A prescription drug information entry system for a database of integrated traditional Chinese and western medicine

Abstract

The present invention relates to the field of prescription entry detection technology, and in particular to a prescription drug information entry system for a Chinese and Western medicine combined drug database, including an acquisition module for acquiring dosage data and indications of drugs in historical prescriptions and prescriptions to be entered; a dosage risk analysis module for determining the dosage fluctuation risk of drugs according to the numerical distribution and numerical fluctuation of dosage data of the same drug in all historical prescriptions; an efficacy mutual exclusion analysis module for determining the degree of overlap of the efficacy of two drugs, and then determining the efficacy mutual exclusion influence index of the target drug in the prescription to be entered; an abnormality analysis module for determining the degree of dosage abnormality; and then determining the probability of prescription abnormality, and determining whether the prescription to be entered needs to be entered according to the probability of prescription abnormality. The present invention can improve the accuracy and reliability of prescription abnormality probability analysis and avoid database pollution caused by abnormal prescription entry.

Description

Technical Field

[0001] The present invention relates to the technical field of prescription entry detection, and in particular to a prescription drug information entry system for a traditional Chinese and western medicine combined drug database. Background Art

[0002] The prescription drug information entry system is an electronic platform specifically used to manage and record prescription drug information. Compared with traditional paper prescriptions, it has the advantages of high credibility, easy retention and supervision, and it is easy to achieve data interoperability and real-time sharing between medical institutions to form a more reasonable medical treatment order.

[0003] The accuracy of prescription drug information is crucial to drug management. In reality, it is inevitable that a small amount of data will be distorted due to objective reasons such as errors in information entry operations, which requires a lot of manpower and material resources to verify and confirm. The existing common method is to set verification rules for drug information, such as whether the dosage reaches the threshold to determine whether data anomalies have occurred. This method has limited verification capabilities and ignores the relationship between different drug dosages. Therefore, the accuracy and reliability of prescription anomaly analysis are insufficient, and abnormal data cannot be accurately screened during information entry, resulting in the entry of abnormal prescriptions. Summary of the invention

[0004] In order to solve the technical problem that the accuracy and reliability of prescription abnormality analysis in the related art are insufficient, and abnormal data cannot be accurately screened when information is entered, resulting in the entry of abnormal prescriptions, the present invention provides a prescription drug information entry system for a Chinese and Western medicine combined drug database, and the technical solution adopted is as follows:

[0005] The present invention proposes a prescription drug information entry system for a Chinese and Western medicine combined drug database, comprising:

[0006] The acquisition module is used to obtain the disease type in the prescription to be entered, as well as the historical prescriptions of the same disease type; determine the dosage data and indications of different drugs in the historical prescriptions and the prescriptions to be entered;

[0007] The dosage risk analysis module is used to determine the dosage fluctuation risk level of each drug based on the numerical distribution and numerical fluctuation of the dosage data of the same drug in all historical prescriptions;

[0008] The efficacy mutual exclusion analysis module is used to determine the degree of overlap of the efficacy of any two drugs based on the proportion of any two drugs appearing in the same historical prescription and the similarity of the indications of the two drugs; any drug in the prescription to be entered is used as the target drug, and the efficacy mutual exclusion impact index of the target drug in the prescription to be entered is determined based on the degree of overlap of the efficacy of the target drug and other drugs in the prescription to be entered;

[0009] The abnormality analysis module is used to determine the degree of dosage abnormality based on the dosage data of each drug in the prescription to be entered and the dosage difference of the corresponding drug in all historical prescriptions, as well as the degree of dosage fluctuation risk; determine the abnormal usage probability of the corresponding drug in the prescription to be entered based on the mutually exclusive influence indicators of the efficacy of the same drug and the degree of dosage abnormality; determine the prescription abnormality probability of the prescription to be entered based on the abnormal usage probability of all drugs in the prescription to be entered, and determine whether the prescription to be entered needs to be entered based on the prescription abnormality probability.

[0010] Furthermore, the step of determining the dosage fluctuation risk level of each drug based on the numerical distribution and numerical fluctuation of dosage data of the same drug in all historical prescriptions includes:

[0011] The difference between the maximum and minimum values ​​of the dosage data of the same drug in all historical prescriptions is taken as the dosage distribution amplitude;

[0012] The numerical variance of the dosage data of the same drug in all historical prescriptions is used as the dosage fluctuation indicator;

[0013] The dose fluctuation risk level of the drug is determined based on the dose distribution amplitude and the dose fluctuation index.

[0014] Furthermore, determining the dose fluctuation risk level of the drug according to the dose distribution amplitude and the dose fluctuation index includes:

[0015] The product of the dose distribution amplitude and the dose fluctuation index is calculated, and the inverse of the product is normalized as the dose fluctuation risk degree of the drug.

[0016] Furthermore, the degree of overlap of the therapeutic effects of any two drugs is determined based on the proportion of any two drugs appearing in the same historical prescription and the similarity of the indications of the two drugs, including:

[0017] Any two drugs are grouped into a drug group, and the frequency of the drug group appearing in all historical prescriptions is taken as the group frequency;

[0018] The ratio of the group frequency to the number of all historical prescriptions was calculated as the frequency overlap ratio;

[0019] Extract keywords from the indications of the two drugs in the drug group respectively, determine the indication keywords of each drug, and use the ratio of the number of repeated keywords in the two drugs to the total number of all keywords as the indication similarity index;

[0020] The product of the frequency overlap ratio and the indication similarity index is calculated, and the maximum and minimum values ​​are normalized as the efficacy overlap.

[0021] Furthermore, according to the degree of overlap between the efficacy of the target drug and other drugs in the prescription to be entered, the efficacy mutual exclusion impact index of the target drug in the prescription to be entered is determined, including:

[0022] Calculate the mean of the overlap between the target drug and other drugs in the prescription to be entered, perform maximum and minimum value normalization, and obtain the target drug's mutually exclusive influence index of efficacy.

[0023] Furthermore, the degree of dosage abnormality is determined based on the dosage data of each drug in the prescription to be entered and the dosage difference of the corresponding drug in all historical prescriptions, as well as the degree of dosage fluctuation risk, including:

[0024] Calculate the mean of the dosage data of each drug in all historical prescriptions as the historical dosage mean of the corresponding drug;

[0025] The difference between the dosage data of any drug in the prescription to be entered and the historical dosage mean is used as the historical dosage difference indicator;

[0026] The product of the historical dose difference index and the dose fluctuation risk level is normalized and used as the dose abnormality level.

[0027] Furthermore, based on the mutually exclusive influencing indicators of the efficacy of the same drug and the degree of abnormal dosage, the abnormal probability of the use of the corresponding drug in the prescription to be entered is determined, including:

[0028] The product of the mutually exclusive efficacy impact index and the degree of dosage abnormality is calculated and normalized as the probability of abnormal use.

[0029] Furthermore, according to the abnormal usage probability of all drugs in the prescription to be entered, the abnormal probability of the prescription to be entered is determined, including:

[0030] The maximum value of the abnormal usage probabilities of all drugs in the prescription to be entered is used as the abnormal prescription probability of the prescription to be entered.

[0031] Furthermore, the step of determining whether the prescription to be entered needs to be entered according to the probability of prescription abnormality includes:

[0032] When the probability of prescription abnormality is greater than a preset abnormality threshold, the prescription to be entered is determined to be abnormal, and entry is suspended;

[0033] When the probability of prescription abnormality is less than or equal to a preset abnormality threshold, the prescription to be entered is determined to be normal and is entered.

[0034] Furthermore, the value of the preset abnormal threshold is 0.78.

[0035] The present invention has the following beneficial effects:

[0036] The present invention obtains dosage data and indications of different drugs in historical prescriptions and prescriptions to be entered, so as to analyze the prescriptions themselves for abnormalities during the information entry process according to the dosage data and indications, thereby timely finding prescriptions with abnormal medication, which is convenient for prescription tracing;

[0037] Furthermore, the dose fluctuation risk level of each drug is determined based on the numerical distribution and numerical fluctuation of the dose data of the same drug in all historical prescriptions. The dose fluctuation risk level can accurately characterize the impact of dose fluctuations. The dose abnormality level is determined by combining the dose data of each drug in the prescription to be entered with the dose difference of the corresponding drug in all historical prescriptions through the dose fluctuation risk, so as to analyze the specific values ​​of the dose. This scheme also analyzes the mutually exclusive effects between multiple drugs, that is, according to the similarity of the indications, the degree of overlap of the efficacy of two drugs is determined, and then according to the degree of overlap of the efficacy, the efficacy mutually exclusive influence index of the target drug in the prescription to be entered is determined. The efficacy mutually exclusive influence index can accurately analyze the mutually exclusive effects between drugs, and avoid the calculation of dose abnormality affected by the superposition of the efficacy of drugs and the mutual exclusion effect.

[0038] Finally, according to the efficacy mutual exclusion impact index and the degree of dosage abnormality, the abnormal use probability of the corresponding drug in the prescription to be entered is determined, and the abnormal use probability of all drugs in the prescription to be entered is determined. According to the abnormal use probability of all drugs in the prescription to be entered, the abnormal prescription probability of the prescription to be entered is determined, and whether the prescription to be entered needs to be entered is determined according to the abnormal prescription probability, that is, by analyzing the abnormal use probability of a single drug, and then combining the abnormal use probability of all drugs to obtain the abnormal prescription probability, it is convenient to enter and screen according to the abnormal prescription probability. In summary, the present invention can effectively combine the efficacy mutual exclusion effect of multi-dimensional quality inspection, improve the accuracy and reliability of abnormal prescription probability analysis, so as to effectively screen when entering information and avoid database pollution caused by abnormal prescription entry. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A structural diagram of a prescription drug information entry system for a traditional Chinese and western medicine combined drug database provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of a prescription drug information entry system for a Chinese and Western medicine combined drug database proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0042] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0043] The following is a detailed description of a specific scheme of a prescription drug information entry system for a traditional Chinese and western medicine combined drug database provided by the present invention in conjunction with the accompanying drawings.

[0044] See also Figure 1 , which shows a structure diagram of a prescription drug information entry system for a traditional Chinese and western medicine combined drug database provided by an embodiment of the present invention, the system includes:

[0045] The acquisition module 101 is used to acquire the disease type in the prescription to be entered, and the historical prescriptions of the same disease type; determine the dosage data and indications of different drugs in the historical prescriptions and the prescription to be entered.

[0046] Among them, the acquisition module 101 is mainly used for data acquisition and provides a data basis. The data acquired in this solution are mainly prescriptions to be entered and historical prescriptions of the same disease type. The prescription to be entered is a prescription for which information entry is to be performed. In the related art, the information entry system only has the function of information entry, that is, directly performing prescription entry. However, in the actual prescription entry process, due to possible misoperation by the pharmacist or information recognition errors during the prescription opening process, the prescription entry is abnormal.

[0047] Among them, the disease type is mainly the disease written in the prescription, which can specifically include colds, liver diseases, cardiovascular diseases, stomach diseases, cancer, kidney diseases, diabetes, etc. Taking colds as an example, the prescriptions related to colds in the drug database can be uniformly collected as historical prescriptions to facilitate the analysis of the prescriptions to be analyzed.

[0048] The dosage data in the embodiment of the present invention is specifically the dosage shown in the prescription. In this scheme, the quantity taken per day is used as the specific dosage unit. For example, the dosage of tablets is a few tablets, and the specific dosage of oral solution is a few bottles, or a few milliliters. Because the analysis of the specific dosage is directly carried out in quantity, the brand and regulation of the drug also need to be considered in different drugs, that is, the same drug, such as amoxicillin capsules, different models of amoxicillin capsules produced by different manufacturers are also regarded as a drug respectively. This limitation makes the overall prescription analysis more rigorous and reliable.

[0049] The indication description in the embodiments of the present invention is the description data of the indication corresponding to the drug. For example, the indication description of compound acetaminophen tablets is: suitable for relieving fever, headache, sore limbs, sneezing, runny nose, nasal congestion, sore throat and other symptoms caused by common cold and influenza.

[0050] It should be noted that the analysis process mainly analyzes dosage issues and indications, that is, the correct drug may be entered, but the dosage may be entered incorrectly, or the drug name may be too complicated, resulting in entry errors. This solution aims to analyze dosage data and indications during the information entry process, thereby analyzing the anomalies in prescription information entry. The specific analysis process is described in the subsequent embodiments.

[0051] The dosage risk analysis module 102 is used to determine the dosage fluctuation risk level of each drug based on the numerical distribution and numerical fluctuation of dosage data of the same drug in all historical prescriptions.

[0052] It is understandable that different drugs have different dosage regulations. For example, a certain drug strictly stipulates that one tablet should be taken every day, and no more or less should be taken, while the dosage of a certain drug can be adjusted according to the condition of the disease. Therefore, the dosage regulations of different drugs are inconsistent, and a specific analysis of the risk level of dosage fluctuation is needed.

[0053] Furthermore, in some embodiments of the present invention, the dosage fluctuation risk level of each drug is determined based on the numerical distribution and numerical fluctuation of the dosage data of the same drug in all historical prescriptions, including: taking the difference between the maximum and minimum values ​​of the dosage data of the same drug in all historical prescriptions as the dosage distribution amplitude; taking the numerical variance of the dosage data of the same drug in all historical prescriptions as the dosage fluctuation index; and determining the dosage fluctuation risk level of the drug based on the dosage distribution amplitude and the dosage fluctuation index.

[0054] Among them, the range represents the range of distribution, that is, the larger the numerical value of the dose distribution amplitude, the larger the range of the daily dose of the drug can be distributed, the larger the dose range of the drug, and the smaller the risk. The numerical variance of the dose data represents the overall fluctuation. The larger the numerical variance, the greater the overall fluctuation. The physician has a higher authority to adjust the dose of the drug and the lower the risk.

[0055] Therefore, in an embodiment of the present invention, the dose fluctuation risk level of a drug is determined based on the dose distribution amplitude and the dose fluctuation index, including: calculating the product of the dose distribution amplitude and the dose fluctuation index, and normalizing the inverse of the product as the dose fluctuation risk level of the drug.

[0056] That is, the larger the values ​​of the dose distribution amplitude and the dose fluctuation index, the higher the risk of dose fluctuation, and the dose needs to be strictly controlled. At this time, if the dose changes, the probability of abnormality will be greater.

[0057] The efficacy mutual exclusion analysis module 103 is used to determine the degree of overlap of the efficacy of any two drugs based on the proportion of any two drugs appearing in the same historical prescription and the similarity of the indications of the two drugs; any one of the drugs in the prescription to be entered is used as the target drug, and based on the degree of overlap of the efficacy of the target drug and other drugs in the prescription to be entered, the efficacy mutual exclusion influence index of the target drug in the prescription to be entered is determined.

[0058] In the same prescription, pharmacists usually use combined drugs to treat different diseases, which leads to large differences in the dosage of some prescribed drugs compared to the dosage when used alone. The synergistic effect between general drugs requires strict pharmacokinetic analysis and clinical verification to obtain accurate results, but this plan considers the initial screening of pharmacists when entering the dosage of prescription drugs. Therefore, from the description relationship of the indications between the target drug and other drugs, the impact of other drugs on the risk of dosage differences of the target drug is determined.

[0059] Since the drug database generally records the drug indications in great detail, if the keywords in the indications descriptions of two drugs have the same or similar semantics, it can indicate that there is a certain synergistic effect between the two drugs, which will affect the drug dosage and cause a large difference between the drug dosage and the dosage used alone.

[0060] Furthermore, in some embodiments of the present invention, the degree of overlap of the therapeutic effects of two drugs is determined based on the proportion of any two drugs appearing in the same historical prescription and the similarity of the indications of the two drugs, including: forming a drug group with any two drugs, and taking the frequency of the drug group appearing in all historical prescriptions as the group frequency; calculating the ratio of the group frequency to the number of all historical prescriptions as the frequency overlap proportion; performing keyword extraction on the indications of the two drugs in the drug group respectively, determining the indication keywords of each drug, and taking the ratio of the number of repeated keywords in the two drugs to the total number of all keywords as the indication similarity index; calculating the product of the frequency overlap proportion and the indication similarity index, and normalizing the maximum and minimum values ​​as the degree of overlap of the therapeutic effects.

[0061] In the embodiment of the present invention, the drug group is determined and the frequency of occurrence in all historical prescriptions is recorded, because each drug group can only appear once in a prescription, that is, its essence is to determine the proportion of drug groups appearing in the prescription, which is used as the frequency overlap proportion. The higher the value of the frequency overlap proportion, the more it matches the historical prescription.

[0062] Among them, keyword extraction can be performed using the TF-IDF algorithm or the word2vec algorithm. The indications of the two drugs in the drug group are extracted separately to determine the indication keywords of each drug. For example, the indication of compound acetaminophen tablets is: suitable for relieving fever, headache, sore limbs, sneezing, runny nose, nasal congestion, sore throat and other symptoms caused by common cold and influenza. The extracted indication keywords are: [fever, headache, sore limbs, sneezing, runny nose, nasal congestion, sore throat]. Therefore, the ratio of the number of repeated keywords in the two drugs to the total number of all keywords is used as the indication similarity index. The larger the value of the indication similarity index, the more similar the indications of the two drugs are.

[0063] The product of the frequency overlap ratio and the indication similarity index is normalized to the maximum and minimum values ​​as the efficacy overlap. That is, the higher the frequency overlap ratio and the larger the value of the indication similarity index, the more frequently drugs with similar efficacy are used together, that is, the greater the efficacy overlap.

[0064] Furthermore, in some embodiments of the present invention, based on the degree of overlap in efficacy between the target drug and other drugs in the prescription to be entered, a mutually exclusive influence index of the efficacy of the target drug in the prescription to be entered is determined, including: calculating the mean of the degree of overlap in efficacy between the target drug and other drugs in the prescription to be entered, performing maximum and minimum value normalization processing, and obtaining the mutually exclusive influence index of the efficacy of the target drug.

[0065] Among them, the larger the mean value of the efficacy overlap, the more drugs with the same efficacy exist in the prescription, that is, the easier it is to produce mutually exclusive efficacy effects. The larger the value of the efficacy mutual exclusion influence index, the more strict the supervision of drug dosage entry in the prescription is needed.

[0066] The abnormality analysis module 104 is used to determine the degree of dosage abnormality based on the dosage data of each drug in the prescription to be entered and the dosage difference of the corresponding drug in all historical prescriptions, as well as the degree of dosage fluctuation risk; determine the abnormal usage probability of the corresponding drug in the prescription to be entered based on the mutually exclusive influence indicators of the efficacy of the same drug and the degree of dosage abnormality; determine the prescription abnormality probability of the prescription to be entered based on the abnormal usage probability of all drugs in the prescription to be entered, and determine whether the prescription to be entered needs to be entered based on the prescription abnormality probability.

[0067] It is understandable that the greater the difference between the dosage of a drug in a prescription and the dosage of the drug in the database, the higher the risk of abnormal input of the drug in the prescription. Therefore, the dosage abnormality degree is calculated by combining the dosage data of each drug with the dosage difference of the corresponding drug in all historical prescriptions and the dosage fluctuation risk degree.

[0068] Furthermore, in some embodiments of the present invention, the degree of dosage abnormality is determined based on the dosage difference between the dosage data of each drug in the prescription to be entered and the corresponding drug in all historical prescriptions, as well as the degree of dosage fluctuation risk, including: calculating the mean of the dosage data of each drug in all historical prescriptions as the historical dosage mean of the corresponding drug; taking the difference between the dosage data of any drug in the prescription to be entered and the historical dosage mean as the historical dosage difference index; and normalizing the product of the historical dosage difference index and the dosage fluctuation risk degree as the dosage abnormality degree.

[0069] Among them, the average of all dosage data belonging to the same drug in all historical prescriptions is taken to obtain the average level of the drug dosage. When the difference from the average level is large, it indicates that it is more abnormal. Therefore, the larger the value of the historical dosage difference index is, the more abnormal the dosage data of the corresponding drug in the prescription to be entered is.

[0070] Among them, the dose fluctuation risk degree represents the risk of dose fluctuation. The larger the value is, the higher the risk of dose data fluctuation is, that is, the dose change is more likely to be abnormal. Therefore, the product of the historical dose difference index and the dose fluctuation risk degree is normalized as the dose abnormality degree.

[0071] Furthermore, in some embodiments of the present invention, the abnormal usage probability of the corresponding drug in the prescription to be entered is determined based on the mutually exclusive influence index of the efficacy and the degree of abnormal dosage of the same drug, including: calculating the product of the mutually exclusive influence index of the efficacy and the degree of abnormal dosage, and normalizing it as the abnormal usage probability.

[0072] Among them, the larger the value of the efficacy mutual exclusion influence index, the more drugs with the same efficacy exist in the prescription, that is, the easier it is to produce efficacy mutual exclusion effect, and the larger the value of the dosage abnormality degree, the greater the difference between the dosage data and the historical prescription, and the higher the probability of dosage abnormality. Therefore, the product of the efficacy mutual exclusion influence index and the dosage abnormality degree is calculated and normalized as the usage abnormality probability.

[0073] Furthermore, in some embodiments of the present invention, the prescription abnormality probability of the prescription to be entered is determined based on the abnormal usage probability of all drugs in the prescription to be entered, including: taking the maximum value of the abnormal usage probability of all drugs in the prescription to be entered as the prescription abnormality probability of the prescription to be entered.

[0074] Among them, the probability of prescription abnormality also indicates the possibility that the prescription to be entered itself is abnormal. Since prescription errors cannot occur, in order to make the overall inspection more rigorous, a maximum analysis is performed directly, that is, the maximum value of the probability of abnormal use of all drugs in the prescription to be entered is taken as the probability of prescription abnormality of the prescription to be entered.

[0075] Determine whether the prescription to be entered needs to be entered based on the probability of prescription abnormality, including: when the probability of prescription abnormality is greater than a preset abnormality threshold, determine that the prescription to be entered is abnormal and suspend entry; when the probability of prescription abnormality is less than or equal to the preset abnormality threshold, determine that the prescription to be entered is normal and enter it.

[0076] The preset abnormality threshold is a threshold value of the probability of prescription abnormality. In an embodiment of the present invention, the preset abnormality threshold can be set based on input requirements. Optionally, the value of the preset abnormality threshold is 0.78.

[0077] It can be understood that the larger the value of the prescription abnormality probability is, the greater the abnormality of the corresponding prescription dosage is. Therefore, when the prescription abnormality probability is greater than the preset abnormality threshold, the prescription to be entered is determined to be abnormal. At this time, the entry can be suspended and it will be marked as an abnormal prescription for further analysis or manual review. When the prescription abnormality probability is less than or equal to the preset abnormality threshold, the prescription to be entered is determined to be normal. At this time, it can be directly entered into the prescription drug information related file of the drug database.

[0078] The present invention obtains dosage data and indications of different drugs in historical prescriptions and prescriptions to be entered, so as to analyze the prescriptions themselves for abnormalities during the information entry process according to the dosage data and indications, thereby timely finding prescriptions with abnormal medication, which is convenient for prescription tracing;

[0079] Furthermore, the dose fluctuation risk level of each drug is determined based on the numerical distribution and numerical fluctuation of the dose data of the same drug in all historical prescriptions. The dose fluctuation risk level can accurately characterize the impact of dose fluctuations. The dose abnormality level is determined by combining the dose data of each drug in the prescription to be entered with the dose difference of the corresponding drug in all historical prescriptions through the dose fluctuation risk, so as to analyze the specific values ​​of the dose. This scheme also analyzes the mutually exclusive effects between multiple drugs, that is, according to the similarity of the indications, the degree of overlap of the efficacy of two drugs is determined, and then according to the degree of overlap of the efficacy, the efficacy mutually exclusive influence index of the target drug in the prescription to be entered is determined. The efficacy mutually exclusive influence index can accurately analyze the mutually exclusive effects between drugs, and avoid the calculation of dose abnormality affected by the superposition of the efficacy of drugs and the mutual exclusion effect.

[0080] Finally, according to the mutually exclusive influencing index of efficacy and the degree of dosage abnormality, the abnormal use probability of the corresponding drug in the prescription to be entered is determined, and according to the abnormal use probability of all drugs in the prescription to be entered, the abnormal prescription probability of the prescription to be entered is determined, and according to the abnormal prescription probability, it is determined whether the prescription to be entered needs to be entered, that is, by analyzing the abnormal use probability of a single drug, and then combining the abnormal use probabilities of all drugs to obtain the abnormal prescription probability, it is convenient to enter and screen according to the abnormal prescription probability. In summary, the present invention can effectively improve the accuracy and reliability of the abnormal prescription probability analysis, so as to perform effective screening when entering information and avoid database pollution caused by abnormal prescription entry.

[0081] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A prescription drug information entry system for a Chinese and Western medicine combined drug database, characterized in that: The system comprises: The acquisition module is used to obtain the disease type in the prescription to be entered, as well as the historical prescriptions of the same disease type; determine the dosage data and indications of different drugs in the historical prescriptions and the prescriptions to be entered; The dosage risk analysis module is used to determine the dosage fluctuation risk level of each drug based on the numerical distribution and numerical fluctuation of the dosage data of the same drug in all historical prescriptions; The efficacy mutual exclusion analysis module is used to determine the degree of overlap of the efficacy of any two drugs based on the proportion of any two drugs appearing in the same historical prescription and the similarity of the indications of the two drugs; any drug in the prescription to be entered is used as the target drug, and the efficacy mutual exclusion impact index of the target drug in the prescription to be entered is determined based on the degree of overlap of the efficacy of the target drug and other drugs in the prescription to be entered; The abnormality analysis module is used to determine the degree of dosage abnormality based on the dosage difference between each drug in the prescription to be entered and the corresponding drug in all historical prescriptions, as well as the degree of dosage fluctuation risk; determine the abnormal use probability of the corresponding drug in the prescription to be entered based on the mutually exclusive influence index of the efficacy of the same drug and the degree of dosage abnormality; determine the abnormal use probability of the prescription to be entered based on the abnormal use probability of all drugs in the prescription to be entered, and determine whether the prescription to be entered needs to be entered based on the abnormal prescription probability; Determining the risk level of dosage fluctuation of each drug based on the numerical distribution and numerical fluctuation of dosage data of the same drug in all historical prescriptions includes: The difference between the maximum and minimum values ​​of the dosage data of the same drug in all historical prescriptions is taken as the dosage distribution amplitude; The numerical variance of the dosage data of the same drug in all historical prescriptions is used as the dosage fluctuation indicator; Determining the degree of risk of drug dosage fluctuation according to the dosage distribution amplitude and dosage fluctuation index; Determining the dose fluctuation risk level of a drug according to the dose distribution amplitude and the dose fluctuation index includes: Calculating the product of the dose distribution amplitude and the dose fluctuation index, and normalizing the inverse of the product as the dose fluctuation risk degree of the drug; The degree of overlap of the efficacy of two drugs is determined based on the proportion of any two drugs appearing in the same historical prescription and the similarity of the indications of the two drugs, including: Any two drugs are grouped into a drug group, and the frequency of the drug group appearing in all historical prescriptions is taken as the group frequency; The ratio of the group frequency to the number of all historical prescriptions was calculated as the frequency overlap ratio; Extract keywords from the indications of the two drugs in the drug group respectively, determine the indication keywords of each drug, and use the ratio of the number of repeated keywords in the two drugs to the total number of all keywords as the indication similarity index; The product of the frequency overlap ratio and the indication similarity index is calculated, and the maximum and minimum values ​​are normalized as the efficacy overlap.

2. A prescription drug information entry system for a Chinese and Western medicine combined drug database as claimed in claim 1, characterized in that: According to the degree of overlap between the efficacy of the target drug and other drugs in the prescription to be entered, the efficacy mutual exclusion impact index of the target drug in the prescription to be entered is determined, including: Calculate the mean of the overlap between the target drug and other drugs in the prescription to be entered, perform maximum and minimum value normalization, and obtain the target drug's mutually exclusive influence index of efficacy.

3. A prescription drug information entry system for a Chinese and Western medicine combined drug database as claimed in claim 1, characterized in that: Determine the degree of dosage abnormality based on the dosage data of each drug in the prescription to be entered and the dosage difference of the corresponding drug in all historical prescriptions, as well as the degree of dosage fluctuation risk, including: Calculate the mean of the dosage data of each drug in all historical prescriptions as the historical dosage mean of the corresponding drug; The difference between the dosage data of any drug in the prescription to be entered and the historical dosage mean is used as the historical dosage difference indicator; The product of the historical dose difference index and the dose fluctuation risk level is normalized and used as the dose abnormality level.

4. A prescription drug information entry system for a Chinese and Western medicine combined drug database as claimed in claim 1, characterized in that: According to the mutually exclusive influencing indicators of the efficacy of the same drug and the degree of abnormal dosage, the abnormal probability of the use of the corresponding drug in the prescription to be entered is determined, including: The product of the mutually exclusive efficacy impact index and the degree of dosage abnormality is calculated and normalized as the probability of abnormal use.

5. The Chinese and Western medicine combined medicine database prescription drug information entry system as claimed in claim 1, characterized in that: Determining the abnormal probability of the prescription to be entered according to the abnormal usage probability of all drugs in the prescription to be entered includes: The maximum value of the abnormal usage probabilities of all drugs in the prescription to be entered is used as the abnormal prescription probability of the prescription to be entered.

6. A prescription drug information entry system for a Chinese and Western medicine combined drug database as claimed in claim 1, characterized in that: The step of determining whether the prescription to be entered needs to be entered according to the probability of prescription abnormality includes: When the probability of prescription abnormality is greater than a preset abnormality threshold, the prescription to be entered is determined to be abnormal, and entry is suspended; When the probability of prescription abnormality is less than or equal to a preset abnormality threshold, the prescription to be entered is determined to be normal and is entered.

7. A prescription drug information entry system for a Chinese and Western medicine combined drug database as claimed in claim 6, characterized in that: The value of the preset abnormal threshold is 0.78.

Images