Narcotic combined consumption management system and method

Abstract

The invention relates to the technical field of anesthetic combined consumption management, and discloses an anesthetic combined consumption management system and method, and the method comprises the following steps: 1, obtaining the total primary consumption and the total secondary consumption of an operation, recognizing the operation feature data of the secondary consumption, and carrying out the similar feature classification of the operation feature data; and 2, based on the result of similar feature classification of the operation feature data, calculating to obtain an operation evaluation coefficient. According to the method, the actual condition of the secondary consumption of the anesthetic can be reflected more accurately by processing the regular and irregular change signals respectively, so that the prediction accuracy is improved, the inventory of the anesthetic can be managed more effectively based on the accurate prediction result, the condition of excessive storage or shortage is reduced, the resource utilization efficiency is improved, and the economic benefit is increased. By accurately calculating the preparation amount of the anesthetic, the waste can be reduced, the medical cost can be reduced, and the time for re-extraction due to insufficient anesthetic in the operation process can be shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthetic drug consumption management, and specifically relates to an anesthetic drug consumption management system and method. Background Art

[0002] Anesthetic drugs are a class of drugs that play a crucial role in the medical field. They are mainly used during surgeries or certain medical procedures to temporarily render patients unconscious or relieve pain, ensuring the smooth progress of surgeries or procedures.

[0003] During surgeries, the reasonable management of anesthetic drugs is of utmost importance. Traditional anesthetic drug management methods often lack accurate analysis of the consumption patterns of anesthetic drugs during surgeries and effective countermeasures. On the one hand, when estimating the dosage of anesthetic drugs, different surgical types and patient individual differences have different impacts on the secondary consumption of anesthetic drugs. In actual surgeries, there are often situations where the reserve of anesthetic drugs is either excessive or insufficient. Excessive drug reserve causes waste and increases medical costs, while insufficient drug reserve may require temporary extraction during the surgery, which not only delays the surgery time but also may pose certain risks to patients. Summary of the Invention

[0004] The purpose of the present invention is to provide an anesthetic drug consumption management system and method to solve the above problems in actual surgeries, where there are often situations where the reserve of anesthetic drugs is either excessive or insufficient. Excessive drug reserve causes waste and increases medical costs, while insufficient drug reserve may require temporary extraction during the surgery, which not only delays the surgery time but also may pose certain risks to patients.

[0005] In a first aspect, the present invention provides an anesthetic drug consumption management method, including the following steps:

[0006] Step 1: Obtain the initial consumption total and secondary consumption total of the surgery, identify the surgical characteristic data with secondary consumption, and classify the similar characteristics of the surgical characteristic data.

[0007] Step 2: Based on the result of classifying the similar characteristics of the surgical characteristic data, calculate the surgical evaluation coefficient, analyze the variation relationship between the surgical evaluation coefficient and the secondary consumption total of anesthetic drugs, and generate a non-regular variation signal or a regular variation signal.

[0008] Step 3: Based on the analysis result of the variation relationship between the surgical evaluation coefficient and the secondary consumption total of anesthetic drugs, construct a calculation model for the reserve amount of anesthetic drugs.

[0009] Step 4: Based on the calculation model for the reserve amount of anesthetic drugs, output the predicted value of the secondary consumption total of anesthetic drugs, and analyze it in combination with the actual value of the secondary consumption total of anesthetic drugs to obtain the actual reserve amount of the secondary consumption total of anesthetic drugs.

[0010] In a second aspect, the present invention provides an anesthetic drug consumption management system, which includes:

[0011] Similar feature classification module: Obtain the total initial consumption and total secondary consumption of the surgery, identify the surgical feature data with secondary consumption, and classify the surgical feature data according to similar features;

[0012] Change relationship judgment module: Based on the result of classifying similar features from the surgical feature data, calculate the surgical evaluation coefficient, analyze the change relationship between the surgical evaluation coefficient and the total secondary consumption of anesthetic drugs, and generate an irregular change signal or a regular change signal;

[0013] Model construction module: Based on the analysis result of the change relationship between the surgical evaluation coefficient and the total secondary consumption of anesthetic drugs, construct a calculation model for the reserve quantity of anesthetic drugs;

[0014] Actual reserve quantity calculation module: Based on the calculation model for the reserve quantity of anesthetic drugs, output the predicted value of the total secondary consumption of anesthetic drugs, and analyze it in combination with the actual value of the total secondary consumption of anesthetic drugs to obtain the actual reserve quantity of the total secondary consumption of anesthetic drugs.

[0015] Advantages of the present invention:

[0016] 1. By classifying similar features of the surgical feature data, the present invention optimizes the use and management of anesthetic drugs, improves the utilization efficiency of medical resources, and by calculating the surgical evaluation coefficient and analyzing its change relationship with the total secondary consumption of anesthetic drugs, can more accurately predict the consumption of anesthetic drugs under different surgical types, provide a scientific decision-making basis for doctors, and reduce drug waste;

[0017] 2. By separately processing regular and irregular change signals, the present invention can more accurately reflect the actual situation of the secondary consumption of anesthetic drugs, thereby improving the prediction accuracy. Based on the accurate prediction results, it can more effectively manage the inventory of anesthetic drugs, reduce the situation of overstocking or shortage, improve the resource utilization efficiency, and by accurately calculating the reserve quantity of anesthetic drugs, it can reduce waste, lower medical costs, and can also reduce the time for re-extracting due to insufficient anesthetic drugs during the surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of a method for joint consumption management of anesthetic drugs according to the present invention;

[0020] Figure 2 is a schematic structural diagram of a system for joint consumption management of anesthetic drugs according to the present invention;

[0021] Figure 3 is a schematic structural diagram of a device for joint consumption management of anesthetic drugs according to the present invention.

[0022] In the figure: 3, computer device; 301, processor; 302, memory; 303, computer program. Detailed implementation manners

[0023] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0024] Embodiment 1

[0025] Figure 1 is a flowchart of a method for joint consumption management of anesthetic drugs provided in Embodiment 1 of the present invention. The embodiments of the present invention are applicable to the situation where there is a secondary consumption of anesthetic drugs during surgery. The method for joint consumption management of anesthetic drugs can be executed by a system for joint consumption management of anesthetic drugs, which can be implemented by software and / or hardware, and can be configured in a device for joint consumption management of anesthetic drugs. Optionally, a device for joint consumption management of anesthetic drugs can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc. The embodiments of the present invention do not limit this.

[0026] As Figure 1 shown, the method for joint consumption management of anesthetic drugs provided in the embodiments of the present invention specifically includes the following steps:

[0027] Step 1: Obtain the total consumption amount of anesthetic drugs, where the total consumption amount of anesthetic drugs includes the initial consumption amount and the secondary consumption amount, identify the surgical characteristic data with secondary consumption, and classify the similar characteristics of the surgical characteristic data;

[0028] In some embodiments, based on any surgery in the historical database, obtain the initial consumption amount and the secondary consumption amount of the anesthetic drugs used;

[0029] Extract the surgical feature data where there is secondary consumption of anesthetic drugs during the surgical process (i.e., the total secondary consumption is not zero). The surgical feature data includes the surgical type and the surgical patient information;

[0030] Specifically, the surgical types include but are not limited to: coronary artery bypass grafting, brain tumor resection, liver transplantation, orthopedic joint replacement surgery, cesarean section in obstetrics and gynecology;

[0031] The surgical patient information includes but is not limited to: patient age, patient weight, the patient's underlying disease status, and allergy history;

[0032] Perform encoding processing on the surgical feature data;

[0033] Exemplarily, the surgical type is categorical data and one-hot encoding is used. For example, for a given set of surgical types (coronary artery bypass grafting, brain tumor resection, liver transplantation, orthopedic joint replacement surgery, cesarean section in obstetrics and gynecology), it is encoded as a binary vector. For example, coronary artery bypass grafting is encoded as [1,0,0,0,0] indicating that this surgery is coronary artery bypass grafting, while other surgical types are 0; brain tumor resection is encoded as [0,1,0,0,0] indicating that this surgery is brain tumor resection, and so on;

[0034] The patient age is binned, dividing the age into different intervals, such as [0 - 18], [19 - 30], [31 - 50], [51 - 70], [70, +∞], and then each interval is encoded using one-hot encoding;

[0035] The patient weight is binned, for example, [0 - 50kg], [51 - 70kg], [71 - 90kg], [90, +∞], and then each interval is encoded using one-hot encoding;

[0036] The type of underlying disease is categorical data, and each disease can be one-hot encoded;

[0037] Use the K-Means clustering algorithm for similar feature classification. The specific process is as follows:

[0038] Take the surgically feature data after encoding processing as the input data of the K-Means algorithm;

[0039] Set the number of clusters K value. The selection of the K value is determined by those skilled in the art according to the actual business scenario and data analysis results;

[0040] Exemplarily, by trying different K values multiple times and observing the silhouette coefficient of the clustering result to judge the clustering effect. The silhouette coefficient ranges from [-1,1]. The closer the value is to 1, the better the clustering effect, that is, the samples within the class have high similarity and the samples between classes have low similarity;

[0041] Suppose that after multiple experiments, the value of K is determined to be N and the algorithm starts to run. The K-Means algorithm will randomly select N data points as the initial clustering centers;

[0042] For each surgical feature data point, calculate its distances from the N clustering centers and assign it to the cluster where the nearest clustering center is located;

[0043] Among them, the methods for calculating the distances from the N clustering centers include, but are not limited to: Euclidean distance;

[0044] After the preliminary division of all data points is completed, recalculate the mean value of the data points within each cluster to update the positions of the clustering centers, calculate the distances from each data point to the new clustering centers again, and reassign the data points to the nearest clusters;

[0045] Continuously repeat the process of updating the clustering centers and reassigning the data points until the clustering centers no longer change or reach the preset maximum number of iterations. At this time, the clustering process ends;

[0046] Among them, the maximum number of iterations is set by those skilled in the art according to experience;

[0047] Through the clustering process, the surgeries with secondary consumption of anesthetic drugs are classified into N categories according to similar characteristics;

[0048] For surgeries in different categories, the secondary consumption of anesthetic drugs may have similar patterns or influencing factors. For example, a certain category may mainly include coronary artery bypass grafting surgeries and liver transplantation surgeries performed on patients in the age range of [51 - 70] and weight range of [71 - 90 kg] with cardiovascular-related underlying diseases. Such surgeries may be due to the characteristics of the patient's physical condition and surgical type. Such classification results help to further analyze the relationship between the secondary consumption of anesthetic drugs and surgical characteristics subsequently, providing a basis for optimizing the use of anesthetic drugs;

[0049] Step 2: Based on the results of the similarity feature classification of surgical feature data, calculate the surgical evaluation coefficient and analyze the change relationship between the surgical evaluation coefficient and the total amount of secondary consumption of anesthetic drugs;

[0050] In some embodiments, based on any surgical feature classification, obtain the disease severity coefficient and the estimated surgical duration of the patient;

[0051] Calculate the ratio of the estimated surgical duration to the anesthetic duration per unit of anesthetic drug to obtain the estimated surgical duration ratio. Among them, the anesthetic duration per unit of anesthetic drug is set by those skilled in the art based on historical experimental data from multiple times;

[0052] Among them, the process of obtaining the disease severity coefficient is as follows:

[0053] The keywords of the patient's condition are divided into aggravated, newly added, relieved, and disappeared, and the corresponding weights of the severity of the keywords for the patient are 4, 3, 2, and 1 respectively; a word segmentation tool is used to segment the text data of each follow-up visit medical record of the patient to obtain the "chief complaint", "current medical history", "past medical history", and "medication prescribed" in the words, and the text after the "chief complaint" and before the "current medical history" is used as the chief complaint text content data for each follow-up visit; count the number of occurrences of each keyword in the chief complaint text content data of all the patient's follow-up visits, calculate the product of the number of occurrences of each keyword and the corresponding weight of the severity of the patient, and take the sum of the products of all the keywords as the severity coefficient of the patient's chief complaint condition;

[0054] Multiply the severity coefficient of the condition by the ratio of the estimated duration of the operation to obtain the operation evaluation coefficient;

[0055] The function of calculating the operation evaluation coefficient: By comprehensively considering the severity coefficient of the patient's condition and the ratio of the estimated duration of the operation, the operation evaluation coefficient can provide a quantitative index for doctors to measure the risk status faced by the current patient during the operation and anesthesia process. For example, in a complex coronary artery bypass grafting operation, if the severity coefficient of the patient's condition is high and the estimated duration of the operation is long, the corresponding operation evaluation coefficient will also be large, which prompts the doctor to pay closer attention to the changes in the patient's vital signs and take preparatory measures to deal with various possible risks in advance, so as to ensure the safe progress of the operation;

[0056] The second function: It is a key factor in analyzing the change relationship of the total secondary consumption of anesthetic drugs. There is a close relationship between the operation evaluation coefficient calculated based on different operation types and patient individual characteristics and the total secondary consumption of anesthetic drugs. Taking orthopedic joint replacement surgery as an example, through the analysis of a large amount of historical operation data, it is found that a certain operation evaluation coefficient within a specific range corresponds to a certain anesthetic drug secondary consumption pattern. Doctors can, based on the operation evaluation coefficient, combined with past experience data and analysis results, more accurately estimate the amount of anesthetic drugs required for this operation, avoid problems caused by excessive or insufficient drug reserves, reduce drug waste, and improve the utilization efficiency of medical resources;

[0057] The third function: The operation evaluation coefficient can also be used to evaluate the impact of the first anesthetic consumption on the patient's anesthetic effect. In actual operations, an appropriate dose of anesthetic drugs is the key to ensuring that the patient is painless and in a stable physiological state during the operation. By analyzing the operation evaluation coefficient, doctors can judge whether the current anesthetic plan can meet the operation requirements. For example, in some long-term operations, if the operation evaluation coefficient indicates that the patient may develop tolerance to anesthetic drugs or requires a higher dose of anesthetic drugs to maintain a stable anesthetic effect, doctors can take corresponding measures in a timely manner to ensure the smooth progress of the operation and the safety and comfort of the patient;

[0058] Obtain multiple groups of evaluation coefficients and their corresponding total secondary consumption amounts of anesthetic drugs. Using the surgical evaluation coefficient as the abscissa and the total secondary consumption amount as the ordinate, plot the curve of the change in the total secondary consumption amount;

[0059] Connect the two endpoints of the curve of the change in the total secondary consumption amount with a straight line to obtain the reference line for the change in the total secondary consumption amount;

[0060] Identify whether there is a turning point in the curve of the change in the total secondary consumption amount;

[0061] If there is a turning point, obtain the X-axis coordinate value of the curve of the change in the total secondary consumption amount corresponding to the turning point, and divide it into multiple sections according to the surgical evaluation coefficient corresponding to the turning point to obtain the surgical evaluation coefficient sections;

[0062] Obtain the starting endpoint of the reference line for the change in the total secondary consumption amount within the surgical evaluation coefficient section, and draw a tangent line from the turning point of the curve of the change in the total secondary consumption amount to the starting endpoint of the reference line for the change in the total secondary consumption amount;

[0063] Calculate the included angle between the tangent line and the reference line for the change in the total secondary consumption amount to obtain the included angle to be analyzed, and obtain the set sequence XJ of included angles to be analyzed = {α 1 , α 2 ,... α i}, where i = 1, 2,..., n, and n represents the number of included angles to be analyzed;

[0064] Exemplarily, mark the coordinates of the turning point of the curve of the change in the total secondary consumption amount as (x1, y1), and mark the coordinates of the starting endpoint of the reference line for the change in the total secondary consumption amount as (x0, y0). Through the formula: Calculate the included angle α1 to be analyzed;

[0065] Compare the included angle to be analyzed with the threshold of the included angle to be analyzed, where the threshold of the included angle to be analyzed is set by professionals in the field according to experience;

[0066] If the included angle to be analyzed is less than the threshold of the included angle to be analyzed, mark it as a small included angle;

[0067] If the included angle to be analyzed is greater than or equal to the threshold of the included angle to be analyzed, mark it as a large included angle;

[0068] Obtain all the set sequences DJ of small included angles = {dj 1 , dj 2 ,... dj j}, where j = 1, 2,..., m, and m represents the number of small included angles;

[0069] Through the formula: Calculate the rule judgment value GL, where a and b are preset proportionality coefficients, a = 0.75, and b = 0.25;

[0070] It should be noted that when the ratio of m to n is processed, the calculated value is the proportion of the small angle in the angle to be analyzed. The larger the proportion, the closer the linear trend between the quadratic consumption total change curve and the quadratic consumption total change reference line; What is calculated is the standard deviation. The smaller the standard deviation, the smaller the dispersion degree of the small angle set, the closer the small angles are to each other, and the closer the linear trend between the quadratic consumption total change curve and the quadratic consumption total change reference line;

[0071] Compare the rule judgment value with the rule judgment threshold, where the rule judgment threshold is set by professionals in the field according to experience;

[0072] If the rule judgment value is less than or equal to the rule judgment threshold, the quadratic consumption total change curve is a non-linear rule change, and a non-rule change signal is generated;

[0073] If the rule judgment value is greater than the rule judgment threshold, the quadratic consumption total change curve is a linear rule change, and a rule change signal is generated;

[0074] If there is no turning point, a non-rule change signal is generated;

[0075] It should be noted that the second derivative of a linear function is zero, and a turning point is a point where the sign of the second derivative changes. When there is no turning point in the change curve, it is very likely that it does not change at a constant rate of change because a curve without a turning point may have various complex shapes, such as exponential growth or decline, logarithmic change, etc., which are non-linear forms;

[0076] The technical solution of this embodiment is: obtain the total consumption of anesthetic drugs, identify the surgical characteristic data for similar characteristic classification, then calculate the surgical evaluation coefficient based on the classification result, analyze its relationship with the change of the secondary consumption total of anesthetic drugs, and generate corresponding signals by judging the linear rule of the change curve;

[0077] Thus, by classifying similar characteristics of surgical characteristic data, the use and management of anesthetic drugs are optimized, the utilization efficiency of medical resources is improved, and by calculating the surgical evaluation coefficient and analyzing its relationship with the change of the secondary consumption total of anesthetic drugs, the consumption of anesthetic drugs under different surgical types can be predicted more accurately, providing a scientific decision-making basis for doctors and reducing drug waste;

[0078] Embodiment 2

[0079] Based on the above embodiment, as Figure 1As shown in the figure, an anesthetic drug consumption management method provided by an embodiment of the present invention specifically includes the following steps:

[0080] Step 3: Based on the analysis result of the change relationship between the surgical evaluation coefficient and the total secondary consumption of anesthetic drugs, construct a calculation model for the prepared amount of anesthetic drugs;

[0081] In some embodiments, based on the regular change signal, use the least squares method to fit the change curve of time - actual incoming warehouse quantity to obtain the secondary consumption fitting line, and the secondary consumption fitting line is the calculation model for the prepared amount of anesthetic drugs;

[0082] Based on the irregular change signal, use machine learning and deep learning models to construct a calculation model for the prepared amount of anesthetic drugs;

[0083] Among them, the machine learning and deep learning models include but are not limited to the random forest regression model and the multi-layer perceptron neural network model;

[0084] Step 4: Based on the constructed calculation model for the prepared amount of anesthetic drugs, output the predicted value of the total secondary consumption of anesthetic drugs, combine the predicted value of the total secondary consumption of anesthetic drugs with the actual value of the total secondary consumption of anesthetic drugs for analysis, and adjust the predicted value of the total secondary consumption of anesthetic drugs to obtain the actual prepared amount of the total secondary consumption of anesthetic drugs;

[0085] In some embodiments, based on the calculation model for the prepared amount of anesthetic drugs, obtain the surgical characteristic data of the patient and identify the surgical characteristic classification to which the patient belongs;

[0086] Based on the surgical characteristic classification to which the patient belongs, output the predicted value of the total secondary consumption of anesthetic drugs and obtain the actual value of the total secondary consumption of anesthetic drugs;

[0087] Calculate the difference between the predicted value of the total secondary consumption of anesthetic drugs and the actual value of the total secondary consumption of anesthetic drugs to obtain the prediction deviation value;

[0088] One function of calculating the prediction deviation value is that the prediction deviation value intuitively reflects the deviation degree between the prediction result and the actual usage situation by calculating the difference between the predicted value of the total secondary consumption of anesthetic drugs and the actual value;

[0089] The second function is that it enables more accurate use of the anesthetic dosage for the next time through data analysis based on the obtained prediction deviation value, reduces the time for temporary extraction, and increases the efficiency of anesthetizing the surgery;

[0090] The third function is that based on the obtained deviation, a more accurate estimate of the future usage amount can be made, which can effectively reduce the number of anesthetic consumption times;

[0091] Based on the analysis of several surgeries, obtain the prediction deviation value data sequence PC = {pc1 , pc 2 ,... pc q}, q = 1, 2, ……, p, where p represents the number of surgeries analyzed;

[0092] Calculate the standard deviation of the predicted deviation value data and set a standard deviation threshold.

[0093] If the standard deviation of the predicted deviation value is less than or equal to the standard deviation threshold, it indicates that the predicted deviation value data is relatively stable. Sum and average the predicted deviation value data to obtain the predicted deviation mean.

[0094] Calculate the difference between the predicted value of the total secondary consumption of anesthetic drugs and the predicted deviation mean to obtain the actual reserve quantity of the total secondary consumption of anesthetic drugs.

[0095] If the standard deviation of the predicted deviation value is greater than the standard deviation threshold, it indicates that the predicted deviation value data is unstable. Use the weighted moving average method to calculate the actual reserve quantity of the total secondary consumption of anesthetic drugs.

[0096] The calculation formula is: where SJ represents the actual reserve quantity of the total secondary consumption of anesthetic drugs, YC represents the predicted value of the total secondary consumption of anesthetic drugs, w q represents the weight of the qth predicted deviation value, PC q represents the qth predicted deviation value;

[0097] It should be noted that the weights can be set in an exponentially weighted manner. The specific calculation formula is: w d = (1 - β) p-q * β, where β is the attenuation factor, which is set by those skilled in the art based on historical experience;

[0098] Ensuring an adequate supply of anesthetic drugs is crucial for the safety of surgeries. Step four helps enhance the safety during surgeries and improve the quality of medical services by providing a more accurate prediction of the reserve quantity of anesthetic drugs.

[0099] The technical solution of this embodiment is as follows: By analyzing the variation relationship between the surgical evaluation coefficient and the total secondary consumption of anesthetic drugs, a calculation model for the reserve quantity of anesthetic drugs is constructed. For regularly varying signals, the least squares method is used to fit a quadratic consumption fitting line as the calculation model. For irregularly varying signals, machine learning and deep learning models (such as random forest regression and multi-layer perceptron neural network) are used to construct the model. Based on the constructed model, the predicted value of the total secondary consumption of anesthetic drugs is output, and it is analyzed and adjusted in combination with the actual value to obtain the actual reserve quantity of anesthetic drugs. During the adjustment process, according to the stability of the predicted deviation value data, either directly summing and averaging or using the weighted moving average method is selected to calculate the final actual reserve quantity of anesthetic drugs.

[0100] By separately processing regular and irregular change signals, the actual situation of the secondary consumption amount of anesthetic drugs can be more accurately reflected, thereby improving the accuracy of prediction. Based on the accurate prediction results, the inventory of anesthetic drugs can be more effectively managed, the situations of overstocking or shortage can be reduced, and the resource utilization efficiency can be improved. By precisely calculating the preparation amount of anesthetic drugs, waste can be reduced, medical costs can be lowered, and the time for re-extracting due to insufficient anesthetic drugs during the operation can be reduced.

[0101] Embodiment III

[0102] Based on the above embodiments, as Figure 2 shown, an anesthetic drug combined consumption management system provided by an embodiment of the present invention specifically includes:

[0103] Similar feature classification module: Obtain the total consumption amount of anesthetic drugs, where the total consumption amount of anesthetic drugs includes the primary total consumption amount and the secondary total consumption amount, identify the surgical feature data with secondary consumption, and classify the surgical feature data according to similar features;

[0104] Change relationship judgment module: Based on the result of classifying similar features according to the surgical feature data, calculate the surgical evaluation coefficient, and analyze the change relationship between the surgical evaluation coefficient and the secondary total consumption amount of anesthetic drugs;

[0105] Model construction module: Based on the analysis result of the change relationship between the surgical evaluation coefficient and the secondary total consumption amount of anesthetic drugs, construct a calculation model for the preparation amount of anesthetic drugs;

[0106] Actual preparation amount calculation module: Based on the constructed calculation model for the preparation amount of anesthetic drugs, output the predicted value of the secondary total consumption amount of anesthetic drugs, analyze by combining the predicted value of the secondary total consumption amount of anesthetic drugs with the actual value of the secondary total consumption amount of anesthetic drugs, and adjust the predicted value of the secondary total consumption amount of anesthetic drugs to obtain the actual preparation amount of the secondary total consumption amount of anesthetic drugs.

[0107] Embodiment IV

[0108] As Figure 3 shown, an embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements an anesthetic drug combined consumption management method as described in any one of the above methods.

[0109] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand,

[0110] Figure 3 This is only an example of the computer device 3 and does not constitute a limitation on the computer device 3. It may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0111] The so-called processor 301 may be a central processing unit (CPU). This processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0112] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or will be output.

[0113] Embodiment Five

[0114] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements an anesthetic drug combined consumption management method as described in any one of the above methods.

[0115] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above embodiment methods of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0116] In the above embodiments, the descriptions of the various embodiments have their own focuses. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0118] In the embodiments disclosed in this application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0119] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0121] The above has described in detail one embodiment of the present invention, but the content described is only the preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for managing the joint consumption of anesthetics, characterized in that: The following steps are involved: Step 1: Obtain the total amount of primary consumption and secondary consumption of the surgery, identify the surgical feature data with secondary consumption, and classify the surgical feature data by similar features; Step 2: Based on the results of similar feature classification of surgical feature data, the surgical evaluation coefficient is calculated, and the relationship between the surgical evaluation coefficient and the total amount of secondary consumption of anesthetic drugs is analyzed to generate irregular change signals or regular change signals; Step 3: Based on the analysis results of the relationship between the surgical evaluation coefficient and the total amount of secondary consumption of anesthetic drugs, a calculation model for the amount of anesthetic drug reserve is constructed; Step 4: Based on the anesthetic drug reserve calculation model, the predicted value of the total secondary consumption of anesthetic drugs is output, and combined with the actual value of the total secondary consumption of anesthetic drugs for analysis, the actual reserve amount of the total secondary consumption of anesthetic drugs is obtained.

2. A method for managing the joint consumption of anesthetics according to claim 1, characterized in that: The process of classifying the surgical feature data into similar features is as follows: Based on any surgery in the historical database, obtain the total initial consumption and the total secondary consumption of the anesthetic drugs used; Extract surgical feature data of secondary consumption of anesthetic drugs during surgery; The surgical feature data are encoded and then classified according to similar features using the K-Means clustering algorithm.

3. A method for managing joint consumption of anesthetics according to claim 1, characterized in that: The process of obtaining the relationship between the surgical evaluation coefficient and the total amount of secondary consumption of anesthetic drugs is as follows: The severity coefficient of the disease and the estimated duration of surgery were analyzed and the evaluation coefficient was calculated; Obtain multiple groups of evaluation coefficients and their corresponding total secondary consumption of anesthetic drugs, and draw a curve of total secondary consumption change with the surgical evaluation coefficient as the horizontal axis and the total secondary consumption as the vertical axis; Connect the two end points of the secondary consumption total amount change curve with a straight line to obtain a secondary consumption total amount change reference line; Identify whether there is a turning point in the change curve of the total secondary consumption. If there is no turning point, generate an irregular change signal; If there is a turning point, analyze the turning point of the secondary consumption total amount change curve to obtain the angle to be analyzed, and analyze the angle to be analyzed to obtain the regularity judgment value; The regularity judgment value is compared with the regularity judgment threshold. If the regularity judgment value is less than or equal to the regularity judgment threshold, an irregular change signal is generated. If the regularity judgment value is greater than the regularity judgment threshold, a regular change signal is generated.

4. A method for managing the joint consumption of anesthetics according to claim 3, characterized in that: The process of obtaining the rule judgment value is as follows: Obtain a set of angles to be analyzed, compare the angle to be analyzed with a threshold value of the angle to be analyzed, and if the angle to be analyzed is smaller than the threshold value of the angle to be analyzed, mark it as a small angle, and obtain a set of small angles; By formula: Calculate the regularity judgment value GL, where a and b are preset proportional coefficients, n represents the number of angles to be analyzed, m represents the number of small angles, and dj j represents the jth small angle.

5. A method for managing the joint consumption of anesthetics according to claim 4, characterized in that: The process of obtaining the angle to be analyzed is as follows: Obtaining the surgical evaluation coefficient of the change curve of the total secondary consumption corresponding to the turning point, dividing the curve into multiple sections according to the surgical evaluation coefficient corresponding to the turning point to obtain the surgical evaluation coefficient section, obtaining the starting endpoint of the reference line of the change of the total secondary consumption within the surgical evaluation coefficient section, and drawing a tangent line between the turning point of the change curve of the total secondary consumption and the starting endpoint of the reference line of the change of the total secondary consumption; Calculate the angle between the tangent line and the reference of the change in the total amount of secondary consumption to obtain the angle to be analyzed.

6. The method for managing the joint consumption of anesthetics according to claim 1, characterized in that: The process of obtaining the evaluation coefficient is as follows: Based on any surgical feature classification, the patient's disease severity coefficient and the estimated operation duration are obtained, the estimated operation duration is ratioed to the unit anesthetic anesthesia duration to obtain the estimated operation duration ratio, and the disease severity coefficient is multiplied by the estimated operation duration ratio to obtain the operation evaluation coefficient.

7. The method for managing the joint consumption of anesthetics according to claim 1, characterized in that: The process of constructing the anesthetic drug reserve amount calculation model is as follows: Based on the regular change signal, the least square method is used to fit the time-actual warehouse volume change curve to obtain the secondary consumption fitting line, which is the calculation model of the anesthetic drug reserve volume. Based on irregular changing signals, a model for calculating the amount of anesthetic drug preparation was constructed using machine learning and deep learning models.

8. The method for managing the joint consumption of anesthetics according to claim 1, characterized in that: The process of obtaining the actual reserve amount of the total amount of secondary consumption of anesthetics is as follows: The predicted value of the total amount of secondary consumption of anesthetic drugs is analyzed in combination with the actual value of the total amount of secondary consumption of anesthetic drugs to obtain the standard deviation of the predicted deviation value and set the standard deviation threshold; If the standard deviation of the predicted deviation value is less than or equal to the standard deviation threshold, the predicted deviation value data is summed and averaged to obtain the predicted deviation mean; The difference between the predicted value of the total amount of secondary consumption of anesthetic drugs and the average value of the predicted deviation is calculated to obtain the actual reserve amount of the total amount of secondary consumption of anesthetic drugs; If the standard deviation of the predicted deviation value is greater than the standard deviation threshold, the weighted moving average method is used to calculate the actual reserve amount of the total secondary consumption of anesthetics; The calculation formula is: Among them, SJ represents the actual reserve amount of the total amount of secondary consumption of anesthetic drugs, YC represents the predicted value of the total amount of secondary consumption of anesthetic drugs, and w q It represents the weight of the qth prediction deviation value, PC q It represents the qth prediction deviation value.

9. A method for managing the joint consumption of anesthetics according to claim 8, characterized in that: The process of obtaining the standard deviation of the predicted deviation value is as follows: Based on the anesthetic drug preparation calculation model, the patient's surgical characteristic data is obtained to identify the patient's surgical characteristic classification; Based on the patient's surgical feature classification, output the predicted value of the total secondary consumption of anesthetics, and obtain the actual value of the total secondary consumption of anesthetics; The difference between the predicted value of the total amount of secondary consumption of anesthetic drugs and the actual value of the total amount of secondary consumption of anesthetic drugs is calculated to obtain a predicted deviation value; Based on the analysis of several surgeries, the predicted deviation value data series is obtained, and the standard deviation of the predicted deviation value data is calculated.

10. An anesthetic drug consumption management system, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Similar feature classification module: obtains the total amount of primary consumption and secondary consumption of the surgery, identifies the surgical feature data with secondary consumption, and classifies the surgical feature data by similar features; Change relationship judgment module: Based on the results of similar feature classification of surgical feature data, the surgical evaluation coefficient is calculated, and the change relationship between the surgical evaluation coefficient and the total amount of secondary consumption of anesthetic drugs is analyzed to generate irregular change signals or regular change signals; Model building module: Based on the analysis results of the changing relationship between the surgical evaluation coefficient and the total amount of secondary consumption of anesthetic drugs, a calculation model for the amount of anesthetic drug preparation is constructed; Actual reserve quantity calculation module: Based on the anesthetic reserve quantity calculation model, it outputs the predicted value of the total secondary consumption of anesthetics, and analyzes it in combination with the actual value of the total secondary consumption of anesthetics to obtain the actual reserve quantity of the total secondary consumption of anesthetics.

Images