Intelligent medium-long operation anesthesia target control system

Abstract

The application provides a kind of intelligent medium and long operation anesthesia target control system, comprising: matching model construction module, for obtaining historical operation category data and corresponding historical anesthesia mode data, and constructing operation category and anesthesia mode matching model;Anesthesia mode determination module, for obtaining the operation category of patient to be carried out, based on operation category and anesthesia mode matching model, determine the anesthesia mode and anesthesia drug dosage to be used by patient;Anesthesia target control implementation module, for implementing intelligent anesthesia target control according to anesthesia mode, based on the preset anesthesia mode and sign state data cyclic cross-linking control model.This application provides the anesthesia mode of static suction composite anesthesia according to the characteristics of medium and long operation, by establishing the cyclic cross-linking control model of intelligent anesthesia, sign state monitoring, sign state data display, realizes anesthesia drug precision target control, improves the safety of medium and long operation anesthesia.

Description

Technical Field

[0001] This invention relates to the field of intelligent anesthesia technology, and in particular to an intelligent target control system for anesthesia in medium- and long-term surgeries. Background Technology

[0002] Medium and long surgeries require a long anesthesia time. If only one type of anesthesia is used, the best anesthesia effect cannot be achieved. There are three types of anesthesia: inhalation anesthesia, intravenous anesthesia, and combined inhalation and intravenous anesthesia. Combined inhalation and intravenous anesthesia combines inhalation anesthesia and intravenous anesthesia. Combined inhalation and intravenous anesthesia can achieve the best anesthesia effect for medium and long surgeries. However, combined inhalation and intravenous anesthesia increases the workload and difficulty of anesthesia for anesthesiologists. In the midst of busy anesthesia, inappropriate operation is prone to occur. At the same time, it is necessary to combine EEG anesthesia parameters, vital sign parameters, and respiratory system parameters to achieve stable anesthesia of the patient's vital signs.

[0003] In existing medium- and long-term surgical anesthesia procedures, there are still problems such as imprecise intravenous anesthesia dosage based on inhaled anesthetic dosage as the basic anesthetic dosage; there is also a lack of systematic and detailed anesthesia target control programs for different surgical categories, and the technology for adjusting the anesthetic dosage based on the anesthesia monitoring process is not yet perfect. Therefore, an intelligent medium- and long-term surgical anesthesia target control system is needed. Summary of the Invention

[0004] This invention provides an intelligent target control system for anesthesia in medium- and long surgeries. Based on the characteristics of medium- and long surgeries, it provides anesthesia methods of combined intravenous and inhalation anesthesia. By establishing a cyclical cross-linking control model that integrates intelligent anesthesia, monitoring of vital signs, and display of vital signs data, it achieves precise target control of anesthetic drugs and improves the safety of anesthesia in medium- and long surgeries.

[0005] This invention provides an intelligent target control system for anesthesia in medium- to long-term surgeries, comprising:

[0006] The matching model building module is used to obtain historical surgical category data and corresponding historical anesthesia method data, and to build a matching model between surgical category and anesthesia method;

[0007] The anesthesia method determination module is used to obtain the type of surgery the patient will undergo, and based on the surgical category and anesthesia method matching model, to determine the anesthesia method and dosage of anesthetic drugs to be used for the patient.

[0008] The anesthesia target control implementation module is used to implement intelligent anesthesia target control based on a preset control model that cyclically links anesthesia method and vital sign status data, according to the anesthesia method.

[0009] Furthermore, the matching model building module includes a historical data acquisition unit and a matching model generation unit;

[0010] The historical data acquisition unit is used to acquire historical surgical category data and corresponding historical anesthesia method data based on the medical big data system, and generate historical surgical category datasets and historical modified anesthesia method datasets.

[0011] The matching model generation unit is used to construct a matching model between surgical categories and anesthesia methods based on historical surgical category datasets and historical modified anesthesia method datasets; the surgical category and anesthesia method matching model is used to establish the matching relationship between surgical categories and anesthesia methods.

[0012] Furthermore, the historical data acquisition unit includes:

[0013] Using a pre-set anesthesia teaching simulation device, anesthesia simulation experiments were conducted using a historical surgical category dataset to obtain an anesthesia simulation dataset. The anesthesia simulation dataset was compared with the historical anesthesia method dataset. Based on the pre-set data adoption standards, the historical anesthesia method dataset was corrected according to the comparison results to generate the first corrected historical anesthesia method dataset.

[0014] The first revised dataset of historical anesthesia methods was evaluated by an expert review panel. Based on the evaluation results, a second revision was made to generate the second revised dataset of historical anesthesia methods.

[0015] A historical revised anesthesia method dataset is generated based on the second revised historical anesthesia method dataset.

[0016] Furthermore, the matching model construction module also includes a matching model classification unit, used to classify the matching models of surgical categories and anesthesia methods, specifically including:

[0017] Obtain patient age information, physical signs information, and disease information corresponding to historical surgical categories;

[0018] Based on age information data, several age information ranges are set according to age span values, and the age information range is set as the first label; based on physical sign information data, several physical sign information ranges are set according to health status, and the physical sign information range is set as the second label; based on disease information data, several disease information ranges are set according to disease severity, and the disease information range is set as the third label.

[0019] Using the first, second, and third labels as the basis for division, the surgical category and anesthesia method matching model is divided into several surgical category and anesthesia method matching sub-models.

[0020] Furthermore, the anesthesia method determination module includes a surgical category acquisition unit, an anesthesia method determination unit, and an anesthetic drug dosage determination unit;

[0021] The surgical category acquisition unit is used to acquire patients' age information, physical signs information, and disease information, and determine the corresponding surgical category based on the age information, physical signs information, and disease information.

[0022] The anesthesia method determination unit is used to determine the anesthesia method that matches the surgical category based on the surgical category and the anesthesia method matching model.

[0023] The anesthetic drug dosage determination unit is used to determine the basic dosage and variable dosage of anesthetic drugs. The basic dosage of anesthetic drugs is determined through inhaled anesthetic drugs, and the variable dosage of anesthetic drugs is determined through intravenous injection.

[0024] Furthermore, the anesthesia target control implementation module includes a cyclic cross-linking control model establishment unit and an intelligent anesthesia target control implementation unit;

[0025] The cyclic cross-linking control model establishment unit is used to establish a cyclic cross-linking control model for anesthesia target control drug administration based on the anesthesia method adopted and by using vital sign data monitoring equipment and vital sign data display equipment.

[0026] The intelligent anesthesia target control implementation unit is used to perform basic anesthesia using an anesthesia machine via inhaled anesthetic drugs, monitor vital signs through vital sign data monitoring equipment and vital sign data display equipment, and perform variable anesthesia via intravenous drug injection using an anesthesia infusion pump based on the data displayed by the vital sign data display equipment.

[0027] Furthermore, the monitoring of vital signs data in the intelligent anesthesia target control implementation unit includes:

[0028] Acquire monitoring time points; monitoring time points include the time when the basic surgical state is met, the time when the preset anesthesia depth is reached, the time when the first operation time is taken, and the time when the second operation time is taken; the second operation time is longer than the first operation time.

[0029] Obtain the patient's vital signs and status indicators; these indicators include brain function, cardiac function, pulmonary function, hemodynamics, and blood oxygen saturation.

[0030] Establish a monitoring process view and conduct monitoring based on the monitoring process view; the monitoring process view uses the monitoring time point as the coordinate value on the horizontal axis and the patient's vital signs and intravenous drug injection volume as several types of coordinate values ​​on the vertical axis.

[0031] Furthermore, the intelligent anesthesia target control implementation unit also includes a monitoring anomaly alert subunit, used to alert users of abnormal monitoring results, specifically including:

[0032] Obtain anomaly datasets from historical monitoring records located at different monitoring time points;

[0033] Based on a pre-trained long short-term memory neural network, the probability of anomalies in monitoring records is predicted using a dataset of historical monitoring record anomalies.

[0034] Based on the probability magnitude, select the historical monitoring record abnormal dataset that is less than the preset probability threshold, and set the data in the historical monitoring record abnormal dataset as the critical alarm data;

[0035] Set the upper and lower limits of the critical alarm data value; collect and obtain monitoring record data at the monitoring time point location; when the monitoring record data value is lower than the upper limit of the critical alarm data value, or higher than the lower limit of the critical alarm data value, issue a monitoring alert and obtain monitoring abnormal results.

[0036] Furthermore, it also includes an anesthesia target control adjustment module, specifically including:

[0037] Establish surgical safety assessment standards based on surgical category and anesthesia method;

[0038] Based on the numerical values ​​of patients' vital signs and status indicators, establish patient comfort assessment standards;

[0039] Based on surgical safety assessment criteria and patient comfort assessment criteria, seven target-controlled anesthesia adjustment modes were established; these modes include high safety-high comfort mode, high safety-medium comfort mode, high safety-low comfort mode, medium safety-high comfort mode, and medium safety-medium comfort mode.

[0040] Based on the obtained monitoring anomaly results, seven anesthesia target control adjustment methods were selected for adjustment.

[0041] Furthermore, it also includes a module for generating dynamic demonstration videos of key milestones in anesthesia target control. This module is used to calculate the time taken from the end of surgery to the patient's awakening. Based on the time taken, combined with the anesthesia method and monitoring process views, it generates dynamic demonstration videos of key milestones throughout the surgery, including:

[0042] Record the patient's surgery end time and patient awakening time, and set the patient's status value at the end of surgery and the patient's status value at the time of awakening; add the patient's surgery end time and patient awakening time as the horizontal axis coordinate and the corresponding patient's surgery end time and patient awakening status value as the vertical axis coordinate to the anesthesia method and monitoring process view;

[0043] Based on the anesthesia method and monitoring process view, the materials for video production are obtained; the materials are divided into a first material library and a second material library according to the preset importance and quantity; the first material library is used to provide clinical reference materials for medical staff; the second material library is used to provide popular science materials for patients; based on the first material library and the second material library, a dynamic demonstration video of the important nodes of the entire surgical process is produced.

[0044] Compared with the prior art, the present invention has the following advantages and beneficial effects: Based on the characteristics of medium and long surgery, it provides an anesthesia method of combined intravenous and inhalation anesthesia. By establishing a cyclic cross-linking control model for intelligent anesthesia, monitoring of vital signs, and display of vital signs data, it achieves precise target control of anesthetic drugs and improves the safety of anesthesia for medium and long surgery.

[0045] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0046] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0047] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0048] Figure 1 This is a schematic diagram of the structure of an intelligent target control system for anesthesia in medium-to-long surgeries according to the present invention;

[0049] Figure 2 This is a schematic diagram of the matching model construction module structure of an intelligent target control system for medium- and long-term surgical anesthesia according to the present invention;

[0050] Figure 3 This is a schematic diagram of the anesthesia mode determination module of an intelligent medium-to-long-term surgical anesthesia target control system of the present invention. Detailed Implementation

[0051] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0052] This invention provides an intelligent target control system for anesthesia in medium- to long-term surgeries, such as... Figure 1 As shown, it includes:

[0053] The matching model building module is used to obtain historical surgical category data and corresponding historical anesthesia method data, and to build a matching model between surgical category and anesthesia method;

[0054] The anesthesia method determination module is used to obtain the type of surgery the patient will undergo, and based on the surgical category and anesthesia method matching model, to determine the anesthesia method and dosage of anesthetic drugs to be used for the patient.

[0055] The anesthesia target control implementation module is used to implement intelligent anesthesia target control based on a preset control model that cyclically links anesthesia method and vital sign status data, according to the anesthesia method.

[0056] The working principle of the above technical solution is as follows: For medium- to long-term surgeries with extended anesthesia times, different anesthetic medication methods are required to ensure successful completion. These methods include inhalation anesthesia, intravenous anesthesia, and combined inhalation and intravenous anesthesia. Combined inhalation and intravenous anesthesia combines the advantages of the first two methods, ensuring optimal anesthetic effect, but requires constant monitoring of patient safety throughout the procedure. Therefore, firstly, a matching model construction module acquires historical surgical category data and corresponding historical anesthesia method data, and constructs a surgical category-anesthesia method matching model. Secondly, an anesthesia method determination module acquires the surgical category to be performed by the patient, and based on the surgical category-anesthesia method matching model, determines the anesthesia method and dosage to be used. Finally, an anesthesia target control implementation module implements intelligent anesthesia target control based on a preset anesthesia method and vital sign status data cyclical cross-linking control model.

[0057] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment, based on the characteristics of medium and long surgery, a combined intravenous and inhalation anesthesia method is provided. By establishing a cyclic cross-linking control model for intelligent anesthesia, monitoring of vital signs, and display of vital signs data, precise target control of anesthetic drugs is achieved, thereby improving the safety of anesthesia for medium and long surgery.

[0058] In one embodiment, such as Figure 2 As shown, the matching model building module includes a historical data acquisition unit and a matching model generation unit;

[0059] The historical data acquisition unit is used to acquire historical surgical category data and corresponding historical anesthesia method data based on the medical big data system, and generate historical surgical category datasets and historical modified anesthesia method datasets.

[0060] The matching model generation unit is used to construct a matching model between surgical categories and anesthesia methods based on historical surgical category datasets and historical modified anesthesia method datasets; the matching model between surgical categories and anesthesia methods is used to establish the matching relationship between surgical categories and anesthesia methods.

[0061] The working principle of the above technical solution is as follows: historical data is acquired through a medical big data system, and a matching model between surgical categories and anesthesia methods is constructed based on the historical data. This allows for the convenient and quick establishment of a correspondence between surgical categories and the anesthesia methods used, and the matching is performed based on this relationship. Specifically, this includes: acquiring historical surgical category data and corresponding historical anesthesia method data based on the medical big data system, generating a historical surgical category dataset and a historical corrected anesthesia method dataset; constructing a matching model between surgical categories and anesthesia methods based on the historical surgical category dataset and the historical corrected anesthesia method dataset; and using the matching model to establish the matching relationship between surgical categories and anesthesia methods.

[0062] The beneficial effects of the above technical solution are as follows: by using the solution provided in this embodiment, historical data is obtained through the medical big data system, and a matching model between surgical categories and anesthesia methods is constructed based on the historical data, which can accurately establish the correspondence between surgical categories and anesthesia methods and facilitate the selection of anesthesia methods.

[0063] In one embodiment, the historical data acquisition unit includes:

[0064] Using a pre-set anesthesia teaching simulation device, anesthesia simulation experiments were conducted using a historical surgical category dataset to obtain an anesthesia simulation dataset. The anesthesia simulation dataset was compared with the historical anesthesia method dataset. Based on the pre-set data adoption standards, the historical anesthesia method dataset was corrected according to the comparison results to generate the first corrected historical anesthesia method dataset.

[0065] The first revised dataset of historical anesthesia methods was evaluated by an expert review panel. Based on the evaluation results, a second revision was made to generate the second revised dataset of historical anesthesia methods.

[0066] A historical revised anesthesia method dataset is generated based on the second revised historical anesthesia method dataset.

[0067] The working principle of the above technical solution is as follows: The acquired historical data needs to be verified for its validity and scientific validity. Therefore, verification and correction are carried out in two aspects. First, using a pre-set anesthesia teaching simulation device, anesthesia simulation experiments are conducted using historical surgical category datasets to obtain anesthesia simulation datasets. These datasets are then compared with historical anesthesia method datasets. Based on pre-set data adoption standards and the comparison results, the historical anesthesia method datasets are corrected to generate a first corrected historical anesthesia method dataset. Second, an expert review is conducted to evaluate the first corrected historical anesthesia method dataset. Based on the evaluation results, a second correction is performed to generate a second corrected historical anesthesia method dataset. Finally, based on the second corrected historical anesthesia method dataset, a historical corrected anesthesia method dataset is generated.

[0068] The beneficial effects of the above technical solution are as follows: by using the solution provided in this embodiment, the reliability and scientific nature of the data can be guaranteed by revising the historical anesthesia method dataset twice.

[0069] In one embodiment, the matching model construction module further includes a matching model classification unit for classifying the surgical category and anesthesia method matching models, specifically including:

[0070] Obtain patient age information, physical signs information, and disease information corresponding to historical surgical categories;

[0071] Based on age information data, several age information ranges are set according to age span values, and the age information range is set as the first label; based on physical sign information data, several physical sign information ranges are set according to health status, and the physical sign information range is set as the second label; based on disease information data, several disease information ranges are set according to disease severity, and the disease information range is set as the third label.

[0072] Using the first, second, and third labels as the basis for division, the surgical category and anesthesia method matching model is divided into several surgical category and anesthesia method matching sub-models.

[0073] The working principle of the above technical solution is as follows: In order to facilitate the precise division of the surgical category and anesthesia method matching model, it is necessary to establish model labels based on different category characteristics, thereby dividing the model into several matching sub-models, which helps to improve the relevance and practicality of the surgical category and anesthesia method matching model. Specifically, the following steps are taken: Obtain the patient's age information, vital sign information, and disease information data corresponding to historical surgical category data; Based on the age information data, set several age information ranges according to the age span value, and set the age information range as the first label; Based on the vital sign information data, set several vital sign information ranges according to the health status, and set the vital sign information range as the second label; Based on the disease information data, set several disease information ranges according to the severity of the disease, and set the disease information range as the third label; Using the first label, second label, and third label as the division criteria, the surgical category and anesthesia method matching model is divided into several surgical category and anesthesia method matching sub-models.

[0074] The beneficial effects of the above technical solution are as follows: by using the solution provided in this embodiment, the matching model of surgical category and anesthesia method is refined, thereby improving the pertinence and practicality of the matching model of surgical category and anesthesia method.

[0075] In one embodiment, such as Figure 3 As shown, the anesthesia method determination module includes a surgical category acquisition unit, an anesthesia method determination unit, and an anesthetic drug dosage determination unit;

[0076] The surgical category acquisition unit is used to acquire patients' age information, physical signs information, and disease information, and determine the corresponding surgical category based on the age information, physical signs information, and disease information.

[0077] The anesthesia method determination unit is used to determine the anesthesia method that matches the surgical category based on the surgical category and the anesthesia method matching model.

[0078] The anesthetic drug dosage determination unit is used to determine the basic dosage and variable dosage of anesthetic drugs. The basic dosage of anesthetic drugs is determined through inhaled anesthetic drugs, and the variable dosage of anesthetic drugs is determined through intravenous injection.

[0079] The working principle of the above technical solution is as follows: acquire the patient's age information, vital sign information, and disease information; determine the corresponding surgical category based on the age information, vital sign information, and disease information; determine the anesthesia method that matches the surgical category based on the surgical category and anesthesia method matching model; and use an anesthetic drug dosage determination unit to determine the basic dosage and variable dosage of anesthetic drugs. The basic dosage of anesthetic drugs is determined by inhaled anesthetic drugs, and the variable dosage of anesthetic drugs is determined by intravenous injection.

[0080] Hypotension during anesthesia induction is defined as arterial hypotension occurring within the first 20 minutes after anesthesia induction, or between anesthesia induction and the start of surgery. The incidence of hypotension during anesthesia induction varies considerably depending on the criteria used. To better monitor the occurrence of hypotension during anesthesia induction, this embodiment establishes a logistic regression prediction model to calculate the probability of hypotension during anesthesia induction. The calculation formula is as follows:

[0081]

[0082] Where U is the probability of hypotension during the anesthesia induction period, H represents the heart rate value, and α represents the regression coefficient corresponding to the heart rate value;

[0083] Ace / Arb represents the number of drugs used, either an angiotensin-converting enzyme inhibitor (Ace) or an angiotensin receptor blocker (Arb), and β represents the regression coefficient corresponding to the number of drugs used, either an angiotensin-converting enzyme inhibitor (Ace) or an angiotensin receptor blocker (Arb).

[0084] Bmi represents the patient's body mass index value, and γ represents the regression coefficient corresponding to the patient's body mass index value;

[0085] Ma represents the change in the patient's average blood pressure value, and δ represents the regression coefficient corresponding to the change in the patient's average blood pressure value.

[0086] e-(α*H+β*Ace / Arb*Bmi-δ*Ma) It is an exponential function, representing the calculation of the natural number e to the power of -(α*H+β*Ace / Arb-γ*Bmi-δ*Ma); e≈2.71828;

[0087] The above model shows that a patient's heart rate and the use of angiotensin-converting enzyme inhibitors (Ace) or angiotensin receptor blockers (Arb) are precipitating factors for the probability of hypotension during anesthesia induction. Changes in the patient's mean blood pressure and body mass index (BMI) are protective factors against this probability. An increase in heart rate increases the probability of hypotension, while an increase in BMI decreases it. By monitoring changes in heart rate and mean blood pressure, the probability of hypotension during anesthesia induction can be determined. By setting a probability threshold, the probability of hypotension during anesthesia induction can be controlled, and an early warning can be issued if the threshold is exceeded.

[0088] The beneficial effects of the above technical solution are as follows: By using the solution provided in this embodiment, the type of surgery to be performed can be determined by obtaining the patient's condition information, and the anesthesia method to be used can be determined more clearly, which is conducive to the safe conduct of anesthesia; by predicting and warning of hypotension during the anesthesia induction stage, the occurrence of hypotension during the anesthesia induction stage can be avoided, high-risk patients who may have hypotension during the anesthesia induction stage can be identified in time, and corresponding preventive measures and intervention plans can be taken to reduce the occurrence of adverse reactions after surgery.

[0089] In one embodiment, the anesthesia target control implementation module includes a cyclic cross-linking control model establishment unit and an intelligent anesthesia target control implementation unit;

[0090] The cyclic cross-linking control model establishment unit is used to establish a cyclic cross-linking control model for anesthesia target control drug administration based on the anesthesia method adopted and by using vital sign data monitoring equipment and vital sign data display equipment.

[0091] The intelligent anesthesia target control implementation unit is used to perform basic anesthesia using an anesthesia machine via inhaled anesthetic drugs, monitor vital signs through vital sign data monitoring equipment and vital sign data display equipment, and perform variable anesthesia via intravenous drug injection using an anesthesia infusion pump based on the data displayed by the vital sign data display equipment.

[0092] The working principle of the above technical solution is as follows: the cyclic cross-linking control model establishment unit is used to establish an anesthesia target control drug cyclic cross-linking control model based on the anesthesia method adopted and using vital sign data monitoring equipment and vital sign data display equipment.

[0093] The intelligent anesthesia target control implementation unit is used to perform basic anesthesia using an anesthesia machine via inhaled anesthetic drugs, monitor vital signs through vital sign data monitoring equipment and vital sign data display equipment, and perform variable anesthesia via intravenous drug injection using an anesthesia infusion pump based on the data displayed by the vital sign data display equipment.

[0094] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment and establishing an anesthesia target-controlled drug cycle cross-linking control model, the changes in the patient's vital signs when using anesthesia can be accurately monitored, and corresponding anesthesia target-controlled adjustments can be made to improve the quality and effectiveness of monitoring.

[0095] In one embodiment, monitoring of vital signs data in the intelligent anesthesia target control implementation unit includes:

[0096] Acquire monitoring time points; monitoring time points include the time when the basic surgical state is met, the time when the preset anesthesia depth is reached, the time when the first operation time is taken, and the time when the second operation time is taken; the second operation time is longer than the first operation time.

[0097] Obtain the patient's vital signs and status indicators; these indicators include brain function, cardiac function, pulmonary function, hemodynamics, and blood oxygen saturation.

[0098] Establish a monitoring process view and conduct monitoring based on the monitoring process view; the monitoring process view uses the monitoring time point as the coordinate value on the horizontal axis and the patient's vital signs and intravenous drug injection volume as several types of coordinate values ​​on the vertical axis.

[0099] The working principle of the above technical solution is as follows: Anesthetic drugs can alter the electrical activity in the central nervous system through electroencephalography (EEG). With increasing dosage of most anesthetic drugs, the changes in the average frequency and amplitude of the EEG show a certain similarity. The use of certain higher concentrations of anesthetic drugs can cause sudden onset inhibition; therefore, effective monitoring using monitoring images is necessary, specifically including:

[0100] Acquire monitoring time points; monitoring time points include the time when the basic surgical state is met, the time when the preset anesthesia depth is reached, the time when the first operation time is taken, and the time when the second operation time is taken; the second operation time is longer than the first operation time.

[0101] Obtain the patient's vital signs and status indicators; these indicators include brain function, cardiac function, pulmonary function, hemodynamics, and blood oxygen saturation.

[0102] Establish a monitoring process view and conduct monitoring based on the monitoring process view; the monitoring process view uses the monitoring time point as the coordinate value on the horizontal axis and the patient's vital signs and intravenous drug injection volume as several types of coordinate values ​​on the vertical axis.

[0103] The beneficial effects of the above technical solution are as follows: by adopting the solution provided in this embodiment, the changes in the patient's vital signs during the operation and anesthesia can be displayed more intuitively through the monitoring process view, thereby improving the quality of monitoring.

[0104] In one embodiment, the intelligent anesthesia target control implementation unit further includes a monitoring anomaly alert subunit, used to alert users of abnormal monitoring results, specifically including:

[0105] Obtain anomaly datasets from historical monitoring records located at different monitoring time points;

[0106] Based on a pre-trained long short-term memory neural network, the probability of anomalies in monitoring records is predicted using a dataset of historical monitoring record anomalies.

[0107] Based on the probability magnitude, select the historical monitoring record abnormal dataset that is less than the preset probability threshold, and set the data in the historical monitoring record abnormal dataset as the critical alarm data;

[0108] Set the upper and lower limits of the critical alarm data value; collect and obtain monitoring record data at the monitoring time point location; when the monitoring record data value is lower than the upper limit of the critical alarm data value, or higher than the lower limit of the critical alarm data value, issue a monitoring alert and obtain monitoring abnormal results.

[0109] The working principle of the above technical solution is as follows: For acquiring monitoring anomaly results, by utilizing a historical monitoring record anomaly dataset and a historical long short-term memory neural network, the probability of monitoring record anomalies is first predicted, and then further judgment is made; specifically including:

[0110] Obtain anomaly datasets from historical monitoring records located at different monitoring time points;

[0111] Based on a pre-trained long short-term memory neural network, the probability of anomalies in monitoring records is predicted using a dataset of historical monitoring record anomalies.

[0112] Based on the probability magnitude, select the historical monitoring record abnormal dataset that is less than the preset probability threshold, and set the data in the historical monitoring record abnormal dataset as the critical alarm data;

[0113] Set the upper and lower limits of the critical alarm data value; collect and obtain monitoring record data at the monitoring time point location; when the monitoring record data value is lower than the upper limit of the critical alarm data value, or higher than the lower limit of the critical alarm data value, issue a monitoring alert and obtain monitoring abnormal results.

[0114] The beneficial effects of the above technical solution are as follows: by using the solution provided in this embodiment, and by utilizing a long short-term memory neural network and setting upper and lower limits for the data values ​​of critical alarm data, abnormal monitoring data can be accurately obtained, thereby improving the accuracy of abnormal monitoring results.

[0115] In one embodiment, it further includes an anesthesia target control adjustment module, specifically comprising:

[0116] Establish surgical safety assessment standards based on surgical category and anesthesia method;

[0117] Based on the numerical values ​​of patients' vital signs and status indicators, establish patient comfort assessment standards;

[0118] Based on surgical safety assessment criteria and patient comfort assessment criteria, seven target-controlled anesthesia adjustment modes were established; these modes include high safety-high comfort mode, high safety-medium comfort mode, high safety-low comfort mode, medium safety-high comfort mode, and medium safety-medium comfort mode.

[0119] Based on the obtained monitoring anomaly results, seven anesthesia target control adjustment methods were selected for adjustment.

[0120] The working principle of the above technical solution is as follows: by establishing surgical safety assessment standards and patient comfort assessment standards, the anesthesia method can be adjusted based on monitoring abnormal results; specifically including:

[0121] Establish surgical safety assessment standards based on surgical category and anesthesia method;

[0122] Based on the numerical values ​​of patients' vital signs and status indicators, establish patient comfort assessment standards;

[0123] Based on surgical safety assessment criteria and patient comfort assessment criteria, seven target-controlled anesthesia adjustment modes were established; these modes include high safety-high comfort mode, high safety-medium comfort mode, high safety-low comfort mode, medium safety-high comfort mode, and medium safety-medium comfort mode.

[0124] Based on the obtained monitoring anomaly results, seven anesthesia target control adjustment methods were selected for adjustment.

[0125] The beneficial effects of the above technical solution are as follows: by adopting the solution provided in this embodiment, a basis for adjusting the anesthesia method is provided by establishing surgical safety assessment standards and patient comfort assessment standards.

[0126] In one embodiment, the system further includes a dynamic demonstration video generation module for key anesthesia target control nodes. This module is used to calculate the time taken from the end of surgery to the patient's awakening, and based on the time taken, combined with the anesthesia method and monitoring process view, to generate a dynamic demonstration video of key nodes throughout the entire surgery, including:

[0127] Record the patient's surgery end time and patient awakening time, and set the patient's status value at the end of surgery and the patient's status value at the time of awakening; add the patient's surgery end time and patient awakening time as the horizontal axis coordinate and the corresponding patient's surgery end time and patient awakening status value as the vertical axis coordinate to the anesthesia method and monitoring process view;

[0128] Based on the anesthesia method and monitoring process view, the materials for video production are obtained; the materials are divided into a first material library and a second material library according to the preset importance and quantity; the first material library is used to provide clinical reference materials for medical staff; the second material library is used to provide popular science materials for patients; based on the first material library and the second material library, a dynamic demonstration video of the important nodes of the entire surgical process is produced.

[0129] The working principle of the above technical solution is as follows: It also includes S5, which calculates the time taken from the end of surgery to the patient's awakening, and generates a dynamic demonstration video of the important nodes of the entire surgery based on the time taken, combined with the anesthesia method and monitoring process diagram; the specific steps are as follows:

[0130] Record the patient's surgery end time and patient awakening time, and set the patient's status value at the end of surgery and the patient's status value at the time of awakening; add the patient's surgery end time and patient awakening time as the horizontal axis coordinate and the corresponding patient's surgery end time and patient awakening status value as the vertical axis coordinate to the anesthesia method and monitoring process diagram.

[0131] S503: Based on the anesthesia method and monitoring process diagram, obtain the materials for video production; divide the materials into a first material library and a second material library according to the preset importance and quantity; the first material library is used to provide clinical reference materials for medical staff; the second material library is used to provide popular science materials for patients; based on the first material library, produce a dynamic demonstration video of the important nodes of the first surgery process for medical staff to study and research; based on the second material library, produce a dynamic demonstration video of the important nodes of the second surgery process for patients and their families to watch.

[0132] The beneficial effects of the above technical solution are as follows: By providing the anesthesia method and monitoring process view in the form of video data to medical staff and patients, the solution provided by this embodiment can provide a basis for medical staff to study and research, and provide psychological comfort and guidance for patients and their families to understand the surgical process.

[0133] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An intelligent target control system for anesthesia in medium- to long-term surgeries, characterized in that, include: The matching model building module is used to obtain historical surgical category data and corresponding historical anesthesia method data, and to build a matching model between surgical category and anesthesia method; The anesthesia method determination module is used to obtain the type of surgery the patient will undergo, and based on the surgical category and anesthesia method matching model, to determine the anesthesia method and dosage of anesthetic drugs to be used for the patient. The anesthesia target control implementation module is used to implement intelligent anesthesia target control based on a preset anesthesia method and vital sign status data cyclical cross-linking control model according to the anesthesia method; The anesthesia method determination module includes a surgical category acquisition unit, an anesthesia method determination unit, and an anesthetic drug dosage determination unit. The surgical category acquisition unit is used to acquire patients' age information, physical signs information, and disease information, and determine the corresponding surgical category based on the age information, physical signs information, and disease information. The anesthesia method determination unit is used to determine the anesthesia method that matches the surgical category based on the surgical category and the anesthesia method matching model. The anesthetic drug dosage determination unit is used to determine the basic dosage and variable dosage of anesthetic drugs. The basic dosage of anesthetic drugs is determined through inhaled anesthetic drugs, and the variable dosage of anesthetic drugs is determined through intravenous injection. To monitor the occurrence of hypotension during anesthesia induction, a logistic regression prediction model was established to calculate the probability of hypotension during anesthesia induction. The calculation formula is as follows: ， in, To determine the probability of hypotension during anesthesia induction, Represents heart rate value. This represents the regression coefficient corresponding to the heart rate value; Representative of using an angiotensin-converting enzyme inhibitor (ACEI) ) or angiotensin receptor blockers ( The quantity value of the drug. This corresponds to the use of an angiotensin-converting enzyme inhibitor (ACEI). ) or angiotensin receptor blockers ( The regression coefficient of the quantity value of drugs; This represents the patient's body mass index value. The regression coefficient represents the patient's body mass index value; The value representing the change in the patient's average blood pressure value. Regression coefficients representing changes in the patient's average blood pressure; It is an exponential function; By detecting changes in the patient's heart rate and average blood pressure, the probability of hypotension during the anesthesia induction period can be obtained. By setting a probability threshold, the probability of hypotension during the anesthesia induction period can be controlled, and an early warning can be issued in time if the probability threshold is exceeded.

2. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 1, characterized in that, The matching model building module includes a historical data acquisition unit and a matching model generation unit; The historical data acquisition unit is used to acquire historical surgical category data and corresponding historical anesthesia method data based on the medical big data system, and generate historical surgical category datasets and historical modified anesthesia method datasets. The matching model generation unit is used to construct a matching model between surgical categories and anesthesia methods based on historical surgical category datasets and historical modified anesthesia method datasets; the surgical category and anesthesia method matching model is used to establish the matching relationship between surgical categories and anesthesia methods.

3. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 2, characterized in that, The historical data acquisition unit includes: Using a pre-set anesthesia teaching simulation device, anesthesia simulation experiments were conducted using a historical surgical category dataset to obtain an anesthesia simulation dataset. The anesthesia simulation dataset was compared with the historical anesthesia method dataset. Based on the pre-set data adoption standards, the historical anesthesia method dataset was corrected according to the comparison results to generate the first corrected historical anesthesia method dataset. The first revised dataset of historical anesthesia methods was evaluated by an expert review panel. Based on the evaluation results, a second revision was made to generate the second revised dataset of historical anesthesia methods. A historical revised anesthesia method dataset is generated based on the second revised historical anesthesia method dataset.

4. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 1, characterized in that, The matching model construction module also includes a matching model classification unit, used to classify the matching models between surgical categories and anesthesia methods, specifically including: Obtain patient age information, physical signs information, and disease information corresponding to historical surgical categories; Based on age information data, several age information ranges are set according to age span values, and the age information range is set as the first label; based on physical sign information data, several physical sign information ranges are set according to health status, and the physical sign information range is set as the second label; based on disease information data, several disease information ranges are set according to disease severity, and the disease information range is set as the third label. Using the first, second, and third labels as the basis for division, the surgical category and anesthesia method matching model is divided into several surgical category and anesthesia method matching sub-models.

5. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 1, characterized in that, The anesthesia target control implementation module includes a cyclic cross-linking control model establishment unit and an intelligent anesthesia target control implementation unit; The cyclic cross-linking control model establishment unit is used to establish a cyclic cross-linking control model for anesthesia target control drug administration based on the anesthesia method adopted and by using vital sign data monitoring equipment and vital sign data display equipment. The intelligent anesthesia target control implementation unit is used to perform basic anesthesia using an anesthesia machine via inhaled anesthetic drugs, monitor vital signs through vital sign data monitoring equipment and vital sign data display equipment, and perform variable anesthesia via intravenous drug injection using an anesthesia infusion pump based on the data displayed by the vital sign data display equipment.

6. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 5, characterized in that, Monitoring of vital signs data in the intelligent anesthesia target control implementation unit includes: Acquire monitoring time points; monitoring time points include the time when the basic surgical condition is met, the time when the preset anesthesia depth is reached, the time when the first surgery time is taken, and the time when the second surgery time is taken; the second time is longer than the first time. Obtain the patient's vital signs and status indicators; these indicators include brain function, cardiac function, pulmonary function, hemodynamics, and blood oxygen saturation. Establish a monitoring process view and conduct monitoring based on the monitoring process view; the monitoring process view uses the monitoring time point as the coordinate value on the horizontal axis and the patient's vital signs and intravenous drug injection volume as several types of coordinate values ​​on the vertical axis.

7. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 5, characterized in that, The intelligent anesthesia target control implementation unit also includes a monitoring anomaly alert subunit, used to alert users of abnormal monitoring results, specifically including: Obtain anomaly datasets from historical monitoring records located at different monitoring time points; Based on a pre-trained long short-term memory neural network, the probability of anomalies in monitoring records is predicted using a dataset of historical monitoring record anomalies. Based on the probability magnitude, select the historical monitoring record abnormal dataset that is less than the preset probability threshold, and set the data in the historical monitoring record abnormal dataset as the critical alarm data; Set the upper and lower limits of the critical alarm data value; collect and obtain monitoring record data at the monitoring time point location; when the monitoring record data value is lower than the upper limit of the critical alarm data value, or higher than the lower limit of the critical alarm data value, issue a monitoring alert and obtain monitoring abnormal results.

8. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 7, characterized in that, It also includes an anesthesia target control adjustment module, specifically including: Establish surgical safety assessment standards based on surgical category and anesthesia method; Based on the numerical values ​​of patients' vital signs and status indicators, establish patient comfort assessment standards; Based on surgical safety assessment criteria and patient comfort assessment criteria, five target-controlled anesthesia adjustment modes were established; these modes include high safety-high comfort mode, high safety-medium comfort mode, high safety-low comfort mode, medium safety-high comfort mode, and medium safety-medium comfort mode. Based on the obtained abnormal monitoring results, five anesthesia target control adjustment methods were selected for adjustment.

9. The intelligent target control system for anesthesia in medium-to-long surgeries according to claim 5, characterized in that, It also includes a module for generating dynamic demonstration videos of key milestones in anesthesia target control, used to calculate the time from the end of surgery to the patient's awakening. Based on the time, combined with the anesthesia method and monitoring process view, it generates dynamic demonstration videos of key milestones throughout the surgery, including: Record the patient's surgery end time and patient awakening time, and set the patient's status value at the end of surgery and the patient's status value at the time of awakening; add the patient's surgery end time and patient awakening time as the horizontal axis coordinate and the corresponding patient's surgery end time and patient awakening status value as the vertical axis coordinate to the anesthesia method and monitoring process view; Based on the anesthesia method and monitoring process view, the materials for video production are obtained; the materials are divided into a first material library and a second material library according to the preset importance and quantity; the first material library is used to provide clinical reference materials for medical staff; the second material library is used to provide popular science materials for patients; based on the first material library and the second material library, a dynamic demonstration video of the important nodes of the entire surgical procedure is produced.

Images