CN109636623A - Medical data method for detecting abnormality, device, equipment and storage medium - Google Patents
Medical data method for detecting abnormality, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109636623A CN109636623A CN201811226395.1A CN201811226395A CN109636623A CN 109636623 A CN109636623 A CN 109636623A CN 201811226395 A CN201811226395 A CN 201811226395A CN 109636623 A CN109636623 A CN 109636623A
- Authority
- CN
- China
- Prior art keywords
- medical data
- detected
- data
- medical
- default
- 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
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The present invention provides a kind of medical data method for detecting abnormality, device, equipment and storage medium based on big data, this method comprises: obtaining the abnormality detection when detecting abnormality detection request and requesting corresponding medical data to be detected；Judge the effective historical record that whether there is the corresponding insured people of target of the medical data to be detected in historical data base；Judge the medical data to be detected with the presence or absence of abnormal based on effective historical record of the insured people of the target if there are effective historical records of the corresponding insured people of target of the medical data to be detected in historical data base；If the medical data to be detected has exception, the medical data to be detected is subjected to abnormal marking.The present invention is based on the technologies such as relational network analysis, data normalization, data update, realize to abnormal behavior of swiping the card, can help the use of specification medical insurance card.
Description
Technical field
The present invention relates to medical data processing technology more particularly to a kind of medical data method for detecting abnormality, device,
Equipment and storage medium.
Background technique
Social medical insurance is state and society according to certain laws and regulations, is provided for the labourer into scope of insurance coverage
Basic medical demand guarantee when illness and the social security system established.Social medical insurance card (abbreviation medical insurance card of the present invention) is
It by Ministry of Labour and Social Security's unified planning, is issued towards the society by various regions labor and social security department, is applied to labour and society is protected
Hinder the integrated circuit card (IC card) of every business scope.
Medical insurance card is the daily important documents for seeing a doctor purchase of insurant, is the carrier of Personal Account of Medical Insurance, is used for
Insurant essential information is recorded, including the personal basic medical insurance expense paid, according to the cut-in of regulation ratio by employment list
Position pay basic medical insurance expense, other funds, interest.It is that insurant carries out the non-financial dedicated of basic medical consumption
Card.Medical insurance card is Individual account of social health insurance personality card, and personally card is identification code, and storage recites personal identification number
Code, name, gender and account sum are appropriated, the detailed profiles such as consumption.
Universal with social medical services and medical insurance card, more and more people enjoy a series of correlations using medical insurance card
Medical services.According to relevant regulations, medical insurance card, which can only limit, to be used in person and is only used in medical services, but some
People rents other people social security cards or insured people oneself and helps others to pay with the social security card of oneself using social security card arbitrage or insured people,
These abnormal behaviours all destroy the operating specification of medical insurance card, we use it is necessary to prevent this unreasonable medical insurance card, because
This, we are badly in need of a kind of detection method of medical insurance card exception medical data.
Summary of the invention
The main purpose of the present invention is to provide a kind of medical data method for detecting abnormality, it is intended to which solution can not detect exception
The technical issues of brush medical insurance card behavioral data.
To achieve the above object, the present invention provides a kind of medical data method for detecting abnormality, which is characterized in that the medical treatment
Detection method includes the following steps for data exception:
When detecting abnormality detection request, obtains the abnormality detection and request corresponding medical data to be detected；
Judge the effective history that whether there is the corresponding insured people of target of the medical data to be detected in historical data base
Record；
If there are effective historical record of the corresponding insured people of target of the medical data to be detected in historical data base,
Based on effective historical record of the insured people of the target, judge the medical data to be detected with the presence or absence of abnormal；
If the medical data to be detected has exception, the medical data to be detected is subjected to abnormal marking.
Optionally, it whether there is the corresponding insured people of target of the medical data to be detected in the judgement historical data base
Effective historical record the step of after include:
If effective historical record of the corresponding insured people of target of the medical data to be detected is not present in historical data base,
Diagnosis and treatment normative database is then inquired according to the medical data to be detected, obtains the corresponding diagnosis and treatment rule of the medical data to be detected
Model；
Based on the diagnosis and treatment specification, judge the medical data to be detected with the presence or absence of abnormal；
If the medical data to be detected has exception, the medical data to be detected is subjected to abnormal marking.
Optionally, the judgement medical data to be detected includes: later with the presence or absence of abnormal step
If there is no exceptions for the medical data to be detected, using the medical data to be detected as effective historical record
It is added to historical data base.
Optionally, effective historical record based on the insured people of the target judges that the medical data to be detected is
It is no to include: in the presence of abnormal step
Default first analysis indexes are obtained, according to effective historical record of the insured people of the target, obtain each default first
The corresponding historical data of analysis indexes and error threshold；
Each default corresponding current data of first analysis indexes is extracted from the medical data to be detected, each will preset the
The corresponding current data of one analysis indexes is compared with corresponding historical data, and it is corresponding to obtain each default first analysis indexes
Difference；
Judge whether there is default first analysis indexes that corresponding difference is greater than corresponding error threshold；
Default first analysis indexes that difference is greater than corresponding error threshold are corresponded to if it exists, then determine the medical treatment to be detected
Data exist abnormal.
Optionally, effective historical record based on the insured people of the target judges that the medical data to be detected is
It is no to include: in the presence of abnormal step
Default second analysis indexes and each default corresponding weight of second analysis indexes are obtained, and is joined based on the target
Effective historical record of guarantor obtains each default corresponding historical data of second analysis indexes；
Each default corresponding current data of second analysis indexes is extracted from the medical data to be detected, each will preset the
The corresponding current data of two analysis indexes is compared with corresponding historical data, and it is corresponding to obtain each default second analysis indexes
Difference；
Based on each default corresponding difference of second analysis indexes and weight, the calculating medical data to be detected is corresponding to be added
Weight average error amount；
The weighted average error value and preset reasonable error threshold value are compared, judge the weighted average error
Whether value is greater than reasonable error threshold value；
If the weighted average error value is greater than reasonable error threshold value, determine that there are different for the medical data to be detected
Often.
Optionally, described to carry out each default corresponding current data of second analysis indexes and corresponding historical data pair
Include: than, the step of obtaining each default second analysis indexes corresponding difference
When default second analysis indexes are diagnosis and treatment item index or medicament categories index, from the current data
Current diagnosis and treatment item or current medical type are extracted, history diagnosis and treatment item or history drug kind are extracted from the historical data
Class；
Calculate the similarity or current medical type and history drug kind of the current diagnosis and treatment item and history diagnosis and treatment item
The similarity of class；
Based on diagnosis and treatment item index described in the similarity calculation or the corresponding difference of medicament categories index.
Optionally, if there are the effective of the corresponding insured people of target of the medical data to be detected in the historical data base
Historical record, then effective historical record based on the insured people of the target judge the medical data to be detected with the presence or absence of different
Normal step includes:
If being obtained in historical data base there are effective historical record of the corresponding insured people of target of the medical data to be detected
Take effective historical record quantity of the insured people of the target；
If effective historical record quantity is greater than preset threshold, effective history note based on the insured people of the target
Record judges the medical data to be detected with the presence or absence of abnormal；
If effective historical record quantity is less than preset threshold, according to the medical data inquiry diagnosis and treatment rule to be detected
Model database obtains the corresponding diagnosis and treatment specification of the medical data to be detected；Based on the diagnosis and treatment specification, the doctor to be detected is judged
Data are treated with the presence or absence of abnormal.
In addition, to achieve the above object, the present invention also provides a kind of medical data abnormal detector, the medical datas
Abnormal detector includes:
Module is obtained, for the abnormality detection being obtained and requesting corresponding doctor to be detected when detecting abnormality detection request
Treat data；
Historical query module whether there is the corresponding target of the medical data to be detected for judging in historical data base
Effective historical record of insured people；
Abnormal judgment module, if for there are the corresponding insured people of target of the medical data to be detected in historical data base
Effective historical record, then whether effective historical record based on the insured people of the target judge the medical data to be detected
There are exceptions；
Abnormal marking module, if there is exception for the medical data to be detected, by the medical data to be detected
Carry out abnormal marking.
In addition, to achieve the above object, the present invention also provides a kind of medical data abnormality detecting apparatus, the medical datas
Abnormality detecting apparatus includes processor, memory and is stored in the doctor that can be executed on the memory and by the processor
It treats data exception and detects program, wherein realizing when the medical data abnormality detecting program is executed by the processor as above-mentioned
Medical data method for detecting abnormality the step of.
In addition, to achieve the above object, the present invention also provides a kind of storage medium, being stored with medical treatment on the storage medium
Data exception detects program, wherein realizing such as above-mentioned medical treatment when the medical data abnormality detecting program is executed by processor
The step of data exception detection method.
The embodiment of the present invention is by the way that it is corresponding to be detected to obtain abnormality detection request when detecting abnormality detection request
Medical data；Judge the effective history that whether there is the corresponding insured people of target of the medical data to be detected in historical data base
Record；If there are effective historical record of the corresponding insured people of target of the medical data to be detected, bases in historical data base
In effective historical record of the insured people of the target, judge the medical data to be detected with the presence or absence of abnormal；If described to be checked
It surveys medical data and there is exception, then the medical data to be detected is subjected to abnormal marking, so that detection device is according to each ginseng
The medical treatment habit of guarantor carries out abnormality detection insured people medical data to be detected, as the doctor of medical data to be detected and insured people
When treatment habit deviates, medical data to be detected needs to verify under the further line of user there may be violation situation, can be effective
Detect abnormal behavior of swiping the card, the use of specification medical insurance card.
Detailed description of the invention
Fig. 1 is the medical data abnormality detecting apparatus structural representation for the hardware running environment that the embodiment of the present invention is related to
Figure；
Fig. 2 is the flow diagram of medical data method for detecting abnormality first embodiment of the present invention；
Fig. 3 is the flow diagram of medical data method for detecting abnormality second embodiment of the present invention；
Fig. 4 is the flow diagram of medical data method for detecting abnormality 3rd embodiment of the present invention；
Fig. 5 is the functional block diagram of medical data abnormal detector first embodiment of the present invention.
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.
Referring to Figure 1, Fig. 1 is the hardware structural diagram of medical data abnormality detecting apparatus provided by the present invention.
The medical data abnormality detecting apparatus can be PC, be also possible to smart phone, tablet computer, portable calculating
The equipment equipment having a display function such as machine, desktop computer, optionally, the medical data abnormality detecting apparatus can be clothes
Business device equipment, there are the rear end management system of medical data abnormality detection, user is by the rear end management system to medical number
It is managed according to abnormality detecting apparatus.
The medical data abnormality detecting apparatus may include: the components such as processor 10 and memory 20.In the doctor
It treats in data exception detection device, the processor 10 is connect with the memory 20, is stored with medical treatment on the memory 20
Data exception detects program, and processor 10 can call the medical data abnormality detecting program stored in memory 20, and realize
The step of embodiment as each such as following medical data method for detecting abnormality.
The memory 20 can be used for storing software program and various data.Memory 20 can mainly include storage journey
Sequence area and storage data area, wherein storing program area can the (ratio of application program needed for storage program area, at least one function
Such as medical data abnormality detecting program)；Storage data area may include database, such as the present invention need to inquire and obtain effective history
Record etc..In addition, memory 20 may include high-speed random access memory, it can also include nonvolatile memory, such as
At least one disk memory, flush memory device or other volatile solid-state parts.
Processor 10 is the control centre of medical data abnormality detecting apparatus, entire using various interfaces and connection
The various pieces of medical data abnormality detecting apparatus, by run or execute the software program being stored in memory 20 and/or
Module, and the data being stored in memory 20 are called, execute the various functions and processing of medical data abnormality detecting apparatus
Data, to carry out integral monitoring to medical data abnormality detecting apparatus.Processor 10 may include one or more processing units；
Optionally, processor 10 can integrate application processor and modem processor, wherein the main processing operation system of application processor
System, user interface and application program etc., modem processor mainly handles wireless communication.It is understood that above-mentioned modulation
Demodulation processor can not also be integrated into processor 10.
It will be understood by those skilled in the art that medical data abnormality detecting apparatus structure shown in Fig. 1 is not constituted pair
The restriction of medical data abnormality detecting apparatus may include components more more or fewer than diagram, or combine certain components, or
The different component layout of person.
Based on above-mentioned hardware configuration, each embodiment of the method for the present invention is proposed, detection device hereinafter is medical number
According to the abbreviation of abnormality detecting apparatus.
The present invention provides a kind of medical data method for detecting abnormality.
It is the flow diagram of medical data method for detecting abnormality first embodiment of the present invention referring to Fig. 2, Fig. 2.
In the present embodiment, the medical data method for detecting abnormality the following steps are included:
Step S10 obtains the corresponding medical number to be detected of abnormality detection request when detecting abnormality detection request
According to；
Abnormality detection request is that triggering medical data method for detecting abnormality of the present invention corresponds to medical data abnormality detecting program
The instruction of starting can trigger abnormality detection request by a preset external event/page request, as user input it is different
The clicking operation often detected；It can also be by using the mode of timing JOB (task) as medical data abnormality detecting program
Start interface, triggering is carried out at regular intervals to the abnormality detection of medical data, medical number to be detected can also received
It carries out abnormality detection, can also be carried out after the data volume of received medical data to be detected reaches certain threshold value different immediately after
Often detection.Optionally, the present invention can be one or more of medical data auditing flow to the abnormality detection of medical data
Flow nodes, can be by the abnormality detecting program of the circulation automatic trigger medical data of flow nodes.
Medical data that medical data to be detected, that is, abnormality detection request is directed toward, request detection.Medical data include but
It is not limited to: when secondary visit type, diagnosis and treatment item mark, consultation time, diagnostic result, medicining condition, the diagnosis and treatment amount of money, charges for drug
Deng.
After insured people's brush medical insurance card, medical data can be uploaded to hospital equipment by card swiping device, then by hospital equipment
It is sent to detection device or is uploaded directly into detection device, can directly be stored in the memory of detection device, it is different in progress
Often when detection, detection device directly obtains medical data to be detected according to abnormality detection request from local storage, can also be with
It is stored in data storage device/cloud of medical data, so that detection device is when carrying out the detection of abnormal medical data, according to
Abnormality detection request obtains medical data to be detected from data storage device/cloud.
Step S20 judges to whether there is the corresponding insured people's of target of the medical data to be detected in historical data base
Effective historical record；
Historical data base is used to store the historical medical data of insured people, can also store the historical medical data of insured people
The data obtained after being further processed, for example, by the characteristic for obtain after data processing to medical data,
Such as: insured people A swipes the card 12 times for 1 year, each amount of money 150.
Effective historical record refers to after abnormality detection, determines medical data without exception, in the present embodiment, insured people's
Effective historical record is for judging the new medical data of the insured people with the presence or absence of abnormal.
Each insured people has the medical insurance number for being specific to oneself, and it is each that medical insurance number, which is the medical insurance account of insured people,
The medical insurance identification number of a insured people can inquire unique, specific insured people according to medical insurance number, meanwhile, insured people often swipes the card
Once, a medical data is just generated, in the present embodiment, using medical insurance number as the mark of medical data.Specifically, it is getting
After medical data to be detected, corresponding medical insurance number to be detected is obtained based on the medical data to be detected；Based on medical insurance number to be detected
Enquiry of historical data library judges with the presence or absence of the corresponding effective historical record of medical insurance number to be detected in historical data base, i.e., to be checked
Survey effective historical record of the corresponding insured people of target of medical data.
When insured people uses medical insurance card for the first time, swipe the card record in historical data base there are no the history of the insured people, or
The history of the insured people of person swipes the card record and all swipes the card record for abnormal medical insurance, and it is insured that this is also not present in historical data base at this time
Effective historical record of people.If effective historical record of the insured people of target is not present in historical data base, then target can be joined
The information of guarantor marks, can also be according to medical data to be detected from preset diagnosis and treatment normative database for manual examination and verification
Corresponding diagnosis and treatment specification is obtained, so that detection device voluntarily compares the abnormal judgement of progress.
Step S30, if effectively going through there are the corresponding insured people of target of medical data to be detected in historical data base
Records of the Historian record, then effective historical record based on the insured people of the target judge the medical data to be detected with the presence or absence of abnormal；
The abnormal judgement of medical data to be detected, the judge index being related to includes but is not limited to: type (diagnosis and treatment item kind
Class/medicament categories), time (diagnosis and treatment item time/purchase medicine time), the frequency (the diagnosis and treatment item frequency/medication frequency), the amount of money (examines
Treat item amount/drug amount of money).
In one embodiment, the corresponding historical data of each index is obtained based on the analysis of effective historical record, for example, by ginseng
Effective historical record of guarantor A, which is analyzed, to be obtained: insured people A is diabetes, and purchase pharmacopoeia class is a, 1-5 of the purchase medicine time at the beginning of the month
Number, monthly for 8 times, the amount of money is every time 200 to the purchase medicine frequency.By type, time, the frequency, the amount of money etc. in medical data to be detected
The corresponding data of index are compared with normal historical data, judge whether there is certain or a variety of exceptions.Wherein, difference refers to
Target corresponds to different Exception Types extremely, and such as type exception, time anomaly, the frequency is abnormal, the amount of money is abnormal, can distinguishing identifier difference
The abnormality detection medical data of Exception Type.
The medical datas such as visit type, diagnosis and treatment item mark, consultation time, administration time, the amount of money of some chronic patients
With certain rule, and this rule will not be broken easily, this rule is related to disease, also with the concrete condition phase of patient
It closes, if this rule is broken, it is most likely that the case where medical insurance card uses extremely occur.
For the rule for obtaining insured people's medical data, historical data base is pre-established, for storing all doctors of insured people
Brushing card data is protected, after the medical data that will acquire carries out data normalization processing, history number is stored in preset data structure
According in library, optionally, data is carried out to every medical data and extract the corresponding historical data of acquisition pre-set level, by pre-set level
Corresponding data correlation storage can be directly to structuring when detection device calculates corresponding mean value to each pre-set level
Data carry out quick obtaining and operation, the mean value for calculating acquisition is used to carry out medical data to be detected for detection device abnormal
Detection.
Optionally, to promote the accuracy that judges extremely, in an embodiment, only reach in the quantity of effective historical record
When certain threshold value, just as the standard judged extremely, i.e. raising sample size, to improve the accuracy of law mining, into
And promote the accuracy judged extremely.Specifically, the step S30 includes:
Step S301, if effectively going through there are the corresponding insured people of target of medical data to be detected in historical data base
Records of the Historian record, obtains effective historical record quantity of the insured people of the target；
Effective historical record of the insured people of goal, the effective Historical medical's number of any one of the insured people of feeling the pulse with the finger-tip mark
According to effective historical record quantity, that is, effective historical record item number is stored by effective historical medical data to historical data
Before library, data normalization processing is carried out to effective historical medical data of acquisition, history is stored in preset data structure
In database, when detecting the request for obtaining effective historical record quantity, effective history is counted based on preset data structure
Quantity is recorded, and is exported, the efficiency for obtaining effective historical record quantity can be promoted.
Step S302, if effective historical record quantity is greater than preset threshold, based on having for the insured people of the target
Historical record is imitated, judges the medical data to be detected with the presence or absence of abnormal；
Preset threshold can also preset system default value by user by user's temporarily customized setting.If having
It imitates historical record quantity and is greater than preset threshold, then the quantity of effective historical record is enough to support the medical treatment rule of the insured people of target
Excavation, then be directly based upon effective historical record of the insured people of target, judge the medical data to be detected with the presence or absence of abnormal.
Step S303, if effective historical record quantity is less than preset threshold, according to the medical data to be detected
Diagnosis and treatment normative database is inquired, the corresponding diagnosis and treatment specification of the medical data to be detected is obtained；Based on the diagnosis and treatment specification, institute is judged
Medical data to be detected is stated with the presence or absence of abnormal.
If effective historical record quantity is less than preset threshold, illustrate effective historical record sample size not enough, thus
There may be certain contingency for medical treatment rule out, to avoid such case, obtain more accurate medical treatment rule, based on examining
Treating the diagnosis and treatment specification in normative database judges the medical data to be detected with the presence or absence of abnormal.
The medical data to be detected is carried out abnormal mark if the medical data to be detected has exception by step S40
Note.
If it is determined that medical data to be detected has exception, then medical data to be detected is subjected to abnormal marking, and export different
Normal testing result, to prompt user verify under line.If medical data to be detected there is no abnormal, to historical data base into
Row data update, and are added to historical data base for medical data to be detected as effective historical record.
Because insured people's state of an illness changes and will lead to its medical data and change, in order to avoid detection device will be this
In the case of normal variation labeled as abnormal, reduce the workload audited under line, in an embodiment, detecting medical treatment to be detected
Data are deposited when abnormal, judge whether the corresponding insured people of target has newest diagnostic result, it may be assumed that if medical data to be detected is deposited
Whether there is update in the diagnostic result of exception, the insured people of inquiry judging target；If the diagnostic result of the insured people of target has update,
Obtain the newest diagnostic result of the insured people of target；Diagnosis and treatment normative database is inquired according to the newest diagnostic result, it is newest to obtain this
The corresponding normal medical specification of diagnostic result, medical data to be detected and the normal medical specification are compared, judged to be checked
Medical data is surveyed with the presence or absence of abnormal；If the medical data to be detected exist it is abnormal, by the medical data to be detected into
Row abnormal marking.
Further, preferably to carry out abnormal marking, so that detection device and/or user select medical data to be detected
It selects corresponding processing mode to be handled, in another embodiment, if medical data to be detected has exception, obtains medical treatment to be detected
The Exception Type of data；Corresponding abnormal mark is obtained according to the Exception Type, and abnormal marking is carried out to medical data to be detected.
Further, in the revision directive inputted after being verified under detecting user's line, by the inspection of medical data to be detected
It is normal for surveying status modifier, and is added to medical data to be detected as effective historical record in historical data base.
The present embodiment is by obtaining the abnormality detection and requesting corresponding medical treatment to be detected when detecting abnormality detection request
Data；Judge the effective history note that whether there is the corresponding insured people of target of the medical data to be detected in historical data base
Record；If being based in historical data base there are effective historical record of the corresponding insured people of target of the medical data to be detected
Effective historical record of the insured people of target judges the medical data to be detected with the presence or absence of abnormal；If described to be detected
There is exception in medical data, then the medical data to be detected is carried out abnormal marking, so that detection device is according to each insured
The medical treatment habit of people carries out abnormality detection insured people medical data to be detected, when the medical treatment of medical data to be detected and insured people
When habit deviates, medical data to be detected is needed to verify under the further line of user, can effectively be examined there may be violation situation
Measure abnormal behavior of swiping the card, the use of specification medical insurance card.
Further, referring to Fig. 3, in medical data method for detecting abnormality second embodiment of the present invention, the step S20
Include: later
Step S50, if the effective of the corresponding insured people of target of the medical data to be detected is not present in historical data base
Historical record then inquires diagnosis and treatment normative database according to the medical data to be detected, obtains the medical data pair to be detected
The diagnosis and treatment specification answered；
When effective historical record of the insured people of target being not present in historical data base, based on diagnosis and treatment specification to doctor to be detected
It treats data and carries out abnormal judgement.
Diagnosis and treatment normative database is pre-established, disease and corresponding diagnosis and treatment specification sample are stored in diagnosis and treatment normative database, and
The sample of the new disease of timed collection and diagnosis and treatment specification, optionally, diagnosis and treatment normative database are also stored with abnormal diagnosis and treatment specification, root
Diagnosis and treatment normative database is inquired according to medical data to be detected, judges whether the medical data to be detected meets diagnosis and treatment specification or exception
It is abnormal then directly to determine that medical data to be detected exists if meeting abnormal diagnosis and treatment specification for diagnosis and treatment specification.
The corresponding diagnosis and treatment specification of the medical data to be detected is obtained, specifically can include: extract in medical data to be detected
Diagnostic result, the diagnostic result includes main diagnosis (disease) and secondary diagnosis (subdivision disease, including complication etc.)；According to examining
Diagnosis and treatment normative database described in disconnected result queries, obtains the corresponding diagnosis and treatment specification of the diagnostic result.Optionally, the diagnostic result
It can be a coding or other identifier symbol.
Step S51 is based on the diagnosis and treatment specification, judges the medical data to be detected with the presence or absence of abnormal；
The corresponding diagnosis and treatment specification of one diagnostic result (or disease), including to be used medicament categories, diagnosis and treatment item, examine
Treatment/purchase medicine the frequency, diagnosis and treatment item and drug amount of money etc., by medicament categories, diagnosis and treatment item, diagnosis and treatment/purchase in medical data to be detected
The medicine frequency, diagnosis and treatment item and drug amount of money etc. and corresponding medicament categories in diagnosis and treatment specification, diagnosis and treatment item, the diagnosis and treatment/purchase medicine frequency,
Diagnosis and treatment item and the drug amount of money etc. are compared, if having any different, it is abnormal to determine that medical data to be detected exists.
The medical data to be detected is carried out abnormal mark if the medical data to be detected has exception by step S52
Note.
It should be noted that in Fig. 3, step S40 is also step S52 because step S52 is identical as step S40.
If medical data to be detected has exception, medical data to be detected is subjected to abnormal marking, optionally, output
Abnormality detection result, to notify user verify under line.It, will in the revision directive inputted after being verified under detecting user's line
The detecting state of the medical data to be detected of the insured people is changed to normally, and using the medical data to be detected of the insured people as having
Effect historical record is added in historical data base.There may be individuals patients special circumstances really, need to violate it is general just
Normal diagnosis and treatment specification is treated, perhaps because other cause specifics cause medical insurance swipe the card exception or because uncollected diagnosis tie
The change of diagnosis and treatment scheme caused by fruit, personnel are verifying actual conditions under line, it is believed that there is no when abnormal swipe the card, can correct inspection
Survey result.
If there is no exceptions for the medical data to be detected, normal medical data to be detected be remembered as effective history
Record.
The present embodiment by historical data base be not present the insured people of target effective historical record when, according to be detected
Medical data inquires diagnosis and treatment normative database, obtains the corresponding diagnosis and treatment specification of the medical data to be detected, is advised based on the diagnosis and treatment
Model judges the medical data to be detected with the presence or absence of abnormal, to realize the abnormality detection to insured people brushing card data for the first time.
Further, such as Fig. 4, in medical data method for detecting abnormality 3rd embodiment of the present invention, in the step S30
Based on effective historical record of the insured people of the target, judge that the medical data to be detected is wrapped with the presence or absence of the step for exception
It includes:
Step S31 obtains default first analysis indexes, according to effective historical record of the insured people of the target, obtains each
The default corresponding historical data of first analysis indexes and error threshold；
Medical data to be detected and effective historical record/diagnosis and treatment specification are carried out to the comparison of default first analysis indexes, with
It realizes and the exception of medical data to be detected is judged.Default first analysis indexes, it may include: type (diagnosis and treatment item type/drug
Type), the time (diagnosis and treatment item time/purchase medicine time), the frequency (the diagnosis and treatment item frequency/medication frequency), the amount of money (diagnosis and treatment item gold
Volume/drug the amount of money), default first analysis indexes may also include diagnostic result etc., and the present embodiment is not to default first analysis indexes
It is limited, default first analysis indexes can be arranged by system default, can also be customized by the user and set before abnormality detection
It sets, default first analysis indexes can be directly stored in preset address, directly obtain from the preset address.
Each default corresponding historical data of first analysis indexes, for example, medicament categories are aspirin, purchase the medicine time
For month No.1 to No. five, the medication frequency is every two months primary, and the drug amount of money is 200 primary, wherein medicament categories/purchase medicine
Time/medication the frequency/drug amount of money is default first analysis indexes, " aspirin ", " No.1 is to No. five ", " every two months one
It is secondary ", " 200 " be each default corresponding historical data of first analysis indexes.
Because an insured people may have multiple history to swipe the card record, record of swiping the card each time can all form one and effectively go through
Records of the Historian record, in every effective historical record each default corresponding historical data of first analysis indexes may some distinguish, then can obtain
The average value for taking all effective historical records is used as the default corresponding historical data of first analysis indexes each in the present embodiment
It is compared in medical data to be detected, to carry out abnormal judgement.Optionally, determining medical data to be detected, there is no abnormal
When, after medical data to be detected is carried out data normalization processing, it is stored in historical data base with preset data structure,
When detection device calculates corresponding mean value to each pre-set level, quick obtaining and operation directly are carried out to the data of structuring.
Because the different patient's actual conditions for suffering from same disease are different, required diagnosis and treatment item, consultation time, charges for drug with
Frequency etc. also has subtle difference, for example, disease A, the frequency for the B categories of drugs eaten is 10 ± 3 times/month, that is, suffers from the people of A disease, eat B
The frequency of categories of drugs is all normal in 10 ± 3 times/month.Therefore, each default first analysis indexes have corresponding error threshold
Value can reduce erroneous judgement, improve the flexibility judged extremely because considering this reasonable otherness.
Step S32 extracts each default corresponding current data of first analysis indexes from the medical data to be detected, will
Each default corresponding current data of first analysis indexes is compared with corresponding historical data, is obtained each default first analysis and is referred to
Mark corresponding difference；
Medical data to be detected is analyzed, each default corresponding current data of first analysis indexes is obtained, by each default first
The corresponding current data of analysis indexes is compared with corresponding historical data, in the data of all default first analysis indexes
In, some are numerical value, can directly carry out numerical value and relatively obtain a numerical difference, such as: the time is (when diagnosis and treatment item time/purchase medicine
Between), the frequency (the diagnosis and treatment item frequency/medication frequency), the amount of money (the diagnosis and treatment item amount of money/drug amount of money).All first point default
In the data for analysing index, also some are not numerical value, such as type (diagnosis and treatment item type/medicament categories), this default first analysis
Numerical difference can not be directly obtained after index comparison, then can calculate the similarity for obtaining the two, corresponding difference is obtained based on similarity
Value.
Step S33 judges whether there is default first analysis indexes that corresponding difference is greater than corresponding error threshold；
Each default corresponding current data of first analysis indexes is compared with corresponding historical data, is obtained each default
The corresponding difference of first analysis indexes, if each default corresponding difference of first analysis indexes is less than the error threshold, then to
Detection medical data belongs to normal error range, i.e., there is no exceptions for medical data to be detected, if each default first analysis
The corresponding difference of index is greater than the error threshold, then medical data to be detected is not belonging to normal error range.
Step S34 corresponds to default first analysis indexes that difference is greater than corresponding error threshold if it exists, then determine it is described to
It detects medical data and there is exception.
In medical data to be detected in each default corresponding current data of first analysis indexes, as long as one first point default
It analyses the corresponding difference of index and is greater than corresponding error threshold, it is abnormal just to illustrate that medical data to be detected exists.
The present embodiment obtains default first analysis indexes, according to effective historical record of the insured people of the target, obtains each
The default corresponding historical data of first analysis indexes and error threshold；Each default first is extracted from the medical data to be detected
The corresponding current data of analysis indexes carries out each default corresponding current data of first analysis indexes with corresponding historical data
Comparison obtains each default corresponding difference of first analysis indexes；It judges whether there is corresponding difference and is greater than corresponding error threshold
Default first analysis indexes；Default first analysis indexes that difference is greater than corresponding error threshold are corresponded to if it exists, then described in judgement
There is exception in medical data to be detected, as long as because a default corresponding difference of first analysis indexes is greater than corresponding error threshold,
It is abnormal to decide that medical data to be detected exists, more suspicious data can be obtained, avoid missing abnormal data.
Further, in medical data method for detecting abnormality fourth embodiment of the present invention, institute is based in the step S30
The effective historical record for stating the insured people of target judges that the medical data to be detected includes: with the presence or absence of the step for exception
Step S35 obtains default second analysis indexes and each default corresponding weight of second analysis indexes, and is based on institute
The effective historical record for stating the insured people of target obtains each default corresponding historical data of second analysis indexes；
Default second analysis indexes, it may include: type (diagnosis and treatment item type/medicament categories), time are (when diagnosis and treatment item
Between/purchase the medicine time), the frequency (the diagnosis and treatment item frequency/medication frequency), the amount of money (the diagnosis and treatment item amount of money/drug amount of money, the present embodiment
In default second analysis indexes can be identical with default first analysis indexes in 3rd embodiment, analyze and refer to default second
When marking identical as default first analysis indexes, associated description is identical as default first analysis indexes, does not repeat, and presets the second analysis
Index can not also be identical with default first analysis indexes.
Default second analysis indexes of difference, corresponding respective weight.Have in medical data to be detected multiple second point default
The data for analysing index have different degrees of influence for abnormal judgement, for example, medication type is general for specific disease
Relatively fixed, the therapeutic effect of drug used has similitude, if purchase medicine type difference is larger, i.e., similitude is lower, then pole
It is likely to be and swipes the card lack of standardizationly, therefore, compared to purchase medicine time, the purchase medicine frequency, purchase medicine type is for the influence that judges extremely
Larger, this default corresponding weight of second analysis indexes of purchase medicine type is larger.
Each default corresponding historical data of second analysis indexes in the present embodiment, refers to and carries out to a plurality of historical medical data
Value obtaining after conformity calculation, for being judged extremely, optionally, determining medical data to be detected, there is no abnormal
When, after medical data to be detected is carried out data normalization processing, it is stored in historical data base with preset data structure,
When detection device calculates corresponding mean value to each pre-set level, quick obtaining and operation directly are carried out to the data of structuring.Example
Such as, for purchasing the medicine time, the purchase medicine date in first historical data is July 3, and the purchase medicine date of Article 2 is August 4th,
The purchase medicine date of Article 3 is September 2nd, then calculating and obtaining the mean value on purchase medicine date is No. 3 monthly, this this i.e. implementation of mean value
Purchase medicine time corresponding historical data in example.
Step S36 extracts each default corresponding current data of second analysis indexes from the medical data to be detected, will
Each default corresponding current data of second analysis indexes is compared with corresponding historical data, is obtained each default second analysis and is referred to
Mark corresponding difference；
Medical data to be detected is analyzed, each default corresponding current data of second analysis indexes is obtained, by each default second
The corresponding current data of analysis indexes is compared with corresponding historical data, in the data of all default second analysis indexes
In, some are numerical value, can directly carry out numerical value and relatively obtain a numerical difference, such as: the time is (when diagnosis and treatment item time/purchase medicine
Between), the frequency (the diagnosis and treatment item frequency/medication frequency), the amount of money (the diagnosis and treatment item amount of money/drug amount of money).All second point default
In the data for analysing index, also some are not numerical value, such as type (diagnosis and treatment item type/medicament categories), this default second analysis
Numerical difference can not be directly obtained after index comparison, then can calculate the similarity for obtaining the two, corresponding difference is obtained based on similarity
Value.
Step S37 calculates the medical data to be detected based on each default corresponding difference of second analysis indexes and weight
Corresponding weighted average error value；
The sum of products of each default second analysis indexes corresponding difference and weight, medical data as to be detected are corresponding
Weighted average error value.
The weighted average error value and preset reasonable error threshold value are compared, judge the weighting by step S38
Whether average error value is greater than reasonable error threshold value；
In one embodiment, different diseases correspond to different reasonable error threshold values.Reasonable error threshold value, can be used big data
Technical treatment medical data sample obtains, and specifically, calculates the mean value of medical data sample, and obtain all medical data samples
With the error amount of mean value, the corresponding error threshold of each medical data sample is calculated based on the error amount, is based on each medical data sample
This corresponding error threshold calculates the mean error threshold value of all medical data samples, which is reasonable error
Threshold value.
Step S39 determines the medical data to be detected if the weighted average error value is greater than reasonable error threshold value
There are exceptions.
If weighted average error value is greater than reasonable error threshold value, illustrating medical data to be detected, there are larger with usual data
Difference, it is likely that there are exceptions, therefore, it is determined that medical data to be detected has exception.
The present embodiment is by calculating the medical treatment to be detected based on each default corresponding difference of second analysis indexes and weight
The corresponding weighted average error value of data；The weighted average error value and preset reasonable error threshold value are compared, sentenced
Whether the weighted average error value of breaking is greater than reasonable error threshold value；If the weighted average error value is greater than reasonable error threshold
Value it is abnormal then to determine that the medical data to be detected exists, because the weighted average error value for judging extremely is all pre-
If the weighted results of the second analysis indexes corresponding difference and weight, the weighted value of only all default second analysis indexes is greater than
Reasonable error threshold value just determines that medical data to be detected is abnormal data, can more accurately interpretation abnormal data, line can be reduced
The data bulk of lower confirmation reduces examination amount under line.
It further, will described in the step S36 in the 5th embodiment of medical data method for detecting abnormality of the present invention
Each default corresponding current data of second analysis indexes is compared with corresponding historical data, is obtained each default second analysis and is referred to
The step of marking corresponding difference include:
Step S40 works as when default second analysis indexes are diagnosis and treatment item index or medicament categories index from described
Current diagnosis and treatment item or current medical type are extracted in preceding data, and history diagnosis and treatment item or history are extracted from the historical data
Medicament categories；
In the data of all default second analysis indexes, some are numerical value, can directly carry out numerical value and relatively obtain one
A numerical difference, such as: time (diagnosis and treatment item time/purchase medicine time), the frequency (the diagnosis and treatment item frequency/medication frequency), the amount of money (diagnosis and treatment
Item amount/drug the amount of money)；In the data of all default second analysis indexes, also some are not numerical value, such as type (diagnosis and treatment
Project kind/medicament categories), numerical difference can not be directly obtained after this default second analysis indexes comparison, therefore, to this pre-
If the second analysis indexes carry out similarity calculation, corresponding difference is obtained based on similarity.
Step S41, calculate the current diagnosis and treatment item and history diagnosis and treatment item similarity or current medical type with go through
The similarity of history medicament categories；
It can first calculate in current diagnosis and treatment item (or medicament categories) and history diagnosis and treatment item (or medicament categories), identical diagnosis and treatment
The quantity of project accounts for the first ratio of diagnosis and treatment item total quantity, and diagnosis and treatment item total quantity here refers to current diagnosis and treatment item and history
The sum of diagnosis and treatment item, in one embodiment, the similarity in the first ratio i.e. embodiment；In another embodiment, acquisition is worked as
Preceding diagnosis and treatment item (or medicament categories) and identical and similar diagnosis and treatment item in history diagnosis and treatment item (or medicament categories) calculate phase
The second ratio of diagnosis and treatment item total quantity is accounted for the quantity with similar diagnosis and treatment item, it is similar in the second ratio i.e. embodiment
Degree.
Step S42, based on diagnosis and treatment item index or the corresponding difference of medicament categories index described in the similarity calculation.
Similarity is higher, and difference is smaller, it may be assumed that similarity and difference negative correlation, negative correlation coefficient can be by user
It is obtained by calculating, big data processing analysis can also be based on by system and is obtained.
The present embodiment is by when default second analysis indexes are diagnosis and treatment item index or medicament categories index, from institute
State and extract current diagnosis and treatment item or current medical type in current data, from the historical data extract history diagnosis and treatment item or
History medicament categories；Calculate the similarity or current medical type and history medicine of the current diagnosis and treatment item and history diagnosis and treatment item
The similarity of species；It, can based on diagnosis and treatment item index described in the similarity calculation or the corresponding difference of medicament categories index
The default second analysis indexes progress similarity calculation of acquisition numerical difference is calculated to can not directly carry out numerical value, and then is guaranteed subsequent
It smoothly calculates and obtains weighted average error value or diagnosis and treatment item index or the corresponding difference of medicament categories index, to carry out exception
Judgement.
Optionally, step S41, example scheme described in S42 is applicable to 3rd embodiment, default second analysis therein
Index can be replaced default first analysis indexes.
In addition, the present invention also provides a kind of medical data corresponding with above-mentioned each step of medical data method for detecting abnormality is different
Normal detection device.
It is the functional block diagram of medical data abnormal detector first embodiment of the present invention referring to Fig. 5, Fig. 5.
In the present embodiment, medical data abnormal detector of the present invention includes:
Module 10 is obtained, for it is corresponding to be detected to obtain abnormality detection request when detecting abnormality detection request
Medical data；
Historical query module 20 whether there is the corresponding mesh of the medical data to be detected for judging in historical data base
Mark effective historical record of insured people；
Abnormal judgment module 30, if for there are the corresponding target of the medical data to be detected is insured in historical data base
Effective historical record of people, then effective historical record based on the insured people of the target judge that the medical data to be detected is
It is no to there is exception；
Abnormal marking module 40, if there is exception for the medical data to be detected, by the medical number to be detected
According to progress abnormal marking.
Further, the medical data abnormal detector further include:
Specification obtains module, if insured for the corresponding target of the medical data to be detected to be not present in historical data base
Effective historical record of people then inquires diagnosis and treatment normative database according to the medical data to be detected, obtains the doctor to be detected
Treat the corresponding diagnosis and treatment specification of data；
First abnormal judgment module judges the medical data to be detected with the presence or absence of different for being based on the diagnosis and treatment specification
Often；
The abnormal marking module 40 will be described to be detected if being also used to the medical data to be detected has exception
Medical data carries out abnormal marking.
Further, the medical data abnormal detector further include:
Data update module, if there is no exceptions for the medical data to be detected, by the medical number to be detected
It is added to historical data base according to as effective historical record.
Further, the medical data abnormal detector further include:
First obtains module, for obtaining default first analysis indexes, is remembered according to effective history of the insured people of the target
Record obtains each default corresponding historical data of first analysis indexes and error threshold；
Second obtains module, and for extracting from the medical data to be detected, each default first analysis indexes are corresponding works as
Each default corresponding current data of first analysis indexes is compared with corresponding historical data, is obtained each default by preceding data
The corresponding difference of first analysis indexes；
First judgment module, default first analysis that corresponding error threshold is greater than for judging whether there is corresponding difference refer to
Mark；
Second abnormal judgment module, default first analysis that corresponding error threshold is greater than for corresponding to difference if it exists refer to
It is abnormal then to determine that the medical data to be detected exists for mark.
Further, the medical data abnormal detector further include:
Third obtains module, for obtaining default second analysis indexes and each default corresponding power of second analysis indexes
Weight, and effective historical record based on the insured people of the target obtain each default corresponding historical data of second analysis indexes；
4th obtains module, and for extracting from the medical data to be detected, each default second analysis indexes are corresponding works as
Each default corresponding current data of second analysis indexes is compared with corresponding historical data, is obtained each default by preceding data
The corresponding difference of second analysis indexes；
First computing module, for calculating described to be checked based on each default corresponding difference of second analysis indexes and weight
Survey the corresponding weighted average error value of medical data；
Second judgment module is sentenced for comparing the weighted average error value and preset reasonable error threshold value
Whether the weighted average error value of breaking is greater than reasonable error threshold value；
Third exception judgment module, if for the weighted average error value be greater than reasonable error threshold value, determine described in
Medical data to be detected exists abnormal.
Further, the medical data abnormal detector further include:
Extraction module is used for when default second analysis indexes are diagnosis and treatment item index or medicament categories index, from
Current diagnosis and treatment item or current medical type are extracted in the current data, and history diagnosis and treatment item is extracted from the historical data
Or history medicament categories；
Second computing module, for calculating the similarity or current medical of the current diagnosis and treatment item Yu history diagnosis and treatment item
The similarity of type and history medicament categories；Based on diagnosis and treatment item index described in the similarity calculation or medicament categories index pair
The difference answered.
Further, the medical data abnormal detector further include:
Third judgment module, if for there are the corresponding insured people of target of the medical data to be detected in historical data base
Effective historical record, obtain effective historical record quantity of the insured people of the target；
4th abnormal judgment module is based on the mesh if being greater than preset threshold for effective historical record quantity
The effective historical record for marking insured people judges the medical data to be detected with the presence or absence of abnormal；
5th abnormal judgment module, if effective historical record quantity is less than preset threshold, according to described to be detected
Medical data inquires diagnosis and treatment normative database, obtains the corresponding diagnosis and treatment specification of the medical data to be detected；It is advised based on the diagnosis and treatment
Model judges the medical data to be detected with the presence or absence of abnormal.
The present invention also proposes a kind of storage medium, is stored thereon with computer program.The storage medium can be Fig. 1's
Memory 20 in medical data abnormality detecting apparatus, be also possible to as ROM (Read-Only Memory, read-only memory)/
At least one of RAM (Random Access Memory, random access memory), magnetic disk, CD, the storage medium packet
Some instructions are included to use so that the equipment equipment with processor (can be mobile phone, computer, server, the network equipment
Or medical data abnormality detecting apparatus in the embodiment of the present invention etc.) execute method described in each embodiment of the present invention.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the server-side 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 for this process, method, article or server-side institute
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wrapping
Include in process, method, article or the server-side of the element that there is also other identical elements.
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.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of medical data method for detecting abnormality, which is characterized in that the medical data method for detecting abnormality includes following step
It is rapid:
When detecting abnormality detection request, obtains the abnormality detection and request corresponding medical data to be detected；
Judge the effective historical record that whether there is the corresponding insured people of target of the medical data to be detected in historical data base；
If being based in historical data base there are effective historical record of the corresponding insured people of target of the medical data to be detected
Effective historical record of the insured people of target judges the medical data to be detected with the presence or absence of abnormal；
If the medical data to be detected has exception, the medical data to be detected is subjected to abnormal marking.
2. medical data method for detecting abnormality as described in claim 1, which is characterized in that be in the judgement historical data base
Include: after no the step of there are effective historical records of the corresponding insured people of target of the medical data to be detected
If effective historical record of the corresponding insured people of target of the medical data to be detected, root are not present in historical data base
Diagnosis and treatment normative database is inquired according to the medical data to be detected, obtains the corresponding diagnosis and treatment specification of the medical data to be detected；
Based on the diagnosis and treatment specification, judge the medical data to be detected with the presence or absence of abnormal；
If the medical data to be detected has exception, the medical data to be detected is subjected to abnormal marking.
3. medical data method for detecting abnormality as claimed in claim 1 or 2, which is characterized in that the judgement is described to be detected
Medical data whether there is abnormal step
If the medical data to be detected is added there is no exception using the medical data to be detected as effective historical record
To historical data base.
4. medical data method for detecting abnormality as described in claim 1, which is characterized in that described to be based on the insured people of the target
Effective historical record, judge that the medical data to be detected includes: with the presence or absence of abnormal step
Default first analysis indexes are obtained, according to effective historical record of the insured people of the target, obtain each default first analysis
The corresponding historical data of index and error threshold；
Each default corresponding current data of first analysis indexes is extracted from the medical data to be detected, it will be each first point default
The corresponding current data of analysis index is compared with corresponding historical data, obtains each default corresponding difference of first analysis indexes
Value；
Judge whether there is default first analysis indexes that corresponding difference is greater than corresponding error threshold；
Default first analysis indexes that difference is greater than corresponding error threshold are corresponded to if it exists, then determine the medical data to be detected
There are exceptions.
5. medical data method for detecting abnormality as described in claim 1, which is characterized in that described to be based on the insured people of the target
Effective historical record, judge that the medical data to be detected includes: with the presence or absence of abnormal step
Default second analysis indexes and each default corresponding weight of second analysis indexes are obtained, and is based on the insured people of the target
Effective historical record, obtain each default corresponding historical data of second analysis indexes；
Each default corresponding current data of second analysis indexes is extracted from the medical data to be detected, it will be each second point default
The corresponding current data of analysis index is compared with corresponding historical data, obtains each default corresponding difference of second analysis indexes
Value；
Based on each default corresponding difference of second analysis indexes and weight, it is flat to calculate the corresponding weighting of the medical data to be detected
Equal error amount；
The weighted average error value and preset reasonable error threshold value are compared, judge that the weighted average error value is
It is no to be greater than reasonable error threshold value；
If the weighted average error value is greater than reasonable error threshold value, it is abnormal to determine that the medical data to be detected exists.
6. medical data method for detecting abnormality as claimed in claim 5, which is characterized in that described to refer to each default second analysis
It marks corresponding current data to compare with corresponding historical data, obtains the step of each default corresponding difference of second analysis indexes
Suddenly include:
When default second analysis indexes are diagnosis and treatment item index or medicament categories index, extracted from the current data
Current diagnosis and treatment item or current medical type, extract history diagnosis and treatment item or history medicament categories from the historical data；
Calculate the similarity or current medical type and history medicament categories of the current diagnosis and treatment item and history diagnosis and treatment item
Similarity；
Based on diagnosis and treatment item index described in the similarity calculation or the corresponding difference of medicament categories index.
7. medical data method for detecting abnormality as claimed in claim 1 or 2, which is characterized in that if in the historical data base
There are effective historical record of the corresponding insured people of target of the medical data to be detected, then having based on the insured people of the target
Historical record is imitated, judges that the medical data to be detected includes: with the presence or absence of abnormal step
If there are effective historical records of the corresponding insured people of target of the medical data to be detected in historical data base, institute is obtained
State effective historical record quantity of the insured people of target；
Sentenced if effective historical record quantity is greater than preset threshold based on effective historical record of the insured people of the target
The medical data to be detected that breaks is with the presence or absence of abnormal；
If effective historical record quantity is less than preset threshold, diagnosis and treatment specification number is inquired according to the medical data to be detected
According to library, the corresponding diagnosis and treatment specification of the medical data to be detected is obtained；Based on the diagnosis and treatment specification, the medical number to be detected is judged
According to the presence or absence of abnormal.
8. a kind of medical data abnormal detector, which is characterized in that the medical data abnormal detector includes:
Module is obtained, for when detecting abnormality detection request, obtaining the corresponding medical number to be detected of abnormality detection request
According to；
Historical query module, it is insured with the presence or absence of the corresponding target of the medical data to be detected in historical data base for judging
Effective historical record of people；
Abnormal judgment module, if for having there are the corresponding insured people of target of medical data to be detected in historical data base
Historical record is imitated, then effective historical record based on the insured people of the target judges that the medical data to be detected whether there is
It is abnormal；
Abnormal marking module carries out the medical data to be detected if there is exception for the medical data to be detected
Abnormal marking.
9. a kind of medical data abnormality detecting apparatus, which is characterized in that the medical data abnormality detecting apparatus include processor,
Memory and it is stored in the medical data abnormality detecting program that can be executed on the memory and by the processor, wherein
When the medical data abnormality detecting program is executed by the processor, the doctor as described in any one of claims 1 to 7 is realized
The step for the treatment of data exception detection method.
10. a kind of storage medium, which is characterized in that medical data abnormality detecting program is stored on the storage medium, wherein
When the medical data abnormality detecting program is executed by processor, the medical number as described in any one of claims 1 to 7 is realized
The step of according to method for detecting abnormality.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811226395.1A CN109636623A (en) | 2018-10-19 | 2018-10-19 | Medical data method for detecting abnormality, device, equipment and storage medium |
| PCT/CN2019/095406 WO2020078053A1 (en) | 2018-10-19 | 2019-07-10 | Medical data anomaly detection method, apparatus, and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811226395.1A CN109636623A (en) | 2018-10-19 | 2018-10-19 | Medical data method for detecting abnormality, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109636623A true CN109636623A (en) | 2019-04-16 |
Family
ID=66066515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811226395.1A Pending CN109636623A (en) | 2018-10-19 | 2018-10-19 | Medical data method for detecting abnormality, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109636623A (en) |
| WO (1) | WO2020078053A1 (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459276A (en) * | 2019-08-15 | 2019-11-15 | 北京嘉和海森健康科技有限公司 | A kind of data processing method and relevant device |
| CN110688406A (en) * | 2019-09-06 | 2020-01-14 | 平安医疗健康管理股份有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN110781222A (en) * | 2019-10-14 | 2020-02-11 | 平安医疗健康管理股份有限公司 | Abnormal medical insurance application detection method and device, computer equipment and storage medium |
| CN111028089A (en) * | 2019-11-25 | 2020-04-17 | 泰康保险集团股份有限公司 | Abnormal operation identification method and device, computer storage medium and electronic equipment |
| WO2020078053A1 (en) * | 2018-10-19 | 2020-04-23 | 平安医疗健康管理股份有限公司 | Medical data anomaly detection method, apparatus, and device, and storage medium |
| CN111538311A (en) * | 2020-04-22 | 2020-08-14 | 北京航空航天大学 | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining |
| CN111612647A (en) * | 2020-05-14 | 2020-09-01 | 深圳旦倍科技有限公司 | Method and device for detecting abnormal data of meter, meter and readable storage medium |
| CN112036749A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying risk user based on medical data and computer equipment |
| CN112365987A (en) * | 2020-10-27 | 2021-02-12 | 平安科技（深圳）有限公司 | Diagnostic data anomaly detection method and device, computer equipment and storage medium |
| CN112445846A (en) * | 2020-12-01 | 2021-03-05 | 平安医疗健康管理股份有限公司 | Medical item identification method, device, equipment and computer readable storage medium |
| CN113049935A (en) * | 2021-03-04 | 2021-06-29 | 长鑫存储技术有限公司 | Semiconductor intelligent detection system, intelligent detection method and storage medium |
| CN113130053A (en) * | 2021-03-24 | 2021-07-16 | 大光惠世医疗科技有限公司 | Self-service registration method and device based on user activity data |
| CN113506577A (en) * | 2021-06-25 | 2021-10-15 | 贵州电网有限责任公司 | Method for perfecting voiceprint library based on incremental acquisition of telephone recording |
| CN113761340A (en) * | 2021-01-15 | 2021-12-07 | 北京京东拓先科技有限公司 | Information recommendation method and device, electronic equipment and computer readable medium |
| CN113780792A (en) * | 2021-09-03 | 2021-12-10 | 广州云从鼎望科技有限公司 | Medical insurance violation monitoring method and device and computer readable storage medium |
| WO2022082908A1 (en) * | 2020-10-19 | 2022-04-28 | 浙江大学山东工业技术研究院 | Two-stage-screening-process-based method and apparatus for detecting abnormal medicine purchase of medical insurance |
| CN114612887A (en) * | 2021-09-01 | 2022-06-10 | 腾讯科技（深圳）有限公司 | Bill abnormity detection method, device, equipment and computer readable storage medium |
| CN114757792A (en) * | 2022-06-15 | 2022-07-15 | 南京云联数科科技有限公司 | Medical insurance wind control management method and equipment based on multi-field data |
| CN115329905A (en) * | 2022-10-13 | 2022-11-11 | 湖南鼎誉检验检测股份有限公司 | Food detection method, system and storage medium |
| WO2024082780A1 (en) * | 2022-10-18 | 2024-04-25 | 华为云计算技术有限公司 | Data query method, and related apparatus |
Citations (10)
| 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 |
| CN104182824A (en) * | 2014-08-08 | 2014-12-03 | 平安养老保险股份有限公司 | Rule checking system and rule checking method for recognizing medical insurance reimbursement violations |
| CN106447500A (en) * | 2016-11-09 | 2017-02-22 | 北京好运到信息科技有限公司 | Method for scoring according to matching degree of diseases and drugs and system of scoring method |
| CN107133438A (en) * | 2017-03-03 | 2017-09-05 | 平安医疗健康管理股份有限公司 | Medical act monitoring method and device |
| CN107133437A (en) * | 2017-03-03 | 2017-09-05 | 平安医疗健康管理股份有限公司 | The method and device that monitoring medicine is used |
| CN107451401A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical insurance intelligent checks method and system |
| CN107451400A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical act monitoring method and system |
| WO2018010105A1 (en) * | 2016-07-12 | 2018-01-18 | 曹庆恒 | System for analyzing data characteristics of prescribed drug usage reasonableness |
| 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 |
| CN107871285A (en) * | 2017-12-06 | 2018-04-03 | 和金在线（北京）科技有限公司 | A kind of health insurance pays for the method for detecting and system of fraud and abuse |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833039A (en) * | 2017-02-13 | 2018-03-23 | 平安医疗健康管理股份有限公司 | Medical care cost method and system |
| CN108492196B (en) * | 2018-03-08 | 2020-11-10 | 平安医疗健康管理股份有限公司 | Wind control method for deducing medical insurance violation behavior through data analysis |
| CN109636623A (en) * | 2018-10-19 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Medical data method for detecting abnormality, device, equipment and storage medium |
-
2018
- 2018-10-19 CN CN201811226395.1A patent/CN109636623A/en active Pending
-
2019
- 2019-07-10 WO PCT/CN2019/095406 patent/WO2020078053A1/en active Application Filing
Patent Citations (10)
| 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 |
| CN104182824A (en) * | 2014-08-08 | 2014-12-03 | 平安养老保险股份有限公司 | Rule checking system and rule checking method for recognizing medical insurance reimbursement violations |
| WO2018010105A1 (en) * | 2016-07-12 | 2018-01-18 | 曹庆恒 | System for analyzing data characteristics of prescribed drug usage reasonableness |
| CN106447500A (en) * | 2016-11-09 | 2017-02-22 | 北京好运到信息科技有限公司 | Method for scoring according to matching degree of diseases and drugs and system of scoring method |
| CN107133438A (en) * | 2017-03-03 | 2017-09-05 | 平安医疗健康管理股份有限公司 | Medical act monitoring method and device |
| CN107133437A (en) * | 2017-03-03 | 2017-09-05 | 平安医疗健康管理股份有限公司 | The method and device that monitoring medicine is used |
| CN107451401A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical insurance intelligent checks method and system |
| CN107451400A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical act monitoring method and system |
| 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 |
| CN107871285A (en) * | 2017-12-06 | 2018-04-03 | 和金在线（北京）科技有限公司 | A kind of health insurance pays for the method for detecting and system of fraud and abuse |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020078053A1 (en) * | 2018-10-19 | 2020-04-23 | 平安医疗健康管理股份有限公司 | Medical data anomaly detection method, apparatus, and device, and storage medium |
| CN110459276A (en) * | 2019-08-15 | 2019-11-15 | 北京嘉和海森健康科技有限公司 | A kind of data processing method and relevant device |
| CN110459276B (en) * | 2019-08-15 | 2022-05-24 | 北京嘉和海森健康科技有限公司 | Data processing method and related equipment |
| CN110688406A (en) * | 2019-09-06 | 2020-01-14 | 平安医疗健康管理股份有限公司 | Data processing method, data processing device, computer equipment and storage medium |
| CN110781222A (en) * | 2019-10-14 | 2020-02-11 | 平安医疗健康管理股份有限公司 | Abnormal medical insurance application detection method and device, computer equipment and storage medium |
| CN111028089A (en) * | 2019-11-25 | 2020-04-17 | 泰康保险集团股份有限公司 | Abnormal operation identification method and device, computer storage medium and electronic equipment |
| CN111538311A (en) * | 2020-04-22 | 2020-08-14 | 北京航空航天大学 | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining |
| CN111612647A (en) * | 2020-05-14 | 2020-09-01 | 深圳旦倍科技有限公司 | Method and device for detecting abnormal data of meter, meter and readable storage medium |
| CN111612647B (en) * | 2020-05-14 | 2023-05-23 | 深圳旦倍科技有限公司 | Meter abnormal data detection method, device, meter and readable storage medium |
| CN112036749A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying risk user based on medical data and computer equipment |
| WO2022082908A1 (en) * | 2020-10-19 | 2022-04-28 | 浙江大学山东工业技术研究院 | Two-stage-screening-process-based method and apparatus for detecting abnormal medicine purchase of medical insurance |
| WO2021180242A1 (en) * | 2020-10-27 | 2021-09-16 | 平安科技（深圳）有限公司 | Method and apparatus for detecting anomaly in diagnostic data, and computer device and storage medium |
| CN112365987B (en) * | 2020-10-27 | 2023-06-06 | 平安科技（深圳）有限公司 | Diagnostic data abnormality detection method, diagnostic data abnormality detection device, computer device, and storage medium |
| CN112365987A (en) * | 2020-10-27 | 2021-02-12 | 平安科技（深圳）有限公司 | Diagnostic data anomaly detection method and device, computer equipment and storage medium |
| CN112445846A (en) * | 2020-12-01 | 2021-03-05 | 平安医疗健康管理股份有限公司 | Medical item identification method, device, equipment and computer readable storage medium |
| CN113761340A (en) * | 2021-01-15 | 2021-12-07 | 北京京东拓先科技有限公司 | Information recommendation method and device, electronic equipment and computer readable medium |
| CN113049935A (en) * | 2021-03-04 | 2021-06-29 | 长鑫存储技术有限公司 | Semiconductor intelligent detection system, intelligent detection method and storage medium |
| CN113130053A (en) * | 2021-03-24 | 2021-07-16 | 大光惠世医疗科技有限公司 | Self-service registration method and device based on user activity data |
| CN113506577A (en) * | 2021-06-25 | 2021-10-15 | 贵州电网有限责任公司 | Method for perfecting voiceprint library based on incremental acquisition of telephone recording |
| CN114612887B (en) * | 2021-09-01 | 2023-01-10 | 腾讯科技（深圳）有限公司 | Bill abnormity detection method, device, equipment and computer readable storage medium |
| CN114612887A (en) * | 2021-09-01 | 2022-06-10 | 腾讯科技（深圳）有限公司 | Bill abnormity detection method, device, equipment and computer readable storage medium |
| CN113780792A (en) * | 2021-09-03 | 2021-12-10 | 广州云从鼎望科技有限公司 | Medical insurance violation monitoring method and device and computer readable storage medium |
| CN114757792A (en) * | 2022-06-15 | 2022-07-15 | 南京云联数科科技有限公司 | Medical insurance wind control management method and equipment based on multi-field data |
| CN115329905B (en) * | 2022-10-13 | 2022-12-09 | 湖南鼎誉检验检测股份有限公司 | Food detection method, system and storage medium |
| CN115329905A (en) * | 2022-10-13 | 2022-11-11 | 湖南鼎誉检验检测股份有限公司 | Food detection method, system and storage medium |
| WO2024082780A1 (en) * | 2022-10-18 | 2024-04-25 | 华为云计算技术有限公司 | Data query method, and related apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020078053A1 (en) | 2020-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636623A (en) | Medical data method for detecting abnormality, device, equipment and storage medium | |
| US11152089B2 (en) | Medical scan hierarchical labeling system | |
| KR102088980B1 (en) | System and Method for Providing personalized hospital information | |
| Saulle et al. | Supervised dosing with a long‐acting opioid medication in the management of opioid dependence | |
| Sperber et al. | An upper and lower bound of the medication possession ratio | |
| CN109636613A (en) | Medical data abnormality recognition method, device, terminal and storage medium | |
| Kea et al. | Interpreting the national hospital ambulatory medical care survey: United States emergency department opioid prescribing, 2006–2010 | |
| US7814035B2 (en) | Large-scale information collection and mining | |
| US20090062623A1 (en) | Identifying possible medical conditions of a patient | |
| KR101723382B1 (en) | Smart healthcare system and method for providing social network service of sustaainable healthcare | |
| CN109416820A (en) | User satisfaction is automatically determined and is responded | |
| Nichols et al. | Community-based delivery of HIV treatment in Zambia: costs and outcomes | |
| CN105260588A (en) | Health protection robot system and data processing method thereof | |
| CN109461482A (en) | Health plan generation method, device, computer equipment and storage medium | |
| Watson et al. | Cost-effectiveness of pembrolizumab plus axitinib vs nivolumab plus ipilimumab as first-line treatment of advanced renal cell carcinoma in the US | |
| CN113994436A (en) | System and method for healthcare providers to treat patients using multiple N-of-1 micro-therapies | |
| CN109598302B (en) | Method, device and equipment for predicting treatment cost and computer readable storage medium | |
| US20220293256A1 (en) | Machine learning analysis of databases | |
| CN109767067A (en) | Method and Related product based on more evaluative dimensions evaluation hospital | |
| US20220005565A1 (en) | System with retroactive discrepancy flagging and methods for use therewith | |
| US20100088111A1 (en) | System and method for obtaining, processing and evaluating individual blood type and ayurvedic core constitution (prakruti) to construct a personalized health risk assessment report | |
| Lamers-Johnson et al. | Academy of nutrition and dietetics nutrition research network: validation of a novel nutrition informatics tool to assess agreement between documented nutrition care and evidence-based recommendations | |
| US8818825B1 (en) | Patient authentication fraud prevention system and method | |
| Tannery et al. | Impact and user satisfaction of a clinical information portal embedded in an electronic health record | |
| KR102437462B1 (en) | Method, server and program for providing medical data brokerage services based on AI |
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 |