Screening and sorting method and system for main therapeutic drugs in medical prescriptions

By screening and calculating the weight value of medical pre-requisite medication information, screening out the main therapeutic medications and sorting them, the problem of low accuracy of recommendations for pre-requisite medications by traditional Chinese medicine in the existing technology is solved, and accurate recommendation of drugs is achieved.

CN114067945BActive Publication Date: 2025-04-25BEIJING JIAHE HAISEN HEALTH TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202111360649.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-17
Publication Date
2025-04-25
Estimated Expiration
2041-11-17

AI Technical Summary

Technical Problem

The accuracy of recommendations for pre-art Chinese medicine pre-order medications is low, which makes model learning complex and difficult to achieve high prediction accuracy.

Method used

By identifying and screening the medical pre-order information of the target medical record, the weight value of each drug under the admission diagnosis is calculated, the main treatment drugs are screened out, and the weight value is sorted according to the weight value.

Benefits of technology

Accurate recommendations of drugs for diagnosis and treatment plans have been achieved, the accuracy of recommendations for major therapeutic drugs has been improved, and the problem of low recommendation accuracy in the existing technology has been alleviated.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114067945B_ABST
    Figure CN114067945B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for screening and sorting the main therapeutic drugs in medical orders, including: identifying and screening the medical order drug information of the target medical record to obtain the medical order drug set of the target medical record; calculating the weight value of each drug in the medical order drug set under the admission diagnosis of the target medical record; based on the weight value, screening out the drugs belonging to the main therapeutic drugs in the medical order drug set to obtain the main therapeutic drug set; based on the weight value, sorting the drugs in the main therapeutic drug set. The present invention alleviates the technical problem of low accuracy of the recommendation of the main therapeutic drugs in the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of medical prescription drug screening, and in particular to a method and system for screening and sorting main therapeutic drugs in medical prescriptions. Background Art

[0002] Electronic medical records contain a comprehensive, detailed, timely and accurate description of individual patient health information, and contain a wealth of information and knowledge. Through in-depth analysis and mining of information in electronic medical records, a large amount of medical knowledge closely related to patients can be obtained, which can then be used to build clinical decision support systems and provide personalized health information services. For example, the core content of current medical artificial intelligence research is to recommend corresponding clinical diagnosis and treatment decision support based on changes in the condition of hospitalized patients at different time points based on electronic medical records.

[0003] When learning the doctor's prescription medication based on the electronic medical record, the drugs are obtained from the patient's hospitalization prescription. However, the medication in the prescription is all the drug information according to the doctor's condition during the patient's hospitalization, including functional medications, auxiliary medications, temporary medications and other types of drugs. Therefore, each patient will have several types of drug information during hospitalization or before each change in condition. If the model includes all drugs in the learning and recommendation, the complexity and difficulty of the model learning will be greatly increased due to the large number of labels, and thus a high prediction accuracy cannot be achieved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method and system for screening and sorting the main therapeutic drugs in medical orders, so as to alleviate the technical problem of low accuracy in recommending the main therapeutic drugs in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides a method for screening and sorting medical order main therapeutic drugs, comprising: identifying and screening medical order drug information of a target medical record to obtain a medical order drug set of the target medical record; calculating a weight value of each drug in the medical order drug set under the admission diagnosis of the target medical record; based on the weight value, screening out drugs that are main therapeutic drugs in the medical order drug set to obtain a main therapeutic drug set; and based on the weight value, sorting the drugs in the main therapeutic drug set.

[0006] Furthermore, the medical order and medication information of the target medical record is identified and screened to obtain the medical order and medication set of the target medical record, including: identifying the medical order and medication information of the target medical record to obtain all drugs related to the medical order and medication information to obtain a first drug set; screening out drugs whose order type is temporary orders in the first drug set, and screening out drugs whose drug category is non-primary therapeutic drugs, to obtain a second drug set; the non-primary therapeutic drugs include auxiliary drugs and supportive treatment drugs; screening out drugs whose use frequency is less than or equal to the preset frequency or whose use duration is less than or equal to the preset duration in the second drug set to obtain the medical order and medication set.

[0007] Further, calculating the weight value of each drug in the set of prescribed medications under the admission diagnosis of the target medical record includes: calculating the weight value of each drug under the corresponding admission diagnosis by the following formula: IMPT NB =log(p(x i =1|y j =1))-log(p(x i =1|y j =0)); where IMPT NB is the weight value, log(p(x i =1|y j =1)) is the diagnosis of admission y j Conditional drugs x i The logarithmic probability value, log(p(x i =1|y j =0)) means no admission diagnosis y j Conditional drugs x i The logarithmic probability value of .

[0008] Furthermore, based on the weight value, drugs that are main therapeutic drugs are screened out from the medical order drug set to obtain the main therapeutic drug set, including: screening out drugs whose weight values ​​are less than a preset threshold from the medical order drug set to obtain a third drug set, and screening out drugs whose weight values ​​are greater than or equal to the preset threshold to obtain a fourth drug set; from the third drug set, screening out drugs whose indications are consistent with the admission diagnosis of the target medical record to obtain a fifth drug set; and taking the sum of the fourth drug set and the fifth drug set as the main therapeutic drug set.

[0009] Furthermore, based on the weight value, the drugs in the main therapeutic drug set are sorted, including: sorting the drugs in the main therapeutic drug set in descending order according to the corresponding weight values.

[0010] In a second aspect, an embodiment of the present invention further provides a system for screening and sorting medical orders for major therapeutic drugs, comprising: an identification module, a calculation module, a screening module and a sorting module; wherein the identification module is used to identify and screen the medical order medication information of the target medical record to obtain the medical order medication set of the target medical record; the calculation module is used to calculate the weight value of each drug in the medical order medication set under the admission diagnosis of the target medical record; the screening module is used to screen out the drugs that are major therapeutic drugs in the medical order medication set based on the weight value to obtain the major therapeutic drug set; the sorting module is used to sort the drugs in the major therapeutic drug set based on the weight value.

[0011] Furthermore, the calculation module is also used to calculate the weight value of each drug under the corresponding admission diagnosis by the following formula: IMPT NB =log(p(x i =1|y j =1))-log(p(x i =1|y j =0)); where IMPT NB is the weight value, log(p(x i =1|y j =1)) is the diagnosis of admission y j Conditional drugs x i The logarithmic probability value, log(p(x i =1|y j =0)) means no admission diagnosis y j Conditional drugs x i The logarithmic probability value of .

[0012] Furthermore, the screening module is also used to: screen out the drugs whose weight values ​​are less than a preset threshold in the medical prescription medication set to obtain a third drug set, and screen out the drugs whose weight values ​​are greater than or equal to the preset threshold to obtain a fourth drug set; in the third drug set, screen out the drugs whose drug indications are consistent with the admission diagnosis of the target medical record to obtain a fifth drug set; and use the sum of the fourth drug set and the fifth drug set as the main treatment drug set.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0014] In a fourth aspect, an embodiment of the present invention further provides a computer-readable medium having a non-volatile program code executable by a processor, wherein the program code enables the processor to execute the method described in the first aspect.

[0015] The present invention provides a method and system for screening and sorting the main therapeutic drugs in medical orders, which can identify and screen the medical order medication information in medical records, and further screen out the main therapeutic drugs according to the weight value of the drugs to the admission diagnosis, and can make an importance ranking according to the correlation between the drugs and the admission diagnosis, so as to achieve accurate recommendation of drugs for diagnosis and treatment plans, and alleviate the technical problem of low accuracy of recommendation of main therapeutic drugs in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of a method for screening and sorting main therapeutic drugs in a doctor's order provided by an embodiment of the present invention;

[0018] Figure 2 A schematic diagram of a system for screening and sorting primary therapeutic medications in medical prescriptions provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Embodiment 1:

[0021] Figure 1 1 is a flow chart of a method for screening and sorting the main treatment drugs in a doctor's prescription provided according to an embodiment of the present invention. Figure 1 As shown, the method specifically comprises the following steps:

[0022] Step S102, identifying and screening the medical prescription and medication information of the target medical record to obtain the medical prescription and medication set of the target medical record.

[0023] In the embodiment of the present invention, the target medical record is an electronic medical record, and the target medical record includes hospitalization medical order information. The hospitalization medical order information is the doctor's instructions to the patient on diet, medication, laboratory tests, etc. according to the patient's condition and treatment needs during hospitalization, including three categories: long-term medical order, temporary medical order, and standby medical order. The medical order medication set is a set of medicines in the hospitalization medical order information.

[0024] Step S104, calculating the weight value of each drug in the set of prescribed medications under the admission diagnosis of the target medical record.

[0025] Specifically, the weight value of each drug under the corresponding admission diagnosis is calculated by the following formula:

[0026] IMPT NB =log(p(x i =1|y j =1))-log(p(x i =1|y j =0));

[0027] Among them, IMPT NB is the weight value, log(p(x i =1|y j =1)) is the diagnosis of admission y j Conditional drugs x i The logarithmic probability value, log(p(x i =1|y j =0)) means no admission diagnosis y j Conditional drugs x i The logarithmic probability value of . Among them, i and j are the drug number and admission diagnosis number respectively.

[0028] Step S106, based on the weight value, screen out the drugs that are main treatment drugs in the set of prescribed drugs to obtain the set of main treatment drugs.

[0029] Step S108, sorting the drugs in the main therapeutic drug set based on the weight values.

[0030] The present invention provides a method for screening and sorting the main therapeutic drugs in medical orders, which can identify and screen the medical order medication information in medical records, and further screen out the main therapeutic drugs according to the weight value of the drugs to the admission diagnosis, and can rank the importance of the drugs according to the correlation between the drugs and the admission diagnosis, so as to achieve accurate recommendation of drugs for diagnosis and treatment plans, and alleviate the technical problem of low accuracy of recommendation of main therapeutic drugs in the prior art.

[0031] Optionally, step S102 specifically includes the following steps:

[0032] Step S1021, identifying the medical prescription medication information of the target medical record, obtaining all the drugs related to the medical prescription medication information, and obtaining a first drug set;

[0033] Step S1022, screening out drugs whose prescription type is temporary prescription and drugs whose drug category is non-primary therapeutic drugs in the first drug set, to obtain a second drug set; non-primary therapeutic drugs include auxiliary drugs and supportive treatment drugs; wherein the drug category can be obtained from a preset drug knowledge base;

[0034] Step S1023, in the second drug set, the drugs with a medication frequency less than or equal to a preset frequency or a medication duration less than or equal to a preset duration are screened out to obtain a set of prescribed medications. For example, drugs with a medication frequency less than or equal to 1 time and a medication duration less than or equal to 3 days are screened out, wherein the preset medication frequency and the preset medication duration are determined according to medical expert advice or statistical methods.

[0035] In an embodiment of the present invention, through the method in the above steps S1021-S1023, the medical prescription medication information in the medical record can be preliminarily screened, and non-primary therapeutic drugs can be determined by category, which can reduce the complexity of subsequent screening and help improve the accuracy of subsequent screening.

[0036] Specifically, step S106 also includes the following steps:

[0037] Step S1061, screening out drugs with weight values ​​less than a preset threshold value from the set of prescribed drugs to obtain a third drug set, and screening out drugs with weight values ​​greater than or equal to the preset threshold value to obtain a fourth drug set;

[0038] Step S1062, screening out drugs whose drug indications are consistent with the admission diagnosis of the target medical record from the third drug set, to obtain a fifth drug set; wherein the drug indications can be obtained by calling a preset drug knowledge base;

[0039] Step S1063, taking the sum of the fourth drug set and the fifth drug set as the main treatment drug set.

[0040] In an embodiment of the present invention, for the screening process of the main therapeutic drugs in the doctor's order, the drugs in the doctor's order drug set are first divided into a main treatment drug set (i.e., the fourth drug set) and a screened drug set (i.e., the third drug set) according to a preset threshold, and then from the screened drug set, it is checked whether the indication of each drug is consistent with the admission diagnosis of the target medical record, and then the consistent drug set (i.e., the fifth drug set) is also divided into the main treatment drug set, that is, the fifth drug set is merged with the fourth drug set to obtain the final main therapeutic drug set.

[0041] Optionally, sorting the drugs in the main therapeutic drug set includes: sorting the drugs in the main therapeutic drug set in descending order according to corresponding weight values.

[0042] From the above description, it can be seen that an embodiment of the present invention provides a method for screening and ranking the main therapeutic drugs in medical orders. By screening and ranking the drugs based on the weight values ​​of the drugs related to the admission diagnosis, a set of main therapeutic drugs in the medical orders ranked by relative importance can be obtained, so that the diagnosis and treatment plan based on this method can achieve more accurate prediction and evaluation indicators based on relative importance, alleviating the technical problem of low accuracy of recommendation of main therapeutic drugs in the prior art.

[0043] Embodiment 2:

[0044] Figure 2 Schematic diagram of a system for screening and sorting the main treatment drugs in medical prescriptions provided according to an embodiment of the present invention. Figure 2 As shown, the system includes: an identification module 10, a calculation module 20, a screening module 30 and a sorting module 40.

[0045] Specifically, the identification module 10 is used to identify and screen the medical prescription and medication information of the target medical record to obtain the medical prescription and medication set of the target medical record.

[0046] The calculation module 20 is used to calculate the weight value of each drug in the set of medical prescriptions under the admission diagnosis of the target medical record.

[0047] The screening module 30 is used to screen out the drugs belonging to the main treatment drugs in the medical prescription drug set based on the weight value to obtain the main treatment drug set.

[0048] The sorting module 40 is used to sort the drugs in the main therapeutic drug set based on the weight values.

[0049] The present invention provides a system for screening and sorting medical prescriptions for major therapeutic drugs, which can identify and screen medical prescription medication information in medical records, and further screen out major therapeutic drugs according to the weight values ​​of the drugs to the admission diagnosis, and can rank the importance of the drugs according to the correlation between the drugs and the admission diagnosis, so as to achieve accurate recommendations for drugs in diagnosis and treatment plans, alleviating the technical problem of low accuracy in recommending major therapeutic drugs in the prior art.

[0050] Specifically, the identification module 10 is also used to: identify the medical order medication information of the target medical record, obtain all the drugs related to the medical order medication information, and obtain a first drug set; screen out the drugs whose order type is temporary medical order in the first drug set, and screen out the drugs whose drug category is non-primary therapeutic drugs, and obtain a second drug set; non-primary therapeutic drugs include auxiliary drugs and supportive treatment drugs; screen out the drugs in the second drug set whose frequency of use is less than or equal to the preset frequency or whose use duration is less than or equal to the preset duration, and obtain a medical order medication set.

[0051] Optionally, the computing module 20 is further configured to:

[0052] The weight value of each drug under the corresponding admission diagnosis is calculated by the following formula:

[0053] IMPT NB =log(p(x i =1|y j =1))-log(p(x i =1|y j =0));

[0054] Among them, IMPT NB is the weight value, log(p(x i =1|y j =1)) is the diagnosis of admission y j Conditional drugs x i The logarithmic probability value, log(p(x i =1|y j =0)) means no admission diagnosis y j Conditional drugs x i The logarithmic probability value of .

[0055] Optionally, the screening module 30 is also used to: screen out drugs whose weight values ​​are less than a preset threshold in the medical prescription medication set to obtain a third drug set, and screen out drugs whose weight values ​​are greater than or equal to the preset threshold to obtain a fourth drug set; in the third drug set, screen out drugs whose drug indications are consistent with the admission diagnosis of the target medical record to obtain a fifth drug set; and use the sum of the fourth drug set and the fifth drug set as the main treatment drug set.

[0056] Optionally, the sorting module 40 is further used to sort the drugs in the main therapeutic drug set in descending order according to the corresponding weight values.

[0057] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method in the first embodiment when executing the computer program.

[0058] The embodiment of the present invention further provides a computer-readable medium having a non-volatile program code executable by a processor, wherein the program code enables the processor to execute the method in the above-mentioned embodiment 1.

[0059] 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 with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for screening and sorting the main therapeutic drugs in medical prescriptions, characterized in that: include: Identify and filter the medical prescription medication information of the target medical record to obtain the medical prescription medication set of the target medical record; Calculate the weight value of each drug in the set of prescribed medications under the admission diagnosis of the target medical record; Based on the weight value, screening out drugs belonging to main therapeutic drugs from the set of prescribed drugs to obtain a set of main therapeutic drugs; Based on the weight values, the drugs in the set of primary therapeutic drugs are sorted; Calculating the weight value of each drug in the set of prescribed medications under the admission diagnosis of the target medical record, including: The weight value of each drug under the corresponding admission diagnosis is calculated by the following formula: IMPT NB =log(p(x i =1|y j =1))-log(p(x i =1|y j =0)); Among them, IMPT NB is the weight value, log(p(x i =1|y j =1)) is the diagnosis of admission y j Conditional drugs x i The logarithmic probability value, log(p(x i =1|y j =0)) means no admission diagnosis y j Conditional drugs x i The logarithmic probability value of .

2. The method according to claim 1, characterized in that: Identify and filter the medical prescription medication information of the target medical record to obtain the medical prescription medication set of the target medical record, including: Identify the medical prescription medication information of the target medical record, obtain all drugs related to the medical prescription medication information, and obtain a first drug set; Screening out drugs whose prescription type is temporary prescription in the first drug set and drugs whose drug category is non-primary therapeutic drugs, to obtain a second drug set; the non-primary therapeutic drugs include auxiliary drugs and supportive treatment drugs; The drugs whose medication frequency is less than or equal to the preset frequency or whose medication duration is less than or equal to the preset duration are screened out from the second drug set to obtain the doctor's prescription medication set.

3. The method according to claim 1, characterized in that Based on the weight value, the drugs belonging to the main therapeutic drugs are screened out from the set of prescribed drugs to obtain the set of main therapeutic drugs, including: Screening out drugs whose weight values ​​are less than a preset threshold value from the set of prescribed drugs to obtain a third drug set, and screening out drugs whose weight values ​​are greater than or equal to the preset threshold value to obtain a fourth drug set; In the third drug set, drugs whose drug indications are consistent with the admission diagnosis of the target medical record are screened out to obtain a fifth drug set; The sum of the fourth drug set and the fifth drug set is used as the main therapeutic drug set.

4. The method according to claim 1, characterized in that: Based on the weight value, the drugs in the main therapeutic drug set are sorted, including: The drugs in the main therapeutic drug set are sorted in descending order according to the corresponding weight values.

5. A system for screening and sorting the main treatment drugs in medical prescriptions, characterized in that: include: Identification module, calculation module, screening module and sorting module; among them, The identification module is used to identify and screen the medical prescription medication information of the target medical record to obtain the medical prescription medication set of the target medical record; The calculation module is used to calculate the weight value of each drug in the set of prescribed medications under the admission diagnosis of the target medical record; The screening module is used to screen out the drugs belonging to the main therapeutic drugs from the set of prescribed drugs based on the weight values ​​to obtain the set of main therapeutic drugs; The sorting module is used to sort the drugs in the main therapeutic drug set based on the weight value; The computing module is further used for: The weight value of each drug under the corresponding admission diagnosis is calculated by the following formula: IMPT NB =log(p(x i =1|y j =1))-log(p(x i =1|y j =0)); Among them, IMPT NB is the weight value, log(p(x i =1|y j =1)) is the diagnosis of admission y j Conditional drugs x i The logarithmic probability value, log(p(x i =1|y j =0)) means no admission diagnosis y j Conditional drugs x i The logarithmic probability value of .

6. The system according to claim 5, characterized in that The screening module is further used for: Screening out drugs whose weight values ​​are less than a preset threshold value from the set of prescribed drugs to obtain a third drug set, and screening out drugs whose weight values ​​are greater than or equal to the preset threshold value to obtain a fourth drug set; In the third drug set, drugs whose drug indications are consistent with the admission diagnosis of the target medical record are screened out to obtain a fifth drug set; The sum of the fourth drug set and the fifth drug set is used as the main therapeutic drug set.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer-readable medium having a non-volatile program code executable by a processor, characterized in that: The program code enables the processor to execute the method according to any one of claims 1 to 4.

Citation Information

Patent Citations

  • Medication recommendation method and device based on sorting algorithm, equipment and storage medium

    CN113436746A