CN110675924B - Method and device for automatically generating case report table, readable medium and electronic equipment - Google Patents
Method and device for automatically generating case report table, readable medium and electronic equipment Download PDFInfo
- Publication number
- CN110675924B CN110675924B CN201910766199.1A CN201910766199A CN110675924B CN 110675924 B CN110675924 B CN 110675924B CN 201910766199 A CN201910766199 A CN 201910766199A CN 110675924 B CN110675924 B CN 110675924B
- Authority
- CN
- China
- Prior art keywords
- data
- case report
- configuration file
- report table
- filled
- 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.)
- Active
Links
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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for automatically generating a case report table, a computer readable storage medium and electronic equipment, wherein the method comprises the following steps: performing semantic triple processing on standard subject data corresponding to the clinical trial scheme to determine clinical trial research data; and determining a first target case report table according to the first configuration file of the case report table to be filled corresponding to the clinical test scheme and the clinical test research data. By the technical scheme, the target case report table is automatically generated, the target case report table does not need to be manually filled, errors in the manual filling process are avoided, and therefore the input efficiency and the data quality of the target case report table are improved.
Description
Technical Field
The invention relates to the technical field of energy, in particular to a method, a device, a readable medium and electronic equipment for automatically generating a case report table.
Background
The clinical trial needs to design a Case Report Form (CRF) meeting the requirements of clinical trial protocol before starting, and the Case report form is a file designed according to the clinical trial protocol and used for recording the trial data of each subject in the research process. The quality and efficiency of case report entry is a key factor affecting the final quality and cost of clinical trials.
Currently, the recording mode of the case report table is mainly manually copied from an electronic medical record system or a paper medical record into the case report table by a Clinical coordinator (CRC).
However, clinical coordinators need to browse and search massive information in electronic information systems or paper medical records in hospitals according to characteristic information of subjects, and can perform manual entry only after fully understanding whether semantics of fields in a case report table are consistent with semantics of fields in the medical records according to found medical record information, so that entry time of the case report table and the possibility of data errors (such as transcription errors and missing reports) are increased, and entry efficiency and data quality of the case report table are reduced.
Disclosure of Invention
The invention provides a method and a device for automatically generating a case report table, a computer readable storage medium and electronic equipment, which are used for automatically generating a target case report table without manually filling the target case report table, so that errors in the manual filling process are avoided, and the input efficiency and the data quality of the target case report table are improved.
In a first aspect, the present invention provides a method for automatically generating a case report table, including:
performing semantic triple processing on standard subject data corresponding to the clinical trial scheme to determine clinical trial research data;
and determining a first target case report table according to the first configuration file of the case report table to be filled corresponding to the clinical test scheme and the clinical test research data.
Preferably, the first and second liquid crystal display panels are,
further comprising: determining a synonym array corresponding to a standard name in a clinical test scheme according to a preset storage form, forming a synonym library according to the synonym array, and establishing an index mode of the synonym library;
and inquiring whether synonyms exist in the sample subject data corresponding to the clinical test scheme in the synonym library according to the index mode, and when the synonyms exist, replacing the synonyms by using the standard name words corresponding to the existing synonyms to determine standard subject data.
Preferably, the first and second electrodes are formed of a metal,
performing semantic triple processing on two-dimensional data in standard subject data corresponding to the clinical test scheme to determine semantic triple data;
performing data correlation on the semantic triple data based on subject identification to determine clinical trial study data.
Preferably, the first and second electrodes are formed of a metal,
determining a first target case report table according to the first configuration file of the case report table to be filled corresponding to the clinical test scheme and the clinical test research data, wherein the determining of the first target case report table comprises the following steps:
generating a first configuration file based on semantic triples according to a case report table to be filled corresponding to the clinical test scheme, wherein the first configuration file comprises a data selection rule;
matching the first configuration file with data in the clinical trial research data to obtain pre-filled data;
and correspondingly filling the pre-filling data into the case report table to be filled so as to determine a first target case report table.
Preferably, the first and second electrodes are formed of a metal,
further comprising: and according to a second configuration file corresponding to the clinical test scheme, performing data verification on the data in the first target case report table to determine a verification label, and determining a second target case report table according to the verification label.
Preferably, the first and second electrodes are formed of a metal,
the data verification of the data in the first target case report table according to the second configuration file corresponding to the clinical trial scheme to determine a verification tag, and the determination of the second target case report table according to the verification tag includes:
generating a second configuration file based on the semantic triple according to the clinical test scheme, wherein the second configuration file comprises a data inspection rule corresponding to the first configuration file;
performing data verification on the data in the first target case report table according to the second configuration file, and determining a verification tag corresponding to the data, wherein the verification tag marks abnormal data in the first target case report table, or corrects the first configuration file, and/or the second configuration file and/or standard subject data;
and determining a second target case report table according to the check label corresponding to the data.
Preferably, the first and second electrodes are formed of a metal,
and when the data in the first target case report table does not meet the data inspection rule, determining a check label corresponding to the data.
In a second aspect, the present invention provides an apparatus for automatically generating a case report form, comprising:
the semantic processing module is used for performing semantic triple processing on standard subject data corresponding to the clinical test scheme so as to determine clinical test research data;
and the table generation module is used for determining a first target case report table according to the first configuration file of the case report table to be filled corresponding to the clinical test scheme and the clinical test research data.
In a third aspect, the invention provides a computer-readable storage medium comprising executable instructions which, when executed by a processor of an electronic device, cause the processor to perform the method according to any one of the first aspect.
In a fourth aspect, the present invention provides an electronic device, comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method according to any one of the first aspect.
The invention provides a method, a device, a computer readable storage medium and electronic equipment for automatically generating a case report table, wherein the method comprises the steps of performing semantic triple processing on standard subject data corresponding to a clinical test scheme to determine clinical test research data which is convenient to store, analyze and process, and selecting required data of the case report table to be filled from the clinical test research data according to a first configuration file of the case report table to be filled corresponding to the clinical test scheme so as to automatically generate a first target case report table without manual filling, thereby reducing the recording time of the target case report table, avoiding data errors caused by manual filling and improving the data quality of the target case report table.
Further effects of the above-mentioned unconventional preferred modes will be described below in conjunction with specific embodiments.
Drawings
In order to more clearly illustrate the embodiments or the prior art solutions of the present invention, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a schematic flow chart of a method for automatically generating a case report table according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of another method for automatically generating a case report table according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus for automatically generating a case report table according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail and completely with reference to the following embodiments and accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As previously known, the data in the case report form is often manually filled in. The manual filling is time-consuming and labor-consuming, and the filling errors and omissions are easy to occur. The invention tries to establish clinical trial research data based on the semantic triples based on the standard subject data, and automatically generates a first target case report table by utilizing a first configuration file of the case report table to be filled corresponding to the clinical trial scheme. Compared with the traditional method, the method has the advantages that the research cost of clinical tests is reduced, the research efficiency is improved, and meanwhile, data errors in the manual filling process can be avoided.
Referring to fig. 1, a method for automatically generating a case report table according to an embodiment of the present invention is shown. The method in this embodiment includes the following steps:
Clinical trials refer to any systematic study of drugs in humans (patients or healthy volunteers) to confirm or reveal the effects, adverse effects and/or absorption, distribution, metabolism and excretion of the test drugs in order to determine the efficacy and safety of the test drugs. Clinical trials are a necessary process for the clinical application of new drugs and new therapies from laboratories, and with the rapid development of pharmaceutical and medical technologies, the demand for clinical trials has become more and more abundant, and more patients are expected to be exposed to the latest therapeutic drugs or therapeutic methods through clinical trials.
The Linchuan protocol describes in detail how a clinical trial should be conducted, including subject inclusion/exclusion criteria, trial objectives, brief introduction to trial drugs, trial design and study methodology, observation metrics, data processing analysis, and how to deal with adverse events.
The test subjects are important components of clinical trial research, for a clinical trial, a clinical researcher can determine a clinical trial scheme corresponding to the clinical trial, a plurality of test subjects meeting the grouping standard are selected according to the clinical trial scheme, in order to ensure the reliability and the effectiveness of the clinical trial, after the test drugs are taken by the test subjects, the test subjects need to regularly check according to a visit period (the clinical trial scheme is usually provided with a visit window which is a time period within the scope of each visit period specified by the clinical trial scheme, the visit period is an ultra-window, the visit period is specifically the date of the test subject check, the visit times are calculated from the day when the test drugs are taken by the test subjects, the visit window exists in each visit, and the time interval between two visit periods is the visit period), the check data of the test subjects are collected to obtain comprehensive and complete test subject data, the test subject data are usually stored in an electronic information system in a hospital for convenient data record management, and the condition that the test subjects can be subjected to the ultra-window and multiple collection in the regular check process is considered, a case report table is used for collecting, screening, summarizing the test subject data, and determining the curative effect of the subsequent drug and the subsequent test.
In the data collection process of the testee, considering the problem that the data unit and the data format of the testee data are diversified, in order to ensure the uniformity of the data of the testee, the data unit and the data format of the unified testee data are required to be unified in advance to determine the standard data of the testee, in order to store, analyze and process the data more conveniently, the data of the standard testee is subjected to semantic triple processing to determine the clinical test research data, the clinical test research data do not change the data of the standard testee, and therefore the reasonable and effective analysis result is ensured.
And 102, determining a first target case report table according to the first configuration file of the case report table to be filled corresponding to the clinical test scheme and the clinical test research data.
The technical scheme provided by the embodiment of the invention is that for a certain clinical test, a clinical researcher already designs a clinical test scheme corresponding to the clinical test, so that the standard subject data and the first configuration file both correspond to the same clinical test scheme, and the reasonability of a first target case report table corresponding to the clinical test scheme is ensured.
The case report form is a file designed according to the clinical test protocol and is a carrier for collecting data of the testee. After a clinical trial plan is formulated, a clinical researcher usually designs a case report table under the cooperation of biomedicine, for example, a plurality of questions related to effectiveness indexes and safety indexes are determined in a targeted manner according to requirements of the clinical trial plan, the questions are divided to determine a plurality of tables, each table comprises a plurality of questions and fields to be filled corresponding to the questions, a preset case report table is formed by using the tables, and a plurality of data values corresponding to the fields to be filled are subsequently recorded into the preset case report table, so that the case report table can be obtained.
The preset case report table indirectly represents the requirements of a clinical trial scheme, a first configuration file of the case report table to be filled can be determined according to the preset case report table, the case report table to be filled comprises a plurality of tables, each table comprises a plurality of subjects to be filled and fields to be filled corresponding to the subjects to be filled, each field to be filled comprises a plurality of data items to be filled, one data item corresponds to one cell and one subject, the condition of multi-acquisition of data of a single inspection index of the subject is considered, the clinical trial research data generally records the data of the subject comprehensively, so that one data item to be filled possibly corresponds to a plurality of data values in the clinical trial research data, at the moment, a reasonable data value corresponding to the data value to be filled is selected from the plurality of data values to be filled in the data item to be filled, and the reference value of the data in the first target case report table is ensured. In order to accurately determine each topic and each corresponding field in a case report table to be filled from clinical trial research data, a first configuration file of the case report table to be filled needs to be determined, the first configuration file can select each topic and each corresponding field from the clinical trial research data, and the topics and the corresponding fields of the topics are filled into the case report table to be filled correspondingly so as to automatically generate a first target case report table, and the first target case report table can timely, completely and accurately record standard subject data.
According to the technical scheme, the method has the beneficial effects that: based on semantic triple processing, standard subject data can be processed in a unified mode so as to be convenient for subsequent storage, analysis and processing, based on a first configuration file of a case report table to be filled, all questions and fields corresponding to all the questions can be selected from clinical test research data to be filled into the case report table to be filled, so that a first target case report table can be generated automatically, manual filling of the case report table is not needed in the process, the labor cost of clinical tests is reduced, errors in the manual filling process are avoided, and therefore the entry efficiency and the data quality of the target case report table are improved.
Fig. 1 shows only a basic embodiment of the method of the present invention, and based on this, certain optimization and expansion can be performed, and other preferred embodiments of the method can also be obtained.
Fig. 2 shows another embodiment of the method for automatically generating a case report table according to the present invention. Based on the foregoing embodiments, the present embodiment performs more detailed description and a certain degree of optimization on the process of automatically generating the second target medical record report table. For ease of explanation and illustration, the present embodiments will be described in conjunction with the following detailed scenarios. Of course, it should be understood that the method described in the present embodiment is also applicable in other relevant scenarios.
The specific scenario combined in this embodiment is as follows: clinical researchers designed clinical trial protocols for phase III clinical trials of XXX drugs, the clinical trial protocols corresponding to sample subject data, the sample subject data including a plurality of tables, each table including partial data corresponding to all subjects, the plurality of tables recording complete data of the subjects, exemplified here by sample subject data including a subject basis information table from 2018, no. 4, month 5 to 2018, no. 4, month 6, a blood routine checklist, a urine routine checklist. The method aims to automatically generate a second target medical record report table of the clinical test scheme based on standard subject data corresponding to the clinical test scheme.
In an actual method, the data size in the sample subject data is large, and considering the data processing manner of each table is similar, for convenience of description, only the blood routine checklist in the sample subject data is taken as an example for explanation, and it is assumed that specific contents of the blood routine checklist from No. 4/month 5 in 2018 to No. 4/month 6 in 2018 are as shown in table 1:
TABLE 1
In table 1, A1 represents the result of white blood cell count in the blood routine test item of 2018, month 4 and 4 of the subject with subject number 001, and the meanings of the other data are the same and are not repeated.
The method in this embodiment includes the following steps:
The clinical trial protocol typically includes a plurality of standard names, which specifically refer to nouns that can be used as the case report in the clinical trial protocol, for example, the standard names may be "white blood cell count", "subject number", "test item", "sub item", "unit", etc. in table 1. The standard name word corresponds to a plurality of synonyms (a group of words having the same or similar meaning), for convenience of subsequent storage query, the plurality of synonyms corresponding to the standard name word are organized and stored in an array form of key-value (key-value) to determine a synonym array corresponding to the standard name word, the synonym array specifically refers to a set of a plurality of synonyms corresponding to the standard name word, and taking the standard name word as "white cell count" in table 1, and taking the plurality of synonyms corresponding to the white cell count "as" white cell count "," white cell (WBC) "," WBC "as examples, and organizing the" white cell count "," WBC (WBC) "," WBC "corresponding to the" white cell count "to obtain" white cell count: synonym array of [ white blood cell count, white Blood Cell (WBC), WBC ] "," white blood cell count "corresponds to" key "in the key-value," [ white blood cell count, white Blood Cell (WBC), WBC ] corresponds to "value" in the key-value.
The synonym arrays stored by the key values form a synonym library, an index mode can be established for the synonym library for quickly determining the standard name words corresponding to a certain noun, when a certain noun is input, the electronic equipment can quickly inquire the standard name words corresponding to the input noun, the index mode comprises but is not limited to inverted index, a document list containing a certain noun can be quickly obtained, the document list comprises the synonym array corresponding to the noun, and therefore the standard name words corresponding to the noun are determined from the synonym array.
In order to normalize the data to facilitate storage, analysis and processing of the electronic device, synonym query needs to be performed on nouns of the sample subject data to determine whether the nouns have synonyms, that is, whether the nouns are standard names is judged, when the nouns have synonyms, the nouns are replaced by the standard names corresponding to the nouns, synonym normalization processing is performed on all nouns in the sample subject data, and then standard subject data is obtained, the obtained standard subject data does not contain synonyms, and all nouns are standard names.
It should be noted that the sample subject data may be subjected to other data preprocessing that does not include synonym standardization processing, such as unifying unit and data format, but the data dimension of the sample subject data cannot be reduced, so as to ensure the trueness of the sample subject data.
For example, if the synonyms "white blood cell count" and "WBC" in table 1 are found in the synonyms library, and "white blood cell count" is used instead of "white blood cell count" and "WBC", the contents of the standard blood routine look-up table are as shown in table 2:
TABLE 2
The meaning of each data in table 2 is the same as table 1, and is not repeated.
And 203, performing semantic triple processing on the two-dimensional data in the standard subject data to determine semantic triple data.
The standard subject data is two-dimensional data, and the two-dimensional data specifically refers to data corresponding to two different attributes, for example, data values in cells with intersecting rows and columns in a table, so that the recording of electronic equipment is facilitated, the processing speed is improved, the two-dimensional data is converted into data of a pivot structure, namely semantic triple processing is performed on each two-dimensional data in the standard subject data, and semantic triple data is formed by using each two-dimensional data subjected to the semantic triple processing.
For example, in table 2, semantic triple processing is performed on a plurality of two-dimensional data corresponding to the subject number 001, except for the column data (e.g., 001, 002, 003, … …) corresponding to the subject number, the check item, the sub-item, the date, the unit, and the column data corresponding to the subject number in table 2, the other data are two-dimensional data, e.g., A1, A2, A3, etc., and the specific content corresponding to the subject number 001 is as shown in table 3:
TABLE 3
Specific contents of the plurality of two-dimensional data in table 3 are as in table 4:
TABLE 4
Semantic triplexing the two-dimensional data in table 3 (i.e. the data values in the cells in table 4) to obtain semantic triples corresponding to the subject with subject number 001, where the semantic triples corresponding to the subject with subject number 001 include the following specific contents:
event1: [001, test item, blood routine ]
Event2: [ Event1, check date, 2018.4.4]
Event3: [ Event1, subentry, white blood cell count ]
Event4: [ Event2, result, A1]
Event5: [ Event2, unit, 10^9/L ]
Event6 [ Event1, check date, 2018.4.5]
Event7: [ Event6, result, A2]
Event8: [ Event7, unit, 10^9/L ]
Event9: [ Event1, check date, 2018.4.6]
Event10: [ Event9, result, A3]
Event11: [ Event9, unit, 10^9/L ]
Wherein, event1 [001, inspection item, blood routine ] is a semantic triple, event1 [001, inspection item, blood routine ] indicates that the inspection item corresponding to the subject with the subject number 001 is blood routine, event1 in Event2 [ Event1, inspection date, 2018.4.4] indicates that Event1 [001, inspection item, blood routine ], that is, event2 [ Event1, inspection date, 2018.4.4] indicates that the inspection item corresponding to the subject with the subject number 001 is blood routine inspection date of 2018, 4 months and 4 days, and the meaning of other semantic triples is the same and is not repeated.
Each subject corresponds to a plurality of semantic triples, and the semantic triples corresponding to the subjects form semantic triplet data.
And 204, performing data association on the semantic triple data based on the subject identification to determine clinical trial research data.
In order to facilitate the subsequent analysis of the semantic triple data, a plurality of semantic triples in the semantic triple data need to be associated, and here, a subject is associated with a plurality of semantic triples corresponding to the subject to form a semantic triple network corresponding to the subject, and clinical trial study data is further formed through the semantic triple networks respectively corresponding to the subjects. Here, subject identification includes, but is not limited to, a subject number. Since each subject identifier is unique, a plurality of semantic triads corresponding to the same subject identifier can be associated to establish a semantic triad network corresponding to the subject, and a knowledge network is formed by the semantic triad networks of the plurality of subjects, so that clinical trial research data can be determined.
For example, taking the specific content of the semantic triples corresponding to the subject with the subject number 001 as an example, event3: [ Event1, subentry, white blood cell count ] is associated with Event2: [ Event1, inspection date, 2018.4.4], event6: [ Event1, inspection date, 2018.4.5], event9: [ Event1, inspection date, 2018.4.6], event2: [ Event1, inspection date, 2018.4.4] is associated with Event1: [001, inspection item, blood routine ], and the association relationship of the semantic triples with Event2: [ Event1, inspection date, 2018.4.4] is similar and not described much.
The method comprises the steps of determining a preset case report table according to a clinical test scheme, wherein the preset case report table comprises a plurality of tables, each table comprises a plurality of topics and fields to be filled corresponding to the topics for convenient sorting and analysis, the plurality of topics comprise, but are not limited to, subject numbers, sexes, ages, verification times, inspection items and the like, in order to automatically generate a first target case report table, a first configuration file needs to be determined, in order to ensure the accuracy of the first configuration file and the uniformity of the first configuration file and clinical test research data, the first configuration file based on semantic triplets is generated according to the preset case report table of the clinical test scheme, in consideration of the fact that overwindow data exists in standard subject data and data is subjected to multi-sampling on a certain inspection index during inspection, the first configuration file comprises data selection rules of the topics to be filled in the case report table to be filled and the fields to be filled corresponding to the topics, the plurality of data values in the fields to be filled respectively correspond to one subject, the first configuration file can also comprise data selection rules corresponding to the records in the case report table to be filled, the data in the fields to be filled respectively correspond to one subject, and the specific data filling rules in the case report table are not limited, and the embodiments of the invention are provided.
It should be noted that the first configuration file based on the semantic triple can be directly generated according to the to-be-filled case report table in the clinical trial scheme, and the method has high technical difficulty and high cost. Or, determining a first initial configuration file according to a case report table to be filled in a clinical trial scheme, wherein the first initial configuration file has a wider application range, a simple file format and easy processing, and the first initial configuration file is converted into a semantic triple to form the first configuration file.
For example, suppose that the clinical trial plan includes 3 visit periods, the first visit period is the day of taking the trial medicine, the second visit period is the ith day of taking the medicine, the third visit period is the i + n th day of taking the trial medicine, the third visit period of the subject in the clinical trial plan is 2018/4/1 as an example, the data selection rule of the result of the white blood cell count of the third visit period (2018/4/1) in the first target case report table is the result of selecting the white blood cell count of the time closest to the third visit period (2018/4/1), the subject number in the case report table is 001, and the specific content of the first configuration file corresponding to the result of the white blood cell count of the third visit period (2018/4/1) is as follows:
event10 [ subject, subject number, 001]
Event20 [ Event10, subentry, white blood cell count ]
Event30 [ Event10, third visit period, 2018.4.1]
Event40 [? Recently, event30]
Where Event20: [ Event10, children, white blood cell count ] is associated with Event30: [ Event10, third visit, 2018.4.1], event40 [? Recently, "? "indicates absent, event40 [? Recently, event30] indicates that subject number 001 picked the white blood cell count closest to the third visit session (2018/4/1) as a result of his white blood cell count at the third visit session (2018/4/1).
And step 206, matching the first configuration file with data in the clinical trial research data to obtain pre-filling data, and correspondingly filling the pre-filling data into the case report table to be filled so as to determine a first target case report table.
Here, the first profile and the clinical trial study data are connected by the subject identifier, so that the first profile can be matched with the data in the clinical trial study data according to the subject identifier.
The first configuration file can reasonably select pre-filling data from clinical trial research data, the pre-filling data comprises all questions corresponding to a case report table to be filled and fields corresponding to all the questions, the fields comprise a plurality of data values corresponding to the questions, the pre-filling data is correspondingly filled into the case report table to be filled, a first target case report table is automatically generated, the first target case report table comprises a plurality of fields and the questions corresponding to the fields, or the first target case report table comprises a plurality of records, and one record is a line of data.
It should be noted that, according to the data selection rule in the first configuration file, the pre-filled data selected from the clinical trial study data has a greater reference value for the clinical trial, that is, the first target case report table has a greater reference value.
For example, the subject with the subject number of 001 acquires the result of the white blood cell count corresponding to each of the 2018/4/4 to 2018/4/6 days in the periodic inspection process, while the to-be-filled case report table only needs the result of the white blood cell count of the third visit period (2018/4/1), at this time, the result of the white blood cell count is selected from the clinical trial research data according to the first configuration file and is filled in the to-be-filled case report table, taking the specific content of the first configuration file as an example, according to the subject number of 001, the first configuration file is matched with the semantic triad network corresponding to the subject number of 001 in the clinical trial research data to obtain the result of the white blood cell count of A1, and the A1 can be filled in the data item of the result of the white blood cell count of 2018/4/1 corresponding to the subject number of 001 in the to-be-filled in the case report table.
The data in the automatically generated first target case report table is only selected from clinical trial research data, and the obtained data in the first target case report table is ensured to be complete and accurate, so that the quality of the clinical trial research data is ensured, and the safety and the effectiveness of the medicine are favorably evaluated. Meanwhile, the case report table does not need to be manually filled in the process, the labor cost of the clinical test is reduced, the research efficiency of the clinical test is improved, and errors (such as transcription errors and data omission) in the manual filling process are avoided.
And step 207, generating a second configuration file based on the semantic triple according to the clinical test scheme, wherein the second configuration file comprises a data inspection rule corresponding to the first configuration file.
Different access windows are corresponding to different clinical test schemes, and different access windows (for example, some clinical test schemes require blood pressure to be measured within 2 minutes, electrocardiogram to be measured within two minutes, blood drawing to be performed within two minutes, blood pressure to be measured within 1 hour, electrocardiogram to be measured within 1 hour, and blood drawing to be performed within 1 hour) correspond to different data selection requirements and data ranges, in order to ensure the accuracy and the uniformity of the second configuration file, a second configuration file based on semantic triples is generated according to the clinical test schemes, the second configuration file comprises data inspection rules corresponding to the first configuration file, the data inspection rules mainly aim at fields and/or records in the first target case report table, or the overall data condition, not aiming at a single data value, and mainly detect abnormal data in the first target case report table, and the abnormal data comprises but is not limited to overwindow data, data outside a value range (data value range), and missing data.
It should be noted that the second configuration file based on the semantic triple can be directly generated according to the clinical test scheme, and the method has high technical difficulty and high cost. Or, according to the clinical trial scheme, determining a second initial configuration file, where the second initial configuration file is simple in file format, easy to process, and wide in application range, and by performing semantic triple conversion on the second initial configuration file to form the second configuration file, the method may generate the second configuration file more simply, and may modify the second configuration file easily, and specifically, what manner to generate the second configuration file may be determined in combination with actual requirements.
For example, taking the example of detecting whether the blood routine corresponding to the subject with the subject number 001 is over-window or not, and the data checking rule of whether the over-window is the third visit period (2018/4/1) + -1 day, the specific contents of the second configuration file are as follows:
event100: [ subject, subject number, 001]
Event200 [ Event100, third visit period, 2018.4.1]
Event300 [ actual check time, calculated time difference, distance ]
Event400 [ Event300, value field, + -1]
The data in the first target case report table can be subjected to data verification in consideration of the data quality and the data reference value of the first target case report table, wherein the data comprises each field, each record and the whole data so as to verify the data in the first target case report table in all directions and angles, one field comprises a plurality of data values corresponding to one subject, one record comprises a plurality of data values corresponding to one subject, and the data detection is mainly based on the fields and/or the records and mainly aims to determine the accuracy and the abnormal condition of the plurality of data values in the fields and/or the records. When the data values in the fields and/or records do not satisfy the data checking rule, it is indicated that the data values in the fields and/or records are abnormal, for example, the data values in the fields and/or records are super-window data, missing values exist in the data values in the fields and/or records, and some data values in the fields and/or records are located outside the value range.
Obviously, when the data in the first target case report table satisfies the data checking rule, the second target case report table is the same as the first target case report table.
The reasons for the data not satisfying the data checking rule include, but are not limited to, data omission, data over-window data, data checking rule being too strict or too loose, data selection rule being wrong, data value abnormality corresponding to a field or record (for example, the result A1 of white blood cell count in table 1 is located outside the value range of the result of white blood cell count), data checking including data checking and data correction, after abnormal data is checked, in a possible case, the checking result can be directly marked in the area where the abnormal data corresponds to the first target case report table, the abnormal data is not corrected, but only marked, so that a subsequent clinical researcher can analyze and judge the abnormal data, at this time, the check tag is used to mark the abnormal data in the first target case report table, and the abnormal data includes, but is not limited to, data value missing, data over-window data, and the like. In another possible scenario, the clinical researcher may determine the check label by analyzing the abnormal data and determining the check label according to the analysis result, wherein the check label is used to correct the first configuration file, the second configuration file and/or the standard subject data, so that the electronic device automatically corrects the abnormal data in the first target case report table to determine the second target case report table, wherein the data source of the second target case report table and the clinical trial database do not change the real data value, but only determine the data with larger reference value to the clinical trial through data selection.
For example, taking the above example of detecting whether the blood routine corresponding to the subject with the subject number 001 is over-window, the data checking rule of whether the blood routine is over-window is the third visit period (2018/4/1) + -1 day, i.e. whether the checking date is between 2018/3/31 and 2018/4/2, obviously, if the data checking date is not between 2018/4/4 and 2018/4/6, the checking result is over-window. At this time, the check label corresponding to the super-window can be determined, and the column data of the result of the white blood cell count corresponding to 2018/4/1 in the first target case report table is marked by the check label to be super-window data, so that subsequent researchers can analyze the super-window data.
And step 210, determining a second target case report table according to the check label corresponding to the data.
Obviously, in one possible case, the check label can reflect the abnormal condition of the data in the first target case report table, so that the second target case report table can be used as the reference for the clinical researcher to modify the data, so as to perform check and correction on the first configuration file and the second configuration file, and check the standard subject data, for example, if the researcher judges that the data check rule in the second target case report table is too strict or too loose, the data check rule is changed, and the second configuration file is corrected; if the data selection rule is judged to be wrong, changing the data selection rule and correcting the first configuration file; if the data value is judged to be abnormal and not advisable, the data value can be deleted. In another possible scenario, the check label can correct the abnormal data in the first target case report table, where the abnormal data can be deleted and replaced again from the clinical trial study data, but the original data value cannot be changed, thereby improving the data quality of the second target case report table, so that the second target case report table can be directly used as the reference basis of the clinical trial study, so as to more accurately determine the curative effect and safety of the trial drug.
According to the technical scheme, on the basis of the embodiment shown in fig. 1, the method further has the following beneficial effects: the embodiment discloses a synonym standardization process for sample subject data in detail, and further comprises a step and a process of utilizing a second configuration file to carry out data verification on a first target case report table so as to determine a verification tag, and utilizing the verification tag to determine a second target case report table with higher reference value. Therefore, the data quality of the second target case report table is guaranteed, and the method for automatically generating the case report table is more accurate on the whole; according to the second target case report table with higher reference value, the clinical researcher can more accurately determine the curative effect and the safety of the test drug.
Referring to fig. 3, based on the same concept as the method embodiment of the present invention, an embodiment of the present invention further provides an apparatus for automatically generating a case report table, including:
the semantic processing module 301 is configured to perform semantic triple processing on standard subject data corresponding to a clinical test scheme to determine clinical test research data;
the table generating module 302 is configured to determine a first target case report table according to the first configuration file of the case report table to be filled corresponding to the clinical test scenario and the clinical test research data.
According to the technical scheme, the beneficial effects of the embodiment are as follows: based on semantic triple processing, standard subject data can be processed in a unified mode so as to be convenient for subsequent storage, analysis and processing, based on a first configuration file of a case report table to be filled, all questions and fields corresponding to all the questions can be selected from clinical test research data to be filled into the case report table to be filled, so that a first target case report table can be generated automatically, manual filling of the case report table is not needed in the process, the labor cost of clinical tests is reduced, errors in the manual filling process are avoided, and therefore the entry efficiency and the data quality of the target case report table are improved.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. On the hardware level, the electronic device includes a processor 401 and a memory 402 storing execution instructions, and optionally an internal bus 403 and a network interface 404. The Memory 402 may include a Memory 4021, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory 4022 (e.g., at least 1 disk Memory); the processor 401, the network interface 404, and the memory 402 may be connected to each other by an internal bus 403, and the internal bus 403 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like; the internal bus 403 may be divided into an address bus, a data bus, a control bus, etc., which is indicated by only one double-headed arrow in fig. 4 for convenience of illustration, but does not indicate only one bus or one type of bus. Of course, the electronic device may also include hardware required for other services. When the processor 401 executes execution instructions stored by the memory 402, the processor 401 executes the method in any of the embodiments of the present invention and is at least used for executing the method shown in fig. 1 and 2.
In a possible implementation mode, the processor reads corresponding execution instructions from the nonvolatile memory to the memory and then runs the corresponding execution instructions, and corresponding execution instructions can also be obtained from other equipment, so that the device for automatically generating the case report table is formed on a logic level. The processor executes the execution instructions stored in the memory, so that the method for automatically generating the case report table provided by any embodiment of the invention is realized through the executed execution instructions.
The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Embodiments of the present invention further provide a computer-readable storage medium, which includes an execution instruction, and when a processor of an electronic device executes the execution instruction, the processor executes a method provided in any embodiment of the present invention. The electronic device may specifically be the electronic device shown in fig. 4; the execution instruction is a computer program corresponding to a device for automatically generating a case report form.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
All the embodiments in the invention are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
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 boiler 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 boiler. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or boiler that comprises the element.
The above description is only an example of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (9)
1. A method for automatically generating a case report form, comprising:
performing semantic triple processing on standard subject data corresponding to the clinical trial scheme to determine clinical trial research data;
determining a first target case report table according to a first configuration file of a case report table to be filled corresponding to the clinical test scheme and the clinical test research data, wherein the first configuration file comprises a subject to be filled in the case report table to be filled and a data selection rule of a field to be filled corresponding to the subject to be filled;
further comprising:
according to a second configuration file corresponding to the clinical test scheme, performing data verification on the data in the first target case report table to determine a verification label, and determining a second target case report table according to the verification label; wherein the second configuration file comprises data inspection rules corresponding to the first configuration file, and the check label marks abnormal data in the first target case report table or corrects the first configuration file, and/or the second configuration file and/or standard subject data;
the first configuration file is acquired in the following mode: determining a first initial configuration file according to a case report table to be filled corresponding to the clinical test scheme, and performing semantic triple conversion on the first initial configuration file to form the first configuration file;
the second configuration file is obtained in the following manner: and determining a second initial configuration file according to the clinical test scheme, and performing semantic triple conversion on the second initial configuration file to form the second configuration file.
2. The method of claim 1, further comprising:
determining a synonym array corresponding to a standard name in a clinical test scheme according to a preset storage form, forming a synonym library according to the synonym array, and establishing an index mode of the synonym library;
and inquiring whether synonyms exist in the sample subject data corresponding to the clinical test scheme in the synonym library according to the index mode, and replacing by using standard name words corresponding to the existing synonyms when the synonyms exist so as to determine standard subject data.
3. The method of claim 1, wherein the performing semantic triple processing on standard subject data corresponding to the clinical trial protocol to determine clinical trial study data comprises:
performing semantic triple processing on two-dimensional data in standard subject data corresponding to the clinical test scheme to determine semantic triple data;
performing data correlation on the semantic triple data based on subject identification to determine clinical trial study data.
4. The method of claim 1, wherein determining a first target case report form according to the first configuration file of the case report form to be filled out corresponding to the clinical trial protocol and the clinical trial study data comprises:
matching the first configuration file with data in the clinical trial research data to obtain pre-filled data;
and correspondingly filling the pre-filling data into the case report table to be filled so as to determine a first target case report table.
5. The method of claim 1, wherein the data checking the data in the first target case report table according to the second configuration file corresponding to the clinical trial protocol to determine a check label, and determining a second target case report table according to the check label comprises:
performing data verification on the data in the first target case report table according to the second configuration file, and determining a verification tag corresponding to the data;
and determining a second target case report table according to the check label corresponding to the data.
6. The method of claim 5, wherein when the data in the first target case report table does not satisfy the data validation rule, determining a validation tag corresponding to the data.
7. An apparatus for automatic generation of a case report form, comprising:
the semantic processing module is used for performing semantic triple processing on standard subject data corresponding to the clinical test scheme so as to determine clinical test research data;
the table generation module is used for determining a first target case report table according to a first configuration file of a case report table to be filled corresponding to the clinical test scheme and the clinical test research data, wherein the first configuration file comprises a subject to be filled in the case report table to be filled and a data selection rule of a field to be filled corresponding to the subject to be filled;
the table generation module is further to: according to a second configuration file corresponding to the clinical test scheme, performing data verification on the data in the first target case report table to determine a verification label, and determining a second target case report table according to the verification label; wherein the second configuration file comprises data inspection rules corresponding to the first configuration file, and the check label marks abnormal data in the first target case report table or corrects the first configuration file, and/or the second configuration file and/or standard subject data;
the first configuration file is acquired in the following mode: determining a first initial configuration file according to a case report table to be filled corresponding to the clinical test scheme, and performing semantic triple conversion on the first initial configuration file to form the first configuration file;
the second configuration file is obtained in the following manner: and determining a second initial configuration file according to the clinical test scheme, and performing semantic triple conversion on the second initial configuration file to form the second configuration file.
8. A computer-readable storage medium comprising executable instructions that, when executed by a processor of an electronic device, cause the processor to perform the method of any of claims 1-6.
9. An electronic device comprising a processor and a memory storing execution instructions, the processor performing the method of any of claims 1-6 when the processor executes the execution instructions stored by the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910766199.1A CN110675924B (en) | 2019-08-19 | 2019-08-19 | Method and device for automatically generating case report table, readable medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910766199.1A CN110675924B (en) | 2019-08-19 | 2019-08-19 | Method and device for automatically generating case report table, readable medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110675924A CN110675924A (en) | 2020-01-10 |
| CN110675924B true CN110675924B (en) | 2023-03-10 |
Family
ID=69075399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910766199.1A Active CN110675924B (en) | 2019-08-19 | 2019-08-19 | Method and device for automatically generating case report table, readable medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110675924B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111859899A (en) * | 2020-07-06 | 2020-10-30 | 合肥森亿智能科技有限公司 | Method, device, equipment and storage medium for parsing and filling Word document |
| CN112286937A (en) * | 2020-11-04 | 2021-01-29 | 重庆医科大学附属儿童医院 | Electroencephalogram report generation and query method and system |
| CN112331355B (en) * | 2020-11-26 | 2024-03-19 | 微医云(杭州)控股有限公司 | Disease type evaluation table generation method and device, electronic equipment and storage medium |
| CN114300079B (en) * | 2021-12-30 | 2023-05-30 | 卫宁健康科技集团股份有限公司 | Case discussion report acquisition method, electronic equipment and storage medium |
| CN114300085A (en) * | 2021-12-31 | 2022-04-08 | 科临达康医药生物科技(北京)有限公司 | Clinical trial individual patient report generation method, device and equipment |
| CN114566247B (en) * | 2022-04-20 | 2022-08-12 | 浙江太美医疗科技股份有限公司 | Automatic CRF generation method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886046A (en) * | 2014-03-11 | 2014-06-25 | 中国信息安全测评中心 | Automatic semanteme extraction method for Web data exchange |
| CN105608325A (en) * | 2013-07-17 | 2016-05-25 | 中国中医科学院 | Novel clinical case data acquisition system and acquisition method |
| CN106933806A (en) * | 2017-03-15 | 2017-07-07 | 北京大数医达科技有限公司 | The determination method and apparatus of medical synonym |
| CN107767929A (en) * | 2017-11-13 | 2018-03-06 | 医渡云（北京）技术有限公司 | CRF filling method, device, electronic equipment and storage medium |
| CN109446340A (en) * | 2018-10-17 | 2019-03-08 | 长沙瀚云信息科技有限公司 | A kind of Medicine standard term ontology management system and method, equipment and storage medium |
| CN109766329A (en) * | 2018-12-29 | 2019-05-17 | 湖南网数科技有限公司 | A kind of clinical data unit generation method and device for supporting that exchange is shared |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413261B (en) * | 2013-08-06 | 2017-02-08 | 中国中医科学院 | General clinical test electronic data acquiring system and method |
| CN108597565B (en) * | 2018-04-11 | 2021-07-02 | 浙江大学 | Clinical queue data collaborative verification method based on OCR and named entity extraction technology |
-
2019
- 2019-08-19 CN CN201910766199.1A patent/CN110675924B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105608325A (en) * | 2013-07-17 | 2016-05-25 | 中国中医科学院 | Novel clinical case data acquisition system and acquisition method |
| CN103886046A (en) * | 2014-03-11 | 2014-06-25 | 中国信息安全测评中心 | Automatic semanteme extraction method for Web data exchange |
| CN106933806A (en) * | 2017-03-15 | 2017-07-07 | 北京大数医达科技有限公司 | The determination method and apparatus of medical synonym |
| CN107767929A (en) * | 2017-11-13 | 2018-03-06 | 医渡云（北京）技术有限公司 | CRF filling method, device, electronic equipment and storage medium |
| CN109446340A (en) * | 2018-10-17 | 2019-03-08 | 长沙瀚云信息科技有限公司 | A kind of Medicine standard term ontology management system and method, equipment and storage medium |
| CN109766329A (en) * | 2018-12-29 | 2019-05-17 | 湖南网数科技有限公司 | A kind of clinical data unit generation method and device for supporting that exchange is shared |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110675924A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110675924B (en) | Method and device for automatically generating case report table, readable medium and electronic equipment | |
| Kahn et al. | A harmonized data quality assessment terminology and framework for the secondary use of electronic health record data | |
| Denney et al. | Validating the extract, transform, load process used to populate a large clinical research database | |
| Johnson et al. | A data quality ontology for the secondary use of EHR data | |
| US6952695B1 (en) | Spontaneous adverse events reporting | |
| CN110826309B (en) | System and method for generating clinical test electronic case report table | |
| Ford et al. | Optimising the use of electronic health records to estimate the incidence of rheumatoid arthritis in primary care: what information is hidden in free text? | |
| US8548827B2 (en) | Computer-implemented method for medical diagnosis support | |
| Lin et al. | External validation of an algorithm to identify patients with high data-completeness in electronic health records for comparative effectiveness research | |
| CN111640475A (en) | Management system for clinical test | |
| US10522249B2 (en) | Multiple computer server system for organizing healthcare information | |
| D’Amore et al. | Interoperability progress and remaining data quality barriers of certified health information technologies | |
| Franceschini et al. | A novel approach for estimating the omitted‐citation rate of bibliometric databases with an application to the field of bibliometrics | |
| Koola et al. | Predicting 30-day hospital readmission risk in a national cohort of patients with cirrhosis | |
| Bae et al. | The challenges of data quality evaluation in a joint data warehouse | |
| Bilder et al. | Informative group testing for multiplex assays | |
| Weng | Clinical data quality: a data life cycle perspective | |
| CN114005498A (en) | Clinical test data logic checking method and device, equipment and storage medium | |
| Corl et al. | The impact of inpatient point-of-care blood glucose quality control testing | |
| Vallamkonda et al. | Identifying and reconciling patients’ allergy information within the electronic health record | |
| Henke et al. | An extract-transform-load process design for the Incremental Loading of German Real-World Data based on FHIR and OMOP CDM: Algorithm Development and Validation | |
| Rossell | Big data and statistics: A statistician’s perspective | |
| Nya‐Ngatchou et al. | Point‐of‐care blood glucose measurement errors overestimate hypoglycaemia rates in critically ill patients | |
| Brown et al. | Making audit actionable: an example algorithm for blood pressure management in chronic kidney disease | |
| Soares et al. | An interdisciplinary approach to reducing errors in extracted electronic health record data for research |
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 |