CN110136789A - A kind of data governance quality detection method based on electronic health record application - Google Patents
A kind of data governance quality detection method based on electronic health record application Download PDFInfo
- Publication number
- CN110136789A CN110136789A CN201910398406.2A CN201910398406A CN110136789A CN 110136789 A CN110136789 A CN 110136789A CN 201910398406 A CN201910398406 A CN 201910398406A CN 110136789 A CN110136789 A CN 110136789A
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- health record
- electronic health
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 73
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 201000010099 disease Diseases 0.000 claims abstract description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 6
- 239000002131 composite material Substances 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 14
- 238000013499 data model Methods 0.000 claims description 7
- 238000013210 evaluation model Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 238000013441 quality evaluation Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 238000012372 quality testing Methods 0.000 claims description 3
- 238000007796 conventional method Methods 0.000 claims description 2
- 239000013589 supplement Substances 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 description 7
- 230000014759 maintenance of location Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 208000028659 discharge Diseases 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of data governance quality detection methods based on electronic health record application, belong to medical data applied technical field.Data governance quality detection method based on electronic health record application of the invention, by coverage detection, relevance detection, the detection for constituting analysis and map analysis completion data governance quality, the coverage detection includes that the detection of quantity dimension and time dimension detect;Constituting analysis includes composite target and specific operational indicator;Map analysis includes basic dictionary mapping index and disease, operation code mapping index.The data governance quality detection method based on electronic health record application of the invention is able to ascend the comprehensive and confidence level that data administer detection, has good application value.
Description
Technical field
The present invention relates to medical data applied technical fields, specifically provide a kind of data improvement based on electronic health record application
Quality determining method.
Background technique
Medical data is generated by hospital information system, and the composition of hospital information system is extremely complex, and back-end data table is few
Then several hundred, more then thousands of, electronic medical record system belongs to one of them very important system.It is answered in actual medical data
With having many tables in scene and information is redundancy and nugatory, therefore the basis of medical data application is to medical data
Carry out data improvement.The method that current data is administered is that data-oriented application scenarios establish various data models first, is then led to
It crosses and extracts, cleans, integrates initial data and data are loaded onto new model in database layer, the detection of data governance quality exists
It is particularly important during this.
However the detection of data governance quality, currently without the method for system, now common processing means are for specific
Data model compares the data volume variation for administering front and back.Although the method can reflect the quality that data are administered to a certain extent
Situation, but the problem of its reflection, is very unilateral and has many unworthiness.Such as the new many situations of data model
Under with original table be not one-to-one relationship, and the method is also without reference to the inspection of the quality condition for administering content
It surveys.
Summary of the invention
Technical assignment of the invention be in view of the above problems, provide it is a kind of be able to ascend data administer detection it is complete
The data governance quality detection method based on electronic health record application of face property and confidence level.
The further technical assignment of the present invention is to provide a kind of data governance quality Integrated Evaluation Model.
To achieve the above object, the present invention provides the following technical scheme that
It is a kind of based on electronic health record application data governance quality detection method, this method from coverage detect, relevance
Detection constitutes the detection that four aspects of analysis and map analysis carry out data governance quality, and finally by comprehensive data
Calculation model of mass is by quality of data quantificational expression.
Preferably, the coverage detection includes the detection of quantity dimension and time dimension detection.
Preferably, the quantity dimension detection includes the data figureofmerit inspection for single table proposed based on conventional method
Survey and the quality testing based on service integration index, wherein the data volume Indexs measure for being directed to single table is suitable for data mould after improvement
The data of type only are from a table in former data, are judged according to the data volume difference of model after calculating former table and administering.
Preferably, the time dimension detection includes that time range detects and be segmented detection, time range detection is true
Whether the beginning and ending time of fixed each model business datum and initial data time range are consistent.
Preferably, the relevance is detected as the scene that satisfaction needs correlation inquiry application between multiple models, count respectively
Calculating can correct associated data volume between the data volume that can be associated in comparison initial data and the model for administering completion.
Preferably, the composition analysis is to choose important content in conjunction with business feature and carry out accounting analysis, confirm number
According to accuracy, the index for constituting analysis can be composite target, can also be individually designed specific in conjunction with each data model
Operational indicator.
Preferably, the map analysis includes basic dictionary mapping and disease, operation standard set mapping.
Preferably, basic dictionary mapping index firstly the need of the code value and title for calculating each dictionary whether one by one
It is corresponding, calculate accounting situation of each dictionary item in corresponding traffic table further to supplement the content for constituting analysis.
A kind of data governance quality Integrated Evaluation Model, the assessment models are based on the coverage detection, relevance inspection
It surveys, constitute analysis and map analysis, one quantitative value of the model final output is as unified quality evaluation standard.
λ is introduced in the assessment modelsiCoverage detection is adjusted as balance factor, relevance detection, constitutes analysis
With the accounting situation of map analysis, λiRelationship between value and its parameter is expressed as follows:
Compared with prior art, the data governance quality detection method of the invention based on electronic health record application has following
It is outstanding the utility model has the advantages that it is described based on electronic health record application data governance quality detection method first by coverage detection,
Relevance detection, composition analysis, the detection of four aspect of map analysis have carried out comprehensive assessment to data governance quality, finally again
By administer assessment models give quantitative quality condition reference value, in the whole process by data volume with operational indicator
The detection and analysis of multi-angle give comprehensive data governance quality evaluation criteria, have good application value.
Detailed description of the invention
Fig. 1 is the flow chart of the data governance quality detection method of the present invention based on electronic health record application.
Specific embodiment
Below in conjunction with drawings and examples, to the data governance quality detection side of the invention based on electronic health record application
Method is described in further detail.
Embodiment
As shown in Figure 1, the data governance quality detection method of the invention based on electronic health record application, this method is from covering
Degree detection, relevance detection constitute the detection that four aspects of analysis and map analysis carry out data governance quality.
1, coverage detects
Coverage detection mainly contains the detection of quantity dimension and time dimension detection.
The detection of quantity dimension can be indicated by data retention than index C1, and data retention ratio indicates number closer to 1
It is higher according to governance quality.
In the method for quality testing of the processing based on service integration index, we according to the business feature of hospital data,
Hospital admission amount is separately designed, medical three indexs of number and medical expenditure are judged.We are bright to cover ratio by index
Index C2 is indicated, and index covering is than indicating that data governance quality is higher closer to 1.Illustrate by taking the calculating of medical amount ratio as an example
It is as follows:
Index covering is compared than index C2 according to medical amount, when than three indexs of medical expenditure are calculated medical number:
Time dimension detection can be indicated by time range than index C3, be needed in calculating process using then span
The concept of degree, i.e., the business hours of one table across number of days, specific formula for calculation is expressed as follows:
Time or month are refined on the basis of the quantity dimension detection that time dimension detection can also be generally noted above
Carry out the statistics of more detailed dimension.For example each year nearly 3 years data retention can be subdivided into than index C1 for data retention
Than counting.
2, relevance detects
For electronic health record application scenarios we propose respectively medical-diagnosis than R1, medical-drug ratio R2, it is medical-
Expense ratio R3, it goes to a doctor-examines than the relevance detection of this 4 critical index progress data governance qualities of R4.With medical-diagnosis
Than being described as follows for index R1:
Herein it should be noted that can have multiple diagnosis records tables and diagnostics table, such as branch, inpatient department in electronic health record
There are admission records, with first page of illness case diagnosis etc., to apply above with admission diagnosis, discharge record with discharge diagnosis, first page of illness case
Diagnosis records can be calculated when formula with the overall condition of diagnostics table, can also be separated and be calculated, it is flat finally to carry out summation again
?.
3, constitutive character is analyzed
The index for constituting and analyzing is mentioned in summary of the invention can be composite target, can also combine each data model list
Specific operational indicator is solely designed, such as in expenditure pattern, we can calculate separately accounting index of the outpatient service with hospitalization cost
F1.For another example for diagnostic model, we can be respectively in initial data and Governance Model according to medical amount calculated for rank
The accounting index F2 of preceding 10 disease finally carries out otherness comparison based on the above accounting situation.The present invention is with composite target door
It examines and is described as follows for the accounting F1 with hospitalization cost:
4, map analysis
The map analysis stage combine this dictionary of gender, first determine whether original table in Governance Model whether all include
Whether identical dictionary item (such as male, women) and dictionary item code value are consistent (such as 1 represent male, 2 represent women), so
Combine outpatient service table that can provide the medical analysis indexes M1 of specific gender afterwards.And it is more direct for disease, operation standard set
The disease or operation code for detecting hospital are with the correspondence situation between ICD9 and ICD10, first is that how many, which is calculated, to complete
It is corresponding, second is that judging whether corresponding situation is accurate.The present invention for analysis indexes M1 Jiu Zhen not be illustrated: count respectively first
Dictionary item is calculated unanimously than M11 with dictionary item accounting M12:
The medical analysis indexes M1 combination dictionary item of gender unanimously may be expressed as: than M11 with dictionary item accounting M12
Gender is gone to a doctor analysis indexes M1=dictionary item unanimously compares M11* dictionary item accounting M12
One quantitative value of data governance quality Integrated Evaluation Model final output as unified quality evaluation standard,
λ is introduced in the assessment modelsiCoverage detection is adjusted as balance factor, relevance detection, constitutes analysis and mapping point
The accounting situation of analysis, λiRelationship between value and its parameter can be expressed as follows:
Balance factor is combining coverage detection C, relevance detection R, the content for constituting analysis F, tetra- aspect of map analysis M
Later, the calculation formula of data governance quality Integrated Evaluation Model can be expressed as follows:
Wherein n1, n2, n3, n4 have respectively represented the quantity of quality index in four detection contents.Ci, Ri, Fi, Mi then generation
The specific targets item of each corresponding detection content of table.
Embodiment described above, the only present invention more preferably specific embodiment, those skilled in the art is at this
The usual variations and alternatives carried out within the scope of inventive technique scheme should be all included within the scope of the present invention.
Claims (9)
1. a kind of data governance quality detection method based on electronic health record application, it is characterised in that: this method is examined from coverage
It surveys, relevance detection, constitute the detection that four aspects of analysis and map analysis carry out data governance quality, and finally by comprehensive
The quality of data computation model of conjunction is by quality of data quantificational expression.
2. the data governance quality detection method according to claim 1 based on electronic health record application, it is characterised in that: institute
Stating coverage detection includes the detection of quantity dimension and time dimension detection.
3. the data governance quality detection method according to claim 2 based on electronic health record application, it is characterised in that: institute
The detection of quantity dimension is stated to include the data volume Indexs measure for being directed to single table proposed based on conventional method and refer to based on service integration
Target quality testing, wherein only being from suitable for the data of data model after administering in original for the data volume Indexs measure of single table
One table of data judges according to the data volume difference of model after calculating former table and administering.
4. the data governance quality detection method according to claim 3 based on electronic health record application, it is characterised in that: institute
Stating time dimension detection includes that time range detects and be segmented detection, and time range detection is determining each model business datum
Whether the beginning and ending time is consistent with initial data time range.
5. the data governance quality detection method according to claim 4 based on electronic health record application, it is characterised in that: institute
State relevance be detected as meeting need multiple models between the scene applied of correlation inquiry, calculating separately in comparison initial data can be with
It can correct associated data volume between the data volume to associate and the model for administering completion.
6. the data governance quality detection method according to claim 5 based on electronic health record application, it is characterised in that: institute
Composition analysis is stated important content to be chosen and carrying out accounting analysis, confirm the accuracy of data, constitute analysis in conjunction with business feature
Index can be composite target, the individually designed specific operational indicator of each data model can also be combined.
7. the data governance quality detection method according to claim 6 based on electronic health record application, it is characterised in that: institute
Stating map analysis includes basic dictionary mapping and disease, operation standard set mapping.
8. the data governance quality detection method according to claim 7 based on electronic health record application, it is characterised in that: institute
It states whether basic dictionary mapping index corresponds firstly the need of the code value for calculating each dictionary with title, further calculates every
Accounting situation of a dictionary item in corresponding traffic table supplements the content for constituting analysis.
9. a kind of data governance quality Integrated Evaluation Model, it is characterised in that: the assessment models be based on claim 1,2,3,4,
5, the detection of coverage described in 6,7,8 any one, relevance detection, composition analysis and map analysis, the model final output
Quantitative value is as unified quality evaluation standard.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910398406.2A CN110136789A (en) | 2019-05-14 | 2019-05-14 | A kind of data governance quality detection method based on electronic health record application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910398406.2A CN110136789A (en) | 2019-05-14 | 2019-05-14 | A kind of data governance quality detection method based on electronic health record application |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110136789A true CN110136789A (en) | 2019-08-16 |
Family
ID=67573781
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910398406.2A Pending CN110136789A (en) | 2019-05-14 | 2019-05-14 | A kind of data governance quality detection method based on electronic health record application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110136789A (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015073349A1 (en) * | 2013-11-14 | 2015-05-21 | 3M Innovative Properties Company | Systems and methods for obfuscating data using dictionary |
CN105741196A (en) * | 2016-03-01 | 2016-07-06 | 万达信息股份有限公司 | Four-dimension-based data quality monitoring and evaluating method |
CN105824847A (en) * | 2015-01-09 | 2016-08-03 | 国网浙江省电力公司 | Information integration quality evaluation method |
CN106874483A (en) * | 2017-02-20 | 2017-06-20 | 山东鲁能软件技术有限公司 | A kind of device and method of the patterned quality of data evaluation and test based on big data technology |
CN107256247A (en) * | 2017-06-07 | 2017-10-17 | 九次方大数据信息集团有限公司 | Big data data administering method and device |
CN107368957A (en) * | 2017-07-04 | 2017-11-21 | 广西电网有限责任公司电力科学研究院 | A kind of construction method of equipment condition monitoring quality of data evaluation and test system |
CN108154293A (en) * | 2017-12-20 | 2018-06-12 | 中国电子科技集团公司信息科学研究院 | A kind of Urban Data maturity appraisal procedure and system |
CN108615115A (en) * | 2018-05-02 | 2018-10-02 | 山东汇贸电子口岸有限公司 | A kind of implementation method of government data collecting flowchart |
CN109377017A (en) * | 2018-09-27 | 2019-02-22 | 广东电网有限责任公司信息中心 | A kind of information system is practical and data health degree evaluation method |
CN109542886A (en) * | 2018-11-23 | 2019-03-29 | 山东浪潮云信息技术有限公司 | A kind of data quality checking method of Government data |
-
2019
- 2019-05-14 CN CN201910398406.2A patent/CN110136789A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015073349A1 (en) * | 2013-11-14 | 2015-05-21 | 3M Innovative Properties Company | Systems and methods for obfuscating data using dictionary |
CN105824847A (en) * | 2015-01-09 | 2016-08-03 | 国网浙江省电力公司 | Information integration quality evaluation method |
CN105741196A (en) * | 2016-03-01 | 2016-07-06 | 万达信息股份有限公司 | Four-dimension-based data quality monitoring and evaluating method |
CN106874483A (en) * | 2017-02-20 | 2017-06-20 | 山东鲁能软件技术有限公司 | A kind of device and method of the patterned quality of data evaluation and test based on big data technology |
CN107256247A (en) * | 2017-06-07 | 2017-10-17 | 九次方大数据信息集团有限公司 | Big data data administering method and device |
CN107368957A (en) * | 2017-07-04 | 2017-11-21 | 广西电网有限责任公司电力科学研究院 | A kind of construction method of equipment condition monitoring quality of data evaluation and test system |
CN108154293A (en) * | 2017-12-20 | 2018-06-12 | 中国电子科技集团公司信息科学研究院 | A kind of Urban Data maturity appraisal procedure and system |
CN108615115A (en) * | 2018-05-02 | 2018-10-02 | 山东汇贸电子口岸有限公司 | A kind of implementation method of government data collecting flowchart |
CN109377017A (en) * | 2018-09-27 | 2019-02-22 | 广东电网有限责任公司信息中心 | A kind of information system is practical and data health degree evaluation method |
CN109542886A (en) * | 2018-11-23 | 2019-03-29 | 山东浪潮云信息技术有限公司 | A kind of data quality checking method of Government data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Forlano et al. | High-throughput, machine learning–based quantification of steatosis, inflammation, ballooning, and fibrosis in biopsies from patients with nonalcoholic fatty liver disease | |
Sánchez et al. | SDSS-IV MaNGA–an archaeological view of the cosmic star formation history | |
Ahmed et al. | Developing and validating risk prediction models in an individual participant data meta-analysis | |
Li et al. | Medical costs associated with type 2 diabetes complications and comorbidities | |
White et al. | Uncertainty of measurement in quantitative medical testing: a laboratory implementation guide | |
Park et al. | Can non‐clinical repolarization assays predict the results of clinical thorough QT studies? Results from a research consortium | |
Liu et al. | A min–max combination of biomarkers to improve diagnostic accuracy | |
Phelan et al. | A prospective study of the impact of automated dipstick urinalysis on the diagnosis of preeclampsia | |
CN110031624A (en) | Tumor markers detection system based on multiple neural networks classifier, method, terminal, medium | |
Luo et al. | DiagTest3Grp: an R package for analyzing diagnostic tests with three ordinal groups | |
Sam et al. | A comprehensive FFQ developed for use in New Zealand adults: reliability and validity for nutrient intakes | |
CN106461664A (en) | Circulating tumor cell diagnostics for lung cancer | |
CN112635057B (en) | Esophageal squamous carcinoma prognosis index model construction method based on clinical phenotype and LASSO | |
Bae et al. | Validity and reproducibility of a food frequency questionnaire to assess dietary nutrients for prevention and management of metabolic syndrome in Korea | |
Jo et al. | Development of a virtual diabetes register using information technology in New Zealand | |
Achilihu et al. | Tobacco use classification by inexpensive urinary cotinine immunoassay test strips | |
Jeong et al. | Accuracy of the new creatinine-based equations for estimating glomerular filtration rate in Koreans | |
Han et al. | Association of parental education with tooth loss among Korean Elders | |
Obstfeld et al. | Data mining approaches to reference interval studies | |
Baron et al. | Enhanced creatinine and estimated glomerular filtration rate reporting to facilitate detection of acute kidney injury | |
Lin et al. | Joint temporal dietary and physical activity patterns: associations with health status indicators and chronic diseases | |
Alfieri et al. | Continuous and early prediction of future moderate and severe Acute Kidney Injury in critically ill patients: development and multi-centric, multi-national external validation of a machine-learning model | |
Sultana et al. | Overview of the European post‐authorisation study register post‐authorization studies performed in Europe from September 2010 to December 2018 | |
Saravia et al. | Food Diary, Food Frequency Questionnaire, and 24-Hour Dietary Recall | |
Hogan et al. | Compliance with standards for STARD 2015 reporting recommendations in pathology |
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 |