular wave signal, and obtain the phase eigenvalue θ of the rectangular wave signal within the corresponding period. i The characteristic Fi for each period is calculated using the following formula:

[0013]

[0014] The features of each cycle are fused to form multiple sets of feature labels F corresponding to different signals, where F = F = {F1, F2, F3, ..., F...} N};

[0015] Step 3: Extract the signal curve corresponding to each neural stimulus and perform feature extraction as in Step 2 to obtain feature labels for multiple samples. Based on the feature labels of multiple samples in each class, a classification cluster is formed, and the target neural network is determined based on the clustering degree index.

[0016] The second data processing module triggers a pre-operative data processing instruction to end based on the user's second operation. This instruction includes at least the acquisition of data such as a third electromyographic signal graph, the corresponding stimulation current magnitude, the corresponding scale and amplitude scale, and the maximum amplitude adjustment of the electromyographic signal. Specifically, the electromyographic signal graph is acquired by using a stimulation probe to collect the electromyographic response signal corresponding to the surgical target area.

[0017] Furthermore, the postoperative nerves near the target surgical object are determined by the third electromyographic signal pattern, and the electromyographic signal pattern at this time is recorded as the fourth electromyographic signal pattern. The nerve processing unit near the target surgical object includes the same components as the first data processing module mentioned above, which will not be elaborated here.

[0018] The comparison and analysis module compares and analyzes the obtained second and fourth electromyographic signal images to obtain the similarity of the electromyographic signal images. If the similarity between the two is greater than a preset threshold, the above electromyographic signal images are used as the final electromyographic signal images of the surgical report and output.

[0019] Before outputting the report, the report generation module reconfirms the patient and doctor information. In the report printing and editing section, the second and fourth electromyographic signal images saved during the current surgery are selected and stored in the data table position of the corresponding field in the monitoring report, and finally a neurological status monitoring report is generated.

[0020] The embodiments of this invention bring the following beneficial effects: An automatic algorithm is proposed for real-time data processing and analysis, generating a neurological status monitoring report based on electromyographic signals during and before surgery, as well as nerve confirmation and comparative analysis. The generation of monitoring reports eliminates the need for manual writing, significantly improving the efficiency of report generation and data processing during the surgical procedure. The amount of data generated by intraoperative neurological status monitoring is enormous; with the system proposed in this invention, professional technicians are no longer required to manually monitor and intercept signals in real time and perform extensive subsequent data analysis. The processing center automatically interprets the signals in real time, alleviating the burden of manual data processing.

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of the present invention, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This application includes a block diagram of the system for generating intraoperative neurological status monitoring reports;

[0024] Figure 2 An example of intraoperative electromyographic signal graphics of one embodiment of this application;

[0025] Figure 3 An example of electromyographic signal graphics before the end of surgery according to one embodiment of this application. Detailed Implementation

[0026] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used only to describe differences in name and should not be construed as indicating or implying relative importance. Physical quantities in formulas, unless otherwise specified, should be understood as basic quantities in the International System of Units (SI), or derived quantities derived from basic quantities through mathematical operations such as multiplication, division, differentiation, or integration.

[0028] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0029] like Figure 1 As shown, in a first aspect provided by an embodiment of the present invention, the present invention provides a system for generating intraoperative neurological status monitoring reports, comprising:

[0030] The startup module generates a report and sends a report generation instruction to the data processing center based on the user's first operation, and obtains relevant data on the current doctor and patient, as well as information on intraoperative consumables.

[0031] Specifically, the user's first action can be initiated by the doctor scanning a QR code that is uniquely associated with the surgery. Scanning the code will trigger a report generation instruction to be sent to the data processing center.

[0032] The condition judgment module, after receiving the report generation instruction, obtains the impedance data of the connecting wires and inserted catheters, and judges whether the impedance is lower than the set value based on the impedance data. If it is lower than the set value, the intraoperative data processing steps are performed.

[0033] The first data processing module triggers intraoperative data processing instructions based on the user's second operation. The intraoperative data includes at least the first electromyographic signal graph, the corresponding stimulation current magnitude, the corresponding current time scale and amplitude scale, and the maximum amplitude adjustment of the electromyographic signal. The time scale, amplitude scale, and stimulation current parameters can be set in advance.

[0034] See the appendix for details. Figure 2Intraoperative electromyography (EMG) signal patterns are obtained by using stimulation probes to acquire EMG response signals corresponding to the surgical target area.

[0035] Furthermore, the nerves near the target surgical object are determined by the first electromyographic signal pattern, and the electromyographic signal pattern at this time is recorded as the second electromyographic signal pattern. The nerve processing unit for determining the nerves near the target surgical object includes the following processing procedures:

[0036] Step 1: Receive intraoperative muscle stimulation and acquire the corresponding electromyographic signal S. Decompose the signal S to obtain multiple sets of different signal curves.

[0037] Step 2: Perform periodic segmentation on multiple sets of different signals, and obtain the electromyographic signal representation Fi for each period based on the following feature extraction algorithm:

[0038] For the two maximum abrupt change points Q1 and Q2 within each period, calculate the distances L1 and L2 from the abrupt change points to the beginning of the corresponding period, respectively; simultaneously, convert the signal within each period into a rectangular wave signal, and obtain the phase eigenvalue θ of the rectangular wave signal within the corresponding period. i The characteristic Fi for each period is calculated using the following formula:

[0039]

[0040] The features of each cycle are fused to form multiple sets of feature labels F corresponding to different signals, where F = {F1, F2, F3, ..., F...} n};

[0041] Step 3: Extract the signal curve corresponding to each neural stimulus and perform feature extraction as in Step 2 to obtain feature labels for multiple samples. Based on the feature labels of multiple samples in each class, a classification cluster is formed, and the target neural network is determined based on the clustering degree index.

[0042] Assuming that each category of data samples corresponds to an extracted feature label, the resulting classification clusters are divided into C = {C1, C2, ..., C}. j}, define cluster C i Center point and cluster C j The distance between the center points is D(C) i C j )=d(μ i ,μ j ), where μ represents the center point of cluster C;

[0043]

[0044] To calculate the distance between samples, we define d(·,·) as the distance between two samples, and use the following distance measurement:

[0045]

[0046] Where F is the feature label corresponding to the signal, P is an integer greater than 2, and n is the feature dimension;

[0047] The clustering degree index ND is expressed as follows:

[0048]

[0049] The average distance between cluster samples is denoted as avg(C), and d(·,·) represents the distance between two samples, where k is the number of cluster samples.

[0050] The smaller the ND value, the smaller the intra-class distance and the larger the inter-class distance. Through a preset number of iterations, the signal category of the stimulated nerve is determined based on the clustering results of the current feature label, thereby identifying the target nerve near the target surgical object.

[0051] The second data processing module triggers a pre-operative data processing instruction to end based on the user's second operation. This instruction includes at least the acquisition of data such as a third electromyographic signal graph, the corresponding stimulation current magnitude, the corresponding scale and amplitude scale, and the maximum amplitude adjustment of the electromyographic signal. Specifically, the electromyographic signal graph is acquired by using a stimulation probe to collect the electromyographic response signal corresponding to the surgical target area.

[0052] Furthermore, the postoperative nerves near the target surgical object are determined by the third electromyographic signal pattern, and the electromyographic signal pattern at this time is recorded as the fourth electromyographic signal pattern. The nerve processing unit near the target surgical object includes the same components as the first data processing module mentioned above, which will not be elaborated here.

[0053] For details on the comparative analysis module, please refer to the appendix. Figure 3 The second and fourth electromyographic signal images are compared and analyzed to obtain the similarity of the electromyographic signal images. If the similarity is greater than a preset threshold, the above electromyographic signal images are used as the final electromyographic signal images of the surgical report and output.

[0054] The report generation module reconfirms patient and doctor information before outputting the report. In the report printing and editing section, multiple selected electromyographic (EMG) signal images saved during the current surgery are selected. These EMG signal images are saved as screenshots. Based on the chronological order of the intraoperative data, the screenshots are stored in the corresponding data table positions of the monitoring report, ultimately generating a neurological status monitoring report. Preferably, the second and fourth EMG signal images saved during the current surgery are selected, the corresponding screenshot files are located, and a neurological status monitoring report is generated.

[0055] In another embodiment, the present invention also 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, when executing the program, can realize the system functions of the above-described intraoperative neurological state monitoring report generation system.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A system for generating intraoperative neurological status monitoring reports, characterized in that... Include: The first data processing module triggers intraoperative data processing instructions based on the user's second operation. The intraoperative data includes at least the first electromyographic signal graph, the corresponding stimulation current magnitude, the corresponding current time scale and amplitude scale, and the maximum amplitude adjustment of the electromyographic signal. The second data processing module triggers the pre-operative data processing instruction to end according to the user's second operation, which includes at least the acquisition of data including at least the third electromyographic signal graph, the corresponding stimulation current magnitude, the corresponding scale and amplitude scale, and the maximum amplitude adjustment of the electromyographic signal. Furthermore, the postoperative nerves near the target surgical object are identified through the third electromyographic signal pattern, and the electromyographic signal pattern at this time is recorded as the fourth electromyographic signal pattern; The comparison and analysis module compares and analyzes the obtained second and fourth electromyographic signal images to obtain the similarity of the electromyographic signal images. If the similarity between the two is greater than a preset threshold, the above electromyographic signal images are used as the final electromyographic signal images of the surgical report and output. Before outputting the report, the report generation module reconfirms the patient and doctor information. In the print report editing section, multiple selected electromyographic signals saved during the current operation are selected. These electromyographic signals are saved by taking screenshots. According to the time sequence during the operation, they are stored in the data table position of the corresponding field of the monitoring report, and finally a neurological status monitoring report is generated. In the second data processing module, the nerves near the target surgical object are determined by the first electromyography (EMG) signal pattern, and the EMG signal pattern at this time is recorded as the second EMG signal pattern. The nerves near the target surgical object processing unit includes the following processing steps: Step 1: Receive intraoperative muscle stimulation and acquire the corresponding electromyographic signal S. Decompose the signal S to obtain multiple sets of different signal curves. Step 2: Perform periodic segmentation on multiple sets of different signals, and obtain the electromyographic signal representation Fi for each period based on the following feature extraction algorithm: For the two maximum abrupt change points Q1 and Q2 within each period, calculate the distances L1 and L2 from the abrupt change points to the beginning of the corresponding period, respectively; simultaneously, convert the signal within each period into a rectangular wave signal, and obtain the phase eigenvalues ​​of the rectangular wave signal within the corresponding period. The characteristic Fi for each period is calculated using the following formula: The features of each cycle are fused to form multiple sets of feature labels F corresponding to different signals, where ; Step 3: Extract the signal curve corresponding to each neural stimulus and perform feature extraction as in Step 2 to obtain feature labels for multiple samples. Based on the feature labels of multiple samples in each class, a classification cluster is formed, and the target neural network is determined based on the clustering degree index.

2. The generation system according to claim 1, characterized in that, It also includes: a startup module that sends a report generation instruction to the data processing center based on the user's first operation, and obtains relevant data of the current doctor and patient, as well as information on intraoperative consumables.

3. The generation system according to claim 2, characterized in that, It also includes: The condition judgment module, after receiving the report generation instruction, obtains the impedance data of the connecting wires and inserted catheters, and judges whether the impedance is lower than the set value based on the impedance data. If it is lower than the set value, the intraoperative data processing steps are performed.

4. The generation system according to claim 2, characterized in that: Electromyography (EMG) signal patterns are obtained by using stimulation probes to acquire EMG response signals corresponding to the surgical target area.

5. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, can implement the system functions as described in any one of claims 1-4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, characterized in that, when the program is executed by a processor, it can implement the system functions as described in any one of claims 1-4.

Images