Generation system of intraoperative neural state monitoring report

Abstract

According to the system for generating the intraoperative neural state monitoring report, data are processed and analyzed in real time through an automatic algorithm, and the neural state monitoring report is generated based on electromyographic signals in an operation and before the operation and neural confirmation and contrastive analysis. The generation of the monitoring report does not need manual writing, and the generation efficiency of the monitoring report is greatly improved. Through the system provided by the invention, professional technicians do not need to manually monitor and intercept signals in real time and carry out subsequent mass data analysis, and the processing center automatically carries out real-time signal interpretation, so that the manual data processing pressure is relieved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing and report generation, and in particular, to a method and system for generating an intraoperative nerve status monitoring report. Background Art

[0002] With the continuous progress of medical data processing technology, intraoperative nerve status monitoring has become an indispensable technology in surgeries such as neurosurgery and spinal surgery. By real-time monitoring the patient's neuroelectrophysiological signals during the surgery, it helps surgeons evaluate the impact of surgical operations on the nervous system, thereby reducing the risk of intraoperative nerve injury. Advanced algorithms are used to perform real-time processing and analysis on the data to generate accurate and detailed monitoring reports.

[0003] Existing monitoring reports usually need to be manually written, which is time-consuming and error-prone, affecting the efficiency of the surgical process, and the generation efficiency of the monitoring report is relatively low. The data generated by intraoperative nerve status monitoring is huge and requires professional technical personnel to perform real-time interpretation, which places relatively high requirements on medical resources. Summary of the Invention

[0004] The purpose of the present invention is to provide a system for generating an intraoperative nerve status monitoring report to alleviate the technical problems existing in the prior art.

[0005] In a first aspect, the present invention provides a system for generating an intraoperative nerve status monitoring report, including:

[0006] A generation start module that sends a report generation instruction to the data processing center according to a first operation of the user, and obtains relevant data of the current doctor and patient, as well as intraoperative consumable information;

[0007] A condition judgment module that, after the processing center receives the report generation instruction, obtains impedance data of the connection wire and the inserted catheter, and judges whether the impedance is lower than a set value based on the impedance data. When it is lower than the set value, an intraoperative data processing step is performed;

[0008] A first data processing module that triggers an intraoperative data processing instruction according to a second operation of the user, where the intraoperative data at least includes a first electromyogram signal pattern, the corresponding stimulation current magnitude, the corresponding current time scale and amplitude scale, and the maximum amplitude adjustment of the electromyogram signal; among them, the time scale, amplitude scale, and stimulation current parameters can be set in advance. Specifically, the electromyogram signal pattern is obtained by using a stimulation probe to collect the electromyogram response signal corresponding to the surgical target area;

[0009] Furthermore, the nerve near the target surgical object is determined through the first electromyogram signal pattern of the electromyogram signal, and the electromyogram signal pattern at this time is recorded as the second electromyogram signal pattern. The process of determining the nerve processing unit near the target surgical object includes the following processing procedures:

[0010] Step 1: Receive intraoperative muscle stimulation and collect the corresponding electromyogram signal S. Decompose the signal S to obtain multiple groups of different signal curves.

[0011] Step 2: Perform period segmentation on multiple groups of different signals, and obtain the characterization Fi of the electromyogram signal within each period according to the following feature extraction algorithm:

[0012] For the two largest mutation points Q1 and Q2 within each period, calculate the distances L1 and L2 from the mutation points to the leading end point within the corresponding period respectively; at the same time, 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 , and the calculation of the feature Fi for each period adopts the following formula:

[0013]

[0014] Fuse the features of each period to form the feature markers F corresponding to multiple groups of different signals, where F = {F 1 , F 2 , F 3 ,..., F N};

[0015] Step 3: Perform feature extraction as in Step 2 by extracting the signal curves corresponding to each nerve stimulation to obtain the feature markers corresponding to multiple samples. Based on the feature markers of multiple samples of each class, form a classification cluster, and determine the target nerve based on the clustering degree index.

[0016] The second data processing module triggers a pre-operation end data processing instruction according to the user's second operation, which at least includes obtaining data at least including the third electromyogram signal graph, the corresponding stimulation current magnitude, the corresponding scale and amplitude scale, and the maximum amplitude adjustment of the electromyogram signal; the specific electromyogram signal graph is obtained by using a stimulation probe to collect the electromyogram response signal corresponding to the surgical target area.

[0017] Furthermore, determine the postoperative nerve near the target surgical object through the third electromyogram signal graph of the electromyogram signal, and record the electromyogram signal graph at this time as the fourth electromyogram signal graph. It is determined that the nerve processing unit near the target surgical object is the same as the above first data processing module, which will not be elaborated here.

[0018] The control analysis module performs a comparative analysis based on the obtained second electromyogram signal graph and the fourth electromyogram signal graph to obtain the similarity of the electromyogram signal graphs. If the similarity between the two is greater than the preset threshold, the above electromyogram signal graphs are respectively used as the final electromyogram signal graphs of the surgical report and output.

[0019] The report generation module, before outputting the report, reconfirms the patient and doctor information. In the report printing and editing section, it selects the second and fourth electromyogram signal graphs saved during the current surgery and stores them in the corresponding data table positions in the monitoring report, and finally generates a nerve status monitoring report.

[0020] The embodiments of the present invention bring the following beneficial effects: An automatic algorithm for real-time processing and analysis of data is proposed, and a nerve status monitoring report is generated based on the electromyogram signals during and before the end of the surgery, as well as nerve confirmation and comparative analysis. Generating the monitoring report does not require manual writing, which greatly improves the generation efficiency of the monitoring report and the processing efficiency of data in the surgical process. The amount of data generated by intraoperative nerve status monitoring is huge. Through the system proposed in the present invention, it is no longer necessary for professional technicians to manually monitor and intercept signals in real time and perform a large amount of subsequent data analysis. The processing center automatically interprets the signals in real time, reducing the manual data processing pressure.

[0021] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specifically describes preferred embodiments in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the related art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 The block diagram of the system for generating an intraoperative nerve status monitoring report of the present application;

[0024] Figure 2 An example of an intraoperative electromyogram signal graph in one embodiment of the present application;

[0025] Figure 3 An example of an electromyogram signal graph before the end of the surgery in one embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0027] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third" are only used to describe name differences and should not be construed as indicating or implying relative importance. Physical quantities in the formulas, unless otherwise specifically marked, should be understood as the basic quantities of the basic units of the International System of Units, or derived quantities derived from the basic quantities through mathematical operations such as multiplication, division, differentiation, or integration.

[0028] In the description of the present invention, it should be noted that unless otherwise clearly specified and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] As Figure 1 shown, in the first aspect provided by the embodiments of the present invention, the present invention provides a system for generating intraoperative nerve status monitoring reports, including:

[0030] A report generation start module that sends a report generation instruction to the data processing center according to the user's first operation, and obtains relevant data of the current doctor and patient, as well as intraoperative consumable information;

[0031] Specifically, the user's first operation can be triggered by the doctor's scanning. For example, by scanning the two-dimensional code uniquely corresponding to the current surgery, the report generation instruction is sent to the data processing center by scanning the code;

[0032] A condition judgment module. After the processing center receives the report generation instruction, it obtains the impedance data of the connecting wire and the inserted catheter, and judges whether the impedance is lower than the set value according to the impedance data. When it is lower than the set value, the intraoperative data processing step is performed;

[0033] A first data processing module that triggers an intraoperative data processing instruction according to the user's second operation, where the intraoperative data at least includes the first electromyogram signal pattern, the corresponding stimulation current magnitude, the corresponding current time scale and amplitude scale, and the maximum amplitude adjustment of the electromyogram signal; among them, the time scale, amplitude scale, and stimulation current parameters can be set in advance.

[0034] Specifically, refer to the appendix Figure 2, during the operation, the intraoperative EMG signal pattern is used to collect the EMG response signal corresponding to the surgical target area by using a stimulating probe;

[0035] Furthermore, the nerve near the target surgical object is determined through the first EMG signal pattern of the EMG signal, and the EMG signal pattern at this time is recorded as the second EMG signal pattern. The process of determining the nerve processing unit near the target surgical object includes the following steps:

[0036] Step 1: Receive intraoperative muscle stimulation and collect the corresponding EMG signal S, decompose the signal S, and obtain multiple groups of different signal curves;

[0037] Step 2: Perform period segmentation on multiple groups of different signals, and obtain the characterization Fi of the EMG signal in each period according to the following feature extraction algorithm:

[0038] For the two maximum mutation points Q1 and Q2 in each period, calculate the distances L1 and L2 from the mutation points to the leading end point in the corresponding period respectively; at the same time, convert the signal in each period into a rectangular wave signal, and obtain the phase eigenvalue θ of the rectangular wave signal in the corresponding period i , for the calculation of the feature Fi in each period, the following formula is used:

[0039]

[0040] Fuse the features of each period to form feature markers F corresponding to multiple groups of different signals, where F = {F 1 , F 2 , F 3 ,..., F n};

[0041] Step 3: Perform feature extraction as in Step 2 by extracting the signal curves corresponding to each nerve stimulation, obtain the feature markers corresponding to multiple samples, form a classification cluster based on the feature markers of multiple samples in each category, and determine the target nerve based on the clustering degree index;

[0042] Assume that the data samples of each category correspond to the extracted feature markers, then the formed classification cluster is divided into C = {C 1 , C 2 , …, C j}, define the distance between the center point of cluster C i and the center point of cluster C j as D(C i , C j ) = d(μ i , μ j ), where μ represents the center point of cluster C;

[0043]

[0044] Calculate the distance between samples. Define d(·,·) to represent the distance between two samples, and use the following distance for measurement:

[0045]

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

[0047] Calculate the clustering degree index ND, which is expressed as:

[0048]

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

[0050] The smaller the above ND value, the smaller the intra-class distance and the larger the inter-class distance of the division. Through cyclic calculations for a preset number of times, the signal category attribution of the nerve stimulated is determined based on the clustering result for the current feature marker, and then the target nerve near the target surgical object is determined.

[0051] The second data processing module triggers a pre-operative data processing instruction according to the user's second operation, which at least includes obtaining data such as at least the third electromyogram signal graph, the corresponding stimulation current magnitude, the corresponding scale and amplitude scale, and the maximum amplitude adjustment of the electromyogram signal; the specific electromyogram signal graph is obtained by using a stimulation probe to collect the electromyogram response signal corresponding to the surgical target area;

[0052] Furthermore, the postoperative nerve near the target surgical object is determined through the electromyogram signal graph of the third electromyogram signal, and the electromyogram signal graph at this time is recorded as the fourth electromyogram signal graph. The determination of the nerve processing unit near the target surgical object is the same as the above first data processing module and will not be elaborated here.

[0053] The control analysis module, specifically refer to Appendix Figure 3 , perform a comparative analysis based on the obtained second electromyogram signal graph and the fourth electromyogram signal graph to obtain the similarity of the electromyogram signal graphs. If the similarity between the two is greater than the preset threshold, the above electromyogram signal graphs are respectively used as the final electromyogram signal graphs of the surgical report and output;

[0054] The report generation module, before outputting the report, reconfirms the patient and doctor information. In the report editing section for printing, select multiple selected electrical signal graphs saved during the current surgery. The above electromyogram signal graphs are saved by taking screenshots. According to the chronological order during the surgery, the screenshots are stored in the corresponding data table positions of the corresponding fields of the monitoring report, and finally a nerve status monitoring report is generated. Preferably, select the second and fourth electromyogram signal graphs saved during the current surgery, find the corresponding screenshot files, and generate a nerve status monitoring report.

[0055] In another embodiment, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. Wherein, when the processor executes the program, it can implement the system functions of the above-mentioned intraoperative nerve state monitoring and reporting generation system.

[0056] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions 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: A first data processing module triggers an intraoperative data processing instruction according to a second operation of the user, wherein the intraoperative data at least includes a first electromyographic signal graph, a corresponding stimulation current magnitude, a corresponding current time scale and amplitude scale, and an electromyographic signal maximum amplitude adjustment; A second data processing module, triggering the end of the pre-operative data processing instruction according to the second operation of the user, wherein the acquisition data at least includes at least a third electromyographic signal graph, a corresponding stimulation current magnitude, a corresponding scale and amplitude scale, and an electromyographic signal maximum amplitude adjustment; Further, determining a postoperative nerve near the target surgical object through the third myoelectric signal pattern, and recording the myoelectric signal pattern at this time as a fourth myoelectric signal pattern; A comparison and analysis module performs comparison and analysis on the second electromyographic signal graph and the fourth electromyographic signal graph to obtain the electromyographic signal graph similarity. If the similarity between the two is greater than a preset threshold, the electromyographic signal graphs are used as the final electromyographic signal graphs of the surgical report and output; The report generation module reconfirms the patient and doctor information before outputting the report. In the printed report editing section, multiple selected electrical signal graphs saved in the current operation are selected. The above electromyographic signal graphs are saved by screenshots. According to the time sequence during the operation, they are stored in the data table location of the corresponding field of the corresponding monitoring report, and finally a neural status monitoring report is generated.

2. The generation system according to claim 1, characterized in that It further includes: generating a start module, sending a report generation instruction to a data processing center according to a first operation of the user, and obtaining relevant data of the current doctor and patient and information on consumables during surgery.

3. The generation system according to claim 2, characterized in that: Further comprising: Conditional judgment module: After the processing center receives the report generation instruction, it obtains the impedance data of the connecting wire and the inserted catheter, and judges whether the impedance is lower than the set value based on the impedance data. If it is lower than the set value, it performs intraoperative data processing steps.

4. The generation system according to claim 2, characterized in that: The myoelectric signal graph uses a stimulation probe to collect the myoelectric response signal corresponding to the surgical target area.

5. The generation system according to claim 3, characterized in that: In the second data processing module, 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 process: Step 1, receiving intraoperative muscle stimulation and collecting corresponding electromyographic signals S, performing signal decomposition on the signal S to obtain multiple groups of different signal curves; Step 2: perform period segmentation on multiple groups of different signals, and obtain the representation Fi of the electromyographic signal in each period according to the following feature extraction algorithm: For the two maximum mutation points Q1 and Q2 in each cycle, the distances from the mutation points to the first and second endpoints in the corresponding cycle are calculated as L1 and L2 respectively; at the same time, the signal in each cycle is converted into a rectangular wave signal, and the phase characteristic value θ of the rectangular wave signal in the corresponding cycle is obtained. i , the characteristic Fi calculation in each cycle adopts the following formula: The features of each cycle are integrated to form multiple sets of feature labels F corresponding to different signals, where F = {F1, F2, F3, ..., F N }; Step 3, extract the signal curve corresponding to each nerve stimulation and perform feature extraction as in step 2 to obtain feature labels corresponding to multiple samples, form a classification cluster based on the feature labels of each type of multiple samples, and determine the target nerve based on the clustering degree index.

6. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the control system function of any one of claims 1 to 5 can be realized when the processor executes the program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the program, when executed by a processor, can implement the control system function as claimed in any one of claims 1 to 5.

Images