CN109615204A - Method for evaluating quality, device, equipment and the readable storage medium storing program for executing of medical data - Google Patents

Method for evaluating quality, device, equipment and the readable storage medium storing program for executing of medical data Download PDF

Info

Publication number
CN109615204A
CN109615204A CN201811462376.9A CN201811462376A CN109615204A CN 109615204 A CN109615204 A CN 109615204A CN 201811462376 A CN201811462376 A CN 201811462376A CN 109615204 A CN109615204 A CN 109615204A
Authority
CN
China
Prior art keywords
data
medical
testing result
group
detection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201811462376.9A
Other languages
Chinese (zh)
Other versions
CN109615204B (en
Inventor
黄越
陈明东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Medical and Healthcare Management Co Ltd
Original Assignee
Ping An Medical and Healthcare Management Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Medical and Healthcare Management Co Ltd filed Critical Ping An Medical and Healthcare Management Co Ltd
Priority to CN201811462376.9A priority Critical patent/CN109615204B/en
Publication of CN109615204A publication Critical patent/CN109615204A/en
Application granted granted Critical
Publication of CN109615204B publication Critical patent/CN109615204B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/06395—Quality analysis or management
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/08—Insurance
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Educational Administration (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Technology Law (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The present invention is based on the thoughts of big data analysis processing, it is proposed method for evaluating quality, device, equipment and the readable storage medium storing program for executing of a kind of medical data, method includes: to read base data table, medical insurance tables of data and the medical tables of data of each medical patient, and base data table, medical insurance tables of data and medical tables of data are set as a group element, form medical data group；Data rationality checking, the detection of data correspondence and Articulation detection are carried out to each group element in medical data group respectively, generate testing result；According to the corresponding relationship between preset testing result and credit rating, target quality level corresponding with the testing result generated is determined, and according to target quality level, quality evaluation is carried out to medical data group.This programme will test the data reasonability of each group element in medical data group, the testing result of correspondence and Articulation, as the quality evaluation foundation of medical data, so that assessment is more accurate, improve the efficiency and the degree of automation of assessment.

Description

Method for evaluating quality, device, equipment and the readable storage medium storing program for executing of medical data
Technical field
The invention mainly relates to medical system technical fields, specifically, being related to a kind of quality evaluation side of medical data Method, device, equipment and readable storage medium storing program for executing.
Background technique
With the development of system of social security, with medical insurance and more and more using the medical personnel of medical insurance, everyone exists When each medical institutions are gone to a doctor using medical insurance, all kinds of medical datas can be generated, and all kinds of medical data storages are in different tables of data In, to carry out Classification Management, subsequent accounting, the planning etc. for then carrying out medical insurance fund according to the medical data.
But because the medical data of each patient is dispersed in each tables of data, once having lacked in some tables of data The medical data corresponding relationship examined between certain medical data or each patient of personnel is incorrect, is easy to cause the number Relationship according to each data between data each in table and tables of data is chaotic, so that the accounting of medical insurance fund, there are larger mistakes for planning Difference；To be particularly important to quality evaluation of the data each in tables of data in integrality and corresponding relationship.But it is existing to be directed to The evaluation scheme of such quality of data depends on artificial progress, is carried out by artificial mode to the data in each tables of data Verification assessment, verification are easy to appear error, lead to assessment inaccuracy and low efficiency.
Summary of the invention
The main object of the present invention is to provide method for evaluating quality, device, equipment and the readable storage of a kind of medical data Medium, it is intended to solve the problems, such as quality evaluation inaccuracy, the low efficiency in the prior art to medical data.
To achieve the above object, the present invention provides a kind of method for evaluating quality of medical data, the matter of the medical data Measure appraisal procedure the following steps are included:
Read base data table, medical insurance tables of data and the medical tables of data of each medical patient, and by the base data table, Medical insurance tables of data and medical tables of data are set as a group element, form medical data group；
Data rationality checking, the detection of data correspondence are carried out to each group element in the medical data group respectively and hooked Relationship detection is checked, testing result is generated；
According to the corresponding relationship between preset testing result and credit rating, the testing result pair with generation is determined The target quality level answered, and according to the target quality level, quality evaluation is carried out to the medical data group.
Preferably, the testing result includes the first testing result, the second testing result and third testing result；
The each group element in the medical data group carries out data rationality checking, the detection of data correspondence respectively With Articulation detect, generate testing result the step of include:
Each described group of element is arranged using data respectively and carries out data rationality checking as unit, generates the first testing result；
The detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generates the second testing result；
To there are the cells of operational data to carry out Articulation detection in each described group of element, third detection knot is generated Fruit.
Preferably, the data rationality checking include assigning null data detection and numerical value range detection, it is described to each described Group element arranges the step of carrying out data rationality checking as unit, generating the first testing result using data respectively
The data column in each described group of element are traversed one by one respectively, read the column identifier of each data column, and root According to each column identifier, the value type data column in each data column are determined；
The cell in each data column with the presence or absence of data for null value is detected, data are the unit of null value if it exists Lattice, then to the abnormal identifier of each cell addition first；
The target data for exceeding preset range in each value type data column with the presence or absence of numerical value is detected, is counted if it exists Value exceeds the target data of preset range, then to the abnormal identifier of target data addition second；
According to the quantity of the described first abnormal identifier and the second abnormal identifier, the first testing result is generated.
Preferably, described that the detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generate the Include: before the step of two testing results
Judge whether the first abnormal rate in first testing result is greater than default value, if first abnormal rate is big In the default value, then stop carrying out correspondence detection to each described group of element；
If first abnormal rate is not more than the default value, according to the correspondence in each described group of element between data Relationship, determining the first corresponding data corresponding with each described first abnormal identifier, and with each second exception identifier Corresponding second corresponding data；
First corresponding data and the second corresponding data are rejected from each described group of element, to each described group of element It is updated, and executes and the detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generate the second inspection The step of surveying result.
Preferably, described that the detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generate the The step of two testing results includes:
It selects any described group of element as target group element from each described group of element, and will be removed in each described group of element Other described group of element except the target group element are set as to contrast groups element；
Read in the target group element the first row identifier of data line and each described to each number in contrast groups element According to the second capable row identifier, and judge it is each it is described to whether exist in each second row identifier of contrast groups element with The corresponding object identifier of first row identifier；
If there is object identifier corresponding with first row identifier, the data pair of each described group of element are completed Answering property detects；
Object identifier corresponding with first row identifier if it does not exist, then to having, there is no the corresponding mesh The data line for marking first row identifier of identifier adds third exception identifier, and according to the third exception identifier Quantity generate the second testing result.
Preferably, described to there are the cells of operational data to carry out Articulation detection in each described group of element, it generates The step of third testing result includes:
The cell mark of cell in each described group of element is read, and determines that there are operations according to cell mark The Set cell of data；
It detects in the cell data of each Set cell with the presence or absence of the object element that Articulation detection is abnormal Lattice data；
The abnormal Set cell data of Articulation detection if it exists, then to Set cell data addition the 4th Abnormal identifier, and third testing result is generated according to the quantity of the described 4th abnormal identifier.
Preferably, the corresponding relationship according between preset testing result and credit rating determines the institute with generation The step of stating testing result corresponding target quality level include:
It reads with first abnormal rate, the second abnormal rate and third detection knot in second testing result The corresponding weighting coefficient of third abnormal rate in fruit；
First abnormal rate, the second abnormal rate and third abnormal rate are weighted respectively with each weighting coefficient It calculates, generates object detection results；
Corresponding relationship between the object detection results and preset testing result and credit rating is compared, really Fixed target quality level corresponding with the object detection results.
In addition, to achieve the above object, the present invention also proposes a kind of quality assessment device of medical data, the medical treatment number According to quality assessment device include:
Read module, for reading base data table, medical insurance tables of data and the medical tables of data of each medical patient, and by institute It states base data table, medical insurance tables of data and medical tables of data and is set as a group element, form medical data group；
Detection module, for carrying out data rationality checking, data respectively to each group element in the medical data group Correspondence detection and Articulation detection, generate testing result；
Evaluation module, for determining and generation according to the corresponding relationship between preset testing result and credit rating The corresponding target quality level of the testing result, and according to the target quality level, matter is carried out to the medical data group Amount assessment.
In addition, to achieve the above object, the present invention also proposes a kind of quality assessment arrangement of medical data, the medical treatment number According to quality assessment arrangement include: memory, processor, communication bus and the medical data being stored on the memory Quality evaluation program；
The communication bus is for realizing the connection communication between processor and memory；
The processor is used to execute the quality evaluation program of the medical data, to perform the steps of
Read base data table, medical insurance tables of data and the medical tables of data of each medical patient, and by the base data table, Medical insurance tables of data and medical tables of data are set as a group element, form medical data group；
Data rationality checking, the detection of data correspondence are carried out to each group element in the medical data group respectively and hooked Relationship detection is checked, testing result is generated；
According to the corresponding relationship between preset testing result and credit rating, the testing result pair with generation is determined The target quality level answered, and according to the target quality level, quality evaluation is carried out to the medical data group.
In addition, to achieve the above object, the present invention also provides a kind of readable storage medium storing program for executing, the readable storage medium storing program for executing storage Have one perhaps more than one program the one or more programs can be held by one or more than one processor Row is to be used for:
Read base data table, medical insurance tables of data and the medical tables of data of each medical patient, and by the base data table, Medical insurance tables of data and medical tables of data are set as a group element, form medical data group；
Data rationality checking, the detection of data correspondence are carried out to each group element in the medical data group respectively and hooked Relationship detection is checked, testing result is generated；
According to the corresponding relationship between preset testing result and credit rating, the testing result pair with generation is determined The target quality level answered, and according to the target quality level, quality evaluation is carried out to the medical data group.
The method for evaluating quality of the medical data of the present embodiment passes through the basic data for each medical patient that will be read Table, medical insurance tables of data and medical tables of data form the medical data group of medical patient as group element；And respectively to medical data Each group of element carries out data rationality checking, the detection of data correspondence and Articulation detection in group, generates testing result；In advance The corresponding relationship being first provided between testing result and credit rating, can be true according to the corresponding relationship after generating testing result Fixed corresponding target quality level, and then according to target quality level, quality evaluation is carried out to medical data group.It is cured by detection Data reasonability, correspondence and the Articulation of each group element in data group are treated, testing result generated reflects each group element Internal data and each group element between the integrality of data and the correctness of corresponding relationship；With corresponding with the testing result Target quality level is as according to the quality evaluation for carrying out medical data；It avoids carrying out verification assessment in a manual manner, so that The assessment of medical data is more accurate, improves the efficiency and the degree of automation of assessment.
Detailed description of the invention
Fig. 1 is the flow diagram of the method for evaluating quality first embodiment of medical data of the invention；
Fig. 2 is the functional block diagram of the quality assessment device first embodiment of medical data of the invention；
Fig. 3 is the device structure schematic diagram for the hardware running environment that present invention method is related to.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of method for evaluating quality of medical data.
Fig. 1 is please referred to, Fig. 1 is the flow diagram of the method for evaluating quality first embodiment of medical data of the present invention.? In the present embodiment, the method for evaluating quality of the medical data includes:
Step S10, reads base data table, medical insurance tables of data and the medical tables of data of each medical patient, and by the base Plinth tables of data, medical insurance tables of data and medical tables of data are set as a group element, form medical data group；
The method for evaluating quality of medical data of the invention is applied to server, is suitable for through server to medical institutions Medical data carry out quality evaluation；Wherein medical data is essential information and treatment process of the medical institutions to medical patient The data recorded, name, age, gender, ID card No., medical place, consultation time, the illness letter of such as medical patient Breath, medication information, patient pay the amount of money, medical insurance reimbursed sum etc. for oneself.Medical institutions carry out such number for each medical patient According to record, and classify in recording process according to basic data, medical insurance data and medical data, generate basic number respectively According to table, medical insurance tables of data and medical tables of data, Classification Management is carried out with the medical data to each medical patient；It is directed to each table simultaneously In belong to the data of same medical patient and distribute same identifier, to establish medical incidence relation of the patient in each table.It is such as right In medical patient A, a is accorded with to the personal information allocation identification such as its name, age, gender, ID card No., and basic number is recorded According in table；And the amount of money and the same allocation identification symbol a of medical insurance reimbursed sum are paid for oneself to medication information, patient, medical insurance number is recorded According in table；A is accorded with to medical place, consultation time, illness information also allocation identification, is recorded in medical tables of data.Wherein in order to Ensure the uniqueness of medical Patient identifier, establishes medical archive, medical shelves for the first medical patient to go to a doctor to medical institutions The uniqueness of medical patient is characterized in case by the ID card No. and identifier of the patient that goes to a doctor.When medical patient to medical institutions just When examining, judge whether that there is medical archive corresponding with its ID card No., the identifier of the medical archive read if having, As the identifier of patient's medical data generated in treatment process of going to a doctor, if not having corresponding medical archive, for The medical patient establishes medical archive, and allocation identification accords with, to record the subsequent medical data of medical patient.
The quality height that medical data are recorded to assess medical institutions to each medical patient, sets the inspection of interval time Survey mechanism, such as a detection in month are primary or season detection one is inferior, carry out quality evaluation according to the result of detection.Specifically Ground, when detecting interarrival time, server reads the base data table for each medical patient that medical institutions are recorded, medical insurance Tables of data and medical tables of data；Because of the different type number that the data in each tables of data with identical identifier are same patient According to incidence relation between each tables of data；And the base data table of reading, medical insurance tables of data and medical tables of data are formed Medical data group.Each tables of data is as the group element in the medical data group, with medical data group as a whole to each medical The medical data of patient carries out quality evaluation.
Step S20 carries out data rationality checking, data correspondence to each group element in the medical data group respectively Detection and Articulation detection, generate testing result；
Further, using base data table, medical insurance tables of data and medical tables of data as group element, medical data is formed After group, then the data in each group of element are carried out with the detection of rationality checking, correspondence detection and Articulation, and generated Testing result.Wherein rationality checking is whether each data are null value in group element, and whether the numberical range of each data is reasonable etc., To ensure the complete reasonable of recorded medical data；Correspondence is detected as whether medical patient has correspondence in each group element Data, to ensure the correctness of data corresponding relationship between each group element；Articulation be detected as group element internal data or Whether the operation result of the data to require calculation in data between group element is correct, to ensure each data in medical data group The correctness of operation.For the different types of detection, the having differences property of mode of detection, testing result generated is also different Sample；Specifically, testing result includes the first testing result, the second testing result and third testing result, in medical data group Each group element carry out respectively data rationality checking, data correspondence detection and Articulation detection, generate testing result Step includes:
Step S21 is arranged each described group of element using data respectively and carries out data rationality checking as unit, generates the first inspection Survey result；
Understandably, each group element exists in the form of tables of data, and each data are deposited in tables of data in the form of " ranks " Wherein each categorical data of " row " corresponding same medical patient, " column " corresponding same type of each data.In view of not The data of same type have different requirement of reasonableness, and such as the data of value type, requiring data first is not null value, together Shi Yaoqiu data in the reasonable scope, and are directed to the data of different value types, and the zone of reasonableness is not also identical；And for non-number The data of Value Types, then requiring data is not null value.Because " column " each in tables of data characterize the type of each data, from And when data carry out rationality checking in each group element, it is arranged using data and is detected as unit, in order to according to each number Rationality checking is carried out according to type；The rationality checking that as unit carries out data is arranged each group of element using data respectively, it is raw At the first testing result.
Step S22 carries out the detection of data correspondence respectively to each described group of element with data behavior unit, generates the second inspection Survey result；
Further, whether there is corresponding data in each group element for detecting medical patient because correspondence is detected, And " row " each in tables of data characterizes each data type of medical patient, so that data correspond in each group element Property detection when, detected with data behavior unit, in order to carry out correspondence detection according to each medical patient；It is i.e. right respectively Each group of element carries out the correspondence detection of data with data behavior unit, generates the second testing result.
Step S23 generates third to there are the cells of operational data to carry out Articulation detection in each described group of element Testing result.
Understandably, the case where medical data of the patient in treatment process, there are operations；Such as each use in medication information The sum of medicine amount of money is equal to the total amount of medication, and patient pays the sum of the amount of money and medical insurance reimbursed sum for oneself and is equal to medical total amount etc.；It will For such data to require calculation as operational data, different operational datas is present in each group element of data sheet form In different units lattice.In order to ensure the correctness of such operation, need to there are the cells of operational data to carry out Articulation Detection；Articulation detection generates third testing result for judging whether the operation between operational data is correct.
Further, rationality checking is carried out to data in group element, correspondence detects and constructs Articulation detection, First testing result, the second testing result and third testing result generated, are the component part of testing result；By right First testing result, the second testing result and third testing result are weighted integration, generate testing result, and then by the generation Testing result corresponding to credit rating assess the quality of medical data.
Step S30 determines the inspection with generation according to the corresponding relationship between preset testing result and credit rating The corresponding target quality level of result is surveyed, and according to the target quality level, quality evaluation is carried out to the medical data group.
Further, the present embodiment is previously provided with the corresponding relationship between testing result and credit rating, testing result Characterize in group element that there are unreasonable, the not corresponding or incorrect abnormal data quantity of operation, between credit rating Corresponding relationship, which then characterizes possessed abnormal data quantity in group element, influences the quality of medical data group.Work as testing result Middle abnormal data quantity is more, then corresponding credit rating is lower, and it is poorer to characterize recorded medical data quality；And abnormal number Data bulk is fewer, then corresponding credit rating is higher, and it is better to characterize recorded medical data quality.By the testing result of generation It is compared with preset corresponding relationship, that is, can determine credit rating corresponding with the testing result of the generation；By the corresponding quality Grade characterizes each group element, i.e., the quality of each medical data recorded in medical data group as target quality level.
The method for evaluating quality of the medical data of the present embodiment passes through the basic data for each medical patient that will be read Table, medical insurance tables of data and medical tables of data form the medical data group of medical patient as group element；And respectively to medical data Each group of element carries out data rationality checking, the detection of data correspondence and Articulation detection in group, generates testing result；In advance The corresponding relationship being first provided between testing result and credit rating, can be true according to the corresponding relationship after generating testing result Fixed corresponding target quality level, and then according to target quality level, quality evaluation is carried out to medical data group.Because of medical data Group is substantially in treatment process and is formed by medical data by all kinds of medical data, thus the quality evaluation to medical data group, Its quality evaluation substantially to medical data；Pass through data reasonability, the correspondence of each group element in detection medical data group And Articulation, testing result generated, data is complete between the internal data and each group element of reflection each group element The correctness of property and corresponding relationship；Using target quality level corresponding with the testing result as according to the matter for carrying out medical data Amount assessment；It avoids carrying out verification assessment in a manual manner, so that the assessment of medical data is more accurate, improves the effect of assessment Rate and the degree of automation.
Further, in another embodiment of method for evaluating quality of medical data of the present invention, the data reasonability inspection Surveying includes assigning null data detection and numerical value range detection, and described arranged using data respectively each described group of element carries out data as unit Rationality checking, generate the first testing result the step of include:
Step S211 respectively traverses the data column in each described group of element one by one, reads the column mark of each data column Know symbol, and according to each column identifier, determines the value type data column in each data column；
Understandably, because to each group element carry out data rationality checking when, for the value type number in group element According to column, other than carrying out assigning null data detection, it is also necessary to carry out numberical range rationality checking；For the number in area's grouping elements Value Types data column and non-numeric type data column are previously provided with column identifier, and value type for each data column It is characterized with the different column identifier of non-numeric type.Before carrying out rationality checking, respectively to data in each group element arrange by One is traversed, and reads the column identifier in each data column, and each column identifier of reading and pre-set column are marked Know symbol comparison, search the column identifier for wherein characterizing value type, the column data with this identifier is determined as value type Data column.
Step S212 detects the cell in each data column with the presence or absence of data for null value, and data are sky if it exists The cell of value, then to the abnormal identifier of each cell addition first；
Further, the value type data column and non-numeric type data column organized in element are required to carry out null value inspection Survey, as detection for record gender non-numeric type data arrange and for recording the age value type data column in whether There are unwritten cells etc.；Each data column in group element are detected, judgement is wherein with the presence or absence of data The cell of null value.Data are the cell of null value if it exists, then illustrate not record data in the cell, in data column Data are imperfect；To not record the abnormal identifier of each unit lattice addition first of data to this, to characterize in each group element Existing abnormal data.
Step S213 detects the number of targets for exceeding preset range in each value type data column with the presence or absence of numerical value According to numerical value exceeds the target data of preset range if it exists, then to the abnormal identifier of target data addition second；
After carrying out null value detection to each data column in group element, further value type data therein are arranged and are carried out Numberical range detection；Because different value types has different numberical ranges, if the numberical range at age is 0~150 years old, certain The Fee Amount of similar drug is 30~90 yuan etc., thus when detecting according to numberical range corresponding to value type data into Row.It is corresponding in the identifier of characterization value type data column when the column identifier according to reading determines value type data column The data that carry arrange corresponding numberical range；The preset range that the corresponding numberical range is arranged as data, and with should Whether the numerical value of each data and the preset range compare in data column, judge the numerical value of each data in the preset range It is interior, if illustrating that the numberical range of each data in data column is reasonable in the preset range；If being deposited in the numerical value of each data Certain data numerical value exceed the preset range, then illustrate that the numberical range of such data is unreasonable, using such data as Target data in value type data column, and the abnormal mark of target data addition second to the numerical value beyond preset range Symbol characterizes the abnormal data in the presence of each group element.
Step S214 generates the first inspection according to the quantity of the described first abnormal identifier and the second abnormal identifier Survey result.
Further, the data of all data column carry out null value detection and numberical range in each group element Detection, and to the abnormal identifier of cell and target data addition first for being detected as null value and the second abnormal identifier it Afterwards；By the first abnormal identifier and the second abnormal identifier, that is, produce the first testing result, the first testing result table Levied group element in there are the quantity accountings of unreasonable abnormal data.Specifically, the abnormal identifier of statistics first each the respectively Second quantity of one quantity and the second abnormal identifier, then be added with first quantity with the second quantity, it is added obtained knot Fruit is the first abnormal total amount in group element there are unreasonable abnormal data；And then had data in statistics group element Total amount of data does ratio with the first abnormal total amount and the total amount of data, and obtained ratio result is unreasonable in group element Abnormal data quantity accounting；Using the ratio result as the first abnormal rate, and by the first abnormal total amount, the first abnormal rate, The data of the reflections exception such as the first abnormal identifier quantity and the second abnormal identifier quantity form set, as the first detection knot Fruit, with the quantity height in embodiment group element with unreasonable abnormal data.
Further, described to each constituent element in another embodiment of method for evaluating quality of medical data of the present invention Include: before the step of element carries out the detection of data correspondence respectively with data behavior unit, generates the second testing result
Step S24, judges whether the first abnormal rate in first testing result is greater than default value, if described first Abnormal rate is greater than the default value, then stops carrying out correspondence detection to each described group of element；
Understandably, the data of each data column carry out rationality checking in group element, after generating the first testing result, First testing result reflects in group element may be higher with the quantity accounting of abnormal data, i.e., in group element containing it is more not Reasonable data.If continuing to carry out medical data correspondence detection and Articulation detection, reference value is lower；Thus in order to The height for characterizing the abnormal data quantity accounting reflected in the first testing result, is previously provided with default value.By the first inspection The first abnormal rate and the default value surveyed in result compare, and judge whether the first abnormal rate is greater than the default value；If first Abnormal rate is greater than the default value, then illustrates that abnormal data unreasonable in group element is more, and stops pair to each group element Answering property detects.
Step S25, if first abnormal rate be not more than the default value, according to data in each described group of element it Between corresponding relationship, determining the first corresponding data corresponding with each first exception identifier, and with it is each described second different Corresponding second corresponding data of normal identifier；
And when judging the first abnormal rate no more than default value, then illustrate abnormal data unreasonable in group element compared with Few, quantity accounting carries out correspondence detection to group element in acceptable zone of reasonableness.Specifically, correspondence is being carried out Before detection, abnormal data unreasonable in group element is rejected, to avoid correspondence detection is influenced.Because each group element it Between data line there are consistent medical patients to need when rejecting to the abnormal data in a certain group of element to other In group element with data progress is corresponding possessed by the consistent medical patient of the abnormal data rejects.For same in each group element The data of one medical patient are assigned same identifier, using the same identifier as the corresponding pass between data in each group element It is, and determines other data of medical patient belonging to abnormal data according to the corresponding relationship.Such as tables of data of going to a doctor In data B not in its preset range, and its addition identifier be b, then carry mark for all in the tables of data of going to a doctor Know the data that other data of symbol b are rejected as needs；It is searched simultaneously into base data table and medical insurance tables of data and carries mark The data for knowing symbol b, the data rejected as needs.Because abnormal data includes assigning null data and the unreasonable data of numberical range, To the identified data for needing to reject, it is divided into the first corresponding number corresponding with the first exception identifier according to the two types According to and the second corresponding data corresponding with the second abnormal identifier, i.e. other numbers of medical patient belonging to assigning null data According to and the unreasonable medical patient of numberical range other data.
Step S26 rejects first corresponding data and the second corresponding data, to each institute from each described group of element It states a group element to be updated, and executes and the detection of data correspondence is carried out with data behavior unit respectively to each described group of element, it is raw The step of at the second testing result.
Further, after determining the first corresponding data and the second corresponding data in each group element, then by this first Corresponding data and the second corresponding data are rejected from each group element, and each group element rejected after operating is updated to new constituent element Element；On the basis of the new group element, the detection of data correspondence is carried out with data behavior unit, generates the second testing result. Specifically, step S22 includes:
Step S221 selects any described group of element as target group element from each described group of element, and will be each described Other described group of element in group element in addition to the target group element are set as to contrast groups element；
Specifically, when carrying out correspondence detection to each group element, a group element is arbitrarily selected from medical data group As target group element, and using other group of element as to contrast groups element；Such as using base data table as target group element, and Using medical insurance tables of data and medical tables of data as to contrast groups element, to carry out target group element and between contrast groups element Comparison, judges whether each medical patient has corresponding data in each group element.
Step S222 reads in the target group element the first row identifier of data line and each described to contrast groups Second row identifier of each data line in element, and judge each described to be in each second row identifier of contrast groups element It is no to there is object identifier corresponding with first row identifier；
Because the data line in group element is corresponding with medical patient, all data in same data line are a medical patient Had, carries the medical corresponding identifier of patient；In comparison, the arbitrary number in target group element is first read line by line According to the line number of data line is corresponding in the quantity and target group element of data streams read；And then read mark entrained in each data Know symbol, medical patient corresponding to each row data in target group element is characterized, using the entrained identifier as the first rower Know symbol.A data, the quantity of data streams read and to right are arbitrarily read from each data line to contrast groups element simultaneously It is more corresponding than the line number of data line in group element；And then identifier entrained in each data is read, it characterizes in contrast groups element Medical patient corresponding to each row data, using the entrained identifier as the second row identifier.By the first row identifier by One and the second row identifier comparison, whether judge in the second row identifier in the presence of target corresponding with each first row identifier Row identifier.It should be noted that because to include multiple groups of elements in contrast groups element, to need to read for each group of element The second row identifier of wherein the had data of each data line is taken, so that being formed by the second row identifier includes multiple groups；Wherein The group number of second row identifier is consistent with to the group number of elements in contrast groups element, such as above-mentioned as to contrast groups element Medical insurance tables of data and medical tables of data, corresponding second identifier symbol is respectively second identifier symbol in medical insurance tables of data and just Examine the second identifier symbol in tables of data；When by the first row identifier and the comparison of the second row identifier, need and the second row of each group Identifier compares, and judges whether there is target mark corresponding with the first row identifier in the second row identifier of each group Symbol is known, to ensure that medical patient has corresponding data in each group element.
Step S223 completes each constituent element if there is object identifier corresponding with first row identifier The data correspondence detection of element；
Further, during the comparison process, if judging to exist in each second row identifier corresponding with the first row identifier Object identifier when, then illustrate the corresponding medical patient of the first row identifier, wait in contrast groups element existing pair at other The data correspondence detection of the data answered, the medical patient is normal；In turn by other first row identifiers in target group element It is compared with each second row identifier, until all first row identifiers compare completion.If the first all row identifiers exist There is corresponding target row identifier in each second row identifier, illustrates each medical patient in medical data group The detection of data correspondence is normal, completes the data correspondence detection of each group element.
Step S224, if it does not exist object identifier corresponding with first row identifier are then not present to having The data line of first row identifier of the corresponding object identifier adds third exception identifier, and according to the third The quantity of abnormal identifier generates the second testing result.
There is no corresponding mesh when there are certain first row identifiers in each first row identifier in each second row identifier Row identifier is marked, i.e., object identifier corresponding with the first row identifier is not present in each second row identifier, then explanation should The corresponding relationship of the corresponding medical patient's data in each group element of first row identifier is abnormal, and corresponding object identifier should be not present The first row identifier derive from data line, third exception identifier is added to the data line in its source, and by third exception Identifier generates the second testing result, there is the quantity accounting of not corresponding abnormal data in characterization group element.Specifically, it unites The quantity of third exception identifier is counted as the second abnormal total amount, and in statistics group element had data total amount of data, use The abnormal total amount of the second of statistics and the total amount of data do ratio, and obtained ratio result is not corresponding exception in group element The quantity accounting of data；Using the ratio result as the second abnormal rate, and the second abnormal total amount, the second abnormal rate and third is different The data of the reflections exceptions such as normal identifier quantity form set, not right to have in embodiment group element as the second testing result Answer the quantity height of abnormal data.
Further, described to each constituent element in another embodiment of method for evaluating quality of medical data of the present invention In element there are the cell of operational data carry out Articulation detection, generate third testing result the step of include:
Step S231, reads the cell mark of cell in each described group of element, and is identified really according to the cell Surely there is the Set cell of operational data；
The present embodiment is carrying out Articulation to there are the cells of operational data to be provided with cell mark in group element When detection, the cell mark of cell in each group element is read；When reading cell there are when cell mark, then illustrate The cell has operational data, requires calculation；And when not reading cell mark in cell, then explanation is to list Do not have operational data in first lattice, does not need to carry out operation；To determine that there are the targets of operational data according to cell mark Cell.Or different lists can also be set for the cell with operational data and the cell without operational data First case marker is known, and the mark of cell possessed by each unit lattice is read, and then has the unit of operational data with the characterization of setting Case marker knowledge compares, and determines Set cell wherein with operational data.
Step S232 is detected in the cell data of each Set cell with the presence or absence of Articulation detection exception Set cell data；
Understandably, the operation mode of nonidentity operation data and operand are different, such as some may be and tool There is a certain data C sum operation of the medical patient of the operational data, and other may be and have the operational data just Examine another data D additive operation of patient；It is wherein added or additive operation characterizes operation mode, and data C and data D characterization is transported Calculate object.Before carrying out Articulation detection to each operational data, it is thus necessary to determine that the operation mode of each operational data and operation Object.Specifically, determining that characterization has operation there are when the Set cell of operational data according to the cell of reading mark The corresponding operation mode of the operational data and operand are carried accordingly in the cell mark of data；Wherein operation pair As including being carried out the unit where the data of operation by operand characterization and operational data by operand and operation result Lattice, operation result characterization by operand data and operational data carry out the cell where the obtained result of operation.? When Articulation is detected, read by the cell number in the data and Set cell in operand characterization unit lattice According to the two is carried out operation according to operation mode, obtains operational data result；Read the knot in operation result institute characterization unit lattice Fruit data compare the obtained operational data result of operation and result data, judge the consistency of the two.Both pass through Cell data of the consistency to detect each Set cell in the Set cell abnormal with the presence or absence of Articulation detection Data；When the two is consistent, then illustrating that the cell data operation in Set cell is correct, Articulation detection is normal, after It resumes studies and the cell data in next Set cell is taken to be detected, until the cell data in all Set cells Detection is completed；When detecting the operational data result and inconsistent result data of cell data in Set cell, then Illustrate that the cell data operation in Set cell is incorrect, Articulation detection is abnormal, the cell of each Set cell There are the Set cell data that Articulation detection is abnormal in data.
Step S233, Articulation detects abnormal Set cell data if it exists, then to the Set cell number Third testing result is generated according to the abnormal identifier of addition the 4th, and according to the quantity of the described 4th abnormal identifier.
Further, when the object element that Articulation detection exception is not present in the cell data of each Set cell Lattice data then illustrate that the Articulation detection of each Set cell is normal, cell number in each Set cell in group element According to operation it is correct.And when there are the Set cells that Articulation detection is abnormal in the cell data of each Set cell Data then illustrate the Set cell data in each Set cell there are operation mistake, add to the Set cell data 4th abnormal identifier, and third testing result is generated by the 4th abnormal identifier, pass is checked to exist to hook in characterization group element It is the quantity accounting of the abnormal data of mistake.Specifically, the quantity of the 4th abnormal identifier is counted as the 4th abnormal total amount, and The total amount of data of had data in statistics group element does ratio with the 4th abnormal total amount of statistics and the total amount of data, gained To ratio result be group element in the incorrect abnormal data of Articulation quantity accounting；Using the ratio result as Three abnormal rate, and the data of the reflections exceptions such as the abnormal identifier quantity of third exception total amount, third abnormal rate and the 4th are formed Set, as third testing result, with the quantity height of the abnormal data in embodiment group element with Articulation mistake.
Further, described according to preset inspection in another embodiment of method for evaluating quality of medical data of the present invention The corresponding relationship between result and credit rating is surveyed, determines the step of target quality level corresponding with the testing result generated Suddenly include:
Step S31 is read with first abnormal rate, the second abnormal rate in second testing result and described the The corresponding weighting coefficient of third abnormal rate in three testing results；
Further, after generating the first testing result, the second testing result and third testing result, the first detection As a result the first abnormal rate in characterizes the quantity accounting in group element there are unreasonable abnormal data, in the second testing result The second abnormal rate characterize the quantity accounting that there is not corresponding abnormal data in group element, and the in third testing result Three abnormal rate characterize in group element that there are the quantity accountings of the incorrect abnormal data of Articulation；By all kinds of different to characterizing The first abnormal rate, the second abnormal rate and the third abnormal rate of constant amount accounting are integrated, and it is whole to produce reflection medical data The testing result of weight.And in view of different abnormal data types is different to the influence degree of medical data quality, such as The exception of Articulation type can affect greatly medical data, and unreasonable type is abnormal caused by medical data It influences relatively weak；To the influence for more accurate all kinds of exceptions of embodiment to medical data quality, for all kinds of exceptions It is provided with corresponding weighting coefficient, read and characterizes all kinds of exceptions, i.e. the first abnormal rate, the second abnormal rate and third abnormal rate Corresponding weighting coefficient, to be integrated by each weighting coefficient to the first abnormal rate, the second abnormal rate and third abnormal rate.
Step S32, with each weighting coefficient respectively to first abnormal rate, the second abnormal rate and third abnormal rate It is weighted, generates object detection results；
It, will be each after reading weighting coefficient corresponding with the first abnormal rate, the second abnormal rate and third abnormal rate Weighting coefficient and corresponding first abnormal rate, the second abnormal rate and third abnormal rate are transferred in preset formula, to pass through Preset formula is respectively weighted the first abnormal rate, the second abnormal rate and third abnormal rate with each weighting coefficient, meter Calculating obtained result is the object detection results detected to medical data group.Wherein preset formula are as follows:
Y=(k1*x1+k2*x2+k3*x3)/3
Wherein y indicates object detection results, and it is different that x1, x2 and x3 respectively indicate the first abnormal rate, the second abnormal rate and third Normal rate, k1, k2 and k3 respectively indicate weighting coefficient corresponding with x1, x2 and x3.
By the first abnormal rate of generation, the second abnormal rate and third abnormal rate and each weighting coefficient of reading, it is transferred to In the preset formula, x1, x2, x3, k1, k2 and k3 therein are replaced, is calculated and produces object detection results.
Step S33, by the corresponding relationship between the object detection results and preset testing result and credit rating into Row comparison, determines target quality level corresponding with the object detection results.
Further, by the corresponding relationship between the object detection results of generation and preset testing result and credit rating Comparison, determination and testing result corresponding to object detection results, and the corresponding testing result is corresponding in corresponding relationship Credit rating, target quality level as corresponding with object detection results.Wherein in preset corresponding relationship, testing result It is substantially one section of numberical range, and object detection results are compared with the numberical range, determines corresponding testing result.As in advance If corresponding relationship in, testing result credit rating corresponding between 0.05-0.1 is level-one, testing result 0.11~ Corresponding credit rating is second level between 0.2, and testing result credit rating corresponding between 0.21~0.3 is three Grade；It is 0.15 when calculating obtained object detection results through preset formula, then is carried out with the testing result in corresponding relationship pair Than it is found that corresponding object detection results are second level.And then by target quality level, quality evaluation is carried out to medical data group； It can wherein be assessed by the corresponding relationship between credit rating and quality height, if credit rating level-one corresponds to high quality, i.e., The medical data that credit rating is level-one will be computed and be evaluated as the medical data of high quality, realize and pass through credit rating height table Levy the quality height of medical data.
In addition, referring to figure 2., the present invention provides a kind of quality assessment device of medical data, in medical data of the present invention Quality assessment device first embodiment in, the quality assessment device of the medical data includes:
Read module 10, for reading base data table, medical insurance tables of data and the medical tables of data of each medical patient, and will The base data table, medical insurance tables of data and medical tables of data are set as a group element, form medical data group；
Detection module 20, for carrying out data rationality checking, number respectively to each group element in the medical data group According to correspondence detection and Articulation detection, testing result is generated；
Evaluation module 30, for determining and generating according to the corresponding relationship between preset testing result and credit rating The corresponding target quality level of the testing result medical data group is carried out and according to the target quality level Quality evaluation.
The quality assessment device of the medical data of the present embodiment, by read module 10 by each medical patient's of reading Base data table, medical insurance tables of data and medical tables of data form the medical data group of medical patient as group element；Detection module 20, which carry out data rationality checking, the detection of data correspondence and Articulation to each group of element in medical data group respectively, examines It surveys, generates testing result；The corresponding relationship being previously provided between testing result and credit rating, after generating testing result, Evaluation module 30 is according to the corresponding relationship, it may be determined that corresponding target quality level, and then according to target quality level, to medical treatment Data group carries out quality evaluation.Medical number is formed by by all kinds of medical data because medical data group is substantially in treatment process According to thus the quality evaluation to medical data group, the substantially quality evaluation to medical data；By detecting medical data group Data reasonability, correspondence and the Articulation of middle each group element, testing result generated reflect the inside number of each group element The correctness of the integrality of data and corresponding relationship accordingly and between each group element；With aimed quality corresponding with the testing result Grade is as according to the quality evaluation for carrying out medical data；It avoids carrying out verification assessment in a manual manner, so that medical data Assessment it is more accurate, improve the efficiency and the degree of automation of assessment.
Further, in another embodiment of quality assessment device of medical data of the present invention, the testing result includes First testing result, the second testing result and third testing result, the detection module are used for:
Each described group of element is arranged using data carry out data rationality checking as unit respectively, generates the first testing result；
The detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generates the second testing result；
To there are the cells of operational data to carry out Articulation detection in each described group of element, third detection knot is generated Fruit.
Further, in another embodiment of quality assessment device of medical data of the present invention, the detection module is also used In:
The data column in each described group of element are traversed one by one respectively, read the column identifier of each data column, and root According to each column identifier, the value type data column in each data column are determined；
The cell in each data column with the presence or absence of data for null value is detected, data are the unit of null value if it exists Lattice, then to the abnormal identifier of each cell addition first；
The target data for exceeding preset range in each value type data column with the presence or absence of numerical value is detected, is counted if it exists Value exceeds the target data of preset range, then to the abnormal identifier of target data addition second；
According to the quantity of the described first abnormal identifier and the second abnormal identifier, the first testing result is generated.
Further, in another embodiment of quality assessment device of medical data of the present invention, the detection module is also used In:
Judge whether the first abnormal rate in first testing result is greater than default value, if first abnormal rate is big In the default value, then stop carrying out correspondence detection to each described group of element；
If first abnormal rate is not more than the default value, according to the correspondence in each described group of element between data Relationship, determining the first corresponding data corresponding with each described first abnormal identifier, and with each second exception identifier Corresponding second corresponding data；
First corresponding data and the second corresponding data are rejected from each described group of element, to each described group of element It is updated, and executes and the detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generate the second inspection The step of surveying result.
Further, in another embodiment of quality assessment device of medical data of the present invention, the detection module is also used In:
It selects any described group of element as target group element from each described group of element, and will be removed in each described group of element Other described group of element except the target group element are set as to contrast groups element；
Read in the target group element the first row identifier of data line and each described to each number in contrast groups element According to the second capable row identifier, and judge it is each it is described to whether exist in each second row identifier of contrast groups element with The corresponding object identifier of first row identifier；
If there is object identifier corresponding with first row identifier, the data pair of each described group of element are completed Answering property detects；
Object identifier corresponding with first row identifier if it does not exist, then to having, there is no the corresponding mesh The data line for marking first row identifier of identifier adds third exception identifier, and according to the third exception identifier Quantity generate the second testing result.
Further, in another embodiment of quality assessment device of medical data of the present invention, the detection module is also used In:
The cell mark of cell in each described group of element is read, and determines that there are operations according to cell mark The Set cell of data；
It detects in the cell data of each Set cell with the presence or absence of the object element that Articulation detection is abnormal Lattice data；
The abnormal Set cell data of Articulation detection if it exists, then to Set cell data addition the 4th Abnormal identifier, and third testing result is generated according to the quantity of the described 4th abnormal identifier.
Further, in another embodiment of quality assessment device of medical data of the present invention, the evaluation module is also wrapped It includes:
Reading unit, for reading with first abnormal rate, the second abnormal rate in second testing result and The corresponding weighting coefficient of third abnormal rate in the third testing result；
Generation unit is used for each weighting coefficient respectively to first abnormal rate, the second abnormal rate and third Abnormal rate is weighted, and generates object detection results；
Determination unit, for by between the object detection results and preset testing result and credit rating it is corresponding pass System compares, and determines target quality level corresponding with the object detection results.
Wherein, each virtual functions module of the quality assessment device of above-mentioned medical data is stored in medical data shown in Fig. 3 Quality assessment arrangement memory 1005 in, processor 1001 execute medical data quality evaluation program when, realize Fig. 2 institute Show the function of modules in embodiment.
Referring to Fig. 3, Fig. 3 is the device structure schematic diagram for the hardware running environment that present invention method is related to.
The quality assessment arrangement of medical data of the embodiment of the present invention can be PC (personal computer, individual calculus Machine), it is also possible to the terminal devices such as smart phone, tablet computer, E-book reader, portable computer.
As shown in figure 3, the quality assessment arrangement of the medical data may include: processor 1001, such as CPU (Central Processing Unit, central processing unit), memory 1005, communication bus 1002.Wherein, communication bus 1002 for realizing Connection communication between processor 1001 and memory 1005.Memory 1005 can be high-speed RAM (random access Memory, random access memory), it is also possible to stable memory (non-volatile memory), such as disk storage Device.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
Optionally, the quality assessment arrangement of the medical data can also include user interface, network interface, camera, RF (Radio Frequency, radio frequency) circuit, sensor, voicefrequency circuit, WiFi (Wireless Fidelity, WiMAX) mould Block etc..User interface may include display screen (Display), input unit such as keyboard (Keyboard), and optional user connects Mouth can also include standard wireline interface and wireless interface.Network interface optionally may include the wireline interface, wireless of standard Interface (such as WI-FI interface).
It will be understood by those skilled in the art that the quality assessment arrangement structure of medical data shown in Fig. 3 is not constituted Restriction to the quality assessment arrangement of medical data may include than illustrating more or fewer components, or the certain portions of combination Part or different component layouts.
As shown in figure 3, as may include operating system, network communication in a kind of memory 1005 of readable storage medium storing program for executing The quality evaluation program of module and medical data.Operating system is the quality assessment arrangement hardware for managing and controlling medical data With the program of software resource, the operation of the quality evaluation program and other softwares and/or program of medical data is supported.Network is logical Believe module for realizing the communication between each component in the inside of memory 1005, and with its in the quality assessment arrangement of medical data It is communicated between its hardware and software.
In the quality assessment arrangement of medical data shown in Fig. 3, processor 1001 is deposited in memory 1005 for executing The quality evaluation program of the medical data of storage realizes the step in each embodiment of the method for evaluating quality of above-mentioned medical data.
The present invention provides a kind of readable storage medium storing program for executing, the readable storage medium storing program for executing is stored with one or more than one journey Sequence, the one or more programs can also be executed by one or more than one processor for realizing above-mentioned doctor Treat the step in each embodiment of method for evaluating quality of data.
It should also be noted that, herein, the terms "include", "comprise" or its any other variant are intended to non- It is exclusive to include, so that the process, method, article or the device that include a series of elements not only include those elements, It but also including other elements that are not explicitly listed, or further include solid by this process, method, article or device Some elements.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including There is also other identical elements in the process, method of the element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art The part contributed out can be embodied in the form of software products, which is stored in one as described above In readable storage medium storing program for executing (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be hand Machine, computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all at this Under the design of invention, using equivalent structure transformation made by description of the invention and accompanying drawing content, or directly/it is used in it indirectly He is included in scope of patent protection of the invention relevant technical field.

Claims (10)

1. a kind of method for evaluating quality of medical data, which is characterized in that the method for evaluating quality of the medical data include with Lower step:
Read base data table, medical insurance tables of data and the medical tables of data of each medical patient, and by the base data table, medical insurance Tables of data and medical tables of data are set as a group element, form medical data group；
Data rationality checking, the detection of data correspondence and hook are carried out to each group element in the medical data group respectively and check pass System's detection, generates testing result；
According to the corresponding relationship between preset testing result and credit rating, determine corresponding with the testing result generated Target quality level, and according to the target quality level, quality evaluation is carried out to the medical data group.
2. the method for evaluating quality of medical data as described in claim 1, which is characterized in that the testing result includes first Testing result, the second testing result and third testing result；
The each group element in the medical data group carries out data rationality checking, the detection of data correspondence respectively and hooks Checking the step of relationship detects, generates testing result includes:
Each described group of element is arranged using data respectively and carries out data rationality checking as unit, generates the first testing result；
The detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generates the second testing result；
To there are the cells of operational data to carry out Articulation detection in each described group of element, third testing result is generated.
3. the method for evaluating quality of medical data as claimed in claim 2, which is characterized in that the data rationality checking packet Include assigning null data detection and numerical value range detection, it is described to each described group of element respectively using data arrange for unit progress data it is reasonable Property detection, generate the first testing result the step of include:
The data column in each described group of element are traversed one by one respectively, read the column identifier of each data column, and according to each The column identifier determines the value type data column in each data column；
The cell in each data column with the presence or absence of data for null value is detected, data are the cell of null value if it exists, then To the abnormal identifier of each cell addition first；
The target data for exceeding preset range in each value type data column with the presence or absence of numerical value is detected, numerical value is super if it exists The target data of preset range out, then to the abnormal identifier of target data addition second；
According to the quantity of the described first abnormal identifier and the second abnormal identifier, the first testing result is generated.
4. the method for evaluating quality of medical data as claimed in claim 3, which is characterized in that described to each described group of element point Include: before the step of not carrying out the detection of data correspondence with data behavior unit, generating the second testing result
Judge whether the first abnormal rate in first testing result is greater than default value, if first abnormal rate is greater than institute Default value is stated, then stops carrying out correspondence detection to each described group of element；
If first abnormal rate is not more than the default value, according to the corresponding pass in each described group of element between data System, determining the first corresponding data corresponding with each described first abnormal identifier, and with each second exception identifier pair The second corresponding data answered；
First corresponding data and the second corresponding data are rejected from each described group of element, to be carried out to each described group of element It updates, and executes and the detection of data correspondence is carried out with data behavior unit respectively to each described group of element, generate the second detection knot The step of fruit.
5. the method for evaluating quality of medical data as claimed in claim 4, which is characterized in that described to each described group of element point Not with data behavior unit carry out the detection of data correspondence, generate the second testing result the step of include:
Select any described group of element as target group element from each described group of element, and described by removing in each described group of element Other described group of element except target group element are set as to contrast groups element；
Read in the target group element the first row identifier of data line and each described to each data line in contrast groups element The second row identifier, and judge it is each it is described to whether exist in each second row identifier of contrast groups element with it is described The corresponding object identifier of first row identifier；
If there is object identifier corresponding with first row identifier, the data correspondence of each described group of element is completed Detection；
Object identifier corresponding with first row identifier if it does not exist, then to having, there is no the corresponding target marks The data line for knowing first row identifier of symbol adds third exception identifier, and according to the number of the third exception identifier Amount generates the second testing result.
6. the method for evaluating quality of medical data as claimed in claim 5, which is characterized in that described in each described group of element There are the cell of operational data carry out Articulation detection, generate third testing result the step of include:
The cell mark of cell in each described group of element is read, and determines that there are operational datas according to cell mark Set cell；
It detects in the cell data of each Set cell with the presence or absence of the Set cell number that Articulation detection is abnormal According to；
The abnormal Set cell data of Articulation detection if it exists are then abnormal to Set cell data addition the 4th Identifier, and third testing result is generated according to the quantity of the described 4th abnormal identifier.
7. the method for evaluating quality of medical data as claimed in claim 6, which is characterized in that described to be tied according to preset detection The step of corresponding relationship between fruit and credit rating, determining target quality level corresponding with the testing result that is generating, wraps It includes:
It reads with first abnormal rate, in the second abnormal rate and the third testing result in second testing result The corresponding weighting coefficient of third abnormal rate；
Meter is weighted to first abnormal rate, the second abnormal rate and third abnormal rate respectively with each weighting coefficient It calculates, generates object detection results；
Corresponding relationship between the object detection results and preset testing result and credit rating is compared, determine with The corresponding target quality level of the object detection results.
8. a kind of quality assessment device of medical data, which is characterized in that the quality assessment device of the medical data includes:
Read module, for reading base data table, medical insurance tables of data and the medical tables of data of each medical patient, and by the base Plinth tables of data, medical insurance tables of data and medical tables of data are set as a group element, form medical data group；
Detection module, it is corresponding for carrying out data rationality checking, data respectively to each group element in the medical data group Property detection and Articulation detection, generate testing result；
Evaluation module, for determining described with generation according to the corresponding relationship between preset testing result and credit rating The corresponding target quality level of testing result, and according to the target quality level, quality is carried out to the medical data group and is commented Estimate.
9. a kind of quality assessment arrangement of medical data, which is characterized in that the quality assessment arrangement of the medical data includes: to deposit Reservoir, processor, communication bus and the medical data being stored on the memory quality evaluation program；
The communication bus is for realizing the connection communication between processor and memory；
The processor is used to execute the quality evaluation program of the medical data, to realize such as any one of claim 1-7 The step of method for evaluating quality of the medical data.
10. a kind of readable storage medium storing program for executing, which is characterized in that be stored with the quality evaluation of medical data on the readable storage medium storing program for executing It realizes when the quality evaluation program of program, the medical data is executed by processor as of any of claims 1-7 The step of method for evaluating quality of medical data.
CN201811462376.9A 2018-11-30 2018-11-30 Quality evaluation method, device and equipment of medical data and readable storage medium Active CN109615204B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811462376.9A CN109615204B (en) 2018-11-30 2018-11-30 Quality evaluation method, device and equipment of medical data and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811462376.9A CN109615204B (en) 2018-11-30 2018-11-30 Quality evaluation method, device and equipment of medical data and readable storage medium

Publications (2)

Publication Number Publication Date
CN109615204A true CN109615204A (en) 2019-04-12
CN109615204B CN109615204B (en) 2023-02-03

Family

ID=66005832

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811462376.9A Active CN109615204B (en) 2018-11-30 2018-11-30 Quality evaluation method, device and equipment of medical data and readable storage medium

Country Status (1)

Country Link
CN (1) CN109615204B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111554406A (en) * 2020-04-10 2020-08-18 安徽华米智能科技有限公司 Physiological data processing method and device, electronic equipment and storage medium
CN112201330A (en) * 2020-09-29 2021-01-08 四川省人民医院 Medical quality monitoring and evaluating method combining DRGs tool and Bayesian model

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102013084A (en) * 2010-12-14 2011-04-13 江苏大学 System and method for detecting fraudulent transactions in medical insurance outpatient services
CN103077494A (en) * 2013-01-09 2013-05-01 北京中科金财科技股份有限公司 Method and system for processing and evaluating dynamic data
CN104134157A (en) * 2014-08-08 2014-11-05 平安养老保险股份有限公司 Suspicious behavior audit system and method in medical insurance reimbursement process
CN104133810A (en) * 2014-08-08 2014-11-05 平安养老保险股份有限公司 System and method for verifying medical insurance reimbursement qualification
CN105574334A (en) * 2015-12-15 2016-05-11 深圳安泰创新科技股份有限公司 Medical information processing method and system
CN106156502A (en) * 2016-07-05 2016-11-23 东软集团股份有限公司 The appraisal procedure of a kind of report examination & verification and device
CN107609980A (en) * 2017-09-07 2018-01-19 平安医疗健康管理股份有限公司 Medical data processing method, device, computer equipment and storage medium
CN107785057A (en) * 2017-06-19 2018-03-09 平安医疗健康管理股份有限公司 Medical data processing method, device, storage medium and computer equipment
CN108305176A (en) * 2018-01-05 2018-07-20 上海栈略数据技术有限公司 A kind of optimization medical care insurance intelligent checks system based on reaction type machine learning
CN108492196A (en) * 2018-03-08 2018-09-04 平安医疗健康管理股份有限公司 The air control method of medical insurance unlawful practice is inferred by data analysis
CN108596770A (en) * 2017-12-29 2018-09-28 山大地纬软件股份有限公司 Medicare fraud detection device and method based on outlier analysis

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102013084A (en) * 2010-12-14 2011-04-13 江苏大学 System and method for detecting fraudulent transactions in medical insurance outpatient services
CN103077494A (en) * 2013-01-09 2013-05-01 北京中科金财科技股份有限公司 Method and system for processing and evaluating dynamic data
CN104134157A (en) * 2014-08-08 2014-11-05 平安养老保险股份有限公司 Suspicious behavior audit system and method in medical insurance reimbursement process
CN104133810A (en) * 2014-08-08 2014-11-05 平安养老保险股份有限公司 System and method for verifying medical insurance reimbursement qualification
CN105574334A (en) * 2015-12-15 2016-05-11 深圳安泰创新科技股份有限公司 Medical information processing method and system
CN106156502A (en) * 2016-07-05 2016-11-23 东软集团股份有限公司 The appraisal procedure of a kind of report examination & verification and device
CN107785057A (en) * 2017-06-19 2018-03-09 平安医疗健康管理股份有限公司 Medical data processing method, device, storage medium and computer equipment
CN107609980A (en) * 2017-09-07 2018-01-19 平安医疗健康管理股份有限公司 Medical data processing method, device, computer equipment and storage medium
CN108596770A (en) * 2017-12-29 2018-09-28 山大地纬软件股份有限公司 Medicare fraud detection device and method based on outlier analysis
CN108305176A (en) * 2018-01-05 2018-07-20 上海栈略数据技术有限公司 A kind of optimization medical care insurance intelligent checks system based on reaction type machine learning
CN108492196A (en) * 2018-03-08 2018-09-04 平安医疗健康管理股份有限公司 The air control method of medical insurance unlawful practice is inferred by data analysis

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111554406A (en) * 2020-04-10 2020-08-18 安徽华米智能科技有限公司 Physiological data processing method and device, electronic equipment and storage medium
CN111554406B (en) * 2020-04-10 2024-02-27 安徽华米健康科技有限公司 Physiological data processing method, device, electronic equipment and storage medium
CN112201330A (en) * 2020-09-29 2021-01-08 四川省人民医院 Medical quality monitoring and evaluating method combining DRGs tool and Bayesian model
CN112201330B (en) * 2020-09-29 2024-03-08 四川省人民医院 Medical quality monitoring and evaluating method combining DRGs tool and Bayesian model

Also Published As

Publication number Publication date
CN109615204B (en) 2023-02-03

Similar Documents

Publication Publication Date Title
Brada et al. Does investor protection increase foreign direct investment? A meta‐analysis
CN110246031A (en) Appraisal procedure, system, equipment and the storage medium of business standing
CN109360084A (en) Appraisal procedure and device, storage medium, the computer equipment of reference default risk
CN106997493A (en) Lottery user attrition prediction method and its system based on multi-dimensional data
CN106022849A (en) New media value and effect evaluation method and system
CN109636613A (en) Medical data abnormality recognition method, device, terminal and storage medium
CN106469395A (en) A kind of data commodity dynamic comprehensive appraisal procedure and system
CN110009449A (en) Business trust appraisal procedure, server and storage medium
CN109299085A (en) A kind of data processing method, electronic equipment and storage medium
CN106529110A (en) Classification method and equipment of user data
CN109801692A (en) A kind of Medical record database method for evaluating quality and device
CN108335723A (en) Test validity judgment method and device
Lawson et al. The impact of quality variations on patients undergoing surgery for renal cell carcinoma: a national cancer database study
CN108520351A (en) Rural Land Circulation pattern Performance Evaluation Methods, system, equipment, storage medium
CN109615204A (en) Method for evaluating quality, device, equipment and the readable storage medium storing program for executing of medical data
CN105740434B (en) Network information methods of marking and device
CN106447144A (en) Target object evaluation method and target object evaluation device
CN107704869A (en) A kind of corpus data methods of sampling and model training method
CN106502881A (en) A kind of method of testing of commodity ordering rule and device
CN110503567A (en) Data verification method, equipment, storage medium and device
CN110147941A (en) Content of examination acquisition methods, Stakeholder Evaluation method and device
CN108985595A (en) The move transaction service evaluation method and device mutually commented based on counterparty
Liu et al. Equilibrium information in credence goods
CN107194190A (en) Method and device of the service object to cost impacts is recognized in medical expenses database
CN107133747A (en) A kind of method for evaluating quality and device

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