Preposed auditing system and method for traditional Chinese medicine prescription

Abstract

The embodiment of the invention discloses a pre-auditing system and method for a traditional Chinese medicine prescription, and the system comprises a data collection module which is used for obtaining information data; the information data comprises traditional Chinese medicine prescriptions and medical record information; the extraction module is used for performing feature extraction on the traditional Chinese medicine prescription and the medical record information to obtain respective corresponding feature information; the auditing module is used for transmitting the feature information to an auditing model constructed by utilizing a knowledge base in advance for auditing so as to obtain a result whether the auditing is passed or not; if the verification is passed, transmitting the information data to a subsequent charging system; the method has the beneficial effects that the defects that in the prior art, only contents such as incompatibility of a prescription, over-dose use of toxic medicinal materials and the like are checked, the coverage is narrow, and the actual condition of a patient is not combined are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of prescription review, and in particular to a pre-review system and method for a traditional Chinese medicine prescription. Background Art

[0002] Traditional Chinese medicine prescriptions include prescriptions for Chinese patent medicines and prescriptions for Chinese herbal medicine slices. The difficulty in their prior review lies, on the one hand, in the fact that different schools of Chinese medicine may have different views on the same type of disease; on the other hand, it is necessary to take into account the particularity of traditional Chinese medicine prescriptions; for example, due to differences in the patient's physical constitution, the same type of disease may correspond to different combinations of medications, making the medication flexible and changeable, and the dosage, composition and compatibility of traditional Chinese medicine prescriptions often vary greatly.

[0003] At present, the pre-prescription review used in the existing technology only reviews whether there are any incompatibility contraindications in the prescription itself, whether toxic medicinal materials are used in excessive doses, etc. It has a narrow coverage, does not take into account the actual situation of the patient, and is difficult to meet the actual needs of prescription review. Summary of the invention

[0004] In order to overcome the deficiencies in the prior art, the object of the present invention is to provide a pre-review system and method for traditional Chinese medicine prescriptions.

[0005] Aspect 1: A pre-review system for traditional Chinese medicine prescriptions, comprising:

[0006] A data acquisition module, used to obtain information data; wherein the information data includes Chinese medicine prescriptions and medical records information;

[0007] An extraction module, used to extract features from the Chinese medicine prescription and medical record information respectively to obtain corresponding feature information;

[0008] The audit module is used to transmit the characteristic information to the audit model pre-built using the knowledge base for audit to obtain the result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system.

[0009] Preferably, the feature extraction of the traditional Chinese medicine prescription and medical record information specifically includes:

[0010] Extracting features of the decoction pieces and the corresponding dosage in the Chinese medicine prescription;

[0011] Feature extraction is performed on past medical history, diagnosis information and side effects in the medical record information.

[0012] Preferably, the associated factors include similar compounds, similar diseases, combination, treatment, cause and connection, and each factor is used as a corresponding edge type.

[0013] Preferably, the audit model includes a first audit model and a second audit model;

[0014] The first review model is used for reviewing the dosage of single-ingredient decoction pieces, reviewing the number of prescription drug ingredients, reviewing the total prescription dosage, reviewing the incompatibility taboos, reviewing the labeling of decoction pieces, and reviewing the taboos for the user population; wherein each decoction piece is associated with corresponding origin information;

[0015] The second audit model is used to output corresponding reminder information when the first audit model fails the audit, and transmit the reminder information to the second audit model for re-audit.

[0016] Preferably, the second audit model includes a plurality of audit sub-models, each audit sub-model receiving information data associated with a reminder message; wherein each audit sub-model is pre-trained based on a neural network.

[0017] Preferably, the aforementioned pre-review system for traditional Chinese medicine prescriptions further comprises an optimization module, wherein the optimization module is used to:

[0018] Mining the compatibility relationship between different Chinese medicines through association rules, and displaying the compatibility relationship of Chinese medicines corresponding to the diagnosis in the Chinese medicine prescription through a network diagram;

[0019] Use the topological structure in complex network theory to analyze the core nodes of the network;

[0020] Based on the obtained core nodes, the number of medicinal ingredients in the traditional Chinese medicine prescription is reduced to achieve prescription optimization, and the optimized traditional Chinese medicine prescription is transmitted to the doctor for confirmation.

[0021] A second aspect: A method for pre-review of a Chinese medicine prescription, applied to a pre-review system for a Chinese medicine prescription described in the first aspect, the method comprising:

[0022] Acquiring information data; wherein the information data includes Chinese medicine prescriptions and medical records information;

[0023] Extracting features from the Chinese medicine prescription and medical record information respectively to obtain corresponding feature information;

[0024] The characteristic information is transmitted to the audit model constructed in advance using the knowledge base for audit to obtain a result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system.

[0025] Preferably, the feature extraction of the traditional Chinese medicine prescription and medical record information specifically includes:

[0026] Extracting features of the decoction pieces and the corresponding dosage in the Chinese medicine prescription;

[0027] Feature extraction is performed on past medical history, diagnosis information and side effects in the medical record information.

[0028] Preferably, the audit model includes a first audit model and a second audit model;

[0029] The first review model is used for reviewing the dosage of single-ingredient decoction pieces, reviewing the number of prescription drug ingredients, reviewing the total prescription dosage, reviewing the incompatibility taboos, reviewing the labeling of decoction pieces, and reviewing the taboos for the user population; wherein each decoction piece is associated with corresponding origin information;

[0030] The second audit model is used to output corresponding reminder information when the first audit model fails the audit, and transmit the reminder information to the second audit model for re-audit.

[0031] Preferably, the method further comprises:

[0032] Mining the compatibility relationship between different Chinese medicines through association rules, and displaying the compatibility relationship of Chinese medicines corresponding to the diagnosis in the Chinese medicine prescription through a network diagram;

[0033] Use the topological structure in complex network theory to analyze the core nodes of the network;

[0034] Based on the obtained core nodes, the number of medicinal ingredients in the traditional Chinese medicine prescription is reduced to achieve prescription optimization, and the optimized traditional Chinese medicine prescription is transmitted to the doctor for confirmation.

[0035] The above technical scheme has the following advantages: the present invention proposes a pre-review system and method for Chinese medicine prescriptions, which extracts features from the Chinese medicine prescriptions and medical record information respectively to obtain their respective corresponding feature information; the feature information is transmitted to a review model pre-constructed using a knowledge base for review to obtain a result of whether the review is passed; if the review is passed, the information data is transmitted to a subsequent charging system; thereby overcoming the defects of the prior art that only the content of the review is focused on whether there are incompatibility contraindications in the prescription itself, whether toxic medicinal materials are used in excess of the dose, etc., which has a narrow coverage and does not take into account the actual situation of the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a system block diagram of a pre-review system for traditional Chinese medicine prescriptions provided by an embodiment of the present invention;

[0037] Figure 2 It is a flow chart of a method for pre-review of a traditional Chinese medicine prescription provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other examples, in order to avoid confusing the present invention, known circuits, software or methods are not specifically described.

[0039] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0040] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0041] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0042] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in one embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification are not necessarily all referring to the same embodiment or example.

[0043] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0044] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0045] refer to Figure 1 As shown, a pre-review system for traditional Chinese medicine prescriptions provided by an embodiment of the present invention includes:

[0046] A data acquisition module, used to obtain information data; wherein the information data includes Chinese medicine prescriptions and medical records information;

[0047] An extraction module, used to extract features from the Chinese medicine prescription and medical record information respectively to obtain corresponding feature information;

[0048] The audit module is used to transmit the characteristic information to the audit model pre-built using the knowledge base for audit to obtain the result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system.

[0049] In this embodiment, if the review fails, a modification or double-signing process is performed;

[0050] The knowledge base is constructed based on the "Terms of Clinical Diagnosis and Treatment of Traditional Chinese Medicine", "Terms of Basic Theory of Traditional Chinese Medicine", "Expert Consensus on Clinical Application of Chinese Herbal Medicine Pieces", "Chinese Pharmacopoeia", "Golden Chamber" and "Treatise on Febrile Diseases", etc., so as to be used for subsequent review;

[0051] The pre-review system is connected to the hospital management information system (HIS system) of the hospital or medical institution to obtain the information data; in other applications, the information data also includes the examination data of the corresponding personnel in the medical record information; such as corresponding laboratory indicators, imaging images, etc., which are not listed one by one here.

[0052] The feature extraction of the traditional Chinese medicine prescription and medical record information specifically includes:

[0053] Extracting features of the decoction pieces and the corresponding dosage in the Chinese medicine prescription;

[0054] Feature extraction is performed on past medical history, diagnosis information and side effects in the medical record information.

[0055] Specifically, semantic network or natural language processing technology is used to transform the information on rational use of Chinese herbal medicines into logical, organized and standardized data rules that can be recognized by computers.

[0056] Furthermore, in order to improve the accuracy of the audit and reduce the corresponding misjudgment and manual review workload;

[0057] The audit model includes a first audit model and a second audit model;

[0058] The first review model is used for reviewing the dosage of single-ingredient decoction pieces, reviewing the number of prescription drug ingredients, reviewing the total prescription dosage, reviewing the incompatibility taboos, reviewing the labeling of decoction pieces, and reviewing the taboos for the user population; wherein each decoction piece is associated with corresponding origin information;

[0059] The second audit model is used to output corresponding reminder information when the first audit model fails the audit, and transmit the reminder information to the second audit model for re-audit.

[0060] In this embodiment, by setting up two different models, the actual situation can be fully responded to. There are some situations such as large dosage, combination of drugs and co-use of antagonistic drugs, thereby avoiding overly mechanical review and processing; while giving reminders, a targeted re-review is carried out based on these special situations in combination with the second review model.

[0061] In this embodiment, the second audit model includes multiple audit sub-models, each audit sub-model receives information data associated with a reminder message; wherein each audit sub-model is pre-trained based on a neural network; that is, each special case is specifically reviewed again through the corresponding audit sub-model to improve its accuracy; the neural network can adopt a long short-term memory network, which is not limited here.

[0062] The above scheme is adopted to extract features from the Chinese medicine prescription and medical record information respectively to obtain their respective corresponding feature information; the feature information is transmitted to the audit model constructed in advance using the knowledge base for audit to obtain the result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system; thereby overcoming the defects of the prior art that only the content of the prescription itself is audited for whether there are incompatibility taboos, whether toxic medicinal materials are used in excess of dosage, etc., which has a narrow coverage and does not take into account the actual situation of the patient.

[0063] Furthermore, in order to better combine the actual situation of the patient, the review module also derives corresponding contraindication information based on the inspection data, and transmits the contraindication information to the first review model for corresponding contraindication review; for example, during severe kidney disease, some herbal medicines cannot be used, but can be used in the early stages; using the laboratory indicators in the inspection data can make medication more accurate and safe.

[0064] Furthermore, in another embodiment, based on the above technical solution, the aforementioned pre-review system for traditional Chinese medicine prescriptions further includes an optimization module, wherein the optimization module is used to:

[0065] Mining the compatibility relationship between different Chinese medicines through association rules, and displaying the compatibility relationship of Chinese medicines corresponding to the diagnosis in the Chinese medicine prescription through a network diagram; that is, the Chinese medicines associated with the symptoms in the diagnosis;

[0066] Use the topological structure in complex network theory to analyze the core nodes of the network;

[0067] Based on the obtained core nodes, the number of medicinal ingredients in the traditional Chinese medicine prescription is reduced to achieve prescription optimization, and the optimized traditional Chinese medicine prescription is transmitted to the doctor for confirmation.

[0068] In this embodiment, the compatibility relationship between different Chinese medicines is mined according to the Apriori algorithm; and then the core drug nodes in the Chinese medicine network are discovered through analysis, so as to select a shorter path, thereby reducing the number of medicinal flavors and optimizing the prescription.

[0069] Based on the inventive concept of the above system, reference Figure 2 As shown, an embodiment of the present invention also provides a method for pre-review of a Chinese medicine prescription, which is applied to the above-mentioned system for pre-review of a Chinese medicine prescription, and the method includes:

[0070] S101, obtaining information data; wherein the information data includes Chinese medicine prescriptions and medical record information;

[0071] S102, extracting features from the Chinese medicine prescription and medical record information respectively to obtain corresponding feature information;

[0072] S103, transmitting the characteristic information to the audit model pre-built using the knowledge base for audit to obtain a result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system.

[0073] In this embodiment, the feature extraction of the traditional Chinese medicine prescription and medical record information specifically includes:

[0074] Extracting features of the decoction pieces and the corresponding dosage in the Chinese medicine prescription;

[0075] Feature extraction is performed on past medical history, diagnosis information and side effects in the medical record information.

[0076] The audit model includes a first audit model and a second audit model;

[0077] The first review model is used for reviewing the dosage of single-ingredient decoction pieces, reviewing the number of prescription drug ingredients, reviewing the total prescription dosage, reviewing the incompatibility taboos, reviewing the labeling of decoction pieces, and reviewing the taboos for the user population; wherein each decoction piece is associated with corresponding origin information;

[0078] The second audit model is used to output corresponding reminder information when the first audit model fails the audit, and transmit the reminder information to the second audit model for re-audit; wherein, the second audit model includes multiple audit sub-models, each audit sub-model receives information data associated with a reminder information; wherein, each audit sub-model is pre-trained based on a neural network.

[0079] Furthermore, the method further comprises:

[0080] Mining the compatibility relationship between different Chinese medicines through association rules, and displaying the compatibility relationship of Chinese medicines corresponding to the diagnosis in the Chinese medicine prescription through a network diagram;

[0081] Use the topological structure in complex network theory to analyze the core nodes of the network;

[0082] Based on the obtained core nodes, the number of medicinal ingredients in the traditional Chinese medicine prescription is reduced to achieve prescription optimization, and the optimized traditional Chinese medicine prescription is transmitted to the doctor for confirmation.

[0083] It should be noted that for more specific working process and examples of this method, please refer to the aforementioned system embodiment section, which will not be repeated here.

[0084] The above method is adopted to extract features from the Chinese medicine prescription and medical record information respectively to obtain their respective corresponding feature information; the feature information is transmitted to the audit model constructed in advance using the knowledge base for audit to obtain the result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system; thereby overcoming the defects in the prior art that only the content of the prescription itself is audited for whether there are incompatibility taboos, whether toxic medicinal materials are used in excess of dosage, etc., which has a narrow coverage and does not take into account the actual situation of the patient.

[0085] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminals and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0087] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A pre-review system for traditional Chinese medicine prescriptions, characterized by: include: A data acquisition module, used to acquire information data; wherein the information data includes Chinese medicine prescriptions and medical records information; An extraction module, used to extract features from the Chinese medicine prescription and medical record information respectively to obtain corresponding feature information; The audit module is used to transmit the characteristic information to the audit model pre-built using the knowledge base for audit to obtain the result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system.

2. A pre-review system for Chinese medicine prescriptions according to claim 1, characterized in that: The feature extraction of the traditional Chinese medicine prescription and medical record information specifically includes: Extracting features of the decoction pieces and the corresponding dosage in the Chinese medicine prescription; Feature extraction is performed on past medical history, diagnosis information and side effects in the medical record information.

3. A pre-review system for Chinese medicine prescriptions according to claim 2, characterized in that: The audit model includes a first audit model and a second audit model; The first review model is used for reviewing the dosage of single-ingredient decoction pieces, reviewing the number of prescription drug ingredients, reviewing the total prescription dosage, reviewing the incompatibility taboos, reviewing the labeling of decoction pieces, and reviewing the taboos for the user population; wherein each decoction piece is associated with corresponding origin information; The second audit model is used to output corresponding reminder information when the first audit model fails the audit, and transmit the reminder information to the second audit model for re-audit.

4. A pre-review system for Chinese medicine prescriptions according to claim 3, characterized in that: The second audit model includes multiple audit sub-models, each audit sub-model receives information data associated with a reminder message; wherein each audit sub-model is pre-trained based on a neural network.

5. A pre-review system for Chinese medicine prescriptions according to any one of claims 1 to 4, characterized in that: It also includes an optimization module, wherein the optimization module is used to: Mining the compatibility relationship between different Chinese medicines through association rules, and displaying the compatibility relationship of Chinese medicines corresponding to the diagnosis in the Chinese medicine prescription through a network diagram; Use the topological structure in complex network theory to analyze the core nodes of the network; Based on the obtained core nodes, the number of medicinal ingredients in the traditional Chinese medicine prescription is reduced to achieve prescription optimization, and the optimized traditional Chinese medicine prescription is transmitted to the doctor for confirmation.

6. A method for pre-review of a traditional Chinese medicine prescription, characterized in that: The method applied to the pre-review system of a traditional Chinese medicine prescription as claimed in claim 1 comprises: Acquiring information data; wherein the information data includes Chinese medicine prescriptions and medical records information; Extracting features from the Chinese medicine prescription and medical record information respectively to obtain corresponding feature information; The characteristic information is transmitted to the audit model constructed in advance using the knowledge base for audit to obtain a result of whether the audit is passed; if the audit is passed, the information data is transmitted to the subsequent charging system.

7. The method for pre-review of a Chinese medicine prescription according to claim 6, characterized in that: The feature extraction of the traditional Chinese medicine prescription and medical record information specifically includes: Extracting features of the decoction pieces and the corresponding dosage in the Chinese medicine prescription; Feature extraction is performed on past medical history, diagnosis information and side effects in the medical record information.

8. The method for pre-review of a Chinese medicine prescription according to claim 7, characterized in that: The audit model includes a first audit model and a second audit model; The first review model is used for reviewing the dosage of single-ingredient decoction pieces, reviewing the number of prescription drug ingredients, reviewing the total prescription dosage, reviewing the incompatibility taboos, reviewing the labeling of decoction pieces, and reviewing the taboos for the user population; wherein each decoction piece is associated with corresponding origin information; The second audit model is used to output corresponding reminder information when the first audit model fails the audit, and transmit the reminder information to the second audit model for re-audit.

9. A method for pre-review of a Chinese medicine prescription according to claim 7 or 8, characterized in that: The method further comprises: Mining the compatibility relationship between different Chinese medicines through association rules, and displaying the compatibility relationship of Chinese medicines corresponding to the diagnosis in the Chinese medicine prescription through a network diagram; Use the topological structure in complex network theory to analyze the core nodes of the network; Based on the obtained core nodes, the number of medicinal ingredients in the traditional Chinese medicine prescription is reduced to achieve prescription optimization, and the optimized traditional Chinese medicine prescription is transmitted to the doctor for confirmation.

Images