CN112289454A - Labeling method and device for clinical data, storage medium and terminal - Google Patents
Labeling method and device for clinical data, storage medium and terminal Download PDFInfo
- Publication number
- CN112289454A CN112289454A CN202010948805.4A CN202010948805A CN112289454A CN 112289454 A CN112289454 A CN 112289454A CN 202010948805 A CN202010948805 A CN 202010948805A CN 112289454 A CN112289454 A CN 112289454A
- Authority
- CN
- China
- Prior art keywords
- data
- clinical data
- screening
- labeling
- execution task
- 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.)
- Granted
Links
- 238000002372 labelling Methods 0.000 title claims abstract description 67
- 238000012216 screening Methods 0.000 claims abstract description 107
- 238000000034 method Methods 0.000 claims abstract description 26
- 230000001960 triggered effect Effects 0.000 claims abstract description 16
- 238000012550 audit Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 8
- 239000012634 fragment Substances 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 8
- 230000000007 visual effect Effects 0.000 description 6
- 238000011160 research Methods 0.000 description 3
- 208000008589 Obesity Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000020824 obesity Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
A label printing method and device for clinical data, a storage medium and a terminal are provided, wherein the label printing method for clinical data comprises the following steps: when a trigger tagging execution task is detected, acquiring target clinical data to be processed, wherein the tagging execution task is provided with a corresponding data source and a screening condition, the target clinical data is sourced from the data source, and the number of the data sources is one or more; screening the target clinical data according to the screening conditions; and labeling the target clinical data meeting the screening condition, wherein the label corresponds to the triggered labeling execution task. According to the scheme, the data query efficiency can be improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a method and a device for labeling clinical data, a storage medium and a terminal.
Background
The data of the hospital has the characteristics of huge data volume, high growth speed, diversified types and sources and relatively low data value density.
When the data are used, if a user needs to set a plurality of screening conditions for accurately positioning a certain batch of data, the set plurality of screening conditions are adopted to perform complex screening operation so as to acquire the required data. The data screening operation is long in time consumption, and the data query efficiency is low.
Disclosure of Invention
The technical problem solved by the embodiment of the invention is that the data query efficiency is low.
In order to solve the above technical problem, an embodiment of the present invention provides a method for labeling clinical data, including: when a trigger tagging execution task is detected, acquiring target clinical data to be processed, wherein the tagging execution task is provided with a corresponding data source and a screening condition, the target clinical data is sourced from the data source, and the number of the data sources is one or more; screening the target clinical data according to the screening conditions; and labeling the target clinical data meeting the screening condition, wherein the label corresponds to the triggered labeling execution task.
Optionally, the tagging execution task is created in the following manner: generating the labeling execution task according to the selected screening field and the data source and a set template; or according to the input statement, performing semantic recognition on the statement to obtain the data source and the screening condition, and generating the labeling execution task based on the data source and the screening condition.
Optionally, the generating the labeling execution task includes: configuring timing execution information of a task, and generating the labeled execution task according to the timing execution information of the task, the screening condition and a data source and a set template, wherein the timing execution information of the task is used for controlling the time for executing the labeled execution task.
Optionally, the generating the labeled execution task based on the data source and the screening condition includes: obtaining the type of the label, and determining the creation state of the label according to the type of the label; when the label is a personal label, generating the labeling execution task based on the data source and the screening condition, and creating the label; when the type of the tag is a department tag or an institution-level tag, submitting a tag creation application to a specified object, determining the creation condition of the tag based on audit feedback of the specified object, creating the tag when the audit of the specified object passes, and failing to create the tag when the audit of the specified object does not pass.
Optionally, the labeling method for clinical data further includes: and when the deleting operation of the label is detected, deleting the label and the corresponding labeling execution task.
Optionally, the acquiring target clinical data to be processed includes: acquiring a first time point of executing the labeling execution task in the previous period, wherein the first time point is before a second time point, and the second time point refers to a time point of triggering the labeling execution task in the current period; and acquiring the clinical data of which the generation time is between the first time point and the second time point from the data source, and taking the clinical data generated between the first time point and the second time point as the target clinical data.
Optionally, the screening the target clinical data according to the screening condition includes: when the data volume of the target clinical data exceeds a set threshold, splitting the target clinical data into a plurality of data segments; and respectively screening each data fragment according to the screening conditions.
Optionally, the splitting the target clinical data into a plurality of data segments includes: according to the generation time of each clinical data in the target clinical data and the set time interval duration, the target clinical data is divided into a plurality of data segments.
Optionally, the screening the target clinical data according to the screening condition includes: and adopting a multithreading mode to asynchronously screen the target clinical data according to the screening conditions.
Optionally, the labeling method for clinical data further includes: after labeling the target clinical data meeting the screening conditions, generating and storing derivative data, wherein the derivative data at least comprises: identification information of the tag, identification information of a patient corresponding to the target clinical data, and a name of the tag.
Optionally, the generating the derivative data includes: and generating the derivative data according to a set period, or generating the derivative data in real time by matching with a labeling execution operation.
Optionally, the labeling method for clinical data further includes: obtaining a statistical condition; and acquiring data meeting the statistical condition from the derived data, and displaying the data.
The embodiment of the invention also provides a labeling device for clinical data, which comprises: the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring target clinical data to be processed when a tag execution task is detected to be triggered, the tag execution task is provided with a corresponding data source and a screening condition, the target clinical data is sourced from the data source, and the number of the data sources is one or more; the screening unit is used for screening the target clinical data according to the screening conditions; and the labeling unit is used for labeling the target clinical data meeting the screening condition, wherein the label corresponds to the triggered labeling execution task.
An embodiment of the present invention further provides a storage medium, where the computer-readable storage medium is a non-volatile storage medium or a non-transitory storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the computer program performs any of the above steps of the method for tagging clinical data.
The embodiment of the invention also provides a terminal, which comprises a memory and a processor, wherein the memory is stored with a computer program capable of running on the processor, and the processor executes the steps of any one of the above clinical data labeling methods when running the computer program.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
when the fact that the label printing execution task is triggered is detected, target clinical data meeting the screening condition are obtained from one or more data sources according to the corresponding data sources and the screening condition of the label printing execution task, the target clinical data meeting the screening condition are printed with labels, the labels correspond to the triggered label printing execution task, label printing processing is conducted on the target clinical data through the method, when clinical data are inquired subsequently, the corresponding clinical data can be inquired through the labels, multiplexing of the data can be achieved, compared with the prior art, the clinical data are preprocessed according to the screening condition corresponding to the labels when a plurality of screening conditions are needed to be set for each inquiry, the clinical data inquiry condition can be reduced, and therefore data inquiry efficiency is improved.
Furthermore, the labeling execution task can be generated according to the selected screening field and the data source and the set template, and the threshold and the difficulty of configuring the labeling execution task can be reduced.
Drawings
FIG. 1 is a flow chart of a method for tagging clinical data in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a clinical data labeling apparatus according to an embodiment of the present invention.
Detailed Description
As described above, hospital data has the characteristics of huge data volume, fast growth speed, diversified types and sources, and relatively low data value density, and currently, each time data is queried, a plurality of screening conditions need to be set to acquire the required data through complex screening operations.
In order to solve the problem, in the embodiment of the invention, when the trigger tagging execution task is detected, according to the corresponding data source and the screening condition of the labeled execution task, acquiring target clinical data meeting the screening condition from one or more data sources, labeling the target clinical data meeting the screening condition, wherein the label corresponds to the triggered labeled execution task, labeling the target clinical data by the above method, when clinical data is inquired subsequently, the corresponding clinical data can be inquired through the label, the multiplexing of data can be realized, compared with the prior art that each query needs to be provided with a plurality of screening conditions, since the clinical data is preprocessed according to the screening condition corresponding to the tag, the query condition of the clinical data can be reduced, and thus it is expected that the data query efficiency is improved.
In order to make the aforementioned objects, features and advantages of the embodiments of the present invention more comprehensible, specific embodiments accompanied with figures are described in detail below.
Referring to fig. 1, a flowchart of a labeling method for clinical data in an embodiment of the present invention is shown, which may specifically include the following steps:
and step S11, when the trigger labeling execution task is detected, acquiring target clinical data to be processed.
In particular implementations, tagging to perform tasks may be triggered in a variety of ways.
In an embodiment of the present invention, the tagging execution task may be actively triggered by the user. For example, a key for triggering labeling is arranged on the visual interface, and a user can trigger the labeling task by triggering the key arranged on the visual interface. As another example, a user may trigger a tagged execution task by entering a language or instructions for triggering the tagged execution task, or the like.
In another embodiment of the present invention, the tagging execution task may be executed periodically, and when the periodic execution time set by the tagging execution task is reached, the tagging execution task is triggered.
In specific implementation, the labeling execution task has corresponding data sources and screening conditions, the number of the data sources can be one or more, the data sources are used for providing target clinical data to be processed, and the data sources can be scientific research databases, databases of various hospitals, and other types of data sources. The screening condition is used for finding out the target clinical data meeting the requirement from the target clinical data to be processed in the data source.
In particular implementations, the tagged execution task may be created in a variety of ways.
In an embodiment of the present invention, the tagging execution task may be generated according to a set template according to the selected screening field and the data source.
In a specific implementation, the target clinical data is stored in the data source in a form of a table, different fields may be set in the table, the selected fields may be from fields in the table, that is, fields corresponding to all metadata in the data source may be selected as screening fields, and one or more selected screening fields form a screening condition, where metadata (metadata) is data (data about data) for describing data, and for each table, metadata is a field in a header of each table, such as name, gender, age, height, and the like. All fields in fields corresponding to all metadata in the data source can be used as screening fields and then as screening conditions to screen data, and flexibility of configuration of the screening conditions can be improved. In addition, the screening fields forming the screening conditions are from the fields of the metadata in the table, so that the probability of data being queried can be improved, and the accuracy of labeling is improved.
In some embodiments, SQL statements may be generated from the data source according to the selected filter fields and according to a set template, and tagged execution tasks may be generated based on the generated SQL statements.
Structured Query Language (SQL) is a database Query and programming Language for accessing data and querying, updating, and managing relational database systems. It is understood that other languages may be adopted, and a statement in the corresponding language is generated according to the selected filter field and the data source and the set template, and a labeled execution task is generated based on the generated statement.
In another embodiment of the invention, according to an input statement, semantic recognition is performed on the statement to obtain a data source and a screening condition, and a labeling execution task is generated based on the data source and the screening condition.
Specifically, a user can input a sentence through the visual operation interface, the input sentence can include a screening condition and a data source, the input sentence is subjected to semantic recognition, the data source and the screening condition can be extracted from the sentence, and a tagging execution task is generated based on the data source and the screening condition.
For example, the sentence input by the user through the visual operation interface is: in the first data source, a male obese patient with a height of over 150CM and a weight of over 120kg is searched. Performing semantic recognition on the statement, wherein the obtained screening conditions are as follows: height over 150CM, weight over 120kg and male, label name obesity. After the screening conditions of height over 150CM, weight over 120kg, male and the first data source are obtained, the labeling execution task can be generated according to the set template.
Furthermore, when generating the labeled execution task, the method can also configure the timing execution information of the task, and generate the labeled execution task according to the set template based on the timing execution information of the configured task, the screening condition and the data source. The timing execution information of the task can be used for controlling the time for executing the labeled execution task. For example, the tagging execution task is executed once per day. As another example, the tagging execution task is performed once per week. For another example, the tagging execution task is executed once a month. It can be understood that the execution period of the labeling execution task can also be set according to the actual requirement.
Further, the target clinical data to be processed may be acquired as follows. And acquiring a first time point of executing the labeling execution task in the previous period and acquiring a second time point of triggering the labeling execution task in the current period, wherein the first time point is before the second time point. And acquiring clinical data of which the generation time is between a first time point and a second time point from a data source, and taking the clinical data generated between the first time point and the second time point as target clinical data to be processed.
And step S12, screening the target clinical data according to the screening conditions.
In specific implementation, there may be a case where the data volume of the obtained target clinical data is large, and when the data volume of the target clinical data is large, in order to improve the efficiency of performing screening processing on the target clinical data, a multithreading manner may be adopted to asynchronously screen the target clinical data according to the screening conditions, so as to improve the efficiency of performing a task by tagging.
Specifically, when the data amount of the target clinical data exceeds a set threshold, the target clinical data is split into a plurality of data pieces. Each data fragment can be screened separately according to the screening conditions.
In particular implementations, the targeted clinical data may be split into multiple data segments in a variety of ways. For example, the target clinical data is divided into a plurality of data segments according to the generation time of each clinical data in the target clinical data and according to the set time interval duration. As another example, the target clinical data is split into multiple data segments by the size of the data volume. It is to be understood that the target clinical data may also be split in other ways, which are not illustrated here.
In step S13, the target clinical data satisfying the screening condition is labeled.
In specific implementation, after the target clinical data meeting the screening condition is obtained, the target clinical data meeting the screening condition may be labeled, where the label corresponds to the triggered labeled execution task, that is, each label has a one-to-one labeled execution task.
After the target clinical data meeting the screening condition is labeled, the association between the target clinical data and the label is established.
In particular implementations, each tag typically has a corresponding tag Identification (ID) and tag name. Each piece of clinical data includes patient identification information (e.g., patient ID), and after a certain piece of clinical data is labeled, an association between the label ID, the label name, and the patient ID is established.
Thereafter, for the labeled clinical data, in addition to being searched for by the specific information included in the clinical data, the labeled clinical data may also be searched for by the name of the label or the ID of the label, or the like.
For example, by the tag name "fat," all clinical data with the "fat" tag can be searched.
Therefore, when the trigger tagging execution task is detected, the target clinical data meeting the screening condition is acquired from one or more data sources according to the corresponding data sources and the screening condition of the tagging execution task, the target clinical data meeting the screening condition is tagged, the tag corresponds to the triggered tagging execution task, the tagging processing is performed on the target clinical data in the above mode, when the clinical data is subsequently queried, the corresponding clinical data can be queried through the tag, the data multiplexing can be realized, compared with the prior art, when a plurality of screening conditions are required to be set for each query, the clinical data query conditions can be reduced due to the fact that the clinical data are preprocessed according to the screening condition corresponding to the tag, and therefore the data query efficiency can be expected.
In specific implementation, the tags can be classified according to requirements, and different types of tags have different attributes or permissions and the like. For example, tags may be classified as personal tags, department tags, or yard-level tags. The usage right of the personal tag is only limited to the person who creates the tag, that is, only the user who creates the personal tag can see and use the personal tag, and the personal tag is invisible to the user who does not create the tag. The usage right of the department label or the institution label can be oriented to all users or specified user groups, for example, the department label or the institution label can be oriented to medical care and scientific research personnel of the whole hospital or medical care personnel or specified scientific research personnel of the hospital. As another example, a personal tag may be configured to be created directly without approval, while a department tag or an institution-level tag is configured to be created by an auditor.
Specifically, the generation of the labeled execution task based on the data source and the screening condition may be specifically realized by the following steps:
obtaining the type of the label, and determining the creation state of the label according to the type of the label; when the label is a personal label, generating the labeling execution task based on the data source and the screening condition, and creating the label; when the type of the tag is a department tag or a hospital-level tag, submitting a tag creation application to a specified object, determining the creation condition of the tag based on the audit feedback of the specified object, and creating the tag when the audit of the specified object passes; and when the specified object is not approved, the label is failed to be created.
Correspondingly, for the designated object, the tags needing to be audited can be checked through the tag management entry arranged on the visual operation interface. The designated object can be audited against the tag to be audited and give audit feedback, where the audit feedback can include audit pass or reject. The visual operation interface can be provided with a 'pass' key and a 'reject' key. When the specified object triggers the 'pass' key, the given audit feedback is that the audit is passed, and the label can be successfully created. When the specified object triggers the 'reject' key, the audit feedback gives a reject, and the label creation fails.
In particular implementations, the tags may be managed as desired. For example, when a delete operation of a tag is detected, the tag and a tagging execution task corresponding to the tag may be deleted. For another example, the name of the tag and the tag execution task corresponding to the tag may be modified according to the modification operation. It is understood that other management of the tags may be performed according to actual needs.
In specific implementation, the new tag, the deleted tag or the updated tag meeting the set condition may be counted according to the set statistical condition.
For example, the number of added tags, the number of deleted tags, and the number of updated tags in a certain time period are counted.
Further, after labeling the target clinical data that meets the screening criteria, derivative data can be generated and stored. The derived data may include at least: the tag ID of the tag, the patient ID of the patient to which the target clinical data corresponds, the name of the tag, and the like.
In particular implementations, the derived data generated may be used for querying and use of subsequent data. For example, statistical analysis may be performed based on the derived data and the results of the statistical analysis may be presented in a report format.
In the medical field, clinical data is generally data related to people, and can be generally divided into two dimensions of people and people, wherein people refer to patients, and the patients can be identified by patient IDs, patient names, medical insurance card numbers, identification card numbers and the like. The number of times of a person refers to each visit of a patient, and each visit of each patient can be regarded as one person. In performing statistical analysis based on the derived data, it may be performed on a person, person number, label, or the like basis.
In a specific implementation, the clinical data may be classified according to people or people times, and the clinical data may be labeled by using people or people times as labels to classify the clinical data.
For example, data associated with a patient is looked up and tagged with a label corresponding to the patient.
For another example, a certain visit of a certain patient is searched, and the data related to the visit of the patient is labeled with the visit. For example, data related to a second hospitalization of a certain patient is searched, and the searched data related to the second hospitalization are labeled with the second hospitalization.
The statistical analysis is carried out based on the derived data, on one hand, the range of the clinical data of the statistical analysis can be reduced, on the other hand, the corresponding value can be obtained under the condition that the original clinical data is not modified, the multiplexing of the labeled clinical data is realized, the generation and calculation of the later data can be reduced, the positioning of the information of the patient is accelerated, and the statistical analysis efficiency is improved. In addition, when performing statistical analysis or data search based on the derived data, the tag, the person, the number of people, the tag value, or each field in the clinical data can be used as the search condition. There may be one or more tags for a piece of clinical data, each of which may serve as a search criteria in the statistical analysis.
It is understood that some tags are valued tags, such as a gender tag can have tag values of 0, 1, where 0 represents male and 1 represents female, and for a valued tag, the derived data can be classified or tagged with the tag value.
In specific implementation, the abnormal point can be found according to the statistical analysis and report display result of the derived data.
In specific implementation, corresponding abnormal alarm threshold values can be set for some set fields in the report, whether the fields in the report reach the abnormal alarm threshold values or not is automatically detected, and when the abnormal alarm threshold values are reached, abnormal prompts can be output.
For example, when obesity statistics is performed based on the derived data, a weight field is set in the report, an abnormal alarm reminding threshold value of 180kg is set for the weight field, and when it is detected that the weight value of the data corresponding to the weight field is greater than 180kg, abnormal alarm reminding can be performed.
For another example, when statistical analysis is performed on a certain sign indicator of a certain patient, whether data corresponding to the sign is abnormal or not can be determined according to the variation trend of the data corresponding to the sign.
It can be understood that the statistical conditions concerned are different according to different actual statistical requirements, and the configuration may be specifically performed according to the actual requirements.
In particular, the clinical data may be labeled manually. For example, a user may directly tag clinical data in a data source, and for tags that already exist in a tag library, the user may select a tag from the tag library and bind the selected tag with the clinical data. As another example, when a user directly tags clinical data in a data source, the user may create a tag name and corresponding tag enforcement policy for tags that are not present in the database. The label library is used for storing each created label and a label execution task corresponding to each label.
In order to facilitate a person skilled in the art to better understand and implement the embodiments of the present invention, the embodiments of the present invention further provide a labeling apparatus for clinical data.
Referring to fig. 2, a schematic structural diagram of a labeling apparatus for clinical data in an embodiment of the present invention is shown. The labeling device 20 for clinical data may include:
the acquiring unit 21 is configured to acquire target clinical data to be processed when a trigger tagging execution task is detected, where the tagging execution task has a corresponding data source and a screening condition, the target clinical data is derived from the data source, and the number of the data sources is one or more;
a screening unit 22, configured to screen the target clinical data according to the screening condition;
and a labeling unit 23, configured to label the target clinical data meeting the screening condition, where the label corresponds to the triggered labeling execution task.
In a specific implementation, the specific working principle and the working flow of the clinical data labeling device 20 may refer to the description of the improved clinical data labeling method in the above embodiment of the present invention, and are not described herein again.
Embodiments of the present invention further provide a storage medium, where the computer-readable storage medium is a non-volatile storage medium or a non-transitory storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the computer program performs any of the steps of the method for tagging clinical data provided in the above embodiments of the present invention.
The embodiment of the present invention further provides a terminal, which includes a memory and a processor, where the memory stores a computer program that can be run on the processor, and the processor executes any of the steps of the method for tagging clinical data provided in the above embodiment of the present invention when running the computer program.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in any computer readable storage medium, and the storage medium may include: ROM, RAM, magnetic or optical disks, and the like.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (15)
1. A method for tagging clinical data, comprising:
when a trigger tagging execution task is detected, acquiring target clinical data to be processed, wherein the tagging execution task is provided with a corresponding data source and a screening condition, the target clinical data is sourced from the data source, and the number of the data sources is one or more;
screening the target clinical data according to the screening conditions;
and labeling the target clinical data meeting the screening condition, wherein the label corresponds to the triggered labeling execution task.
2. The method of tagging clinical data according to claim 1, wherein the tagging performance task is created by:
generating the labeling execution task according to the selected screening field and the data source and a set template;
or according to the input statement, performing semantic recognition on the statement to obtain the data source and the screening condition, and generating the labeling execution task based on the data source and the screening condition.
3. The method of tagging clinical data according to claim 2, wherein said generating said tagged execution task comprises:
configuring timing execution information of a task, and generating the labeled execution task according to the timing execution information of the task, the screening condition and a data source and a set template, wherein the timing execution information of the task is used for controlling the time for executing the labeled execution task.
4. The method of claim 2, wherein the generating the tagged execution task based on the data source and the screening criteria comprises:
obtaining the type of the label, and determining the creation state of the label according to the type of the label;
when the label is a personal label, generating the labeling execution task based on the data source and the screening condition, and creating the label;
when the type of the tag is a department tag or an institution-level tag, submitting a tag creation application to a specified object, determining the creation condition of the tag based on audit feedback of the specified object, creating the tag when the audit of the specified object passes, and failing to create the tag when the audit of the specified object does not pass.
5. The method of labeling clinical data according to claim 1, further comprising: and when the deleting operation of the label is detected, deleting the label and the corresponding labeling execution task.
6. The method for tagging clinical data according to claim 1, wherein the obtaining target clinical data to be processed comprises:
acquiring a first time point of executing the labeling execution task in the previous period and a second time point of triggering the labeling execution task in the current period, wherein the first time point is before the second time point;
and acquiring the clinical data of which the generation time is between the first time point and the second time point from the data source, and taking the clinical data generated between the first time point and the second time point as the target clinical data.
7. The method for labeling clinical data according to claim 1, wherein the screening the target clinical data according to the screening condition comprises:
when the data volume of the target clinical data exceeds a set threshold, splitting the target clinical data into a plurality of data segments;
and respectively screening each data fragment according to the screening conditions.
8. The method of tagging clinical data as claimed in claim 7, wherein said splitting said target clinical data into a plurality of data segments comprises:
according to the generation time of each clinical data in the target clinical data and the set time interval duration, the target clinical data is divided into a plurality of data segments.
9. The method for labeling clinical data according to claim 1, wherein the screening the target clinical data according to the screening condition comprises:
and adopting a multithreading mode to asynchronously screen the target clinical data according to the screening conditions.
10. The method of tagging clinical data according to any one of claims 1 to 9, further comprising:
after labeling the target clinical data meeting the screening conditions, generating and storing derivative data, wherein the derivative data at least comprises: identification information of the tag, identification information of a patient corresponding to the target clinical data, and a name of the tag.
11. The method for tagging clinical data according to claim 10, wherein said generating derivative data comprises:
and generating the derivative data according to a set period, or generating the derivative data in real time by matching with a labeling execution operation.
12. The method of labeling clinical data according to claim 10, further comprising:
obtaining a statistical condition;
and acquiring data meeting the statistical condition from the derived data, and displaying the data.
13. An apparatus for tagging clinical data, comprising:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring target clinical data to be processed when a tag execution task is detected to be triggered, the tag execution task is provided with a corresponding data source and a screening condition, the target clinical data is sourced from the data source, and the number of the data sources is one or more;
the screening unit is used for screening the target clinical data according to the screening conditions;
and the labeling unit is used for labeling the target clinical data meeting the screening condition, wherein the label corresponds to the triggered labeling execution task.
14. A storage medium, a computer-readable storage medium being a non-volatile storage medium or a non-transitory storage medium, having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, performs the steps of the method of tagging clinical data according to any one of claims 1 to 12.
15. A terminal comprising a memory and a processor, the memory having stored thereon a computer program operable on the processor, wherein the processor, when executing the computer program, performs the steps of the method of tagging clinical data of any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010948805.4A CN112289454B (en) | 2020-09-10 | 2020-09-10 | Labeling method and device for clinical data, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010948805.4A CN112289454B (en) | 2020-09-10 | 2020-09-10 | Labeling method and device for clinical data, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112289454A true CN112289454A (en) | 2021-01-29 |
| CN112289454B CN112289454B (en) | 2022-06-17 |
Family
ID=74420396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010948805.4A Active CN112289454B (en) | 2020-09-10 | 2020-09-10 | Labeling method and device for clinical data, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112289454B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674867A (en) * | 2021-07-27 | 2021-11-19 | 上海药慧信息技术有限公司 | Clinical data mining method and device, electronic equipment and storage medium |
| CN114334067A (en) * | 2022-03-10 | 2022-04-12 | 上海柯林布瑞信息技术有限公司 | Label processing method and device for clinical data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104111994A (en) * | 2014-07-04 | 2014-10-22 | 北京思特奇信息技术股份有限公司 | Label data screening method and device based on mixed data source |
| CN109524120A (en) * | 2018-11-09 | 2019-03-26 | 医渡云（北京）技术有限公司 | Calculation method, system, equipment and storage medium are extracted in clinical data automation |
| US20190205303A1 (en) * | 2017-12-28 | 2019-07-04 | Alibaba Group Holding Limited | Data processing method and apparatus |
| CN110737706A (en) * | 2019-09-06 | 2020-01-31 | 平安城市建设科技(深圳)有限公司 | Data management method, device, equipment and computer readable storage medium |
| CN110955481A (en) * | 2019-11-27 | 2020-04-03 | 北京锐安科技有限公司 | Label task generation method and device, storage medium and electronic equipment |
-
2020
- 2020-09-10 CN CN202010948805.4A patent/CN112289454B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104111994A (en) * | 2014-07-04 | 2014-10-22 | 北京思特奇信息技术股份有限公司 | Label data screening method and device based on mixed data source |
| US20190205303A1 (en) * | 2017-12-28 | 2019-07-04 | Alibaba Group Holding Limited | Data processing method and apparatus |
| CN109524120A (en) * | 2018-11-09 | 2019-03-26 | 医渡云（北京）技术有限公司 | Calculation method, system, equipment and storage medium are extracted in clinical data automation |
| CN110737706A (en) * | 2019-09-06 | 2020-01-31 | 平安城市建设科技(深圳)有限公司 | Data management method, device, equipment and computer readable storage medium |
| CN110955481A (en) * | 2019-11-27 | 2020-04-03 | 北京锐安科技有限公司 | Label task generation method and device, storage medium and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674867A (en) * | 2021-07-27 | 2021-11-19 | 上海药慧信息技术有限公司 | Clinical data mining method and device, electronic equipment and storage medium |
| CN114334067A (en) * | 2022-03-10 | 2022-04-12 | 上海柯林布瑞信息技术有限公司 | Label processing method and device for clinical data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112289454B (en) | 2022-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10019431B2 (en) | Systems and methods for active column filtering | |
| US9875293B2 (en) | System and method for news events detection and visualization | |
| JP2013137763A (en) | System and method for merging source record based on existence rule | |
| US10235637B2 (en) | Generating feature vectors from RDF graphs | |
| AU2018411565B2 (en) | System and methods for generating an enhanced output of relevant content to facilitate content analysis | |
| CN112289454B (en) | Labeling method and device for clinical data, storage medium and terminal | |
| TW201421395A (en) | System and method for recursively traversing the internet and other sources to identify, gather, curate, adjudicate, and qualify business identity and related data | |
| CA2985961C (en) | Domain specific language to query medical data | |
| US10585869B2 (en) | System and method for generating, maintaining, and querying a database for computer investigations | |
| US20150193511A1 (en) | Graphical record matching process replay for a data quality user interface | |
| US11636078B2 (en) | Personally identifiable information storage detection by searching a metadata source | |
| WO2014173946A1 (en) | Database management system | |
| CN111143422A (en) | Data retrieval method, data retrieval device, storage medium, and electronic device | |
| US10146881B2 (en) | Scalable processing of heterogeneous user-generated content | |
| CN116541752B (en) | Metadata management method, device, computer equipment and storage medium | |
| US20120259661A1 (en) | Systems and methods for data mining of DICOM structured reports | |
| US20180046779A1 (en) | Caching technology for clinical data sources | |
| US11475031B2 (en) | Identification and compiling of information relating to an entity | |
| CN117076742A (en) | Data blood edge tracking method and device and electronic equipment | |
| JP2006107299A (en) | Medical information system and medical information display method | |
| US10311049B2 (en) | Pattern-based query result enhancement | |
| WO2014114761A1 (en) | Data management system | |
| US11880392B2 (en) | Systems and methods for associating data with a non-material concept | |
| Senthilkumar et al. | A unified approach to detect the record duplication using bat algorithm and fuzzy classifier for health informatics | |
| WO2018031012A1 (en) | Caching technology for clinical data sources |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Labeling methods and devices, storage media, and terminals for clinical data Granted publication date: 20220617 Pledgee: Minhang Branch of Shanghai Rural Commercial Bank Co.,Ltd. Pledgor: Shanghai kelinbrui Information Technology Co.,Ltd. Registration number: Y2024310000269 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |