A rapid detection method for anesthetic components based on artificial intelligence

Abstract

The present invention relates to the technical field of anesthetic component detection, and specifically to a method for rapid detection of anesthetic components based on artificial intelligence. The method obtains the correlation influence degree according to the content fluctuation of each anesthetic component at each evaporation temperature and the change trend of each anesthetic component at different evaporation temperatures; in the current use of anesthetics, the contribution of different anesthetic components to the absorption spectrum in different bands is analyzed to determine the characteristic band; according to the correlation influence of the anesthetic components and the evaporation temperature in the currently used anesthetic, the gas spectrum data and contribution degree in the characteristic band, the gas concentration of the anesthetic component is obtained. The present invention obtains a more accurate concentration of anesthetic gas components by analyzing the influence of evaporation temperature changes on anesthetic components in historical use, combined with the preferred absorption of spectra in different bands, so as to make the detection process more efficient and accurate and improve the quality of rapid detection results.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthetic component detection, and in particular to a method for rapid detection of anesthetic components based on artificial intelligence. Background Art

[0002] Anesthetics are mostly used during surgery. The composition of anesthetics varies according to different anesthesia requirements. During surgery, the anesthesiologist will monitor the concentration of vaporized anesthetic components to ensure the safe and stable use of anesthetics. If the concentration of anesthetic components is not suitable, serious consequences will occur. Therefore, rapid detection of anesthetic components is extremely important for real-time control and adjustment of anesthetics.

[0003] When detecting anesthetic gases, the concentrations of different anesthetic gases can usually be analyzed based on the gas spectrum absorption degree obtained by the spectrometer. However, when injecting anesthetics, the anesthetic liquid is generally vaporized through an evaporator, and the vaporized anesthetic gas is transported to the human body through an anesthesia machine. During the evaporation and vaporization process, the temperature will affect the mixing of the anesthetic components, which will in turn affect the absorption characteristics of different anesthetic gases to light when different anesthetic components absorb the spectrum. The detection error of the anesthetic gas concentration due to the temperature effect is large, resulting in poor quality of the results of rapid detection of anesthetic components. Summary of the invention

[0004] In order to solve the technical problem in the prior art that the detection error of anesthetic gas concentration is large due to the influence of temperature, resulting in poor quality of the result of rapid detection of anesthetic components, the purpose of the present invention is to provide a rapid detection method of anesthetic components based on artificial intelligence, and the technical scheme adopted is as follows:

[0005] According to one aspect of an embodiment of the present invention, a method for rapid detection of anesthetic components based on artificial intelligence is provided.

[0006] A rapid detection method for anesthetic components based on artificial intelligence, comprising:

[0007] Obtain historical content data of each anesthetic component of the anesthetic at different evaporation temperatures and historical gas spectrum data at different bands; obtain gas spectrum data of each anesthetic component in the current anesthetic of the current surgery at different bands;

[0008] According to the historical content data fluctuation of each anesthetic component at each evaporation temperature and the changing trend of the historical data fluctuation of each anesthetic component at different evaporation temperatures, the correlation effect of each anesthetic component and each evaporation temperature is obtained;

[0009] According to the proportion of each anesthetic component in the current anesthetic in the historical gas spectrum data in each band, the contribution of each anesthetic component in each band is determined; based on the contribution, the characteristic band of each anesthetic component is determined;

[0010] Based on the correlation influence between each anesthetic component in the current anesthetic and each evaporation temperature, and according to the gas spectrum data and contribution degree of each anesthetic component in the current anesthetic in the characteristic band, the concentration data of each anesthetic component in the current anesthetic is determined.

[0011] In the above scheme, considering the different processes and types of anesthetics used in different surgeries, even at the same evaporation temperature, the content of anesthetic components will have different change relationships. Therefore, it is necessary to reflect the change range of the anesthetic component content at temperature and the change trend of each anesthetic component at different evaporation temperatures according to the content fluctuation of each anesthetic component at each evaporation temperature, and reflect the mixed influence of temperature increase on the anesthetic component, and obtain the correlation influence degree. Therefore, the influence of temperature on the anesthetic gas mixture is analyzed by combining the historical scenes of anesthetic use, and the accuracy of the subsequent temperature adjustment detection process is improved. Further, in the current environment of anesthetic use, the absorption contribution of different anesthetic components in different bands of the spectrum can be analyzed, so as to select a better band for spectral absorption analysis of different anesthetic components of the current anesthetic according to the contribution degree, that is, to determine the characteristic band and improve the analysis efficiency. Finally, the correlation influence of the anesthetic component and the evaporation temperature is adjusted, and the gas concentration of the anesthetic component is analyzed more efficiently according to the gas spectrum data and contribution degree of the characteristic band, so as to achieve fast and accurate component detection. The present invention obtains more accurate concentrations of anesthetic gas components by analyzing the effects of changes in evaporation temperature on anesthetic components during historical use, combining the optimization of spectral absorption in different bands, making the detection process more efficient and accurate, and improving the quality of rapid detection results.

[0012] Furthermore, the method for obtaining the correlation influence includes:

[0013] At each evaporation temperature, the change of each anesthetic component at each evaporation temperature is determined according to the degree of change of the historical content data of each anesthetic component;

[0014] Determine the effect of each anesthetic component on the change of evaporation temperature based on the degree of change trend of each anesthetic component at all evaporation temperatures;

[0015] Combined with the change of each anesthetic component at each evaporation temperature and the influence of each anesthetic component on the change of evaporation temperature, the correlation influence of each anesthetic component and each evaporation temperature is determined.

[0016] In the above scheme, the change in the historical content data of the same anesthetic component at the same evaporation temperature reflects that the anesthetic component will adjust its content according to demand in the same anesthesia scenario. The change of each anesthetic component at each evaporation temperature is obtained by the degree of change, reflecting that the higher the demand for adjustment of the content of the anesthetic component, the greater the impact after vaporization, so the degree of correlation needs to be paid more attention. Further analyze the changing trend of the change of the same anesthetic component at different evaporation temperatures to reflect the degree of influence of temperature changes. Combined with the change impact and the change situation, the change impact is quantitatively adjusted through the change situation to obtain the correlation impact between each anesthetic component and each temperature data, so as to facilitate the subsequent correction of the detection and analysis results based on the correlation impact.

[0017] Furthermore, the method for obtaining the change condition includes:

[0018] At each evaporation temperature, the range of each anesthetic component corresponding to all historical content data is taken as the change of each anesthetic component at each evaporation temperature.

[0019] In the above scheme, the range of historical content data, that is, the degree of change, is reflected through the extreme difference, which more comprehensively considers the possibility of numerical changes.

[0020] Furthermore, the method for obtaining the change impact includes:

[0021] Arrange the changes of each anesthetic component in order of evaporation temperature from small to large to obtain the change sequence of each anesthetic component;

[0022] According to the numerical change between each change situation and the adjacent change situation in the change sequence of each anesthetic component, the change degree of each change situation is obtained;

[0023] A straight line fitting is performed on the change in the change sequence of each anesthetic component, and the fitting slope is negatively correlated to obtain the change trend of each anesthetic component;

[0024] Through the change trend of each anesthetic component and the distribution disorder of all change degrees in the change sequence of each anesthetic component, it is determined that each anesthetic component is affected by the change of evaporation temperature.

[0025] In the above scheme, the higher the temperature, the more uniform the gas mixing. Therefore, when the correlation between the anesthetic component and the evaporation temperature is greater, the variable range of the historical content data of the anesthetic component is smaller as the temperature rises. Therefore, the change trend degree is obtained by fitting the slope to reflect this change relationship, and the trend fitting is evaluated and adjusted by the actual change degree of each change situation. When the change degree is more complex, the credibility of the change trend degree is lower. The change impact is obtained by combining the change impact to more accurately reflect the degree to which the anesthetic component is affected by temperature.

[0026] Furthermore, the determination of the influence of the change in evaporation temperature on each anesthetic component by the change trend of each anesthetic component and the distribution disorder of all change degrees in the change sequence of each anesthetic component includes:

[0027] The change trend of each anesthetic component is negatively correlated with the difference of the value 1 to obtain the change correlation of each anesthetic component;

[0028] The variances of all the changes in the change series of each anesthetic component are negatively correlated and mapped as the trend weight of each anesthetic component;

[0029] The product of the change correlation of each anesthetic component and the trend weight was taken as the change impact of each anesthetic component.

[0030] In the above scheme, the change correlation reflects the possibility that the change trend is a uniform change. When the change trend degree is closer to the uniform change, the correlation between the anesthetic component and the temperature is stronger. The variance reflects the distribution chaos. When the chaos of the change degree is lower, the credibility of the trend fitting is higher. Therefore, when the change correlation and the trend weight are larger, the change impact is greater, which means that the correlation between the anesthetic component and the temperature is greater, making the credibility of the change impact high, which is convenient for the subsequent comprehensive analysis of the correlation.

[0031] Furthermore, the method for obtaining the contribution degree includes:

[0032] Taking each band as an analysis segment in turn, for any anesthetic component in the current anesthetic, obtaining the absorbance of the anesthetic component according to the historical gas spectrum data of the anesthetic component in the analysis segment;

[0033] Combining historical gas spectrum data of all anesthetic components in the current anesthetic on the analysis segment, determining the historical total absorbance of the current anesthetic;

[0034] The ratio of the absorbance of the anesthetic component to the total historical absorbance of the current anesthetic is taken as the contribution of the anesthetic component to the analysis segment.

[0035] In the above scheme, the distribution diversity of anesthetic components in anesthetics used in anesthesia scenarios is taken into account. Through the known absorption conditions of historical analysis and the comprehensive absorption conditions of each anesthetic component in the current anesthetic, the contribution of each anesthetic component in the absorption process of the current anesthetic after historical analysis is obtained, thereby reducing the overlapping error of the absorption conditions during the current analysis alone and improving the detection capability of the current anesthesia.

[0036] Further, obtaining the absorbance of the anesthetic component according to the historical gas spectrum data of the anesthetic component in the analysis segment includes:

[0037] The accumulated value of all historical gas spectrum data of the anesthetic component in the analysis section is taken as the absorbance of the anesthetic component.

[0038] Furthermore, determining the characteristic band of each anesthetic component based on the contribution degree includes:

[0039] For any anesthetic component in the current anesthetic, when the contribution of the anesthetic component on the band is greater than a preset contribution rate, the corresponding band is used as the characteristic band of the anesthetic component.

[0040] In the above scheme, the characteristic bands of anesthetic components with significant contributions are screened out for subsequent absorption analysis, thereby reducing the calculation of data with low characteristics, thereby improving the accuracy and the speed of subsequent analysis.

[0041] Further, based on the correlation influence between each anesthetic component and each evaporation temperature in the current anesthetic, according to the gas spectrum data and contribution degree of each anesthetic component in the current anesthetic in the characteristic band, the gas concentration data of each anesthetic component in the current anesthetic is determined, including:

[0042] Obtaining the current evaporation temperature of the current anesthetic; for any anesthetic component in the current anesthetic, negatively mapping the correlation effect between the anesthetic component and the current evaporation temperature as the temperature contribution of the anesthetic component;

[0043] The gas concentration data of the anesthetic component is used as the dependent variable of the multiple linear regression, the temperature contribution of the anesthetic component, the gas spectrum data of the anesthetic component in each characteristic band and the contribution degree are used as the independent variables of the multiple linear regression, and the multiple linear regression model of the anesthetic component in each characteristic band is constructed;

[0044] An optimal regression model is determined among all multivariate linear regression models of the anesthetic component, and gas concentration data of the anesthetic component is obtained through the optimal regression model.

[0045] In the above scheme, the linear relationship between multiple independent variables and dependent variables is reflected by the regression model, and the dependent variable results, that is, the gas concentration data, are determined by multiple independent variables. The relationship between multiple regression models can be obtained in different characteristic bands, and the optimal regression model is obtained through evaluation to more accurately obtain the gas concentration data of each anesthetic component.

[0046] Furthermore, the method for determining the optimal solution regression model includes:

[0047] The mean square error is used as the evaluation index of each multivariate linear regression model; the cross-validation results of each multivariate linear regression model are obtained through cross-validation;

[0048] According to the evaluation indicators and cross-validation results, the optimal solution regression model is determined from all multivariate linear regression models.

[0049] According to another aspect of an embodiment of the present invention, a rapid detection system for anesthetic components based on artificial intelligence is provided.

[0050] An artificial intelligence-based rapid detection system for anesthetic components, comprising:

[0051] A data acquisition module is used to acquire historical content data of each anesthetic component of the anesthetic at different evaporation temperatures and historical gas spectrum data at different bands; in the current anesthetic of the current surgery, the gas spectrum data of each anesthetic component at different bands is acquired;

[0052] A correlation analysis module is used to obtain the correlation effect of each anesthetic component and each evaporation temperature according to the fluctuation of the historical content data of each anesthetic component at each evaporation temperature and the changing trend of the fluctuation of the historical data of each anesthetic component at different evaporation temperatures;

[0053] The characteristic band analysis module is used to determine the contribution of each anesthetic component in each band according to the proportion of historical gas spectrum data of each anesthetic component in the current anesthetic in each band; and determine the characteristic band of each anesthetic component based on the contribution;

[0054] The detection module is used to determine the gas concentration data of each anesthetic component in the current anesthetic based on the correlation influence of each anesthetic component in the current anesthetic and each evaporation temperature, according to the gas spectrum data and contribution degree of each anesthetic component in the current anesthetic in the characteristic band.

[0055] According to yet another aspect of an embodiment of the present invention, a computer device is provided.

[0056] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of a method for rapid detection of anesthetic components based on artificial intelligence as described above.

[0057] According to yet another aspect of an embodiment of the present invention, a computer-readable storage medium is provided.

[0058] A computer-readable storage medium having a computer program stored therein, wherein the computer program can be executed by at least one processor so as to enable the at least one processor to perform the steps of the above-mentioned method for rapid detection of anesthetic components based on artificial intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 A flow chart of a method for rapid detection of anesthetic components based on artificial intelligence provided by one embodiment of the present invention;

[0061] Figure 2 A schematic diagram of gas spectrum data of multiple anesthetic components provided by an embodiment of the present invention;

[0062] Figure 3 A schematic diagram of the structure of an anesthesia machine provided by one embodiment of the present invention;

[0063] Figure 4 A flow chart of a method for obtaining correlation influence provided by an embodiment of the present invention;

[0064] Figure 5 A structural diagram of an artificial intelligence-based rapid anesthetic component detection system provided by one embodiment of the present invention;

[0065] Figure 6 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of a rapid detection method of anesthetic components based on artificial intelligence proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0067] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0068] The specific scheme of the method for rapid detection of anesthetic components based on artificial intelligence provided by the present invention is described in detail below with reference to the accompanying drawings.

[0069] Embodiment 1:

[0070] The embodiment of the present invention provides a method for rapid detection of anesthetic components based on artificial intelligence. Figure 1 , which shows a flow chart of a method for rapid detection of anesthetic components based on artificial intelligence provided by an embodiment of the present invention, the method comprising the following steps:

[0071] S1: Obtain historical content data of each anesthetic component of the anesthetic at different evaporation temperatures and historical gas spectrum data at different bands; in the current anesthetic of the current surgery, obtain gas spectrum data of each anesthetic component at different bands.

[0072] In order to facilitate the rapid detection of the real-time anesthesia process, it is necessary to first analyze the temperature influence of different anesthetic components based on historical data to improve the detection efficiency of the current anesthesia process. In the embodiment of the present invention, the evaporation temperature of various anesthetics and the historical content data of each anesthetic component of the corresponding anesthetic are obtained from the hospital anesthesia department database. The content of the anesthetic component refers to the ratio of various anesthetic components in the anesthetic. This ratio is a fixed ratio generated according to specific anesthesia needs. It is vaporized at the evaporation temperature and transmitted as an anesthetic gas. At the same time, the historical gas spectrum data of each anesthetic component in different bands is obtained through a spectrometer. Please refer to Figure 2 , which shows a schematic diagram of gas spectrum data of multiple anesthetic components provided by an embodiment of the present invention. The band is a range of continuous wavelengths. As an example, the embodiment of the present invention divides the value of the maximum wavelength equally, and the segment corresponding to each group of values ​​is taken as a band, and 50 bands are obtained. The selection of specific bands can be screened according to the specific implementation situation, and is not limited here.

[0073] At the same time, based on the accuracy of historical data, the current intraoperative anesthetic usage is obtained. During the operation of the anesthesia machine, the gas spectrum data of each anesthetic component in different bands of the embodiment is obtained. The division and selection of the band are consistent with the historical data. Please refer to Figure 3 , which shows a schematic diagram of the structure of an anesthesia machine provided by an embodiment of the present invention. After the anesthetic solution is vaporized, it will be transported to the human body's respiratory receiving point along with carrier gases such as oxygen.

[0074] At this point, the acquisition of anesthetic-related data is completed.

[0075] S2: Based on the historical content data fluctuations of each anesthetic component at each evaporation temperature and the changing trend of the historical data fluctuations of each anesthetic component at different evaporation temperatures, the correlation effect of each anesthetic component and each evaporation temperature is obtained.

[0076] The proportion of anesthetics before use is fixed. By controlling the carrier flow rate, the anesthesiologist can adjust the concentration of anesthetic gas. Since the anesthetic needs to be evaporated during the anesthesia process, different temperatures will lead to different mixing uniformity of different anesthetic components, that is, there are differences in the proportions of different anesthetic components. At the same time, due to the use of various anesthetics during the surgical process, the proportions of anesthetics will also be different. If only the overall correlation is analyzed, it is difficult to obtain accurate related situation effects. Therefore, combined with the changes in the proportions of anesthetics in different scenarios and the evaporation temperature, a comprehensive analysis of the correlation between each anesthetic component and each evaporation temperature is conducted.

[0077] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the associated influence can be found in Figure 4 , which shows a flow chart of a method for obtaining association influence provided by an embodiment of the present invention, the method comprising the following steps:

[0078] S201: At each evaporation temperature, according to the degree of change of the historical content data of each anesthetic component, determine the change of each anesthetic component at each evaporation temperature.

[0079] The changes in historical content data of the same anesthetic component at the same evaporation temperature reflect that the anesthetic component will adjust its content according to demand in the same anesthesia scenario. The changes in each anesthetic component at each evaporation temperature are obtained by the degree of change. The higher the adjustment demand for the content of the anesthetic component at this evaporation temperature, the greater the impact after vaporization, so higher attention should be paid to the degree of correlation.

[0080] Preferably, in some implementations of the embodiments of the present invention, the method for acquiring the change situation includes:

[0081] At each evaporation temperature, the range of all historical content data corresponding to each anesthetic component is used as the change of each anesthetic component at each evaporation temperature. The range reflects the range of historical content data, that is, the degree of change, and more comprehensively considers the change of values.

[0082] In other embodiments of the present invention, calculations that reflect the degree of change, such as the interquartile range, may also be used to obtain the change situation, which is not limited here.

[0083] S202: Determine the influence of the change of the evaporation temperature on each anesthetic component according to the degree of the change trend of the change of each anesthetic component at all evaporation temperatures.

[0084] Further analysis of the changing trend of the same anesthetic component at different evaporation temperatures reflects the degree to which the anesthetic component is affected by the change in evaporation temperature. Considering that the higher the temperature, the more uniform the gas mixture. Therefore, when the correlation between the anesthetic component and the evaporation temperature is greater, the range of variation of the historical content data of the anesthetic component is smaller as the temperature rises. Based on this feature, the negative correlation between the change and the evaporation temperature reflects the change impact.

[0085] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the change impact includes:

[0086] The change conditions of each anesthetic component are arranged in order of evaporation temperature from small to large to obtain a change sequence of each anesthetic component. According to the numerical change between each change condition and the adjacent change condition in the change sequence of each anesthetic component, the change degree of each change condition is obtained. As an example, the difference between each change condition and each adjacent change condition is averaged to obtain the change degree of each change condition, reflecting the local change degree of the change condition. In other embodiments of the present invention, the ratio of the difference between two adjacent change conditions of each change condition to the corresponding temperature difference can be used as the change degree, which also reflects the local change degree of each change condition, and this is not limited here.

[0087] Furthermore, a linear fit is performed on the changes in the change sequence of each anesthetic component, and the fitting slope is negatively correlated to obtain the change trend of each anesthetic component. It should be noted that linear fitting is a technical means well known to those skilled in the art, such as least squares linear fitting, and is not limited here.

[0088] Finally, the influence of the change of evaporation temperature on each anesthetic component was determined through the change trend of each anesthetic component and the distribution disorder of all change degrees in the change sequence of each anesthetic component.

[0089] In a specific implementation of an embodiment of the present invention, the difference between the change trend degree of each anesthetic component and the value 1 is negatively correlated to obtain the change correlation of each anesthetic component; the variance of all change degrees in the change sequence of each anesthetic component is negatively correlated to serve as the trend weight of each anesthetic component; the product of the change correlation of each anesthetic component and the trend weight is used as the change impact of each anesthetic component.

[0090] The change correlation reflects the possibility that the change trend is a uniform change. When the change trend is closer to a uniform change, the correlation between the anesthetic component and the temperature is stronger. The variance reflects the distribution disorder. When the disorder of the change degree is lower, the credibility of the trend fitting is higher. Therefore, the greater the change correlation and trend weight, the greater the change impact, which means that the correlation between the anesthetic component and the temperature is greater.

[0091] The positive correlation is reflected in the form of a product. In other embodiments of the present invention, the cumulative value of the change correlation of each anesthetic component and the trend weight can also be used as the change impact of each anesthetic component, which will not be elaborated here.

[0092] S203: Determine the correlation effect between each anesthetic component and each evaporation temperature based on the change of each anesthetic component at each evaporation temperature and the effect of the change of the evaporation temperature on each anesthetic component.

[0093] The influence of changes and the change conditions are comprehensively considered, and the influence of changes is quantitatively adjusted through the change conditions of each anesthetic component at each evaporation temperature, so as to obtain the correlation influence between each anesthetic component and each temperature data, so as to facilitate the subsequent correction of detection and analysis results based on the correlation influence.

[0094] As an example, the product of the change of each anesthetic component at each evaporation temperature and the change impact of each anesthetic component is used as the correlation impact of each anesthetic component with each evaporation temperature. When the change is greater, it means that the demand for correlation analysis is higher, and when the change impact is greater, it means that the correlation degree is higher, so the correlation impact is greater.

[0095] In other embodiments of the present invention, the change of each anesthetic component at each evaporation temperature and the sum of the change influence of each anesthetic component can also be used as the correlation influence of each anesthetic component and each evaporation temperature, which will not be elaborated here.

[0096] S3: Determine the contribution of each anesthetic component in each band according to the proportion of historical gas spectrum data of each anesthetic component in the current anesthetic in each band; determine the characteristic band of each anesthetic component based on the contribution.

[0097] When analyzing the spectral absorption, the different anesthetic components in the anesthetic are taken in by the human body in different amounts during anesthesia and the composition of the anesthetic components in different anesthesia situations are different, resulting in differences in the accumulated concentrations of different anesthetic components. This causes overlap in the gas spectrum data for detection, so directly analyzing the concentration of the anesthetic components through the gas spectrum data of the anesthetic components will produce large errors. Therefore, in the current environment of using anesthetics, the absorption contribution of different anesthetic components in different bands of the spectrum is analyzed based on historical data, so that the better bands for spectral absorption analysis of different anesthetic components of the current anesthetic are selected according to the contribution, that is, the characteristic bands are determined to improve the analysis efficiency.

[0098] Preferably, in some implementations of the embodiments of the present invention, the method for obtaining the contribution degree includes:

[0099] Each band is used as an analysis segment in turn, and for any anesthetic component in the current anesthetic, the absorbance of the anesthetic component is obtained based on the historical gas spectrum data of the anesthetic component in the analysis segment. In one implementation of an embodiment of the present invention, the cumulative value of all historical gas spectrum data of the anesthetic component in the analysis segment is used as the absorbance of the anesthetic component to reflect the comprehensive absorption of the anesthetic component. In other embodiments of the present invention, the mean value of all historical gas spectrum data of the anesthetic component in the analysis segment can also be used as the absorbance of the anesthetic component to characterize the absorption, which will not be elaborated here.

[0100] Furthermore, the historical gas spectrum data of all anesthetic components in the current anesthetic are combined in the analysis segment to determine the historical total absorbance of the current anesthetic. The ratio of the absorbance of the anesthetic component to the historical total absorbance of the current anesthetic is used as the contribution of the anesthetic component in the analysis segment. The higher the contribution, the better the absorption of the anesthetic component in the analysis segment, and the higher the credibility in subsequent analysis.

[0101] Preferably, in some implementations of the embodiments of the present invention, the method for determining the characteristic band of each anesthetic component based on the contribution degree includes:

[0102] For any anesthetic component in the current anesthetic, when the contribution of the anesthetic component on the band is greater than the preset contribution rate, the corresponding band is used as the characteristic band of the anesthetic component. By screening out the characteristic bands of anesthetic components with significant contributions for subsequent absorption analysis, the calculation of low-characteristic data is reduced, and the accuracy is improved while the speed of subsequent analysis is increased.

[0103] In a specific implementation of the embodiment of the present invention, the preset contribution rate is set to 0.38. The specific value can be selected by the implementer according to the specific implementation situation, which will not be described in detail here.

[0104] At this point, the screening of characteristic bands is completed.

[0105] S4: Based on the correlation influence between each anesthetic component in the current anesthetic and each evaporation temperature, and according to the gas spectrum data and contribution degree of each anesthetic component in the current anesthetic in the characteristic band, the gas concentration data of each anesthetic component in the current anesthetic is determined.

[0106] Finally, through the correlation between the anesthetic components and the evaporation temperature, the gas concentration of the anesthetic components can be analyzed more efficiently according to the gas spectrum data and contribution degree of the characteristic band. Through the temperature influence of each anesthetic component in the current anesthetic, the significant situation of spectral absorption combined with the actual gas spectrum data obtained, the gas concentration of each anesthetic component can be inferred and analyzed more comprehensively.

[0107] Preferably, in some implementations of the embodiments of the present invention, the method for acquiring the gas concentration data of each anesthetic component in the current anesthetic comprises:

[0108] The current evaporation temperature of the current anesthetic is obtained. For any anesthetic component in the current anesthetic, the correlation effect between the anesthetic component and the current evaporation temperature is negatively correlated and mapped as the temperature contribution of the anesthetic component. When the correlation effect is higher, it means that the anesthetic component changes significantly due to the influence of temperature, and the temperature affects the proportion of the anesthetic component to a high degree. Therefore, based on the analysis of the temperature correlation, the contribution of this anesthetic component is lower under high temperature conditions.

[0109] Furthermore, the gas concentration data of the anesthetic component is used as the dependent variable of the multiple linear regression, and the temperature contribution of the anesthetic component, the gas spectrum data and contribution degree of the anesthetic component in each characteristic band are used as the independent variables of the multiple linear regression to construct a multiple linear regression model of the anesthetic component in each characteristic band. The linear relationship between multiple independent variables and the dependent variable is reflected by the regression model, and the dependent variable result, that is, the gas concentration data, is determined by multiple independent variables. The relationship between multiple regression models can be obtained in different characteristic bands. It should be noted that the construction of the multiple linear regression model is a technical means well known to those skilled in the art and will not be elaborated here.

[0110] Finally, the optimal solution regression model is determined in all multivariate linear regression models of the anesthetic component, and the gas concentration data of the anesthetic component is obtained through the optimal solution regression model. As an example, the mean square error is used as the evaluation index of each multivariate linear regression model, and the cross-validation result of each multivariate linear regression model is obtained through cross-validation. The evaluation index and the cross-validation result are used to evaluate the performance of the model, that is, accuracy, reliability or versatility, etc. According to the evaluation index and the cross-validation result, the optimal solution regression model is determined from all multivariate linear regression models. In other embodiments of the present invention, the optimal solution regression model can also be evaluated and determined based on the feasibility cost and complexity of the regression model to achieve more efficient data detection and analysis, which will not be elaborated here.

[0111] By obtaining the gas concentration of each anesthetic component in the current anesthetic, the total amount of each anesthetic component ingested by the patient can be monitored in real time to ensure the safe and stable use of anesthetics. There is no restriction on the processing of the data after detection.

[0112] It should be noted that, in order to facilitate calculation, all indicator data involved in the calculation in the embodiment of the present invention are preprocessed to eliminate the dimension effect. The specific means of eliminating the dimension effect are technical means well known to those skilled in the art and are not limited here.

[0113] In summary, the present invention takes into account the different processes and types of anesthetics used in different surgeries. Even at the same evaporation temperature, the content of anesthetic components will have different change relationships. Therefore, it is necessary to reflect the change range of the anesthetic component content at temperature and the change trend of each anesthetic component at different evaporation temperatures according to the content fluctuation of each anesthetic component at each evaporation temperature, and reflect the mixed influence of temperature increase on the anesthetic component, and obtain the correlation influence degree. Thus, the influence degree of temperature on the anesthetic gas mixture is analyzed by combining the historical scenes of anesthetic use, and the accuracy of the subsequent temperature adjustment detection process is improved. Further, in the current environment of anesthetic use, the absorption contribution of different anesthetic components in different bands of the spectrum can be analyzed, so as to select a better band for spectral absorption analysis for different anesthetic components of the current anesthetic according to the contribution degree, that is, to determine the characteristic band, and improve the analysis efficiency. Finally, through the adjustment of the correlation influence of the anesthetic component and the evaporation temperature, according to the gas spectrum data and contribution degree of the characteristic band, the gas concentration of the anesthetic component can be more efficiently analyzed, and fast and accurate component detection can be achieved. The present invention obtains more accurate concentrations of anesthetic gas components by analyzing the effects of changes in evaporation temperature on anesthetic components during historical use, combining the optimization of spectral absorption in different bands, making the detection process more efficient and accurate, and improving the quality of rapid detection results.

[0114] Embodiment 2:

[0115] The embodiment of the present invention provides a rapid detection system for anesthetic components based on artificial intelligence. Figure 5 , which shows a structural diagram of an artificial intelligence-based rapid detection system for anesthetic components provided by an embodiment of the present invention. The system 700 includes: a data acquisition module 701, a correlation analysis module 702, a characteristic band analysis module 703 and a detection module 704.

[0116] The data acquisition module 701 is used to acquire the historical content data of each anesthetic component of the anesthetic at different evaporation temperatures and the historical gas spectrum data at different bands; in the current anesthetic of the current surgery, the gas spectrum data of each anesthetic component at different bands is acquired;

[0117] The correlation analysis module 702 is used to obtain the correlation influence of each anesthetic component and each evaporation temperature according to the historical content data fluctuation of each anesthetic component at each evaporation temperature and the change trend of the historical data fluctuation of each anesthetic component at different evaporation temperatures;

[0118] The characteristic band analysis module 703 is used to determine the contribution of each anesthetic component in each band according to the proportion of historical gas spectrum data of each anesthetic component in the current anesthetic in each band; and determine the characteristic band of each anesthetic component based on the contribution;

[0119] The detection module 704 is used to determine the gas concentration data of each anesthetic component in the current anesthetic based on the correlation effect between each anesthetic component in the current anesthetic and each evaporation temperature, according to the gas spectrum data and contribution degree of each anesthetic component in the current anesthetic in the characteristic band.

[0120] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. Since the specific implementation process of a rapid detection system of anesthetic components based on artificial intelligence in this embodiment is the same as the specific implementation process of a rapid detection method of anesthetic components based on artificial intelligence in the above embodiment, it will not be described in detail here.

[0121] Embodiment 3:

[0122] The present invention also provides a computer device, see Figure 6 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device 800 at least includes, but is not limited to, a memory 801, a processor 802 and a communication interface 803 that can be interconnected and communicated via a bus 810.

[0123] The memory 801 may include a large-capacity memory for data or instructions, including at least one type of computer-readable storage medium, the readable storage medium including a flash memory, a hard disk, a read-only memory, a magnetic disk or an optical disk, etc. The memory 801 may be inside or outside the computer device. In an embodiment of the present invention, the memory 801 may be a read-only memory for storing computer program instructions.

[0124] The processor 802 may include one or more integrated circuits for controlling the overall operation of the computer device 800. In the embodiment of the present invention, the processor 802 reads and executes computer program instructions stored in the memory 801 to implement Figure 1 The steps of an artificial intelligence-based rapid detection method for anesthetic components in Example 1 are shown.

[0125] The communication interface 803 is used to establish a communication connection between the computer device 800 and other electronic devices. In an embodiment of the present invention, the communication interface 803 is used to connect the computer device 800 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 800 and the external terminal, etc.

[0126] Embodiment 4:

[0127] The embodiment of the present invention also provides a computer-readable storage medium, such as a flash memory, a hard disk, an optical disk or a server, etc., on which computer program instructions are stored, and the program instructions are executed by a processor to implement corresponding functions. The computer-readable storage medium in the embodiment of the present invention is used to store computer program instructions of a method for rapid detection of anesthetic components based on artificial intelligence, and the processor executes the steps of the method for rapid detection of anesthetic components based on artificial intelligence.

[0128] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A rapid detection method for anesthetic components based on artificial intelligence, characterized in that: The method comprises: Obtain historical content data of each anesthetic component of the anesthetic at different evaporation temperatures and historical gas spectrum data at different bands; obtain gas spectrum data of each anesthetic component in the current anesthetic of the current surgery at different bands; According to the historical content data fluctuation of each anesthetic component at each evaporation temperature and the changing trend of the historical data fluctuation of each anesthetic component at different evaporation temperatures, the correlation effect of each anesthetic component and each evaporation temperature is obtained; The method for obtaining the association impact includes: At each evaporation temperature, the change of each anesthetic component at each evaporation temperature is determined according to the degree of change of the historical content data of each anesthetic component; Determine the effect of each anesthetic component on the change of evaporation temperature based on the degree of change trend of each anesthetic component at all evaporation temperatures; Combined with the change of each anesthetic component at each evaporation temperature and the influence of each anesthetic component on the change of evaporation temperature, determine the correlation effect of each anesthetic component with each evaporation temperature; According to the proportion of each anesthetic component in the current anesthetic in the historical gas spectrum data in each band, the contribution of each anesthetic component in each band is determined; based on the contribution, the characteristic band of each anesthetic component is determined; Based on the correlation influence of each anesthetic component in the current anesthetic and each evaporation temperature, and according to the gas spectrum data and contribution degree of each anesthetic component in the current anesthetic in the characteristic band, the gas concentration data of each anesthetic component in the current anesthetic is determined; include: Obtaining the current evaporation temperature of the current anesthetic; for any anesthetic component in the current anesthetic, negatively mapping the correlation effect between the anesthetic component and the current evaporation temperature as the temperature contribution of the anesthetic component; The gas concentration data of the anesthetic component is used as the dependent variable of the multiple linear regression, the temperature contribution of the anesthetic component, the gas spectrum data of the anesthetic component in each characteristic band and the contribution degree are used as the independent variables of the multiple linear regression, and the multiple linear regression model of the anesthetic component in each characteristic band is constructed; An optimal regression model is determined among all multivariate linear regression models of the anesthetic component, and gas concentration data of the anesthetic component is obtained through the optimal regression model.

2. According to claim 1, a rapid detection method of anesthetic components based on artificial intelligence is characterized in that: The method for obtaining the change situation includes: At each evaporation temperature, the range of each anesthetic component corresponding to all historical content data is taken as the change of each anesthetic component at each evaporation temperature.

3. According to claim 1, a rapid detection method of anesthetic components based on artificial intelligence is characterized in that: The method for obtaining the change impact includes: Arrange the changes of each anesthetic component in order of evaporation temperature from small to large to obtain the change sequence of each anesthetic component; According to the numerical change between each change situation and the adjacent change situation in the change sequence of each anesthetic component, the change degree of each change situation is obtained; A straight line fitting is performed on the change in the change sequence of each anesthetic component, and the fitting slope is negatively correlated to obtain the change trend of each anesthetic component; Through the change trend of each anesthetic component and the distribution disorder of all change degrees in the change sequence of each anesthetic component, it is determined that each anesthetic component is affected by the change of evaporation temperature.

4. According to claim 3, a rapid detection method of anesthetic components based on artificial intelligence is characterized in that: The method of determining the influence of the change in evaporation temperature on each anesthetic component by the change trend of each anesthetic component and the distribution disorder of all change degrees in the change sequence of each anesthetic component includes: The change trend of each anesthetic component is negatively correlated with the difference of the value 1 to obtain the change correlation of each anesthetic component; The variances of all the changes in the change series of each anesthetic component are negatively correlated and mapped as the trend weight of each anesthetic component; The product of the change correlation of each anesthetic component and the trend weight was taken as the change impact of each anesthetic component.

5. According to claim 1, a rapid detection method of anesthetic components based on artificial intelligence is characterized in that: The method for obtaining the contribution degree includes: Taking each band as an analysis segment in turn, for any anesthetic component in the current anesthetic, obtaining the absorbance of the anesthetic component according to the historical gas spectrum data of the anesthetic component in the analysis segment; Combining historical gas spectrum data of all anesthetic components in the current anesthetic on the analysis segment, determining the historical total absorbance of the current anesthetic; The ratio of the absorbance of the anesthetic component to the total historical absorbance of the current anesthetic is taken as the contribution of the anesthetic component to the analysis segment.

6. According to claim 5, a rapid detection method of anesthetic components based on artificial intelligence is characterized in that: The step of obtaining the absorbance of the anesthetic component according to the historical gas spectrum data of the anesthetic component in the analysis section includes: The accumulated value of all historical gas spectrum data of the anesthetic component in the analysis section is taken as the absorbance of the anesthetic component.

7. According to claim 1, a rapid detection method of anesthetic components based on artificial intelligence is characterized in that: The characteristic bands of each anesthetic component are determined based on the contribution degree, including: For any anesthetic component in the current anesthetic, when the contribution of the anesthetic component on the band is greater than a preset contribution rate, the corresponding band is used as the characteristic band of the anesthetic component.

8. According to claim 1, a rapid detection method of anesthetic components based on artificial intelligence is characterized in that: The method for determining the optimal solution regression model includes: The mean square error is used as the evaluation index of each multivariate linear regression model; the cross-validation results of each multivariate linear regression model are obtained through cross-validation; According to the evaluation indicators and cross-validation results, the optimal solution regression model is determined from all multivariate linear regression models.

Images