CN109948806A - Decision model optimization method, device, storage medium and equipment - Google Patents
Decision model optimization method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN109948806A CN109948806A CN201910241936.6A CN201910241936A CN109948806A CN 109948806 A CN109948806 A CN 109948806A CN 201910241936 A CN201910241936 A CN 201910241936A CN 109948806 A CN109948806 A CN 109948806A
- Authority
- CN
- China
- Prior art keywords
- decision
- information
- decision information
- characteristics data
- medical characteristics
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 88
- TVZRAEYQIKYCPH-UHFFFAOYSA-N 3-(trimethylsilyl)propane-1-sulfonic acid Chemical compound C[Si](C)(C)CCCS(O)(=O)=O TVZRAEYQIKYCPH-UHFFFAOYSA-N 0.000 claims description 118
- 238000012360 testing method Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 210000001503 joint Anatomy 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 18
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 52
- 201000010099 disease Diseases 0.000 description 51
- 238000012549 training Methods 0.000 description 17
- 206010009944 Colon cancer Diseases 0.000 description 8
- 208000001333 Colorectal Neoplasms Diseases 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 239000000203 mixture Substances 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- YXTKHLHCVFUPPT-YYFJYKOTSA-N (2s)-2-[[4-[(2-amino-5-formyl-4-oxo-1,6,7,8-tetrahydropteridin-6-yl)methylamino]benzoyl]amino]pentanedioic acid;(1r,2r)-1,2-dimethanidylcyclohexane;5-fluoro-1h-pyrimidine-2,4-dione;oxalic acid;platinum(2+) Chemical compound [Pt+2].OC(=O)C(O)=O.[CH2-][C@@H]1CCCC[C@H]1[CH2-].FC1=CNC(=O)NC1=O.C1NC=2NC(N)=NC(=O)C=2N(C=O)C1CNC1=CC=C(C(=O)N[C@@H](CCC(O)=O)C(O)=O)C=C1 YXTKHLHCVFUPPT-YYFJYKOTSA-N 0.000 description 3
- GAGWJHPBXLXJQN-UORFTKCHSA-N Capecitabine Chemical compound C1=C(F)C(NC(=O)OCCCCC)=NC(=O)N1[C@H]1[C@H](O)[C@H](O)[C@@H](C)O1 GAGWJHPBXLXJQN-UORFTKCHSA-N 0.000 description 3
- GAGWJHPBXLXJQN-UHFFFAOYSA-N Capecitabine Natural products C1=C(F)C(NC(=O)OCCCCC)=NC(=O)N1C1C(O)C(O)C(C)O1 GAGWJHPBXLXJQN-UHFFFAOYSA-N 0.000 description 3
- 229960004117 capecitabine Drugs 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- GHASVSINZRGABV-UHFFFAOYSA-N Fluorouracil Chemical compound FC1=CNC(=O)NC1=O GHASVSINZRGABV-UHFFFAOYSA-N 0.000 description 2
- ZSTCHQOKNUXHLZ-PIRIXANTSA-L [(1r,2r)-2-azanidylcyclohexyl]azanide;oxalate;pentyl n-[1-[(2r,3r,4s,5r)-3,4-dihydroxy-5-methyloxolan-2-yl]-5-fluoro-2-oxopyrimidin-4-yl]carbamate;platinum(4+) Chemical compound [Pt+4].[O-]C(=O)C([O-])=O.[NH-][C@@H]1CCCC[C@H]1[NH-].C1=C(F)C(NC(=O)OCCCCC)=NC(=O)N1[C@H]1[C@H](O)[C@H](O)[C@@H](C)O1 ZSTCHQOKNUXHLZ-PIRIXANTSA-L 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 229960002949 fluorouracil Drugs 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- DWAFYCQODLXJNR-BNTLRKBRSA-L oxaliplatin Chemical compound O1C(=O)C(=O)O[Pt]11N[C@@H]2CCCC[C@H]2N1 DWAFYCQODLXJNR-BNTLRKBRSA-L 0.000 description 2
- 229960001756 oxaliplatin Drugs 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- PXGOKWXKJXAPGV-UHFFFAOYSA-N Fluorine Chemical compound FF PXGOKWXKJXAPGV-UHFFFAOYSA-N 0.000 description 1
- CZPWVGJYEJSRLH-UHFFFAOYSA-N Pyrimidine Chemical compound C1=CN=CN=C1 CZPWVGJYEJSRLH-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 229960001921 calcium levofolinate Drugs 0.000 description 1
- KVUAALJSMIVURS-QNTKWALQSA-L calcium;(2s)-2-[[4-[[(6s)-2-amino-5-formyl-4-oxo-1,6,7,8-tetrahydropteridin-6-yl]methylamino]benzoyl]amino]pentanedioate Chemical compound [Ca+2].C([C@@H]1N(C=O)C=2C(=O)N=C(NC=2NC1)N)NC1=CC=C(C(=O)N[C@@H](CCC([O-])=O)C([O-])=O)C=C1 KVUAALJSMIVURS-QNTKWALQSA-L 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 239000011737 fluorine Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 210000000664 rectum Anatomy 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000009394 selective breeding Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Abstract
This disclosure relates to data processing field, a kind of decision model optimization method, device, storage medium and equipment are provided.The described method includes: receiving medical characteristics data, and the first decision information corresponding with the medical characteristics data is determined according to decision model;First decision information is sent to Multidisciplinary Cooperation system;And the second decision information that Multidisciplinary Cooperation system is sent is received, and optimize to the decision model according to the medical characteristics data and the second decision information;Wherein, the second decision information is determined according to the medical characteristics data and the first decision information.The disclosure can provide accurate decision information to the medical characteristics data received, and be optimized by decision information to decision model, and the decision model optimization method can be made to have higher accuracy.
Description
Technical field
This disclosure relates to data processing field, and in particular to a kind of decision model optimization method, decision model optimization device,
Computer readable storage medium and equipment.
Background technique
With the development of big data technology, obtained extensively based on the decision support technique of Data Analysis Services in various fields
General application.
DSS is analyzed and processed data information using knowledge base logic rules and the relevant technologies, for work
Personnel provide decision assistant and support.In the prior art, the mode that DSS is analyzed and processed data information are as follows:
Data information to be processed is obtained by man-machine interactive interface, by inference machine according to knowledge base logic rules to the data information
It is analyzed and processed, obtains decision support scheme.But in practical applications due to the limitation and data of knowledge base logic rules
The complexity of information, complicated and changeable for decision process and professional more demanding data information, existing technology are difficult to mention
For accurately and effectively decision support scheme.
Therefore, it is necessary to a kind of decision model optimization method and device be provided, to solve decision support system in the prior art
The low problem of decision accuracy rate of uniting.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of decision model optimization method, device, storage medium and equipment, and then at least
Overcome the problems, such as that DSS accuracy rate present in the relevant technologies is low to a certain extent.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of decision model optimization method is provided, comprising:
Medical characteristics data are received, and determine that the first decision corresponding with the medical characteristics data is believed according to decision model
Breath;
First decision information is sent to Multidisciplinary Cooperation system;And
Receive the second decision information that the Multidisciplinary Cooperation system is sent, and according to medical characteristics data and described
Second decision information optimizes the decision model;Wherein, second decision information is according to the medical characteristics data
It is determined with first decision information.
In one embodiment of the present disclosure, it is described according to the medical characteristics data and second decision information to institute
It states decision model and optimizes and include:
Data set is established according to the medical characteristics data and second decision information;And
The decision model is trained using the data set;Wherein, the medical characteristics data are determined as described
The input signal of plan model, output signal of second decision information as the decision model.
In one embodiment of the present disclosure, described to be established according to the medical characteristics data and second decision information
Data set includes:
Judge whether the medical characteristics data are continuous characteristic value;
If the medical characteristics data are continuous characteristic value, sliding-model control is carried out to the medical characteristics data, is obtained
To Discrete Eigenvalue;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
In one embodiment of the present disclosure, corresponding with the medical characteristics data according to decision model determination described
Before first decision information, further includes:
According to medical characteristics data pre-stored in database and decision information to the archetype based on machine learning
Training, obtains the decision model.
In one embodiment of the present disclosure, the archetype includes Bayes model, decision-tree model, logistic regression
One of model, SVM model and neural network model are a variety of.
In one embodiment of the present disclosure, in second decision information for receiving the Multidisciplinary Cooperation system and sending
Before, further includes:
The medical characteristics data are sent to the Multidisciplinary Cooperation system.
In one embodiment of the present disclosure, which is characterized in that described determining special with the medical treatment according to decision model
Before corresponding first decision information of sign data, further includes:
The decision support request that user sends is received, according to medical characteristics data described in the decision support request.
According to another aspect of the present disclosure, a kind of decision model optimization method is provided, comprising:
Receive the first decision information that medical characteristics data and DSS are sent;Wherein, the first decision letter
Breath is determined according to decision model and the medical characteristics data;
The second decision information is determined according to the medical characteristics data and first decision information;
Second decision information is sent to the DSS, for according to the medical characteristics data and institute
The second decision information is stated to optimize the decision model.
It is in one embodiment of the present disclosure, described that second decision information is sent to the DSS,
For being optimized according to the medical characteristics data and second decision information to the decision model, comprising:
Second decision information is sent to the DSS;
Data set is established according to the medical characteristics data and second decision information using the DSS;
And
The decision model is trained according to the data set using the DSS;Wherein, the doctor
Input signal of the characteristic as the decision model is treated, second decision information is believed as the output of the decision model
Number.
In one embodiment of the present disclosure, it is described using the DSS according to the medical characteristics data with
Second decision information establishes data set and includes:
Judge whether the medical characteristics data are continuous characteristic value by the DSS;
If the medical characteristics data are continuous characteristic value, sliding-model control is carried out to the medical characteristics data, is obtained
To Discrete Eigenvalue;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
In one embodiment of the present disclosure, the decision model optimization method further include:
The decision support request that user sends is received, according to medical characteristics data described in the decision support request.
According to another aspect of the present disclosure, a kind of decision model optimization method is provided, comprising:
Receive at least one decision information pair;Wherein, each decision information is to including the first decision information and the second decision
Information, first decision information is determined according to decision model preset in medical characteristics data and DSS, described
Second decision information is determined by Multidisciplinary Cooperation system according to the medical characteristics data and first decision information;
Detect the decision information that at least one described first decision information of decision information centering is different from the second decision information
It is right;
The decision information that will test to being sent to the DSS, for according to the medical characteristics data and
Second decision information of decision information centering optimizes the decision model.
In one embodiment of the present disclosure, the decision information that will test is to being sent to the decision support system
System, for being optimized according to the medical characteristics data and second decision information to the decision model, comprising:
The decision information that will test is to being sent to the DSS;
Data set is established according to the medical characteristics data and second decision information using the DSS;
And
The decision model is trained according to the data set using the DSS;Wherein, the doctor
Input signal of the characteristic as the decision model is treated, second decision information is believed as the output of the decision model
Number.
In one embodiment of the present disclosure, it is described using the DSS according to the medical characteristics data with
Second decision information establishes data set and includes:
Judge whether the medical characteristics data are continuous characteristic value by the DSS;
If the medical characteristics data are continuous characteristic value, sliding-model control is carried out to the medical characteristics data, is obtained
To Discrete Eigenvalue;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
According to another aspect of the present disclosure, a kind of decision model optimization method is provided, comprising:
DSS receives medical characteristics data, and corresponding with the medical characteristics data according to decision model determination
The first decision information;
First decision information is sent to Multidisciplinary Cooperation system by the DSS;
The Multidisciplinary Cooperation system determines the second decision according to first decision information and the medical characteristics data
Information;
First decision information is sent to database and the Multidisciplinary Cooperation system by the DSS
Second decision information is sent to the database;
When the database detection to first decision information and second decision information be not identical, by described the
Two decision informations are sent to the DSS;
The DSS receives the second decision information that the database is sent, and according to the medical characteristics number
The decision model is optimized according to second decision information.
According to another aspect of the present disclosure, a kind of decision model optimization device is provided, comprising:
Data determining module, for receiving medical characteristics data, and according to decision model determination and the medical characteristics number
According to corresponding first decision information;
Information sending module, for first decision information to be sent to Multidisciplinary Cooperation system;And
Model optimization module, the second decision information sent for receiving the Multidisciplinary Cooperation system, and according to described
Medical characteristics data and second decision information optimize the decision model;Wherein, the second decision information root
It is determined according to the medical characteristics data and first decision information.
According to another aspect of the present disclosure, a kind of decision model optimization device is provided, comprising:
Information receiving module, the first decision information sent for receiving medical characteristics data and DSS;Its
In, first decision information is determined according to decision model and the medical characteristics data;
Information determination module, for determining that the second decision is believed according to the medical characteristics data and first decision information
Breath;
Information sending module, for second decision information to be sent to the DSS, according to
Medical characteristics data and second decision information optimize the decision model.
According to another aspect of the present disclosure, a kind of decision model optimization device is provided, comprising:
Information butt joint receives module, for receiving at least one decision information pair;Wherein, each decision information is to including
First decision information and the second decision information, first decision information is according to pre- in medical characteristics data and DSS
If decision model determine that second decision information is by Multidisciplinary Cooperation system according to the medical characteristics data and described the
One decision information determines;
Information is to detection module.It is different from second for detecting at least one described first decision information of decision information centering
The decision information pair of decision information;
Information is to sending module, and the decision information for will test is to the DSS is sent to, with basis
The medical characteristics data and second decision information of decision information centering optimize the decision model.
According to another aspect of the present disclosure, a kind of decision model optimization system is provided, comprising: DSS, more
Section's cooperative system and database;
The DSS is for executing following steps:
Medical characteristics data are received, and determine that the first decision corresponding with the medical characteristics data is believed according to decision model
Breath;
First decision information is sent to the Multidisciplinary Cooperation system;
First decision information is sent to the database;And
The second decision information that the database is sent is received, and according to the medical characteristics data and second decision
Information optimizes the decision model;
The Multidisciplinary Cooperation system is for executing following steps:
Receive first decision information and the medical characteristics data;
The second decision information is determined according to first decision information and the medical characteristics data;And
Second decision information is sent to database;
The database is for executing following steps:
Receive the first decision information that the DSS the is sent and Multidisciplinary Cooperation system is sent second
Decision information;And
When detecting that first decision information and second decision information be not identical, by second decision information
It is sent to the DSS.
According to another aspect of the present disclosure, a kind of computer readable storage medium is provided, computer program is stored thereon with,
The program realizes any of the above-described decision model optimization method when being executed by processor.
According to the another further aspect of the disclosure, a kind of equipment is provided, the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes any of the above-described decision model optimization method.
Compared with prior art, the disclosure at least have it is following difference and the utility model has the advantages that
The disclosure provides a kind of decision model optimization method, this method by two stage decision system to genius morbi data into
Row analysis processing, determines final decision support data, and the decision support data is used for the decision model in decision system
Type optimizes, to realize more accurate decision-making results.On the one hand, pass through pair of DSS and Multidisciplinary Cooperation system
Layer decision-making mode, can effectively reduce the decision error of DSS, improve the accuracy of complex disease decision, it is ensured that suffer from
Person can obtain treatment promptly and accurately;On the other hand, final decision scheme is being determined by Multidisciplinary Cooperation system every time
Afterwards, final decision scheme is back to DSS to optimize decision model, makes it have higher accuracy.Again
On the one hand, by the connected applications of DSS and Multidisciplinary Cooperation system, existing Multidisciplinary Cooperation is efficiently solved
It is difficult to quick obtaining patient disease information in system, and the patient disease before meeting can not be carried out according to disease customized information
The problem of decision scheme saves after finish message and meeting.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is the one of the disclosure
A little embodiments for those of ordinary skill in the art without creative efforts, can also be according to these
Attached drawing obtains other attached drawings.In the accompanying drawings:
Fig. 1 illustrates a kind of flow chart of decision model optimization method in disclosure embodiment;
Fig. 2 illustrates a kind of flow chart of decision model optimization method in the embodiment of the present disclosure;
Fig. 3 illustrates a kind of flow chart of data set method for building up in the embodiment of the present disclosure;
Fig. 4 illustrates a kind of flow chart of decision model optimization method in another embodiment of the disclosure;
Fig. 5 illustrates a kind of flow chart of decision model optimization method in the another embodiment of the disclosure;
Fig. 6 illustrates a kind of flow chart of decision model optimization method in disclosure a further embodiment;
Fig. 7 illustrates a kind of structure chart of decision cooperation platform in the embodiment of the present disclosure;
Fig. 8 illustrates a kind of structure chart of decision model optimization device in disclosure embodiment;
Fig. 9 illustrates a kind of structure chart of decision model optimization device in another embodiment of the disclosure;
Figure 10 illustrates a kind of structure chart of decision model optimization device in the another embodiment of the disclosure;
Figure 11 illustrates a kind of structure chart of decision model optimization system in disclosure embodiment;
Figure 12 illustrates a kind of structure chart of equipment in disclosure embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein;On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the example illustration of the disclosure, it is not necessarily drawn to scale.Identical attached drawing in attached drawing
Label indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are
Functional entity, not necessarily must be corresponding with physically or logically independent entity.These can be realized using software form
Functional entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or in heterogeneous networks and/or
These functional entitys are realized in processor device and/or microcontroller device.Flow chart shown in the drawings is only exemplary theory
It is bright, it is not necessary to including all steps.For example, the step of having can also decompose, and the step of having can merge or part is closed
And therefore the sequence that actually executes be possible to change according to the actual situation.In addition, the term " first " of the disclosure, " second " are only
It is the purpose for differentiation, it should not be as the limitation of the disclosure.
Present disclose provides a kind of decision model optimization methods, with reference to Fig. 1, method includes the following steps:
Step S11: medical characteristics data are received, and determine corresponding with the medical characteristics data the according to decision model
One decision information;
Step S13: first decision information is sent to Multidisciplinary Cooperation system;
Step S15: the second decision information that the Multidisciplinary Cooperation system is sent is received, and according to the medical characteristics number
The decision model is optimized according to second decision information;Wherein, second decision information is according to the medical treatment
Characteristic and first decision information determine.
Present disclose provides a kind of decision model optimization methods, and this method is by two stage decision system to genius morbi data
State data are analyzed, and determine final decision support data, and by the decision support data be used for in decision system certainly
Plan model optimizes, to realize more accurate decision-making results.On the one hand, pass through DSS and Multidisciplinary Cooperation system
Bilevel leader-follower decision mode, can effectively reduce the decision error of DSS, improve the accuracy of complex disease decision, really
Treatment promptly and accurately can be obtained by protecting patient;On the other hand, final decision is being determined by Multidisciplinary Cooperation system every time
After scheme, final decision scheme is back to DSS, decision model is optimized, it is higher accurate to make it have
Property and professional.In another aspect, passing through the connected applications of DSS and Multidisciplinary Cooperation system, efficiently solve existing
Multidisciplinary Cooperation system in be difficult to quick obtaining patient disease information, and meeting can not be carried out according to disease customized information
The problem of decision scheme saves after preceding patient disease finish message and meeting.
Disclosure embodiment provides firstly a kind of decision model optimization method, and the method can be used for by decision branch
The decision cooperation platform of system, Multidisciplinary Cooperation system and database composition is held, correspondingly, decision model optimization device can be protected
There are in the decision cooperation platform.The method can also be applied individually to any DSS, correspondingly, decision model is excellent
Makeup is set and can be stored in the DSS.Below by taking the application scenarios of medical aid decision as an example, in conjunction with implementation
Decision model optimization method described in the disclosure is described in detail in example.
Fig. 1 illustrates a kind of flow chart of decision model optimization method, with reference to Fig. 1, the decision model optimization
Method the following steps are included:
Step S11: medical characteristics data are received, and determine corresponding with the medical characteristics data the according to decision model
One decision information;
It can also include: user before step S11 to the decision branch in an exemplary embodiment of the disclosure
It holds system and sends decision support request, and send medical characteristics data to the DSS;In response to the decision
Support request, DSS executes each step of decision model optimization method in present embodiment and each embodiment.
Wherein, the user may include that the medical services such as the clinician, physician and/or nurse of basic hospital mention
Donor;The medical characteristics data may include patient disease characteristic information, such as may include patient main suit's information, can also be with
Including the data information that doctor's clinic observation, detection obtain, it may include the identity informations such as patient age, gender, also can wrap
The vital sign informations such as pulse, body temperature are included, can also include the auxiliary examinations information such as blood routine detection data, can also include suffering from
The relevant informations such as person's present illness history, medical history, family's medical history.
First decision information can be based on being analyzed and processed the preliminary decision-making party obtained to patient disease characteristic information
Case, for example, may include principle of reatment, principle of reatment illustrate, the information such as the method group of realizing principle of reatment, the application to this not
It is particularly limited to.
It can also include: to be deposited in advance according to database before step S11 in an exemplary embodiment of the disclosure
The medical characteristics data and decision information of storage determine decision model.Specifically, database may include " disease-disease-decision
Scheme " three layer model, the i.e. specifying information of disease, feature knowledge, frequency and specificity and the corresponding decision-making party of the disease
Case;It can also only include " disease-decision scheme " two-layer model, i.e., each disease type and the corresponding decision-making party of the type disease
Case.Database also may include medical knowledge, clinical data and clinical experience etc. information.
For example, determine that decision model can according to the first medical characteristics data stored in database and first decision information
To include: to be received based on the genius morbi information and corresponding decision scheme information stored in clinical knowledge library to the information
Collection, arrange, classification, filtering, processing etc. simultaneously establish logic association knowledge point, and using warning prompting, information button, cure in groups
It advises, the expression-form of document management, related data, provides diagnosis, treatment, nursing, operation, rationally use for disease information to be diagnosed
The decision support of medicine etc., and suggestion, prompting, alarm, calculating, prediction side are provided for the diagnoses and treatment process of clinician
The decision support in face.
It can also include: according to preparatory in database before step S11 in an exemplary embodiment of the disclosure
The medical characteristics data and decision information of storage obtain the decision model to the archetype training based on machine learning.Its
In, archetype can include but is not limited to Bayes model, decision-tree model, Logic Regression Models, SVM model and nerve
Network model etc., there is no special restriction on this for this example.
By taking colorectal cancer disease as an example, according to colorectal cancer characteristic information and its determination of corresponding decision decision information
Decision model may include:
Data set is established according to colorectal cancer characteristic information and colorectal cancer decision decision information, and the data set is divided
For training dataset and test data set;
The archetype based on machine learning is trained using the training dataset, obtains training result;Wherein,
The training result includes the incidence relation of colorectal cancer characteristic information and colorectal cancer decision decision information;
The training result is tested using the test data set;
If the test result of the training result meets default testing standard, using the model after training as the decision
Model.
For example, in the decision model based on decision tree training, medical characteristics data may include the patient disease
The T of state by stages, N by stages, information, the decision information such as high risk factor, low danger factor and age may include for the disease
Used decision scheme, such as XELOX (capecitabine+oxaliplatin), FOLFOX (oxaliplatin+Calciumlevofolinate+fluorine urine
Pyrimidine), the information such as capecitabine and fluorouracil;When to archetype training after, available T by stages+it is high-risk because
When plain+older, the decision information needed is FOLFOX;Alternatively, T by stages when can according to the different phase of T by stages, select
XELOX, FOLFOX, capecitabine or fluorouracil etc..Herein it should be added that, due to the colorectal cancer of patient
Characteristic information is different (staging is different, medical history is different and the age is different), decision information (the i.e. rectum cancerization needed
Treat decision information) be also not quite similar, it is therefore desirable to by repeatedly different training, according to different colorectal cancer characteristic informations into
Row prediction obtains specific therapeutic scheme.
Then into step S13: first decision information is sent to Multidisciplinary Cooperation system;
Wherein, DSS and Multidisciplinary Cooperation system use same genius morbi data definition, such as example count
It can be integer, long according to definition, be also possible to single-precision floating point type, more precision floats, it is special that the application does not do this
It limits.Based on the same genius morbi data definition rule, Multidisciplinary Cooperation system can directly utilize clinical decision system
The data of transmission formulate the report of case history discussion, so that staff can conveniently and efficiently obtain patient's disease in meeting discussion
Sick information, and after the completion of multidisciplinary meeting, it can be convenient and quickly decision scheme is confirmed and saved.
In an exemplary embodiment of the disclosure, the decision model optimization method can also include: by the doctor
It treats characteristic and is sent to Multidisciplinary Cooperation system.Specifically, after step s 11, i.e., DSS is determining just
After walking decision scheme, patient disease information and preliminary decision scheme can be sent to Multidisciplinary Cooperation system automatically;It can also
With when user thinks that preliminary decision scheme needs to confirm, artificial selection will send patient disease information and preliminary decision scheme
To multidisciplinary cooperative system.Patient disease information is sent to Multidisciplinary Cooperation system by DSS, avoids the need for using
Family provides the problem of patient disease information again, and can make Multidisciplinary Cooperation system patient disease information in time, and root
The second decision scheme is determined according to patient disease information and the first decision scheme.In addition, DSS and Multidisciplinary Cooperation system
System uses identical genius morbi data definition, Multidisciplinary Cooperation system can directly using the medical characteristics data that receive and
Preliminary decision scheme forms final decision scheme.
In an exemplary embodiment of the disclosure, the decision model optimization method can also include: will be medical special
Sign data are sent to database.Specifically, DSS can be after receiving patient disease information by the information
Database is sent to be saved, it can also be after determining preliminary decision scheme according to patient disease information by the patient disease
Information is sent to database and is saved, and can also determine when receiving final decision scheme by the patient disease information and finally
Plan scheme is sent to database jointly and is saved.It should be appreciated that by medical characteristics number in the decision model optimization method
It can be carried out before or after any step according to the step of being sent to database, the application is not specially limited this.Also
It should be appreciated that being sent to the data in database through DSS should also include medical characteristics data and final decision side
Incidence relation between case.The step whole can both protect effective preservation patient disease information and corresponding decision scheme, detection
The information such as data can be used for doctor, the staff of expert researchs and analyses the disease.
In an exemplary embodiment of the disclosure, the decision model optimization method can also include: that second determines
Plan information is sent to database.It specifically, can be final certainly by this when Multidisciplinary Cooperation system determines final decision scheme
Plan scheme is sent to database and is saved, can also be final certainly by this when DSS receives final decision scheme
Plan scheme is sent to database and is saved.It should be appreciated that the second decision information is sent out in the decision model optimization method
Sending to the step of database can carry out before or after any step, and the application is not specially limited this.In addition, certainly
Plan supports that same genius morbi number can also be used between system and database and between Multidisciplinary Cooperation system and database
According to definition rule, data information relevant to the disease is effectively received and stored to realize.
It can also include: Multidisciplinary Cooperation system after step s 13 in an exemplary embodiment of the disclosure
Patient disease information is received, consultation of doctors information is sent Xiang doctor's client according to consultation of doctors request, to formulate final decision scheme;
And final decision scheme is back to DSS.Specifically, Multidisciplinary Cooperation system is receiving consultation of doctors request
When, it can be carried out according to patient information application cooperation hospital expert doctor, the central hospital expert doctor etc. received multidisciplinary
The consultation of doctors formulates final decision scheme according to patient disease information and preliminary decision scheme.Wherein, Multidisciplinary Cooperation system utilizes more
The staff of a subject participates in session discussing, passes through image and the exchange of the complete information of audio in meeting on line, can be effective
The defects of preliminary decision scheme is improved, so that more accurately auxiliary base doctor carries out disease decision.
Then into step S15: receiving the second decision information that the Multidisciplinary Cooperation system is sent, and according to the doctor
It treats characteristic and second decision information optimizes the decision model;Wherein, second decision information according to
The medical characteristics data and first decision information determine.
In an exemplary embodiment of the disclosure, Fig. 2 illustrates a kind of decision model in the embodiment of the present disclosure
The flow chart of optimization method.With reference to Fig. 2, according to the medical characteristics data and second decision information to the decision model
It optimizes, may comprise steps of:
Step S21: data set is established according to the medical characteristics data and second decision information;And
Step S23: decision model is trained using the data set;Wherein, using the medical characteristics data as
The input of decision model is trained decision model using the output of the second decision information as the decision model, passes through tune
The weight size of each parameter in whole decision model, so that the decision diagnostic result more accurate and effective of decision model.
Fig. 3 illustrates a kind of flow chart of data set method for building up in the embodiment of the present disclosure;With reference to Fig. 3, according to institute
State medical characteristics data and second decision information establish data set can with the following steps are included:
Step S31: judge whether the medical characteristics data are continuous characteristic value;
Step S33: if the medical characteristics data are continuous characteristic value, the medical characteristics data are carried out discrete
Change processing, obtains Discrete Eigenvalue;
Step S35: being normalized the Discrete Eigenvalue and standardization, obtains normal scatter characteristic value;
And
Step S37: data set is established according to the normal scatter characteristic value and second decision information.
Specifically, it is possible, firstly, to according to the corresponding numerical value of medical characteristics data judge the medical characteristics data whether be
Continuous characteristic value;For example, when the corresponding numerical value of medical characteristics data is a certain interval value, it can be determined that the medical characteristics data
For continuous characteristic value, such as blood pressure;When the corresponding numerical value of medical characteristics data is some fixed value, it can be determined that the medical treatment
Characteristic is Discrete Eigenvalue, such as age;Further, if medical characteristics data are continuous characteristic value, to medical treatment
Characteristic carries out sliding-model control, obtains Discrete Eigenvalue;Such as it can be each by the high pressure, low pressure and median of pressure value
A numerical value is taken, multiple Discrete Eigenvalues are obtained;Secondly, Discrete Eigenvalue is normalized and standardization, obtain
Normal scatter characteristic value;For example, international standards of medical education can be referred to, Discrete Eigenvalue is processed into unified with international standards of medical education
Numerical value;For example, international unit etc. can be uniformly processed into the temperature value of body temperature;Again, normal scatter feature is utilized
Value and the second decision information establish data set;It is output with the second decision information finally, being input with normal scatter characteristic value
Decision model is trained, by constantly adjusting the weight of each parameter of decision model, it is made to have higher accuracy and specially
Industry.
For example, the hospital expert consultation of doctors by Multidisciplinary Cooperation system, if preliminary decision scheme is adopted, i.e., the
In one decision information situation identical with the second decision information, the first decision letter can be reinforced by being trained to decision model
Weight of the breath with the second decision information in decision model training, enables to decision model to determine identical medical characteristics data
Plan is more accurate;If preliminary decision scheme is not adopted, i.e., in the first decision information and the different situation of the second decision information
Under, by being trained to decision model, can be substituted with the decision relationship between medical characteristics data and the first decision information
Fall the decision relationship between first medical characteristics data and the first decision information, enhancing decision model to medical characteristics data into
The accuracy of row decision.
Another embodiment of the disclosure provides a kind of decision model optimization method, and the method can be used for by decision branch
The decision cooperation platform of system (CDSS system), Multidisciplinary Cooperation system (MDT system) and database composition is held, correspondingly, certainly
Plan model optimization device can be stored in the decision cooperation platform.The method can also be applied individually to any Multidisciplinary Cooperation
System, correspondingly, decision model optimization device can be stored in the Multidisciplinary Cooperation system.With reference to Fig. 4, the method packet
Include following steps:
Step S41: the first decision information that medical characteristics data and DSS are sent is received;Wherein, described
One decision information is determined according to decision model and the medical characteristics data;
Then into step S43: determining that the second decision is believed according to the medical characteristics data and first decision information
Breath;
Then into step S45: second decision information being sent to the DSS, for according to
Medical characteristics data and second decision information optimize the decision model.
In an exemplary embodiment of the disclosure, step S45 may include:
Second decision information is sent to the DSS;
Data set is established according to the medical characteristics data and second decision information using the DSS;
And
The decision model is trained according to the data set using the DSS;Wherein, the doctor
Input signal of the characteristic as the decision model is treated, second decision information is believed as the output of the decision model
Number.
Specifically, it is built using the DSS according to the medical characteristics data and second decision information
Vertical data set may include:
Judge whether the medical characteristics data are continuous characteristic value by the DSS;
If the medical characteristics data are continuous characteristic value, sliding-model control is carried out to the medical characteristics data, is obtained
To Discrete Eigenvalue;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
The decision model optimization method can also include:
The decision support request that user sends is received, according to medical characteristics data described in the decision support request.
Another embodiment of the disclosure provides a kind of decision model optimization method, and the method can be used for by decision branch
The decision cooperation platform of system (CDSS system), Multidisciplinary Cooperation system (MDT system) and database composition is held, correspondingly, certainly
Plan model optimization device can be stored in the decision cooperation platform.The method can also be applied individually to any database, phase
It answers, decision model optimization device can save in the database.With reference to Fig. 5, the described method comprises the following steps:
Step S51: at least one decision information pair is received;Wherein, each decision information to include the first decision information and
Second decision information, first decision information are true according to medical characteristics data and decision model preset in DSS
Fixed, second decision information is true according to the medical characteristics data and first decision information by Multidisciplinary Cooperation system
It is fixed;
Then into step S53: detecting at least one described first decision information of decision information centering and determine different from second
The decision information pair of plan information;
Then into step S55: the decision information that will test is to the DSS is sent to, for according to institute
It states medical characteristics data and second decision information of decision information centering optimizes the decision model.
Specifically, true according to decision model by DSS first in the decision model optimization method
Fixed the first decision information corresponding with the medical characteristics data received, is sent to Multidisciplinary Cooperation system for the first decision information
And database;Secondly, determining the second decision according to the first decision information and medical characteristics data by Multidisciplinary Cooperation system again
Information, and second decision information is sent to database;It is corresponding certainly to realize that database receives each genius morbi data
Plan is to information.It is appreciated that the first decision information can also be sent to database, i.e. Multidisciplinary Cooperation by Multidisciplinary Cooperation system
System is after determining the second decision information, using the first decision information and the second decision information as a decision information to common
It is sent to database, disclosure comparison is not specially limited.
In one embodiment, the decision model optimization method can also include: to detect at least one decision letter
Cease the first decision information of centering decision information pair identical with the second decision information;By the decision information to being sent to decision support
System, for strengthening the incidence relation in the decision model between genius morbi data and the first decision information.
In one embodiment, step S55 may include:
The decision information that will test is to being sent to the DSS;
Data set is established according to the medical characteristics data and second decision information using the DSS;
And
The decision model is trained according to the data set using the DSS;Wherein, the doctor
Input signal of the characteristic as the decision model is treated, second decision information is believed as the output of the decision model
Number.
Specifically, it is built by the DSS according to the medical characteristics data and second decision information
Vertical data set may include:
Judge whether the medical characteristics data are continuous characteristic value using the DSS;
If the medical characteristics data are continuous characteristic value, sliding-model control is carried out to the medical characteristics data, is obtained
To Discrete Eigenvalue;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
Another embodiment of the disclosure provides a kind of decision model optimization method, and the method can be used for by decision branch
The decision cooperation platform of system (CDSS system), Multidisciplinary Cooperation system (MDT system) and database composition is held, correspondingly, certainly
Plan model optimization device can be stored in the decision cooperation platform.With reference to Fig. 6, the described method comprises the following steps:
Step S60: DSS receives medical characteristics data, and according to decision model determination and the medical characteristics
Corresponding first decision information of data;
Then into step S61: first decision information is sent to Multidisciplinary Cooperation system by the DSS
System;
Then into step S63: the Multidisciplinary Cooperation system is according to first decision information and the medical characteristics
Data determine the second decision information;
Then into step S65: first decision information is sent to database, Yi Jisuo by the DSS
It states Multidisciplinary Cooperation system and second decision information is sent to the database;
Then into step S67: when the database detection to first decision information and second decision information
When not identical, second decision information is sent to the DSS;
Then into step S69: the DSS receives the second decision information that the database is sent, and root
The decision model is optimized according to the medical characteristics data and second decision information.
It should be noted that DSS, Multidisciplinary Cooperation system and database can be respectively as executing subjects
Each step in above-mentioned above embodiment and embodiment is executed, can also be combined with each other or combine to execute above-mentioned decision
Model optimization method.In short, in the content documented by the disclosure, each technology described in each embodiment and embodiment
Feature can be applied in other embodiments and embodiment.
In the exemplary embodiment of the application, a kind of structure chart of decision cooperation platform is as shown in Figure 7.Below with
Decision model optimization method is described in detail for application environment shown in Fig. 7.
When base doctor applies for that decision cooperation platform carries out decision assistant, sent out by user terminal 74 to DSS 71
Decision support request and patient disease information are sent, DSS 71 divides the patient disease information according to decision model
Analysis processing, determines the preliminary decision scheme for being directed to the patient disease information.Base doctor can be according to the preliminary decision scheme pair
Patient treats, and can also send the consultation of doctors to DSS 71 and Multidisciplinary Cooperation system 72 by client 74 and ask
It asks.Correspondingly, requesting in response to the consultation of doctors, patient disease information and preliminary decision scheme are sent to more by DSS 71
Subject cooperative system 72, Multidisciplinary Cooperation system 72 request multidisciplinary expert (such as cooperation hospital expert doctor and/or center doctor
Institute expert doctor) consultation of doctors discussion is carried out to the patient disease information, formulate the final decision scheme for being directed to the patient disease information;
And final decision scheme is back to DSS 71 by Multidisciplinary Cooperation system 72, DSS 71 is according to final
Decision scheme optimizes decision model.
Wherein, the consultation of doctors operation may include: that Multidisciplinary Cooperation system 72 is participated in the cooperation transmission of hospital's client 75
Consultation of doctors request invites cooperation hospital expert to participate in the consultation of doctors;And at the application center for receiving the cooperation transmission of hospital's client 75
When hospital expert participates in the request of the consultation of doctors, is sent to central hospital's client 76 and participate in consultation of doctors request, invite central hospital expert
Participate in the consultation of doctors.Multidisciplinary Cooperation system participates in the consultation of doctors using the staff of multiple subjects and discusses, passes through on line image in meeting
It exchanges, effectively the defects of preliminary decision scheme can be improved with the complete information of audio, thus more accurately auxiliary
Base doctor is helped to carry out disease decision.In addition, patient disease information can be sent to database 73 by DSS 71, with
And final decision scheme is sent to database 73 by Multidisciplinary Cooperation system 72, for central hospital expert carry out data analysis,
Disease research and formulation are used for the decision model of disease decision assistant.
In the decision cooperation platform, firstly, obtaining patient disease information by DSS (receives medical treatment
Characteristic), the patient disease may include identity characteristic information, vital sign information and/or the auxiliary examination letter of patient
Breath;Secondly, being based on preset decision model, DSS handles the patient disease information analysis, obtains just
It walks decision scheme (i.e. the first decision information);It again, is the accuracy for ensuring decision scheme, DSS will be described preliminary
Decision scheme is sent to Multidisciplinary Cooperation system, is held a consultation to obtain final decision scheme (i.e. by Multidisciplinary Cooperation system
Two decision informations), and the final decision scheme is back to the DSS;Finally, DSS according to
The patient disease information, the preliminary decision scheme and the final decision scheme are corrected optimization to the decision model
This method analyzes genius morbi data by two-stage system, determines final decision support data, and by the decision branch
It holds decision model in the decision system that data are used for optimize, to realize more accurate decision-making results.
Another embodiment of the disclosure provides a kind of decision model optimization device, and Fig. 8 illustrates a kind of decision
The structure chart of model optimization device.Refering to what is shown in Fig. 8, the decision model optimization device 80 includes:
Data determining module 81, for receiving medical characteristics data, and according to decision model determination and the medical characteristics
Corresponding first decision information of data;
Information sending module 82, for first decision information to be sent to Multidisciplinary Cooperation system;And
Model optimization module 83, the second decision information sent for receiving the Multidisciplinary Cooperation system, and according to institute
It states medical characteristics data and second decision information optimizes the decision model;Wherein, second decision information
It is determined according to the medical characteristics data and first decision information.
In an exemplary embodiment of the disclosure, the model optimization module 83 may include:
Data set establishes module, for establishing data set according to the medical characteristics data and second decision information;
And
Model training module, for being trained using the data set to the decision model;Wherein, the medical treatment is special
Levy input signal of the data as the decision model, output signal of second decision information as the decision model.
In an exemplary embodiment of the disclosure, the data set establishes module and may include:
Characteristic value judgment module, for judging whether the medical characteristics data are continuous characteristic value;
Sliding-model control module, if being continuous characteristic value for the medical characteristics data, to the medical characteristics number
According to sliding-model control is carried out, Discrete Eigenvalue is obtained;
Normalized module obtains standard for the Discrete Eigenvalue being normalized and standardization
Discrete Eigenvalue;And
Data set establishes module, for establishing data using the normal scatter characteristic value and second decision information
Collection.
In an exemplary embodiment of the disclosure, the decision model optimization device 80 can also include:
Decision model obtains module, is used for according to medical characteristics data pre-stored in database and decision information to base
In the archetype training of machine learning, the decision model is obtained.
In an exemplary embodiment of the disclosure, the decision model optimization device 80 can also include:
Medical characteristics data transmission blocks, for the medical characteristics data to be sent to the Multidisciplinary Cooperation system.
In an exemplary embodiment of the disclosure, the decision model optimization device 80 can also include:
Request module is received, for receiving the decision support request of user's transmission, according to the decision support request
The medical characteristics data.
Another embodiment of the disclosure provides a kind of decision model optimization device, and Fig. 9 illustrates a kind of decision
The structure chart of model optimization device.Refering to what is shown in Fig. 9, the decision model optimization device 90 includes:
Information receiving module 91, the first decision information sent for receiving medical characteristics data and DSS;
Wherein, first decision information is determined according to decision model and the medical characteristics data;
Information determination module 92, for determining the second decision according to the medical characteristics data and first decision information
Information;
Information sending module 93, for second decision information to be sent to the DSS, according to institute
It states medical characteristics data and second decision information optimizes the decision model.
In an exemplary embodiment of the disclosure, the decision model optimization device 90 can also include:
Data set establishes module, for establishing data set according to the medical characteristics data and second decision information;
And
Model training module, for being trained using the data set to the decision model;Wherein, the medical treatment is special
Levy input signal of the data as the decision model, output signal of second decision information as the decision model.
In an exemplary embodiment of the disclosure, the data set establishes module and may include:
Characteristic value judgment module, for judging whether the medical characteristics data are continuous characteristic value;
Sliding-model control module, if being continuous characteristic value for the medical characteristics data, to the medical characteristics number
According to sliding-model control is carried out, Discrete Eigenvalue is obtained;
Normalized module obtains standard for the Discrete Eigenvalue being normalized and standardization
Discrete Eigenvalue;And
Data set establishes module, for establishing data using the normal scatter characteristic value and second decision information
Collection.
In an exemplary embodiment of the disclosure, the decision model optimization device 90 can also include:
Medical characteristics data acquisition module, for receiving the decision support request of user's transmission, and according to the decision branch
Hold medical characteristics data described in request.
Another embodiment of the disclosure provides a kind of decision model optimization device, and Figure 10 illustrates a kind of decision
The structure chart of model optimization device.Refering to what is shown in Fig. 10, the decision model optimization device 100 includes:
Information butt joint receives module 101, for receiving at least one decision information pair;Wherein, each decision information pair
Including the first decision information and the second decision information, first decision information is according to medical characteristics data and DSS
In preset decision model determine that second decision information is by Multidisciplinary Cooperation system according to the medical characteristics data and institute
The first decision information is stated to determine;
Information is different from detection module 102 for detecting at least one described first decision information of decision information centering
The decision information pair of second decision information;
Information is to sending module 103, and the decision information for will test is to the DSS is sent to, with root
The decision model is optimized according to the medical characteristics data and second decision information of decision information centering.
In an exemplary embodiment of the disclosure, the decision model optimization device 100 can also include:
Data set establishes module, for establishing data set according to the medical characteristics data and second decision information;
And
Model training module, for being trained using the data set to the decision model;Wherein, the medical treatment is special
Levy input signal of the data as the decision model, output signal of second decision information as the decision model.
In an exemplary embodiment of the disclosure, the data set establishes module and may include:
Characteristic value judgment module, for judging whether the medical characteristics data are continuous characteristic value;
Sliding-model control module, if being continuous characteristic value for the medical characteristics data, to the medical characteristics number
According to sliding-model control is carried out, Discrete Eigenvalue is obtained;
Normalized module obtains standard for the Discrete Eigenvalue being normalized and standardization
Discrete Eigenvalue;And
Data set establishes module, for establishing data using the normal scatter characteristic value and second decision information
Collection.
Another embodiment of the disclosure provides a kind of decision model optimization device, and Figure 11 illustrates a kind of decision
The structure chart of model optimization device.With reference to shown in Figure 11, the decision model optimization device 110 includes: DSS
111, Multidisciplinary Cooperation system 112 and database 113;
DSS 111 is stated for executing following steps:
Medical characteristics data are received, and determine that the first decision corresponding with the medical characteristics data is believed according to decision model
Breath;
First decision information is sent to the Multidisciplinary Cooperation system;
First decision information is sent to the database;And
The second decision information that the database is sent is received, and according to the medical characteristics data and second decision
Information optimizes the decision model;
The Multidisciplinary Cooperation system 112 is for executing following steps:
Receive first decision information and the medical characteristics data;
The second decision information is determined according to first decision information and the medical characteristics data;And
Second decision information is sent to database;
The database 113 is for executing following steps:
Receive the first decision information that the DSS the is sent and Multidisciplinary Cooperation system is sent second
Decision information;And
When detecting that first decision information and second decision information be not identical, by second decision information
It is sent to the DSS.
Another embodiment of the disclosure provides a kind of computer readable storage medium, is stored thereon with and can be realized this theory
The program product of the bright book above method.In some possible embodiments, various aspects of the invention are also implemented as one
The form of kind program product comprising program code, when described program product is run on the terminal device, said program code
For making the terminal device execute described in above-mentioned " illustrative methods " part of this specification various examples according to the present invention
The step of property embodiment.
Program product can be run on terminal device, such as server.In this document, readable storage medium storing program for executing can be
It is any to include or the tangible medium of storage program, the program can be commanded execution system, device or device using or with
It is used in combination.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., can also include normal
The procedural programming language-of rule such as " C " language or similar programming language.Program code can fully exist
It executes in user calculating equipment, partly execute on a user device, executing, as an independent software package partially in user
Upper side point is calculated to execute or execute in remote computing device or server completely on a remote computing.It is relating to
And in the situation of remote computing device, remote computing device can pass through the network of any kind, including local area network (LAN) or wide
Domain net (WAN), is connected to user calculating equipment, or, it may be connected to external computing device (such as mentioned using Internet service
It is connected for quotient by internet).
Another embodiment of the disclosure provides a kind of equipment that can be realized the above method.Those of skill in the art
Member is it is understood that various aspects of the invention can be implemented as system, method or program product.Therefore, each side of the invention
It face can be with specific implementation is as follows, it may be assumed that complete hardware embodiment, complete Software Implementation are (including firmware, micro-
Code etc.) or hardware and software in terms of combine embodiment, may be collectively referred to as circuit, " module " or " system " here.
The equipment 1200 of this embodiment according to the present invention is described referring to Figure 12.The equipment 1200 that Figure 12 is shown
An only example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 12, equipment 1200 is showed in the form of universal computing device.The component of equipment 1200 may include but
It is not limited to: at least one above-mentioned processing unit 1210, at least one above-mentioned storage unit 1220, connection different system components (packet
Include storage unit 1220 and processing unit 1210) bus 1230, display unit 1240.
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 1210
Row, so that various according to the present invention described in the execution of the processing unit 1210 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 1210 can execute each step in the respective embodiments described above.
Storage unit 1220 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 1221 and/or cache memory unit 1222, it can further include read-only memory unit (ROM) 1223.
Storage unit 1220 can also include program/utility with one group of (at least one) program module 1225
1224, such program module 1225 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 1230 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Equipment 1200 can also be with one or more external equipments 1201 (such as keyboard, sensing equipment, bluetooth equipment etc.)
Communication, the equipment mutual with the equipment 1200 can be also enabled a user to one or more and is communicated, and/or with make the equipment
The 1200 any equipment (such as router, modem etc.) that can be communicated with one or more of the other calculating equipment are led to
Letter.This communication can be carried out by input/output (I/O) interface 1250.Also, equipment 1200 can also pass through Network adaptation
Device 1260 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet)
Communication.As shown, network adapter 1260 is communicated by bus 1230 with other modules of equipment 1200.It should be understood that the greatest extent
Pipe is not shown in the figure, and can use other hardware and/or software module with bonding apparatus 1200, including but not limited to: microcode is set
Standby driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system
System etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
It should be appreciated that above-mentioned attached drawing is only the exemplary of processing included by method according to an exemplary embodiment of the present invention
Illustrate, rather than limits purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, being also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (21)
1. a kind of decision model optimization method characterized by comprising
Medical characteristics data are received, and the first decision information corresponding with the medical characteristics data is determined according to decision model;
First decision information is sent to Multidisciplinary Cooperation system;And
The second decision information that the Multidisciplinary Cooperation system is sent is received, and according to the medical characteristics data and described second
Decision information optimizes the decision model;Wherein, second decision information is according to the medical characteristics data and institute
The first decision information is stated to determine.
2. decision model optimization method according to claim 1, which is characterized in that described according to the medical characteristics data
The decision model is optimized with second decision information and includes:
Data set is established according to the medical characteristics data and second decision information;And
The decision model is trained using the data set;Wherein, the medical characteristics data are as the decision model
The input signal of type, output signal of second decision information as the decision model.
3. decision model optimization method according to claim 2, which is characterized in that described according to the medical characteristics data
Establishing data set with second decision information includes:
Judge whether the medical characteristics data are continuous characteristic value;
If the medical characteristics data be continuous characteristic value, to the medical characteristics data carry out sliding-model control, obtain from
Dissipate characteristic value;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
4. decision model optimization method according to claim 1, which is characterized in that it is described according to decision model determine with
Before corresponding first decision information of the medical characteristics data, further includes:
The archetype based on machine learning is trained according to medical characteristics data pre-stored in database and decision information,
Obtain the decision model.
5. decision model optimization method according to claim 4, which is characterized in that the archetype includes Bayes mould
One of type, decision-tree model, Logic Regression Models, SVM model and neural network model are a variety of.
6. decision model optimization method according to claim 1, which is characterized in that receive the Multidisciplinary Cooperation described
Before the second decision information that system is sent, further includes:
The medical characteristics data are sent to the Multidisciplinary Cooperation system.
7. decision model optimization method according to claim 1 to 6, which is characterized in that described according to decision
Model determines before the first decision information corresponding with the medical characteristics data, further includes:
The decision support request that user sends is received, according to medical characteristics data described in the decision support request.
8. a kind of decision model optimization method characterized by comprising
Receive the first decision information that medical characteristics data and DSS are sent;Wherein, the first decision information root
It is determined according to decision model and the medical characteristics data;
The second decision information is determined according to the medical characteristics data and first decision information;
Second decision information is sent to the DSS, for according to the medical characteristics data and described the
Two decision informations optimize the decision model.
9. decision model optimization method according to claim 8, which is characterized in that described to send out second decision information
It send to the DSS, is used for according to the medical characteristics data and second decision information to the decision model
It optimizes, comprising:
Second decision information is sent to the DSS;
Data set is established according to the medical characteristics data and second decision information using the DSS;And
The decision model is trained according to the data set using the DSS;Wherein, the medical treatment is special
Levy input signal of the data as the decision model, output signal of second decision information as the decision model.
10. decision model optimization method according to claim 9, which is characterized in that described to utilize the decision support system
System establishes data set with second decision information according to the medical characteristics data and includes:
Judge whether the medical characteristics data are continuous characteristic value by the DSS;
If the medical characteristics data be continuous characteristic value, to the medical characteristics data carry out sliding-model control, obtain from
Dissipate characteristic value;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
11. the decision model optimization method according to any one of claim 8-10, which is characterized in that further include:
The decision support request that user sends is received, according to medical characteristics data described in the decision support request.
12. a kind of decision model optimization method characterized by comprising
Receive at least one decision information pair;Wherein, each decision information to include the first decision information and the second decision information,
First decision information determines that described second determines according to decision model preset in medical characteristics data and DSS
Plan information is determined by Multidisciplinary Cooperation system according to the medical characteristics data and first decision information;
Detect the decision information pair that at least one described first decision information of decision information centering is different from the second decision information;
The decision information that will test is to being sent to the DSS, for according to medical characteristics data and described
The second decision information of decision information centering optimizes the decision model.
13. decision model optimization method according to claim 12, which is characterized in that the decision information that will test
To the DSS is sent to, it is used for according to the medical characteristics data and second decision information to the decision
Model optimizes, comprising:
The decision information that will test is to being sent to the DSS;
Data set is established according to the medical characteristics data and second decision information using the DSS;And
The decision model is trained according to the data set using the DSS;Wherein, the medical treatment is special
Levy input signal of the data as the decision model, output signal of second decision information as the decision model.
14. decision model optimization method according to claim 13, which is characterized in that described to utilize the decision support system
System establishes data set with second decision information according to the medical characteristics data and includes:
Judge whether the medical characteristics data are continuous characteristic value by the DSS;
If the medical characteristics data be continuous characteristic value, to the medical characteristics data carry out sliding-model control, obtain from
Dissipate characteristic value;
The Discrete Eigenvalue is normalized and standardization, obtains normal scatter characteristic value;And
Data set is established using the normal scatter characteristic value and second decision information.
15. a kind of decision model optimization method characterized by comprising
DSS receives medical characteristics data, and determines corresponding with the medical characteristics data the according to decision model
One decision information;
First decision information is sent to Multidisciplinary Cooperation system by the DSS;
The Multidisciplinary Cooperation system determines the second decision information according to first decision information and the medical characteristics data;
First decision information is sent to database and the Multidisciplinary Cooperation system for institute by the DSS
It states the second decision information and is sent to the database;
When the database detection to first decision information and second decision information be not identical, described second is determined
Plan information is sent to the DSS;
The DSS receives the second decision information that the database is sent, and according to the medical characteristics data and
Second decision information optimizes the decision model.
16. a kind of decision model optimizes device characterized by comprising
Data determining module, for receiving medical characteristics data, and according to decision model determination and the medical characteristics data pair
The first decision information answered;
Information sending module, for first decision information to be sent to Multidisciplinary Cooperation system;And
Model optimization module, the second decision information sent for receiving the Multidisciplinary Cooperation system, and according to the medical treatment
Characteristic and second decision information optimize the decision model;Wherein, second decision information is according to institute
It states medical characteristics data and first decision information determines.
17. a kind of decision model optimizes device characterized by comprising
Information receiving module, the first decision information sent for receiving medical characteristics data and DSS;Wherein, institute
The first decision information is stated to be determined according to decision model and the medical characteristics data;
Information determination module, for determining the second decision information according to the medical characteristics data and first decision information;
Information sending module, for second decision information to be sent to the DSS, according to the medical treatment
Characteristic and second decision information optimize the decision model.
18. a kind of decision model optimizes device characterized by comprising
Information butt joint receives module, for receiving at least one decision information pair;Wherein, each decision information is to including first
Decision information and the second decision information, first decision information according to medical characteristics data with it is preset in DSS
Decision model determines that second decision information is determined according to the medical characteristics data with described first by Multidisciplinary Cooperation system
Plan information determines;
Information is different from the second decision to detection module, for detecting at least one described first decision information of decision information centering
The decision information pair of information;
Information is to sending module, and decision information for will test is to being sent to the DSS, according to
Medical characteristics data and second decision information of decision information centering optimize the decision model.
19. a kind of decision model optimization system characterized by comprising DSS, Multidisciplinary Cooperation system and data
Library;
The DSS is for executing following steps:
Medical characteristics data are received, and the first decision information corresponding with the medical characteristics data is determined according to decision model;
First decision information is sent to the Multidisciplinary Cooperation system;
First decision information is sent to the database;And
The second decision information that the database is sent is received, and according to the medical characteristics data and second decision information
The decision model is optimized;
The Multidisciplinary Cooperation system is for executing following steps:
Receive first decision information and the medical characteristics data;
The second decision information is determined according to first decision information and the medical characteristics data;And
Second decision information is sent to the database;
The database is for executing following steps:
Receive the first decision information that the DSS is sent and the second decision that the Multidisciplinary Cooperation system is sent
Information;And
When detecting that first decision information and second decision information be not identical, second decision information is sent
To the DSS.
20. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method as described in claim 1-15 is any is realized when execution.
21. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in claim 1-15 is any.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910241936.6A CN109948806A (en) | 2019-03-28 | 2019-03-28 | Decision model optimization method, device, storage medium and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910241936.6A CN109948806A (en) | 2019-03-28 | 2019-03-28 | Decision model optimization method, device, storage medium and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109948806A true CN109948806A (en) | 2019-06-28 |
Family
ID=67012180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910241936.6A Pending CN109948806A (en) | 2019-03-28 | 2019-03-28 | Decision model optimization method, device, storage medium and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109948806A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110570943A (en) * | 2019-09-04 | 2019-12-13 | 医渡云(北京)技术有限公司 | method and device for intelligently recommending MDT (minimization of drive test) grouping, electronic equipment and storage medium |
CN112712874A (en) * | 2020-12-29 | 2021-04-27 | 北京浪潮数据技术有限公司 | Intelligent pulse feeling method and device, electronic equipment and storage medium |
CN113781277A (en) * | 2021-08-05 | 2021-12-10 | 北京远盟普惠健康科技有限公司 | Terminal, system and data processing method for developing health maintenance service |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101414324A (en) * | 2008-09-01 | 2009-04-22 | 中国网通集团宽带业务应用国家工程实验室有限公司 | Electronic medical system |
CN105787252A (en) * | 2016-01-18 | 2016-07-20 | 贡京京 | Medical decision supporting method and system |
CN107025375A (en) * | 2017-03-14 | 2017-08-08 | 芜湖卫健康物联网医疗科技有限公司 | A kind of cloud classification diagnosis and treatment data handling system and its data processing method |
CN107491630A (en) * | 2016-06-10 | 2017-12-19 | 韩国电子通信研究院 | Clinical decision support integrated system and use its clinical decision support method |
CN107785058A (en) * | 2017-07-24 | 2018-03-09 | 平安科技(深圳)有限公司 | Anti- fraud recognition methods, storage medium and the server for carrying safety brain |
CN107799160A (en) * | 2017-10-26 | 2018-03-13 | 医渡云(北京)技术有限公司 | Medication aid decision-making method and device, storage medium, electronic equipment |
CN107845429A (en) * | 2017-10-16 | 2018-03-27 | 李洪波 | A kind of method and system of online medical advice |
EP2909335B1 (en) * | 2012-10-17 | 2018-05-30 | Institut National de la Recherche Agronomique | Prognostic of diet impact on obesity-related co-morbidities |
CN108805416A (en) * | 2018-05-22 | 2018-11-13 | 阿里巴巴集团控股有限公司 | A kind of risk prevention system processing method, device and equipment |
CN108877926A (en) * | 2018-05-15 | 2018-11-23 | 中山市徕康医疗信息软件技术有限公司 | A kind of quick diagnosis and treatment and point intelligent assistance system examined of suitable family doctor |
CN109166105A (en) * | 2018-08-01 | 2019-01-08 | 中国人民解放军南京军区南京总医院 | The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image |
CN109360655A (en) * | 2018-12-13 | 2019-02-19 | 湖南德雅曼达科技有限公司 | A kind of section of institute of medical institutions two-stage infection risk assessment system and method |
CN109378065A (en) * | 2018-10-30 | 2019-02-22 | 医渡云(北京)技术有限公司 | Medical data processing method and processing device, storage medium, electronic equipment |
CN109460795A (en) * | 2018-12-17 | 2019-03-12 | 北京三快在线科技有限公司 | Classifier training method, apparatus, electronic equipment and computer-readable medium |
CN109493926A (en) * | 2018-10-30 | 2019-03-19 | 中山大学肿瘤防治中心 | Processing method, device, medium and the electronic equipment of colorectal cancer medical data |
-
2019
- 2019-03-28 CN CN201910241936.6A patent/CN109948806A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101414324A (en) * | 2008-09-01 | 2009-04-22 | 中国网通集团宽带业务应用国家工程实验室有限公司 | Electronic medical system |
EP2909335B1 (en) * | 2012-10-17 | 2018-05-30 | Institut National de la Recherche Agronomique | Prognostic of diet impact on obesity-related co-morbidities |
CN105787252A (en) * | 2016-01-18 | 2016-07-20 | 贡京京 | Medical decision supporting method and system |
CN107491630A (en) * | 2016-06-10 | 2017-12-19 | 韩国电子通信研究院 | Clinical decision support integrated system and use its clinical decision support method |
CN107025375A (en) * | 2017-03-14 | 2017-08-08 | 芜湖卫健康物联网医疗科技有限公司 | A kind of cloud classification diagnosis and treatment data handling system and its data processing method |
CN107785058A (en) * | 2017-07-24 | 2018-03-09 | 平安科技(深圳)有限公司 | Anti- fraud recognition methods, storage medium and the server for carrying safety brain |
CN107845429A (en) * | 2017-10-16 | 2018-03-27 | 李洪波 | A kind of method and system of online medical advice |
CN107799160A (en) * | 2017-10-26 | 2018-03-13 | 医渡云(北京)技术有限公司 | Medication aid decision-making method and device, storage medium, electronic equipment |
CN108877926A (en) * | 2018-05-15 | 2018-11-23 | 中山市徕康医疗信息软件技术有限公司 | A kind of quick diagnosis and treatment and point intelligent assistance system examined of suitable family doctor |
CN108805416A (en) * | 2018-05-22 | 2018-11-13 | 阿里巴巴集团控股有限公司 | A kind of risk prevention system processing method, device and equipment |
CN109166105A (en) * | 2018-08-01 | 2019-01-08 | 中国人民解放军南京军区南京总医院 | The malignancy of tumor risk stratification assistant diagnosis system of artificial intelligence medical image |
CN109378065A (en) * | 2018-10-30 | 2019-02-22 | 医渡云(北京)技术有限公司 | Medical data processing method and processing device, storage medium, electronic equipment |
CN109493926A (en) * | 2018-10-30 | 2019-03-19 | 中山大学肿瘤防治中心 | Processing method, device, medium and the electronic equipment of colorectal cancer medical data |
CN109360655A (en) * | 2018-12-13 | 2019-02-19 | 湖南德雅曼达科技有限公司 | A kind of section of institute of medical institutions two-stage infection risk assessment system and method |
CN109460795A (en) * | 2018-12-17 | 2019-03-12 | 北京三快在线科技有限公司 | Classifier training method, apparatus, electronic equipment and computer-readable medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110570943A (en) * | 2019-09-04 | 2019-12-13 | 医渡云(北京)技术有限公司 | method and device for intelligently recommending MDT (minimization of drive test) grouping, electronic equipment and storage medium |
CN110570943B (en) * | 2019-09-04 | 2021-03-12 | 医渡云(北京)技术有限公司 | Method and device for intelligently recommending MDT (minimization of drive test) grouping, electronic equipment and storage medium |
CN112712874A (en) * | 2020-12-29 | 2021-04-27 | 北京浪潮数据技术有限公司 | Intelligent pulse feeling method and device, electronic equipment and storage medium |
CN113781277A (en) * | 2021-08-05 | 2021-12-10 | 北京远盟普惠健康科技有限公司 | Terminal, system and data processing method for developing health maintenance service |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tu et al. | Towards generalist biomedical ai | |
Guo et al. | The application of medical artificial intelligence technology in rural areas of developing countries | |
US20220139568A1 (en) | Virtual telemedicine mechanism | |
US10496788B2 (en) | Holistic hospital patient care and management system and method for automated patient monitoring | |
US10593426B2 (en) | Holistic hospital patient care and management system and method for automated facial biological recognition | |
US20200402665A1 (en) | Unplanned readmission prediction using an interactive augmented intelligent (iai) system | |
US20150213217A1 (en) | Holistic hospital patient care and management system and method for telemedicine | |
US20150213222A1 (en) | Holistic hospital patient care and management system and method for automated resource management | |
US20150213225A1 (en) | Holistic hospital patient care and management system and method for enhanced risk stratification | |
US20150213202A1 (en) | Holistic hospital patient care and management system and method for patient and family engagement | |
US20150213223A1 (en) | Holistic hospital patient care and management system and method for situation analysis simulation | |
CN104364817A (en) | Systems and methods for providing transparent medical treatment | |
WO2015157577A2 (en) | Holistic hospital patient care and management system and method for telemedicine | |
CN109948806A (en) | Decision model optimization method, device, storage medium and equipment | |
US11769593B2 (en) | Comprehensive diagnosis and care system | |
KR102479692B1 (en) | Big data and cloud system based AI(artificial intelligence) emergency medical care decision-making and emergency patient transfer system and method thereof | |
Ho et al. | A call for an ethics and governance action plan to harness the power of artificial intelligence and digitalization in nephrology | |
Berg et al. | Emergency department operations II: patient flow | |
Mohsin et al. | The role of artificial intelligence in prediction, risk stratification, and personalized treatment planning for congenital heart diseases | |
Walters et al. | Virtualized care systems, medical artificial intelligence, and real-time clinical monitoring in COVID-19 diagnosis, screening, surveillance, and prevention | |
Sharma et al. | Addressing the challenges of AI-based telemedicine: Best practices and lessons learned | |
Dogan | Process mining based on patient waiting time: an application in health processes | |
Tiwari et al. | Symptoms are known by their companies: towards association guided disease diagnosis assistant | |
Chintala | Improving Healthcare Accessibility with AI-Enabled Telemedicine Solutions | |
US20230130914A1 (en) | System and method for patient care handoff |
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 |