CN114300151A - Construction method, device, equipment and medium of medical adverse reaction data warehouse - Google Patents
Construction method, device, equipment and medium of medical adverse reaction data warehouse Download PDFInfo
- Publication number
- CN114300151A CN114300151A CN202111648426.4A CN202111648426A CN114300151A CN 114300151 A CN114300151 A CN 114300151A CN 202111648426 A CN202111648426 A CN 202111648426A CN 114300151 A CN114300151 A CN 114300151A
- Authority
- CN
- China
- Prior art keywords
- data
- medical
- standard
- dimension
- medical data
- 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
Images
Abstract
The embodiment of the specification provides a method for constructing a medical adverse reaction data warehouse, which is characterized by comprising the following steps: obtaining medical data comprising a drug name and an adverse reaction description of a drug represented by the drug name; processing the content of the medical data into standard medical data based on a preset medical expression dictionary to obtain a standardized medical data layer; mapping the normative medical data of the normative medical data layer into standard data which accords with a standard expression form to obtain a standard data layer; wherein the standard expression format at least complies with E2B R3; building a data warehouse comprising associated dimension tables and fact tables according to standard data of the standard data layer; wherein the dimension table comprises dimension data used for representing adverse drug reaction trend, and the fact table comprises measurement data used for performing data statistics on the dimension data. Through the implementation mode of the specification, the medicine enterprise can perform multidimensional OLAP analysis on adverse reactions of medicines.
Description
Technical Field
The specification relates to the technical field of computer data processing, in particular to a construction method, a device, equipment and a storage medium of a medical adverse reaction data warehouse.
Background
The medical adverse reaction data is huge and is continuously updated, and the adverse reaction trend obtained through the medical adverse reaction data is large in calculation amount and delayed in timeliness. In order to obtain the adverse reaction trend result of the medicine, the medicine enterprise needs to research each medicine and then perform repeated and large-batch calculation, so that the efficiency is low, and the time and the labor are consumed.
Disclosure of Invention
In view of this, a plurality of embodiments of the present disclosure are directed to providing a method, an apparatus, a device and a storage medium for constructing a medical adverse reaction data warehouse, which can quickly obtain an analysis result of multidimensional Online Analytical Processing (OLAP) of adverse drug reactions.
The embodiment of the specification provides a method for constructing a medical adverse reaction data warehouse, which is characterized by comprising the following steps: obtaining medical data comprising a drug name and an adverse reaction description of a drug represented by the drug name; processing the content of the medical data into standard medical data based on a preset medical expression dictionary to obtain a standard medical data layer; mapping the normative medical data of the normative medical data layer into standard data which accords with a standard expression form to obtain a standard data layer; wherein the standard expression format at least complies with E2B R3; building a data warehouse comprising associated dimension tables and fact tables according to standard data of the standard data layer; wherein the dimension table comprises dimension data used for representing adverse drug reaction trend, and the fact table comprises measurement data used for performing data statistics on the dimension data.
The embodiment of the present specification provides a device for constructing a medical adverse reaction data warehouse, which is characterized by comprising: an acquisition module for acquiring medical data including a drug name and an adverse reaction description of a drug represented by the drug name; the normalization module is used for processing the content of the medical data into normative medical data based on a preset medical expression dictionary to obtain a normative medical data layer; the standardization module is used for mapping the standardized medical data of the standardized medical data layer into standard data which accords with a standard expression form to obtain a standard data layer; wherein the standard expression format at least complies with E2B R3; a building module for building a data warehouse including associated dimension tables and fact tables according to standard data of the standard data layer; wherein the dimension table comprises dimension data used for representing adverse drug reaction trend, and the fact table comprises measurement data used for performing data statistics on the dimension data.
The embodiment of the specification provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the method of the embodiment when executing the computer program.
The present specification embodiments propose a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the embodiments.
According to the adverse medical reaction data warehouse, the adverse medical reaction trend can be quickly obtained, the purpose of obtaining the multi-dimensional adverse drug reaction result is achieved, and the effect of improving the adverse drug reaction data calculating efficiency is achieved.
Drawings
FIG. 1 is a diagram illustrating different peer interactions in an example scenario provided by an embodiment.
FIG. 2 is a diagram illustrating different peer interactions in an example scenario provided by an embodiment.
Fig. 3 is a schematic diagram illustrating a flow of a construction method in an example scenario provided by an embodiment.
Fig. 4 is a schematic diagram illustrating a flow of a construction method in an example scenario provided by an embodiment.
Fig. 5 is a schematic diagram illustrating a flow of a construction method in an example scenario provided by an embodiment.
FIG. 6 is a diagram illustrating a client in an example scenario provided by an embodiment.
FIG. 7 is a diagram illustrating a client in an example scenario provided by an embodiment.
FIG. 8 is a diagram illustrating a client in an example scenario provided by an embodiment.
FIG. 9 is a diagram illustrating a client in an example scenario provided by an embodiment.
FIG. 10 is a diagram illustrating a client in an example scenario provided by an embodiment.
Fig. 11 is a schematic diagram illustrating an apparatus according to an exemplary scenario provided in an embodiment.
FIG. 12 is a functional diagram of an electronic device according to an embodiment.
Detailed Description
In order to make the technical solution of the present invention better understood, the technical solution of 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 only a part of the embodiments of the present invention, not all of the embodiments of the present invention. All other embodiments obtained by a person of ordinary skill in the art without any inventive work based on the embodiments in the present specification belong to the protection scope of the present specification.
Please refer to fig. 1, fig. 2 and fig. 3. The present specification provides a scenario example of a method for constructing a medical adverse reaction data warehouse. A part of the medicine enterprises are obtained through clinical tests, and medical data uploaded by a supervision organization records information of report types, research types, report sources, patient sexes, ages, medicines and adverse reactions. The staff member uploads this report to the server.
The server receives the report and judges that the report expresses the drug name and the adverse drug reaction, so that the report can be subjected to subsequent processing.
Please refer to fig. 4. The preset medical expression dictionary is divided into a plurality of data subsets, the server searches in the medical data and judges that the 'report type' in the report is matched with the 'report type' data subset in the preset medical expression dictionary. Further calculating the vector distance between the vector of the "report from study" and the vector of the data in the data subset of "report type" in the preset medical expression dictionary, and as a result, displaying that the vector distance between the vector of the "report from study" and the vector of the "study" is minimum, so that the vector distance between the vector of the "report type from study" in the report: reports from the study "convert to" report type: study "was conducted. The server ultimately converts this report into computer-storable, normalized medical data that can be identified: "reports from study" were converted to "study", male "to" 1 ", penicillin to" aspirin ", and penicillin to" aspirin ". The server stores the normative medical data to a normative medical data layer.
Please refer to fig. 5. The server converts the contents of the normalized medical data layer to comply with the requirements of E2B R3, in accordance with the requirements of E2B R3. The server calculates the vector distance of the vector of the "report type" entry in the normalized medical data layer to the vector of each field in E2B R3, resulting in the display of each field in E2B R3 that is closest to the vector of the "report type" entry in the normalized medical data layer being "C13". The server judges in the data of "C13", report type: study "should select" 1 ", so" report type: the study "switched to" C131 ". The server converts other contents of the report, and the result is' C131; c5.42; c1. CN11; H2F; h2.431; y5.43110102-25583-8547; B5B 221-85204-25 ". And the server stores the converted data to the standard data layer.
The server stores all report contents meeting the standard in a data warehouse respectively comprising a dimension table and a fact table. After the server receives a plurality of medical data, the server calculates the 'headache' adverse reaction signal value of the 'amoxicillin' through a mathematical model, stores the adverse reaction signal value in a dimension table, and stores 'sex' data, 'age' data, 'research type' data, 'report type' data and 'report source' data in the 'headache' adverse reaction report of the 'amoxicillin' in a fact table for subsequent analysis.
Please refer to fig. 6 and 7. The construction method of the medical adverse reaction data warehouse can be applied to a system comprising a client and a server. The staff of the medicine enterprise can input the medicine name at the client, and the server obtains the medicine specified dimension data and the measurement data corresponding to the medicine identification after calculation.
Please refer to fig. 8. The staff of the drug enterprise inputs a drug name "aliskiren at the client, and selects the specified analysis dimension" report country: all; the generation country: all; signal trend: gender ".
Clicking the search control, the client sends a request with the additional content of the aliskiren to the server. And after receiving the request, the server searches the database for adverse reaction data generated by taking the aliskiren and returns the adverse reaction data to the client.
Please refer to fig. 9. The client displays adverse reactions generated by the aliskiren including lymphocyte adoptive therapy, headache and lethargy, and the user wants to check the trend of the adverse reaction of the lymphocyte adoptive therapy, so that the user clicks the lymphocyte adoptive therapy. The client sends a data analysis request of the adverse reaction of lymphocyte adoptive therapy with the additional components of the aliskiren to the server.
After receiving the request, the server reads the data of the adverse reaction of lymphocyte adoptive therapy of the aliskiren in a dimension table in a constructed data warehouse; from the fact table of the data warehouse completed in the construction, the data of the adverse reaction of the "adoptive therapy of lymphocytes" of "aliskiren" are read, in the "reporting country: all; the generation country: in all "cases, the number of adverse reaction reports per quarter of this adverse reaction.
Please refer to fig. 10. And the server feeds the dimension data and the measurement data back to the client. The user sees at the client the "adoptive therapy of lymphocytes" of aliskiren "as an adverse reaction in quarterly ordered designated analytical dimension" reporting country: all; the generation country: all "different gender trend. The user can improve the aliskiren on the basis of the change trends.
The above description is only exemplary of the present disclosure and should not be construed as limiting the present disclosure, and any modifications, equivalents and the like that are within the spirit and principle of the present disclosure are intended to be included within the scope of the present disclosure.
The construction system for providing the medical adverse reaction data warehouse in the embodiment of the specification can comprise a client and a server. The client may be an electronic device with network access capabilities. Specifically, for example, the client may be a desktop computer, a tablet computer, a notebook computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, a smart speaker, a microphone, and the like. Wherein, wearable equipment of intelligence includes but not limited to intelligent bracelet, intelligent wrist-watch, intelligent glasses, intelligent helmet, intelligent necklace etc.. Alternatively, the client may be software capable of running in the electronic device. The server may be an electronic device having a certain arithmetic processing capability. Which may have a network communication module, a processor, memory, etc. Of course, the server may also refer to software running in the electronic device. The server may also be a distributed server, which may be a system with multiple processors, memory, network communication modules, etc. operating in coordination. Alternatively, the server may also be a server cluster formed by several servers. Or, with the development of scientific technology, the server can also be a new technical means capable of realizing the corresponding functions of the specification implementation mode. For example, it may be a new form of "server" implemented based on quantum computing.
Please refer to fig. 3. The construction method of the medical adverse reaction data warehouse provided by the embodiment of the specification can quickly obtain the medical adverse reaction trend. The method comprises the following steps.
S110: medical data is obtained that includes a drug name and a description of an adverse reaction of a drug represented by the drug name.
The drug name may be a generic name for the drug, or may be a name for a drug for which the user wishes to have a trend towards adverse drug reactions. The medical data describing adverse reactions to the drug may be at least one of: medical reports, patient basic information, drug usage, drug indications, adverse reactions reports, adverse event descriptions, and medical data of adverse event outcomes.
The medication name and medical data describing the adverse reaction of the medication represented by the medication name may be brought to the drug enterprise for investigation, and the results collected quarterly and entered into the server. In some embodiments, the medical data describing the adverse reaction may also originate from a commercial medical database, or from a government or medical institution.
S120: and processing the content of the medical data into standard medical data based on a preset medical expression dictionary to obtain a standard medical data layer.
The preset medical expression dictionary may be a preset medical expression dictionary associated with a computer language. The normative medical data may be medical data that is conveniently stored in a computer server. The processing of the content of the medical Data into the normative medical Data may be the processing of the medical Data using ods (operational Data store), hdfs (hadoop Distributed File system), and KUDU methods. The normative medical data layer may be an area of the computer where the converted normative medical data is stored. For example, based on a preset medical expression dictionary, the 'mother-of-food' of the medical data is processed into the normative medical data 'mother-of-food' by using a vector distance calculation method.
The content of the medical data is processed into the standard medical data, and the medical data can be converted into a language form which can be recognized and processed by a computer, so that the subsequent analysis and processing are facilitated.
S130: mapping the normative medical data of the normative medical data layer into standard data which accords with a standard expression form to obtain a standard data layer; wherein the standard expression format at least complies with E2B R3.
The E2B R3 may be an international standard for electronic transmission of individual safety reports of adverse drug events. The mapping of the normative medical data layer to the standard data conforming to the standard expression form may be converting the normative medical data to the standard data conforming to the standard expression form through a mathematical model. The standard data layer may be an area of the computer where the converted standard data is stored. For example, the "report type: the study "Standard form in E2B R3 is" C131 ".
With the stricter regulations on the drug alert in countries or regions around the world, the method for reporting the safety report of the adverse drug event to the drug regulatory department is gradually transited and perfected from the paper report to the electronic report, and the standard medical data of the standard medical data layer is converted into the standard expression form at least following the E2BR3, so that the application range of the construction method of the adverse medical reaction data warehouse can be expanded.
S140: building a data warehouse comprising associated dimension tables and fact tables according to standard data of the standard data layer; wherein the dimension table comprises dimension data used for representing adverse drug reaction trend, and the fact table comprises measurement data used for performing data statistics on the dimension data.
The data warehouse can be a calculation method for analyzing the adverse medical reactions, and the variation trend of the adverse drug reactions is obtained by storing the adverse medical reactions in the data warehouse. The dimension tables and fact tables may be a form of storage for data in the data warehouse. The dimension data may be an adverse reaction signal value calculated by a mathematical model, for example, an adverse reaction signal value calculated by a proportional report ratio method, a report ratio method, and a bayesian decision interval progressive neural network method. The measurement data can be basic information of the patient in the medical data, such as the sex of the patient, the age of the patient and the country of the patient.
By analyzing the data of the dimension table and the fact table, the user can find the change condition of the adverse reaction trend of the medicine, so that the follow-up improvement and improvement of the medicine are facilitated.
The adverse reaction trend of the medicine is analyzed by using a data warehouse method, the medical data is required to meet the processing requirement, the internationalization condition of the data in the big data era is considered, the medical data needs to be stored in a standard medical data layer firstly, then the medical data is stored in a standard data layer, and finally the data is converted into a form which can be displayed on a client side by using a method of constructing a dimension table and a fact table, so that a user can check and analyze the data.
In some embodiments, the step of obtaining medical data comprising a drug name and an adverse reaction description for a drug represented by the drug name comprises: removing medical text data which do not relate to the name of the medicine in the medical text data; and removing the medical text data which does not relate to adverse drug reaction description in the medical text data.
The removing of the medical text data that does not relate to the name of the drug may be analyzing the medical text data, and in the case that the medical text data does not express the name of the drug, performing no subsequent processing on the medical text data. In the removing of the medical text data, the medical text data which does not relate to the adverse drug reaction description may be that the medical text data is analyzed, and the medical text data is not subjected to subsequent processing under the condition that the medical text data does not express the adverse drug reaction.
The medical data can be collected after the medicine enterprises are researched, and the medical data can be processed firstly, so that the efficiency is improved, and the operation is reduced because the medical data can have abnormal values and cannot be subjected to subsequent analysis.
In some embodiments, the preset medical expression dictionary is divided into a plurality of data subsets according to medical data for matching; the data subset comprises an expression vocabulary and a specification vocabulary used for matching with medical data; processing the content of the medical data into normalized medical data based on a preset medical expression dictionary to obtain a normalized medical data layer, comprising: matching in the medical data by using the expression vocabulary to obtain target data; and replacing the target data with a standard vocabulary corresponding to the expression vocabulary.
The data subset may be a classification of the preset medical expression dictionary with respect to medical expression words; the expression vocabulary can be words related to data warehouse construction in the medical data; the standard vocabulary can be a vocabulary for converting the expression vocabulary into a computer language; the target data may be words that express a meaning that is close to the expression vocabulary in the medical data. For example, the medical data may be "age: age 31; sex: male; medicine preparation: three penicillin tablets are taken; adverse reactions: headache feeling "; the data subset of the preset medical expression dictionary may include a "gender" subset, an "age" subset, an "adverse reaction" subset, and an "adverse reaction outcome" subset. Splitting the content of the medical data according to semantics, converting the medical data into an age: middle-aged; sex: male; medicine preparation: amoxicillin; adverse reactions: headache; adverse reaction results: none ".
The medical data is converted into the standardized medical data, so that a required result is obtained, and computer statistics and analysis are facilitated.
In some embodiments, mapping the normative medical data of the normative medical data layer to standard data conforming to a standard expression form, resulting in a standard data layer, comprises: determining fields involved by the standard data layer according to E2B R3; acquiring target normative medical data corresponding to the fields in the normative medical data layer; generating standard data for the field based on the target normative medical data.
The fields involved in the standard data layer may be information fields required for individual case safety reporting of adverse drug events as specified in E2B R3; obtaining, in the canonical medical data layer, target canonical medical data corresponding to the field may be a field required for searching in the canonical medical data layer, and the target canonical medical data may be a field required for specification by E2B R3; generating the standard data for the field based on the target normative medical data may be converting the target normative medical data to a standard form. For example, the server will "age: middle-aged; sex: male; medicine preparation: amixiline; adverse reactions: headache; adverse reaction results: none conversion criteria data may be "H2F; h2.431; y5.43110102-25583-8547; B5B 221-85204-25; B2D 30 ".
In order to meet the requirement of data internationalization, the data can be converted into an international universal form, the application range of the method and the result is expanded, and more users can obtain the expected result conveniently.
In some embodiments, the normative medical data is divided into a plurality of entries; obtaining, in the normative medical data layer, target normative medical data corresponding to the fields, including: determining a field corresponding to the entry in the mapping relation set; wherein the set of mapping relationships includes index data for matching with the entry, the index data corresponding to a field.
The entry may be a classification of the medical data; the target normative medical data may be desired normative medical data; the set of mapping relationships may be establishing a mapping relationship between the normative medical data and the normative data; the index data may be an index relationship between the number of entries of the normative medical data and the standard data. For example, the entry of the canonical medical data may be a "gender" entry, and the field corresponding to the "gender" entry is "H2" through matching of the index data.
By establishing the mapping relation between the normative medical data and the standard data, the normative medical data can be more accurately converted into the standard data, and the occurrence of error events is reduced.
The index information comprises index vectors for characterizing the respective fields; determining a field corresponding to the entry, including: generating a feature vector for the entry; performing vector matching operation on the feature vector and the index vector to obtain a target index vector; and taking the field corresponding to the target index vector as the field corresponding to the entry.
The index information comprises index vectors for characterizing the corresponding fields, and real number vectors for characterizing the corresponding fields can be calculated through a mathematical model; the feature vector of the item can be a real vector that can characterize the item through calculation of a mathematical model; the vector matching operation of the feature vector and the index vector may be calculating a vector distance of the index vector and the feature vector of the entry; the target index vector may be the index vector calculated to have the smallest vector distance to the feature vector of the entry. For example, the index vector having the smallest vector distance from the feature vector of the "age" entry is calculated as the "H2.4" index vector, and the field corresponding to the "age" entry is the "H2.4" index information.
In some embodiments, the specified dimension data corresponds to a business identity; a step of receiving a data analysis request accompanied by a medication identifier, comprising: receiving a data analysis request attached with a medicine identifier and a target service identifier; correspondingly, the step of reading the specified dimension data from the dimension table of the data warehouse comprises the following steps: and reading the specified dimension data corresponding to the target service identification from the dimension table of the data warehouse.
The target service identifier may be a name of a drug or a name of a bad response that a user wishes to obtain, or may be basic information of a patient in medical data, such as sex of the patient, age of the patient, and country where the patient is located; the receiving of the data analysis request with the medicine identifier and the target service identifier may be that the user inputs the target service identifier at the client, and the client sends the target service identifier to the server; the reading of the specified dimension data corresponding to the target service identifier from the dimension table of the data warehouse may be searching for the specified dimension data corresponding to the target service identifier in the dimension table of the data warehouse, and sorting the specified dimension data into a data table to be returned to the client. The client can display the adverse reaction report trend of a certain dimension of a certain adverse reaction of a certain drug. For example, the client may display "adverse reaction signal variation trend of proportional reporting method of amoxicillin with respect to headache adverse reactions classified by gender".
In some embodiments, the specified analysis dimensions include reporting countries, occurring countries, and signal trends; wherein the signal trend includes gender and age.
The specified analysis dimension can be a multi-dimensional OLAP analysis dimension desired by a user; the report country may be a report filling country; the country of occurrence may be an adverse-reaction country of occurrence; the signal trend may be a change in adverse drug reactions over time; the gender may be the gender of the patient; the age may be an age at which adverse reactions occur upon taking the drug. The user can get more accurate results by setting the specified analysis dimension.
Please refer to fig. 11. The embodiment of this description still provides a construction equipment of medical adverse reaction data warehouse, and characterized by includes: the device comprises an acquisition module, a normalization module and a standardization module.
An acquisition module for acquiring medical data including a drug name and an adverse reaction description of a drug represented by the drug name;
the normalization module is used for processing the content of the medical data into normative medical data based on a preset medical expression dictionary to obtain a normative medical data layer;
the standardization module is used for mapping the standardized medical data of the standardized medical data layer into standard data which accords with a standard expression form to obtain a standard data layer; wherein the standard expression format at least complies with E2B R3;
a building module for building a data warehouse including associated dimension tables and fact tables according to standard data of the standard data layer; wherein the dimension table comprises dimension data used for representing adverse drug reaction trend, and the fact table comprises measurement data used for performing data statistics on the dimension data.
Please refer to fig. 12. In some embodiments, a computer device may be provided, comprising a memory having a computer program stored therein and a processor that implements the method steps of the embodiments when executing the computer program.
In some embodiments, a computer-readable storage medium may be provided, on which a computer program is stored, which when executed by a processor implements the method steps in the embodiments. The specific functions and effects achieved by the extraction device for data in medical information can be explained by referring to other embodiments in this specification, and are not described herein again. All or part of the modules in the medical information data extraction device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In some embodiments, a computer device may be provided, comprising a memory having a computer program stored therein and a processor that implements the method steps of the embodiments when executing the computer program.
In some embodiments, a computer-readable storage medium may be provided, on which a computer program is stored, which when executed by a processor implements the method steps in the embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include processes of the embodiments of the methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The description is made in a progressive manner among the embodiments of the present specification. The different embodiments focus on the different parts described compared to the other embodiments. After reading this specification, one skilled in the art can appreciate that many embodiments and many features disclosed in the embodiments can be combined in many different ways, and for the sake of brevity, all possible combinations of features in the embodiments are not described. However, as long as there is no contradiction between combinations of these technical features, the scope of the present specification should be considered as being described.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, the embodiments themselves are emphasized differently from the other embodiments, and the embodiments can be explained in contrast to each other. Any combination of the embodiments in this specification based on general technical common knowledge by those skilled in the art is encompassed in the disclosure of the specification.
The above description is only an embodiment of the present disclosure, and is not intended to limit the scope of the claims of the present disclosure. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.
Claims (12)
1. A construction method of a medical adverse reaction data warehouse is characterized by comprising the following steps:
obtaining medical data comprising a drug name and an adverse reaction description of a drug represented by the drug name;
processing the content of the medical data into standard medical data based on a preset medical expression dictionary to obtain a standardized medical data layer;
mapping the normative medical data of the normative medical data layer into standard data which accords with a standard expression form to obtain a standard data layer; wherein the standard expression format at least complies with E2B R3;
building a data warehouse comprising associated dimension tables and fact tables according to standard data of the standard data layer; wherein the dimension table comprises dimension data used for representing adverse drug reaction trend, and the fact table comprises measurement data used for performing data statistics on the dimension data.
2. The method of claim 1, wherein the medical data includes at least one of: medical report, basic information of patients, dosage of medication, medical indications, adverse reaction report, adverse event description and adverse event results;
the step of obtaining medical data comprising a drug name and an adverse reaction description for a drug represented by the drug name, comprising:
removing medical text data which do not relate to the name of the medicine in the medical text data;
and removing the medical text data which does not relate to adverse drug reaction description in the medical text data.
3. The method according to claim 1, wherein the preset medical expression dictionary is divided into a plurality of data subsets in accordance with medical data for matching; the data subset comprises an expression vocabulary and a specification vocabulary used for matching with medical data;
processing the content of the medical data into normalized medical data based on a preset medical expression dictionary to obtain a normalized medical data layer, comprising:
matching in the medical data by using the expression vocabulary to obtain target data;
and replacing the target data with a standard vocabulary corresponding to the expression vocabulary.
4. The method of claim 1, wherein mapping canonical medical data of the canonical medical data layer to standard data that conforms to a standard expression form, resulting in a standard data layer, comprises:
determining fields involved by the standard data layer according to E2B R3;
acquiring target normative medical data corresponding to the fields in the normative medical data layer;
generating standard data for the field based on the target normative medical data.
5. The method of claim 4, wherein the normative medical data is divided into a plurality of entries; obtaining, in the normative medical data layer, target normative medical data corresponding to the fields, including:
determining a field corresponding to the entry in the mapping relation set; wherein the set of mapping relationships includes index data for matching with the entry, the index data corresponding to a field.
6. The method of claim 5, wherein the index information comprises an index vector for characterizing the respective field; determining a field corresponding to the entry, including:
generating a feature vector for the entry;
performing vector matching operation on the feature vector and the index vector to obtain a target index vector; and taking the field corresponding to the target index vector as the field corresponding to the entry.
7. The method of claim 1, further comprising:
receiving a data analysis request with a medicine identification and a designated analysis dimension;
reading analysis-specified dimension data from a dimension table of the data warehouse;
reading metric data corresponding to the drug identification from the fact table of the data warehouse according to the specified dimension data;
and feeding back the specified dimension data and the measurement data corresponding to the medicine identification to a sender of the data analysis request.
8. The method of claim 7, wherein the specified analysis dimensions include reporting country, occurrence country, and signal trend; wherein the signal trend includes gender and age.
9. The method of claim 7, wherein the specified dimension data corresponds to a business identifier; a step of receiving a data analysis request accompanied by a medication identifier, comprising: receiving a data analysis request attached with a medicine identifier and a target service identifier;
correspondingly, the step of reading the specified dimension data from the dimension table of the data warehouse comprises the following steps:
and reading the specified dimension data corresponding to the target service identification from the dimension table of the data warehouse.
10. An apparatus for constructing a medical adverse reaction data warehouse, comprising:
an acquisition module for acquiring medical data including a drug name and an adverse reaction description of a drug represented by the drug name;
the normalization module is used for processing the content of the medical data into normative medical data based on a preset medical expression dictionary to obtain a normative medical data layer;
the standardization module is used for mapping the standardized medical data of the standardized medical data layer into standard data which accords with a standard expression form to obtain a standard data layer; wherein the standard expression format at least complies with E2B R3;
a building module for building a data warehouse including associated dimension tables and fact tables according to standard data of the standard data layer; wherein the dimension table comprises dimension data used for representing adverse drug reaction trend, and the fact table comprises measurement data used for performing data statistics on the dimension data.
11. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 9 when executing the computer program.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111648426.4A CN114300151A (en) | 2021-12-29 | 2021-12-29 | Construction method, device, equipment and medium of medical adverse reaction data warehouse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111648426.4A CN114300151A (en) | 2021-12-29 | 2021-12-29 | Construction method, device, equipment and medium of medical adverse reaction data warehouse |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114300151A true CN114300151A (en) | 2022-04-08 |
Family
ID=80974423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111648426.4A Pending CN114300151A (en) | 2021-12-29 | 2021-12-29 | Construction method, device, equipment and medium of medical adverse reaction data warehouse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114300151A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062973A (en) * | 2017-11-30 | 2018-05-22 | 江西洪都航空工业集团有限责任公司 | A kind of health care data analysing method |
| US20190057191A1 (en) * | 2017-08-21 | 2019-02-21 | International Business Machines Corporation | Cognitive framework to identify medical case safety reports in free form text |
| CN110704526A (en) * | 2019-09-27 | 2020-01-17 | 北京深度制耀科技有限公司 | Method, device and equipment for acquiring adverse event information and storage medium |
| CN111177516A (en) * | 2019-12-30 | 2020-05-19 | 嘉兴太美医疗科技有限公司 | Medication alert system and method of processing feedback data thereof |
| CN112131339A (en) * | 2020-09-28 | 2020-12-25 | 上海梅斯医药科技有限公司 | Name standardization standard processing method, device, computer and storage medium |
-
2021
- 2021-12-29 CN CN202111648426.4A patent/CN114300151A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190057191A1 (en) * | 2017-08-21 | 2019-02-21 | International Business Machines Corporation | Cognitive framework to identify medical case safety reports in free form text |
| CN108062973A (en) * | 2017-11-30 | 2018-05-22 | 江西洪都航空工业集团有限责任公司 | A kind of health care data analysing method |
| CN110704526A (en) * | 2019-09-27 | 2020-01-17 | 北京深度制耀科技有限公司 | Method, device and equipment for acquiring adverse event information and storage medium |
| CN111177516A (en) * | 2019-12-30 | 2020-05-19 | 嘉兴太美医疗科技有限公司 | Medication alert system and method of processing feedback data thereof |
| CN112131339A (en) * | 2020-09-28 | 2020-12-25 | 上海梅斯医药科技有限公司 | Name standardization standard processing method, device, computer and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11119980B2 (en) | Self-learning operational database management | |
| Ma et al. | Intelligent healthcare systems assisted by data analytics and mobile computing | |
| US11704321B2 (en) | Techniques for relationship discovery between datasets | |
| US11200248B2 (en) | Techniques for facilitating the joining of datasets | |
| US11461368B2 (en) | Recommending analytic tasks based on similarity of datasets | |
| US11928463B2 (en) | Auto mapping recommender | |
| US11341449B2 (en) | Data distillery for signal detection | |
| WO2020057021A1 (en) | Data table processing method and device, computer device and storage medium | |
| US11373101B2 (en) | Document analyzer | |
| CN111078776A (en) | Data table standardization method, device, equipment and storage medium | |
| Das et al. | A CV parser model using entity extraction process and big data tools | |
| CN110765101A (en) | Label generation method and device, computer readable storage medium and server | |
| CN114579653A (en) | Data set-based CDA document generation method and device and electronic equipment | |
| US20230153357A1 (en) | Method of processing an observation information, electronic device and storage medium | |
| CN111984797A (en) | Customer identity recognition device and method | |
| CN117056308A (en) | Method for generating financial big data blood-edge relation based on OpenLinear database | |
| CN114300151A (en) | Construction method, device, equipment and medium of medical adverse reaction data warehouse | |
| US20230044287A1 (en) | Semantics based data and metadata mapping | |
| CN114281923A (en) | Medicine name searching method, device, equipment and storage medium | |
| Kim et al. | SPMgr: Dynamic workflow manager for sampling and filtering data streams over Apache Storm | |
| CN109657010B (en) | Document processing method, device and storage medium | |
| Shukla et al. | An emerging trend of big data for high volume and varieties of data to search of agricultural data | |
| Fadiya et al. | The importance of big data technology | |
| US20220075949A1 (en) | Association Determination | |
| CN112558913A (en) | Conversation method and device based on aggregated card, computer equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220729 Address after: 201703 room 1288, Zone C, 12 / F, block B, No. 1-72, Lane 2855, Huqingping highway, Zhaoxiang Town, Qingpu District, Shanghai Applicant after: Shanghai Taimei Digital Technology Co.,Ltd. Address before: 3 / F, building 9, smart industry innovation park, 36 Changsheng South Road, Jiaxing City, Zhejiang Province, 314001 Applicant before: Zhejiang Taimei Medical Technology Co.,Ltd. |