CN109767067A - Method and Related product based on more evaluative dimensions evaluation hospital - Google Patents
Method and Related product based on more evaluative dimensions evaluation hospital Download PDFInfo
- Publication number
- CN109767067A CN109767067A CN201811527749.6A CN201811527749A CN109767067A CN 109767067 A CN109767067 A CN 109767067A CN 201811527749 A CN201811527749 A CN 201811527749A CN 109767067 A CN109767067 A CN 109767067A
- Authority
- CN
- China
- Prior art keywords
- hospital
- medical
- risk
- dimension
- index
- 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 70
- 238000011156 evaluation Methods 0.000 title claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims description 50
- 230000004069 differentiation Effects 0.000 claims description 31
- 238000001514 detection method Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 5
- 238000012731 temporal analysis Methods 0.000 claims description 5
- 238000000700 time series analysis Methods 0.000 claims description 5
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 description 38
- 238000013507 mapping Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 11
- 238000005070 sampling Methods 0.000 description 11
- 239000003814 drug Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 229940079593 drug Drugs 0.000 description 5
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001965 increasing effect Effects 0.000 description 3
- 238000012502 risk assessment Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000005713 exacerbation Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 229920002521 macromolecule Polymers 0.000 description 1
- 239000012567 medical material Substances 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 239000002547 new drug Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
This application discloses a kind of methods and Related product based on more evaluative dimensions evaluation hospital, and this method is applied to electronic equipment, this method comprises: obtaining the medical data of any one hospital from medical data base；Obtain preset multiple evaluative dimensions, multiple risk indexs of the hospital on the multiple evaluative dimension are determined according to the medical data, wherein, each the corresponding risk index of default dimension, the risk index are used to indicate value-at-risk of the hospital in medical expense；Weighted value is distributed to the multiple evaluative dimension, the multiple risk index is weighted according to the weighted value, obtains the ultimate risk index of the hospital.The embodiment of the present application increases the mode of evaluation hospital, improves the accuracy of Hospital evaluation.
Description
Technical field
This application involves electronic technology fields, and in particular to a kind of method and correlation based on more evaluative dimensions evaluation hospital
Product.
Background technique
As national basic medical security system is constantly reinforced and the continuous improvement of economic level, insurant life
Improve, people increasingly pay close attention to health, and focus is gradually transferred to and is seen a doctor, in terms of health, as people pay close attention to coke
The transfer of point causes the medical expense data of hospital in continual growth, increases there are subjective reason and odjective cause,
Wherein, odjective cause includes: the improvement of living standard, and the health examination of the enhancing of health perception, system attracts people's attention；
The exacerbation of aging of population, the speed for causing patient to increase are accelerated；High-tech Medical Devices, macromolecule medical material, new drug, spy
The development application of medicine etc. increases medical expense data.Subjective reason: hospital, medical staff abuse in order to which number one appearance is some
Medicine, arbitrary imposition of fees, the random means such as inspection of applying add additional medical expense data.Currently, the reason of causing medical expense data to increase
It is numerous, and the growth trend of Different hospital medical expense data is different.
But at present to hospital medical expense carry out risk assessment mode is single, accuracy is low, easily hospital is produced
Raw erroneous judgement.It is urgent to provide the methods that a kind of medical expense data of various dimensions evaluation hospital increase.
Summary of the invention
The embodiment of the present application provides a kind of method and Related product based on more evaluative dimensions evaluation hospital, to from more
A evaluative dimension evaluates hospital, improves the accuracy of Hospital evaluation.
In a first aspect, the embodiment of the present application provides a kind of method based on more evaluative dimensions evaluation hospital, the method packet
It includes:
The medical data of any one hospital is obtained from medical data base；
Preset multiple evaluative dimensions are obtained, determine the hospital in the multiple evaluative dimension according to the medical data
On multiple risk indexs, wherein each corresponding risk index of default dimension, the risk index is for indicating the doctor
Value-at-risk of the institute in medical expense；
Weighted value is distributed to the multiple evaluative dimension, the multiple risk index is added according to the weighted value
Power, obtains the ultimate risk index of the hospital.
Second aspect, the embodiment of the present application provide a kind of electronic equipment based on more evaluative dimensions evaluation hospital, the electricity
Sub- equipment includes:
Acquiring unit, for obtaining the medical data of any one hospital from medical data base；
Determination unit determines the hospital in institute for obtaining preset multiple evaluative dimensions according to the medical data
State multiple risk indexs on multiple evaluative dimensions, wherein each corresponding risk index of default dimension, the risk index
For indicating value-at-risk of the hospital in medical expense；
Computing unit, for distributing weighted value to the multiple evaluative dimension, according to the weighted value to the multiple wind
Dangerous index is weighted, and obtains the ultimate risk index of the hospital.
The third aspect, a kind of electronic equipment, which is characterized in that including processor, memory, communication interface, the storage
Device is stored with computer program, and the computer program is executed in the method realized as described in relation to the first aspect by the processor
The instruction of step.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are used to store computer program,
Wherein, the computer program is executed by processor, to realize method 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 obtaining the medical data of hospital in the embodiment of the present application, determining the doctor according to the medical data
Multiple risk indexs of the institute on multiple evaluative dimensions, and weighted value is distributed to multiple evaluative dimension, obtain the hospital most
Whole risk index determines risk index of the hospital in medical expense, and therefore, the risk on comprehensive multiple evaluative dimensions refers to
Number, improves the accuracy to Hospital evaluation.
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 a kind of flow diagram of method that hospital is evaluated based on more evaluative dimensions provided by the embodiments of the present application；
Fig. 2 is a kind of flow diagram of method that hospital is evaluated based on expense contribution degree provided by the embodiments of the present application；
Fig. 3 is a kind of flow diagram of method that hospital is evaluated based on risk indicator provided by the embodiments of the present application；
Fig. 3 A is a kind of signal for selecting submatrix to obtain assembled scheme based on sliding window frame provided by the embodiments of the present application
Figure；
Fig. 4 is that a kind of process of method for being overspend risk assessment hospital based on medical insurance fund provided by the embodiments of the present application is shown
It is intended to；
Fig. 5 is a kind of flow diagram of the method based on differentiation metrics evaluation hospital provided by the embodiments of the present application；
A kind of Fig. 5 A random index provided by the embodiments of the present application shows with the part mapping relationship of pairs of matrix
It is intended to；
Fig. 6 is a kind of structural representation of electronic equipment that hospital is evaluated based on more evaluative dimensions provided by the embodiments of the present application
Figure；
Fig. 7 is a kind of functional unit of electronic equipment based on more evaluative dimensions evaluation hospital provided by the embodiments of the present application
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..
Referring initially to Fig. 1, Fig. 1 is a kind of method that hospital is evaluated based on more evaluative dimensions provided by the embodiments of the present application
Flow diagram, this method are applied to electronic equipment, and this method includes the content as shown in step S101~S103:
Step S101, the medical data of any one hospital is obtained from medical data base.
Wherein, the medical data includes: that medical expense, emergency treatment number, medical insurance policies, the bedspace of hospital, population are old
Age trend, the Directory Scope of medical insurance, medical insurance fund revenue and expenditure, medical number data, drug expenditure data and other to medical treatment
The growth of expense has contributive data, etc..
Optionally, the medical data that any one hospital is obtained from medical data base specifically includes: using sampling technique
It from the medical data sampled in the medical data base in preset time period, specifically includes: being touched in the task of medical server
Pre-set sampling interval and sampling duration in device are sent out, and the sampling interval and sampling duration are stored to medical server
Configuration file in, when starting task trigger acquisition medical data, parse the configuration file, read the sampling interval
With sampling duration, control data collector is adopted from the medical data base according to the sampling interval and sampling duration
Sample obtains medical data.It is understood that adjustment sampling interval and sampling duration are to adjust the medical data got
Quantity.
Wherein, the preset time period can for 10 days, 20 days, 30 days or other.
Step S102, preset multiple evaluative dimensions are obtained, determine the hospital described more according to the medical data
Multiple risk indexs on a evaluative dimension, wherein each the corresponding risk index of default dimension, the risk index are used for
Indicate value-at-risk of the hospital in medical expense.
Optionally, the multiple evaluative dimension specifically includes: medical expense increase contribution degree dimension, risk indicator dimension,
Medical insurance fund overspends Risk Dimensions, differentiation index dimension and other evaluations.
Below will be to being illustrated for aforementioned four evaluative dimension, but it is not limited to other evaluative dimensions, art technology
Other evaluative dimensions that personnel are contemplated that under the premise of not paying labour belong to the protection scope of the application.
Referring to Fig.2, Fig. 2 is a kind of process of method for evaluating hospital based on expense contribution degree provided by the embodiments of the present application
Schematic diagram, as shown in Fig. 2, when the multiple evaluative dimension includes that medical expense increases contribution degree dimension, it is described according to
Medical data determine multiple risk indexs of the hospital on the multiple evaluative dimension specifically includes the following steps:
Step S101a, obtain preset multiple driving factors, the driving factors be it is relevant to medical expense growth because
Element.
Optionally, the mapping table of hospital and driving factors is pre-established, is obtained based on table lookup operation preset multiple
Driving factors, wherein the driving factors pre-established are related to evaluation object, can set for different evaluation objects different
Driving factors.For example, evaluation object be hospital, driving factors can be set as the growth rate of patient, the reimbursement ratio of medical insurance,
Aging of population trend, the Directory Scope of medical insurance, bedspace in hospital etc. when evaluation object is the cause of disease, can will drive for another example
Factor is set as the medical R & D Cost for the cause of disease, surgery cost when curing the cause of disease, the shield to the patient of the cause of disease
Reason expense, etc..
Step S102a, multiple tributes that the multiple driving factors increase medical expense are determined according to the medical data
Degree of offering.
Optionally, it determines that the multiple driving factors specifically include multiple contribution degrees that medical expense increases: obtaining institute
State the increment of medical expense in medical data；According to each driving in the multiple driving factors of the medical data acquisition because
The variable quantity of element；Determine that the ratio of the variable quantity of each driving factors and the increment of the medical expense is described each
The contribution degree that driving factors increase the medical expense, determine respectively the variable quantities of the multiple default driving factors with it is described
The ratio of the increment of medical expense obtains the multiple contribution degrees increased to medical expense；Alternatively, the medical data is divided
For several time windows, the variation of the increment and each driving factors of the medical expense in each time window is determined
Amount, so that it is determined that the contribution degree that each driving factors increase medical expense under each time window, by each driving factors
The contribution degree that the average value of contribution degree under several time windows increases medical expense as the driving factors, thus
Obtain multiple driving factors multiple contribution degrees that medical expense is increased.
Step S103a, the target drives factor in the multiple driving factors is determined according to the multiple contribution degree.
Optionally, by multiple contribution degrees and contribution degree threshold value comparison, obtain contribution degree be greater than the driving of contribution degree threshold value because
Element label is factor.
Wherein, contribution degree threshold value can be 10%, 20%, 50%, 70%, 80% or other values.
Optionally, multiple contribution degrees that the multiple driving factors increase medical expense are determined according to the medical data
It may include: the medical expense data obtained in medical data, be when curing observed value creation first with the medical expense data
Between sequence, multiple time serieses are respectively created by observed value of multiple driving factors；
Using least square method by first time sequence fit be the first curvilinear equation, multiple time series is fitted to
Multiple curvilinear equations；Multiple curvilinear equation is fitted with the first curvilinear equation respectively, determines the error of fitting in fit procedure,
Obtain multiple errors of fitting；Determine the corresponding multiple contribution degrees of multiple errors of fitting.
Optionally, multiple curvilinear equation is fitted with the first curvilinear equation respectively, fit procedure specifically includes:
Wherein, a is intermediate parameters, f (ti) be the multiple curvilinear equation in any one curvilinear equation, T is the time
The duration of sequence, f (t) are the first curvilinear equation, WiFor error of fitting corresponding with the curvilinear equation.
Wherein, the reasons why determining contribution degree based on error of fitting is: error of fitting represents multiple driving factors in time sequence
Relevance between the varied in duration trend and medical expense variation tendency of column, error of fitting is smaller, illustrates the two default
Variation tendency in duration is close, and the degree of association is high, and positive correlation trend is presented, that is, growing simultaneously or synchronizing reduces, error of fitting
It is bigger, illustrate that the variation tendency of the two differs greatly, even, when medical expense increases, driving factors are being reduced, and the two is presented one
The negatively correlated trend of kind.
Step S104a, determine that the hospital increases contribution degree dimension in medical expense according to the multiple target drives factor
The first risk index on degree.
Optionally, preset multiple dimensions of determining risk index, and each dimension pre-establish risk index with
The mapping relations of driving factors determine multiple risks of the target drives factor under multiple dimension according to the mapping relations respectively
Index refers to according to weighting the risk index under multiple dimension to the pre-assigned weighted value of multiple dimensions and obtaining the first risk
Number.
Refering to Fig. 3, Fig. 3 is that a kind of process of method that hospital is evaluated based on risk indicator provided by the embodiments of the present application is shown
It is intended to, as shown in figure 3, when the multiple evaluative dimension includes risk indicator dimension, it is described to be determined according to the medical data
Multiple risk indexs of the hospital on the multiple evaluative dimension specifically includes the following steps:
Step S101b, preset multiple risk indicators are obtained, the risk indicator is finger relevant to medical expense growth
Mark.
Wherein, the mapping table for presetting hospital and risk indicator obtains the default of the hospital based on table lookup operation
Multiple risk indicators, specifically, preset risk indicator is set according to evaluation object, i.e., for different evaluations
Object can set different risk indicators from evaluative dimension.For example, evaluation object is hospital, evaluative dimension is the payment for medical care of hospital
Used time, risk indicator can be set as the growth rate of patient, the reimbursement ratio of medical insurance, aging of population trend, medical insurance mesh
Bedspace etc. in record range, hospital.
Step S102b, the multiple risk indicator is combined according to preset rules, obtains multiple assembled schemes.
Optionally, the multiple risk indicator is combined according to preset rules to specifically include: using multiple risk indicator as
Original input data imports database, calls the database using crawler Python algorithm, and can also be called certainly with MATLAB should
Database, it should be understood that Python algorithm is exemplary illustration, does not do unique restriction, obtains the line number m and columns of input
N, of course, it is possible to which the size of line number m and columns n is arranged in the quantity according to multiple default risk indicator automatically, automatically when setting
Guarantee that m*n is more than or equal to N, is also subjected to the line number m of user's input and the size of columns n, is arranged according to the demand of user
The line number and columns of matrix call the matrix systematic function of Python, generate line number for N number of risk indicator as matrix element
Then sliding window h*h is arranged in the risk indicator matrix m*n for being n for m and columns, shown such as Fig. 3 A, utilizes sliding window h*h
Successively frame selects multiple submatrixs in risk indicator matrix, therefore the scale of the submatrix is also h*h, will be in each submatrix
All risk indicators obtain the multiple assembled scheme, the h≤m, h≤n as an assembled scheme.Wherein, sliding is utilized
Window h*h in risk indicator matrix successively select multiple submatrixs and specifically include by frame: the scale h*h of sliding window is arranged
(size) with sliding step S, (wherein, which can be user setting, can also be automatically generated, not done according to the value of the m and n
Limit), sliding window h*h is successively slided in risk indicator matrix m*n according to sliding step S, frame selects multiple submatrixs.
Step S103b, doctor needed for each risk indicator in the multiple assembled scheme is obtained in the medical data
Data are treated, which is added to the multiple assembled scheme, obtains the input data of the multiple assembled scheme, by institute
The input data for stating multiple assembled schemes is sequentially inputted to preparatory trained identification model, obtain multiple outputs as a result, according to
The multiple output result determines the objective cross scheme in the multiple assembled scheme.
Optionally, multiple risk indicators in multiple assembled schemes in each assembled scheme are obtained, medical data base is based on,
The input data set and verifying for determining each assembled scheme collect, that is, are based on medical data base, obtain and the wind in the assembled scheme
The corresponding medical data of dangerous index, obtains the input data set of the assembled scheme；Based on medical data base, the input number is obtained
According to collection to the actual influence of the medical expense of the hospital as a result, collecting the actual influence result set as verifying；Wherein, according to institute
It states multiple output results and determines that the objective cross scheme in the multiple assembled scheme specifically includes: will be in multiple assembled scheme
Each assembled scheme input data set be input to this in advance trained identification model, to obtain the assembled scheme to this
Prediction result verification result corresponding with verifying concentration is fitted, obtains by the prediction result that the medical expense of hospital increases
The input data set of multiple assembled schemes is sequentially inputted to the trained identification model in advance, obtains prediction knot by degree of fitting
Prediction result collection fitting corresponding with the verifying collection is obtained the degree of fitting of multiple assembled schemes by fruit collection, and degree of fitting is maximum
Assembled scheme corresponding to prediction result is as objective cross scheme.Or degree of fitting is greater than to the prediction result institute of degree of fitting threshold value
Corresponding assembled scheme is as objective cross scheme.
Wherein, which can be 0.6,0.7,0.75,0.8 or other values.
Further, such as corresponding degree of fitting of the multiple assembled scheme is respectively less than degree of fitting threshold value, prompts multiple combinations
Scheme is unsatisfactory for demand, re-enters the scale of sliding window or re-enters sliding step, so that frame selects submatrix again,
Multiple assembled schemes are retrieved, until obtaining the new corresponding degree of fitting of multiple assembled schemes greater than the degree of fitting threshold value
When, stop input operation, otherwise, repeats the scale of input sliding window or the operation of sliding step.
Step S104b, the risk indicator in the objective cross scheme is labeled as target risk index.
Step S105b, second risk of the hospital in risk indicator dimension is determined according to the target risk index
Index.
Optionally, preset multiple dimensions of determining risk index, and each dimension pre-establish risk index with
The mapping relations of target risk index determine that target risk index is multiple under multiple dimension according to the mapping relations respectively
Risk index obtains the second risk according to the risk index under multiple dimension is weighted to the pre-assigned weighted value of multiple dimensions
Index.
Refering to Fig. 4, Fig. 4 is a kind of method for overspending risk assessment hospital based on medical insurance fund provided by the embodiments of the present application
Flow diagram, as shown in figure 4, when the multiple evaluative dimension include medical insurance fund over-expense Risk Dimensions when, the basis
The medical data determines that multiple risk indexs of the hospital on the multiple evaluative dimension specifically include:
Step S101c, medical grade, medical insurance directory and the medical insurance policies of the hospital are obtained.
Optionally, the medical grade, medical insurance directory and medical insurance policies of the hospital are obtained from medical information bank.
Step S102c, medical number, the illness information of each medical patient in the medical data are extracted.
Step S103c, by the medical grade, medical insurance directory, medical insurance policies, medical number and each medical patient trouble
Sick information composition input data is input to preparatory trained prediction model, predicts expenditure gold of the hospital on medical insurance fund
Volume.
Optionally, by the illness of the medical grade, medical insurance directory, medical insurance policies, medical number and each medical patient
Information forms input data matrix, is input to preparatory trained prediction model, in the trained prediction model in advance
Weight matrix carry out operation (being in general convolution algorithm), by it is described in advance trained prediction model global pool
After operation, the amount paid to the hospital on medical insurance fund is obtained.
Step S104c, amount received of the hospital on medical insurance fund is obtained.
Optionally, it obtains amount received of the hospital on medical insurance fund to specifically include: obtaining the population of insurant
Structure, medical insurance policies, hospital site, wherein the population structure specifically includes: urban population quantity, people in the countryside number
Amount, medical insurance policies specifically include: the planning to the insured amount for the insured people for belonging to different population structures.Therefore the people according to hospital
Member predicts in location the quantity of insured people, predicts the hospital in medical insurance base according to population structure, hospital location, medical insurance policies
Amount received on gold.
Step S105c, over-expense wind of the hospital on medical insurance fund is determined according to the amount paid and amount received
Danger.
Optionally, the over-expense amount of money of the hospital on medical insurance fund is determined according to the amount paid and amount received,
It determines the corresponding over-expense section of the over-expense amount of money, determines that the hospital is curing with the mapping relations for overspending risk according to over-expense section
Protect the over-expense risk on fund.
Step S106c, third of the hospital on medical insurance fund over-expense Risk Dimensions is determined according to the over-expense risk
Risk index.
Optionally, preset multiple dimensions of determining risk index, and each dimension pre-establish risk index with
The mapping relations for overspending risk determine that multiple risks of the over-expense risk under multiple dimension refer to according to the mapping relations respectively
Number, obtains third risk index according to the risk index under multiple dimension is weighted to the pre-assigned weighted value of multiple dimensions.
Refering to Fig. 5, Fig. 5 is a kind of process of the method based on differentiation metrics evaluation hospital provided by the embodiments of the present application
Schematic diagram, as shown in figure 5, when the multiple evaluative dimension includes differentiation index dimension, it is described according to the medical data
Determine that multiple risk indexs of the hospital on the multiple evaluative dimension specifically include:
Step S101d, the medical data of multiple default hospitals corresponding with the hospital is obtained from medical data base.
Wherein, the multiple default hospital is that multiple hospitals under the same criteria for classifying are in the hospital, described stroke
Minute mark standard specifically includes Hospital Grade, diagnosis and treatment type, geographical location, etc., therefore the multiple default hospital is substantially and the doctor
The identical hospital of institute's type.
Step S102d, based on time series analysis method to the hospital and multiple default hospitals corresponding with the hospital
Medical data carry out difference analysis, determine the hospital at the time of having differences in medical expense data.
Optionally, based on time series analysis method to the doctor of the hospital and multiple default hospitals corresponding with the hospital
It treats data and carries out difference analysis, determine that the hospital specifically includes at the time of having differences in medical expense data: will
The medical data of the hospital and the medical data of multiple default hospitals corresponding with the hospital import database, utilize
Python algorithm transfers the database, based on Time Series Analysis Model ARIMA in Python algorithm, with medical expense data
The first time sequence of the hospital and multiple time serieses of multiple default hospitals are created for observed value；When by described first
Between each of sequence and multiple time serieses time series be averagely divided into several Time Sub-series, according to minimum two
Multiplication carries out linear fit to each Time Sub-series in each time series, obtains the matched curve of each Time Sub-series
Equation；By several Time Sub-series in each of the first time sequence and multiple time serieses time series
Several fit curve equations be iterated, obtain the first time sequence first object curvilinear equation and it is multiple when
Between sequence multiple target fit curve equations；To the first object curvilinear equation and multiple target fit curve equations into
Row feature extraction obtains several corresponding characteristic values of the first object curvilinear equation and multiple target fit curve equations
In several corresponding characteristic values of each aim curve equation, by several corresponding characteristic values of the first object curvilinear equation
And several corresponding characteristic values of each aim curve equation are compared one by one in multiple target fit curve equations, are determined
, there is difference for this feature value in the characteristic value of several corresponding having differences of characteristic value of the first object curvilinear equation
At the time of correspondence in the first time sequence when change labeled as the hospital in medical expense data having differences
Moment.Wherein, at the time of the having differences growth trend of the substantially described hospital in medical expense data with it is described
Multiple default hospitals are at the time of the growth trend difference in medical expense data, for example, the hospital is in t moment medical expense number
According to increasing, and the multiple default hospital is being reduced in t moment medical expense data, determines that t moment is that the hospital is curing
At the time for the treatment of having differences in cost data.
Wherein, the mesh characteristic value specifically includes: maximum value, minimum value, mean value, quantile, variance, extreme value, period.It leads
Numerical value, etc..
Step S103d, the medical data based on the hospital determines the hospital at the moment and in medical expense
Differentiation index in data, the differentiation index are to cause the hospital in medical expense data in having differences
In factor.
Optionally, it determines the hospital in the moment and the differentiation index in medical expense data: obtaining institute
State multiple non-medical cost datas in the medical data of hospital and each hospital in the multiple default hospital, wherein
It include several non-medical cost datas in the medical data of each hospital；It is created respectively using non-medical cost data as observed value
Build the hospital in terms of non-medical data multiple first time sequences and the multiple default hospital in each preset doctor
Multiple time serieses of the institute in terms of non-medical data；It will be every in the multiple first time sequence and the multiple default hospital
The time series belonged under identical non-medical data type in a default hospital is compared one by one, for example, by first time sequence
Multiple time serieses in terms of the number of going to a doctor of time series and the multiple hospital in column in terms of medical number are one by one
It compares；Determine that the hospital is inscribed when described to be had differences in multiple first time sequences in terms of non-medical cost data
The corresponding non-medical data markers of the time series are that the hospital exists in terms of medical expense data by the time series of change
The differentiation index of difference, other described hospitals are all hospitals in the remaining hospital in addition to the hospital.
For example, hospital is t1 at the time of having differences in medical expense data as described in determining, i.e., in t1
It carves variation tendency of the hospital in terms of medical expense data and the variation tendency of multiple default hospital is inconsistent, with non-medical
Cost data is the time series that observed value creates non-medical cost data, it is assumed that non-medical cost data is medical number, medicine
Product cost data, therefore the hospital and multiple default hospitals is respectively created in medical number, the time series of drug expenditure data, so
Afterwards, which is compared with multiple default hospitals in the time series of medical number one by one in the time series of medical number, really
Be scheduled on the t1 moment hospital (determines the hospital in t1 with multiple default hospitals in terms of medical number with the presence or absence of difference
Be engraved in the variation tendency in medical number and multiple default hospitals variation tendency of the t1 moment in medical number whether one
Cause), it such as has differences, the differentiation that medical number is labeled as that the hospital is caused to have differences in terms of medical expense data is referred to
Mark, similarly, by time series of the hospital on drug expenditure and time series one of multiple default hospitals on drug expenditure
One compares, and determines and whether there is difference at the t1 moment.
Step S104d, fourth risk of the hospital in differentiation index dimension is determined according to the differentiation index
Index.
Optionally, preset multiple dimensions of determining risk index, and each dimension pre-establish risk index with
The mapping relations of differentiation index determine multiple risks of the differentiation index under multiple dimension according to the mapping relations respectively
Index refers to according to weighting the risk index under multiple dimension to the pre-assigned weighted value of multiple dimensions and obtaining third risk
Number.
Step S103, weighted value is distributed to the multiple evaluative dimension, the multiple risk is referred to according to the weighted value
Number is weighted, and obtains the ultimate risk index of the hospital.
Optionally, the multiple evaluative dimension distribution weighted value is specifically included: based on medical expense information bank, determines institute
Important level of multiple evaluative dimensions in medical expense is stated, i.e., according to the data and expert's warp in medical expense information bank
It tests, predefines the important level that the multiple evaluative dimension influences medical expense, substantially determine the multiple evaluation dimension
Upper layer i-th of evaluative dimension of evaluative dimension base in degree is compared with lower layer's j-th of evaluative dimension of evaluative dimension base, to medical expense
The importance of influence, the relative weighting a of usage quantityijIt indicates, wherein aijValue be 1-9 and 1-9 inverse, specifically
Are as follows: such as aij=1, the importance that i-th of evaluative dimension and j-th of evaluative dimension influence medical expense is identical, aij=3, i-th
Than j-th evaluative dimension of a evaluative dimension is slightly important, aij=5, than j-th evaluative dimension of i-th of evaluative dimension is important, aij=
7, important more, a of than j-th evaluative dimension of i-th of evaluative dimensionij=9, than j-th evaluative dimension of i-th of evaluative dimension takes
It is just opposite when reciprocal；The pairwise comparison matrix that the multiple evaluative dimension is constructed according to the important level, is built into pair
Comparator matrix specifically includes: the relative weight value of the multiple evaluative dimension arranged according to sequence from small to large, then, benefit
With each relative weight value successively divided by the element of the first row, the pairwise comparison matrix is obtained；To the pairwise comparison matrix into
Row consistency detection, such as by consistency detection, obtain feature corresponding to the maximum eigenvalue of the pairwise comparison matrix to
Amount is not such as adjusted important level of the multiple evaluative dimension in medical expense, is retrieved by consistency detection
Pairwise comparison matrix carries out consistency detection to the pairwise comparison matrix retrieved, such as by consistency detection, then to described
Feature vector corresponding to maximum eigenvalue is normalized, and obtains the weight vector of the multiple evaluative dimension, wherein institute
State the weighted value that the weight coefficient in weight vector is the multiple evaluative dimension.
Wherein, consistency detection is carried out to pairwise comparison matrix to specifically include:
Wherein, CI is the coincident indicator of pairs of matrix, λmaxFor the maximum eigenvalue of pairs of matrix, n is pairs of matrix
Dimension.Therefore when carrying out consistency detection to pairs of matrix, it is calculated as the maximum eigenvalue to matrix using MATLAB, according to maximum
Characteristic value determines the coincident indicator CI of the pairs of matrix, when such as the CI is less than consistency threshold value, determines the pairs of matrix
Pass through consistency detection, wherein coincident indicator CI is bigger, and the inconsistency of pairs of matrix is higher.
Wherein, the consistency threshold value can be 0.01,0.02,0.1 or other values.
Further, after the coincident indicator CI for getting the pairs of matrix, according to random index at
The random index RI that the pairs of matrix is obtained to the mapping table of matrix determines the coincident indicator CI and institute
State the ratio of random index RI, i.e. consistency ratio CR, such as the consistency ratio CR be less than threshold value, determine it is described at
Consistency detection is passed through to matrix.In general, such as ratio determines that the pairs of matrix passes through consistency and examines less than 0.1
It surveys.Wherein, the mapping table of random index and pairs of matrix is to be obtained according to great amount of samples data, as Fig. 5 A illustrates
Show the part mapping relationship of random index Yu pairs of matrix.
Optionally, the multiple risk index is weighted according to the weighted value, obtains the final wind of the hospital
Dangerous index specifically includes: first risk index, the second risk index, third risk index and the 4th risk index are formed
Row vector, wherein each risk index in the row vector is corresponding with weight coefficient in each comfortable weight vector, by the row vector
It is multiplied and is exported as a result, being the ultimate risk index of the hospital by the output result queue with the weight vector.Due to,
Weight coefficient is the weighted value of four evaluative dimensions in weight vector, is column vector based on weight vector, therefore risk index is formed
Row vector is multiplied with weight vector and completes weighting operations, obtains the ultimate risk index of the hospital by corresponding row vector.
For example, four evaluative dimensions in the application such as are predefined to medical expense shadow in medical expense information bank
Loud relatively important grade specifically: differentiation index dimension is most important, and medical expense increases important, the risk of contribution degree dimension time
Index dimension is slightly important, and it is minimum that medical insurance fund overspends Risk Dimensions, and predefines differentiation index dimension, medical expense growth
The important level of contribution degree dimension, risk indicator dimension and medical insurance fund over-expense Risk Dimensions is followed successively by 7,5,3 and 1, therefore can structure
Build out pairs of matrix are as follows:
Its maximum eigenvalue is 4, and the corresponding feature vector of maximum eigenvalue 4 is α=[1,3,5,7]T, α is returned
After one change processing, obtaining weight vector is β=[0.0625,0.1875,0.3125,0.4375]T, CI=0, RI=0.98, CR=0
< 0.1, therefore the pairs of matrix passes through consistency detection.Therefore determine differentiation index dimension, medical expense increase contribution degree dimension,
The weighted value of risk indicator dimension and medical insurance fund over-expense Risk Dimensions is respectively 0.4375,0.3125,0.1875,0.0625,
Then by the first risk index, the second risk index, third risk index and the 4th risk index form corresponding row vector λ=
[third risk index, the second risk index, the first risk index, the 4th risk index], therefore can obtain ultimate risk index is γ *
The 4th wind of β=0.0625* third risk index+0.1875* the second risk index the first risk index of+0.3125*+0.4375*
Dangerous index.
As can be seen that in the embodiment of the present application, obtaining the medical data of hospital, determined according to the medical data in difference
Alienation index dimension, medical expense increase four of contribution degree dimension, risk indicator dimension and medical insurance fund over-expense Risk Dimensions
Risk index is then based on medical expense information bank and is allocated weight to the four dimensions, moreover, when distributing weight into
Then row consistency detection is weighted place to four risk indexs according to weight to guarantee the reasonability of the weight of distribution
Reason obtains the ultimate risk index of the hospital, therefore is handled by a weighting of four dimensions, improves to Hospital evaluation
Accuracy increases the mode to Hospital evaluation, moreover, obtaining ultimate risk index moreover, being related to four dimensions evaluation hospital
Data reference can be provided for medical system reform, improve Medical treatment system, protect public interest.
It is consistent with above-mentioned embodiment shown in FIG. 1, referring to Fig. 6, Fig. 6 is that one kind provided by the embodiments of the present application is based on
The structural schematic diagram of the electronic equipment 600 of more evaluative dimensions evaluation hospital, as shown in fig. 6, electronic equipment 600 include processor,
Memory, communication interface and one or more programs, wherein said one or multiple programs are different from said one or multiple
Application program, and said one or multiple programs are stored in above-mentioned memory, and are configured to be executed by above-mentioned processor,
Above procedure includes the instruction for executing following steps；
The medical data of any one hospital is obtained from medical data base；
Preset multiple evaluative dimensions are obtained, determine the hospital in the multiple evaluative dimension according to the medical data
On multiple risk indexs, wherein each corresponding risk index of default dimension, the risk index is for indicating the doctor
Value-at-risk of the institute in medical expense；
Weighted value is distributed to the multiple evaluative dimension, the multiple risk index is added according to the weighted value
Power, obtains the ultimate risk index of the hospital.
In a possible example, when the multiple evaluative dimension includes that medical expense increases contribution degree dimension, in root
In terms of determining multiple risk indexs of the hospital on the multiple evaluative dimension according to the medical data, in above procedure
Instruction is specifically used for executing following operation: obtaining preset multiple driving factors, the driving factors are to increase with medical expense
Relevant factor；Multiple contribution degrees that the multiple driving factors increase medical expense are determined according to the medical data；Root
The target drives factor in the multiple driving factors is determined according to the multiple contribution degree；According to the multiple target drives factor
Determine that the hospital increases the first risk index in contribution degree dimension in medical expense.
In a possible example, when the multiple evaluative dimension includes risk indicator dimension, according to the medical treatment
In terms of data determine multiple risk indexs of the hospital on the multiple evaluative dimension, the instruction in above procedure is specifically used
In executing following operation: the preset multiple risk indicators of acquisition, the risk indicator is index relevant to medical expense growth；
The multiple risk indicator is combined according to preset rules, obtains multiple assembled schemes；It is obtained in the medical data described more
The medical data is added to the multiple assembled scheme, obtained by medical data needed for each risk indicator in a assembled scheme
To the input data of the multiple assembled scheme, the input data of the multiple assembled scheme is sequentially inputted to train in advance
Identification model, obtain multiple outputs as a result, determining target in the multiple assembled scheme according to the multiple output result
Assembled scheme；Risk indicator in the objective cross scheme is labeled as target risk index；Referred to according to the target risk
Mark determines second risk index of the hospital in risk indicator dimension.
In a possible example, when the multiple evaluative dimension includes medical insurance fund over-expense Risk Dimensions, in basis
In terms of the medical data determines multiple risk indexs of the hospital on the multiple evaluative dimension, the finger in above procedure
It enables and is specifically used for executing following operation: obtaining the medical grade, medical insurance directory and medical insurance policies of the hospital；Extract the medical treatment
The illness information of medical number, each medical patient in data；By the medical grade, medical insurance directory, medical insurance policies, go to a doctor
Number and the illness information composition input data of each medical patient are input to preparatory trained prediction model, predict the doctor
Amount paid of the institute on medical insurance fund；Obtain amount received of the hospital on medical insurance fund；According to the amount paid
Over-expense risk of the hospital on medical insurance fund is determined with amount received；Determine that the hospital is curing according to the over-expense risk
Protect the third risk index on fund over-expense Risk Dimensions.
In a possible example, when the multiple evaluative dimension includes differentiation index dimension, obtained in advance described
If multiple evaluative dimensions before, the finger in above procedure is also used to execute following operation: obtaining from the medical data base
The medical data of multiple default hospitals corresponding with the hospital；Determining the hospital described more according to the medical data
In terms of multiple risk indexs on a evaluative dimension, the instruction in above procedure is specifically used for executing following operation: being based on the time
Sequence analysis carries out difference analysis to the medical data of the hospital and multiple default hospitals corresponding with the hospital, really
The fixed hospital is at the time of having differences in medical expense data；Based on the medical data of the hospital, the doctor is determined
In the moment and the differentiation index in medical expense data, the differentiation index is that the hospital is caused to cure for institute
Treat the internal factor of having differences in cost data；Determine that the hospital ties up in differentiation index according to the differentiation index
The 4th risk index on degree
Instruction in a possible example, in terms of distributing weighted value to the multiple evaluative dimension, in above procedure
Specifically for executing following operation: being based on medical expense information bank, determine weight of the multiple evaluative dimension in medical expense
Want grade；The pairwise comparison matrix of the multiple evaluative dimension is constructed according to the important level；To the pairwise comparison matrix
It carries out consistency detection and obtains feature corresponding to the maximum eigenvalue of the pairwise comparison matrix such as by consistency detection
Vector does not such as adjust important level of the multiple evaluative dimension in medical expense by consistency detection, again
To pairwise comparison matrix, consistency detection is carried out to the pairwise comparison matrix retrieved, such as by consistency detection, then to institute
It states feature vector corresponding to maximum eigenvalue to be normalized, obtains the weight vector of the multiple evaluative dimension, wherein
Weight coefficient in the weight vector is the weighted value of the multiple evaluative dimension.
In a possible example, the multiple risk index is being weighted according to the weighted value, is being obtained described
In terms of the ultimate risk index of hospital, the instruction in above procedure is specifically used for executing following operation: first risk is referred to
Number, the second risk index, third risk index and the 4th risk index form row vector, by the row vector and the weight vector
It is multiplied and is exported as a result, being the ultimate risk index of the hospital by the output result queue.
The electronic equipment based on more evaluative dimensions evaluation hospital involved in above-described embodiment is shown refering to Fig. 7, Fig. 7
A kind of 700 possible functional unit forms block diagram, and electronic equipment 700 includes acquiring unit 710, determination unit 720, calculates list
First 730, wherein；
Acquiring unit 710, for obtaining the medical data of any one hospital from medical data base；
Determination unit 720 determines that the hospital exists according to the medical data for obtaining preset multiple evaluative dimensions
Multiple risk indexs on the multiple evaluative dimension, wherein each the corresponding risk index of default dimension, the risk refer to
Number is for indicating value-at-risk of the hospital in medical expense；
Computing unit 730, for distributing weighted value to the multiple evaluative dimension, according to the weighted value to the multiple
Risk index is weighted, and obtains the ultimate risk index of the hospital.
In a possible example, when the multiple evaluative dimension includes that medical expense increases contribution degree dimension, in root
The hospital is determined in multiple risk indexs on the multiple evaluative dimension according to the medical data, and determination unit 720 has
Body is used for: obtaining preset multiple driving factors, the driving factors are factor relevant to medical expense growth；And it is used for
Multiple contribution degrees that the multiple driving factors increase medical expense are determined according to the medical data；And for according to institute
It states multiple contribution degrees and determines target drives factor in the multiple driving factors；And for according to the multiple target drives
Factor determines that the hospital increases the first risk index in contribution degree dimension in medical expense.
In a possible example, when the multiple evaluative dimension includes risk indicator dimension, according to the medical treatment
Data determine the hospital in multiple risk indexs on the multiple evaluative dimension, and determination unit 720 is specifically used for: obtaining
Preset multiple risk indicators are taken, the risk indicator is index relevant to medical expense growth；And for according to default
Rule combines the multiple risk indicator, obtains multiple assembled schemes；And it is described more for being obtained in the medical data
The medical data is added to the multiple assembled scheme, obtained by medical data needed for each risk indicator in a assembled scheme
To the input data of the multiple assembled scheme, the input data of the multiple assembled scheme is sequentially inputted to train in advance
Identification model, obtain multiple outputs as a result, determining target in the multiple assembled scheme according to the multiple output result
Assembled scheme；And for the risk indicator in the objective cross scheme to be labeled as target risk index；And it is used for root
Second risk index of the hospital in risk indicator dimension is determined according to the target risk index.
In a possible example, when the multiple evaluative dimension includes medical insurance fund over-expense Risk Dimensions, in basis
The medical data determine the hospital in multiple risk indexs on the multiple evaluative dimension, determination unit 720, specifically
For: obtain the medical grade, medical insurance directory and medical insurance policies of the hospital；And for extracting in the medical data just
Examine the illness information of number, each medical patient；And it is used for the medical grade, medical insurance directory, medical insurance policies, medical people
The illness information composition input data of several and each medical patient is input to preparatory trained prediction model, predicts the hospital
Amount paid on medical insurance fund；And for obtaining amount received of the hospital on medical insurance fund；And it is used for root
Over-expense risk of the hospital on medical insurance fund is determined according to the amount paid and amount received；And for according to described super
Branch risk determines third risk index of the hospital on medical insurance fund over-expense Risk Dimensions.
In a possible example, when the multiple evaluative dimension includes differentiation index dimension, obtained in advance described
If multiple evaluative dimensions before, acquiring unit 710, be also used to from the medical data base obtain it is corresponding with the hospital
The medical data of multiple default hospitals；Determining that the hospital is more on the multiple evaluative dimension according to the medical data
When a risk index, determination unit 720 is specifically used for: based on time series analysis method to the hospital and with the hospital pair
The medical data for the multiple default hospitals answered carries out difference analysis, determines that the hospital has differences in medical expense data
At the time of change；And for the medical data based on the hospital, determine the hospital at the moment and in medical expense
Differentiation index in data, the differentiation index are to cause the hospital in medical expense data in having differences
In factor；And for determining that fourth risk of the hospital in differentiation index dimension refers to according to the differentiation index
Number.
In a possible example, when distributing weighted value to the multiple evaluative dimension, computing unit 730 is specific to use
In: it is based on medical expense information bank, determines important level of the multiple evaluative dimension in medical expense；And it is used for basis
The important level constructs the pairwise comparison matrix of the multiple evaluative dimension；And for being carried out to the pairwise comparison matrix
Consistency detection obtains feature vector corresponding to the maximum eigenvalue of the pairwise comparison matrix such as by consistency detection,
As by consistency detection, do not adjusted important level of the multiple evaluative dimension in medical expense, retrieving into
To comparator matrix, consistency detection is carried out to the pairwise comparison matrix retrieved, such as by consistency detection, then to it is described most
Feature vector corresponding to big characteristic value is normalized, and obtains the weight vector of the multiple evaluative dimension, wherein described
Weight coefficient in weight vector is the weighted value of the multiple evaluative dimension.
In a possible example, the multiple risk index is being weighted according to the weighted value, is being obtained described
When the ultimate risk index of hospital, computing unit 730 is specifically used for: by first risk index, the second risk index,
Three risk indexs and the 4th risk index form row vector, the row vector is multiplied with the weight vector exported as a result,
It is the ultimate risk index of the hospital by the output result queue.
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
A kind of some or all of method step based on more evaluative dimensions evaluation 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 based on more evaluative dimensions evaluation 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 based on more evaluative dimensions evaluation hospital, which is characterized in that the method is applied to electronic equipment, described
Method includes:
The medical data of any one hospital is obtained from medical data base；
Preset multiple evaluative dimensions are obtained, determine the hospital on the multiple evaluative dimension according to the medical data
Multiple risk indexs, wherein each corresponding risk index of default dimension, the risk index is for indicating that the hospital exists
Value-at-risk in medical expense；
Weighted value is distributed to the multiple evaluative dimension, the multiple risk index is weighted according to the weighted value, is obtained
To the ultimate risk index of the hospital.
2. the method according to claim 1, wherein when the multiple evaluative dimension includes that medical expense increases tribute
It is described that multiple risk indexs of the hospital on the multiple evaluative dimension are determined according to the medical data when degree of offering dimension
It specifically includes:
Preset multiple driving factors are obtained, the driving factors are factor relevant to medical expense growth；
Multiple contribution degrees that the multiple driving factors increase medical expense are determined according to the medical data；
The target drives factor in the multiple driving factors is determined according to the multiple contribution degree；
Determine that the hospital increases the first risk in contribution degree dimension in medical expense according to the multiple target drives factor
Index.
3. the method according to claim 1, wherein when the multiple evaluative dimension includes risk indicator dimension
When, it is described to determine that multiple risk indexs of the hospital on the multiple evaluative dimension specifically wrap according to the medical data
It includes:
Preset multiple risk indicators are obtained, the risk indicator is index relevant to medical expense growth；
The multiple risk indicator is combined according to preset rules, obtains multiple assembled schemes；
Medical data needed for each risk indicator in the multiple assembled scheme is obtained in the medical data, by the medical treatment
Data are added to the multiple assembled scheme, obtain the input data of the multiple assembled scheme, by the multiple assembled scheme
Input data be sequentially inputted to preparatory trained identification model, obtain multiple outputs as a result, according to the multiple output knot
Fruit determines the objective cross scheme in the multiple assembled scheme；
Risk indicator in the objective cross scheme is labeled as target risk index；
Second risk index of the hospital in risk indicator dimension is determined according to the target risk index.
4. the method according to claim 1, wherein when the multiple evaluative dimension includes medical insurance fund over-expense wind
It is described to determine that multiple risk indexs of the hospital on the multiple evaluative dimension have according to the medical data when dangerous dimension
Body includes:
Obtain the medical grade, medical insurance directory and medical insurance policies of the hospital；
Extract medical number, the illness information of each medical patient in the medical data；
The medical grade, medical insurance directory, medical insurance policies, medical number and the illness information of each medical patient are formed into input
Data are input to preparatory trained prediction model, predict amount paid of the hospital on medical insurance fund；
Obtain amount received of the hospital on medical insurance fund；
Over-expense risk of the hospital on medical insurance fund is determined according to the amount paid and amount received；
Third risk index of the hospital on medical insurance fund over-expense Risk Dimensions is determined according to the over-expense risk.
5. the method according to claim 1, wherein when the multiple evaluative dimension includes differentiation index dimension
When, before the preset multiple evaluative dimensions of acquisition, the method also includes:
The medical data of multiple default hospitals corresponding with the hospital is obtained from the medical data base；
It is described to determine that multiple risk indexs of the hospital on the multiple evaluative dimension specifically wrap according to the medical data
It includes:
It is carried out based on medical data of the time series analysis method to the hospital and multiple default hospitals corresponding with the hospital
Difference analysis determines the hospital at the time of having differences in medical expense data；
Based on the medical data of the hospital, determine the hospital in the moment and the differentiation in medical expense data
Index, the differentiation index are to cause the internal factor of the hospital having differences in medical expense data；
Fourth risk index of the hospital in differentiation index dimension is determined according to the differentiation index.
6. method according to claim 1-5, which is characterized in that described distribute the multiple evaluative dimension is weighed
Weight values specifically include:
Based on medical expense information bank, important level of the multiple evaluative dimension in medical expense is determined；
The pairwise comparison matrix of the multiple evaluative dimension is constructed according to the important level；
Consistency detection is carried out to the pairwise comparison matrix and obtains the pairwise comparison matrix such as by consistency detection
Feature vector corresponding to maximum eigenvalue does not such as adjust the multiple evaluative dimension in medical treatment by consistency detection
Important level in expense, retrieves pairwise comparison matrix, carries out consistency detection to the pairwise comparison matrix retrieved,
Such as by consistency detection, then feature vector corresponding to the maximum eigenvalue is normalized, is obtained described more
The weight vector of a evaluative dimension, wherein the weight coefficient in the weight vector is the weighted value of the multiple evaluative dimension.
7. according to the method described in claim 6, it is characterized in that, it is described according to the weighted value to the multiple risk index
It is weighted, the ultimate risk index for obtaining the hospital specifically includes:
First risk index, the second risk index, third risk index and the 4th risk index are formed into row vector, by institute
State row vector be multiplied with the weight vector exported as a result, by it is described output result queue be the hospital ultimate risk refer to
Number.
8. a kind of electronic equipment based on more evaluative dimensions evaluation hospital, which is characterized in that the electronic equipment includes:
Acquiring unit, for obtaining the medical data of any one hospital from medical data base；
Determination unit determines the hospital described more for obtaining preset multiple evaluative dimensions according to the medical data
Multiple risk indexs on a evaluative dimension, wherein each the corresponding risk index of default dimension, the risk index are used for
Indicate value-at-risk of the hospital in medical expense；
Computing unit refers to the multiple risk according to the weighted value for distributing weighted value to the multiple evaluative dimension
Number is weighted, and obtains the ultimate risk index of the hospital.
9. a kind of electronic equipment, which is characterized in that including processor, memory, communication interface, the memory is stored with calculating
Machine program, the computer program are executed by the processor and are realized such as any one of claim 1-7 method.
10. a kind of computer readable storage medium, which is characterized in that it is used to store computer program, wherein the computer
Program is executed by processor, to realize the method according to claim 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811527749.6A CN109767067A (en) | 2018-12-13 | 2018-12-13 | Method and Related product based on more evaluative dimensions evaluation hospital |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811527749.6A CN109767067A (en) | 2018-12-13 | 2018-12-13 | Method and Related product based on more evaluative dimensions evaluation hospital |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109767067A true CN109767067A (en) | 2019-05-17 |
Family
ID=66450529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811527749.6A Pending CN109767067A (en) | 2018-12-13 | 2018-12-13 | Method and Related product based on more evaluative dimensions evaluation hospital |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109767067A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105043A (en) * | 2019-12-19 | 2020-05-05 | 浙江邦盛科技有限公司 | Method for implementing banking case and operation risk prevention and control based on index dimension |
| CN111985837A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Risk analysis method, device and equipment based on hierarchical clustering and storage medium |
| CN111986792A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Medical institution scoring method, device, equipment and storage medium |
| CN112036749A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying risk user based on medical data and computer equipment |
| CN112100270A (en) * | 2020-08-12 | 2020-12-18 | 北京国电通网络技术有限公司 | Information-based examination data mining and analyzing method and device, electronic equipment and medium |
-
2018
- 2018-12-13 CN CN201811527749.6A patent/CN109767067A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111105043A (en) * | 2019-12-19 | 2020-05-05 | 浙江邦盛科技有限公司 | Method for implementing banking case and operation risk prevention and control based on index dimension |
| CN111105043B (en) * | 2019-12-19 | 2023-09-05 | 浙江邦盛科技股份有限公司 | Method for implementing banking case and operation risk prevention and control based on index dimension |
| CN112100270A (en) * | 2020-08-12 | 2020-12-18 | 北京国电通网络技术有限公司 | Information-based examination data mining and analyzing method and device, electronic equipment and medium |
| CN111985837A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Risk analysis method, device and equipment based on hierarchical clustering and storage medium |
| CN111986792A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Medical institution scoring method, device, equipment and storage medium |
| CN112036749A (en) * | 2020-08-31 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Method and device for identifying risk user based on medical data and computer equipment |
| CN111986792B (en) * | 2020-08-31 | 2024-04-05 | 平安医疗健康管理股份有限公司 | Medical institution scoring method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767067A (en) | Method and Related product based on more evaluative dimensions evaluation hospital | |
| Kaya Samut et al. | Analysis of the efficiency determinants of health systems in OECD countries by DEA and panel tobit | |
| CA2849313C (en) | Method for generating healthcare-related validated prediction models from multiple sources | |
| US20190267141A1 (en) | Patient readmission prediciton tool | |
| Hagar et al. | Survival analysis with electronic health record data: Experiments with chronic kidney disease | |
| US20090326976A1 (en) | Estimating healthcare outcomes for individuals | |
| Hosseini et al. | Surgical duration estimation via data mining and predictive modeling: a case study | |
| EP1573624A2 (en) | Systems and methods for automated extraction and processing of billing information in patient records | |
| CN102246197A (en) | Automated management of medical data using expert knowledge and applied complexity science for risk assessment and diagnoses | |
| US20180211727A1 (en) | Automated Evidence Based Identification of Medical Conditions and Evaluation of Health and Financial Benefits Of Health Management Intervention Programs | |
| CN106599553A (en) | Disease early-warning method and device | |
| CN109785944A (en) | Hospital evaluation method and Related product based on data analysis | |
| CN102405473A (en) | A point-of-care enactive medical system and method | |
| CN109767830A (en) | Hospital evaluation method and Related product based on data analysis | |
| Jian et al. | Performance evaluation of inpatient service in Beijing: a horizontal comparison with risk adjustment based on Diagnosis Related Groups | |
| CN109784645A (en) | A kind of hospital department performance arrangement method and device | |
| CN113570162B (en) | Inpatient cost prediction method and device based on artificial intelligence and computer equipment | |
| CN109460942A (en) | Method and Related product based on data assay hospital | |
| CN113724878B (en) | Medical risk information pushing method and device based on machine learning | |
| Folino et al. | A recommendation engine for disease prediction | |
| Einzinger et al. | The GAP-DRG model: Simulation of outpatient care for comparison of different reimbursement schemes | |
| US20170091410A1 (en) | Predicting personalized risk of preventable healthcare events | |
| Ieva et al. | Mining administrative health databases for epidemiological purposes: a case study on acute myocardial infarctions diagnoses | |
| CN116543917A (en) | Information mining method for heterogeneous time sequence data | |
| Chen et al. | Predicting sequenced dental treatment plans from electronic dental records using deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190517 |
|
| RJ01 | Rejection of invention patent application after publication |