Method, device, electronic device and computer medium for determining pharmaceutical codes

By extracting key information from drug instruction manuals and using a pre-created code transposition index, the method addresses the complexity and inaccuracy of ATC code prediction, enabling accurate and automated coding for both new and existing drugs.

JP7577227B2Active Publication Date: 2024-11-01BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2023553759
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2021-01-15
Filing Date
2021-12-15
Publication Date
2024-11-01
Estimated Expiration
2041-12-15

AI Technical Summary

Technical Problem

Predicting a drug's Anatomical Therapeutic Chemical (ATC) code from its molecular formula structure is complex and inaccurate, and current methods are limited to newly developed drugs, failing to provide accurate coding for existing drugs.

Method used

A method and apparatus for determining drug codes by extracting key information from instruction manuals, using a pre-created code transposition index to screen for ATC codes based on drug ingredients and indications, employing natural language processing and a pre-trained classification model to enhance accuracy.

Benefits of technology

Enables accurate and automated ATC coding for both new and existing drugs, simplifying the process and providing reliable coding information for medical information systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007577227000003
    Figure 0007577227000003
  • Figure 0007577227000004
    Figure 0007577227000004
  • Figure 0007577227000005
    Figure 0007577227000005
Patent Text Reader

Abstract

A method and apparatus for determining a drug code, which relates to the field of artificial intelligence technology, includes the steps of: obtaining a drug instruction text (201); extracting key information of the drug from the instruction text (202); obtaining at least one code related to the key information of the drug and ingredients corresponding to each code (203) based on a pre-created code transposition index; and obtaining an Anatomical and Therapeutic Classification System code of the drug by screening the at least one code based on the key information of the drug and ingredients corresponding to each code (204). This method can improve the efficiency of searching drug codes.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] <CROSS REFERENCE TO RELATED APPLICATIONS> This disclosure claims priority to a Chinese patent application filed on January 15, 2021, bearing application number 202110054078.1 and entitled "Method, Apparatus, Electronic Device and Computer Medium for Determining Pharmaceutical Code," the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to the field of computer technology, specifically to the field of artificial intelligence technology, and in particular to methods, apparatus, electronic devices, computer readable media and computer program products for determining pharmaceutical codes. [Background technology]

[0003] The Anatomical Therapeutic Chemical Classification (ATC) system is the World Health Organization's official classification system for drugs. With the progress of medical information system construction, medical institutions, health insurance bureaus and health insurance institutions at all levels are gradually establishing drug precision management systems based on the ATC code system.

[0004] Currently, ATC codes for drugs are generally obtained by predicting the molecular formula structure of a drug using a classification algorithm, but predicting the ATC code of a drug from its molecular formula structure is a complex and low-precision technique and cannot be applied to drugs other than newly developed drugs. Summary of the Invention [Means for solving the problem]

[0005] Embodiments of the present disclosure provide methods, apparatus, electronic devices, computer readable media and computer program products for determining pharmaceutical codes.

[0006] In a first aspect, embodiments of the present disclosure provide a method for determining a pharmaceutical code, the method comprising: obtaining a drug product instruction text; Extracting key information of the medicine from the instruction text; Obtaining at least one code related to the key information of the medicine and ingredients corresponding to each code based on a previously created code transposition index; and obtaining an Anatomical and Therapeutic Classification System code for the drug by screening at least one code based on the drug's key information and the ingredients corresponding to each code.

[0007] In some embodiments, the drug key information includes a pharmaceutical ingredient, and obtaining an Anatomical Therapeutic Classification System code for the drug by screening at least one code based on the drug key information and the ingredients corresponding to each code includes: For each of at least one code, detecting whether an ingredient corresponding to the code satisfies one of a plurality of rules having a priority determined based on pharmaceutical ingredients, and in response to determining that the ingredient corresponding to the code satisfies one of the plurality of rules and that detection of all codes has been completed, determining a candidate code for initial screening that includes the code; In response to determining that the initial screening candidate code has only one, determining that the initial screening candidate code is an Anatomical Therapeutic Classification System code of the drug.

[0008] In some embodiments, the rules are sorted from high to low priority as follows: 1) When there are two or more pharmaceutical ingredients, the ingredients corresponding to the code include all the pharmaceutical ingredients of the drug. 2) If there are two or more pharmaceutical ingredients, the ingredient corresponding to the code contains at least one pharmaceutical ingredient of the drug and contains the word "compound". 3) If there are two or more pharmaceutical ingredients, the ingredient corresponding to the code contains at least one pharmaceutical ingredient of the drug and does not contain the word "compound". 4) If there is one type of pharmaceutical ingredient, the ingredient corresponding to the code includes the pharmaceutical ingredient.

[0009] In some embodiments, the drug key information includes a pharmaceutical ingredient, and obtaining an Anatomical Therapeutic Classification System code for the drug by screening at least one code based on the drug key information and the ingredients corresponding to each code includes: For each of the at least one code, detecting whether the ingredient corresponding to the code matches a pharmaceutical ingredient; In response to determining that the component corresponding to the code matches the pharmaceutical component and that detection of all codes has been completed, obtaining a candidate code for initial screening that includes the code; In response to determining that the initial screening candidate code has only one, determining that the initial screening candidate code is an Anatomical Therapeutic Classification System code of the drug.

[0010] In some embodiments, the drug key information further comprises an indication for the drug, and obtaining an Anatomical Therapeutic Classification System code for the drug by screening at least one code based on the drug key information and the ingredients corresponding to each code includes: determining a disease type corresponding to the drug based on an indication for the drug in response to determining that the initial screening candidate code is a plurality of codes; The method further includes a step of screening a code corresponding to a disease type from the initial screening candidate codes as an Anatomical Therapeutic Classification System code of the drug.

[0011] In some embodiments, determining a disease type corresponding to the drug product based on an indication for the drug product comprises employing a pre-trained classification model to perform disease classification on the indication to obtain a disease type output by the classification model.

[0012] In a second aspect, an embodiment of the present disclosure provides an apparatus for determining a pharmaceutical code, the apparatus comprising: an acquisition unit configured to acquire a prescription text for the medicine; an extraction unit configured to extract key information of the medicine in the instruction text; An acquisition unit configured to acquire at least one code related to key information of a medicine and ingredients corresponding to each code according to a pre-created code transposition index; and a screening unit configured to obtain an Anatomical Therapeutic Classification System code of the drug by screening at least one code based on the key information of the drug and ingredients corresponding to each code.

[0013] In some embodiments, the key information of the drug includes a drug ingredient, and the screening unit comprises: a detection module configured to detect, for each of at least one code, whether an ingredient corresponding to the code satisfies one of a plurality of rules having a priority determined based on the pharmaceutical ingredient; an initial screening module configured to determine, in response to determining that a component corresponding to the code satisfies one of a plurality of rules and that detection of all codes has been completed, a candidate code for initial screening that includes the code; and a decision module configured to determine, in response to determining that the initial screening candidate code has only one, that the initial screening candidate code is an Anatomical Therapeutic Classification System code of the drug.

[0014] In some embodiments, the rules are sorted from high to low priority as follows: 1) When there are two or more pharmaceutical ingredients, the ingredients corresponding to the code include all the pharmaceutical ingredients of the drug. 2) If there are two or more pharmaceutical ingredients, the ingredient corresponding to the code contains at least one pharmaceutical ingredient of the drug and contains the word "compound". 3) If there are two or more pharmaceutical ingredients, the ingredient corresponding to the code contains at least one pharmaceutical ingredient of the drug and does not contain the word "compound". 4) If there is one type of pharmaceutical ingredient, the ingredient corresponding to the code includes the pharmaceutical ingredient.

[0015] In some embodiments, the key information of the drug includes a drug ingredient, and the screening unit comprises: a matching module configured to detect, for each of the at least one code, whether an ingredient corresponding to the code matches a pharmaceutical ingredient; A response module configured to obtain an initial screening candidate code including the code in response to determining that the component corresponding to the code matches the pharmaceutical component and that detection of all codes has been completed; and a coding module configured to determine, in response to determining that the initial screening candidate code has only one, that the initial screening candidate code is an Anatomical Therapeutic Classification System code of the drug.

[0016] In some embodiments, the key information of the drug further comprises an indication for the drug, and the screening unit: a classification module configured to determine a disease type corresponding to the drug based on an indication for the drug in response to determining that the initial screening candidate code is a plurality of codes; and a validation module configured to screen codes corresponding to disease types from the initial screening candidate codes as Anatomical Therapeutic Classification System codes of the medicine.

[0017] In some embodiments, the classification module is further configured to employ a pre-trained classification model to perform disease classification on the indication, thereby obtaining a disease type output by the classification model.

[0018] In a third aspect, an embodiment of the present disclosure provides an electronic device, the electronic device including one or more processors and a storage device in which one or more programs are stored, the one or more processors implementing a method described in any one of the implementation methods of the first aspect when the one or more programs are executed by the one or more processors.

[0019] In a fourth aspect, an embodiment of the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method as set forth in any one of the implementations of the first aspect.

[0020] In a fifth aspect, an embodiment of the present disclosure provides a computer program product comprising a computer program, which when executed by a processor, implements a method as set forth in any one of the implementations of the first aspect.

[0021] The method and apparatus for determining drug codes provided by the embodiments of the present disclosure first obtain the drug instruction text, then extract the key information of the drug in the instruction text, then obtain at least one code related to the key information of the drug and the ingredients corresponding to each code based on the pre-created code transposition index, and finally obtain the Anatomical Therapeutic Chemical Classification System code of the drug by screening at least one code based on the key information of the drug and the ingredients corresponding to each code. In this way, the ATC coding can be automatically performed for the drug based on the drug instruction text through the pre-created code transposition index, which can solve many pharmacists' work difficulties and provide coding basic information for medical information systems. [Brief description of the drawings]

[0022] Other features, objects and advantages of the present disclosure will become more apparent from a reading of the following detailed description of non-limiting embodiments, which is given with reference to the drawings, in which: [Figure 1] FIG. 1 illustrates an exemplary system architecture to which an embodiment of the present disclosure may be applied. [Diagram 2] 1 is a flow chart of one embodiment of a method for determining a pharmaceutical code according to the present disclosure. [Diagram 3] 1 is a flow chart of one embodiment of a method for deriving an Anatomical Therapeutic Classification System code for a drug according to the present disclosure. [Figure 4] 1 is a flow chart of another embodiment of a method for deriving an Anatomical Therapeutic Classification System code for a drug according to the present disclosure. [Diagram 5] 1 is a structural schematic diagram of an embodiment of an apparatus for determining a pharmaceutical code according to the present disclosure; [Figure 6] FIG. 1 is a structural schematic diagram of an electronic device suitable for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] The present disclosure will be described in more detail below with reference to the drawings and embodiments. It can be understood that the specific embodiments described in this specification are only used to describe the related invention and do not limit the invention. For convenience of description, only parts related to the invention are shown in the drawings.

[0024] In addition, the embodiments and features of the embodiments of the present disclosure can be combined with each other if there is no contradiction. Hereinafter, the present disclosure will be described in detail in conjunction with the embodiments with reference to the drawings.

[0025] FIG. 1 illustrates an exemplary system architecture 100 in which the methods for determining drug codes of the present disclosure can be applied.

[0026] 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, and may generally include wireless communication links, etc.

[0027] The terminal devices 101, 102, 103 interact with a server 105 via a network 104 to receive or send messages etc. The terminal devices 101, 102, 103 may have various communication client applications installed, such as instant messaging tools, mailbox clients etc.

[0028] The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be user devices having communication and control functions, and the user devices can communicate with the server 105. When the terminal devices 101, 102, 103 are software, they may be installed in the user devices, and the terminal devices 101, 102, 103 may be realized as multiple software or software modules (e.g., software or software modules for providing distributed services) or as a single software or software module. There is no particular limitation here.

[0029] The server 105 may be a server that provides various services, such as a back-end server for determining drug codes to support the drug processing systems of the terminal devices 101, 102, and 103. The back-end server can analyze and process the instruction texts of drugs in the network and feed back the processing results (e.g., the determined ATC codes) to the terminal devices.

[0030] The server may be hardware or software. If the server is hardware, it may be realized as a distributed server cluster consisting of multiple servers, or as a single server. If the server is software, it may be realized as multiple pieces of software or software modules (e.g., software or software modules for providing distributed services), or as a single piece of software or software module. There are no particular limitations here.

[0031] It should be noted that the method for determining a pharmaceutical code provided by an embodiment of the present disclosure is generally performed by the server 105 .

[0032] It should be understood that the number of terminal devices, networks, and servers in Figure 1 is merely exemplary, and any number of terminal devices, networks, and servers may be included according to the needs of the implementation.

[0033] In some optional implementation methods of this embodiment, as shown in FIG. 2, which shows a flow 200 of one embodiment of a method for determining a drug code according to the present disclosure, the method for determining a drug code includes the following steps:

[0034] In step 201, the instruction manual text for the medicine is obtained.

[0035] In this embodiment, the drug instructions refer to a legal document containing key information about the drug, and are legal guidelines for selecting a drug. Accurately reading and understanding the instructions before using the drug is a prerequisite for safe use of the drug. The drug instructions include the name, specifications, manufacturer, validity period, usage, dosage, drug ingredients, indications or functions / main treatment, contraindications, side effects, and precautions of the drug. Here, the drug name includes generic name, trade name, English name, chemical name, etc. In general, if the user is clear about the generic name of the drug, they can avoid using the drug repeatedly. The drug instructions text is a text for indicating the contents of the drug instructions.

[0036] The executing entity that executes the method for determining a pharmaceutical code can obtain the instruction text by various means, such as obtaining the instruction text in real time from a terminal or reading the instruction text from memory, but this embodiment is not limited to this.

[0037] In step 202, key information of the drug is extracted from the instruction text.

[0038] In this embodiment, by acquiring the instruction text of the drug, the instruction text can be processed in natural language to obtain key information of the drug. The key information of the drug includes drug ingredients or information related to the drug ingredients, and the information related to the drug ingredients includes the drug name, the drug's indications or functions / main treatment, contraindications, side effects, etc. In this embodiment, the drug ingredients may be the main ingredient of the drug.

[0039] Natural language processing technology is currently widely used in scenes in daily life that require semantic understanding. For example, entity recognition technology can recognize entities in text (such as drug names, disease names, and treatment methods), so that the contents of diagnosis, prescriptions, etc. in doctor's instructions can be automatically analyzed, and medical information can be managed in a structured manner. For example, text classification technology can be applied to intelligent triage scenes, so that the patient's description of the condition can be intelligently analyzed, and the examination room can be assigned with high accuracy based on the description information of the condition, thereby improving the efficiency of triage. The combination of natural language processing technology and medical scenes can improve the intelligence of medical scenes and provide users with a good experience.

[0040] In this embodiment, natural language processing can be used to extract pharmaceutical ingredients, pharmaceutical product names, pharmaceutical indications or functions, main indications, contraindications, side effects, etc. from the instruction text. In pharmaceutical instructions, pharmaceutical ingredients are generally included in natural language written in text segments, for example: This product is a compound formulation, containing 10 mg of clindamycin hydrochloride (calculated on the basis of clindamycin) and 8 mg of metronidazole per ml. The excipients are glycerol and ethanol. A natural language processing model (such as a named entity recognition model) can extract the main ingredients therein (non-auxiliary ingredients or excipients), and for the above instruction text, the pharmaceutical ingredients extracted by the natural language processing model include clindamycin hydrochloride, metronidazole, glycerol, and ethanol.

[0041] Optionally, a natural language model consisting of BERT (Bidirectional Encoder Representation from Transformers) + CRF (conditional random field) can be adopted for training to obtain a named entity recognition model for performing entity recognition of the trained pharmaceutical ingredients. The named entity recognition model is used to obtain the key information of the pharmaceutical. In actual operation, the recognition result accuracy of the named entity recognition model can approach 90%, which can fully meet the requirements of actual clinical use.

[0042] According to the differences in the properties and characteristics of medicines, medicines are divided into compound drugs and single-formula drugs. Single-formula drugs refer to single-ingredient drug preparations, and single-formula drugs mainly contain one pharmaceutical ingredient. Compound drugs refer to preparations that mix two or more kinds of drugs, and may be Chinese herbal medicines, Western medicines, or a mixture of Chinese herbal medicines and Western medicines. Compound drugs contain two or more kinds of pharmaceutical ingredients. In this embodiment, for the above different types of medicines, the pharmaceutical ingredients in the key information of the medicine may refer to one type or multiple types.

[0043] In step 203, at least one code related to the key information of the medicine and ingredients corresponding to each code are obtained based on the code transposition index created in advance.

[0044] In this embodiment, the code transposition index is an index library created before extracting key information of a drug from the instruction manual text, and the code transposition index can be reused after being created only once.

[0045] In this embodiment, the created code transposition index is determined based on the code of the medicine that needs to be determined, and the method for determining the code of the medicine provided by the present disclosure is used to determine the ATC code of the medicine, so that the code transposition index can classify the information (ATC Chinese name, ATC English name, ATC code) in the ATC code classification standard defined by the World Health Organization, and transpose the index for each group, for example, to obtain the code transposition index shown in Table 1. Table 1 includes the ATC code and the Chinese and English names of the chemical substances corresponding to the ATC code, where the chemical substances are also pharmaceutical ingredients, that is, the pharmaceutical ingredients corresponding to the ATC code. For example, the English name corresponding to "ticlatone" is "ticlatone", and the ATC code corresponding to "ticlatone" is "D01AE08".

[0046] In addition, since there may be one type of pharmaceutical ingredient or multiple types, there will always be multiple corresponding ATC codes for multiple types of pharmaceutical ingredients, and there may be multiple corresponding ATC codes for one type of pharmaceutical ingredient. For example, in Table 1, ATC codes that can correspond to the ATC codes for drugs including "Tegaful" include "L01BC03" and "L01BC53".

[0047] [Table 1]

[0048] JPEG0007577227000002.jpg64170

[0049] In addition, the number of ATC codes returned by the search engine software can also be set. All pharmaceutical ingredients in the key information of the drug obtained in step 202 are put into the code transposition index to find the code or the ingredients corresponding to the code related thereto, and for each pharmaceutical ingredient, the number of the maximum returned code or the ingredients corresponding to the code can be set to n (n>1), for example, n is set to 10.

[0050] In step 204, an Anatomical Therapeutic Classification System code of the drug is obtained by screening at least one code based on the key information of the drug and the ingredients corresponding to each code.

[0051] In this embodiment, optionally, the at least one code may be one or more, so after obtaining the at least one code, the number of the at least one code can be detected first. If the number of detected codes is one, the obtained code is an ATC code. If the number of detected codes is more than one, it is necessary to obtain the ATC code of the drug by screening at least one code based on the key information of the drug and the ingredients corresponding to each code.

[0052] Because the code directly obtained by searching the inverted index does not necessarily fully meet the requirements of the pharmaceutical ingredients in the key information of the pharmaceutical, in some optional realization methods of this embodiment, obtaining a pharmaceutical Anatomical Therapeutic Classification System code by screening at least one code based on the above-mentioned pharmaceutical key information and the ingredients corresponding to each code includes: for each of at least one code, detecting whether the ingredients corresponding to the code match with the pharmaceutical ingredients; in response to determining that the ingredients corresponding to the code match with the pharmaceutical ingredients and the detection of all codes is completed, obtaining an initial screening candidate code including the code; in response to determining that the initial screening candidate code has only one, determining that the initial screening candidate code is an Pharmaceutical Anatomical Therapeutic Classification System code.

[0053] In this optional realization method, the pharmaceutical ingredients can be expressed in different languages. Whether the pharmaceutical ingredients and the ingredients corresponding to the code match can be detected by the similarity of their contents (Chinese names or English words), or it can be determined based on the diseases that both can treat. For example, if the pharmaceutical ingredients and the ingredients corresponding to the code can both treat two or more of the same diseases, it is determined that the two match. Of course, whether the pharmaceutical ingredients and the ingredients corresponding to the code match can also be detected by other methods, and there is no limitation thereto.

[0054] In this embodiment, the initial screening candidate codes include at least one code that matches all pharmaceutical ingredients of the drug, i.e., at least one such code, and the ingredient corresponding to the code matches the pharmaceutical ingredient.

[0055] In this optional implementation method, the pharmaceutical ingredients in the pharmaceutical key information are matched with the ingredients corresponding to each of at least one code, and when the matching condition is met, an initial screening candidate code containing the code is obtained. After the detection of each of the at least one code is completed, the number of initial screening candidate codes is determined. If there is only one code, the ATC code of the pharmaceutical is obtained. In this way, the initial screening candidate code can be obtained by simply matching the result of the transposed index with the pharmaceutical ingredients, which is simple to implement and convenient to operate.

[0056] In some other optional implementation methods of this embodiment, the key information of the drug further includes an indication for the drug, and obtaining an Anatomical and Therapeutic Classification System code for the drug by screening at least one code based on the key information of the drug and ingredients corresponding to each code further includes, in response to the initial screening candidate codes being detected as multiple codes, a step of determining a disease type corresponding to the drug based on the indication for the drug, and a step of screening a code corresponding to the disease type from the initial screening candidate codes as the Anatomical and Therapeutic Classification System code for the drug.

[0057] The method for determining drug codes provided by the embodiments of the present disclosure includes first obtaining the drug instruction text, then extracting the key information of the drug in the instruction text, then obtaining at least one code related to the key information of the drug and the ingredients corresponding to each code based on the pre-created code transposition index, and finally obtaining the Anatomical Therapeutic Chemical Classification System code of the drug by screening at least one code based on the key information of the drug and the ingredients corresponding to each code. Thus, based on the drug instruction text, the pre-created code transposition index can automatically perform ATC coding for the drug, which can solve many pharmacists' work problems and provide coding basic information for the pharmaceutical information system.

[0058] When the key information of a drug includes a drug ingredient, in some optional implementation methods of this embodiment, as shown in FIG. 3, a flow 300 of one embodiment of a method for obtaining an Anatomical Therapeutic Classification System code of a drug according to the present disclosure is shown, and the method for obtaining an Anatomical Therapeutic Classification System code of the drug includes the following steps:

[0059] In step 301, for each of at least one code, it is detected whether or not the component corresponding to the code satisfies one of a plurality of rules having a priority order, and if the component corresponding to the code satisfies one of the plurality of rules having a priority order, step 302 is executed.

[0060] In this embodiment, the multiple rules are determined based on pharmaceutical ingredients, and after the ingredient corresponding to the code satisfies any one of the multiple rules according to the rule priority, other rules of the multiple rules may not be considered.

[0061] Specifically, the multiple rules are sorted in order of priority from high to low as follows: 1) If there are two or more types of pharmaceutical ingredients, the ingredient corresponding to the code includes all pharmaceutical ingredients of the drug. 2) If there are two or more types of pharmaceutical ingredients, the ingredient corresponding to the code includes at least one pharmaceutical ingredient of the drug and includes the characters "compound". 3) If there are two or more types of pharmaceutical ingredients, the ingredient corresponding to the code includes at least one pharmaceutical ingredient of the drug and does not include the characters "compound". 4) If there is one type of pharmaceutical ingredient, the ingredient corresponding to the code includes the pharmaceutical ingredient.

[0062] In addition, the content, priority and number of each rule among the above multiple rules can be adaptively adjusted based on the pharmaceutical ingredients in the instruction text of the medicine. For example, if the instruction text is the instruction text of a monoprescription drug, the multiple rules may only include the above 1) and 4). For example, if the instruction text is the instruction text of a compound prescription drug, the multiple rules may only include the above 1) to 3).

[0063] In this optional implementation method, multiple rules with priority order can be applied to single-prescription drugs and compound prescription drugs, and compound prescription drugs are given priority in consideration, thereby improving the reliability and comprehensiveness of the ingredient inspection corresponding to the code.

[0064] In step 302, it is detected whether detection of all codes in the at least one code has been completed, and if so, execute step 303; if detection of the at least one code has not been completed, return to execution of step 301.

[0065] In this embodiment, the code is each code arranged in order in at least one code, which is also the current code. In step 302, if the current code (the code) satisfies one of the multiple rules, it is included in the candidate codes for initial screening. In step 302, if the current code does not satisfy any one of the multiple rules, the code is discarded, and the process returns to step 301 to re-detect the code adjacent to the current code in the at least one code as the current code.

[0066] In step 303, candidate codes for initial screening that include the code are determined, and then step 304 is executed.

[0067] In this embodiment, the initial screening candidate code is an ATC code that meets the requirements of the instruction manual text of the initially obtained drug, and the components corresponding to each code in the initial screening candidate code meet one of multiple rules having priority, and the initial screening candidate code may have only one code or may have multiple codes.

[0068] In this optional implementation method, the candidate codes for initial screening include all codes that satisfy one of the multiple rules of the at least one code, i.e., at least one such code, and the component corresponding to the code satisfies one of the multiple rules having priority.

[0069] In step 304, it is detected whether the initial screening candidate code has only one code; if the detection result is that the initial screening candidate code has only one code, step 305 is executed.

[0070] In this embodiment, if the detection result is that there is only one code, it is determined that the current initial screening candidate code is the ATC code of a drug, and there is no need to perform any further detection.

[0071] In this optional embodiment, if there are multiple initial screening candidate codes, optionally similarity matching may be performed on the initial screening candidate codes, and one of the initial screening candidate codes with the highest similarity may be selected as the ATC code for the drug.

[0072] Optionally, if the instruction text is for a compound medicine, all codes among the candidate codes of the initial screening that have the character compound in the ingredient corresponding to the initial screening candidate code may be used as the ATC code of the medicine. If the instruction text is for a compound medicine, all codes among the candidate codes of the initial screening that do not have the character compound in the ingredient corresponding to the initial screening candidate code may be used as the ATC code of the medicine.

[0073] In step 305, the initial screening candidate codes are determined as Anatomical Therapeutic Classification System codes for the drugs.

[0074] In this optional implementation method, when the key information of a drug includes pharmaceutical ingredients, the Anatomical Therapeutic Classification System code of the drug can be determined based on multiple rules determined corresponding to the pharmaceutical ingredients, thereby improving the reliability of ATC code determination.

[0075] In some optional implementations of this embodiment, when the key information of a drug includes drug ingredients and drug indications, as shown in Figure 4, a flow chart 400 of another embodiment of a method for obtaining an Anatomical Therapeutic Classification System code of a drug according to the present disclosure is shown. The method for obtaining an Anatomical Therapeutic Classification System code of the drug includes the following steps:

[0076] In step 401, for each of at least one code, it is detected whether the component corresponding to the code satisfies one of a plurality of rules having a priority order. If the component corresponding to the code satisfies one of a plurality of rules having a priority order, step 402 is executed.

[0077] In step 402, it is detected whether detection for all of the at least one code has been completed, and if so, execute step 403; if detection for the at least one code has not been completed, return to execution of step 401.

[0078] In step 403, candidate codes for initial screening that include the code are determined, and then step 404 is executed.

[0079] In step 404, it is detected whether the initial screening candidate code has only one code. If the detection result is that there is only one code, execute step 405. If the detection result is that the initial screening candidate code has multiple codes, execute step 406.

[0080] In step 405, the initial screening candidate codes are determined as Anatomical Therapeutic Classification System codes for the drugs.

[0081] It should be understood that the operations and features in steps 401 to 405 above correspond to those in steps 301 to 305, respectively, and therefore the description of the operations and features in steps 301 to 305 above is equally applicable to steps 401 to 405 and will not be repeated here.

[0082] In step 406, a disease type corresponding to the drug is determined based on the drug's indication, and then step 407 is performed.

[0083] In this embodiment, a correspondence table between indications and disease types may be set in advance as an option. After obtaining the indications of a drug, the disease type corresponding to the indications of the drug can be quickly obtained based on the correspondence table between indications and disease types set in advance.

[0084] In some optional implementations of this embodiment, determining a disease type corresponding to the drug based on an indication for the drug includes employing a pre-trained classification model to perform disease classification on the indication to obtain a disease type output by the classification model.

[0085] In practical applications, the BERT model is adopted to build a classification model, and the classification model performs disease classification on the indications in the drug's instruction text, so that the probability values ​​of different disease types output by the model can be obtained, for example, classification of 14 disease types can be performed. For example, the indications in the instruction text include "used for acne vulgaris, may also be used for seborrheic dermatitis and rosacea, folliculitis", and classification of 14 disease types is performed to determine which disease the drug is a drug for treating. These classifications are the digestive system, metabolic system, blood and hematopoietic system, cardiovascular system, skin disease, urogenital system, sex hormone, anti-infection, anti-tumor and immune medication, musculoskeletal system, nervous system, anti-parasitic, respiratory system, and sensory system, a total of 14 disease types. These 14 categories also correspond to the 14 disease types in the ATC first-class classification.

[0086] For the indication "used for acne vulgaris, and may also be used for seborrheic dermatitis, rosacea, and folliculitis" in the above instructions, the classification model outputs a confidence score for each of the above 14 disease types. For example, if the classification scores output by the classification model for the above indications are digestive system (2%), metabolic system (7%), blood and hematopoietic system (8%), cardiovascular system (5%), skin disease (80%), urogenital system (1%), sex hormone (8%), anti-infection (10%), anti-tumor and immune medication (2%), musculoskeletal system (2%), nervous system (2%), anti-parasitic (2%), respiratory system (2%), and sensory system (2%), the result obtained is that the disease type of the above indication belongs to skin disease.

[0087] By training a classification model in which disease types correspond to drug indications, it is possible to know which disease the drug is intended to treat from the indication text description in the drug leaflet. In this embodiment, the classification accuracy achieved by employing the classification model can reach 93% or more.

[0088] In this optional realization method, the indications extracted from the instruction text can be input into a pre-trained classification model to obtain the disease type output by the classification model. Furthermore, by comparing the obtained disease type with the disease type corresponding to each code among the candidate codes of the initial screening, a preferred ATC code corresponding to the drug among the candidate codes of the initial screening can be obtained. Since the classification model can improve the accuracy of obtaining the disease type, the reliability of the obtained ATC code of the drug can be ensured.

[0089] In step 407, the initial screening candidate codes are screened for codes corresponding to disease types as Anatomical Therapeutic Classification System codes for drugs.

[0090] In this embodiment, the disease type may be one or more. When the disease type is one, the initial screening candidate code corresponding to the disease type is the ATC code of the medicine. When the disease type is multiple, the initial screening candidate code corresponding to the most common disease type among the disease types can be optionally set as the ATC code of the medicine. Of course, the code corresponding to the first obtained disease type can also be selected as the ATC code of the medicine. The present disclosure is not limited to this.

[0091] In this optional realization method, when the key information of a drug includes drug ingredients and drug indications, an initial screening candidate code among at least one code is determined based on the drug ingredients; when the initial screening candidate codes are multiple codes, the disease type corresponding to the drug is determined based on the drug indications, and the ATC code of the drug is determined from the initial screening candidate code, thereby solving the problem that the same drug has multiple ATC codes, and ensuring the accuracy of ATC code determination.

[0092] Further referring to Figure 5, as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of an apparatus for determining a pharmaceutical code, which corresponds to the embodiment of the method shown in Figure 2, and which can be specifically applied to various electronic devices.

[0093] As shown in FIG. 5, an embodiment of the present disclosure provides an apparatus 500 for determining a drug code, and the apparatus 500 includes an acquisition unit 501, an extraction unit 502, an acquisition unit 503, and a screening unit 504. Here, the acquisition unit 501 may be configured to acquire a drug instruction text. The extraction unit 502 may be configured to extract key information of the drug in the instruction text. The acquisition unit 503 may be configured to obtain at least one code related to the key information of the drug and ingredients corresponding to each code based on a pre-created code transposition index. The screening unit 504 may be configured to obtain an Anatomical Therapeutic Classification System code of the drug by screening at least one code based on the key information of the drug and ingredients corresponding to each code.

[0094] In this embodiment, the specific processing and technical effects of the acquisition unit 501, the extraction unit 502, the acquisition unit 503, and the screening unit 504 in the apparatus 500 for determining a pharmaceutical code may refer to step 201, step 202, step 203, and step 204 in the embodiment corresponding to FIG. 2, respectively.

[0095] In some embodiments, the key information of the drug includes a drug ingredient, and the screening unit 504 includes a detection module (not shown), an initial screening module (not shown), and a determination module (not shown). Here, the detection module may be configured to detect, for each of at least one code, whether the ingredient corresponding to the code satisfies one of a plurality of rules having a priority, and the plurality of rules are determined based on the drug ingredient. The initial screening module may be configured to determine an initial screening candidate code including the code in response to determining that the ingredient corresponding to the code satisfies one of the plurality of rules and that the detection of all codes is completed. The determination module may be configured to determine the initial screening candidate code as an Anatomical Therapeutic Classification System code of the drug in response to determining that the initial screening candidate code has only one.

[0096] In some embodiments, the rules are sorted from high to low priority as follows: 1) if there is more than one pharmaceutical ingredient, the ingredient corresponding to the code includes all pharmaceutical ingredients of the drug. 2) if there is more than one pharmaceutical ingredient, the ingredient corresponding to the code includes at least one pharmaceutical ingredient of the drug and includes the word "compound". 3) if there is more than one pharmaceutical ingredient, the ingredient corresponding to the code includes at least one pharmaceutical ingredient of the drug and does not include the word "compound". 4) if there is one pharmaceutical ingredient, the ingredient corresponding to the code includes the pharmaceutical ingredient.

[0097] In some embodiments, the key information of the drug includes a pharmaceutical ingredient, and the screening unit 504 includes a matching module (not shown), a response module (not shown), and a coding module (not shown). Here, the matching module may be configured to detect, for each of at least one code, whether the ingredient corresponding to the code matches the pharmaceutical ingredient. The response module may be configured to obtain an initial screening candidate code including the code in response to determining that the ingredient corresponding to the code matches the pharmaceutical ingredient and that the detection of all codes is completed. The coding module may be configured to determine the initial screening candidate code as an Anatomical Therapeutic Classification System code of the drug in response to determining that the initial screening candidate code has only one.

[0098] In some embodiments, the key information of the medicine further includes an indication of the medicine, and the screening unit 504 includes a classification module (not shown) and a confirmation module (not shown). Here, the classification module may be configured to determine a disease type corresponding to the medicine based on the indication of the medicine in response to detecting that the initial screening candidate code is a plurality of codes. The confirmation module may be configured to screen the code corresponding to the disease type from the initial screening candidate code as an Anatomical Therapeutic Classification System code of the medicine.

[0099] In some embodiments, the classification module is further configured to employ a pre-trained classification model to perform disease classification on the indication, thereby obtaining a disease type output by the classification model.

[0100] In the method for determining drug code provided by the embodiment of the present disclosure, first, the acquisition unit 501 acquires the drug instruction text, then the extraction unit 502 extracts the key information of the drug in the instruction text, then the acquisition unit 503 obtains at least one code related to the key information of the drug and the ingredients corresponding to each code based on the pre-created code transposition index, and finally, the screening unit 504 obtains the Anatomical Therapeutic Chemical Classification System code of the drug by screening at least one code based on the key information of the drug and the ingredients corresponding to each code. Thus, based on the drug instruction text, the pre-created code transposition index can automatically perform ATC coding for the drug, which can solve the difficulties in the work of most pharmacists and provide coding basic information for the pharmaceutical information system.

[0101] Referring now to FIG. 6, a structural schematic diagram of an electronic device 600 suitable for implementing an embodiment of the present disclosure is shown.

[0102] 6, the electronic device 600 may include a processing unit (such as a central processing unit, a graphics processor, etc.) 601 that can perform various suitable operations and processes according to a program stored in a read only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. The RAM 603 also stores various programs and data necessary for the operation of the electronic device 600. The processing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0103] Typically, the following devices may be connected to the I / O interface 605: input devices 606 including touch screens, touch pads, keyboards, mice, etc.; output devices 607 including LCDs, speakers, vibrators, etc.; storage devices 608 including magnetic tapes, hard disks, etc.; and communication devices 609. The communication devices 609 may enable the electronic device 600 to perform wireless or wired communication to exchange data with other devices. Although FIG. 6 illustrates the electronic device 600 with various devices, it should be understood that the electronic device 600 need not implement or include all the devices shown. Instead, more or less devices may be implemented or included. Each block illustrated in FIG. 6 may represent one device or may represent multiple devices as needed.

[0104] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowcharts may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a product including a computer program carried on a computer-readable medium, the computer program including program code for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication device 609, or may be installed from the storage device 608, or may be installed from the ROM 602. When the computer program is executed by the processing device 601, the above functions defined in the method of the embodiment of the present disclosure are performed.

[0105] It should be noted that the computer readable medium of the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiments of the present disclosure, the computer readable storage medium may be any tangible medium that contains or stores a program, which may be used in or in combination with an instruction execution system, apparatus, or device. In the embodiments of the present disclosure, the computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries the computer readable program code. The propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may transmit, propagate, or transmit a program used by or in connection with an instruction execution system, apparatus, or device. The program code contained in the computer-readable medium may be transmitted over any suitable medium, including but not limited to wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

[0106] The computer-readable medium may be included in the server, or may exist independently without being assembled in the server. The computer-readable medium is loaded with one or more programs, and when the one or more programs are executed by the server, the server obtains the drug instruction text, extracts the drug key information in the instruction text, obtains at least one code related to the drug key information and the ingredients corresponding to each code based on the code transposition index created in advance, and obtains the Anatomical Therapeutic Classification System code of the drug by screening at least one code based on the drug key information and the ingredients corresponding to each code.

[0107] Computer program code for carrying out the operations of the embodiments of the present disclosure can be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as traditional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computer, partially on the user computer, as a separate software package, partially on the user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., connected via the Internet using an Internet Service Provider).

[0108] The flowcharts and block diagrams in the drawings illustrate possible system architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, program segment or part of code, which includes one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than the order marked in the drawings. For example, blocks shown in succession may in fact be executed substantially in parallel, and they may be executed in reverse order depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that executes the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0109] The units included in the embodiments described in the present disclosure may be implemented in software or hardware. The described units may also be located in a processor, and may be described as including an acquisition unit, an extraction unit, an acquisition unit, and a screening unit, where the names of these units may not necessarily be limiting of the units themselves, for example, the acquisition unit may be further described as a unit "configured to acquire instruction text for a medicine."

[0110] The above description is merely a description of the preferred embodiments of the present disclosure and the technical principles applied thereto. Those skilled in the art should understand that the scope of the present disclosure included in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the concept of the present disclosure. For example, the above features and the technical features having similar functions (but not limited to) disclosed in the embodiments of the present disclosure are substituted with each other to form the technical solutions.

Claims

1. obtaining a drug product instruction text; Extracting key information of the medicine from the instruction text; Obtaining at least one code related to the key information of the medicine and ingredients corresponding to each code based on a code transposition index created in advance; and obtaining an Anatomical Therapeutic Classification System code for the drug by screening the at least one code based on key information of the drug and ingredients corresponding to each code.

2. The key information of the drug includes a drug ingredient; Obtaining an Anatomical and Therapeutic Classification System code for the drug by screening the at least one code based on key information of the drug and ingredients corresponding to each code, For each of the at least one code, detecting whether the ingredient corresponding to the code satisfies one of a plurality of rules having a priority order, the plurality of rules being determined based on the pharmaceutical ingredient; determining a candidate code for initial screening that includes the code in response to determining that the component corresponding to the code satisfies one of the plurality of rules and that detection of all codes has been completed; and in response to determining that the initial screening candidate code has only one, determining that the initial screening candidate code is an Anatomical Therapeutic Classification System code for the drug.

3. 3) when the pharmaceutical ingredient has two or more kinds, the ingredient corresponding to the code includes at least one pharmaceutical ingredient of the drug and includes the character "compound", 4) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 5) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 6) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 7) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 8) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 9) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 10) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 11) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 12) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 13) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 14) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 15) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 16) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 17) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 18) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 19) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 20) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 21) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 22) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and 23) when the pharmaceutical ingredient has one kind, the ingredient corresponding to the code includes the pharmaceutical ingredient, and

4. The key information of the drug includes a drug ingredient; Obtaining an Anatomical and Therapeutic Classification System code for the drug by screening the at least one code based on key information of the drug and ingredients corresponding to each code, for each of the at least one code, detecting whether an ingredient corresponding to the code matches the pharmaceutical ingredient; In response to determining that the component corresponding to the code is matched with the pharmaceutical component and that detection of all codes is completed, obtaining an initial screening candidate code including the code; and in response to determining that the initial screening candidate code has only one, determining that the initial screening candidate code is an Anatomical Therapeutic Classification System code for the drug.

5. The key information of the drug further includes an indication of the drug; Obtaining an Anatomical and Therapeutic Classification System code for the drug by screening the at least one code based on key information of the drug and ingredients corresponding to each code, In response to detecting a plurality of candidate codes from the initial screening, determining a disease type corresponding to the drug based on an indication for the drug; The method according to any one of claims 2 to 4, further comprising the step of screening a code corresponding to the disease type from the initial screening candidate codes as an Anatomical Therapeutic Classification System code of the drug.

6. 6. The method of claim 5, wherein determining a disease type corresponding to the drug based on an indication for the drug comprises employing a pre-trained classification model to perform disease classification on the indication to obtain a disease type output by the classification model.

7. an acquisition unit configured to acquire a prescription text for the medicine; an extraction unit configured to extract key information of the medicine in the instruction text; An acquisition unit configured to acquire at least one code related to the key information of the medicine and ingredients corresponding to each code according to a pre-created code transposition index; and a screening unit configured to obtain an Anatomical Therapeutic Classification System code of the drug by screening the at least one code based on key information of the drug and ingredients corresponding to each code.

8. The key information of the drug includes a drug ingredient; The screening unit comprises: a detection module configured to detect, for each of the at least one code, whether an ingredient corresponding to the code satisfies one of a plurality of rules having a priority, the plurality of rules being determined based on the pharmaceutical ingredient; an initial screening module configured to determine, in response to determining that a component corresponding to the code satisfies one of the plurality of rules and that detection of all codes has been completed, a candidate code for initial screening that includes the code; and a determination module configured to determine, in response to determining that the initial screening candidate code has only one, that the initial screening candidate code is an Anatomical Therapeutic Classification System code for the pharmaceutical product.

9. The key information of the drug further includes an indication of the drug; The screening unit comprises: a classification module configured to determine a disease type corresponding to the drug based on an indication for the drug in response to detecting a plurality of candidate codes from the initial screening; 10. The apparatus of claim 8, further comprising: a validation module configured to screen a code corresponding to the disease type from the initial screening candidate codes as an Anatomical Therapeutic Classification System code for the drug.

10. one or more processors; a storage device in which one or more programs are stored; An electronic device, wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

11. A computer readable medium having stored thereon a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

12. A computer program implementing the method according to any one of claims 1 to 6, when said computer program is executed by a processor.

Citation Information

Patent Citations

  • Method for checking mutual affect of medicines and its method

    JP1999195078A

  • Information processing apparatus and control method therefor

    JP2019040467A

  • Information retrieval processing device and method

    US20160180028A1