Method, device, equipment and medium for constructing treatment formula library

Abstract

The present application relates to the field of information processing technology, and provides a method, device, equipment and medium for constructing a treatment formula library, the method comprising: obtaining a medical consultation data set, the medical consultation data set comprising medical consultation data of multiple patients, each of the medical consultation data comprising the diagnosis result and treatment items of the patient's medical consultation; determining the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item; constructing an integer programming model based on the diagnosis result category and the treatment item category corresponding to each patient; solving the integer programming model to obtain the corresponding relationship between the diagnosis result category and the treatment item category; constructing a treatment formula library based on the corresponding relationship between the diagnosis result category and the treatment item category. The embodiment of the present application can automatically extract the diagnosis result category and its corresponding treatment item category and form a treatment formula library.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a method, device, electronic device and computer-readable storage medium for constructing a treatment formula library. Background Art

[0002] Disease treatment formula refers to a series of corresponding treatment measures taken for each type of disease, which forms a method for treating that type of disease. By recording each type of disease and its corresponding treatment measures, a treatment formula library that is as complete as possible is formed, which helps provide guidance for future diagnosis and treatment.

[0003] In the related treatment formula library construction methods, the treatment measures corresponding to each type of disease mainly rely on manual collection, sorting and summarization. However, the manual extraction method relies on strong professional knowledge, and there are many types of diagnostic results and treatment items. The manual extraction method is very inefficient, and there are problems such as incomplete extraction results and high maintenance costs. Therefore, how to provide a treatment formula library construction method that can automatically extract each type of disease and its corresponding treatment measures, that is, extract the diagnosis result category and its corresponding treatment item category to form a treatment formula library, has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method, device, electronic device and computer-readable storage medium for constructing a treatment formula library, which can automatically extract the diagnosis result category and its corresponding treatment item category and construct a treatment formula library.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application proposes a method for constructing a treatment formula library, the method comprising:

[0006] Acquire a medical consultation data set, wherein the medical consultation data set includes medical consultation data of a plurality of patients, and each medical consultation data includes a diagnosis result and treatment items of the patient's medical consultation;

[0007] Determine the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item;

[0008] Based on the diagnosis result category and the treatment item category corresponding to each patient, construct an integer programming model;

[0009] Solving the integer programming model to obtain a corresponding relationship between the diagnosis result category and the treatment item category;

[0010] Based on the correspondence between the diagnosis result categories and the treatment item categories, a treatment formula library is constructed.

[0011] According to the method for constructing a treatment formula library provided by some embodiments of the present invention, the integer programming model is determined by the following formula:

[0012] min L(x1,…,x N )=α1·L e +α2·L r +α3·L2,stx i ∈{1,2,…,M},i=1,2,…,N;

[0013] Wherein, min(·) represents the minimum value, M is the number of the diagnosis result categories, N is the number of the treatment item categories, and x i represents the diagnosis result category to which the i-th treatment item category belongs, and the L e is the first loss function, the L r is the second loss function, L2 is the third loss function, α1 is the first weight coefficient, α2 is the second weight coefficient, and α3 is the third weight coefficient.

[0014] According to the method for constructing a treatment formula library provided by some embodiments of the present invention, the first loss function L e Determined by the following formula:

[0015]

[0016] Wherein, m is the number of patients in the medical consultation data set, and c ij ∈{0,1}, when patient i receives treatment under treatment category j, the c ij is 0, otherwise it is 1; ik ∈{0,1}, when patient i is diagnosed with a disease under diagnosis category k, the d ik is 0, otherwise it is 1; the f(x)∈{0,1}, the specific formula of f(x) is as follows:

[0017] According to the method for constructing a treatment formula library provided by some embodiments of the present invention, the second loss function L r Determined by the following formula:

[0018]

[0019] According to the method for constructing a treatment formula library provided by some embodiments of the present invention, the third loss function L2 is determined by the following formula:

[0020]

[0021] According to the method for constructing a treatment formula library provided by some embodiments of the present invention, obtaining the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item includes:

[0022] Determine the diagnosis result category corresponding to each patient according to the diagnosis result and the preset diagnosis result category;

[0023] According to the treatment items and the preset treatment item classification, the treatment item category corresponding to each patient is determined.

[0024] According to the method for constructing a treatment formula library provided by some embodiments of the present invention, constructing the treatment formula library based on the correspondence between the diagnosis result category and the treatment item category includes:

[0025] Based on the correspondence between the diagnosis result categories and the treatment item categories, determining a treatment formula corresponding to each diagnosis result category, wherein the treatment formula has a correspondence with at least one treatment item category;

[0026] According to the treatment formula, a treatment formula library is constructed.

[0027] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a device for constructing a treatment formula library, the device comprising:

[0028] An acquisition module is used to acquire a medical consultation data set, wherein the medical consultation data set includes medical consultation data of multiple patients, and each medical consultation data includes a diagnosis result and treatment items of the patient's medical consultation;

[0029] A processing module, used to determine the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item;

[0030] A first construction module is used to construct an integer programming model based on the diagnosis result category and the treatment item category corresponding to each patient;

[0031] A solution module, used for solving the integer programming model to obtain the corresponding relationship between the diagnosis result category and the treatment item category;

[0032] The second construction module is used to construct a treatment formula library based on the corresponding relationship between each of the diagnosis result categories and the treatment item categories.

[0033] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program implements the method described in the first aspect when executed by the processor.

[0034] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors to implement the method described in the first aspect above.

[0035] The present application proposes a method, device, equipment and medium for constructing a treatment formula library. The method for constructing a treatment formula library obtains a medical data set including medical data of multiple patients, wherein each medical data includes the diagnosis result and treatment items of the patient's medical treatment, and determines the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and treatment item, thereby constructing and solving an integer programming model based on the diagnosis result category and treatment item category corresponding to each patient, obtaining the correspondence between the diagnosis result category and the treatment item category, and constructing a treatment formula library based on the correspondence between the diagnosis result category and the treatment item category. The embodiment of the present application obtains a medical data set and extracts the diagnosis result category and treatment item category corresponding to each patient, and obtains the correspondence between the diagnosis result category and the treatment item category by constructing and solving an integer programming model about the diagnosis result category and the treatment item category, and constructs a treatment formula library based on the correspondence. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flowchart of a method for constructing a treatment formula library provided in an embodiment of the present application;

[0037] Figure 2 It is a flowchart of a method for constructing a treatment formula library provided in an embodiment of the present application;

[0038] Figure 3 It is a flowchart of a method for constructing a treatment formula library provided in an embodiment of the present application;

[0039] Figure 4 It is a structural schematic diagram of a device for constructing a treatment formula library provided in an embodiment of the present application;

[0040] Figure 5 It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0043] First, the nouns involved in this application are analyzed:

[0044] Integer programming refers to a type of mathematical programming that requires all or part of the variables in the problem to be integers. Integer programming problems are linear or nonlinear programming problems that require decision variables to take integer values. According to the restrictions on decision variables, integer programming can be divided into:

[0045] Pure integer programming: Integer programming where all decision variables are required to be integers;

[0046] Mixed integer programming: Integer programming where some decision vectors are required to be integers;

[0047] Pure 0-1 integer programming: All decision variables are required to be integer programming of 0 or 1;

[0048] Mixed 0-1 integer programming: Integer programming in which some decision variables are required to be 0 or 1.

[0049] Disease treatment formula refers to a series of corresponding treatment measures taken for each type of disease, which forms a method for treating that type of disease. By recording each type of disease and its corresponding treatment measures, a treatment formula library that is as complete as possible is formed, which helps provide guidance for future diagnosis and treatment.

[0050] In the related treatment formula library construction methods, the treatment measures corresponding to each type of disease mainly rely on manual collection, sorting and summarization. However, the manual extraction method relies on strong professional knowledge, and there are many types of diagnostic results and treatment items. The manual extraction method is very inefficient, and there are problems such as incomplete extraction results and high maintenance costs. Therefore, how to provide a treatment formula library construction method that can automatically extract each type of disease and its corresponding treatment measures, that is, extract the diagnosis result category and its corresponding treatment item category to form a treatment formula library, has become a technical problem that needs to be solved urgently.

[0051] Based on this, the embodiments of the present application provide a method, device, electronic device and storage medium for constructing a treatment formula library, which can automatically extract the diagnosis result category and its corresponding treatment item category and construct a treatment formula library.

[0052] The embodiments of the present application provide a method, device, electronic device and storage medium for constructing a treatment formula library, which are specifically illustrated through the following embodiments. First, the method for constructing a treatment formula library in the embodiments of the present application is described.

[0053] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0054] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0055] The method for constructing a therapeutic formula library provided in the embodiment of the present application relates to the field of artificial intelligence and digital medical technology. The method for constructing a therapeutic formula library provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the method for constructing a therapeutic formula library, etc., but is not limited to the above forms.

[0056] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0057] See also Figure 1 , Figure 1 FIG. 1 is a flow chart showing a method for constructing a therapeutic formula library provided in an embodiment of the present application. Figure 1 As shown, the method for constructing the treatment formula library includes but is not limited to steps S110 to S150.

[0058] Step S110, obtaining a medical consultation data set, wherein the medical consultation data set includes medical consultation data of multiple patients, and each medical consultation data includes a diagnosis result and treatment items of the patient's medical consultation.

[0059] It is understandable that the original medical data of the patient includes the main diagnosis name, secondary diagnosis name and consumption details of each case. The diagnosis name can be used to obtain the patient's medical results, and the consumption details include all treatment items undergone by the patient.

[0060] Step S120, determining the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item.

[0061] See also Figure 2 , Figure 2 FIG. 1 is a flow chart showing a method for constructing a therapeutic formula library provided in an embodiment of the present application. Figure 2 As shown, in some embodiments, obtaining the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item includes:

[0062] Step S210, determining the diagnosis result category corresponding to each patient according to the diagnosis result and the preset diagnosis result category;

[0063] Step S220, determining the treatment item category corresponding to each patient according to the treatment items and the preset treatment item classification.

[0064] It can be understood that the diagnosis result and the corresponding treatment item of each patient are obtained from the medical data set, and according to the preset diagnosis result classification and treatment item classification, the diagnosis result category and the corresponding treatment item category of each patient can be determined.

[0065] It should be understood that the preset diagnosis result classification and treatment item classification may be the classification results of experts in the medical field.

[0066] Step S130, constructing an integer programming model based on the diagnosis result category and the treatment item category corresponding to each patient.

[0067] In some embodiments, the integer programming model is determined by the following formula:

[0068] min L(x1,…,x N)=α1·L e +α2·L r +α3·L2,stx i ∈{1,2,…,M},i=1,2,…,N;

[0069] Wherein, min(·) represents the minimum value, M is the number of the diagnosis result categories, N is the number of the treatment item categories, and x i represents the diagnosis result category to which the i-th treatment item category belongs, and the L e is the first loss function, the L r is the second loss function, L2 is the third loss function, α1 is the first weight coefficient, α2 is the second weight coefficient, and α3 is the third weight coefficient.

[0070] It should be noted that the integer programming model includes the objective function, decision variables and constraints.

[0071] In this embodiment, the objective function is α1·L e +α2·L r +α3·L2, where L e is the first loss function, L r is the second loss function, L2 is the third loss function, α1, α2 and α3 are the first, second and third weight coefficients respectively; the decision variable is x i , including the constraints: x i ∈{1,2,…,M}, i=1,2,…,N, M is the number of diagnosis result categories, N is the number of treatment item categories, and the decision variable x i Represents the diagnosis result category corresponding to the i-th treatment item category.

[0072] It should be noted that the first loss function L e , the second loss function L r And the third loss function L2 is about the decision variable x i Function, where the first loss function L e represents the loss caused by matching the treatment item category to the wrong diagnosis result category, and the second loss function L r represents the loss caused by matching the diagnosis result category to the wrong treatment item category. The third loss function L2 represents the desired decision variable x i Don't cluster under a few diagnostic categories.

[0073] Based on the diagnosis result category and treatment item category corresponding to each patient, an integer programming model is constructed, which incorporates the two-way correspondence between the diagnosis result category and the treatment item category. Considering the actual situation that the treatment item categories are not all concentrated in a single diagnosis result category, the three aspects of loss are put into the objective function, and a weight coefficient is set for each loss, which can be adjusted according to the actual effect, so as to obtain a more accurate correspondence between the diagnosis result category and the treatment item category.

[0074] It can be understood that by adjusting the first, second and third weight coefficients, the objective function of the integer programming model includes the first loss function, the second loss function or the third loss function alone, or the objective function of the integer programming model is any two combinations of the first loss function, the second loss function and the third loss function, or the objective function of the integer programming model is a combination of the first loss function, the second loss function and the third loss function.

[0075] Exemplarily, when α2 and α3 are 0, the integer programming model is determined by the following formula:

[0076] min L(x1,…,x N )=α1·L e ,stx i ∈{1,2,…,M},i=1,2,…,N; where the objective function is α1·L e , L e is the first loss function, and α1 is the first weight coefficient.

[0077] Exemplarily, when α1 and α3 are 0, the integer programming model is determined by the following formula:

[0078] min L(x1,…,x N )=α2·L r ,stx i ∈{1,2,…,M},i=1,2,…,N; where the objective function is α2·L r , L r is the second loss function, and α2 is the second weight coefficient.

[0079] Exemplarily, when α1 and α2 are 0, the integer programming model is determined by the following formula:

[0080] min L(x1,…,x N )=α3·L2,stx i ∈{1,2,…,M},i=1,2,…,N; wherein the objective function is α3·L2, L2 is the third loss function, and α3 is the third weight coefficient.

[0081] Exemplarily, when α3 is 0, the integer programming model is determined by the following formula:

[0082] min L(x1,…,x N )=α1·L e +α2·L r ,stx i ∈{1,2,…,M},i=1,2,…,N; where the objective function is α1·L e +α2·L r , L e is the first loss function, α1 is the first weight coefficient, L r is the second loss function, and α2 is the second weight coefficient.

[0083] Exemplarily, when α2 is 0, the integer programming model is determined by the following formula:

[0084] min L(x1,…,x N )=α1·L e +α3·L2,stx i ∈{1,2,…,M},i=1,2,…,N; where the objective function is α1·L e +α3·L2,L e is the first loss function, α1 is the first weight coefficient, L2 is the third loss function, and α3 is the third weight coefficient.

[0085] Exemplarily, when α1 is 0, the integer programming model is determined by the following formula:

[0086] min L(x1,…,x N )=α2·L r +α3·L2,stx i ∈{1,2,…,M},i=1,2,…,N; where the objective function is α2·L r +α3·L2,L r is the second loss function, α2 is the second weight coefficient, L2 is the third loss function, and α3 is the third weight coefficient.

[0087] In some embodiments, the first loss function L e Determined by the following formula:

[0088]

[0089] Wherein, m is the number of patients in the medical data set, M is the number of diagnosis result categories, N is the number of treatment item categories, and x is i represents the diagnosis result category to which the i-th treatment item category belongs, and the c ij∈{0,1}, when patient i receives treatment under treatment category j, the c ij is 0, otherwise it is 1; ik ∈{0,1}, when patient i is diagnosed with a disease under diagnosis category k, the d ik is 0, otherwise it is 1; the f(x)∈{0,1}, the specific formula of f(x) is as follows:

[0090] It is understandable that there are m patients, M diagnosis result categories, and N treatment item categories in the medical data set. For the first loss function L e , when the treatment item category j of the i-th patient matches the diagnosis result category k of patient i, the loss of treatment item category j of patient i is 0, otherwise it is 1. Sum the losses of all treatment item categories j of patient i, and then sum them for all patients to get the first loss function L e The corresponding first loss value.

[0091] In some embodiments, the second loss function L r Determined by the following formula:

[0092]

[0093] Wherein, m is the number of patients in the medical data set, M is the number of diagnosis result categories, N is the number of treatment item categories, and x is i represents the diagnosis result category to which the i-th treatment item category belongs, and the c ij ∈{0,1}, when patient i receives treatment under treatment category j, the c ij is 0, otherwise it is 1; ik ∈{0,1}, when patient i is diagnosed with a disease under diagnosis category k, the d ik is 0, otherwise it is 1; the f(x)∈{0,1}, the specific formula of f(x) is as follows:

[0094] It is understandable that there are m patients, M diagnosis result categories, and N treatment item categories in the medical data set. For the second loss function L r , when the diagnosis result category k of the i-th patient matches the treatment item category j that the patient i has undergone, the loss of the diagnosis result category k of the patient i is 0, otherwise it is 1. Sum the losses of all the diagnosis result categories k of the patient i, and then sum them for all patients to get the second loss function L r The corresponding second loss value.

[0095] In some embodiments, the third loss function L2 is determined by the following formula:

[0096]

[0097] Wherein, N is the number of treatment item categories, and x i represents the diagnosis result category to which the i-th treatment item category belongs, and f(x)∈{0,1}. The specific formula of f(x) is as follows:

[0098] It is understandable that there are m patients, M diagnosis result categories, and N treatment item categories in the medical data set. For the third loss function L2, when the two decision variables x i The values ​​of these two decision variables x are different. i The loss between any two decision variables x is 0, otherwise it is 1. i The losses between them are summed to obtain the third loss value corresponding to the third loss function L2.

[0099] Step S140, solving the integer programming model to obtain the corresponding relationship between the diagnosis result category and the treatment item category.

[0100] It can be understood that the optimal solution is obtained by solving the above integer programming model. According to the meaning of the defined decision variables, that is, the decision variables represent the diagnosis result categories corresponding to the treatment item categories, the optimal solution represents the optimal correspondence between each diagnosis result category and the treatment item category.

[0101] Exemplarily, solving the integer programming model obtains one of the optimal solutions: It means that the i-th treatment item category belongs to the diagnosis result category j in the optimal case.

[0102] It should be understood that the solution method of the integer programming model is known to those skilled in the art and is not the focus of the embodiments of the present application, so it will not be described in detail here.

[0103] Step S150, constructing a treatment formula library based on the correspondence between the diagnosis result categories and the treatment item categories.

[0104] According to the optimal solution obtained by solving the integer programming model, that is, the optimal correspondence between the diagnosis result category and the treatment item category, a treatment formula library is constructed.

[0105] For example, there are 7 diagnosis result categories {M1, M2, M3, M4, M5, M6, M7} and 10 treatment item categories {N1, N2, N3, N4, N5, N6, N7, N8, N9, N10} in the medical consultation dataset. 10}, the correspondence between the diagnosis result category and the treatment item category can be expressed as the optimal solution: It indicates that treatment item categories N1, N3 and N9 belong to diagnosis result category M2 in the best case, and then a treatment formula library is constructed. The treatment formula library includes the correspondence between diagnosis result category M2 and treatment item categories N1, N3 and N9. For example, the treatment formula library stores the correspondence between treatment item category N1 and diagnosis result category M2, the correspondence between treatment item category N3 and diagnosis result category M2, and the correspondence between treatment item category N9 and diagnosis result category M2.

[0106] See also Figure 3 , Figure 3 FIG. 1 is a flow chart showing a method for constructing a therapeutic formula library provided in an embodiment of the present application. Figure 3 As shown, in some embodiments, the construction of a treatment formula library based on the correspondence between the diagnosis result category and the treatment item category includes:

[0107] Step S310, based on the correspondence between the diagnosis result categories and the treatment item categories, determining a treatment formula corresponding to each of the diagnosis result categories, wherein the treatment formula has a correspondence with at least one of the treatment item categories.

[0108] Step S320, constructing a treatment formula library according to the treatment formula.

[0109] It can be understood that based on the correspondence between the diagnosis result category and the treatment item category, a treatment formula for each diagnosis result category is further formed, wherein the treatment formula has a correspondence with at least one treatment item category, and a treatment formula library is constructed based on the formed treatment formula.

[0110] For example, there are 7 diagnosis result categories {M1, M2, M3, M4, M5, M6, M7} and 10 treatment item categories {N1, N2, N3, N4, N5, N6, N7, N8, N9, N10} in the medical consultation dataset. 10}, the correspondence between the diagnosis result category and the treatment item category can be expressed as the optimal solution: as well as, They represent that treatment item categories N2, N4, N6 and N8 belong to diagnosis result category M3 in the best case, and treatment item categories N1, N3, N7 and N 10In the best case, it belongs to the diagnosis result category M7. Based on the correspondence between the above diagnosis result categories and treatment item categories, the treatment formulas for diagnosis result categories M3 and M7 can be determined, where the treatment formula for diagnosis result category M3 is treatment item categories N2, N4, N6 and N8, and the treatment formula for diagnosis result category M7 is treatment item categories N1, N3, N7 and N8. 10 , and then construct a treatment formula library, and store the correspondence between the diagnosis result category and the treatment item category in the form of a treatment formula, that is, one diagnosis result category corresponds to N treatment item categories in the treatment formula library.

[0111] A treatment formula library including treatment formulas is constructed. When querying the treatment formula library, the treatment formula including at least one treatment item category corresponding to the diagnosis result category can be directly obtained by searching the diagnosis result category.

[0112] The present application proposes a method for constructing a treatment formula library. The method for constructing a treatment formula library obtains a medical data set including medical data of multiple patients, wherein each medical data includes the diagnosis result and treatment items of the patient's medical treatment, and determines the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and treatment item, thereby constructing and solving an integer programming model based on the diagnosis result category and treatment item category corresponding to each patient, obtaining the corresponding relationship between the diagnosis result category and the treatment item category, and constructing a treatment formula library based on the corresponding relationship between the diagnosis result category and the treatment item category. The embodiment of the present application obtains a medical data set and extracts the diagnosis result category and treatment item category corresponding to each patient therefrom, obtains the corresponding relationship between the diagnosis result category and the treatment item category by constructing and solving an integer programming model about the diagnosis result category and the treatment item category, and constructs a treatment formula library based on the corresponding relationship.

[0113] It is further understood that, although the operations are described in a specific order in the drawings in the embodiments of the present application, it should not be understood as requiring the operations to be performed in the specific order or serial order shown, or requiring the execution of all the operations shown to obtain the desired results. In certain environments, multitasking and parallel processing may be advantageous.

[0114] See also Figure 4 The present application embodiment further provides a device 100 for constructing a treatment formula library, and the treatment formula construction device 100 includes:

[0115] An acquisition module 110 is used to acquire a medical consultation data set, wherein the medical consultation data set includes medical consultation data of multiple patients, and each medical consultation data includes a diagnosis result and treatment items of the patient's medical consultation;

[0116] A processing module 120, for determining a diagnosis result category and a treatment item category corresponding to each patient according to the diagnosis result and the treatment item;

[0117] A first construction module 130 is used to construct an integer programming model based on the diagnosis result category and the treatment item category corresponding to each patient;

[0118] A solution module 140, used for solving the integer programming model to obtain the corresponding relationship between the diagnosis result category and the treatment item category;

[0119] The second constructing module 150 is used to construct a treatment formula library based on the corresponding relationship between each of the diagnosis result categories and the treatment item categories.

[0120] The present application proposes a device for constructing a treatment formula library. The device for constructing the treatment formula library obtains a medical data set including medical data of multiple patients through an acquisition module, wherein each medical data includes the diagnosis result and treatment items of the patient's medical treatment. The processing module determines the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and treatment item. The first construction module constructs an integer programming model based on the diagnosis result category and treatment item category corresponding to each patient. Then, the integer programming model is solved by the solution module to obtain the correspondence between the diagnosis result category and the treatment item category. The second construction module constructs the treatment formula library based on the correspondence between the diagnosis result category and the treatment item category. The embodiment of the present application obtains a medical data set and extracts the diagnosis result category and treatment item category corresponding to each patient therefrom. By constructing and solving the integer programming model about the diagnosis result category and the treatment item category, the correspondence between the diagnosis result category and the treatment item category is obtained and the treatment formula library is constructed based on the correspondence.

[0121] It should be noted that the information interaction, execution process and other contents between the modules of the above-mentioned device are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0122] See also Figure 5 , Figure 5 The hardware structure of an electronic device provided in an embodiment of the present application is shown, and the electronic device includes:

[0123] The processor 210 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant computer programs to implement the technical solutions provided in the embodiments of the present application;

[0124] The memory 220 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 220 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 220, and the processor 210 calls and executes the method for constructing a treatment formula library in the embodiment of this application;

[0125] Input / output interface 230, used to implement information input and output;

[0126] The communication interface 240 is used to realize the communication interaction between the device and other devices, and the communication can be realized by wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); and the bus 250 transmits information between each component of the device (such as the processor 210, the memory 220, the input / output interface 230 and the communication interface 240);

[0127] The processor 210 , the memory 220 , the input / output interface 230 , and the communication interface 240 are connected to each other in communication within the device via the bus 250 .

[0128] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more computer programs, and the one or more computer programs can be executed by one or more processors to implement the above-mentioned method of constructing a treatment formula library.

[0129] The memory, as a computer-readable storage medium, can be used to store software programs and computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0130] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0131] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0133] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0135] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0136] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0139] If the assembled units are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., and other media that can store programs.

[0140] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for constructing a therapeutic formula library, characterized in that: The method comprises: Acquire a medical consultation data set, wherein the medical consultation data set includes medical consultation data of a plurality of patients, and each medical consultation data includes a diagnosis result and treatment items of the patient's medical consultation; Determine the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item; Based on the diagnosis result category and the treatment item category corresponding to each patient, construct an integer programming model; Solving the integer programming model to obtain a corresponding relationship between the diagnosis result category and the treatment item category; Building a treatment formula library based on the correspondence between the diagnosis result categories and the treatment item categories; The integer programming model is determined by the following formula: ； in, Indicates taking the minimum value, is the number of the diagnosis result categories, is the number of treatment item categories, Indicates The diagnosis result category to which the treatment item category belongs, is the first loss function, is the second loss function, is the third loss function, is the first weight coefficient, is the second weight coefficient, is the third weight coefficient; The first loss function Determined by the following formula: ； Among them, the is the number of patients in the medical consultation data set, , when the patient Type of treatment project Under the project treatment, the is 0, otherwise it is 1; , when the patient Confirmed diagnosis result category The following diseases, is 0, otherwise it is 1; , The specific formula is as follows: ; The second loss function Determined by the following formula: ； The third loss function Determined by the following formula: 。 2. The method according to claim 1, characterized in that Determining the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item includes: Determine the diagnosis result category corresponding to each patient according to the diagnosis result and the preset diagnosis result category; According to the treatment items and the preset treatment item classification, the treatment item category corresponding to each patient is determined.

3. The method according to claim 1, characterized in that The constructing of a treatment formula library based on the correspondence between the diagnosis result category and the treatment item category includes: Based on the correspondence between the diagnosis result categories and the treatment item categories, determining a treatment formula corresponding to each diagnosis result category, wherein the treatment formula has a correspondence with at least one treatment item category; According to the treatment formula, a treatment formula library is constructed.

4. A device for constructing a treatment formula library, characterized in that: The device comprises: An acquisition module is used to acquire a medical consultation data set, wherein the medical consultation data set includes medical consultation data of multiple patients, and each medical consultation data includes a diagnosis result and treatment items of the patient's medical consultation; A processing module, used to determine the diagnosis result category and treatment item category corresponding to each patient according to the diagnosis result and the treatment item; A first construction module is used to construct an integer programming model based on the diagnosis result category and the treatment item category corresponding to each patient; A solution module, used for solving the integer programming model to obtain the corresponding relationship between the diagnosis result category and the treatment item category; A second construction module is used to construct a treatment formula library based on the corresponding relationship between each of the diagnosis result categories and the treatment item categories; The integer programming model is determined by the following formula: ； in, Indicates taking the minimum value, is the number of the diagnosis result categories, is the number of treatment item categories, Indicates The diagnosis result category to which the treatment item category belongs, is the first loss function, is the second loss function, is the third loss function, is the first weight coefficient, is the second weight coefficient, is the third weight coefficient; The first loss function Determined by the following formula: ； Among them, the is the number of patients in the medical consultation data set, , when the patient Type of treatment project Under the project treatment, the is 0, otherwise it is 1; , when the patient Confirmed diagnosis result category The following diseases, is 0, otherwise it is 1; , The specific formula is as follows: ; The second loss function Determined by the following formula: ； The third loss function Determined by the following formula: 。 5. A computer device, characterized in that: include: Memory, used to store programs; A processor, configured to execute the program stored in the memory. When the processor executes the program stored in the memory, the processor is configured to execute: the method as claimed in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute: the method according to any one of claims 1 to 3.

Images