CN109545317A - The method and Related product of behavior in hospital are determined based on prediction model in hospital - Google Patents
The method and Related product of behavior in hospital are determined based on prediction model in hospital Download PDFInfo
- Publication number
- CN109545317A CN109545317A CN201811276180.0A CN201811276180A CN109545317A CN 109545317 A CN109545317 A CN 109545317A CN 201811276180 A CN201811276180 A CN 201811276180A CN 109545317 A CN109545317 A CN 109545317A
- Authority
- CN
- China
- Prior art keywords
- data
- hospitalized
- drug
- default
- insured people
- 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
- 238000000034 method Methods 0.000 title claims abstract description 73
- 239000003814 drug Substances 0.000 claims description 274
- 229940079593 drug Drugs 0.000 claims description 265
- 230000006399 behavior Effects 0.000 claims description 70
- 201000010099 disease Diseases 0.000 claims description 51
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 51
- 238000012360 testing method Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 description 27
- 238000010586 diagram Methods 0.000 description 9
- 238000012795 verification Methods 0.000 description 7
- 238000013439 planning Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000008280 blood Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 210000000214 mouth Anatomy 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012797 qualification Methods 0.000 description 3
- 238000001356 surgical procedure Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 238000002562 urinalysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000000857 drug effect Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
This application discloses a kind of methods and Related product that behavior in hospital is determined based on prediction model in hospital, this method is applied to electronic equipment, this method comprises: receiving the hospitalization data of the insured people inputted in hospitalization information administration interface, diagnostic data and administration data are included at least in the hospitalization data;The diagnostic data in the hospitalization data is extracted, the diagnostic data is input to prediction model of being hospitalized trained in advance, to obtain the probability of being hospitalized of the insured people;When the probability of being hospitalized meets preset condition, the corresponding default administration data of the diagnostic data is obtained;The administration data and the default administration data are compared, determine whether the behavior of being hospitalized of the insured people is legal.The embodiment of the present application advantageously reduces the probability for extracting medical insurance fund, specification behavior in hospital.
Description
Technical field
This application involves field of medical technology, and in particular to a method of behavior of being hospitalized is determined based on prediction model in hospital
And Related product.
Background technique
As national basic medical insurance system is constantly reinforced, medical insurance ranks are added in more and more people, when insured people goes to a doctor, doctor
The medical expense that risk-pooling fund can be big absolutely for insured people reimbursement is protected, but current medical insurance system is still incomplete, causes to report
There are many benefits programs during pin.In many cities, it is not included in the reimbursement scope of medical insurance risk-pooling fund to physical examination project, joins
The physical examination expense of guarantor personal can only be submitted an expense account.It, can as long as hospitalization cost, which has met, pays the conditions such as line but for insured people
Partially or completely hospitalization cost is submitted an expense account using medical insurance risk-pooling fund.Therefore the insured people in part may conspire with doctor, insured
In the case that people is without being hospitalized, insured people is taken in into institute, opens and takes additional drug, to increase drug expenditure, increase in hospital
Total cost has reached hospitalization cost and pays line, to extract medical insurance risk-pooling fund reimbursement drug expenditure.Moreover, even will purchase
To drug high price sell, seek exorbitant profit.
Therefore whether the insured people of existing confirmation has that the mode of qualification in hospital is single, accuracy is low, exists and extracts pool base
The behavior of gold payment drug expenditure.Therefore, whether judge insured people in hospital from medication angle in hospital it is urgent to provide one kind has firmly
The method of institute's qualification.
Summary of the invention
The embodiment of the present application provides a kind of method and Related product that behavior in hospital is determined based on prediction model in hospital, with
Phase judges whether the request of being hospitalized of insured people is legal, and medical insurance fund drug purchase is extracted in reduction according to administration data when being hospitalized
Probability.
In a first aspect, the embodiment of the present application provides a kind of method that behavior in hospital is determined based on prediction model in hospital, it is described
Method is applied to electronic equipment, which comprises
The hospitalization data of the insured people inputted in hospitalization information administration interface is received, includes at least and examines in the hospitalization data
Disconnected data and administration data;
The diagnostic data in the hospitalization data is extracted, the diagnostic data is input to trained in advance be hospitalized and is predicted
Model, to obtain the probability of being hospitalized of the insured people;
When the probability of being hospitalized meets preset condition, the corresponding default administration data of the diagnostic data is obtained;
The administration data and the default administration data are compared, determine the insured people be hospitalized behavior whether
It is legal.
Second aspect, the embodiment of the present application provide a kind of electronic equipment that behavior in hospital is determined based on prediction model in hospital,
The electronic equipment includes:
Receiving unit, for receiving the hospitalization data in the insured people of hospitalization information administration interface input, described be hospitalized is counted
Diagnostic data and administration data are included at least in;
The diagnostic data is input to preparatory instruction for extracting the diagnostic data in the hospitalization data by extraction unit
The prediction model of being hospitalized perfected, to obtain the probability of being hospitalized of the insured people;
Acquiring unit, for it is corresponding default to obtain the diagnostic data when the probability of being hospitalized meets preset condition
Administration data;
Determination unit determines the insured people for the administration data and the default administration data to be compared
Be hospitalized behavior it is whether legal.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, including one or more processors, one or more
Memory, one or more transceivers, and one or more programs, one or more of programs are stored in the storage
In device, and it is configured to be executed by one or more of processors, described program includes for executing as described in relation to the first aspect
Method in step instruction.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, and storage is handed over for electronic data
The computer program changed, wherein the computer program makes the method for computer execution as described in relation to the first aspect.
5th aspect, the embodiment of the present application provide a kind of computer program product, and the computer program product includes depositing
The non-transient computer readable storage medium of computer program is stored up, the computer is operable to make computer to execute such as the
Method described in one side.
Implement the embodiment of the present application, has the following beneficial effects:
As can be seen that in the embodiment of the present application, when occurring to be hospitalized behavior, receiving the hospitalization data of input, extracting institute
The diagnostic data in hospitalization data is stated, the probability of being hospitalized of the insured people is predicted according to prediction model of being hospitalized trained in advance,
When probability meets preset condition in hospital, the corresponding default administration data of the diagnostic data is obtained, it will be in the hospitalization data
Administration data and the default administration data compare, to judge whether the administration data in the hospitalization data reasonable, thus
Judge whether the behavior of being hospitalized of the insured people is legal, so judge the behavior of being hospitalized of insured people, from medication angle with judgement
Insured people is with the presence or absence of false behavior of being hospitalized, and is medical system reform to reduce the probability for extracting medical insurance fund drug purchase
Data reference is provided, Medical treatment system is improved.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present application, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is that a kind of process of method that behavior in hospital is determined based on prediction model in hospital provided by the embodiments of the present application is shown
It is intended to;
Fig. 2 is the process of another method that behavior in hospital is determined based on prediction model in hospital provided by the embodiments of the present application
Schematic diagram;
Fig. 3 is the process of another method that behavior in hospital is determined based on prediction model in hospital provided by the embodiments of the present application
Schematic diagram;
Fig. 4 is a kind of knot of electronic equipment that behavior in hospital is determined based on prediction model in hospital provided by the embodiments of the present application
Structure schematic diagram;
Fig. 5 is a kind of function of electronic equipment that behavior in hospital is determined based on prediction model in hospital provided by the embodiments of the present application
It can unit composition block diagram.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall in the protection scope of this application.
The description and claims of this application and term " first ", " second ", " third " and " in the attached drawing
Four " etc. are not use to describe a particular order for distinguishing different objects.In addition, term " includes " and " having " and it
Any deformation, it is intended that cover and non-exclusive include.Such as it contains the process, method of a series of steps or units, be
System, product or equipment are not limited to listed step or unit, but optionally further comprising the step of not listing or list
Member, or optionally further comprising other step or units intrinsic for these process, methods, product or equipment.
Referenced herein " embodiment " is it is meant that the special characteristic, result or the characteristic that describe can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Electronic equipment in the application may include smart phone (such as Android phone, iOS mobile phone, Windows
Phone mobile phone etc.), tablet computer, palm PC, laptop, mobile internet device MID (Mobile Internet
Devices, referred to as: MID) or wearable device etc., above-mentioned electronic equipment is only citing, and non exhaustive, including but not limited to upper
Electronic equipment is stated, for convenience of description, above-mentioned electronic equipment is known as user equipment (UE) (User in following example
Equipment, referred to as: UE).Certainly in practical applications, above-mentioned user equipment is also not necessarily limited to above-mentioned realization form, such as may be used also
To include: intelligent vehicle mounted terminal, computer equipment etc..
Refering to fig. 1, Fig. 1 is a kind of method that behavior in hospital is determined based on prediction model in hospital provided by the embodiments of the present application
Flow diagram, this method be applied to electronic equipment, this method include the content as shown in step S101~S104:
Step S101, the hospitalization data of insured people inputted in hospitalization information administration interface is received, in the hospitalization data
Including at least diagnostic data and administration data.
Wherein, the described diagnostic data includes at least the demography parameter and disease information of insured people, demography parameter
Including height, weight, age, history of disease, schooling, marital status, etc.;Its disease information is specially disease name, disease
Sick menace level, etc.;The administration data specifically includes: drug variety, dosage (i.e. dosage) of every kind of drug, etc..
Optionally, it gets after doctor opens the diagnostic data taken, insured people submits to be hospitalized to medical institutions and request online, institute
It states and requests to be admitted to hospital for requesting the medical institutions to hospitalize the insured people in hospital, after initiating to be hospitalized and requesting, doctor need to be
The input of hospitalization information administration interface is directed to the hospitalization data of the insured people.
Step S102, the diagnostic data in the hospitalization data is extracted, the diagnostic data is input to and is trained in advance
Be hospitalized prediction model, with obtain the insured people be hospitalized probability.
Optionally, keyword recognition is carried out to the hospitalization data, identifies the diagnostic data in the hospitalization data, i.e.,
Disease name, disease menace level, demography parameter, the disease name, disease menace level, demography parameter composition is defeated
Enter data be input to preset it is trained be hospitalized prediction model, obtain the insured people be hospitalized probability.Wherein, by the disease
Title, disease menace level, demography parameter composition input data specifically include: by the disease name, disease menace level,
Demography parameter is configured to initial characteristics matrix, wherein the information matrix that the initial characteristics matrix is non-zero -1, for described first
Non-zero -1 data in beginning eigenmatrix are normalized, i.e., convert number 0 for all elements in the eigenmatrix
Then~1 data matrix carries out permutatation to the data in the data matrix being 0, i.e., by 0 value in the data matrix
Arranged adjacent forms input data matrix in same a line or same row, and the input data matrix is input to the preparatory training
Good prediction model of being hospitalized executes multilayer forward operation, and the corresponding feature of the input data matrix is obtained after global pool
Described eigenvector is input to softmax classifier by vector, and it is corresponding " classification number " to obtain described eigenvector, obtains institute
" classification number " corresponding specific value is stated, the probability of being hospitalized of the insured people is obtained.
Step S103, when the probability of being hospitalized meets preset condition, the corresponding default medication of the diagnostic data is obtained
Data.
Optionally, when the probability of being hospitalized meets preset condition, the corresponding default medication number of the diagnostic data is obtained
According to specifically including: when the probability of being hospitalized is greater than first threshold, determining that the insured people meets the condition of being hospitalized;It is examined described in acquisition
Disease name in disconnected data;It can be obtained by medical knowledge, when needing in hospital as determined, each Hospital Disease can be pre-established and used
The mapping relations of medicine data can determine that the diagnostic data is corresponding pre- according to the mapping relations of disease name and administration data
If administration data, that is, the dosage of required drug variety and every kind of drug when determining the operation of this disease name,
In, the dosage of every kind of drug can determine value for one, or a section, without limitation.
Wherein, the first threshold can be 0.6,0.7,0.8,0.9 or other values.
For example, it as table 1 shows the mapping relations of disease name and default administration data, is reflected according to shown in table 1
The corresponding default administration data of disease name described in Relation acquisition is penetrated to get the corresponding default drug variety collection of the diagnostic data is arrived
And the medication section in table 1 can currently be replaced with fixed dosage by the medication section of every kind of drug.
Table 1
Step S104, the administration data and the default administration data are compared, determine living for the insured people
Whether institute's behavior is legal.
Optionally, the administration data and default administration data comparison are specifically included: by the administration data with
The default administration data is compared in drug variety dimension, alternatively, by the administration data and the default medication number
It is compared according in drug dosage dimension, alternatively, by the administration data and the default administration data in hospitalization cost
It is compared in contribution degree dimension;As determine in drug variety dimension or drug dosage dimension or hospitalization cost contribution
When spending any one dimension exception of dimension, determine that the behavior of being hospitalized of the insured people is illegal.
Narration in detail is in drug variety dimension, drug dosage dimension and hospitalization cost contribution degree dimension separately below
Comparison method.
Optionally, when comparing in drug variety dimension, the drug variety in the administration data is extracted, obtains the use
The drug variety set A of medicine data;The drug variety in the default administration data is extracted, the default administration data is obtained
Default drug variety set B;It is empty set in the intersection C of the drug variety set A and default drug variety set BWhen,
It determines that the drug variety in the hospitalization data of the insured people is unreasonable, determines that the behavior of being hospitalized of the insured people is illegal;?
When the intersection C of the drug variety set A and default drug variety set B is nonvoid set, the drug variety collection is determined
The difference set for closing A and the default drug variety set B, obtains first set D, i.e. D=A-B, determines the default drug variety
The difference set of set B and the drug variety set A, obtain second set E=B-A, such as i-th yuan in the first set D
I-th drug corresponding to element is that presetting for j-th drug corresponding to j-th of element in the second set E is alternative
Drug determines that i-th of element is the alternative element of j-th of element, then obtain in the first set D it is all can
Substitute element determines the total quantity that the other elements except all alternative elements are removed in the first set D, such as institute
Total quantity is stated greater than second threshold, the drug variety excess in the hospitalization data of the insured people is determined, determines the insured people
Be hospitalized behavior it is illegal, wherein i-th of element be the first set D in any one element, described j-th
Element is any one element in the second set E, and described i, j are the integer more than or equal to 1.Above-mentioned preset can
The reasons why substituting drug is: alternative drug may be present for some drugs at the time of surgery, i.e., both drug effect it is identical,
Function is identical, when such as lacking wherein a certain drug in a short time, can open another drug is taken to be used as substitution drug at the time of surgery,
I.e. the two can be used flexibly in medication, therefore, remove the drug variety set and phase in the default drug variety set
Same element and alternative element obtains surplus element, the second threshold as described in being still greater than the total quantity of the surplus element
Value, determine that the drug variety in the drug variety set is excessive, that is, determine insured people when in hospital, open taken it is a large amount of other
The drug unrelated with current procedure determines that the medication of the insured people is unreasonable, therefore exists and extract medical insurance fund payment purchase medicine row
For.
Wherein, the second threshold can be 6,7,9,11,13 or other values.
Certainly, it may be determined that the sum of the other elements except all alternative elements is removed in the first set D
The ratio of amount and the element total quantity in the first set D, such as ratio are greater than fractional threshold, determine the drug variety
Drug variety in set is excessive, that is, determines insured people when in hospital, opens and has taken other a large amount of medicines unrelated with current procedure
Product determine that the medication of the insured people is unreasonable, therefore exist and extract medical insurance fund payment purchase medicine behavior.
Wherein, the fractional threshold can be 05,06,07,08 or other values.
Certainly, when comparing on genre dimension, it may also include following method:
Determine the similarity of the drug variety set Yu the default drug variety set;As the similarity is less than phase
Like degree threshold value, second yuan in the first element total quantity and default drug variety set in the drug variety set is obtained
Plain total quantity, such as the second element total quantity are greater than the first element total quantity, determine the administration data of the insured people
It is unreasonable, it determines the drug variety excess in the hospitalization data of the insured people, determines that the behavior of being hospitalized of the insured people does not conform to
Method.
Wherein,
S is the similarity of the drug variety set and the default drug variety set, and A is the drug variety collection
It closes, B is the default drug variety set, and Card (A ∩ B) is the element number in A ∩ B, and Card (A ∪ B) is in A ∪ B
Element number.
Wherein, the similarity threshold can be 0.5,0.6,0.7,0.8 or other values.
Optionally, when comparing in drug dosage dimension, due to comparing between identical drug, drug medication can be determined
Whether measure reasonable, therefore when the total quantity is less than or equal to the second threshold, obtain the drug variety set A and institute
State the intersection C of default drug variety set B;The practical use of each drug in the intersection C is determined according to the administration data
Dose determines the default dosage of the drug according to the default administration data;If the practical dosage is more than described pre-
If when dosage, determining the medication excess of the drug;The total quantity of the drug of medication excess in the intersection C is obtained, is determined
The ratio of the total quantity of the drug of medication excess and the total quantity of the element in the intersection in the intersection;As the ratio is big
In third threshold value, the drug medication excess in the hospitalization data of the insured people is determined, determine the behavior of being hospitalized of the insured people
It is illegal.
Wherein, the third threshold value can be 0.5,0.6,0.7,0.8 or other values.
Optionally, when being compared in hospitalization cost contribution degree dimension, due to the drug variety set and the default medicine
There are alternative drugs in kind class set, and some alternative drugs are expensive drug, such as detect drug kind to hide
Whether class excessive and drug dosage whether excess, then the alternative drug for taking a large amount of valuableness can be opened, to increase cost of hospitalization
Drug expenditure in, and at this time since the drug variety set is close with the default drug variety set, it can not judge
The insured people whether there is the behavior for extracting medical insurance fund drug purchase, therefore in the total quantity less than or equal to described
The dosage of any one of second threshold and the intersection drug non-excess when, need in the microcosmic judgement institute of expense dimension
Whether the behavior of being hospitalized for stating insured people is reasonable, specifically includes: determining drug total cost, i.e., according to the drug variety set, every
The dosage of kind drug and the unit price of every kind of drug determine the drug total cost, determine Hospitalization expenses, i.e., according to input
The information such as type of surgery, bed type in hospitalization data determine the Hospitalization expenses;Determine the drug total cost to institute
The contribution degree of Hospitalization expenses, i.e. ratio are stated, such as the contribution degree is greater than contribution degree threshold value, determines that being hospitalized for the insured people counts
Drug expenditure excess in determines that the behavior of being hospitalized of the insured people is illegal.
Wherein, the contribution degree threshold value can be 0.7,075,0.8,0.85,0.9 or other values.
As can be seen that in the embodiment of the present application, when occurring to be hospitalized behavior, receiving and being inputted in hospitalization information administration interface
Hospitalization data, extract the diagnostic data in the hospitalization data, according in advance it is trained be hospitalized prediction model prediction described in
The probability of being hospitalized of insured people determines that the insured people meets the condition of being hospitalized when probability in hospital is greater than first threshold, therefore according to pre-
The mapping relations first established obtain the corresponding default administration data of the diagnostic data, and genre dimension, dosage dimension and
Determine whether the administration data of the insured people is reasonable in expense dimension respectively, in the administration data for determining the insured people, really
The fixed insured people this behavior of being hospitalized it is unreasonable, due in three genre dimension, dosage dimension and expense dimension dimensions
Judge that insured people whether there is false scene of being hospitalized, therefore improve the accuracy of the behavior of being hospitalized of the insured people of verification, increases core
It to reduce the probability for extracting medical insurance fund drug purchase, and is therapeutic machine from medication angle verification behavior in hospital to mode
Medication system when structure reform is hospitalized provides data reference, improves the Medical treatment system of medical institutions, protects public interest.
In a possible example, the method also includes:
When the probability of being hospitalized is unsatisfactory for the preset condition, that is, when being less than or equal to the first threshold, by institute
The hospitalization data for stating insured people is forwarded to line coker to center, receives from the line coker to the verification result at center.Reason
When, it pre-establishes line coker and the insured people, which is largely not necessarily to, to be illustrated when the probability of being hospitalized is less than first threshold to center
Hospitalization therefore can not obtain the default administration data of the insured people due to being not necessarily to hospitalization, using comparison method without
Method is accurately judged to the legitimacy that the insured people requests in hospital.Therefore the hospitalization data of the insured people is sent on line and is checked
Whether center prompts the administration data for checking the insured people abnormal, so as to line coker to the system manager at center according to institute
Whether the administration data for stating insured people described in hospitalization data comprehensive descision is abnormal, it is determined whether insured people's storage is hospitalized.
Referring to Fig.2, Fig. 2 is another side for determining behavior in hospital based on prediction model in hospital provided by the embodiments of the present application
The flow diagram of method, this method are applied to electronic equipment, and this method includes the content as shown in step S201~S208:
Step S201, the hospitalization data of insured people inputted in hospitalization information administration interface is received, in the hospitalization data
Including at least diagnostic data and administration data.
Step S202, the diagnostic data in the hospitalization data is extracted, the diagnostic data is input to and is trained in advance
Be hospitalized prediction model, with obtain the insured people be hospitalized probability.
Step S203, when the probability of being hospitalized meets preset condition, the corresponding default medication of the diagnostic data is obtained
Data.
Step S204, the administration data and the default administration data are compared, the administration data as described in determining
When abnormal, determine that the behavior of being hospitalized of the insured people is illegal.
Step S205, it determines the abnormal drug variety in the administration data, obtains abnormal drug variety set.
Optionally, it determines that the abnormal drug variety in the administration data specifically includes: obtaining in the administration data
Drug variety obtains the drug variety collection of the administration data, obtains the drug variety in the default administration data, obtains institute
The default drug variety collection for stating default administration data, when being compared in drug variety dimension, in the medicine for determining the administration data
When kind class excess, the intersection of the drug variety collection Yu the default drug variety collection is obtained, the drug variety is concentrated
The corresponding nomenclature of drug of all drugs in addition to drug and alternative drug in the intersection is labeled as abnormal drug, obtains
To the first abnormal drug variety collection;When being compared in drug dosage dimension, in determining the intersection when drug medication excess,
The corresponding nomenclature of drug of all drugs of medication excess in the intersection is labeled as abnormal drug, obtains the second abnormal drug kind
Class set;When being compared in hospitalization cost contribution degree dimension, when determining drug expenditure exception, by drug in the alternative drug
Expense marks abnormal drug much higher than the corresponding nomenclature of drug of all alternative drugs of substituted drug expenditure, obtains third
Abnormal drug variety collection, by the described first abnormal drug variety collection, the second abnormal drug variety collection and third exception drug variety
The union of collection is labeled as the abnormal drug variety collection.
Step S206, several unreasonable insured people of administration data of the statistics within a preset period of time in hospitalization data,
The abnormal drug variety collection for determining each insured people in several described insured people obtains multiple abnormal drug variety collection.
Step S207, target exception drug variety collection is determined according to the multiple abnormal drug variety collection.
Optionally, determine that target exception drug variety collection specifically includes according to the multiple abnormal drug variety collection: by institute
The abnormal drug variety collection of each insured people is stated labeled as things collection, obtains the corresponding multiple things collection of the multiple insured people,
Wherein, the corresponding things collection of each insured people numbers the things collection of each insured people, using number information as the things
The id information of collection, for example, the things collection of multiple insured people is numbered respectively is 001,002,003 ...;According to FP-
Growth algorithm determines the frequent item set that the multiple things is concentrated, and the element in the frequent item set is marked for doctor
The target administration data for treating mechanism specifically includes the first minimum support P1 of setting, it is more to screen this based on minimum support P
Multiple frequent elements that a things is concentrated, the FP tree of the multiple things collection is constructed using multiple frequent element, and setting is frequent
Number of elements needed for item collection or setting the second minimum support P2, from the FP tree reading meet the number of elements or
Person's support is greater than multiple frequent item sets of P2, obtains the maximum frequent item set of support in the multiple frequent item set, such as should
When the quantity of the maximum frequent item set of support is multiple, the intersection of multiple frequent item set is obtained, by the element in the intersection
As the union of the target exception drug variety collection or the multiple frequent item set of acquisition, using the element of this and concentration as this
Target exception drug variety collection.
The detailed process of determining frequent item set and target exception drug variety collection is exemplified below.
It is assumed that the behavior of being hospitalized for getting 6 insured people within a preset period of time is unreasonable, 6 practical preoperative plannings are obtained
Item Sets, it is 001,002,003,004,005,006 that this 6 practical preoperative planning Item Sets are numbered respectively, by this 6
Element (i.e. preoperative planning project) in practical preoperative planning Item Sets is indicated respectively with letter, for example, the preoperative planning in 001
Item Sets are respectively blood routine, routine urinalysis, electrocardiogram, blood pressure, blood glucose, oral cavity, then, by the blood routine, routine urinalysis, electrocardio
Respectively with alphabetical r, z, h, j, p are indicated, therefore can obtain 001={ r, z, h, j, p } for figure, blood pressure, blood glucose, oral cavity, based on obtaining 001
Mode, can to 002,003,004,005 and 006 preoperative planning project it is alphabetized, obtain 002={ z, y, x, w, v, u, t, s },
003={ z }, 004={ r, x, n, o, s }, 005={ y, r, x, z, q, t, p }, 006={ y, z, x, e, q, s, t, m };It opens first
The first wheel scan is opened, the first minimum support P1=3 is set, by element frequency of occurrence in 001,002,003,004,005,006
It is rejected less than support P1, i.e. rejecting q, n, o, h, j, p, w, v, u and e, obtains new things collection { r, z }, { z, y, x, t, s },
{ z }, { r, x, s }, { y, r, x, z, t }, { y, z, x, s, t } open the second wheel scan and successively scan new things collection, with empty set
Start to create FP tree for root node, the successively addition element into the FP tree when scanning each new things collection, as scan r,
Z } when, can addition element r, z, scan { z, y, x, t, s } when, member can be added in the FP tree that first time addition element r, z are obtained
Plain z, y, x, t, s after all scanning through, complete the building of FP tree;So being provided on the tree node of the FP tree single in set
Element and its total degree occurred in new things concentration, it is corresponding that the frequency of occurrence of the element of the root node in path shows the path
Sequence frequency of occurrence (i.e. support).As can be seen that all elements on each path constitute a frequent item set, and
The root node in each path shows the support of each frequent item set;Then, number of elements needed for frequent item set is set, from
The tree node of the FP tree intercepts root node corresponding with the number of elements, and the element between the tree node and the root node is formed
Frequent item set, for example, setting frequent item set in number of elements be 4 when, can get frequent item set be { z, x, y, s }, z, x, y,
R }, { x, y, s, t }, { x, y, r, t }, and respective support is respectively 2,1,2 and 1, therefore the maximum frequent item set of support is
{ z, x, y, s } and { x, y, s, t }, therefore the union { z, x, y, s, t } of the frequent item set { z, x, y, s } and { x, y, s, t } can be made
For the frequent item set of multiple things collection, i.e., z, x, y, s, t are formed into target exception drug variety collection or by the frequent item set
X, y, s are formed target by frequent item set of the intersection { x, y, s } of { z, x, y, s } and { x, y, s, t } as multiple things collection
Abnormal drug variety collection;Or the second support P2 of setting, third wheel scan is opened based on the second support P2, scanning should
Support is more than or equal to the set of P2 in FP tree, using the set as frequent item set, such as when P2=3, due to set
{ z }, { z, x }, the support of { z, x, y } and { x, y } they are respectively 5,3,3 and 3, determine that it meets P2, by { z }, { z, x }, z, x,
Y } and { x, y are labeled as frequent item set.Since the intersection of { z }, { z, x }, { z, x, y } and { x, y } areIt is unsatisfactory for condition at this time,
Give up, take { z }, { z, x }, the union { z, x, y } of { z, x, y } and { x, y } is used as target frequent item set, i.e., z, x, y is formed mesh
Mark abnormal drug variety collection.
Step S208, the target exception drug variety collection is sent to the network side equipment of medical institutions, to adjust to institute
State the management system that target exception type concentrates any one drug.
As can be seen that in the embodiment of the present application, when occurring to be hospitalized behavior, receiving and being inputted in hospitalization information administration interface
Hospitalization data, extract the diagnostic data in the hospitalization data, according in advance it is trained be hospitalized prediction model prediction described in
The probability of being hospitalized of insured people determines that the insured people meets the condition of being hospitalized when probability in hospital is greater than first threshold, therefore according to pre-
The mapping relations first established obtain the corresponding default administration data of the diagnostic data, and genre dimension, dosage dimension and
Determine whether the administration data of the insured people is reasonable in expense dimension respectively, in the administration data for determining the insured people, really
The fixed insured people this behavior of being hospitalized it is unreasonable, due in three genre dimension, dosage dimension and expense dimension dimensions
Judge that insured people whether there is false scene of being hospitalized, therefore improve the accuracy of the behavior of being hospitalized of the insured people of verification, increases core
To mode, from medication angle verification behavior in hospital, to reduce the probability for extracting medical insurance fund drug purchase;Moreover, determining
The target exception drug variety collection of medical institutions out realizes that hospital's specific aim reforms the medication system in abnormal drug variety collection,
The efficiency of medical system reform is improved, since it is determined that abnormal kind of class set, medical institutions can adjust medical treatment in time and correctly
System improves the ability of medical institutions' reply risk, improves the Medical treatment system of medical institutions, protect public interest.
Optionally, in a possible example, the method also includes:
It determines each department in the medical institutions with clinical operation qualification, obtains each department when default
Between in section several insured people hospitalization data, determine the administration data in several insured people of each department in hospitalization data
Several abnormal insured people, calculate each department in the total quantity of the insured people of the preset time period innerlich anwenden data exception
The ratio for requesting the total quantity of insured people in hospital in the preset time period with each department, according to the ratio to each section
Room is ranked up, and adjustment sequence is reinforced to sequence in first five department in terms of medication in the system of being hospitalized of the department of first five
Management.
As can be seen that analyzing the hospitalization data of each department within a preset period of time in this example, obtain in each department
The ratio of medical insured people's administration data exception, is ranked up each department according to the ratio to obtain ranking results, foundation
Ranking results adjust department in the top, so that the system of being hospitalized of specific aim adjustment department, is hospitalized for medical institution reform and makes
Degree provides data reference, is conducive to the comprehensive quality for improving medical institutions, reduces each department using the mode of being hospitalized and extracts medical insurance
The probability of disbursement from fund purchase expenses for medicine.
Optionally, in a possible example, the method also includes:
All insured people of administration data exception of the medical institutions within a preset period of time in hospitalization data are counted, this is obtained
The abnormal corresponding all hospitalization datas of all insured people of administration data, extract doctor's letter all in all hospitalization datas
Breath, obtains the frequency of occurrences of each information about doctor, supervises the corresponding doctor's of all information about doctor according to the frequency of occurrences
It writes a prescription behavior, specifically includes: to frequency of occurrences ranking first five the corresponding doctor of information about doctor periodically from medical data base
It obtains it and opens the hospitalization data list taken, as the administration data frequency of abnormity in the hospitalization data list is greater than respective preset threshold
When, which is uploaded to hospitalization management system, to supervise the reasonability that the doctor opens the hospitalization data list taken, wherein
The preset threshold is related to doctor's ranking, and the more forward preset threshold of ranking is smaller.
As can be seen that analyzing the hospitalization data of all insured people of administration data exception in this example, each doctor is obtained
The frequency of occurrences of information, according to the frequency of occurrences, supervision doctor opens the hospitalization data list taken, and reducing doctor will be joined by substandard
Guarantor's income is hospitalized to extract the probability of medical insurance fund payment art purchase expenses for medicine.
Refering to Fig. 3, Fig. 3 is another side that behavior in hospital is determined based on prediction model in hospital provided by the embodiments of the present application
The flow diagram of method, this method are applied to electronic equipment, and this method includes the content as shown in step S301~S309:
Step S301, the medical data sample of preset quantity is obtained from the database of medical institutions.
Wherein, in the medical data sample including the demography parameter of insured people, disease name, disease menace level,
Whether hospitalization information, etc..
Step S302, the medical data sample for the preset quantity that will acquire is divided into the training set and the second ratio of the first ratio
The test set of example.
Wherein, first ratio can be 90%, 80%, 70%, 60% or other values.
Wherein, second ratio can be 10%, 20%, 30%, 40% or other values.
Step S303, the predetermined prediction mould of being hospitalized of each medical data sample training in the training set is utilized
Type, with obtain it is described preset it is trained be hospitalized prediction model.
Step S304, trained prediction of being hospitalized is preset to described using each medical data sample in the test set
Model is tested, and if test passes through, executes step S305, and such as test does not pass through, and increases from the database of the medical institutions
Add the quantity of medical data sample, returns and execute S302.
Optionally, trained prediction mould of being hospitalized is preset to described using each medical data sample in the test set
Type carries out test and specifically includes: presetting trained prediction model of being hospitalized to each medical number in the test set using described
Analytical calculation is carried out according to sample, to obtain the corresponding probability of being hospitalized of each medical data sample;Utilize each medical data sample
Identification information, inquire the practical Hospitalization situation of each medical data sample, determine the use of it is described preset it is trained be hospitalized it is pre-
Survey be hospitalized probability and a medical data sample that model obtains practical Hospitalization situation obtain to it is described preset it is trained
The accuracy test result of prediction model in hospital, output result are two-value data, i.e., 0 and 1 two-value data, 0 represents accurately
Property test result be mistake, 1 represent accuracy test result be it is correct, the probability of being hospitalized specially such as obtained is greater than the first threshold
Value, and the practical Hospitalization situation in the medical data sample is to be hospitalized, obtaining its accuracy test result is 1, as obtained
Probability is less than or equal to the first threshold in hospital, and the practical Hospitalization situation in the medical data sample is not to be hospitalized,
Determine that accuracy test result is 1, the accuracy test result of other situations is 0, determines that accuracy test result accounts for institute for 1
There is the percentage of accuracy test result, such as the percentage is greater than percentage threshold (for example, 80%), it is determined that described pre-
If the trained test for being hospitalized prediction model passes through, alternatively, as the percentage ratio is less than or equal to the percentage threshold
Value determines and does not pass through to the test for setting trained prediction model in hospital, need to increase from the database of the medical institutions
Add the quantity of medical data sample, re -training.
Step S305, complete training, obtain it is described preset it is trained be hospitalized prediction model, by it is described preset it is trained
The server of the medical institutions of prediction model insertion in hospital, to predict the probability of being hospitalized of insured people.
Step S306, the hospitalization data of the insured people inputted in hospitalization information administration interface is received.
Wherein, diagnostic data and administration data are included at least in the hospitalization data.
Step S307, the diagnostic data in the hospitalization data is extracted, the diagnostic data is input to the therapeutic machine
What is had been inserted into the server of structure presets trained prediction model of being hospitalized, and obtains the probability of being hospitalized of the insured people.
Step S308, when the probability of being hospitalized meets preset condition, the corresponding default medication of the diagnostic data is obtained
Data.
Step S309, the administration data and the default administration data are compared, are determining the administration data
When abnormal, determine that the behavior of being hospitalized of the insured people is illegal.
As can be seen that in the embodiment of the present application, medical data sample is first obtained from the medical data base of medical institutions,
To train prediction model of being hospitalized, therefore the model of being hospitalized of the application is more targetedly more accurate to the prediction of probability in hospital;And
And when occurring to be hospitalized behavior, the hospitalization data inputted in hospitalization information administration interface is received, is extracted in the hospitalization data
Diagnostic data predicts the probability of being hospitalized of the insured people according to prediction model of being hospitalized trained in advance, and in hospital, probability is greater than
When first threshold, determines that the insured people meets the condition of being hospitalized, therefore obtain the diagnosis number according to the mapping relations pre-established
Determine the insured people's respectively according to corresponding default administration data, and in genre dimension, dosage dimension and expense dimension
Whether administration data is reasonable, in the administration data for determining the insured people, determines that this behavior of being hospitalized of the insured people does not conform to
Reason, due to judging that insured people whether there is false scene of being hospitalized in three genre dimension, dosage dimension and expense dimension dimensions,
Therefore the accuracy of the behavior of being hospitalized of the insured people of verification is improved, verification mode is increased, checks the behavior of being hospitalized from medication angle, from
And reduce the probability for extracting medical insurance fund drug purchase, and medication system when being hospitalized for medical institution reform provides data ginseng
It examines, improves the Medical treatment system of medical institutions, protect public interest.
It is consistent with above-mentioned Fig. 1, Fig. 2, embodiment shown in Fig. 3, referring to Fig. 4, Fig. 4 is provided by the embodiments of the present application
A kind of structural schematic diagram for the electronic equipment 400 determining behavior in hospital based on prediction model in hospital, as shown in figure 4, the electronics is set
Standby 400 include processor, memory, communication interface and one or more programs, wherein said one or multiple programs are different
In said one or multiple application programs, and said one or multiple programs are stored in above-mentioned memory, and are configured
It is executed by above-mentioned processor, above procedure includes the instruction for executing following steps;
The hospitalization data of the insured people inputted in hospitalization information administration interface is received, includes at least and examines in the hospitalization data
Disconnected data and administration data;
The diagnostic data in the hospitalization data is extracted, the diagnostic data is input to trained in advance be hospitalized and is predicted
Model, to obtain the probability of being hospitalized of the insured people;
When the probability of being hospitalized meets preset condition, the corresponding default administration data of the diagnostic data is obtained;
The administration data and the default administration data are compared, determine the insured people be hospitalized behavior whether
It is legal.
In a possible example, when in the diagnostic data include disease name, disease menace level, insured people people
When mouth learns parameter, the diagnostic data is being input to prediction model of being hospitalized trained in advance, to obtain the insured people's
In hospital in terms of probability, the instruction in above procedure is specifically used for executing following operation:
Extract disease name in the diagnostic data, disease menace level, insured people demography parameter;
The disease name, disease menace level, demography parameter composition input data matrix are input to preparatory training
Good prediction model of being hospitalized executes forward operation, to obtain the probability of being hospitalized of the insured people.
In a possible example, when the probability of being hospitalized meets preset condition, it is corresponding to obtain the diagnostic data
In terms of default administration data, the instruction in above procedure is specifically used for executing following operation:
When the probability of being hospitalized is greater than first threshold, determine that the insured people meets the condition of being hospitalized;
Obtain the disease name in the diagnostic data;
The corresponding default administration data of the diagnostic data is determined according to the mapping relations of disease name and administration data.
In a possible example, compares, determine described insured by the administration data and the default administration data
The whether legal aspect of behavior of being hospitalized of people, the instruction in above procedure are specifically used for executing following operation:
The drug variety in the administration data is extracted, the drug variety set of the administration data is obtained;
The drug variety in the default administration data is extracted, the default drug variety collection of the default administration data is obtained
It closes;
When the drug variety set and the default drug variety intersection of sets integrate as empty set, the insured people is determined
Hospitalization data in drug variety it is unreasonable, determine the insured people be hospitalized behavior it is illegal.
In a possible example, in the drug variety extracted in the default administration data, obtain described default
After the default drug variety set of administration data, the instruction in above procedure is also used to execute following operation:
When the drug variety set and the default drug variety intersection of sets integrate as nonvoid set, the drug is determined
The difference set of type set and the default drug variety set, obtains first set, determine the default drug variety set with
The difference set of the drug variety set, obtains second set;
I-th of drug as corresponding to i-th of element in the first set is j-th yuan in the second set
Jth drug corresponding to element presets alternative drug, it is determined that i-th of element is the alternative of j-th of element
Element;
All alternative elements in the first set are obtained, determines and removes described all replace in the first set
For the total quantity of the other elements except element;As the total quantity is greater than second threshold, it is determined that the insured people's is hospitalized
Behavior is illegal;
Wherein, i-th of element is any one element in the first set, and j-th of element is described
Any one element in second set, described i, j are the integer more than or equal to 1.
In a possible example, compares, determine described insured by the administration data and the default administration data
The whether legal aspect of behavior of being hospitalized of people, the instruction in above procedure are specifically used for executing following operation:
When being less than or equal to the second threshold such as the total quantity, obtains the drug variety set and preset with described
Drug variety intersection of sets collection;
The practical dosage that each drug in the intersection is determined according to the administration data, according to the default medication
Data determine the default dosage of the drug;
When being more than the default dosage such as the practical dosage, the medication excess of the drug is determined;
The total quantity for obtaining the drug of medication excess in the intersection determines the total of the drug of medication excess in the intersection
The ratio of quantity and the total quantity of the element in the intersection;
If the ratio is greater than third threshold value, the drug medication excess in the hospitalization data of the insured people is determined, determine
The behavior of being hospitalized of the insured people is illegal.
In a possible example, the instruction in above procedure is also used to execute following operation:
The medical data sample of preset quantity is obtained from the database of medical institutions, includes in the medical data sample
The demography parameter of insured people, disease name, disease menace level, whether hospitalization information;
The medical data sample for the preset quantity that will acquire is divided into the training set of the first ratio and the test of the second ratio
Collection;
Using the predetermined prediction model of being hospitalized of each medical data sample training in the training set, to obtain
It states and presets trained prediction model of being hospitalized, described preset is trained using each medical data sample in the test set
Be hospitalized prediction model tested, if test pass through, training terminate, if test do not pass through, from the medical institutions
Increase the quantity of medical data sample, re -training in database.
The electricity for determining behavior in hospital involved in above-described embodiment based on prediction model in hospital is shown refering to Fig. 5, Fig. 5
A kind of possible functional unit of sub- equipment 500 forms block diagram, electronic equipment 500 include receiving unit 510, extraction unit 520,
Acquiring unit 530, determination unit 540, wherein;
Receiving unit 510, it is described to be hospitalized for receiving the hospitalization data in the insured people of hospitalization information administration interface input
Diagnostic data and administration data are included at least in data;
The diagnostic data is input in advance by extraction unit 520 for extracting the diagnostic data in the hospitalization data
Trained prediction model of being hospitalized, to obtain the probability of being hospitalized of the insured people;
Acquiring unit 530, for it is corresponding pre- to obtain the diagnostic data when the probability of being hospitalized meets preset condition
If administration data;
Determination unit 540 determines described insured for the administration data and the default administration data to be compared
Whether the behavior of being hospitalized of people is legal.
In a possible example, when in the diagnostic data include disease name, disease menace level, insured people people
When mouth learns parameter, the diagnostic data is being input to prediction model of being hospitalized trained in advance, to obtain the insured people's
In hospital when probability, extraction unit 520 is specifically used for: extracting disease name, the disease menace level, ginseng in the diagnostic data
The demography parameter of guarantor;And for the disease name, disease menace level, demography parameter to be formed input data square
Battle array is input to prediction model of being hospitalized trained in advance and executes forward operation, to obtain the probability of being hospitalized of the insured people.
In a possible example, when the probability of being hospitalized meets preset condition, it is corresponding to obtain the diagnostic data
When default administration data, acquiring unit 530 is specifically used for: when the probability of being hospitalized is greater than first threshold, determining described insured
People meets the condition of being hospitalized;And for obtaining the disease name in the diagnostic data;And for according to disease name and use
The mapping relations of medicine data determine the corresponding default administration data of the diagnostic data.
In a possible example, compares, determine described insured by the administration data and the default administration data
When whether the behavior of being hospitalized of people is legal, determination unit 540 is specifically used for: extracting the drug variety in the administration data, obtains
The drug variety set of the administration data;And it for extracting the drug variety in the default administration data, obtains described
The default drug variety set of default administration data;And in the drug variety set and the default drug variety collection
When the intersection of conjunction is empty set, determines that the drug variety in the hospitalization data of the insured people is unreasonable, determine the insured people's
Behavior is illegal in hospital.
In a possible example, in the drug variety extracted in the default administration data, obtain described default
After the default drug variety set of administration data, determination unit 540 is also used to preset in the drug variety set with described
When drug variety intersection of sets is integrated as nonvoid set, the difference of the drug variety set Yu the default drug variety set is determined
Collection, obtains first set, determines the difference set of the default drug variety set and the drug variety set, obtain the second collection
It closes;It and for i-th drug as corresponding to i-th of element in the first set is the jth in the second set
Jth drug corresponding to a element presets alternative drug, it is determined that i-th of element can for j-th of element
Substitute element;And it for obtaining all alternative elements in the first set, determines and removes institute in the first set
State the total quantity of the other elements except all alternative elements;As the total quantity is greater than second threshold, it is determined that the ginseng
The behavior of being hospitalized of guarantor is illegal;Wherein, i-th of element is any one element in the first set, the jth
A element is any one element in the second set, and described i, j are the integer more than or equal to 1.
In a possible example, compares, determine described insured by the administration data and the default administration data
When whether the behavior of being hospitalized of people is legal, determination unit 540 is also used to the total quantity such as and is less than or equal to the second threshold
When, obtain the drug variety set and the default drug variety intersection of sets collection;And for according to the administration data
The practical dosage for determining each drug in the intersection determines the default use of the drug according to the default administration data
Dose;And when for being more than the default dosage such as the practical dosage, determine the medication excess of the drug;And
For obtaining the total quantity of the drug of medication excess in the intersection, the total quantity of the drug of medication excess in the intersection is determined
With the ratio of the total quantity of the element in the intersection;And it is greater than third threshold value for such as the ratio, it determines described insured
Drug medication excess in the hospitalization data of people determines that the behavior of being hospitalized of the insured people is illegal.
In a possible example, electronic equipment 500 further include: training unit 550;
Wherein, training unit 550 are used for: the medical data sample of preset quantity is obtained from the database of medical institutions,
It include the demography parameter of insured people in the medical data sample, disease name, disease menace level, whether hospitalization is believed
Breath;And the medical data sample of the preset quantity for will acquire is divided into the training set of the first ratio and the survey of the second ratio
Examination collection;And for utilizing the predetermined prediction model of being hospitalized of each medical data sample training in the training set, with
Obtain it is described preset trained prediction model of being hospitalized, using each medical data sample in the test set to described default
Trained prediction model of being hospitalized is tested, if test passes through, training terminates, if test does not pass through, from the medical treatment
Increase the quantity of medical data sample, re -training in the database of mechanism.
The embodiment of the present application also provides a kind of computer storage medium, wherein computer storage medium storage is for electricity
The computer program of subdata exchange, it is as any in recorded in above method embodiment which execute computer
It is a kind of to be determined to be hospitalized some or all of the method step of behavior based on prediction model in hospital.
The embodiment of the present application also provides a kind of computer program product, and the computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, the computer program are operable to that computer is made to execute such as above-mentioned side
Some or all of any method that behavior in hospital is determined based on prediction model in hospital recorded in method embodiment step.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, embodiment described in this description belongs to alternative embodiment, related actions and modules not necessarily the application
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of the unit, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also be realized in the form of software program module.
If the integrated unit is realized in the form of software program module and sells or use as independent product
When, it can store in a computer-readable access to memory.Based on this understanding, the technical solution of the application substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment
(can be personal computer, server or network equipment etc.) executes all or part of each embodiment the method for the application
Step.And memory above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
May include: flash disk, read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English:
Random Access Memory, referred to as: RAM), disk or CD etc..
The embodiment of the present application is described in detail above, specific case used herein to the principle of the application and
Embodiment is expounded, the description of the example is only used to help understand the method for the present application and its core ideas;
At the same time, for those skilled in the art can in specific embodiments and applications according to the thought of the application
There is change place, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (10)
1. a kind of method for determining behavior in hospital based on prediction model in hospital, which is characterized in that the method is set applied to electronics
It is standby, which comprises
The hospitalization data of the insured people inputted in hospitalization information administration interface is received, diagnosis number is included at least in the hospitalization data
According to and administration data;
The diagnostic data in the hospitalization data is extracted, the diagnostic data is input to prediction mould of being hospitalized trained in advance
Type, to obtain the probability of being hospitalized of the insured people;
When the probability of being hospitalized meets preset condition, the corresponding default administration data of the diagnostic data is obtained;
The administration data and the default administration data are compared, determine whether the behavior of being hospitalized of the insured people closes
Method.
2. the method according to claim 1, wherein when tight including disease name, disease in the diagnostic data
It is described that the diagnostic data is input to prediction model of being hospitalized trained in advance when weight grade, the demography parameter of insured people,
It is specifically included with obtaining the probability of being hospitalized of the insured people:
Extract disease name in the diagnostic data, disease menace level, insured people demography parameter;
The disease name, disease menace level, demography parameter composition input data matrix are input to trained in advance
Prediction model executes forward operation in hospital, to obtain the probability of being hospitalized of the insured people.
3. method according to claim 1 or 2, which is characterized in that it is described when the probability of being hospitalized meets preset condition,
The corresponding default administration data of the diagnostic data is obtained to specifically include:
When the probability of being hospitalized is greater than first threshold, determine that the insured people meets the condition of being hospitalized;
Obtain the disease name in the diagnostic data;
The corresponding default administration data of the diagnostic data is determined according to the mapping relations of disease name and administration data.
4. method according to claim 1 or 2, which is characterized in that described by the administration data and the default medication
Comparing determines that the insured people's is hospitalized whether behavior is legal specifically includes:
The drug variety in the administration data is extracted, the drug variety set of the administration data is obtained;
The drug variety in the default administration data is extracted, the default drug variety set of the default administration data is obtained;
When the drug variety set and the default drug variety intersection of sets integrate as empty set, living for the insured people is determined
Drug variety in institute's data is unreasonable, determines that the behavior of being hospitalized of the insured people is illegal.
5. according to the method described in claim 4, it is characterized in that, in the drug kind extracted in the default administration data
Class, after obtaining the default drug variety set of the default administration data, the method also includes:
When the drug variety set and the default drug variety intersection of sets integrate as nonvoid set, the drug variety is determined
Set and the difference set of the default drug variety set, obtain first set, determine the default drug variety set with it is described
The difference set of drug variety set, obtains second set;
I-th of drug as corresponding to i-th of element in the first set is j-th of element institute in the second set
Corresponding jth drug presets alternative drug, it is determined that i-th of element is the alternative element of j-th of element;
All alternative elements in the first set are obtained, determines and removes all alternative members in the first set
The total quantity of other elements except element;As the total quantity is greater than second threshold, it is determined that the behavior of being hospitalized of the insured people
It is illegal;
Wherein, i-th of element is any one element in the first set, and j-th of element is described second
Any one element in set, described i, j are the integer more than or equal to 1.
6. according to the method described in claim 5, it is characterized in that, the method also includes:
When being less than or equal to the second threshold such as the total quantity, the drug variety set and the default drug are obtained
Type intersection of sets collection;
The practical dosage that each drug in the intersection is determined according to the administration data, according to the default administration data
Determine the default dosage of the drug;
When being more than the default dosage such as the practical dosage, the medication excess of the drug is determined;
The total quantity for obtaining the drug of medication excess in the intersection determines the total quantity of the drug of medication excess in the intersection
With the ratio of the total quantity of the element in the intersection;
If the ratio is greater than third threshold value, determine the drug medication excess in the hospitalization data of the insured people, determine described in
The behavior of being hospitalized of insured people is illegal.
7. method according to claim 1-6, which is characterized in that the method also includes:
The medical data sample of preset quantity is obtained from the database of medical institutions, includes insured in the medical data sample
The demography parameter of people, disease name, disease menace level, whether hospitalization information;
The medical data sample for the preset quantity that will acquire is divided into the training set of the first ratio and the test set of the second ratio;
It is described pre- to obtain using the predetermined prediction model of being hospitalized of each medical data sample training in the training set
If it is trained be hospitalized prediction model, using each medical data sample in the test set to it is described preset it is trained live
Institute's prediction model is tested, if test passes through, training terminates, if test does not pass through, from the data of the medical institutions
Increase the quantity of medical data sample, re -training in library.
8. a kind of determined to be hospitalized the electronic equipment of behavior based on prediction model in hospital, which is characterized in that the electronic equipment includes:
Receiving unit, for receiving the hospitalization data in the insured people of hospitalization information administration interface input, in the hospitalization data
Including at least diagnostic data and administration data;
The diagnostic data is input to and trains in advance for extracting the diagnostic data in the hospitalization data by extraction unit
Be hospitalized prediction model, with obtain the insured people be hospitalized probability;
Acquiring unit, for obtaining the corresponding default medication of the diagnostic data when the probability of being hospitalized meets preset condition
Data;
Determination unit determines living for the insured people for the administration data and the default administration data to be compared
Whether institute's behavior is legal.
9. a kind of electronic equipment, which is characterized in that including processor, memory, communication interface and one or more program,
In, one or more of programs are stored in the memory, and are configured to be executed by the processor, described program
Include the steps that requiring the instruction in any one of 1-7 method for perform claim.
10. a kind of computer readable storage medium, which is characterized in that it is used to store computer program, wherein the computer
Program makes computer execute the method according to claim 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811276180.0A CN109545317A (en) | 2018-10-30 | 2018-10-30 | The method and Related product of behavior in hospital are determined based on prediction model in hospital |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811276180.0A CN109545317A (en) | 2018-10-30 | 2018-10-30 | The method and Related product of behavior in hospital are determined based on prediction model in hospital |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109545317A true CN109545317A (en) | 2019-03-29 |
Family
ID=65845492
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811276180.0A Pending CN109545317A (en) | 2018-10-30 | 2018-10-30 | The method and Related product of behavior in hospital are determined based on prediction model in hospital |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109545317A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109636650A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the readable storage medium storing program for executing of therapeutic regimen exception |
CN109978701A (en) * | 2019-04-01 | 2019-07-05 | 太平洋医疗健康管理有限公司 | Personal probability forecasting method and the system of being hospitalized |
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 |
CN111091906A (en) * | 2019-10-31 | 2020-05-01 | 中电药明数据科技(成都)有限公司 | Auxiliary medical diagnosis method and system based on real world data |
CN111951924A (en) * | 2020-08-14 | 2020-11-17 | 江苏云脑数据科技有限公司 | Abnormal medication behavior detection method and system |
CN112016302A (en) * | 2020-08-03 | 2020-12-01 | 青岛国新健康产业科技有限公司 | Recognition method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
CN112117009A (en) * | 2020-09-25 | 2020-12-22 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and medium for constructing label prediction model |
US11113770B1 (en) * | 2021-04-13 | 2021-09-07 | Nayya Health, Inc. | Machine-learning driven data analysis based on demographics, risk, and need |
CN113822365A (en) * | 2021-09-28 | 2021-12-21 | 刘玉棚 | Medical data storage and big data mining method and system based on block chain technology |
CN114141386A (en) * | 2021-11-09 | 2022-03-04 | 江苏瑞德信息产业有限公司 | Medicine checking device and method |
CN112016302B (en) * | 2020-08-03 | 2024-04-30 | 青岛国新健康产业科技有限公司 | Identification method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335618A (en) * | 2015-11-10 | 2016-02-17 | 成都数联易康科技有限公司 | Patient feature depiction method and false hospitalization behavior detection method based on the patient feature depiction 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 |
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 |
-
2018
- 2018-10-30 CN CN201811276180.0A patent/CN109545317A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105335618A (en) * | 2015-11-10 | 2016-02-17 | 成都数联易康科技有限公司 | Patient feature depiction method and false hospitalization behavior detection method based on the patient feature depiction 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 |
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 |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109636650A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, terminal and the readable storage medium storing program for executing of therapeutic regimen exception |
CN109978701A (en) * | 2019-04-01 | 2019-07-05 | 太平洋医疗健康管理有限公司 | Personal probability forecasting method and the system of being hospitalized |
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 |
CN111091906B (en) * | 2019-10-31 | 2023-06-20 | 中电药明数据科技(成都)有限公司 | Auxiliary medical diagnosis method and system based on real world data |
CN111091906A (en) * | 2019-10-31 | 2020-05-01 | 中电药明数据科技(成都)有限公司 | Auxiliary medical diagnosis method and system based on real world data |
CN112016302A (en) * | 2020-08-03 | 2020-12-01 | 青岛国新健康产业科技有限公司 | Recognition method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
CN112016302B (en) * | 2020-08-03 | 2024-04-30 | 青岛国新健康产业科技有限公司 | Identification method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
CN111951924A (en) * | 2020-08-14 | 2020-11-17 | 江苏云脑数据科技有限公司 | Abnormal medication behavior detection method and system |
CN112117009A (en) * | 2020-09-25 | 2020-12-22 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and medium for constructing label prediction model |
US11113770B1 (en) * | 2021-04-13 | 2021-09-07 | Nayya Health, Inc. | Machine-learning driven data analysis based on demographics, risk, and need |
CN113822365A (en) * | 2021-09-28 | 2021-12-21 | 刘玉棚 | Medical data storage and big data mining method and system based on block chain technology |
CN113822365B (en) * | 2021-09-28 | 2023-09-05 | 北京恒生芸泰网络科技有限公司 | Medical data storage and big data mining method and system based on block chain technology |
CN114141386A (en) * | 2021-11-09 | 2022-03-04 | 江苏瑞德信息产业有限公司 | Medicine checking device and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109545317A (en) | The method and Related product of behavior in hospital are determined based on prediction model in hospital | |
CN110136788B (en) | Medical record quality inspection method, device, equipment and storage medium based on automatic detection | |
CN109636623A (en) | Medical data method for detecting abnormality, device, equipment and storage medium | |
CN110910976A (en) | Medical record detection method, device, equipment and storage medium | |
CN107731270A (en) | A kind of method and device of automatic examination & verification prescription accuracy | |
CN109670173A (en) | Submit an expense account the investigation method, identification server-side and storage medium of data | |
CN109636613A (en) | Medical data abnormality recognition method, device, terminal and storage medium | |
US11244764B2 (en) | Monitoring predictive models | |
Scott et al. | Learning health systems need to bridge the'two cultures' of clinical informatics and data science | |
CN109934719A (en) | The detection method and detection device of medical insurance unlawful practice, medical insurance control charge system | |
US20070150314A1 (en) | Method for carrying out quality control of medical data records collected from different but comparable patient collectives within the bounds of a medical plan | |
CN113657548A (en) | Medical insurance abnormity detection method and device, computer equipment and storage medium | |
CN109118376A (en) | Medical insurance premium calculation principle method, apparatus, computer equipment and storage medium | |
US20220005565A1 (en) | System with retroactive discrepancy flagging and methods for use therewith | |
CN109377207A (en) | The abnormal method and Related product that behavior determines of being hospitalized | |
CN109191314A (en) | Document method of charging out, device, computer equipment and storage medium | |
CN112447270A (en) | Medication recommendation method, device, equipment and storage medium | |
CN113990482A (en) | Health data processing system and method | |
CN109377388A (en) | Medical insurance is insured method, apparatus, computer equipment and storage medium | |
WO2020087971A1 (en) | Prediction model-based hospitalization rationality prediction method and related products | |
CN113903423A (en) | Medication scheme recommendation method, device, equipment and medium | |
CN114155949A (en) | Examination and verification method, device and equipment for first page of medical record | |
CN109102845B (en) | Medical document auditing method, device, computer equipment and storage medium | |
CN110781222A (en) | Abnormal medical insurance application detection method and device, computer equipment and storage medium | |
CN109935287A (en) | A kind of similarity analysis method, device and equipment of medical record information |
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 |