Anesthesia depth analysis method and analysis system

Abstract

The invention discloses an anesthesia depth analysis method and system, and the method comprises the steps: firstly setting a standard anesthesia depth analysis model, then obtaining original physiological parameters, carrying out the abnormal value screening preprocessing of the original physiological parameters, obtaining an actual physiological parameter set, carrying out the correction calculation of the actual physiological parameter set, and obtaining a basic parameter set; and finally, outputting current anesthesia state parameters according to the basic parameter sets and the standard anesthesia depth analysis model, and outputting predicted anesthesia state parameters according to a plurality of basic parameter sets and the standard anesthesia depth analysis model. According to the invention, automatic data acquisition and calculation are realized, the workload of an anesthetist is effectively reduced, and the anesthesia effect is improved; meanwhile, dependence on personal experience is effectively reduced through data quantitative analysis, and objectivity and accuracy of an analysis result are improved; moreover, the change trend of the anesthesia depth can be predicted according to the existing data, so that intervention in advance is facilitated, and the comprehensiveness of anesthesia depth monitoring is improved.

Description

Technical Field

[0001] This application relates to the field of biomedical technology, specifically to a method and system for analyzing the depth of anesthesia. Background Technology

[0002] Anesthesia is an essential procedure in surgery. During surgery, anesthesiologists need to observe the patient's clinical manifestations regularly or irregularly, and then combine their own experience to determine whether the current anesthetic state meets the requirements of the surgery. The above judgment relies heavily on the anesthesiologist's work experience and is also constrained by factors such as the level of detail in observation. The anesthesiologist's judgment of the patient's anesthetic state is not objective enough, and can only judge the anesthetic state at the current moment. It is impossible to predict changes in the patient's anesthetic state and lacks comprehensive analysis and monitoring of the patient's depth of anesthesia. Summary of the Invention

[0003] The main purpose of this application is to provide a method and system for analyzing the depth of anesthesia, which aims to solve the shortcomings of existing technologies that cannot comprehensively monitor the depth of anesthesia.

[0004] This application achieves the above objectives through the following technical solutions: A method for analyzing the depth of anesthesia includes the following steps: Establish a standard anesthesia depth analysis model; Obtain the raw physiological parameters, and preprocess the raw physiological parameters according to the outlier screening formula to obtain the actual physiological parameter set; The actual physiological parameter set is corrected and calculated to obtain the basic parameter set; Output the current anesthesia status parameters based on the basic parameter set and the standard anesthesia depth analysis model; Based on several basic parameter sets and the standard anesthesia depth analysis model, the predicted anesthesia state parameters are output.

[0005] Optionally, the expression for the standard anesthesia depth analysis model is: , where R represents the total anesthesia score, and k1-k5 are all constants.

[0006] Optionally, the raw physiological parameters are obtained, and the raw physiological parameters are preprocessed according to the outlier screening formula to obtain the actual physiological parameter set, including the following steps: Based on the types of physiological indicators, the raw physiological parameters are divided into several raw parameter sets I1, ..., I2. i ... I a Where 'a' represents the total number of physiological indicators; Calculate the mean of each original parameter set; the expression for calculating the mean of the i-th type of physiological index is as follows: ,in Let j represent the actual physiological parameter numbered j in the i-th type of physiological index, and n represent the total number of samples of the i-th type of physiological index. Calculate the standard deviation of each original parameter set; the expression for calculating the standard deviation of the i-th physiological index is as follows: ,in Let j represent the actual physiological parameter numbered j in the i-th type of physiological index, and n represent the total number of samples of the i-th type of physiological index. Outlier screening was performed on each original parameter set using the mean, standard deviation, and outlier screening formulas to obtain the actual physiological parameter sets I'1, ..., I'. i ... I' a The expression for the outlier screening formula is as follows: , This represents the actual physiological parameter numbered t among the i-th physiological indicators after screening.

[0007] Optionally, the actual physiological parameter set is corrected and calculated to obtain a basic parameter set, including the following steps: Calculate the arithmetic mean of each physiological indicator based on the actual set of physiological parameters; Each physiological indicator was assigned a correction model; The basic parameter set {V} is obtained by performing correction calculations based on the arithmetic mean and each correction model. ** 1, V ** 2, ..., V ** i , ..., V ** a}

[0008] Optionally, the expression for the arithmetic mean is: ,in T represents the actual physiological parameter t in the i-th physiological indicator, m represents the number of parameters in the i-th physiological indicator after outlier screening, and T represents the number of parameters in the i-th physiological indicator. i V represents the set of the i-th physiological index in the actual physiological parameter set, and its expression is {V}. i、1 V i、2 , ..., V i、t , ..., V i、m The corrected calculation expression for the model is as follows: ,in This represents the baseline value of the i-th physiological indicator of the patient before surgery. This represents the reference value for the i-th physiological indicator in healthy individuals. This represents the correction coefficient for the i-th physiological indicator of the patient.

[0009] Optionally, the current anesthesia status parameters can be output based on the basic parameter set and the standard anesthesia depth analysis model; Normalization models and formulas for calculating the total anesthesia score were established for each physiological indicator. The basic parameter set is normalized according to the normalization model to obtain the normalized parameter values ​​of each physiological indicator. The total anesthesia score is calculated based on the values ​​of each normalized parameter. The current anesthesia status parameters are output based on the total anesthesia score and the standard anesthesia depth analysis model.

[0010] Optionally, the calculation expression for the normalized model is as follows: L i and U i Let i and n represent the lower and upper limits of the i-th physiological indicator under the target anesthesia state, respectively. The formula for calculating the total anesthesia score is as follows: Where 'a' represents the total number of physiological indicators. Let represent the weight value of the i-th physiological indicator, and satisfy . .

[0011] Optionally, predicting anesthesia state parameters based on several basic parameter sets and the standard anesthesia depth analysis model includes the following steps: Acquire several basic parameter sets, and generate historical basic parameter sets based on the acquisition time of each basic parameter set, wherein the expression of the historical basic parameter set is {(V ** 1, V ** 2, ..., V ** i , ..., V ** a ) -1 , (V ** 1, V ** 2, ..., V ** i , ..., V ** a )0}, where 0 represents the current state and -1 represents the historical data with the shortest sampling period from the current state; Interpolation calculations are performed based on the historical baseline parameter set to generate a fitted prediction model; Generate a set of basic prediction parameters {V} based on the fitted prediction model. 1，f V 2，f , ..., V i，f , ..., V a，f}; The prediction base parameter set is normalized according to the normalization model to obtain the prediction normalization parameters; The total predicted anesthesia score is calculated based on the predicted normalization parameter values ​​described above. Based on the predicted total anesthesia score and the standard anesthesia depth analysis model, the predicted anesthesia status parameters are output.

[0012] Optionally, an interpolation calculation is performed based on the historical baseline parameter set to generate a fitted prediction model, including the following steps: The historical baseline parameter set is converted into several time-parameter sequence pairs {(V)} ** 1，-1 , t 1，-1 ), (V ** 1，0 , t 1，0 )},...,{(V ** i，-1 , t i，-1 ), (V ** i，0 , t i，0 )},...,{(V ** a，-1 , t a，-1 ), (V ** a，0 , t a，0 )}; Linear interpolation is performed on each of the aforementioned time-parameter sequences to obtain fitting curves for each physiological indicator; wherein the expression for the fitting curve is: ,in This represents the parameter value of the i-th physiological indicator at the predicted time point. Indicates the predicted time point; The fitted curves are then integrated into a fitted prediction model.

[0013] Accordingly, this application also discloses an analysis system based on the above-mentioned anesthesia depth analysis method, including: The data setting module is used to set up a standard anesthesia depth analysis model; The data preprocessing module is used to obtain actual physiological parameters and preprocess the actual physiological parameters according to the outlier screening formula to obtain the actual physiological parameter set. The data correction module is used to perform correction calculations on the actual physiological parameter set to obtain the basic parameter set; The first analysis module is used to output the current anesthesia status parameters based on the basic parameter set and the standard anesthesia depth analysis model. The second analysis module is used to output predicted anesthesia state parameters based on several basic parameter sets and the standard anesthesia depth analysis model.

[0014] Compared with the prior art, this application has the following beneficial effects: This application first sets up a standard anesthesia depth analysis model, then obtains the original physiological parameters and performs outlier screening preprocessing to obtain the actual physiological parameter set, then performs correction calculations on the actual physiological parameter set to obtain the basic parameter set, and finally outputs the current anesthesia state parameters based on the basic parameter set and the standard anesthesia depth analysis model, and also outputs the predicted anesthesia state parameters based on several basic parameter sets and the standard anesthesia depth analysis model. This application quantifies the target anesthesia state using a standard anesthesia depth analysis model. Then, by collecting physiological parameters such as heart rate and blood pressure, abnormality screening is performed first. Then, the basic parameter set is obtained by combining the patient's own physical condition data. Finally, the degree of deviation from the appropriate anesthesia state is quantitatively calculated using the basic parameter set, and the corresponding anesthesia state is output. Compared with the prior art, this application realizes the fully automated data acquisition and calculation, which can effectively reduce the workload of anesthesiologists and improve the anesthesia effect for patients. Secondly, this application can effectively reduce the reliance on the anesthesiologist's personal experience during the analysis process through real-time data analysis, which is conducive to improving the objectivity and accuracy of the analysis results; at the same time, it can lower the threshold for anesthesia analysis. This application can not only analyze the current depth of anesthesia, but also predict future data based on the changing trends of existing data, and finally output the predicted anesthesia status parameters as a reference for the changing trends of the patient's anesthesia status, thereby allowing anesthesiologists a certain amount of lead time for early intervention. This application enables quantitative analysis and prediction of the depth of anesthesia at the current moment and within a certain future time, thereby achieving full-time monitoring and analysis of the depth of anesthesia and effectively improving the comprehensiveness of anesthesia depth monitoring.

[0015] Finally, this application uses measured parameters of various physiological indicators as raw parameters, filters out some outliers, and corrects the data by combining the patient's underlying diseases and other physiological conditions to obtain a set of basic parameters for actual in-depth analysis and prediction. This highly correlates anesthesia analysis with the actual physical condition, eliminates the influence of various interferences, and effectively improves the accuracy of prediction. Attached Figure Description

[0016] Figure 1 A flowchart of an anesthesia depth analysis method provided for Embodiment 1 of this application; Figure 2 A structural diagram of an anesthesia depth analysis system provided in Embodiment 2 of this application; The objectives, features, and advantages of this application will be further explained in conjunction with the implementation methods and with reference to the accompanying drawings. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0019] In this invention, unless otherwise explicitly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0020] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the meaning of "and / or" throughout the text includes three parallel solutions; for example, "A and / or B" includes solution A, solution B, or a solution that simultaneously satisfies A and B. Furthermore, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0021] Implementation method 1: Reference Figure 1 This embodiment, as an optional embodiment of this application, discloses a method for analyzing the depth of anesthesia, including the following steps: S1. Set up a standard anesthesia depth analysis model; Medical staff can set up a standard anesthesia depth classification model based on the patient's actual condition, or they can directly use a pre-stored standard anesthesia depth analysis model. The expression of the standard anesthesia depth analysis model is as follows: R represents the total anesthesia score, and k1-k5 are all constants. The above parameters need to be set or preset parameters need to be called. It should be noted that the appropriate anesthetic state refers to the optimal anesthetic state that is expected to be achieved. The light anesthetic state and the semi-light anesthetic state both refer to the patient's anesthetic state being lighter than the optimal anesthetic state, close to the conscious state, only with different levels of consciousness, and the patient is in a state of insufficient anesthesia. The semi-deep anesthetic state and the deep anesthetic state indicate that the anesthetic state is deeper than the optimal anesthetic state, and the patient is in a state of excessive anesthesia. S2. Obtain the raw physiological parameters, and preprocess the raw physiological parameters according to the outlier screening formula to obtain the actual physiological parameter set; S21. Based on the types of physiological indicators, the raw physiological parameters are divided into several raw parameter sets I1, ..., I2. i ... I a Where 'a' represents the total number of physiological indicators; All raw physiological parameters collected by the device are retrieved, classified according to the type of physiological indicator, and several raw parameter sets I1, ..., I2 are generated. i ... I a Where 'a' represents the total number of physiological indicators; For example, all heart rate parameters can be grouped into the same set to generate a raw parameter set for heart rate; similarly, parameters related to respiratory rate can be grouped into the same set. That is, the general expression for the original parameter set is I. i ={V i,1 V i,2 V i,3 , ..., V i,n The sampling period for different physiological indicators may vary depending on the equipment used, which may result in different numbers of elements in the original parameter set. It should be noted that the specific types of physiological indicators can be specified by medical staff, such as heart rate, respiratory rate, bispectral index, and mean arterial pressure. If four physiological indicators are set as above, then a=4; S22. Calculate the mean of each original parameter set; the expression for calculating the mean of the i-th type of physiological index is: ,in Let j represent the actual physiological parameter numbered j in the i-th type of physiological index, and n represent the total number of samples of the i-th type of physiological index. The parameters of each original parameter set are retrieved and their mean values ​​are calculated. The expression for calculating the mean value of the i-th type of physiological index is as follows: ,in Let j represent the actual physiological parameter numbered j in the i-th type of physiological index, and n represent the total number of samples of the i-th type of physiological index. The mean values ​​of each physiological indicator can be obtained through the above calculations; S23. Calculate the standard deviation of each original parameter set; the expression for calculating the standard deviation of the i-th physiological index is as follows: ,in Let j represent the actual physiological parameter numbered j in the i-th type of physiological index, and n represent the total number of samples of the i-th type of physiological index. Calculate the standard deviation of each physiological indicator according to the formula for calculating standard deviation; S24. Based on the mean, standard deviation, and outlier screening formulas, perform outlier screening on each original parameter set to obtain the actual physiological parameter sets I'1, ..., I' i ... I' a The expression for the outlier screening formula is as follows: , This represents the actual physiological parameter numbered t among the i-th physiological indicators after screening.

[0022] The mean and standard deviation of the same physiological indicator are retrieved, and the screening parameters corresponding to that physiological indicator are calculated using the outlier screening formula. The calculation expression for the outlier screening formula is as follows: , This represents the actual physiological parameter numbered t in the i-th physiological indicator after screening; Then, all the original physiological parameters corresponding to this physiological indicator are compared with the calculation results of the above outlier screening formula. Parameters that meet the standard are retained as actual physiological parameters, while those that do not are deleted as outlier parameters. The above outlier screening can remove some parameters with large errors caused by measurement or instrumentation, thereby avoiding their impact on the analysis results and improving the reliability and accuracy of the final analysis results.

[0023] Repeat the above steps to complete the screening of all physiological indicators. All retained parameters are separated according to the type of physiological indicator and then aggregated to generate the actual physiological parameter set.

[0024] S3. Perform correction calculations on the actual physiological parameter set to obtain the basic parameter set; S31. Calculate the arithmetic mean of each physiological indicator based on the actual set of physiological parameters; Obtain the actual physiological parameter set, and calculate the arithmetic mean of each physiological indicator based on the actual physiological parameter set. The expression for the arithmetic mean is as follows: ,in Let t represent the actual physiological parameter numbered t in the i-th physiological indicator, and m represent the number of parameters of the i-th physiological indicator after outlier screening. It should be noted that m satisfies m≤n. T i V represents the set of the i-th physiological index in the actual physiological parameter set, and its expression is {V}. i、1 V i、2 , ..., V i、t , ..., V i、m}; S32. Set correction models for each physiological indicator; The calculation expression for the corrected model is as follows: ,in This represents the baseline value of the i-th physiological indicator of the patient before surgery. This represents the reference value for the i-th physiological indicator in healthy individuals. This represents the correction coefficient for the i-th physiological indicator of the patient; It should be noted that the above parameters were confirmed by medical staff through data collection or by using preset parameters; if the patient does not have any underlying disease corresponding to the physiological indicators, the corresponding correction coefficient is 0. S33. Obtain the basic parameter set {V} by performing correction calculations based on the arithmetic mean and each correction model. ** 1, V ** 2, ..., V ** i , ..., V ** a}

[0025] Based on the correction model corresponding to each physiological indicator, the corresponding arithmetic mean is corrected to obtain the basic parameter set {V}. ** 1, V ** 2, ..., V ** i , ..., V ** a}; If the patient has an underlying disease that affects the aforementioned physiological indicators, the above corrections can effectively eliminate the influence of the underlying disease on the normal range of physiological parameters, thereby improving the accuracy of the baseline parameters.

[0026] S4. Output the current anesthesia status parameters based on the basic parameter set and the standard anesthesia depth analysis model; S41. Set up normalization models and calculation formulas for the total anesthesia score for each physiological indicator; The calculation expression for the normalization model is as follows: L i and U iThese represent the lower and upper limits of the i-th physiological indicator under the target anesthesia state, respectively: Since the units of various physiological indicators are completely different, it is necessary to perform comprehensive preprocessing of the above parameters through normalization to ensure the consistency of the data. Secondly, in the above normalization model, L i and U i These represent the lower and upper limits of the i-th physiological indicator under the target anesthesia state, respectively. The above parameters need to be determined by medical staff or modified according to the patient's actual situation. In the normalization model described above, values ​​below the lower limit indicate that the anesthesia status is far from satisfactory, while values ​​above the upper limit indicate over-anesthesia. Calculation results can be obtained quickly by setting parameters of 0 and 10. The handling of parameters between the lower and upper limits can effectively measure the deviation from the lower limit, thus objectively reflecting the anesthesia status.

[0027] S42. Normalize the basic parameter set according to the normalization model to obtain the normalized parameter values ​​of each physiological indicator; By combining the parameters from step S33 and the above normalization model, the normalized parameter values ​​{s1, s2, ..., s} of all physiological indicators can be obtained. i , ..., s a}; S43. Calculate the total anesthesia score based on the values ​​of each normalized parameter. The formula for calculating the total anesthesia score is as follows: Where 'a' represents the total number of physiological indicators. Let represent the weight value of the i-th physiological indicator, and satisfy . ; The weights of each physiological indicator are flexibly adjusted and determined by medical staff based on the actual situation, and the final total anesthesia score is calculated by combining the above-mentioned formula for calculating the total anesthesia score.

[0028] S44. Output the current anesthesia status parameters based on the total anesthesia score and the standard anesthesia depth analysis model.

[0029] S5. Output predicted anesthesia state parameters based on several basic parameter sets and the standard anesthesia depth analysis model.

[0030] S51. Obtain several basic parameter sets, and generate a historical basic parameter set based on the acquisition time of each basic parameter set, wherein the expression of the historical basic parameter set is {(V ** 1, V ** 2, ..., V ** i , ..., V ** a )-1 , (V ** 1, V ** 2, ..., V ** i , ..., V ** a )0}, where 0 represents the current state and -1 represents the historical data with the shortest sampling period from the current state; Retrieve historical data from the sampling period closest to the current time, and simultaneously retrieve all basic parameter sets for the current time. Output the two sets of parameters as the historical basic parameter sets. S52. Perform interpolation calculations based on the historical basic parameter set to generate a fitted prediction model; S521. Convert the historical basic parameter set into several time-parameter sequence pairs {(V ** 1，-1 , t 1，-1 ), (V ** 1，0 , t 1，0 )},...,{(V ** i，-1 , t i，-1 ), (V ** i，0 , t i，0 )},...,{(V ** a，-1 , t a，-1 ), (V ** a，0 , t a，0 )}; First, the historical baseline parameter set is paired to generate several time-parameter sequence pairs, where the expression for the time-parameter sequence pair is: {(V ** 1，-1 , t 1，-1 ), (V ** 1，0 , t 1，0 )},...,{(V ** i，-1 , t i，-1 ), (V ** i，0 , t i，0 )},...,{(V ** a，-1 , t a，-1 ), (V ** a，0 , t a，0 )}; S522. Perform linear interpolation calculations on each of the time-parameter sequences to obtain fitting curves for each physiological indicator; wherein the expression for the fitting curve is: ,in This represents the parameter value of the i-th physiological indicator at the predicted time point. This indicates the predicted time point.

[0031] Two time-parameter sequence pairs belonging to the same physiological index are selected from the above, and their values ​​are taken in a standard two-dimensional coordinate system according to the above parameters. The corresponding parameters are calculated according to the expression of the fitted curve, where the expression of the fitted curve is: ,in This represents the parameter value of the i-th physiological indicator at the predicted time point. Indicates the predicted time point; S523. Integrate the fitted curves into a fitted prediction model.

[0032] S53. Generate a set of prediction basic parameters {V} based on the fitted prediction model. 1，f V 2，f , ..., V i，f , ..., V a，f}; The current time is delayed by one sampling period as the prediction time point. Then, the corresponding prediction baseline parameters are calculated based on the fitting curves of each physiological function, and merged into a prediction baseline parameter set {V}. 1，f V 2，f , ..., V i，f , ..., V a，f}; S54. Normalize the predicted basic parameter set according to the normalization model to obtain the predicted normalization parameters; The same normalization model as in step S41 is used to normalize each prediction base parameter, thereby generating a set of prediction normalization parameters; S55. Calculate the total predicted anesthesia score based on the predicted normalization parameter values ​​described above. The predicted total anesthesia score can be calculated using the same formula as in step S43.

[0033] S56. Output the predicted anesthesia status parameters based on the predicted total anesthesia score and the standard anesthesia depth analysis model.

[0034] Substituting the calculated predicted total anesthesia score into the standard anesthesia depth analysis model will output the predicted anesthesia status parameters. It should be noted that in the early stages of anesthesia, due to the lack of sufficient historical parameters, parameters for predicting the anesthesia status are generally not output.

[0035] Compared with the prior art, this application realizes the fully automated data acquisition and calculation, which can effectively reduce the workload of anesthesiologists and improve the anesthesia effect for patients. Secondly, this application can effectively reduce the reliance on the anesthesiologist's personal experience during the analysis process through real-time data analysis, which is conducive to improving the objectivity and accuracy of the analysis results; at the same time, it can lower the threshold for anesthesia analysis. This application can not only analyze the current depth of anesthesia, but also predict future data based on the changing trends of existing data, and finally output the predicted anesthesia status parameters as a reference for the changing trends of the patient's anesthesia status, thereby allowing anesthesiologists a certain amount of lead time for early intervention. This application enables quantitative analysis and prediction of the depth of anesthesia at the current moment and within a certain future time, thereby achieving full-time monitoring and analysis of the depth of anesthesia and effectively improving the comprehensiveness of anesthesia depth monitoring.

[0036] Finally, this application uses measured parameters of various physiological indicators as raw parameters, filters out some outliers, and corrects the data by combining the patient's underlying diseases and other physiological conditions to obtain a set of basic parameters for actual in-depth analysis and prediction. This highly correlates anesthesia analysis with the actual physical condition, eliminates the influence of various interferences, and effectively improves the accuracy of prediction.

[0037] Implementation Method 2 Reference Figure 2 This embodiment, as another optional embodiment of this application, discloses an anesthesia depth analysis system, including a data setting module and a data preprocessing module. The data setting module is used for setting the parameters of the standard anesthesia depth analysis model, and is also used for setting various fixed parameters in the calculation formulas such as the correction model, the normalization model, and the total anesthesia score. The output of the data setting module and the output of the data preprocessing module are respectively connected to the data correction module. The output of the data correction module is respectively connected to the first analysis module and the second analysis module. The inputs of the first analysis module and the second analysis module are also respectively connected to the data setting module to retrieve various required data models. The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method of anaesthesia depth analysis, characterized by, The method comprises the following steps: setting a standard anesthetic depth analysis model; acquiring original physiological parameters, pre-processing the original physiological parameters according to an abnormal value screening formula to acquire an actual physiological parameter set; performing correction calculation on the actual physiological parameter set to acquire a basic parameter set; outputting a current anesthetic state parameter according to the basic parameter set and the standard anesthetic depth analysis model; outputting a predicted anesthetic state parameter according to a plurality of basic parameter sets and the standard anesthetic depth analysis model.

2. The method of claim 1, wherein, The expression of the standard anesthetic depth analysis model is: where R represents a total anesthetic score, and k1-k5 are all constants.

3. The method of claim 1, wherein, The method of acquiring original physiological parameters, pre-processing the original physiological parameters according to an abnormal value screening formula to acquire an actual physiological parameter set comprises the following steps: The original physiological parameters are divided into a plurality of original parameter sets I1,..., Iaaccording to the types of the physiological indexes i ,..., Ia a ; wherein a represents the total number of the physiological indexes; The mean value of each original parameter set is calculated respectively, wherein the calculation expression of the mean value of the i-th physiological index is wherein denotes the actual physiological parameter numbered j in the i-th physiological index, and n denotes the total sampling number of the i-th physiological index. Calculate the standard deviation of each original parameter set respectively; wherein the calculation expression of the standard deviation of the i-th physiological index is wherein denotes the actual physiological parameter numbered j in the i-th physiological index, and n denotes the total sampling number of the i-th physiological index. According to the mean, standard deviation and outlier screening formula, the actual physiological parameter set I'1,..., I'Nis obtained by screening outliers from each original parameter set. i , a ; wherein the expression of the outlier screening formula is: , denotes the actual physiological parameter numbered t in the i th physiological index after screening.

4. The method of claim 1, wherein, The method of performing correction calculation on the actual physiological parameter set to acquire a basic parameter set comprises the following steps: calculating an arithmetic mean value of each physiological index according to the actual physiological parameter set; setting a correction model for each physiological index; According to each arithmetic mean value and each correction model, a basic parameter set {V ** 1, V ** 2,..., V ** i ,..., V ** a} is obtained by correction calculation.

5. The method of claim 4, wherein, The expression of the arithmetic mean is wherein represents the actual physiological parameter numbered t in the i-th physiological index, m represents the parameter number of the i-th physiological index after the abnormal value screening, T i represents the set of the i-th physiological index in the actual physiological parameter set, and the expression thereof is i、1 , V i、2 ,..., V i、t ,..., V i、m}; and the calculation expression of the correction model is wherein represents the base value of the i-th physiological index of the patient before the operation, represents the reference value of the i-th physiological index of the healthy population, represents the correction coefficient of the i-th physiological index of the patient.

6. The method of claim 1, wherein, The method of outputting a current anesthetic state parameter according to the basic parameter set and the standard anesthetic depth analysis model; setting a normalization model and an anesthetic total score calculation formula for each physiological index; normalizing the basic parameter set according to the normalization model to acquire a normalized parameter value of each physiological index; calculating an anesthetic total score according to each normalized parameter value; outputting a current anesthetic state parameter according to the anesthetic total score and the standard anesthetic depth analysis model.

7. The method of claim 6, wherein, The calculation expression of the normalization model is where L i and U i respectively represent the lower limit value and the upper limit value of the i-th physiological index under the target anesthesia state; and the calculation expression of the anesthesia total score is where a represents the total number of the physiological indexes, represents the weight value of the i-th physiological index, and satisfies .

8. The method of claim 1, wherein, The method of outputting a predicted anesthetic state parameter according to a plurality of basic parameter sets and the standard anesthetic depth analysis model comprises the following steps: A plurality of basic parameter sets are acquired, and a history basic parameter set is generated according to a collection time of each basic parameter set, wherein an expression of the history basic parameter set is { (V ** 1, V ** 2,..., V ** i ,..., V ** a ) -1 , (V ** 1, V ** 2,..., V ** i ,..., V ** a ) 0}, wherein 0 represents a current state, and -1 represents history data of a sampling period with the shortest time interval from the current state. performing interpolation calculation according to the historical basic parameter set to generate a fitting prediction model; generating a set of predicted base parameters {V 1，f , V 2，f ,..., V i，f ,..., V a，f} from the fitted predictive model; normalizing the predicted basic parameter set according to a normalization model to acquire a predicted normalized parameter; calculating a predicted anesthetic total score according to each predicted normalized parameter value; outputting a predicted anesthetic state parameter according to the predicted anesthetic total score and the standard anesthetic depth analysis model.

9. The method of claim 8, wherein, The method of performing interpolation calculation according to the historical basic parameter set to generate a fitting prediction model comprises the following steps: converting the historical base parameter set into a number of time-parameter sequence pairs { (V ** 1，-1 , t 1，-1 ), (V ** 1，0 , t 1，0 )},..., { (V ** i，-1 , t i，-1 ), (V ** i，0 , t i，0 )},..., { (V ** a，-1 , t a，-1 ), (V ** a，0 , t a，0 )}; Linear interpolation calculation is respectively performed according to each time-parameter sequence, and a fitting curve of each physiological index is respectively obtained; wherein the expression of the fitting curve is wherein represents the parameter value of the i-th physiological index at the prediction time point, represents the prediction time point; integrating each fitting curve into a fitting prediction model.

10. An analysis system for the analysis of depth of anaesthesia according to any one of claims 1 to 9, characterized in that The method comprises the following steps: a data setting module for setting a standard anesthetic depth analysis model; a data preprocessing module for acquiring actual physiological parameters, pre-processing the actual physiological parameters according to an abnormal value screening formula to acquire an actual physiological parameter set; a data correction module for performing correction calculation on the actual physiological parameter set to acquire a basic parameter set; a first analysis module for outputting a current anesthetic state parameter according to the basic parameter set and the standard anesthetic depth analysis model; a second analysis module for outputting a predicted anesthetic state parameter according to a plurality of basic parameter sets and the standard anesthetic depth analysis model.

Images