Current stimulation method and system for inhibiting stress response between digestive tract anastomosis

Abstract

The embodiment of the invention provides a current stimulation method and system for inhibiting stress response between digestive tract anastomosis, and belongs to the technical field of data processing. The method comprises the following steps: capturing bioelectric current on the body surface of a target patient to obtain first data, and obtaining tissue movement under an endoscope view to obtain second data; performing state trend prediction on the first data to obtain a first prediction result; performing state trend prediction on the second data to obtain a second prediction result; performing data clustering on the first data and the second data to obtain a first clustering result of the first data and a second clustering result of the second data; determining a third prediction result according to the first clustering result; determining a fourth prediction result according to the second clustering result; fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result; and according to the target prediction result, determining a current stimulation strategy for current stimulation of the target patient during digestive tract anastomosis stress response.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an electric current stimulation method and system for suppressing stress response during digestive tract anastomosis. Background Art

[0002] For digestive tract tumors such as gastric cancer and intestinal cancer, radical lesion resection is an important option for salvage treatment through surgery. At present, as the requirements for precision and minimally invasive surgery continue to gain popularity, laparoscopic surgery is commonly used for digestive tract resection and anastomosis. While ensuring that the wound on the patient's body surface is small and the risk of infection is significantly reduced, due to the limited surgical operation interface, the activation characteristics of non-sympathetic nerves are easily captured, resulting in anastomotic instability, anastomotic surface fistulas and surgical failure. In the prior art, electric current stimulation can be applied at an appropriate time to stabilize the anastomotic surface and prevent the occurrence of adverse situations such as tissue fluid backflow affecting the anastomosis. However, the related technology cannot detect the patient's stress response in time, resulting in the inability to quickly determine the timing of applying electric current stimulation, thereby reducing the stability of the anastomotic site.

[0003] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the invention

[0004] The main purpose of the embodiments of the present invention is to provide a current stimulation method and system for suppressing stress response during gastrointestinal anastomosis, aiming to solve the problem in the related art that the patient's stress response cannot be detected in time, resulting in the inability to quickly determine the timing of applying current stimulation, thereby reducing the stability of the anastomotic site.

[0005] In a first aspect, an embodiment of the present invention provides a current stimulation method for suppressing stress response during digestive tract anastomosis, comprising:

[0006] During the operation, the bioelectric current on the surface of the target patient is captured to obtain the first data, and the tissue movement under the endoscopic field of view is obtained to obtain the second data;

[0007] Performing state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the target patient's stress response during digestive tract anastomosis;

[0008] Performing state trend prediction on the second data to obtain a second prediction result corresponding to the second data in the target patient's stress response during digestive tract anastomosis;

[0009] Performing data clustering on the first data and the second data respectively to obtain a first clustering result corresponding to the first data and a second clustering result corresponding to the second data;

[0010] Determine, according to the first clustering result, a third prediction result corresponding to the first data of the target patient's stress response during digestive tract anastomosis;

[0011] Determining, according to the second clustering result, a fourth prediction result corresponding to the second data of the target patient's stress response during digestive tract anastomosis;

[0012] fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the stress response of the target patient during digestive tract anastomosis;

[0013] The current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during gastrointestinal anastomosis is determined according to the target prediction result.

[0014] In a second aspect, an embodiment of the present invention provides an electric current stimulation system for suppressing stress response during digestive tract anastomosis, comprising:

[0015] A data acquisition module, used to capture the bioelectric current on the surface of the target patient during surgery to obtain first data, and to obtain the tissue movement under the endoscopic field of view to obtain second data;

[0016] A first prediction module is used to perform state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the stress response of the target patient during digestive tract anastomosis;

[0017] A second prediction module is used to perform state trend prediction on the second data to obtain a second prediction result corresponding to the second data in the stress response of the target patient during digestive tract anastomosis;

[0018] A data clustering module, used to perform data clustering on the first data and the second data respectively, to obtain a first clustering result corresponding to the first data and a second clustering result corresponding to the second data;

[0019] A third prediction module, used for determining a third prediction result corresponding to the first data in the target patient's stress response during digestive tract anastomosis according to the first clustering result;

[0020] a fourth prediction module, configured to determine, according to the second clustering result, a fourth prediction result corresponding to the second data of the target patient's stress response during digestive tract anastomosis;

[0021] A data fusion module, used for fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the stress response of the target patient during digestive tract anastomosis;

[0022] A strategy determination module is used to determine the current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during gastrointestinal anastomosis according to the target prediction result.

[0023] In a third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any one of the current stimulation methods for suppressing stress response during gastrointestinal anastomosis as provided in the specification of the present invention are realized.

[0024] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any current stimulation method for inhibiting stress response during gastrointestinal anastomosis as provided in the specification of the present invention.

[0025] The embodiment of the present invention provides a current stimulation method and system for suppressing the stress reaction during digestive tract anastomosis. The method includes capturing the bioelectric current on the surface of the target patient to obtain the first data during the operation, and obtaining the second data by obtaining the tissue movement under the endoscopic field of view, so as to obtain the physiological state of the target patient during the operation in real time and comprehensively. Thus, the state trend of the first data is predicted, and the first prediction result corresponding to the first data in the stress reaction of the target patient during digestive tract anastomosis is obtained; the state trend of the second data is predicted, and the second prediction result corresponding to the second data in the stress reaction of the target patient during digestive tract anastomosis is obtained, and then the stress reaction trend of the target patient during digestive tract anastomosis is predicted from different modal data, providing support for subsequent current stimulation. Then, the first data and the second data are clustered respectively to obtain the first clustering result corresponding to the first data and the second clustering result corresponding to the second data; the third prediction result corresponding to the first data in the stress response of the target patient during the digestive tract anastomosis is determined according to the first clustering result; the fourth prediction result corresponding to the second data in the stress response of the target patient during the digestive tract anastomosis is determined according to the second clustering result, and then the stress response trend of the target patient during the digestive tract anastomosis is predicted from different angles for the same modal data, so as to provide support for the subsequent current stimulation; thus, the target prediction result corresponding to the stress response of the target patient during the digestive tract anastomosis is obtained by integrating the first prediction result, the second prediction result, the third prediction result and the fourth prediction result, so as to obtain a more comprehensive and accurate target prediction result, and provide more reliable support for subsequent decision-making; finally, the current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during the digestive tract anastomosis is determined according to the target prediction result. Thus, the current stimulation strategy is determined according to the target prediction result, and personalized and precise stress response regulation can be realized. This precise current stimulation can effectively alleviate the adverse stress response during surgery and improve the stability of the anastomotic site during surgery. It also solves the problem in the related art that the patient's stress response cannot be detected in time, resulting in the inability to quickly determine the timing of applying current stimulation, thereby reducing the stability of the anastomotic site. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0027] Figure 1 A schematic flow chart of a current stimulation method for suppressing stress response during gastrointestinal anastomosis provided by an embodiment of the present invention;

[0028] Figure 2A schematic diagram of the module structure of a current stimulation system for suppressing stress response during gastrointestinal anastomosis provided by an embodiment of the present invention;

[0029] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0032] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0033] The embodiment of the present invention provides a current stimulation method and system for suppressing stress response during gastrointestinal anastomosis. The current stimulation method for suppressing stress response during gastrointestinal anastomosis can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0034] For digestive tract tumors such as gastric cancer and intestinal cancer, radical lesion resection is an important option for salvage treatment through surgery. At present, as the requirements for precision and minimally invasive surgery continue to gain popularity, laparoscopic surgery is commonly used for digestive tract resection and anastomosis. While ensuring that the wound on the patient's body surface is small and the risk of infection is significantly reduced, due to the limited surgical operation interface, the activation characteristics of non-sympathetic nerves are easily captured, resulting in anastomotic instability, anastomotic surface fistulas and surgical failure. In the prior art, electric current stimulation can be applied at an appropriate time to stabilize the anastomotic surface and prevent the occurrence of adverse situations such as tissue fluid backflow affecting the anastomosis. However, the related technology cannot detect the patient's stress response in time, resulting in the inability to quickly determine the timing of applying electric current stimulation, thereby reducing the stability of the anastomotic site.

[0035] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems.

[0036] To this end, the present invention provides a current stimulation method and system for suppressing the stress response during digestive tract anastomosis. The method includes capturing the bioelectric current on the surface of the target patient during the operation to obtain the first data, and obtaining the tissue movement under the endoscopic field of view to obtain the second data, so that the physiological state of the target patient during the operation can be obtained in real time and comprehensively. Thus, the state trend of the first data is predicted, and the first prediction result corresponding to the first data in the stress response of the target patient during digestive tract anastomosis is obtained; the state trend of the second data is predicted, and the second prediction result corresponding to the second data in the stress response of the target patient during digestive tract anastomosis is obtained, and then the stress response trend of the target patient during digestive tract anastomosis is predicted from different modal data, providing support for subsequent current stimulation. Then, the first data and the second data are clustered respectively to obtain the first clustering result corresponding to the first data and the second clustering result corresponding to the second data; the third prediction result corresponding to the first data in the stress response of the target patient during the digestive tract anastomosis is determined according to the first clustering result; the fourth prediction result corresponding to the second data in the stress response of the target patient during the digestive tract anastomosis is determined according to the second clustering result, and then the stress response trend of the target patient during the digestive tract anastomosis is predicted from different angles for the same modal data, so as to provide support for the subsequent current stimulation; thus, the target prediction result corresponding to the stress response of the target patient during the digestive tract anastomosis is obtained by integrating the first prediction result, the second prediction result, the third prediction result and the fourth prediction result, so as to obtain a more comprehensive and accurate target prediction result, and provide more reliable support for subsequent decision-making; finally, the current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during the digestive tract anastomosis is determined according to the target prediction result. Thus, the current stimulation strategy is determined according to the target prediction result, and personalized and precise stress response regulation can be realized. This precise current stimulation can effectively alleviate the adverse stress response during surgery and improve the stability of the anastomotic site during surgery. It also solves the problem in the related art that the patient's stress response cannot be detected in time, resulting in the inability to quickly determine the timing of applying current stimulation, thereby reducing the stability of the anastomotic site.

[0037] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0038] Please refer to Figure 1 , Figure 1 A flow chart of a current stimulation method for suppressing stress response during gastrointestinal anastomosis provided in an embodiment of the present invention.

[0039] like Figure 1As shown, the current stimulation method for suppressing the stress response during digestive tract anastomosis includes steps S101 to S108.

[0040] Step S101: capturing the bioelectric current on the body surface of the target patient during the operation to obtain first data, and obtaining the tissue movement under the endoscopic field of view to obtain second data.

[0041] Exemplarily, a device that can effectively capture biocurrent signals (such as an electrocardiogram or electromyography sensor) is selected. These sensors need to have high sensitivity and low noise interference to ensure that the signal can be accurately acquired. Before the operation, ensure that the target patient's skin is clean to improve the quality of electrode attachment and the stability of the signal. Attach the electrodes to the target patient's body surface in accordance with relevant medical standards and best practices, usually including the chest, abdomen or other specific areas, to ensure that the biocurrent can be effectively captured. Connect the electrodes to a data acquisition device that can record the captured current signal in real time to obtain the first data.

[0042] For example, during surgery, an endoscope is placed in the target tissue area to ensure that tissue movement can be clearly observed, thereby obtaining second data. The first data can reflect the activity of the nervous system, while the second data is directly related to the physiological changes in the surgical area.

[0043] Step S102: perform state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the target patient's stress response during gastrointestinal anastomosis.

[0044] Exemplarily, a neural network model or a deep learning model is used to classify the state trend of the first data to obtain a first prediction result corresponding to the first data in the target patient's stress response during gastrointestinal anastomosis. Among them, the first prediction result includes the existence of a high-risk trend of emergency response and the corresponding probability, the existence of a medium-risk trend of emergency response and the corresponding probability, and the existence of a low-risk trend of emergency response and the corresponding probability. That is, the first prediction result obtained by performing state trend prediction based on the first data includes a high-risk trend and the probability corresponding to the high-risk trend, a medium-risk trend and the probability corresponding to the medium-risk trend, and a low-risk trend and the probability corresponding to the low-risk trend, wherein the high-risk trend, the medium-risk trend, and the low-risk trend are used to characterize the possibility that the target patient may have an emergency response.

[0045] In some embodiments, the state trend prediction of the first data to obtain the first prediction result corresponding to the first data in the stress response of the target patient during gastrointestinal anastomosis includes: randomly generating multiple integers to determine as the first position and the second position, and cutting the first data according to the first position and the second position to obtain the first sub-data, the second sub-data and the third sub-data; using the first ARIMA model to perform data prediction on the first position according to the first sub-data to obtain the first predicted data corresponding to the first position; obtaining the first real data corresponding to the first position from the first data, and performing model correction on the first ARIMA model according to the first real data and the first predicted data to obtain the first target ARIMA model; using the second ARIMA model to perform data prediction on the second position according to the first predicted data and the second sub-data to obtain the second predicted data corresponding to the second position; obtaining the second real data corresponding to the second position from the second data, and performing model correction on the second ARIMA model according to the second real data and the second predicted data to obtain the second target ARIMA model; determining the position corresponding to the end data in the third sub-data as the third position, and determining that the end data in the third sub-data is the third real data corresponding to the third position; removing the third position from the third sub-data to obtain the fourth sub-data, and using the third ARIMA model to predict the data of the third position according to the fourth sub-data to obtain the third predicted data corresponding to the third position; performing model correction on the third ARIMA model according to the third real data and the third predicted data to obtain the third target ARIMA model; merging the first target ARIMA model, the second target ARIMA model and the third target ARIMA model to obtain a spliced ​​ARIMA model; predicting the data corresponding to the next time period of the first data according to the spliced ​​ARIMA model to obtain the first state data; splicing the first data and the first state data to obtain the first spliced ​​data, using the first state prediction model to predict the state trend of the first spliced ​​data, and obtaining the first prediction result corresponding to the first data in the stress response of the target patient during gastrointestinal anastomosis.

[0046] Exemplarily, the total number corresponding to the first data is obtained, and then a plurality of integers are randomly generated to be determined as the first position and the second position, wherein the first position and the second position are both less than the total number. In addition, the plurality of randomly generated integers may be the first position and the second position, or the first position, the second position and the third position, and so on, that is, the present application does not limit the number of randomly generated integers.

[0047] For example, the ARIMA model, whose full name is AutoRegressiveIntegrated MovingAverage model, is a commonly used time series prediction method.

[0048] Exemplarily, the first data is cut from the positions corresponding to the first position and the second position in the first data to obtain the first sub-data, the second sub-data and the third sub-data. Thus, a first ARIMA model is established according to the first sub-data, and then the data at the first position is predicted to obtain the first predicted data. Then, the first real data corresponding to the first position is obtained from the first data, so as to compare the first predicted data with the first real data, calculate the prediction error, and adjust the model parameters of the first ARIMA model to better fit the real data, so as to obtain the first target ARIMA model when the prediction error meets the preset value, that is, the first target ARIMA model is used to simulate the data distribution of the data segment corresponding to the first sub-data.

[0049] Exemplarily, a second ARIMA model is established based on the second sub-data, and then the data at the second position is predicted to obtain the second predicted data. Then, the second real data corresponding to the second position is obtained from the first data, so as to compare the second predicted data with the second real data, calculate the prediction error, and adjust the model parameters of the second ARIMA model to better fit the real data, so as to obtain the second target ARIMA model when the prediction error meets the preset value, that is, the second target ARIMA model is used to simulate the data distribution of the data segment corresponding to the second sub-data.

[0050] Exemplarily, the position corresponding to the end data in the third sub-data is determined as the third position, that is, the position of the last data in the third sub-data is determined as the third position, and then the end data in the third sub-data is determined as the third real data corresponding to the third position, so that the third position is removed from the third sub-data to obtain the fourth sub-data.

[0051] Exemplarily, a third ARIMA model is established based on the fourth sub-data, and then the data at the third position is predicted to obtain third predicted data. Thus, the third predicted data and the third real data are compared, and the prediction error is calculated, so as to adjust the model parameters of the third ARIMA model to better fit the real data, so that when the prediction error meets the preset value, the third target ARIMA model is obtained, that is, the third target ARIMA model is used to simulate the data distribution of the data segment corresponding to the fourth sub-data.

[0052] Exemplarily, the first target ARIMA model, the second target ARIMA model and the third target ARIMA model under different sub-data at continuous moments are spliced ​​to obtain a spliced ​​ARIMA model, and then the spliced ​​ARIMA model is used to predict the next time period of the first data to obtain the first state data. The first state data reflects the bioelectrical signal of the target patient in the next time period. Thus, the first data and its corresponding first state data are spliced ​​to obtain the first spliced ​​data, and then the first spliced ​​data is input into the first state prediction model, and the state trend prediction is performed to obtain the first prediction result. The first state prediction model can be any one of a neural network model or a deep learning model, and then the state trend of the first spliced ​​data is classified according to the first state prediction model to obtain the first prediction result corresponding to the stress response of the target patient during gastrointestinal anastomosis. Among them, the first prediction result includes the existence of an emergency response with a high risk trend and the corresponding probability, the existence of an emergency response with a medium risk trend and the corresponding probability, and the existence of an emergency response with a low risk trend and the corresponding probability. That is, the first prediction result obtained by predicting the status trend based on the first data includes a high-risk trend and the probability corresponding to the high-risk trend, a medium-risk trend and the probability corresponding to the medium-risk trend, and a low-risk trend and the probability corresponding to the low-risk trend, wherein the high-risk trend, the medium-risk trend, and the low-risk trend are used to characterize the possibility of an emergency response in the target patient.

[0053] Step S103: perform state trend prediction on the second data to obtain a second prediction result corresponding to the second data in the target patient's stress response during gastrointestinal anastomosis.

[0054] Exemplarily, a neural network model or a deep learning model is used to classify the state trend of the second data to obtain a second prediction result corresponding to the second data in the target patient's stress response during gastrointestinal anastomosis. Among them, the second prediction result includes the existence of a high-risk trend and the corresponding probability of the emergency response, the existence of a medium-risk trend and the corresponding probability of the emergency response, and the existence of a low-risk trend and the corresponding probability of the emergency response. That is, the second prediction result obtained by performing state trend prediction based on the second data includes a high-risk trend and the probability corresponding to the high-risk trend, a medium-risk trend and the probability corresponding to the medium-risk trend, and a low-risk trend and the probability corresponding to the low-risk trend, wherein the high-risk trend, the medium-risk trend, and the low-risk trend are used to characterize the possibility that the target patient may have an emergency response.

[0055] In some embodiments, the state trend prediction of the second data to obtain a second prediction result corresponding to the second data in the stress response of the target patient during gastrointestinal anastomosis includes: using a long short-term memory network model to predict the second data to obtain second state data corresponding to the next time period of the second data; splicing the second data and the second state data to obtain second spliced ​​data; using a second state prediction model to predict the state trend of the second spliced ​​data to obtain the second prediction result corresponding to the second data in the stress response of the target patient during gastrointestinal anastomosis.

[0056] Exemplarily, first, the second data is predicted using a long short-term memory network (LSTM) model. LSTM is a deep learning model suitable for processing time series data, which can capture long-term dependencies in the data. By training the LSTM model, the second state data of the next time period (i.e., a certain time point in the future) can be predicted.

[0057] Exemplarily, the original second data and the second state data predicted by the LSTM model are spliced ​​together. The purpose of splicing is to combine historical data with future predicted data to better reflect the overall trend and state.

[0058] Exemplarily, the spliced ​​second spliced ​​data is processed using a pre-trained second state prediction model. This model may be another deep learning model (such as a convolutional neural network or a recurrent neural network) that is specifically used to analyze and predict state trends. Through this model, the second prediction result of the second data of the target patient's stress response during gastrointestinal anastomosis can be obtained. The second prediction result reflects the stress response state and trend that may occur in the target patient during this time period. This result can be used as a reference for doctors or other medical professionals to help them better understand and manage the patient's stress response. Among them, the second prediction result includes the existence of an emergency response with a high-risk trend and the corresponding probability, the existence of an emergency response with a medium-risk trend and the corresponding probability, and the existence of an emergency response with a low-risk trend and the corresponding probability. That is, the second prediction result obtained by performing state trend prediction based on the second data includes a high-risk trend and the probability corresponding to the high-risk trend, a medium-risk trend and the probability corresponding to the medium-risk trend, and a low-risk trend and the probability corresponding to the low-risk trend, wherein the high-risk trend, the medium-risk trend, and the low-risk trend are used to characterize the possibility that the target patient may have an emergency response.

[0059] Step S104: cluster the first data and the second data respectively to obtain a first clustering result corresponding to the first data and a second clustering result corresponding to the second data.

[0060] Exemplarily, the distance between any two data is calculated for the first data. Common distance measurement methods include Euclidean distance, Manhattan distance, cosine similarity, etc., and a method suitable for the data characteristics is selected for calculation. Based on the calculated first distance information, a clustering algorithm is used to perform cluster analysis on the first data according to the first clustering information, so as to obtain a first clustering result corresponding to the first data. Commonly used clustering algorithms include but are not limited to: K-means clustering, hierarchical clustering, DBSCAN clustering.

[0061] Exemplarily, the distance between any two data is calculated for the second data. Common distance measurement methods include Euclidean distance, Manhattan distance, cosine similarity, etc., and a method suitable for the data characteristics is selected for calculation. Based on the calculated second distance information, a clustering algorithm is used to perform cluster analysis on the second data according to the second distance information, so as to obtain a second clustering result corresponding to the second data. Commonly used clustering algorithms include but are not limited to: K-means clustering, hierarchical clustering, DBSCAN clustering.

[0062] Step S105: determining a third prediction result corresponding to the first data of the target patient's stress response during gastrointestinal anastomosis according to the first clustering result.

[0063] Exemplarily, each first cluster in the first clustering result is traversed, and the number of samples in each first cluster is counted. The number of data points contained in each first cluster is recorded, which will help the subsequent weighted processing, and then the weight is set in an inverse proportional manner according to the number of data points corresponding to the first cluster counted: the larger the number of data points, the lower the representativeness and relative importance of the cluster, so a smaller weight is assigned to it; the smaller the number of data points, the more likely the cluster contains some special or important features, so a larger weight is assigned to it.

[0064] Exemplarily, the calculated weights are used to fuse the first clusters in the first clustering results, and the data in each first cluster is subjected to feature extraction to obtain the first feature information corresponding to the first cluster, and then the weights corresponding to the first clusters and the first feature information are used to perform weighted averaging or weighted summation on the first clustering results to obtain the first target feature information, and the first target feature information is used to represent the features of the first data. The obtained first target feature information is input into the third state prediction model for processing. This model can be a method based on machine learning or deep learning, which aims to predict the patient's stress response state during gastrointestinal anastomosis. Thus, the model will use the fused first target feature information for prediction and output the third prediction result of the target patient, which reflects the possible stress response of the target patient during gastrointestinal anastomosis. This result can be used for decision support and patient management for doctors.

[0065] In some embodiments, determining the third prediction result corresponding to the first data in the target patient's stress response during gastrointestinal anastomosis based on the first clustering result includes: obtaining a first entropy value corresponding to each first cluster in the first clustering result, and determining a first weight corresponding to the first cluster based on the first entropy value; performing data fusion on the first data based on the first weight and the first cluster to obtain first fused data; and performing state trend prediction on the first fused data using a third state prediction model to obtain the third prediction result corresponding to the first data in the target patient's stress response during gastrointestinal anastomosis.

[0066] Exemplarily, all data in the first cluster are summed to obtain a first sum value, and then each data in the first cluster is divided by the first sum value to obtain the first numerical value proportion corresponding to each data. In addition, it is necessary to count the number of the data in the first cluster to obtain the first number, and then take the natural logarithm of the first numerical value proportion to obtain the first logarithm value, and take the natural logarithm of the first number to obtain the second logarithm value, and then multiply the first numerical value proportion and the first logarithm value and divide it by the second logarithm value and then take the negative number to obtain the first sub-entropy value corresponding to the data, and finally obtain the first sub-entropy value for each data in the first cluster and then sum all the first sub-entropy values ​​to obtain the first entropy value corresponding to the first cluster.

[0067] Exemplarily, the first entropy value corresponding to each first cluster in the first clustering result is obtained, and then the first weight corresponding to the first cluster is obtained according to the following formula:

[0068]

[0069] Among them, w t represents the first weight corresponding to the tth first cluster in the first clustering result, s t represents the first entropy value corresponding to the t-th first-class cluster, s k represents the first entropy value corresponding to the kth first cluster, and h represents the number of clusters corresponding to the first cluster in the first clustering result.

[0070] Exemplarily, the calculated first weight is used to fuse each first cluster in the first clustering result. First, the data in each first cluster is feature extracted to obtain the first feature information corresponding to the first cluster. Then, the first clustering result is weighted averaged or weighted summed using the first weight and the first feature information corresponding to the first cluster, so as to obtain the first fused data. The first fused data is used to represent the characteristics of the first data. The obtained first fused data is input into the third state prediction model for processing. This model can be a method based on machine learning or deep learning, which aims to predict the patient's stress response state during gastrointestinal anastomosis. Thus, the model will use the fused first fusion data for prediction and output the third prediction result of the target patient.

[0071] Exemplarily, the third prediction result reflects the stress response state and trend that may occur in the target patient during the time period. This result can be used as a reference for doctors or other medical professionals to help them better understand and manage patients' stress responses. Among them, the third prediction result includes the existence of a high-risk trend for emergency response and the corresponding probability, the existence of a medium-risk trend for emergency response and the corresponding probability, and the existence of a low-risk trend for emergency response and the corresponding probability. That is, the third prediction result obtained by predicting the state trend based on the first data includes a high-risk trend and the probability corresponding to the high-risk trend, a medium-risk trend and the probability corresponding to the medium-risk trend, and a low-risk trend and the probability corresponding to the low-risk trend, wherein the high-risk trend, the medium-risk trend, and the low-risk trend are used to characterize the possibility that the target patient may have an emergency response.

[0072] Step S106: Determine a fourth prediction result corresponding to the second data in the target patient's stress response during gastrointestinal anastomosis according to the second clustering result.

[0073] Exemplarily, each second cluster in the second clustering result is traversed, and the number of samples in each second cluster is counted. The number of data points contained in each second cluster is recorded, which will help the subsequent weighting process, and then the weight is set in an inverse proportional manner according to the number of data points corresponding to the statistical second cluster: the larger the number of data points, the lower the representativeness and relative importance of the cluster, so a smaller weight is assigned to it; the smaller the number of data points, the more likely the cluster contains some special or important features, so a larger weight is assigned to it.

[0074] Exemplarily, the calculated weights are used to fuse the second clusters in the second clustering results, and the data in each second cluster is subjected to feature extraction to obtain the second feature information corresponding to the second cluster, and then the weights and the second feature information corresponding to the second cluster are used to perform weighted averaging or weighted summation on the second clustering results to obtain the second target feature information, and the second target feature information is used to represent the features of the second data. The obtained second target feature information is input into the third state prediction model for processing. This model can be a method based on machine learning or deep learning, which aims to predict the patient's stress response state during gastrointestinal anastomosis. Thus, the model will use the fused second target feature information for prediction and output the fourth prediction result of the target patient, which reflects the possible stress response of the target patient during gastrointestinal anastomosis. This result can be used for decision support and patient management for doctors.

[0075] In some embodiments, determining the fourth prediction result corresponding to the second data in the target patient's stress response between gastrointestinal anastomosis operations based on the second clustering result includes: obtaining a second entropy value corresponding to each second cluster in the second clustering result, and determining a second weight corresponding to the second cluster based on the second entropy value; performing data fusion on the second data based on the second weight and the second cluster to obtain second fused data; and performing state trend prediction on the second fused data using a fourth state prediction model to obtain the fourth prediction result corresponding to the second data in the target patient's stress response between gastrointestinal anastomosis operations.

[0076] Exemplarily, all data in the second cluster are summed to obtain a second sum value, and then each data in the second cluster is divided by the second sum value to obtain the second numerical value proportion corresponding to each data. In addition, the number of the data in the second cluster is counted to obtain the second number, and then the natural logarithm of the second numerical value proportion is taken to obtain a third logarithm value, and the natural logarithm of the second number is taken to obtain a fourth logarithm value, and then the second numerical value proportion is multiplied by the third logarithm value and divided by the fourth logarithm value and then the negative number is taken to obtain the second sub-entropy value corresponding to the data, and finally, after each data in the second cluster obtains the second sub-entropy value, all the second sub-entropy values ​​are summed to obtain the second entropy value corresponding to the second cluster.

[0077] Exemplarily, the second entropy value corresponding to each second cluster in the second clustering result is obtained, and then the second weight corresponding to the second cluster is obtained according to the following formula:

[0078]

[0079] Among them, w x Indicates the second weight corresponding to the xth second cluster in the second clustering result, s xrepresents the second entropy value corresponding to the x-th second-class cluster, s g represents the second entropy value corresponding to the g-th second cluster, and u represents the number of clusters corresponding to the second cluster in the second clustering result.

[0080] Exemplarily, the calculated second weight is used to fuse each second cluster in the second clustering result, firstly, the data in each second cluster is feature extracted to obtain the second feature information corresponding to the second cluster, and then the second clustering result is weighted averaged or weighted summed using the second weight and the second feature information corresponding to the second cluster, so as to obtain the second fused data, and the second fused data is used to represent the characteristics of the second data. The obtained second fused data is input into the fourth state prediction model for processing. This model can be a method based on machine learning or deep learning, which aims to predict the stress response state of the patient during gastrointestinal anastomosis. Thus, the model will use the fused second fused data for prediction and output the fourth prediction result of the target patient.

[0081] Exemplarily, the fourth prediction result reflects the stress response state and trend that may occur in the target patient during the time period. This result can be used as a reference for doctors or other medical professionals to help them better understand and manage patients' stress responses. Among them, the fourth prediction result includes the existence of a high-risk trend for emergency response and the corresponding probability, the existence of a medium-risk trend for emergency response and the corresponding probability, and the existence of a low-risk trend for emergency response and the corresponding probability. That is, the fourth prediction result obtained by performing state trend prediction based on the second data includes a high-risk trend and the probability corresponding to a high-risk trend, a medium-risk trend and the probability corresponding to a medium-risk trend, and a low-risk trend and the probability corresponding to a low-risk trend, wherein the high-risk trend, the medium-risk trend, and the low-risk trend are used to characterize the possibility that the target patient may have an emergency response.

[0082] Step S107, fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the target patient's stress response during gastrointestinal anastomosis.

[0083] Exemplarily, evidence theory is used to perform information fusion on the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain the target prediction result corresponding to the stress response of the target patient during gastrointestinal anastomosis.

[0084] In some embodiments, the fusing of the first prediction result, the second prediction result, the third prediction result, and the fourth prediction result to obtain the target prediction result corresponding to the stress response of the target patient during gastrointestinal anastomosis, includes: calculating the similarity between any two prediction results of the first prediction result, the second prediction result, the third prediction result, and the fourth prediction result, and determining the abnormal prediction result corresponding to the first prediction result, the second prediction result, the third prediction result, and the fourth prediction result according to the similarity; removing the abnormal prediction result from the first prediction result, the second prediction result, the third prediction result, and the fourth prediction result to obtain a fifth prediction result, a sixth prediction result, and a seventh prediction result; constructing data according to the fifth prediction result, the sixth prediction result, and the seventh prediction result to obtain an eighth prediction result; and fusing the fifth prediction result, the sixth prediction result, the seventh prediction result, and the eighth prediction result to determine the target prediction result corresponding to the stress response of the target patient during gastrointestinal anastomosis.

[0085] Exemplarily, the similarity between any two prediction results among the first prediction result, the second prediction result, the third prediction result and the fourth prediction result is calculated using KL divergence or JS divergence or Hellinger distance, so as to obtain the similarity between any two prediction results.

[0086] For example, the first similarity between the first prediction result and the second prediction result is calculated using KL divergence, the second similarity between the first prediction result and the third prediction result is calculated using KL divergence, the third similarity between the first prediction result and the fourth prediction result is calculated using KL divergence, and the fourth similarity between the second prediction result and the third prediction result is calculated using KL divergence, the fifth similarity between the second prediction result and the fourth prediction result is calculated using KL divergence, and the sixth similarity between the third prediction result and the fourth prediction result is calculated using KL divergence.

[0087] Exemplarily, similar results between the first prediction result and the second prediction result, the third prediction result and the fourth prediction result are obtained from the similarity, and then all similar results are summed to obtain a first correlation value between the first prediction result and the other prediction results, and then similar results between the second prediction result and the first prediction result, the third prediction result and the fourth prediction result are obtained from the similarity, and then all similar results are summed to obtain a second correlation value between the second prediction result and the other prediction results, and so on to obtain a third correlation value between the third prediction result and the other prediction results, and a fourth correlation value between the fourth prediction result and the other prediction results, so that the prediction result corresponding to the minimum value among the first correlation value, the second correlation value, the third correlation value and the fourth correlation value is determined as an abnormal prediction result.

[0088] For example, when the first correlation value is the minimum value, the abnormal prediction result is the first prediction result; when the second correlation value is the minimum value, the abnormal prediction result is the second prediction result, and so on.

[0089] Exemplarily, abnormal prediction results are removed from the first prediction result, the second prediction result, the third prediction result, and the fourth prediction result, thereby obtaining a fifth prediction result, a sixth prediction result, and a seventh prediction result.

[0090] For example, when the abnormal prediction result is the first prediction result, the first prediction result is removed from the first prediction result, the second prediction result, the third prediction result, and the fourth prediction result, so that the second prediction result is determined as the fifth prediction result, the third prediction result is determined as the sixth prediction result, and the fourth prediction result is determined as the seventh prediction result. Or when the abnormal prediction result is the second prediction result, the second prediction result is removed from the first prediction result, the second prediction result, the third prediction result, and the fourth prediction result, so that the first prediction result is determined as the fifth prediction result, the third prediction result is determined as the sixth prediction result, and the fourth prediction result is determined as the seventh prediction result, and so on.

[0091] Exemplarily, the correlation value between the fifth prediction result and the abnormal prediction result is obtained from the similarity. For example, when the abnormal prediction result is the first prediction result, the fifth prediction result is the second prediction result, and the correlation value between the first prediction result and the second prediction result is determined as the correlation value between the fifth prediction result and the abnormal prediction result. Similarly, the correlation value between the sixth prediction result and the abnormal prediction result and the correlation value between the seventh prediction result and the abnormal prediction result are obtained, and then the fifth prediction result, the sixth prediction result and the seventh prediction result are weighted and summed according to the correlation value to obtain the eighth prediction result. That is, after the eighth prediction result is obtained, the eighth prediction result is used to replace the previous abnormal prediction result.

[0092] Exemplarily, the fifth prediction result, the sixth prediction result, the seventh prediction result and the eighth prediction result are fused using evidence theory to obtain the target prediction result corresponding to the stress response of the target patient during gastrointestinal anastomosis.

[0093] In some embodiments, the data construction is performed according to the fifth prediction result, the sixth prediction result, and the seventh prediction result to obtain the eighth prediction result, including: determining the target prediction type corresponding to the eighth prediction result; determining the associated prediction results corresponding to the target prediction type and the non-associated prediction results corresponding to the target prediction type that are not supported according to the fifth prediction result, the sixth prediction result, and the seventh prediction result; determining the target support corresponding to the target prediction type according to the associated prediction results and the non-associated prediction results; determining the eighth prediction result according to the target support and the target prediction type; wherein the target support is obtained according to the following formula:

[0094]

[0095] Among them, sup w represents the target support corresponding to the w-th target prediction type, m represents the number of the associated prediction results, all represents the total number of the associated prediction results and the non-associated prediction results, n represents the number of the non-associated prediction results, P i represents the prediction probability of the i-th associated prediction result for the target prediction type, p t represents the prediction probability of the tth associated prediction result for the target prediction type, Q j represents the prediction probability of the jth non-associated prediction result for the target prediction type, Q e Represents the prediction probability of the e-th non-associated prediction result for the target prediction type.

[0096] Exemplarily, a target prediction type corresponding to the eighth prediction result is obtained from the fifth prediction result, the sixth prediction result, or the seventh prediction result, and the target prediction type is any one of the prediction types of the fifth prediction result, the sixth prediction result, or the seventh prediction result.

[0097] For example, the prediction types included in the fifth prediction result, the sixth prediction result, or the seventh prediction result are the same, but the prediction probabilities corresponding to the prediction types are different, and the prediction types in the fifth prediction result, the sixth prediction result, or the seventh prediction result are high risk trends, medium risk trends, and low risk trends, etc. Then the target prediction type corresponding to the eighth prediction result is any one of high risk trends, medium risk trends, and low risk trends.

[0098] In addition, it should be noted that the prediction type in the fifth prediction result, the sixth prediction result, or the seventh prediction result can be defined according to needs. There is no specific restriction on the name of the prediction type in this application, and it can be defined according to actual needs.

[0099] Exemplarily, the associated prediction result corresponding to the supported target prediction type and the non-associated prediction result corresponding to the unsupported target prediction type are determined according to the fifth prediction result, the sixth prediction result and the seventh prediction result.

[0100] For example, if the prediction type corresponding to the maximum prediction probability in the fifth prediction result is the same as the target prediction type, then the fifth prediction result is determined to be one of the associated prediction results corresponding to the target prediction type; if the prediction type corresponding to the maximum prediction probability in the fifth prediction result is different from the target prediction type, then the fifth prediction result is determined to be one of the non-associated prediction results corresponding to the target prediction type that is not supported, and so on, to obtain the associated prediction results corresponding to the target prediction type and the non-associated prediction results corresponding to the target prediction type that are not supported in the fifth prediction result, the sixth prediction result and the seventh prediction result.

[0101] Exemplarily, the target support corresponding to the target prediction type is determined using the following formula according to the associated prediction results and the non-associated prediction results:

[0102]

[0103] Among them, sup w represents the target support corresponding to the w-th target prediction type, m represents the number of associated prediction results, all represents the total number of associated prediction results and non-associated prediction results, n represents the number of non-associated prediction results, P i represents the prediction probability of the i-th associated prediction result for the target prediction type, p t represents the prediction probability of the tth associated prediction result for the target prediction type, Q j represents the prediction probability of the jth non-associated prediction result for the target prediction type, Q e Represents the predicted probability of the e-th non-associated prediction result for the target prediction type.

[0104] Exemplarily, the support of the target prediction type is calculated using associated prediction results and non-associated prediction results, and the degree of influence of different prediction results on the target prediction type is taken into consideration, so that the target support corresponding to the target prediction type is obtained according to the above formula.

[0105] Exemplarily, the above steps are repeated to obtain the target support corresponding to each target prediction type, and then all target prediction types and corresponding target support are combined into an eighth prediction result, thereby providing support for subsequent prediction result fusion.

[0106] Step S108: determining, according to the target prediction result, a current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during gastrointestinal anastomosis.

[0107] Exemplarily, the final prediction type corresponding to the maximum probability is obtained according to the target prediction result. For example, if the target prediction result shows that the probability of a low-risk trend is 60%, while the probabilities of medium risk and high risk are 30% and 10% respectively, the low-risk trend is selected as the final prediction type. After determining the final prediction type, a pre-set strategy mapping table is used to find the corresponding current stimulation strategy. This mapping table should be based on the knowledge of domain experts and clinical trial data to ensure that the most appropriate and effective intervention measures are provided.

[0108] For example, when the final prediction type is a low-risk trend, the target patient has a low risk of experiencing a significant stress reaction at the current moment during the operation, and the current stimulation strategy is that no current stimulation is required; when the final prediction type is a medium-risk trend, the target patient may have a mild stress reaction, and it is suitable to use mild current stimulation to assist in controlling and reducing pain or tension, so the current stimulation strategy is that mild current stimulation is required; when the final prediction type is a high-risk trend, the target patient is at high risk and may require stronger current stimulation to quickly and effectively help stabilize the patient's physiological state, so the current stimulation strategy is that more obvious current stimulation is required. This can not only improve the accuracy of the prediction and management of stress reactions, but also improve the patient's comfort and safety during surgery, and provide strong decision-making support for medical staff.

[0109] See also Figure 2 , Figure 2An electric current stimulation system 200 for suppressing stress response during gastrointestinal anastomosis provided in an embodiment of the present application includes a data acquisition module 201, a first prediction module 202, a second prediction module 203, a data clustering module 204, a third prediction module 205, a fourth prediction module 206, a data fusion module 207, and a strategy determination module 208, wherein the data acquisition module 201 is used to capture the bioelectric current on the surface of the target patient during the operation to obtain the first data, and to obtain the tissue movement under the endoscopic field of view to obtain the second data; the first prediction module 202 is used to perform a state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the stress response of the target patient during the gastrointestinal anastomosis; the second prediction module 203 is used to perform a state trend prediction on the second data to obtain a state trend prediction result corresponding to the second data in the stress response of the target patient during the gastrointestinal anastomosis a second prediction result; a data clustering module 204, used to perform data clustering on the first data and the second data respectively, to obtain a first clustering result corresponding to the first data and a second clustering result corresponding to the second data; a third prediction module 205, used to determine a third prediction result corresponding to the first data in the stress response of the target patient during gastrointestinal anastomosis according to the first clustering result; a fourth prediction module 206, used to determine a fourth prediction result corresponding to the second data in the stress response of the target patient during gastrointestinal anastomosis according to the second clustering result; a data fusion module 207, used to fuse the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the stress response of the target patient during gastrointestinal anastomosis; a strategy determination module 208, used to determine a current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during gastrointestinal anastomosis according to the target prediction result.

[0110] It should be noted that, those skilled in the art can clearly understand that, for the sake of convenience and brevity of description, the specific working process of the electric current stimulation system 200 for suppressing the stress response between gastrointestinal anastomosis operations described above can refer to the corresponding process in the aforementioned embodiment of the electric current stimulation method for suppressing the stress response between gastrointestinal anastomosis operations, and will not be repeated here.

[0111] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0112] like Figure 3As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0113] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0114] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0115] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0116] The processor is used to run a computer program stored in the memory, and implement any one of the current stimulation methods for suppressing stress response during gastrointestinal anastomosis provided by the embodiments of the present invention when executing the computer program.

[0117] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0118] During the operation, the bioelectric current on the surface of the target patient is captured to obtain the first data, and the tissue movement under the endoscopic field of view is obtained to obtain the second data;

[0119] Performing state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the target patient's stress response during digestive tract anastomosis;

[0120] Performing state trend prediction on the second data to obtain a second prediction result corresponding to the second data in the target patient's stress response during digestive tract anastomosis;

[0121] Performing data clustering on the first data and the second data respectively to obtain a first clustering result corresponding to the first data and a second clustering result corresponding to the second data;

[0122] Determine, according to the first clustering result, a third prediction result corresponding to the first data of the target patient's stress response during digestive tract anastomosis;

[0123] Determining, according to the second clustering result, a fourth prediction result corresponding to the second data of the target patient's stress response during digestive tract anastomosis;

[0124] fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the stress response of the target patient during digestive tract anastomosis;

[0125] The current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during gastrointestinal anastomosis is determined according to the target prediction result.

[0126] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned embodiment of the current stimulation method for suppressing the stress response between gastrointestinal anastomosis operations, and will not be repeated here.

[0127] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of the current stimulation method for inhibiting stress response during gastrointestinal anastomosis as provided in the description of the embodiment of the present invention.

[0128] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0129] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0130] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0131] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A current stimulation method for inhibiting stress response during digestive tract anastomosis, characterized in that: The method comprises: During the operation, the bioelectric current on the surface of the target patient is captured to obtain the first data, and the tissue movement under the endoscopic field of view is obtained to obtain the second data; Performing state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the target patient's stress response during digestive tract anastomosis; Performing state trend prediction on the second data to obtain a second prediction result corresponding to the second data in the target patient's stress response during digestive tract anastomosis; Performing data clustering on the first data and the second data respectively to obtain a first clustering result corresponding to the first data and a second clustering result corresponding to the second data; Determine, according to the first clustering result, a third prediction result corresponding to the first data of the target patient's stress response during digestive tract anastomosis; Determining, according to the second clustering result, a fourth prediction result corresponding to the second data of the target patient's stress response during digestive tract anastomosis; fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the target patient's stress response during digestive tract anastomosis; The current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during gastrointestinal anastomosis is determined according to the target prediction result.

2. The method according to claim 1, characterized in that The performing state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the target patient's stress response during digestive tract anastomosis includes: Randomly generate a plurality of integers to be determined as a first position and a second position, and cut the first data according to the first position and the second position to obtain first sub-data, second sub-data, and third sub-data; Using a first ARIMA model to perform data prediction on the first position according to the first sub-data to obtain first predicted data corresponding to the first position; Obtain first real data corresponding to the first position from the first data, and perform model correction on the first ARIMA model according to the first real data and the first predicted data to obtain a first target ARIMA model; Using a second ARIMA model to perform data prediction on the second position according to the first prediction data and the second sub-data to obtain second prediction data corresponding to the second position; Obtain second real data corresponding to the second position from the second data, and perform model correction on the second ARIMA model according to the second real data and the second predicted data to obtain a second target ARIMA model; Determine the position corresponding to the end data in the third sub-data as the third position, and determine the end data in the third sub-data as the third real data corresponding to the third position; Eliminate the third position from the third sub-data to obtain fourth sub-data, and use a third ARIMA model to perform data prediction on the third position according to the fourth sub-data to obtain third predicted data corresponding to the third position; Modify the third ARIMA model according to the third real data and the third predicted data to obtain a third target ARIMA model; Merging the first target ARIMA model, the second target ARIMA model and the third target ARIMA model to obtain a concatenated ARIMA model; Predicting data corresponding to the next time period of the first data according to the spliced ​​ARIMA model to obtain first state data; The first data and the first state data are spliced ​​to obtain first spliced ​​data, and a first state prediction model is used to predict the state trend of the first spliced ​​data to obtain the first prediction result corresponding to the first data in the target patient's stress response during gastrointestinal anastomosis.

3. The method according to claim 1, characterized in that The performing state trend prediction on the second data to obtain a second prediction result corresponding to the second data in the target patient's stress response during digestive tract anastomosis includes: Using a long short-term memory network model to perform data prediction on the second data to obtain second state data corresponding to a next time period of the second data; splicing the second data and the second state data to obtain second spliced ​​data; A second state prediction model is used to perform state trend prediction on the second spliced ​​data to obtain the second prediction result corresponding to the second data in the target patient's stress response during gastrointestinal anastomosis.

4. The method according to claim 1, characterized in that: The determining, according to the first clustering result, a third prediction result corresponding to the first data of the target patient's stress response during digestive tract anastomosis, includes: Obtaining a first entropy value corresponding to each first cluster in the first clustering result, and determining a first weight corresponding to the first cluster according to the first entropy value; Performing data fusion on the first data according to the first weight and the first cluster to obtain first fused data; The state trend of the first fusion data is predicted by using a third state prediction model to obtain the third prediction result corresponding to the first data in the stress response of the target patient during gastrointestinal anastomosis.

5. The method according to claim 1, characterized in that Determining, according to the second clustering result, a fourth prediction result corresponding to the second data in the target patient's stress response during digestive tract anastomosis, includes: Obtaining a second entropy value corresponding to each second cluster in the second clustering result, and determining a second weight corresponding to the second cluster according to the second entropy value; Performing data fusion on the second data according to the second weight and the second cluster to obtain second fused data; The state trend of the second fusion data is predicted by using a fourth state prediction model to obtain the fourth prediction result corresponding to the second data in the stress response of the target patient during gastrointestinal anastomosis.

6. The method according to claim 1, characterized in that The fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the target patient's stress response during digestive tract anastomosis, comprises: Calculating the similarity between any two prediction results among the first prediction result, the second prediction result, the third prediction result and the fourth prediction result, and determining the corresponding abnormal prediction result among the first prediction result, the second prediction result, the third prediction result and the fourth prediction result according to the similarity; Eliminate the abnormal prediction result from the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a fifth prediction result, a sixth prediction result and a seventh prediction result; Performing data construction according to the fifth prediction result, the sixth prediction result and the seventh prediction result to obtain an eighth prediction result; The fifth prediction result, the sixth prediction result, the seventh prediction result and the eighth prediction result are integrated to determine the target prediction result corresponding to the target patient's stress response during gastrointestinal anastomosis.

7. The method according to claim 6, characterized in that The step of constructing data according to the fifth prediction result, the sixth prediction result and the seventh prediction result to obtain an eighth prediction result includes: Determining a target prediction type corresponding to the eighth prediction result; Determine, according to the fifth prediction result, the sixth prediction result and the seventh prediction result, an associated prediction result corresponding to the target prediction type and a non-associated prediction result corresponding to the target prediction type that is not supported; Determine the target support corresponding to the target prediction type according to the associated prediction result and the non-associated prediction result; Determining the eighth prediction result according to the target support and the target prediction type; The target support is obtained according to the following formula: Among them, sup w represents the target support corresponding to the w-th target prediction type, m represents the number of the associated prediction results, all represents the total number of the associated prediction results and the non-associated prediction results, n represents the number of the non-associated prediction results, P i represents the prediction probability of the i-th associated prediction result for the target prediction type, p t represents the prediction probability of the tth associated prediction result for the target prediction type, Q j represents the prediction probability of the jth non-associated prediction result for the target prediction type, Q e Represents the prediction probability of the e-th non-associated prediction result for the target prediction type.

8. An electric current stimulation system for suppressing stress response during digestive tract anastomosis, characterized in that: include: A data acquisition module, used to capture the bioelectric current on the surface of the target patient during surgery to obtain first data, and to obtain the tissue movement under the endoscopic field of view to obtain second data; A first prediction module is used to perform state trend prediction on the first data to obtain a first prediction result corresponding to the first data in the stress response of the target patient during digestive tract anastomosis; A second prediction module is used to perform state trend prediction on the second data to obtain a second prediction result corresponding to the second data in the stress response of the target patient during digestive tract anastomosis; A data clustering module, used to perform data clustering on the first data and the second data respectively, to obtain a first clustering result corresponding to the first data and a second clustering result corresponding to the second data; A third prediction module, configured to determine, according to the first clustering result, a third prediction result corresponding to the first data of the target patient's stress response during digestive tract anastomosis; a fourth prediction module, configured to determine, according to the second clustering result, a fourth prediction result corresponding to the second data of the target patient's stress response during digestive tract anastomosis; A data fusion module, used for fusing the first prediction result, the second prediction result, the third prediction result and the fourth prediction result to obtain a target prediction result corresponding to the stress response of the target patient during digestive tract anastomosis; A strategy determination module is used to determine the current stimulation strategy corresponding to the current stimulation of the stress response of the target patient during gastrointestinal anastomosis according to the target prediction result.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the current stimulation method for suppressing stress response between digestive tract anastomosis operations as described in any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the current stimulation method for suppressing stress response between gastrointestinal anastomosis operations described in any one of claims 1 to 7.

Images