CN108847280A - The smart cloud medical treatment real-time management system of case-based reasioning - Google Patents
The smart cloud medical treatment real-time management system of case-based reasioning Download PDFInfo
- Publication number
- CN108847280A CN108847280A CN201810642563.9A CN201810642563A CN108847280A CN 108847280 A CN108847280 A CN 108847280A CN 201810642563 A CN201810642563 A CN 201810642563A CN 108847280 A CN108847280 A CN 108847280A
- Authority
- CN
- China
- Prior art keywords
- case
- diagnosis
- database
- medical treatment
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
A kind of smart cloud medical treatment real-time management system of case-based reasioning, the system comprises：Environment sensing layer, suitable for user is acquired by wearable device physiologic information and remote transmission to data center's layer；Data center's layer, suitable for receiving the physiologic information of the user and storing to physiological data library；Cloud computing intelligent medical treatment layer, physiologic information suitable for obtaining user from the physiological data library is analyzed and processed, obtain corresponding medical treatment result, and obtained medical treatment result is passed sequentially through into the data center's layer and the environment sensing layer is sent to the wearable device, so that the user obtains the medical treatment result.The diagnosis and treatment efficiency of disease can be improved in above-mentioned scheme.
Description
Technical field
The present invention relates to field of medical technology, more particularly to a kind of smart cloud medical treatment real-time management of case-based reasioning
System.
Background technique
Intelligent medical treatment is the people's livelihood field application that one important in the strategical planning of smart city, utilizes state-of-the-art information skill
Art can be realized interacting between patient and medical worker, medical institutions, Medical Devices, reach medical information.
In existing intelligent medical treatment system, medical data perception and processing mainly utilize technology of Internet of things, flat by terminal
Platform, via the mode of the long-range device sensor work of internet medium competition so that the perception of teledata obtains and simple
Change is treated as possibility.One of the most common Remote data service method is the important physiology using wearable device monitoring user
Signal is able to achieve wearable device to human body by technologies such as sensing technology, operating system, wireless communication, data processings
Without invade and harass, the monitoring of noninvasive and continuous physiologic information, and have the characteristics that continue working, support abnormal physiological condition alarm.
However, existing intelligent medical treatment system can not expire with the application of numerous sensor and Medical Devices
The problem of process demand of the medical data of sufficient enormous amount, there is inefficiency.
Summary of the invention
Present invention solves the technical problem that being how to improve the diagnosis and treatment efficiency of disease.
In order to solve the above technical problems, the embodiment of the invention provides a kind of medical treatment of the smart cloud of case-based reasioning is real-time
Management system, the system comprises the environment sensing layer successively coupled, data center's layer and cloud computing intelligent medical treatment layers；
The environment sensing layer, the physiologic information that user is acquired by wearable device and remote transmission is to data center
Layer；
The data center's layer, suitable for receiving the physiologic information of the user and storing to physiological data library；
The cloud computing intelligent medical treatment layer, the physiologic information suitable for obtaining user from the physiological data library are analyzed
Processing, obtains corresponding medical treatment result, and obtained medical treatment result is passed sequentially through the data center's layer and the environment
Sensing layer is sent to the wearable device, so that the user obtains the medical treatment result.
Optionally, the environment sensing layer is further adapted for acquiring clinical treatment information from hospital and medical knowledge information is concurrent
It send to the data center's layer；
The data center's layer is further adapted for receiving the clinical treatment information and medical knowledge information and is stored respectively to examining
Disconnected case database and expertise database.
Optionally, there is abnormal physiology suitable for obtaining from the physiological data library in the cloud computing intelligent medical treatment layer
Information generates corresponding target case；The target case is matched with the diagnosis case in diagnosis case database, is obtained
Case is diagnosed to optimal candidate；The diagnosis case database be to the clinical case database and expertise database into
Row processing obtains；When not being matched to optimal candidate diagnosis case, the expertise database is handled to obtain and institute
State the optimal candidate diagnosis case that target case matches；Using the therapeutic scheme of optimal candidate diagnosis case as goal-trail
The Primary treatment scheme of example；When determining that user is satisfied with the Primary treatment scheme being calculated, by the Primary treatment scheme
As final therapeutic scheme；When determining that user is dissatisfied to the Primary treatment scheme being calculated, using adaptation algorithm and institute
It states expertise database to be adjusted the Primary treatment scheme, obtains the final therapeutic scheme.
Optionally, the diagnosis case database uses and represents case database and sub- case database two-level configuration；Institute
State the typical diagnostic case for representing that case database includes the crucial disease characteristic attribute of disease；The sub- case database is packet
Include all diagnosis cases of predetermined disease characteristic attribute；It is described to represent one a pair of case database and the sub- case database
It answers；
The cloud computing intelligent medical treatment layer, suitable for calculating separately the target case using nearest neighbor method and representing case
Similarity numerical value between database；The corresponding sub- case database of case database is represented by similarity numerical value is highest,
As matched sub- case database；Calculate separately the target case and examining in obtained matched sub- case database
The distance between example of settling a lawsuit；Pre-determined distance threshold value will be less than and the corresponding diagnosis case of the smallest distance values is as described best
Candidate diagnosis case.
Optionally, the cloud computing intelligent medical treatment layer, suitable for calculating the target case and gained using following formula
To matched sub- case database in the distance between diagnosis case：
And
Wherein, dti' indicate between diagnosis case in target case and obtained matched sub- case database away from
From WjIndicate the weight of j-th of characteristic attribute, TjIndicate j-th of crucial disease characteristic attribute value of target case, n is to close
The total number of key disease characteristic attribute, YijThe value of the j-th characteristic attribute of i-th of case after indicating normalization, min YiTable
Show the minimal characteristic attribute value of i-th of case after normalizing, max YiIndicate the maximum characteristic attribute of i-th of case after normalizing
Value, YiIndicate the characteristic attribute value of i-th of case after normalizing, MijIndicate intermediate variable.
Optionally, the cloud computing intelligent medical treatment layer, be further adapted for it is described diagnosis case database in diagnosis case into
Row updates.
Optionally, the cloud computing intelligent medical treatment layer, suitable for using the final of the target case and the target case
Therapeutic scheme generates corresponding diagnosis case to be stored；Judge generated wait store diagnosis case and corresponding sub- case data
The similarity numerical value between diagnosis case in library；It is generated wait store diagnosis case and corresponding sub- case data when determining
When the similarity numerical value between diagnosis case in library is all larger than preset similarity threshold, by diagnosis case to be stored generated
Example is stored in the diagnosis case database.
Optionally, the cloud computing intelligent medical treatment layer exists suitable for calculating the diagnosis case in the diagnosis case database
The frequency that is cited in preset time；When determining the frequency that is cited less than preset frequency threshold, by corresponding diagnosis case
It is deleted from the diagnosis case database.
Compared with prior art, the technical solution of the embodiment of the present invention has the advantages that：
Above-mentioned scheme is analyzed and processed using physiologic information of the cloud computing intelligent medical treatment layer to user, and by gained
The data center's layer is passed sequentially through to corresponding medical treatment result and the environment sensing layer is sent to the wearable device, with
So that the user obtains the last diagnostic as a result, for carrying out data using the cloud computing intelligent medical treatment layer based on cloud computing
Analysis and processing, therefore the processing speed of data can be improved, so as to improve diagnosis and treatment efficiency.
Further, case database and sub- case database two-stage are represented by the way that the diagnosis case database to be divided into
Structure so that the cloud computing intelligent medical treatment layer determine optimal candidate diagnose case when, only by target case and the diagnosis
The diagnosis case accordingly represented in the corresponding sub- case database of case database in case database is matched, rather than by mesh
Mark case is matched one by one with all diagnosis cases of the diagnosis case database, therefore optimal candidate diagnosis case can be improved
The retrieval rate of example, so as to further increase diagnosis and treatment efficiency.
Further, the cloud computing intelligent medical treatment layer uses the final treatment of the target case and the target case
The corresponding diagnosis case to be stored of schemes generation, and it is generated wait store diagnosis case and corresponding sub- case data when determining
When the similarity numerical value between diagnosis case in library is all larger than preset similarity threshold, by diagnosis case to be stored generated
Example is stored in the diagnosis case database, and the expansion of diagnosis case database can be effectively prevented, it is ensured that improves diagnosis case
The quality of the diagnosis case stored in example database, improves the accuracy of diagnosis and treatment.
Further, the cloud computing intelligent medical treatment layer is existed by calculating the diagnosis case in the diagnosis case database
The frequency that is cited in preset time, and when determining the frequency that is cited less than preset frequency threshold, by corresponding diagnosis case
Example is deleted from the diagnosis case database, can be simplified to diagnosis case database, be improved diagnosis case database
The quality of middle stored diagnosis case, improves the accuracy of diagnosis and treatment.
Detailed description of the invention
Fig. 1 is that the structure of the smart cloud medical treatment real-time management system of one of embodiment of the present invention case-based reasioning is shown
It is intended to；
Fig. 2 is the flow diagram of one of embodiment of the present invention smart cloud medical method.
Specific embodiment
Technical solution in the embodiment of the present invention is carried out by using physiologic information of the cloud computing intelligent medical treatment layer to user
Analysis processing, and by obtained medical treatment result pass sequentially through the data center's layer and the environment sensing layer be sent to it is described
Wearable device so that the user obtain the last diagnostic as a result, it is possible to increase data processing speed, so as to
Improve diagnosis and treatment efficiency.
It is understandable to enable above-mentioned purpose of the invention, feature and beneficial effect to become apparent, with reference to the accompanying drawing to this
The specific embodiment of invention is described in detail.
In order to make it easy to understand, below in real time by the smart cloud medical treatment first to the case-based reasioning in the embodiment of the present invention
The composition of management system is introduced.
Referring to Fig. 1, the smart cloud medical treatment real-time management system of one of embodiment of the present invention case-based reasioning can be with
Including environment sensing layer 11, data center's layer 12 and cloud computing intelligent medical treatment layer 13.Wherein, environment sensing layer 11 and data center
Layer 12 couples, and the data center's layer 12 is also coupled with cloud computing intelligent medical treatment layer 13.
Smart cloud medical treatment below in conjunction with the case-based reasioning of Fig. 2 embodiment of the present invention described in Fig. 1 is managed in real time
The working principle of reason system is introduced.
With reference to Fig. 2, a kind of smart cloud medical method can be realized using following operation：
Step S201：The physiologic information and remote transmission that environment sensing layer acquires user by wearable device are into data
Central layer.
In specific implementation, the environment sensing layer may include family data module wherein family data module.Wherein,
Family data module collects the physiologic informations such as temperature, heart rate, the blood pressure of user by wearable health monitoring equipment, and will collect
To data remote transmission and be stored in physiological data library.In addition, the wearable device is in the embodiment of the present invention
Smart cloud medical system front end and end, one side can extract physiologic information from user's body and be sent to data center
In physiological data library in stored, on the other hand can be by the diagnosis knot of the smart cloud medical system in the embodiment of the present invention
Fruit information returns to user.
In an embodiment of the present invention, in order to improve the smart cloud medical system in the embodiment of the present invention diagnosis accuracy
And reliability, the environment sensing layer further include hospital data module.Wherein, the hospital data module on the one hand can basis
User collects the clinical information of user when hospital treats, such as user's case history, B ultrasound, electrocardiogram, Chest X-rays diagnostic message,
The information such as medical treatment result, and the data being collected into progress remote transmission is then store in clinical case database；Another party
Face, the related medical diagnosis on disease that medical domain expert can also be provided and be extracted from medical literature by the hospital data module are controlled
The relevant knowledge and experience for the treatment of are transmitted and stored in the expertise database in data center's layer.
It is to be herein pointed out above-mentioned data transfer mode mainly utilize Ethernet, Sensor Network, mobile communication,
The multiple technologies such as M2M, bluetooth are reliably achieved the transmission for the data information that environment sensing layer perceives in real time.
Step S202：The data center's layer receives the physiologic information of the user and stores to physiological data library.
In specific implementation, when receiving physiologic information transmitted by environment sensing layer, data center's layer environment can be with
The physiologic information is received, and the received physiologic information of institute is stored into physiological data library.
In specific implementation, when receiving, the environment sensing layer acquires clinical treatment information from hospital and medical knowledge is believed
When breath, the data center's layer can receive the clinical treatment information and medical knowledge information and be stored respectively to clinical case
Database and expertise database.
In an embodiment of the present invention, the data center's layer includes data access layer, data storage layer, data processing
Layer, wherein：
The data access layer mainly includes synchronization message module and asynchronous message module, be mainly responsible for data perception layer with
The telecommunication management and Message Processing of data center's layer further include the pretreatment of some pairs of message to facilitate the storage of data storage layer
With further application.In an embodiment of the present invention, the asynchronous message module is based on Java Message Service (JMS, Java
Message Service) asynchronous message service, non-abnormality that primary recipient environment sensing layer is sent and non-mandatory disappear
Breath, the purpose is to solve environment sensing layer frequently to communicate and bring loading problem with data center's layer.The synchronization message mould
Block is then to apply (MINA, Multipurpose Infrastructure for Network based on multi-target networks
Applications) the message communicating management of frame first establishes legitimate conversation, so between environment sensing layer and data center's layer
Abnormality and mandatory message, and real-time calling data center stratus background analysis are transmitted afterwards, are returned to operation decision, are guaranteed message
Real-time processing.
The data storage layer includes physiological data library, clinical case database and expertise database.It is wherein clinical
Case database and expertise database use HBase database, are responsible for the storage of system diagnostics case data；Physiological data
Library uses the relational databases such as Oracle then to store the physiologic information of collected user, is quickly located with the business of auxiliary system
Reason.
The data analysis layer includes parallel data processing module, data monitoring module and data access module.Wherein, institute
The various tasks that parallel data processing module is stated as data analysis, data mining provide parallel algorithm, are mainly based on comprising some
The algorithms library of cloud computing parallel computation；The data monitoring module is monitored data by cloud computing application and according to monitoring
Abnormal results selection notice starts the cloud computing intelligent medical treatment layer and carries out Data Analysis Services；The data access module according to
Different needs called data or write-in data from database corresponding in data center's layer.
Step S203：The physiologic information that cloud computing intelligent medical treatment layer obtains user from the physiological data library is analyzed
Processing, obtains corresponding medical treatment result.
In an embodiment of the present invention, intelligent medical treatment layer includes diagnosis case database, inference system and human-computer interaction mould
Block.
Case library is diagnosed, to examine by the disease obtained to clinical case database and the processing of expertise database analysis
Relevant information for the treatment of, including case label, case source, disease type, therapy, prescriptions etc. are storage disease treatment cases
Database.
In specific implementation, the cloud computing intelligent medical treatment layer can be obtained from the physiological data library in data center's layer
It in the presence of abnormal physiological signal, and is analyzed and processed, mainly extracts corresponding key from the abnormal physiologic information
Disease characteristic attribute data generate corresponding target case, and the diagnosis case in target case and diagnosis case database is carried out
Matching, the optimal candidate diagnosis case for obtaining the highest optimal candidate diagnosis case of similarity with retrieval, and matching being obtained
Therapeutic scheme is as Primary treatment scheme, then by being further processed to obtain target to obtained Primary treatment scheme
The corresponding final therapeutic scheme of case.
In an embodiment of the present invention, in order to improve the retrieval rate that optimal candidate diagnoses case, by the diagnosis case
Database, which is divided into, represents case database and sub- case database two-level configuration.Wherein, the case database that represents includes disease
The typical diagnostic case of the crucial disease characteristic attribute of disease；The sub- case database is the institute for including predetermined disease characteristic attribute
There is diagnosis case；It is described to represent case database and the sub- case database one-to-one correspondence.
The cloud computing intelligent medical treatment layer is matching target case with the diagnosis case in diagnosis case database
When obtaining similarity highest optimal candidate diagnosis case, in the target case and generation, are calculated separately using nearest neighbor method first
Similarity numerical value between table case database, and the corresponding sub- case of case database is represented by similarity numerical value is highest
Database, as matched sub- case database.Then, the cloud computing intelligent medical treatment layer calculate separately the target case with
The distance between diagnosis case in obtained matched sub- case database, and calculated distance numerical value is the smallest
Case is diagnosed as the optimal candidate and diagnoses case.
Wherein, the target case is being calculated separately using nearest neighbor method and is representing the similarity between case database
When numerical value, the weight of the crucial disease characteristic attribute of case is determined using comparison method first, wherein the key disease feature
The weight of attribute is expressed as formula with three-level scale with the relative importance with each index in the crucial disease characteristic attribute of measurement
It is as follows：
Wherein, f is enabled1、f2、...、fnFor n crucial disease characteristic attribute index, assessed according to three-level proportion quotiety to
Score value out, all score values may make up matrix Q=(qij)n*n, it is known that matrix element qijBetween there are following relationships：
And crucial disease characteristic attribute index fiWeight coefficient be：
When determining the weight of crucial disease characteristic attribute index, the target case can be calculated using following formula
With represent the similarity numerical value between case：
Wherein, X expression represents case, and S indicates target case, and i ∈ [1, n], n indicate the key that each case is included
The number of disease characteristic attribute；WiIt indicates the attribute weight of i-th of crucial disease characteristic attribute, and hasF is target
Case and the measuring similarity function for representing i-th of crucial disease characteristic attribute in case X.
It is higher to count counted similarity numerical value Similarity (S, X) by formula (4), then it represents that target case with it is corresponding
Representative case between matching degree it is higher, more meet the requirement of retrieval.
When most like representative case S is calculated, then the case for representing sub- case database corresponding to case S
Be case relevant to target case, next again using improved euclidean distance method in corresponding sub- case database into
Row further retrieval, finds most like case, i.e. optimal candidate diagnoses case T.
Wherein, classical Euclidean distance algorithm is as follows：
Wherein, dtiIndicate the distance between i-th of case, X in target case and diagnosis case databaseijIt indicates i-th
The crucial disease characteristic attribute value of j-th of case, TjIndicate j-th of crucial disease characteristic attribute value of target case, WjIndicate the
The weight of j crucial disease characteristic attribute, n are the sum of crucial disease characteristic attribute.
As the d being calculated by formula (5)tiBe worth it is smaller, show target case and it is corresponding diagnosis case between phase
It is high like degree.
Assuming that there is m case in corresponding sub- case database, each case has n crucial disease characteristic attribute, and note is closed
Key disease characteristic attribute integrates as C={ C1, C2..., Cn, wherein CjIt is j-th of crucial disease characteristic attribute, j-th of crucial disease
The mean value for waiting characteristic attribute is denoted asThen：
So as to obtain：
Wherein, MijMake intermediate variable.
Sometimes it because the dimension of each index between crucial disease characteristic attribute is different or order of magnitude difference is larger, then needs pair
The value of original key disease characteristic attribute is normalized in conversion processing to same magnitude, so that the result of calculating can be more acurrate
Embody the adaptation value between target case and source case in ground.
For example, former crucial disease characteristic attribute value can be mapped to by [- 1,1] by following normalization utility function,
I.e.：
Wherein, YijThe value of j-th of characteristic attribute of i-th of case after indicating normalization, MijIndicate intermediate variable.
Then, the data after normalized are further carried out by two times transfer using following formula again, thus will
The numerical value of original key disease characteristic attribute is transformed between [0,1]：
Wherein, YijThe value of j-th of characteristic attribute of i-th of case after indicating normalization, min YiAfter indicating normalization
The minimal characteristic attribute value of i-th of case, max YiIndicate the maximum characteristic attribute value of i-th of case after normalizing, YiExpression is returned
The characteristic attribute value of i-th of case after one change.So, the diagnosis in target case sub- case database corresponding with case is represented
Improved distance between case can be calculated using following formula：
Wherein, dti' indicate between diagnosis case in target case and obtained matched sub- case database away from
From WjIndicate the weight of j-th of characteristic attribute, TjIndicate j-th of crucial disease characteristic attribute value of target case, n is to close
The total number of key disease characteristic attribute.
When between each diagnosis case being calculated in the target case sub- case database corresponding with case is represented
Distance dti' when, distance values are less than the corresponding diagnosis case of minimum range in preset distance threshold as the mesh
The optimal candidate for marking case diagnoses case.
It is to be herein pointed out when determining that optimal candidate diagnoses case, it, may be from correspondence because of the setting of distance threshold
Sub- case database in matching less than corresponding optimal candidate diagnose case.At this point it is possible to by the expertise number
It is handled according to library, to obtain the optimal candidate to match with the target case diagnosis case.
Step S204：The output of obtained medical treatment result is shown to medical worker by cloud computing intelligent medical treatment layer, receives institute
The final diagnosis and treatment knot that medical worker is stated to the feedback information of the medical treatment result, and is generated based on the feedback information of the diagnostic result
Fruit.
In specific implementation, when obtain optimal candidate diagnosis case when, cloud computing intelligent medical treatment layer can will it is described most preferably
Primary treatment scheme output is shown to by Primary treatment scheme of the therapeutic scheme of candidate diagnosis case as target case
Medical worker, when determining that medical worker is satisfied with the Primary treatment scheme being calculated, using the Primary treatment scheme as
Final therapeutic scheme；When determining that medical worker is dissatisfied to the Primary treatment scheme being calculated, using adaptation algorithm and institute
It states expertise database to be adjusted the Primary treatment scheme, obtains the final therapeutic scheme.
Wherein, case and target case are diagnosed by carrying out the optimal candidate that grading search determines to diagnosis case database
Crucial disease characteristic attribute between there may be difference, thus need the treatment side to the optimal candidate diagnosis case retrieved
Case is adjusted.In an embodiment of the present invention, cloud computing intelligent medical treatment layer can be using adaptation algorithm to passing through optimal candidate
The Primary treatment scheme for the target case that diagnosis case obtains is adjusted, as the solution for the most like case screened
Element is operated, and is allowed to be adapted with target case.Specifically, diagnosis case is by crucial disease characteristic attribute collection and the scholar who won the first place in provincial imperial examinations
Element collection composition, the adaptation algorithm are the alternate algorithm based on feedback, for the complex situation of solution structure, pass through analysis
Part invalid in similar solution is replaced, therapeutic scheme compatible with target case is obtained.For example, when disease morphs
When, the partial content in therapeutic scheme will be unable to play therapeutic effect before, in this situation it is desirable to part therapeutic scheme
It is adjusted and replaces, preferably to treat new disease.Wherein, in the alternative Process based on feedback of the adaptation algorithm
In, the adjustment of solution is an interactive process, and the assessment of medical worker (user) feedback guides.The solution of target case is every
After secondary execution, the feedback whether user is satisfied with about solution can be all received.If feedback the result is that dissatisfied, need to discontented
The reason of meaning, is analyzed, analysis the result is that used during case adjustment later, then generate therapeutic scheme, again
It executes and feeds back, until user feedback result is to terminate case adjustment when being satisfied with, obtain final therapeutic scheme.
Step S205：The last diagnostic result is passed through the data center's layer and institute by cloud computing intelligent medical treatment layer respectively
It states environment sensing layer and is sent to the wearable device, so that the user obtains the last diagnostic result.
In specific implementation, when obtaining the final therapeutic scheme of target case, cloud computing intelligent medical treatment layer can be by institute
State that final therapeutic scheme passes sequentially through the data center's layer and the environment sensing layer is sent to the wearable device, so that
It obtains the user and obtains final diagnostic result.
In an embodiment of the present invention, in order to improve the quality for diagnosing case in diagnosis case database, the method is also
Including：
Step S206：Cloud computing intelligent medical treatment layer is updated the diagnosis case in the diagnosis case database.
In an embodiment of the present invention, in one new target case of every generation, cloud computing intelligent medical treatment layer can be adopted
Corresponding diagnosis case to be stored is generated with the final therapeutic scheme of the target case and the target case, and judges to give birth to
At wait store diagnosis case and the diagnosis case in corresponding sub- case database between similarity numerical value；When determination is given birth to
At wait store diagnosis case and the diagnosis case in corresponding sub- case database between similarity numerical value be all larger than it is default
Similarity threshold when, by it is generated wait store diagnosis case be stored in the diagnosis case database.
In an embodiment of the present invention, cloud computing intelligent medical treatment layer can also pass through the diagnosis in diagnosed case database
The mode that case is simplified come to it is described diagnosis case database in diagnosis case be updated, to improve diagnosis case number of cases
According to the quality in library.Wherein, cloud computing intelligent medical treatment layer is being simplified by the diagnosis case in diagnosed case database
Mode come to it is described diagnosis case database in diagnosis case be updated when, the diagnosis case data can be calculated first
The frequency that is cited of diagnosis case within a preset time in library, and when the determining frequency that is cited is less than preset frequency threshold
When, corresponding diagnosis case is deleted from the diagnosis case database.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer instruction, described
The step of smart cloud medical method is executed when computer instruction is run.Wherein, the step of the smart cloud medical method
Suddenly preceding sections are referred to, repeated no more.
The embodiment of the invention also provides a kind of terminal, including memory and processor, energy is stored on the memory
Enough computer instructions run on the processor, the processor execute the wisdom when running the computer instruction
The step of cloud medical method, refers to preceding sections, repeats no more.
Using the above scheme in the embodiment of the present invention, carried out using physiologic information of the cloud computing intelligent medical treatment layer to user
Analysis processing obtains corresponding medical treatment result, and the output of obtained medical treatment result is shown to medical worker, and described in use
The final medical treatment result that medical worker generates the feedback information of the medical treatment result, finally leads to the last diagnostic result respectively
It crosses the data center's layer and the environment sensing layer is sent to the wearable device, so that user acquisition is described most
The processing speed of data can be improved in whole diagnostic result, so as to improve diagnosis and treatment efficiency.
Further, case database and sub- case database two-stage are represented by using the diagnosis case database
Structure so that the cloud computing intelligent medical treatment layer determine optimal candidate diagnose case when, only by target case and the diagnosis
The diagnosis case accordingly represented in the corresponding sub- case database of case database in case database is matched, rather than by mesh
Mark case is matched one by one with all diagnosis cases of the diagnosis case database, therefore optimal candidate diagnosis case can be improved
The retrieval rate of example, so as to further increase diagnosis and treatment efficiency.
Further, the cloud computing intelligent medical treatment layer uses the final treatment of the target case and the target case
The corresponding diagnosis case to be stored of schemes generation, and it is generated wait store diagnosis case and corresponding sub- case data when determining
When the similarity numerical value between diagnosis case in library is all larger than preset similarity threshold, by diagnosis case to be stored generated
Example is stored in the diagnosis case database, and the expansion of diagnosis case database can be effectively prevented, it is ensured that improves diagnosis case
The quality of the diagnosis case stored in example database, improves the accuracy of diagnosis and treatment.
Further, the cloud computing intelligent medical treatment layer is existed by calculating the diagnosis case in the diagnosis case database
The frequency that is cited in preset time, and when determining the frequency that is cited less than preset frequency threshold, by corresponding diagnosis case
Example is deleted from the diagnosis case database, can be simplified to diagnosis case database, be improved diagnosis case database
The quality of middle stored diagnosis case, improves the accuracy of diagnosis and treatment.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in computer readable storage medium, and storage is situated between
Matter may include：ROM, RAM, disk or CD etc..
Although present disclosure is as above, present invention is not limited to this.Anyone skilled in the art are not departing from this
It in the spirit and scope of invention, can make various changes or modifications, therefore protection scope of the present invention should be with claim institute
Subject to the range of restriction.
Claims (8)
1. a kind of smart cloud medical treatment real-time management system of case-based reasioning, which is characterized in that including the environment successively coupled
Sensing layer, data center's layer and cloud computing intelligent medical treatment layer；
The environment sensing layer, the physiologic information that user is acquired by wearable device and remote transmission is to data center's layer；
The data center's layer, suitable for receiving the physiologic information of the user and storing to physiological data library；
The cloud computing intelligent medical treatment layer, the physiologic information suitable for obtaining user from the physiological data library carry out analysis place
Reason, obtains corresponding medical treatment result, and obtained medical treatment result is passed sequentially through the data center's layer and the environment sense
Know that layer is sent to the wearable device, so that the user obtains the medical treatment result.
2. the smart cloud medical treatment real-time management system of case-based reasioning according to claim 1, which is characterized in that
The environment sensing layer is further adapted for acquiring clinical treatment information and medical knowledge information from hospital and is sent to the data
Central core；
The data center's layer is further adapted for receiving the clinical treatment information and medical knowledge information and be stored respectively to diagnosis case
Example database and expertise database.
3. the smart cloud medical treatment real-time management system of case-based reasioning according to claim 2, which is characterized in that described
There is abnormal physiologic information suitable for obtaining from the physiological data library, generate corresponding target in cloud computing intelligent medical treatment layer
Case；The target case is matched with the diagnosis case in diagnosis case database, obtains optimal candidate diagnosis case；
The diagnosis case database is to be handled to obtain to the clinical case database and expertise database；When not matching
When diagnosing case to optimal candidate, the expertise database is handled to obtain is matched most with the target case
Good candidate diagnosis case；Using the therapeutic scheme of optimal candidate diagnosis case as the Primary treatment scheme of target case；When
When determining that user is satisfied with the Primary treatment scheme being calculated, using the Primary treatment scheme as final therapeutic scheme；When
When determining that user is dissatisfied to the Primary treatment scheme being calculated, using adaptation algorithm and the expertise database to institute
It states Primary treatment scheme to be adjusted, obtains the final therapeutic scheme.
4. the smart cloud medical treatment real-time management system of case-based reasioning according to claim 3, which is characterized in that described
Diagnosis case database, which uses, represents case database and sub- case database two-level configuration；The case database that represents includes
The typical diagnostic case of the crucial disease characteristic attribute of disease；The sub- case database be include predetermined disease characteristic attribute
All diagnosis cases；It is described to represent case database and the sub- case database one-to-one correspondence；
The cloud computing intelligent medical treatment layer, suitable for calculating separately the target case using nearest neighbor method and representing case data
Similarity numerical value between library；The corresponding sub- case database of case database is represented by similarity numerical value is highest, as
Matched sub- case database；Calculate separately the diagnosis case in the target case and obtained matched sub- case database
The distance between example；Pre-determined distance threshold value and the corresponding diagnosis case of the smallest distance values will be less than as the optimal candidate
Diagnose case.
5. the smart cloud medical treatment real-time management system of case-based reasioning according to claim 4, which is characterized in that described
Cloud computing intelligent medical treatment layer, suitable for calculating the target case and obtained matched sub- case data using following formula
The distance between diagnosis case in library：
And
Wherein, dti' indicate target case and the distance between the diagnosis case in obtained matched sub- case database, Wj
Indicate the weight of j-th of characteristic attribute, TjIndicate j-th of crucial disease characteristic attribute value of target case, n is crucial disease
Wait the total number of characteristic attribute, YijThe value of j-th of characteristic attribute of i-th of case after indicating normalization, min YiExpression is returned
The minimal characteristic attribute value of i-th of case, max Y after one changeiIndicate the maximum characteristic attribute value of i-th of case after normalizing, Yi
Indicate the characteristic attribute value of i-th of case after normalizing, MijIndicate intermediate variable.
6. according to the smart cloud medical treatment real-time management system of the described in any item case-based reasionings of claim 3-5, feature
It is,
The cloud computing intelligent medical treatment layer is further adapted for being updated the diagnosis case in the diagnosis case database.
7. smart cloud medical system according to claim 6, which is characterized in that the cloud computing intelligent medical treatment layer is suitable for
Corresponding diagnosis case to be stored is generated using the final therapeutic scheme of the target case and the target case；Judgement is given birth to
At wait store diagnosis case and the diagnosis case in corresponding sub- case database between similarity numerical value；When determination is given birth to
At wait store diagnosis case and the diagnosis case in corresponding sub- case database between similarity numerical value be all larger than it is default
Similarity threshold when, by it is generated wait store diagnosis case be stored in the diagnosis case database.
8. the smart cloud medical treatment real-time management system of case-based reasioning according to claim 6, which is characterized in that described
Cloud computing intelligent medical treatment layer, suitable for calculating the frequency that is cited of the diagnosis case in the diagnosis case database within a preset time
Rate；When determining the frequency that is cited less than preset frequency threshold, by corresponding diagnosis case from the diagnosis case database
Middle deletion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810642563.9A CN108847280A (en) | 2018-06-20 | 2018-06-20 | The smart cloud medical treatment real-time management system of case-based reasioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810642563.9A CN108847280A (en) | 2018-06-20 | 2018-06-20 | The smart cloud medical treatment real-time management system of case-based reasioning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108847280A true CN108847280A (en) | 2018-11-20 |
Family
ID=64203178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810642563.9A Pending CN108847280A (en) | 2018-06-20 | 2018-06-20 | The smart cloud medical treatment real-time management system of case-based reasioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108847280A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559833A (en) * | 2018-11-27 | 2019-04-02 | 北京唐冠天朗科技开发有限公司 | A kind of remote diagnosis system and method |
| CN110246046A (en) * | 2019-04-24 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Health informs case maintemance system, method and device |
| CN110957046A (en) * | 2019-11-15 | 2020-04-03 | 合肥工业大学 | Medical health case knowledge matching method and system |
| CN111557651A (en) * | 2020-05-28 | 2020-08-21 | 复旦大学附属儿科医院 | Automatic identifier for venous exudation and phlebitis |
| CN112382383A (en) * | 2020-11-04 | 2021-02-19 | 北京紫冬认知科技有限公司 | Diagnosis and treatment data processing method and device, server and storage medium |
| CN113345587A (en) * | 2021-06-16 | 2021-09-03 | 北京邮电大学 | Man-machine collaborative health case matching method and system based on chronic disease big data |
| CN115359868A (en) * | 2022-09-14 | 2022-11-18 | 亿慧云智能科技（深圳）股份有限公司 | Intelligent medical monitoring method and system based on cloud computing technology |
| CN117238533A (en) * | 2023-11-16 | 2023-12-15 | 首都医科大学附属北京同仁医院 | Medical care system based on intelligent wearing and real-time diagnosis and knowledge graph |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116707A (en) * | 2013-03-04 | 2013-05-22 | 北京工业大学 | Heart disease intelligent diagnostic method based on case reasoning |
| CN104636430A (en) * | 2014-12-30 | 2015-05-20 | 东软集团股份有限公司 | Case knowledge base representation and case similarity obtaining method and system |
| CN105260598A (en) * | 2015-09-29 | 2016-01-20 | 中南大学 | Oral diagnosis and treatment decision support system and decision method |
| US20160125162A1 (en) * | 2014-10-30 | 2016-05-05 | Panasonic Corporation | Method for controlling information terminal, and recording medium |
| CN106055909A (en) * | 2016-06-14 | 2016-10-26 | 华南师范大学 | Treatment plan recommending system based on big data knowledge base |
| CN107845411A (en) * | 2017-12-04 | 2018-03-27 | 青岛大学附属医院 | Clinical medication decision support system |
-
2018
- 2018-06-20 CN CN201810642563.9A patent/CN108847280A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116707A (en) * | 2013-03-04 | 2013-05-22 | 北京工业大学 | Heart disease intelligent diagnostic method based on case reasoning |
| US20160125162A1 (en) * | 2014-10-30 | 2016-05-05 | Panasonic Corporation | Method for controlling information terminal, and recording medium |
| CN104636430A (en) * | 2014-12-30 | 2015-05-20 | 东软集团股份有限公司 | Case knowledge base representation and case similarity obtaining method and system |
| CN105260598A (en) * | 2015-09-29 | 2016-01-20 | 中南大学 | Oral diagnosis and treatment decision support system and decision method |
| CN106055909A (en) * | 2016-06-14 | 2016-10-26 | 华南师范大学 | Treatment plan recommending system based on big data knowledge base |
| CN107845411A (en) * | 2017-12-04 | 2018-03-27 | 青岛大学附属医院 | Clinical medication decision support system |
Non-Patent Citations (2)
| Title |
|---|
| GUO-NIU ZHU等: "An integrated feature selection and cluster analysis techniques for case-based reasoning", 《ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE》 * |
| 赖春媛等: "基于云雾融合的工业物联网能源管理架构", 《电信科学》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559833A (en) * | 2018-11-27 | 2019-04-02 | 北京唐冠天朗科技开发有限公司 | A kind of remote diagnosis system and method |
| CN110246046A (en) * | 2019-04-24 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Health informs case maintemance system, method and device |
| CN110246046B (en) * | 2019-04-24 | 2023-01-10 | 创新先进技术有限公司 | Health notification case maintenance system, method and device |
| CN110957046A (en) * | 2019-11-15 | 2020-04-03 | 合肥工业大学 | Medical health case knowledge matching method and system |
| CN110957046B (en) * | 2019-11-15 | 2024-01-19 | 合肥工业大学 | Medical health case knowledge matching method and system |
| CN111557651A (en) * | 2020-05-28 | 2020-08-21 | 复旦大学附属儿科医院 | Automatic identifier for venous exudation and phlebitis |
| CN111557651B (en) * | 2020-05-28 | 2024-03-12 | 复旦大学附属儿科医院 | Automatic identification instrument for venous exudation and phlebitis |
| CN112382383A (en) * | 2020-11-04 | 2021-02-19 | 北京紫冬认知科技有限公司 | Diagnosis and treatment data processing method and device, server and storage medium |
| CN113345587A (en) * | 2021-06-16 | 2021-09-03 | 北京邮电大学 | Man-machine collaborative health case matching method and system based on chronic disease big data |
| CN115359868A (en) * | 2022-09-14 | 2022-11-18 | 亿慧云智能科技（深圳）股份有限公司 | Intelligent medical monitoring method and system based on cloud computing technology |
| CN117238533A (en) * | 2023-11-16 | 2023-12-15 | 首都医科大学附属北京同仁医院 | Medical care system based on intelligent wearing and real-time diagnosis and knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108847280A (en) | The smart cloud medical treatment real-time management system of case-based reasioning | |
| US20210142915A1 (en) | Clinical predictive analytics system | |
| CN109805898B (en) | Critical death prediction method based on attention mechanism time sequence convolution network algorithm | |
| Khafaga et al. | Optimization of Electrocardiogram Classification Using Dipper Throated Algorithm and Differential Evolution. | |
| CN103690240B (en) | A kind of medical system | |
| Peter et al. | An empirical study on prediction of heart disease using classification data mining techniques | |
| Sufi et al. | Diagnosis of cardiovascular abnormalities from compressed ECG: a data mining-based approach | |
| CN111990989A (en) | Electrocardiosignal identification method based on generation countermeasure and convolution cyclic network | |
| CN103201743A (en) | Method of continuous prediction of patient severity of illness, mortality, and length of stay | |
| Zaeri-Amirani et al. | A feature selection method based on shapley value to false alarm reduction in icus a genetic-algorithm approach | |
| CN108877932A (en) | Smart cloud medical method, computer readable storage medium and terminal | |
| Feng et al. | Dcmn: Double core memory network for patient outcome prediction with multimodal data | |
| Bajpai et al. | Early Prediction of Cardiac Arrest Using Hybrid Machine Learning Models | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| TWI688371B (en) | Intelligent device for atrial fibrillation signal pattern acquisition and auxiliary diagnosis | |
| Santos et al. | Enabling ubiquitous data mining in intensive care-features selection and data pre-processing | |
| CN110580951A (en) | diagnosis and monitoring comprehensive medical system with encrypted communication and encryption method thereof | |
| Elbasi et al. | Efficient early prediction and diagnosis of diseases using machine learning algorithms for IoMT data | |
| US20200185101A1 (en) | Decision support device | |
| Nanarkar et al. | A Survey on Classification and identification of Arrhythmia using Machine Learning techniques | |
| Vatambeti et al. | Intelligent diagnosis of obstetric diseases using HGS-AOA based extreme learning machine | |
| Ancy et al. | A predictive model for kidney failure E-health | |
| Pushparaj et al. | Prediction of Heart Disease Using Hybrid of CNN-LSTM Algorithm | |
| Shenoy | Performance Analysis of Class Imbalance Handling Techniques for Early Sepsis Prediction using Machine Learning Algorithms | |
| Rodrigues et al. | COMPARATIVE ANALYSIS ON SURVIVAL PREDICTION OF HEART FAILURE PATIENTS IN THEIR FOLLOW-UP PERIOD |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181120 |
|
| RJ01 | Rejection of invention patent application after publication |