CN111968756A - Knowledge graph construction method and device for medicine specification - Google Patents
Knowledge graph construction method and device for medicine specification Download PDFInfo
- Publication number
- CN111968756A CN111968756A CN202010723969.7A CN202010723969A CN111968756A CN 111968756 A CN111968756 A CN 111968756A CN 202010723969 A CN202010723969 A CN 202010723969A CN 111968756 A CN111968756 A CN 111968756A
- Authority
- CN
- China
- Prior art keywords
- drug
- graph
- knowledge
- medicine
- medicine specification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 320
- 238000010276 construction Methods 0.000 title claims abstract description 21
- 229940079593 drug Drugs 0.000 claims abstract description 176
- 238000000034 method Methods 0.000 claims abstract description 60
- 206010067484 Adverse reaction Diseases 0.000 claims description 13
- 230000006838 adverse reaction Effects 0.000 claims description 13
- 230000003993 interaction Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 10
- 238000006467 substitution reaction Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 7
- 208000024891 symptom Diseases 0.000 claims description 6
- 229940126673 western medicines Drugs 0.000 claims description 5
- 230000008569 process Effects 0.000 description 7
- 238000012550 audit Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 235000012054 meals Nutrition 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 235000021152 breakfast Nutrition 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 206010019280 Heart failures Diseases 0.000 description 1
- 208000000857 Hepatic Insufficiency Diseases 0.000 description 1
- 206010019663 Hepatic failure Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 208000001647 Renal Insufficiency Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000000172 allergic effect Effects 0.000 description 1
- 208000010668 atopic eczema Diseases 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 201000006370 kidney failure Diseases 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 230000003908 liver function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 244000052769 pathogen Species 0.000 description 1
- 239000000825 pharmaceutical preparation Substances 0.000 description 1
- 229940127557 pharmaceutical product Drugs 0.000 description 1
- 238000009101 premedication Methods 0.000 description 1
- 229940043263 traditional drug Drugs 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Medicinal Chemistry (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention provides a knowledge graph construction method and a knowledge graph construction device for a medicine specification, wherein the method comprises the following steps: data arrangement is carried out on the medicine specification; disassembling knowledge points of multiple dimensions from the sorted medicine specification; constructing a triple of the drug specification according to the knowledge points of the multiple dimensions; and importing the triad of the medicine specification into a graph database to determine the knowledge graph of the medicine specification. According to the method and the device for constructing the knowledge graph of the medicine specification, dimension description with finer granularity is performed on the medicine specification, the method and the device are closer to the understanding mode of a clinician and a clinical pharmacist on the medicine specification, the knowledge graph of the medicine specification is constructed by adopting the graph database, and the retrieval efficiency is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for constructing a knowledge graph of a medicine specification.
Background
The drug insert is the most important evidence of evidence-based for clinicians and clinical pharmacists in providing medication regimens to patients. With the development of medical informatization, the prescription preposed auditing system widely used by various hospitals can conveniently search a medicine specification and automatically prompt a clinician and a clinical pharmacist about the problem of the prescription of a patient according to incompatibility, special population, contraindication, interaction and the like of the medicine specification. The medicine has very important significance for guaranteeing the reasonable and safe medication of patients.
At present, the content of the drug instruction is stored in a relational database according to different fields of indication, incompatibility, usage amount, age, population, contraindication, interaction and the like of the drug instruction according to the requirements of hospital prescription audit, and the corresponding content is searched through full matching or fuzzy matching of the fields in the using process. The information in the database completely corresponding to the searched content is searched through the sex, age, clinical diagnosis, medicine name, usage amount and the like provided by the patient prescription.
The existing scheme can not process more complex query requirements, has low query efficiency, can only find the problem that the prescription of a patient is unreasonable, and can not provide a solution
Disclosure of Invention
The embodiment of the invention provides a knowledge graph construction method and a knowledge graph construction device for a drug specification, which are used for overcoming the defect that the prior art cannot process more complex query requirements, realizing the clinical assistant decision making of clinicians and clinical pharmacists and providing more reasonable and safe medication schemes for patients.
The embodiment of the invention provides knowledge graph construction of a medicine specification, which comprises the following steps:
data arrangement is carried out on the medicine specification;
disassembling knowledge points of multiple dimensions from the sorted medicine specification;
constructing a triple of the drug specification according to the knowledge points of the multiple dimensions;
and importing the triad of the medicine specification into a graph database, and determining the known graph of the medicine specification.
According to the method for constructing the knowledge graph of the medicine specification, the data arrangement of the medicine specification specifically comprises the following steps:
arranging the specifications of the western medicines and the Chinese patent medicines according to the clinical special classification;
according to the medicines with the same common name, the specifications of the medicines with the same common name produced by different manufacturers are arranged.
According to the method for constructing the knowledge graph of the medicine specification, which is disclosed by the embodiment of the invention, the method for disassembling the knowledge points with multiple dimensions from the sorted medicine specification specifically comprises the following steps:
obtaining a sample drug specification, wherein the sample drug specification is a specification with better content integrity selected by a physician and/or pharmacist from a plurality of drug specifications;
according to the sample of the medicine specification, a plurality of classifications are disassembled from the sorted medicine specification, and each classification at least comprises knowledge points of one dimension.
According to the method for constructing the knowledge graph of the drug instruction book, the plurality of classifications include: basic information of drugs, physical conditions, interactions, adverse reactions, medication monitoring, drug substitution, drug concentration, and medication education.
According to the method for constructing the knowledge graph of the drug specification, the constructing of the triple of the drug specification according to the knowledge points of the plurality of dimensions specifically comprises the following steps:
obtaining content of an entity, the content of the entity comprising: drug name, indication, contraindication, examination item, symptom and medical history;
acquiring attributes of each entity, wherein the attributes comprise the dimension of the detailed description entity or the dimension of a set condition;
determining the relationship between the entities according to the content of the specification;
the triplets of the drug specification are determined from the entities, relationships, and attributes.
According to the method for constructing the knowledge graph of the medicine specification, the graph database is Neo4 j.
According to an embodiment of the present invention, after determining the knowledge-graph of the drug specification, the method for constructing the knowledge-graph of the drug specification further includes:
graph retrieval is performed using a query language for graph databases.
The embodiment of the invention also provides a knowledge graph construction device of the medicine specification, which comprises the following steps:
the arrangement module is used for carrying out data arrangement on the medicine specification;
the disassembling module is used for disassembling the knowledge points with multiple dimensions from the finished medicine specification;
the construction module is used for constructing a three-tuple of the medicine specification according to the knowledge points of the plurality of dimensions;
and the determining module is used for importing the triad of the medicine specification into a graph database and determining the knowledge graph of the medicine specification.
The embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the program to implement the steps of the method for constructing a knowledge graph of a drug specification.
Embodiments of the present invention also provide a non-transitory computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the method for constructing a knowledge graph of a drug order according to any one of the above-mentioned embodiments.
According to the method and the device for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the dimension description of the medicine specification with finer granularity is closer to the understanding mode of a clinician and a clinical pharmacist on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without creative efforts for those skilled in the art.
FIG. 1 is a schematic flow chart diagram of a method for constructing a knowledge graph of a drug specification according to an embodiment of the present invention;
FIG. 2 is a logic flow diagram of a method for knowledge-graph construction of a drug specification according to an embodiment of the present invention;
FIG. 3 is a flow chart of a clinical medication logic provided by an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a knowledge-graph constructing apparatus for a drug instruction book according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the prior art, two problems generally exist in the disassembly and utilization of the content of a medicine specification:
firstly, the medicine specification is disassembled mainly according to the requirements of hospital prescription audit and according to the indications, incompatibility, usage amount, age, population, incompatibility, interaction and the like of the medicine specification, the dimension granularity is not fine enough, the problem that the prescription of a patient is unreasonable can only be found, and a solution cannot be provided. Some improved hospital pre-auditor systems currently provide a friendly interface for editing solutions to the problem of unreasonable prescriptions, but are not exhaustive.
Secondly, along with the refinement of the dimension of the medicine specification disassembly, the medicine specification information stored in the traditional relational database can only be queried in one or more fields, and cannot process more complex query requirements, for example, the incidence relation among a plurality of fields needs to be considered during query, and the efficiency is low.
With the increasing importance of intellectualization in the construction of hospital information systems, the drug instruction book knowledge base constructed based on the traditional relational database is difficult to adapt to the requirements of clinical application.
In view of the above technical problems, a method for constructing a knowledge graph of a drug order according to an embodiment of the present invention is described below with reference to fig. 1 to 3, where as shown in fig. 1, the method for constructing a knowledge graph of a drug order according to an embodiment of the present invention includes:
and step 101, performing data arrangement on the medicine specification.
Specifically, as shown in fig. 2, the method for constructing a knowledge graph of a pharmaceutical specification according to the embodiment of the present invention is suitable for a pharmaceutical specification of a domestic western medicine, a pharmaceutical specification of a domestic traditional Chinese medicine, and a pharmaceutical specification of an imported western medicine.
In the process of data arrangement of the medicine specification, the western medicine and Chinese patent medicine specification are arranged according to clinical special classification, and special distribution construction is mainly considered, so that experience is gradually accumulated.
The medicine specifications of each medicine manufacturer are classified and arranged according to the common names of the medicines, and the medicines with the same common name are mainly considered, so that the indications, the usage amount, the contraindications and the like of different manufacturers are possibly different.
And 102, disassembling knowledge points with multiple dimensions from the sorted medicine specification.
Specifically, after data arrangement is performed on the medicine specification, knowledge points of multiple dimensions are disassembled from the arranged medicine specification.
The medicine specification of each universal name medicine is disassembled on the basis of the medicine specification of the first-selected foreign medicine manufacturer, and the completeness of the clinical test of the medicine specification of the main foreign manufacturer and the completeness of the content of the specification are better.
For example, break the drug instructions down into 8 categories (drug basic information, physical condition, interactions, adverse reactions, medication monitoring, drug substitution, drug concentration, and medication education) 109 dimensions.
And 103, constructing a triple of the drug specification according to the knowledge points of the multiple dimensions.
Specifically, after knowledge points of multiple dimensions are disassembled from the sorted medicine specification, the multiple dimensions of the medicine specification disassembly are analyzed, and entities, relationships and attributes are defined according to clinical medication paths, prescription audit specifications and clinical medication experience.
The drug name (common name), indication, contraindication, examination item, symptom, medical history and the like can be defined as entities, the dimension providing detailed description for the entities or the dimension positioning of set conditions is defined as attributes, and the relationship definition between the entities is according to the content of the drug specification.
And 104, importing the triad of the medicine specification into a graph database, and determining a knowledge graph of the medicine specification.
Specifically, after the triplets of the drug order are determined, the triplets of the drug order are imported into a graph database to determine a knowledge graph of the drug order.
Mature graph database products, such as Neo4j, are selected and triples are imported into the graph database. Graph retrieval is performed using a query language for graph databases.
According to the method for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the medicine specification is subjected to dimension description with finer granularity, so that the method is closer to the understanding mode of clinicians and clinical pharmacists on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
Based on any one of the above embodiments, the data arrangement for the drug instruction book specifically includes:
arranging the specifications of the western medicines and the Chinese patent medicines according to the clinical special classification;
according to the medicines with the same common name, the specifications of the medicines with the same common name produced by different manufacturers are arranged.
Specifically, in the embodiment of the invention, the descriptions of western medicines and Chinese patent medicines are sorted according to the clinical special classification, and the descriptions of the medicines with the same common name produced by different manufacturers are sorted according to the medicines with the same common name.
The specifications of the western medicines and the Chinese patent medicines are arranged according to the classification of clinical specialties, and the special specialties are mainly considered as the stage distribution construction, so that the experience is gradually accumulated.
The medicine specifications of each medicine manufacturer are classified and arranged according to the common names of the medicines, and the medicines with the same common name are mainly considered, so that the indications, the usage amount, the contraindications and the like of different manufacturers are possibly different.
According to the method for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the medicine specification is subjected to dimension description with finer granularity, so that the method is closer to the understanding mode of clinicians and clinical pharmacists on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
Based on any one of the above embodiments, the disassembling of the knowledge points of multiple dimensions from the sorted pharmaceutical specification specifically includes:
obtaining a sample drug specification, wherein the sample drug specification is a specification with better content integrity selected by a physician and/or pharmacist from a plurality of drug specifications;
according to the sample of the medicine specification, a plurality of classifications are disassembled from the sorted medicine specification, and each classification at least comprises knowledge points of one dimension.
Specifically, in the embodiment of the present invention, after data arrangement is performed on the medicine manual, knowledge points of multiple dimensions are disassembled from the arranged medicine manual.
The medicine specification of each universal name medicine is disassembled on the basis of the medicine specification of the first-selected foreign medicine manufacturer, and the completeness of the clinical test of the medicine specification of the main foreign manufacturer and the completeness of the content of the specification are better.
For example, break the drug instructions down into 8 categories (drug basic information, physical condition, interactions, adverse reactions, medication monitoring, drug substitution, drug concentration, and medication education) 109 dimensions.
According to the method for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the medicine specification is subjected to dimension description with finer granularity, so that the method is closer to the understanding mode of clinicians and clinical pharmacists on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
Based on any of the above embodiments, the plurality of classifications includes: basic information of the drug, physical conditions, interactions, adverse reactions, medication monitoring, drug substitution, drug concentration and medication education.
Specifically, in the present example, the drug instructions were broken down into 109 dimensions of 8 classifications (drug basis information, physical condition, interaction, adverse reaction, medication monitoring, drug substitution, drug concentration, and medication education).
Wherein, the basic information of the medicine comprises the following dimensions: the latest revision date of the specification, the common name of the medicine, the name of the commodity, the pharmaceutical manufacturing enterprise, the characters, the specifications, the approval document number (national drug standards), the approval document number (imported drug registration certificate number), the storage, the packaging and the validity period.
The physical condition includes the following dimensions: drugs, population classifications, population data, indications, renal insufficiency, renal function data, hepatic insufficiency, hepatic function data, other medical histories, other symptoms, other combinations, other conditions, tumors, heart failure, patient pre-medication bleeding, gender (male/female), allergic components, whether skin tests (yes/no) are required, pathogens causing infections or other diseases, physical condition versus medication specific implications, dosing regimens, recommended start dose (times), recommended start dose (dose/day), recommended start dose (doses/days), recommended maintenance dose (doses/times), recommended maintenance dose (doses/days), recommended maintenance dose administration, recommended maximum dose (doses/times), recommended maximum dose (doses/days), and combinations thereof, The recommended maximum dose usage, the next highest dose, the daily highest dose, the dose adjustment interval, the recommended minimum dose (dose/time), the recommended minimum dose (dose/day), the recommended minimum dose usage, the administration interval time, the course of treatment, the administration cycle, the dose adjustment method, the administration route, the administration period (1. morning; 2. before sleep; 3. before meal; 4. during meal; 5. after meal; 6. am; 7. afternoon; 8. before breakfast; 9. before lunch; 10. before supper; 11. during breakfast; 12. during lunch; 13. during supper; 14. evening; 15. after dinner; 16. morning; 17. at noon; 18. at any time), the relationship with food, whether the drug can be broken off or chewed, whether the recommended oral hygiene is maintained, and the usage is additionally recommended.
The interaction includes the following dimensions: interaction drug a, interaction drug a type, interaction drug B type, drug a blood concentration, drug B blood concentration, drug a bioavailability, drug B bioavailability, effect on the human body, recommended dose of drug a, recommended dose (dose/dose) of drug a, recommended dose of drug B, and detailed explanation of the effect of drug a and drug B.
Adverse reactions included the following dimensions: the medicine, adverse reactions, clinical test names, clinical test time, adverse reaction incidence rate, special range or special value or same meaning of characters, duration of adverse reactions, adverse reaction treatment, dosage value adjustment according to adverse reactions and administration frequency value adjustment according to adverse reactions.
Medication monitoring includes the following dimensions: drug A, drug A type, drug B used together with drug A, drug B type, patient condition, index to be monitored when using the drug, frequency of occurrence of drug influence, which index abnormality is caused when using the drug, and which abnormality is caused when using the drug.
Drug substitutions include the following dimensions: recommended medication and wash periods.
Drug concentrations include the following dimensions: drug A, drug A dose, drug B (recommended compatibility solution), drug B (volume), drug C (strictly prohibited compatibility solution), concentration ratio, solution storage time under certain conditions, dropping speed (ml/min; ml/h; gtt/min), dropping time (d/h/min), and administration route.
According to the method for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the medicine specification is subjected to dimension description with finer granularity, so that the method is closer to the understanding mode of clinicians and clinical pharmacists on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
Based on any of the above embodiments, the constructing a triplet of a drug order according to the knowledge points of the multiple dimensions specifically includes:
obtaining content of an entity, the content of the entity comprising: drug name, indication, contraindication, examination item, symptom and medical history;
acquiring attributes of each entity, wherein the attributes comprise the dimension of the detailed description entity or the dimension of a set condition;
determining the relationship between the entities according to the content of the specification;
the triplets of the drug specification are determined from the entities, relationships, and attributes.
Specifically, in the embodiment of the present invention, after knowledge points of multiple dimensions are disassembled from the sorted medicine specification, the multiple dimensions of the medicine specification disassembly are analyzed, and entities, relationships, and attributes are defined according to clinical medication routes, prescription audit specifications, and clinical medication experience.
The name (common name) of the medicine, the indication, the contraindications, the inspection items, the symptoms, the medical history and the like are defined as entities, the dimension providing detailed description for the entities or the dimension positioning of set conditions is defined as attributes, and the relationship definition between the entities is according to the content of the medicine specification.
For example, for the drug population usage: the entities are defined as drug names and the attributes are population classifications (identities), population data (ages) and usage volumes.
For the pharmaceutical indications: the entity is defined as the name of the medicine and the name of the indication, the relationship is the indication, and the attribute is the source of the evidence.
Diagnosis for indications: the entities are defined as diagnosis and indications and the relationships are mappings.
Contraindications for drugs: the definition entities are medicine names and contraindications names, medication relationships, and the attributes are evidence sources, contraindications and contraindications.
For interactive drugs: the entity is defined as a medicine name A and a medicine name B, the sharing relationship is defined, the relationship attribute is the sharing type, the evidence source is defined, and the attribute is the detailed action.
According to the method for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the medicine specification is subjected to dimension description with finer granularity, so that the method is closer to the understanding mode of clinicians and clinical pharmacists on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
In any of the above embodiments, the graph database is Neo4 j.
Specifically, in the present embodiment, Neo4j is selected as the graph database, and Neo4j is a mature graph database product.
The construction of the medicine specification multi-dimension knowledge graph has the advantages that the multi-dimension data relation modeling is realized, and the graph database has incomparable advantages compared with the traditional relational database.
According to the method for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the medicine specification is subjected to dimension description with finer granularity, so that the method is closer to the understanding mode of clinicians and clinical pharmacists on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
Based on any of the above embodiments, after determining the knowledge-graph of the drug specification, the method further includes:
graph retrieval is performed using a query language for graph databases.
Specifically, in the embodiment of the present invention, after the knowledge graph of the medicine specification is determined, the graph is retrieved by using the query language of the graph database.
Each link in the clinical medication process relates to multi-condition query to support clinical decision, and the retrieval efficiency based on the graph algorithm is higher. For example, traversing the query graph database at a relationship depth of 3 is 4 times faster than a traditional relational database (in MySQL for example). At a depth of 4, the result is 5 orders of magnitude faster. With a depth of 5, the speed of the graph database is even 1000 ten thousand times faster.
According to the method for constructing the knowledge graph of the medicine specification, provided by the embodiment of the invention, the medicine specification is subjected to dimension description with finer granularity, so that the method is closer to the understanding mode of clinicians and clinical pharmacists on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
The traditional drug instruction book knowledge base can only provide the content of the drug instruction book for a clinician and a clinical pharmacist to check, and as shown in fig. 3, each drug selection link needs manual judgment. In recent two years, some intelligent auditor software can perform the function of safety early warning of patient prescriptions by writing a large number of programs and matching traditional relational data, but still cannot realize intelligent medication recommendation. According to the embodiment of the invention, the knowledge graph of the medicine specification based on the graph database is constructed by 8-classification 109-dimension disassembly of the medicine specification and combining the knowledge graph technology according to the clinical medication path, the prescription audit specification and the clinical medication experience, and has the following advantages:
the drug insert is described in a finer granularity dimension, which is closer to the way clinicians and clinical pharmacists understand the drug insert.
The 109-dimensional knowledge graph construction of the drug specification has the advantages that multiple dimensions are formed for modeling the multiple-dimensional data relations, and compared with a traditional relational database, a graph database has incomparable advantages.
In the clinical medication process, each link relates to multi-condition query to support clinical decision, and the retrieval efficiency based on the graph algorithm is higher. For example, the traversal query graph database at a relationship depth of 3 is 4 times faster than the traditional relational database (in MySQL for example). At a depth of 4, the result is 5 orders of magnitude faster. With a depth of 5, the speed of the graph database is even 1000 ten thousand times faster.
The drug instruction book knowledge base constructed by the embodiment of the invention overcomes the defect that the traditional pharmacy knowledge base can only be used for information retrieval, can help clinicians and clinical pharmacists to make clinical auxiliary decisions, and provides more reasonable and safe medication schemes for patients.
The knowledge graph constructing apparatus of the pharmaceutical instruction manual according to the embodiment of the present invention is described below, and the knowledge graph constructing apparatus of the pharmaceutical instruction manual described below and the knowledge graph constructing method of the pharmaceutical instruction manual described above may be referred to in correspondence with each other.
As shown in fig. 4, the knowledge graph constructing apparatus for a pharmaceutical product specification provided in the embodiment of the present invention includes a sorting module 401, a disassembling module 402, a constructing module 403, and a determining module 404, where:
the sorting module 401 is used for sorting data of the medicine specification; the disassembling module 402 is configured to disassemble knowledge points of multiple dimensions from the sorted medicine specification; the building module 403 is configured to build a triple of the drug specification according to the knowledge points of the multiple dimensions; the determination module 404 is configured to import the triplets of the drug order into a graph database and determine a knowledge graph of the drug order.
According to the knowledge graph constructing device for the medicine specification, provided by the embodiment of the invention, the dimension description of the medicine specification with finer granularity is closer to the understanding mode of a clinician and a clinical pharmacist on the medicine specification, and the knowledge graph of the medicine specification is constructed by adopting the graph database, so that the retrieval efficiency is improved.
Fig. 5 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 5: a processor (processor)510, a communication Interface (Communications Interface)520, a memory (memory)530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a method of knowledge graph construction of a drug order, the method comprising: data arrangement is carried out on the medicine specification; disassembling knowledge points of multiple dimensions from the sorted medicine specification; constructing a triple of the drug specification according to the known points of the plurality of dimensions; and importing the triad of the drug specification into a graph database, and determining the knowledge graph of the drug specification.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is capable of executing a method for constructing a knowledge graph of a drug specification, where the method includes: data arrangement is carried out on the medicine specification; disassembling knowledge points of multiple dimensions from the sorted medicine specification; constructing a triple of the drug specification according to the knowledge points of the multiple dimensions; and importing the triad of the medicine specification into a graph database, and determining the knowledge graph of the medicine specification.
In yet another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute a method for constructing a knowledge graph of a drug specification provided in the foregoing embodiments, where the method includes: data arrangement is carried out on the medicine specification; disassembling knowledge points of multiple dimensions from the sorted medicine specification; constructing a triple of the drug specification according to the knowledge points of the multiple dimensions; and importing the triad of the medicine specification into a graph database to determine the knowledge graph of the medicine specification.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate components may or may not be physically separate, and components displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement the present invention without any inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may be modified or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A method for constructing a knowledge graph of a drug instruction book is characterized by comprising the following steps:
data arrangement is carried out on the medicine specification;
disassembling knowledge points of multiple dimensions from the sorted medicine specification;
constructing a triple of the drug specification according to the knowledge points of the multiple dimensions;
and importing the triad of the medicine specification into a graph database to determine the knowledge graph of the medicine specification.
2. The method for building a knowledge graph of a drug specification according to claim 1, wherein the data arrangement of the drug specification specifically comprises:
arranging the specifications of the western medicines and the Chinese patent medicines according to the clinical special classification;
according to the medicines with the same common name, the specifications of the medicines with the same common name produced by different manufacturers are arranged.
3. The method for constructing a knowledge graph of a drug order according to claim 1, wherein the disassembling of knowledge points of multiple dimensions from the sorted drug order specifically comprises:
obtaining a sample drug specification, wherein the sample drug specification is a specification with better content integrity selected by a physician and/or pharmacist from a plurality of drug specifications;
according to the sample of the medicine specification, a plurality of classifications are disassembled from the sorted medicine specification, and each classification at least comprises knowledge points of one dimension.
4. The method of knowledge-graph construction of a drug specification of claim 3 wherein the plurality of classifications comprises: basic information of drugs, physical conditions, interactions, adverse reactions, medication monitoring, drug substitution, drug concentration, and medication education.
5. The method of claim 1, wherein the constructing the triplet of the drug order based on the knowledge points of the plurality of dimensions comprises:
obtaining content of an entity, the content of the entity comprising: drug name, indication, contraindication, examination item, symptom and medical history;
acquiring attributes of each entity, wherein the attributes comprise the dimension of the detailed description entity or the dimension of the set condition;
determining the relationship between the entities according to the content of the specification;
the triplets of the drug specification are determined from the entities, relationships, and attributes.
6. The method of knowledge-graph construction of a drug specification of claim 1 wherein said graph database is Neo4 j.
7. The method of claim 1, wherein determining the knowledge-graph of the drug order further comprises:
graph retrieval is performed using a query language for graph databases.
8. A knowledge graph building apparatus for a drug instruction book, comprising:
the arrangement module is used for carrying out data arrangement on the medicine specification;
the disassembling module is used for disassembling the knowledge points with multiple dimensions from the finished medicine specification;
the construction module is used for constructing the triples of the drug specification according to the knowledge points of the multiple dimensions;
and the determining module is used for importing the triad of the medicine specification into a graph database and determining the knowledge graph of the medicine specification.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method of knowledge-graph construction of a pharmaceutical specification according to any one of claims 1 to 7.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of the method for knowledge-graph construction of a pharmaceutical specification of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010723969.7A CN111968756A (en) | 2020-07-24 | 2020-07-24 | Knowledge graph construction method and device for medicine specification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010723969.7A CN111968756A (en) | 2020-07-24 | 2020-07-24 | Knowledge graph construction method and device for medicine specification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111968756A true CN111968756A (en) | 2020-11-20 |
Family
ID=73362571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010723969.7A Pending CN111968756A (en) | 2020-07-24 | 2020-07-24 | Knowledge graph construction method and device for medicine specification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111968756A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113076301A (en) * | 2021-03-31 | 2021-07-06 | 北京搜狗科技发展有限公司 | Knowledge base construction method, information query method, device and equipment |
CN114005507A (en) * | 2021-09-23 | 2022-02-01 | 厦门大学 | Clinical medication risk assessment method and system based on knowledge graph |
CN114329140A (en) * | 2021-12-28 | 2022-04-12 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
CN114582459A (en) * | 2022-01-27 | 2022-06-03 | 中南大学湘雅三医院 | Information processing method, device and equipment based on diagnosis and treatment data and storage medium |
US20220223245A1 (en) * | 2021-01-13 | 2022-07-14 | Boe Technology Group Co., Ltd. | Drug recommendation method, apparatus and system, electronic device and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377755A (en) * | 2019-07-03 | 2019-10-25 | 江苏省人民医院(南京医科大学第一附属医院) | Reasonable medication knowledge map construction method based on medicine specification |
CN111221979A (en) * | 2019-12-31 | 2020-06-02 | 北京左医健康技术有限公司 | Medicine knowledge graph construction method and system |
-
2020
- 2020-07-24 CN CN202010723969.7A patent/CN111968756A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377755A (en) * | 2019-07-03 | 2019-10-25 | 江苏省人民医院(南京医科大学第一附属医院) | Reasonable medication knowledge map construction method based on medicine specification |
CN111221979A (en) * | 2019-12-31 | 2020-06-02 | 北京左医健康技术有限公司 | Medicine knowledge graph construction method and system |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220223245A1 (en) * | 2021-01-13 | 2022-07-14 | Boe Technology Group Co., Ltd. | Drug recommendation method, apparatus and system, electronic device and storage medium |
CN113076301A (en) * | 2021-03-31 | 2021-07-06 | 北京搜狗科技发展有限公司 | Knowledge base construction method, information query method, device and equipment |
CN114005507A (en) * | 2021-09-23 | 2022-02-01 | 厦门大学 | Clinical medication risk assessment method and system based on knowledge graph |
CN114329140A (en) * | 2021-12-28 | 2022-04-12 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
CN114582459A (en) * | 2022-01-27 | 2022-06-03 | 中南大学湘雅三医院 | Information processing method, device and equipment based on diagnosis and treatment data and storage medium |
CN114582459B (en) * | 2022-01-27 | 2023-04-18 | 中南大学湘雅三医院 | Information processing method, device and equipment based on diagnosis and treatment data and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111968756A (en) | Knowledge graph construction method and device for medicine specification | |
US20200303047A1 (en) | Methods and systems for a pharmacological tracking and representation of health attributes using digital twin | |
Harpaz et al. | Biclustering of adverse drug events in the FDA's spontaneous reporting system | |
Gallagher et al. | Inter-rater reliability of STOPP (Screening Tool of Older Persons’ Prescriptions) and START (Screening Tool to Alert doctors to Right Treatment) criteria amongst physicians in six European countries | |
Kilbridge et al. | Automated surveillance for adverse drug events at a community hospital and an academic medical center | |
JP5832048B1 (en) | Medication related information output device, analysis server, medication related information output system, operation method of medication related information output device, operation program of medication related information output device, operation method of analysis server, and operation program of analysis server | |
WO2016070439A1 (en) | Method, system and device for intelligently selecting medicine | |
Tan et al. | Clinical decision support systems for neonatal care | |
Nguyen et al. | A probabilistic model for reducing medication errors | |
Spitzer et al. | The Pediatrix BabySteps® Data Warehouse—a unique national resource for improving outcomes for neonates | |
Lelong et al. | Building a semantic health data warehouse in the context of clinical trials: development and usability study | |
Tonin et al. | Use of ‘Pharmaceutical services’ Medical Subject Headings (MeSH) in articles assessing pharmacists' interventions | |
Lossio-Ventura et al. | Opioid2MME: Standardizing opioid prescriptions to morphine milligram equivalents from electronic health records | |
Shah et al. | Sources of medication omissions among hospitalized older adults with polypharmacy | |
AU2014350651A1 (en) | System and method of combining medicinal product information of medicaments | |
Christensen et al. | Identifying the “blip on the radar screen”: leveraging big data in defining drug safety and efficacy in pediatric practice | |
Yang et al. | Pharmacist‐led, prescription intervention system‐assisted feedback to reduce prescribing errors: A retrospective study | |
CN112233765A (en) | Intelligent analysis method, system and equipment for repeated medication | |
Plank-Kiegele et al. | Data requirements for the correct identification of medication errors and adverse drug events in patients presenting at an emergency department | |
Bannay et al. | Leveraging national claims and hospital big data: cohort study on a statin-drug interaction use case | |
Oliveira et al. | Contribution of different patient information sources to create the best possible medication history | |
Zhang et al. | Factors associated with pharmacists’ knowledge regarding high-alert medications: a convenience sample survey in China | |
LUPȘE et al. | Extracting and structuring drug information to improve e-prescription and streamline medical treatment | |
Spiers et al. | Clinical terminologies in the NHS: SNOMED CT and dm+ d | |
Li et al. | Ontological organization and bioinformatic analysis of adverse drug reactions from package inserts: Development and usability study |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230704 Address after: Room 611, Unit 1, Floor 5, Building 3, Yard 400, Zhongdong Road, Changping District, Beijing 102218 Applicant after: Beijing Suofei Wisdom Technology Partnership (L.P.) Address before: 100085 room 02-a086, 2 / F, block B, 22 Xinhe Road, Haidian District, Beijing Applicant before: Beijing Suofei medi Technology Co.,Ltd. |
|
TA01 | Transfer of patent application right |