CN113851203B - Neonate eye fundus screening collaborative learning method and system based on POS mechanism - Google Patents
Neonate eye fundus screening collaborative learning method and system based on POS mechanism Download PDFInfo
- Publication number
- CN113851203B CN113851203B CN202111445433.4A CN202111445433A CN113851203B CN 113851203 B CN113851203 B CN 113851203B CN 202111445433 A CN202111445433 A CN 202111445433A CN 113851203 B CN113851203 B CN 113851203B
- Authority
- CN
- China
- Prior art keywords
- node
- diagnosis
- request
- typical case
- treatment
- 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.)
- Active
Links
Images
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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/604—Tools and structures for managing or administering access control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2141—Access rights, e.g. capability lists, access control lists, access tables, access matrices
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Security & Cryptography (AREA)
- Bioethics (AREA)
- Public Health (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Automation & Control Theory (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The method provided by the application realizes high-quality sharing on a neonatal ophthalmologic medical resource chain through a block chain technology, improves the information transmission efficiency and ensures the safety of data exchange and sharing; diagnosis and treatment assistance and learning are provided through the established typical case library and the diagnosis and treatment model library, the diagnosis level of a common doctor is improved, and further, the problem that the traditional POS algorithm is separated from the practical significance and unreasonable in share right distribution is solved through a novel POS consensus mechanism, so that the whole eye ground disease diagnosis and treatment and sharing whole process is mastered by the most trusted nodes, and the data safety is further improved.
Description
Technical Field
The invention relates to the technical field of neonatal fundus screening, in particular to a method and a system for neonatal fundus screening collaborative learning based on a POS mechanism.
Background
The eye ground disease diagnosis and treatment for the neonate are more and more emphasized by people, however, as the diagnosis and treatment has the characteristics of short optimal intervention (treatment period), high eye ground picture similarity, difficult accurate diagnosis and the like, the medical resources which can often perform the diagnosis are very short, and the short supply is mainly reflected by: firstly, the doctor who has the diagnosis and treatment qualification has less resources; secondly, doctors are mostly concentrated in known hospitals, third hospitals or national treatment centers, so that only national and regional diagnosis and treatment centers can carry out diagnosis and treatment, and a part of local primary hospitals lack diagnosis and treatment experience; and thirdly, information transmission among the primary hospitals, the regional diagnosis and treatment center and the national diagnosis and treatment center is not smooth, and an effective cooperative diagnosis and treatment mechanism cannot be established.
In the prior art, when a primary hospital needs to perform the diagnosis and treatment and does not have diagnosis and treatment conditions, the mode shown in fig. 1 is usually adopted, the primary hospital transmits fundus images and related information to be diagnosed to a regional diagnosis and treatment center with a higher medical level and a larger scale, if the regional diagnosis and treatment center still cannot diagnose, the fundus images and the related information need to be continuously transmitted to a higher national treatment center, and after a diagnosis result or a diagnosis report is given by the national treatment center, the fundus images and the related information are transmitted to the primary hospital step by step.
The method has many hidden dangers, for example, the child case information and the diagnosis records for diagnosis belong to secret information, the privacy requirement is high, on the basis that all units do not trust each other, the risk of direct sharing is large, the risk of malicious interception in the transmission process exists, and the data safety is difficult to guarantee. Meanwhile, the method does not fundamentally solve the problem of shortage of medical resources, when facing a plurality of diagnosis and treatment tasks, the higher efficiency is difficult to achieve only by the treatment of a national diagnosis and treatment center, and the transmission efficiency is low, so that the optimal period of the disease diagnosis is easily exceeded.
Disclosure of Invention
The application provides a neonatal fundus screening collaborative learning method and system based on a POS mechanism, and aims to solve the problems of low diagnosis efficiency and poor data safety in the prior art.
In a first aspect, the application provides a coordinated learning method for neonatal fundus screening based on a POS mechanism, which is applied to a block chain bottom platform composed of an application node, a diagnosis node, an audit node, a college expert node, and an authority control node, and the method includes:
the application node generates a first request and stores the first request in an uplink manner; the first request comprises data to be diagnosed, patient information and appointed diagnosis node information;
the diagnostic node corresponding to the first request obtains the first request from the block chain, and generates a diagnostic result according to the first request;
the diagnosis node generates a diagnosis data packet by the diagnosis result, the diagnosis node signature and the first request, and stores the diagnosis data packet in an uplink manner;
the application node acquires a diagnosis data packet corresponding to the first request and stored on a block chain, and judges whether a request for generating a typical case is provided for the diagnosis data packet or not;
if so, the application node generates a case request according to the diagnosis data packet and simultaneously sends the case request to the diagnosis node and the auditing node;
the case auditing node adds cases corresponding to the diagnosis data packet in a typical case library according to authorization information which is fed back by the diagnosis node and relates to the case request;
generating a diagnosis and treatment model by the expert nodes of the colleges and universities according to the cases in the typical case base, and storing the diagnosis and treatment model in a diagnosis and treatment model base corresponding to the typical case base in a block chain;
and the authority control node configures corresponding authority for the nodes corresponding to the cases or the models by adopting a POS common identification mechanism according to the cases stored in the typical case library and the diagnosis and treatment models stored in the diagnosis and treatment model library.
In some embodiments, the step of configuring the corresponding authority for the node corresponding to the case or the model by using the POS consensus mechanism includes:
the authority control node respectively configures a contribution value for the data to be diagnosed, the diagnosis result and the diagnosis model corresponding to each case added into the typical case library;
counting the sum of the contribution values of all nodes corresponding to the case or the model;
and configuring the authority for accessing the typical case base, the authority for calling the diagnosis and treatment model and the share weight in the node consensus for the node according to the sum of the contribution values of the node.
In some embodiments, a CA authentication node is further included in the blockchain system, the method further comprising:
the application node, the diagnosis node or the expert node in colleges and universities send an authentication request to the CA authentication node; the authentication request comprises node information and a node signature;
the CA authentication node verifies the authentication request, and if the authentication request passes the verification, a digital certificate is issued to an application node, a diagnosis node or an expert node in colleges and universities;
the first request also comprises a digital certificate of the application node;
prior to storing the first requested uplink, the method further comprises: and the block chain verifies the first request, and if the first request is not verified, the first request is rejected.
In some embodiments, if the authentication is verified, the CA authentication node configures a public and private key pair for encrypting uplink data for the node sending the authentication request;
the method for generating the first request by the application node and uplink-storing the first request comprises the following steps:
the application node generates a first request for the data to be diagnosed, the patient information and the appointed diagnosis node information;
encrypting the first request by adopting a public key which is configured by the CA node and corresponds to the diagnosis node to obtain a first request ciphertext;
the first request cryptogram is ul stored.
In some embodiments, the diagnostic node obtains the first request from the blockchain, and the step of generating the diagnostic result according to the first request includes:
the diagnosis node decrypts the first request ciphertext by adopting a private key configured by the CA node to obtain a first request, and generates a diagnosis result according to the first request.
In some embodiments, if the diagnostic node is not capable of generating a diagnostic result from the first request, the method further comprises:
the diagnostic node generates a handover request according to the first request and newly-designated diagnostic node information, encrypts the handover request by adopting a public key configured by the CA node and then uplinks and stores the handover request;
and the diagnosis node corresponding to the handover request acquires the handover request from the block chain and generates a diagnosis result according to the handover request.
In some embodiments, the step of generating, by the college expert node, a diagnosis model according to the cases in the typical case base includes:
the college expert node sends a request for applying for accessing the typical case base to the authority control node; the request includes a digital certificate;
the authority control node verifies the authority of the college expert node according to the request;
if the verification is passed, allowing the college expert node to access the typical case base and obtain a case;
and modeling and analyzing by the expert nodes of the colleges and universities according to the obtained cases to obtain a diagnosis and treatment model.
In some embodiments, the right to access the typical case base and the right to invoke the diagnosis and treatment model include:
the basic data can be seen, the basic data can be modified, the analysis result can be seen or the analysis result can be modified.
In some embodiments, the method further comprises:
and the right control node configures the times of accessing the typical case base and calling the diagnosis and treatment model for the node according to the sum of the contribution values of the node.
In a second aspect, the present application further provides a system applying the method of the first aspect.
According to the technical scheme, the scheme of the application has the following beneficial effects:
firstly, data security sharing is realized, a block chain technology is combined with the field of neonatal disease diagnosis, and the privacy and the security of transmitted data are ensured through Hash calculation and a public and private key pair;
establishing a reasonable contribution degree value evaluation mechanism, wherein the higher the contribution degree is, the higher the data visibility is, the higher the modification authority is, so that the whole fundus disease diagnosis and treatment and sharing whole process is mastered by the most trusted node, and the data safety is further improved;
and thirdly, the established typical case library and diagnosis model library are beneficial to improving the diagnosis level of a common doctor, the medical competence is fundamentally expanded, a child fundus disease diagnosis and treatment system with safe data, high transmission efficiency and good closed loop is formed, and more sick children can be treated in time within the best prognosis.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a scene diagram of disease diagnosis and treatment in the prior art;
fig. 2 is an application scene diagram of a cooperative learning method for neonatal fundus screening based on a POS mechanism provided by the present application;
fig. 3 is a schematic flow chart of steps S100 to S400 in the method provided in the present application;
FIG. 4 is a schematic flow chart of steps S100 to S400 according to another embodiment;
fig. 5 is a schematic flowchart of steps S500 to S800 in the method provided by the present application.
Detailed Description
Referring to fig. 2, an application scenario diagram of a cooperative learning method for neonatal fundus screening based on a POS mechanism is provided in the present application;
as can be seen from fig. 2, the method provided in the present application is applied to a block chain bottom platform formed by an application node, a diagnosis node, an audit node, a college expert node, and an authority control node, where the application node refers to a node where a medical institution which does not have diagnosis and treatment qualification per se is located, for example, a base-level hospital node, a regional diagnosis and treatment center node, and a national diagnosis and treatment center node in fig. 2 may all be used as the application node in the present application, and the diagnosis node refers to a node where a medical institution which diagnoses a certain disease to obtain a diagnosis result, and is generally served by the regional diagnosis and treatment center node and the national diagnosis and treatment center node. It should be noted that each node in the blockchain is not in a fixed role, that is, one node may be an application node of one medical diagnosis application, and may also be a diagnosis node, an audit node, or other nodes of another medical diagnosis application.
The method provided by the application is not limited to a method for screening and diagnosing the fundus oculi of the neonate, and the method can be used for other diseases with the same or similar characteristics with the fundus oculi diseases of the neonate. The fundus disease is only exemplified in the present embodiment, and it should be considered that the method of the present application can be applied to other needs for timely intervention, shortage of doctor resources, and prior art as described in the background of the present application.
In an actual application scenario, case auditing nodes are generally served by authoritative medical institutions and medical associations, the main task is to divide fundus disease types according to the similarity of fundus pictures, and generally, the greater the difference between the fundus pictures and existing pictures is, the rarer the explanation is, and the more easily the case is considered as a typical case. The college expert nodes are generally served by colleges, research institutes or other scientific research institutions, experts or researchers of the college, research institutes or other scientific research institutions can perform modeling analysis according to typical cases, and periodically upload various fundus disease diagnosis and treatment models, and the diagnosis and treatment models can provide auxiliary decisions for hospitals and doctors without diagnosis and treatment.
Based on the application scenario, as shown in fig. 3, the method of the present application includes:
s100: the application node generates a first request and stores the first request in an uplink manner; the first request comprises data to be diagnosed, patient information and appointed diagnosis node information;
when a hospital (e.g., a primary hospital) at an application node faces an eye ground diagnosis task, if a doctor does not have the diagnosis capability, a task generation request (first request) can be sent to a blockchain, and other nodes with the diagnosis capability in the blockchain are requested to perform diagnosis, so that the first request at this time at least includes the following information, for example, data to be diagnosed, such as an eye ground picture, and the like, and also includes patient information, such as patient name, age, sex, medical record, and the like, and further includes designated diagnosis node information in the first request, where the designated diagnosis node may be a primary hospital at the primary hospital, or a regional diagnosis center or a national diagnosis center at the primary site, and the like.
The first request may contain, in addition to the above information, identity information of the node that sent the first request, such as a signature of the application node, or a digital certificate issued by a CA certification authority, etc., to prove the authenticity of the request.
Further, in the present application, in order to improve the authenticity and credibility of data transmission and data uplink requests between nodes, each node involved in the method may first obtain a digital certificate by the following method:
specifically, the operation of issuing the digital certificate is completed by CA authentication nodes in the same blockchain system, and the method for each node to acquire the digital certificate includes:
step a: the application node, the diagnosis node or the expert node in colleges and universities send an authentication request to the CA authentication node; the authentication request comprises node information and a node signature;
step b: the CA authentication node verifies the authentication request, and if the authentication request passes the verification, a digital certificate is issued to an application node, a diagnosis node or an expert node in colleges and universities; and meanwhile, the digital certificate and the authentication process data are linked and stored, so that the digital certificate cannot be tampered.
On the basis, in step S100, the first request further includes a digital certificate of the application node; thus, before the first request is stored, the method may further include the step of verifying: and the block chain verifies the first request, if the digital certificate is verified to be legal, the subsequent steps are continuously executed, and if the digital certificate is not verified, the block chain directly refutes the first request and does not execute the subsequent steps.
Further, in order to ensure privacy and security of data, when a CA certification authority issues a digital certificate, a CA certification node configures a public and private key pair for encrypting uplink data for a node sending a certification request; therefore, before the first request of the uplink is sent by the application node, the public key corresponding to the diagnosis node can be used for encryption and then the uplink is sent, only the corresponding diagnosis node can decrypt the encrypted data by using the local private key to obtain the data plaintext, and other nodes can not obtain the data plaintext of the privacy information of the patient even if the request is obtained, so that the problem that the data plaintext is intercepted maliciously in the data transmission process is solved.
Specifically, on this basis, the step S100 is decomposed into:
the application node generates a first request for the data to be diagnosed, the patient information and the appointed diagnosis node information;
encrypting the first request by adopting a public key which is configured by the CA node and corresponds to the diagnosis node to obtain a first request ciphertext;
the first request cryptogram is ul stored.
S200: the diagnostic node corresponding to the first request obtains the first request from the block chain, and generates a diagnostic result according to the first request;
a designated diagnosis node (e.g., regional diagnosis center or national diagnosis center) may automatically obtain a first request (diagnosis requirement) related to itself from the blockchain, and if the node is capable of diagnosing itself, a corresponding diagnosis may be given according to the content of the first request, and a diagnosis result may be given.
Further, if the first request is encrypted in step S100, in step S200, after the diagnostic node obtains the first request, a decryption step is also performed, specifically, the diagnostic node may decrypt the first request ciphertext by using a private key configured by the CA node to obtain the first request, and then generate a diagnostic result according to the first request.
S300: the diagnosis node generates a diagnosis data packet by the diagnosis result, the diagnosis node signature and the first request, and stores the diagnosis data packet in an uplink manner;
in this embodiment, the generated diagnostic data packet can be uplinked after being encrypted, and the public key of the application node is used during encryption, so that the diagnostic data packet can be decrypted only after the application node obtains the diagnostic data packet, and other nodes are prevented from maliciously stealing the diagnostic result or the patient information.
S400: the application node obtains a diagnostic data packet corresponding to the first request stored on the blockchain. After the encrypted diagnosis data packet is decrypted by using the local private key, the application node can obtain the plaintext of the diagnosis result and can correspondingly execute other medical means by referring to the diagnosis result.
The above steps of S100 to S400 are for describing the case where the designated diagnostic node can perform diagnosis, and the case where the diagnostic node cannot perform diagnosis will be described below.
Since the primary hospital can only issue a request to a higher-level hospital when the primary hospital is unable to perform self-diagnosis, but the designated hospital may also be unable to perform diagnosis, when the designated hospital does not have a diagnosis condition, the designated hospital can be used as an intermediate to forward the diagnosis request to the higher-level hospital, and therefore, in one scenario shown in fig. 4, when the diagnosis node does not have a diagnosis condition, the method of the present application further includes:
s210: the diagnosis node generates a handover request according to the first request and newly-assigned diagnosis node information, and the handover request is encrypted by adopting a public key configured by the CA node and then uplink storage is carried out, and at the moment, the public key of the newly-assigned diagnosis node is used for encryption.
S220: and the diagnosis node corresponding to the handover request acquires the handover request from the block chain and generates a diagnosis result according to the handover request.
Fig. 4 shows the case of the handover only once, and it is considered that, when the hospital to be handed over still cannot diagnose, the above handover process may be performed again until the diagnostic node after being handed over has the diagnostic condition.
After the application node obtains the diagnostic data packet, the method of the present application may be continued from fig. 5:
s500: determining whether a request to generate a representative case is made for the diagnostic data package;
based on the analysis of the diagnosis results, the applicant can decide whether the case is of a type that has been presented before or belongs to a more typical case, and a request for generating a typical case can be made according to the decision of the applicant.
If so, the application node generates a case request according to the diagnosis data packet and simultaneously sends the case request to the diagnosis node and the auditing node;
if the case can be used as the typical case, the applicant and the diagnostician need to obtain the consent, and if the diagnostician does not agree to disclose the diagnosis result, the applicant cannot use the case as the typical case without permission.
It should be noted that the case request here should contain various information related to the diagnosis, but the information of the patient, such as the name of the child, sensitive and private data unrelated to the diagnosis, is hidden.
After receiving the case request, the diagnosis node may choose to authorize the case request and also feed back authorization information to the case auditing node, and the case auditing node performs step S600 according to the authorization information about the case request fed back by the diagnosis node: adding cases corresponding to the diagnosis data packets in a typical case library; the typical case base is a storage address of each type of case, and each node can access the typical case base or call the cases in the typical case base according to the authority of the node. When the case auditing node inspects the case request, the case auditing node needs to check whether the inspected case has typicality, is repeated or not, and the case auditing link is started on the premise that the fundus picture provider and the diagnosis result provider agree that the case is shared.
S700: generating a diagnosis and treatment model by the expert nodes of the colleges and universities according to the cases in the typical case base, and storing the diagnosis and treatment model in a diagnosis and treatment model base corresponding to the typical case base in a block chain; the method for generating the diagnosis and treatment model is not limited in the application, and the generated diagnosis and treatment model can be understood as an insertion of an AI model, wherein the insertion contains tens of thousands of case data, and can provide an auxiliary diagnosis effect for some primary hospitals or doctors without diagnosis and treatment experience. With the increasing number of cases in a typical case base, college expert nodes also need to periodically increase/update the diagnosis and treatment model, so that the output result of the model is more accurate and is more practical.
Further, the steps specifically include:
s710: the college expert node sends a request for applying for accessing the typical case base to the authority control node; the request includes a CA-authenticated digital certificate;
s720: the authority control node verifies the authority of the college expert node according to the request; the verification here includes authentication of the identity of the college expert, such as verifying the authenticity of the digital certificate, and also includes verifying whether the node has access or download authority, or whether the current access times reach the permitted times, and so on.
If the verification is passed, allowing the college expert node to access the typical case base and acquiring a case from the typical case base for modeling;
s730: and modeling and analyzing by the expert nodes of the colleges and universities according to the obtained cases to obtain a diagnosis and treatment model.
According to the method, the medical data forming case is provided for college experts, diagnosis and treatment models are generated by the college experts and then provided for medical institutions to use, scientific research and medical resources are effectively integrated, the diagnosis level of common doctors is improved, medical resource force is fundamentally expanded, simple data sharing is not achieved, a child fundus disease diagnosis and treatment system with safe data, efficient transmission and good closed loop is formed, and more sick children can be diagnosed and treated within the best expectation.
S800: and the authority control node configures corresponding authority for the nodes corresponding to the cases or the models by adopting a POS common identification mechanism according to the cases stored in the typical case library and the diagnosis and treatment models stored in the diagnosis and treatment model library.
In this embodiment, in order to increase the enthusiasm of each node to participate in executing a diagnosis and treatment task or providing a case and a diagnosis and treatment model, a "stock right" mechanism is proposed to determine the authority of each node, that is, an improved stock right and interest certification consensus algorithm is provided. The share weight is in direct proportion to the contribution value of the node, and the higher the contribution value is, the higher the weight is when the node participates in consensus, and the higher the authority of the node is. In the scheme, nodes providing basic fundus information (fundus pictures), diagnosis results, diagnosis and treatment models and the like can obtain certain contribution values, and different authorities can be allocated to the nodes according to the contribution values owned by the nodes, for example, when a certain node is specified to access a typical case library, the node can be divided into several authority types such as basic data visible, basic data modifiable, analysis result visible or analysis result modifiable, and the like; while nodes with lower contribution values, which may not have any permissions, are not allowed access.
When the authority is regulated, the authority control node can also configure the times of accessing the typical case base and calling the diagnosis and treatment model for the node according to the sum of the contribution values of the node, for example, the node A is regulated to be accessible to the typical case base four times a day, and the access is not allowed to continue after the preset times are exceeded; or node a may be specified to invoke up to 100 cases, and if so, not allow the invocation to continue, etc.
When defining the contribution value, corresponding judgment basis can be designed, for example, a typical case is provided to increase several contribution values, a diagnosis model is provided to increase several contribution values, and the like. Compared with the traditional POS consensus algorithm, the method provided by the application determines the shares through the contribution value with practical value instead of being input without doubt, all decisions in the block chain network are mastered in the hands of the trusted nodes, and data safety is further improved.
It should be noted that, because the typical case library and the diagnosis and treatment model library are updated in real time, the contribution value of each node may also change in real time, and the authority of each node may also change, for example, one node a may just provide a diagnosis and treatment model, which has an authority to access and modify the typical case library for a period of time, but when no item for increasing the contribution value is provided for a long time thereafter, it may lose the authority that was possessed before, and therefore, the authority control node also operates flexibly.
Specifically, the specific operation process of the authority control node is as follows:
respectively configuring a contribution value for the data to be diagnosed, the diagnosis result and the diagnosis model corresponding to each case added into the typical case base; for different cases, the contribution values may be all set according to a uniform rule, for example, five contribution values are added to the provider of the data to be diagnosed, ten contribution values are added to the provider of the diagnosis result, fifteen contribution values are added to the provider of the diagnosis model, and the like; the higher contribution value may be given to the case with higher importance according to the importance degree of different cases, which is not limited herein.
Counting the sum of the contribution values of all nodes corresponding to the case or the model; this step should be performed periodically, and the next step is performed according to the statistical result of each time;
and configuring the authority for accessing the typical case base, the authority for calling the diagnosis and treatment model and the share weight in the node consensus for the node according to the sum of the contribution values of the node. For example, in a block chain network with three nodes ABC, the share weight of the nodes ABC counted at the last moment is 20%/30%/50%; at the next moment, the share weight may become 60%/10%/30% because a has taken a large contribution value.
According to the technical scheme, the method provided by the application realizes high-quality sharing on the neonatal ophthalmic medical resource chain through the block chain technology, improves the information transmission efficiency, and ensures the safety of data exchange and sharing; diagnosis and treatment assistance and learning are provided through the established typical case library and the diagnosis and treatment model library, the diagnosis level of a common doctor is improved, and further, the problem that the traditional POS algorithm is separated from the practical significance and unreasonable in share right distribution is solved through a novel POS consensus mechanism, so that the whole eye ground disease diagnosis and treatment and sharing whole process is mastered by the most trusted nodes, and the data safety is further improved.
Corresponding to the method, the application also provides a system applying the method, and the system consists of an application node, a diagnosis node, an audit node, a college expert node and an authority control node; the system is configured to perform the above method.
The operation and effect of the system in applying the method can be referred to the description of the embodiment of the method, and will not be described herein again.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
Claims (10)
1. A neonatal fundus screening collaborative learning method based on a POS mechanism is applied to a block chain bottom platform consisting of an application node, a diagnosis node, an audit node, a college expert node and an authority control node; characterized in that the method comprises:
the application node generates a first request and stores the first request in an uplink manner; the first request comprises data to be diagnosed, patient information and appointed diagnosis node information;
the diagnostic node corresponding to the first request obtains the first request from the block chain, and generates a diagnostic result according to the first request;
the diagnosis node generates a diagnosis data packet by the diagnosis result, the diagnosis node signature and the first request, and stores the diagnosis data packet in an uplink manner;
the application node acquires a diagnosis data packet corresponding to the first request and stored on a block chain, and judges whether a request for generating a typical case is provided for the diagnosis data packet or not;
if so, the application node generates a case request according to the diagnosis data packet and simultaneously sends the case request to the diagnosis node and the auditing node;
the case auditing node adds cases corresponding to the diagnosis data packet in a typical case library according to authorization information which is fed back by the diagnosis node and relates to the case request;
generating a diagnosis and treatment model by the expert nodes of the colleges and universities according to the cases in the typical case base, and storing the diagnosis and treatment model in a diagnosis and treatment model base corresponding to the typical case base in a block chain;
and the authority control node configures corresponding authority for the nodes corresponding to the cases or the models by adopting a POS common identification mechanism according to the cases stored in the typical case library and the diagnosis and treatment models stored in the diagnosis and treatment model library.
2. The cooperative learning method for neonatal fundus screening based on POS mechanism as claimed in claim 1, wherein the step of configuring corresponding authority for the node corresponding to the case or model by using POS consensus mechanism comprises:
the authority control node respectively configures a contribution value for the data to be diagnosed, the diagnosis result and the diagnosis model corresponding to each case added into the typical case library;
counting the sum of the contribution values of all nodes corresponding to the case or the model;
and configuring the authority for accessing the typical case base, the authority for calling the diagnosis and treatment model and the share weight in the node consensus for the node according to the sum of the contribution values of the node.
3. The cooperative learning method for neonatal fundus screening based on POS mechanism as claimed in claim 1, wherein said blockchain system further comprises CA authentication node, said method further comprising:
the application node, the diagnosis node or the expert node in colleges and universities send an authentication request to the CA authentication node; the authentication request comprises node information and a node signature;
the CA authentication node verifies the authentication request, and if the authentication request passes the verification, a digital certificate is issued to an application node, a diagnosis node or an expert node in colleges and universities;
the first request also comprises a digital certificate of the application node;
prior to storing the first requested uplink, the method further comprises: and the block chain verifies the first request, and if the first request is not verified, the first request is rejected.
4. The cooperative learning method for neonatal fundus screening based on POS mechanism as claimed in claim 3, wherein if passing the verification, the CA authenticating node configures a public and private key pair for encrypting uplink data for the node sending the authentication request;
the method for generating the first request by the application node and uplink-storing the first request comprises the following steps:
the application node generates a first request for the data to be diagnosed, the patient information and the appointed diagnosis node information;
encrypting the first request by adopting a public key which is configured by the CA node and corresponds to the diagnosis node to obtain a first request ciphertext;
the first request cryptogram is ul stored.
5. The POS mechanism-based neonatal fundus screening cooperative learning method according to claim 4, wherein the step of the diagnosis node acquiring the first request from the block chain, and the step of generating a diagnosis result according to the first request comprises:
the diagnosis node decrypts the first request ciphertext by adopting a private key configured by the CA node to obtain a first request, and generates a diagnosis result according to the first request.
6. The POS mechanism-based neonatal fundus screening cooperative learning method according to claim 1 or 5, wherein if the diagnosis node cannot generate a diagnosis result according to the first request, the method further comprises:
the diagnostic node generates a handover request according to the first request and newly-designated diagnostic node information, encrypts the handover request by adopting a public key configured by the CA node and then uplinks and stores the handover request;
and the diagnosis node corresponding to the handover request acquires the handover request from the block chain and generates a diagnosis result according to the handover request.
7. The POS mechanism-based neonatal fundus screening collaborative learning method according to claim 3, wherein the step of generating a diagnosis and treatment model by the college expert node according to the cases in the typical case base comprises:
the college expert node sends a request for applying for accessing the typical case base to the authority control node; the request includes a digital certificate;
the authority control node verifies the authority of the college expert node according to the request;
if the verification is passed, allowing the college expert node to access the typical case base and obtain a case;
and modeling and analyzing by the expert nodes of the colleges and universities according to the obtained cases to obtain a diagnosis and treatment model.
8. The cooperative learning method for neonatal fundus screening based on POS mechanism as claimed in claim 2, wherein the right to access the typical case base and the right to invoke the diagnosis model comprises:
the basic data can be seen, the basic data can be modified, the analysis result can be seen or the analysis result can be modified.
9. The cooperative learning method for neonatal fundus screening based on POS mechanism according to claim 2, further comprising:
and the right control node configures the times of accessing the typical case base and calling the diagnosis and treatment model for the node according to the sum of the contribution values of the node.
10. A neonate eye ground screening collaborative learning system based on a POS mechanism is characterized in that the system is composed of an application node, a diagnosis node, an audit node, a college expert node and an authority control node; the system is configured to perform the following method:
the application node generates a first request and stores the first request in an uplink manner; the first request comprises data to be diagnosed, patient information and appointed diagnosis node information;
the diagnostic node corresponding to the first request obtains the first request from the block chain, and generates a diagnostic result according to the first request;
the diagnosis node generates a diagnosis data packet by the diagnosis result, the diagnosis node signature and the first request, and stores the diagnosis data packet in an uplink manner;
the application node acquires a diagnosis data packet corresponding to the first request and stored on a block chain, and judges whether a request for generating a typical case is provided for the diagnosis data packet or not;
if so, the application node generates a case request according to the diagnosis data packet and simultaneously sends the case request to the diagnosis node and the auditing node;
the case auditing node adds cases corresponding to the diagnosis data packet in a typical case library according to authorization information which is fed back by the diagnosis node and relates to the case request;
generating a diagnosis and treatment model by the expert nodes of the colleges and universities according to the cases in the typical case base, and storing the diagnosis and treatment model in a diagnosis and treatment model base corresponding to the typical case base in a block chain;
and the authority control node configures corresponding authority for the nodes corresponding to the cases or the models by adopting a POS common identification mechanism according to the cases stored in the typical case library and the diagnosis and treatment models stored in the diagnosis and treatment model library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111445433.4A CN113851203B (en) | 2021-12-01 | 2021-12-01 | Neonate eye fundus screening collaborative learning method and system based on POS mechanism |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111445433.4A CN113851203B (en) | 2021-12-01 | 2021-12-01 | Neonate eye fundus screening collaborative learning method and system based on POS mechanism |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113851203A CN113851203A (en) | 2021-12-28 |
CN113851203B true CN113851203B (en) | 2022-02-15 |
Family
ID=78982564
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111445433.4A Active CN113851203B (en) | 2021-12-01 | 2021-12-01 | Neonate eye fundus screening collaborative learning method and system based on POS mechanism |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113851203B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103577707A (en) * | 2013-11-15 | 2014-02-12 | 上海交通大学 | Robot failure diagnosis method achieved by multi-mode fusion inference |
CN109326337A (en) * | 2018-09-06 | 2019-02-12 | 西安电子科技大学 | Electronic medical record storage and shared model and method based on block chain |
CN110910977A (en) * | 2019-11-12 | 2020-03-24 | 南京工业大学 | Medical data safe storage method integrated with block chain technology |
CN111209313A (en) * | 2020-01-03 | 2020-05-29 | 腾讯科技(深圳)有限公司 | Block chain-based medical item data query method and device |
CN112331353A (en) * | 2020-11-10 | 2021-02-05 | 上海计算机软件技术开发中心 | Medical artificial intelligence model training system and method based on block chain |
CN112349368A (en) * | 2020-09-29 | 2021-02-09 | 福建西岸康健管理有限公司 | Electronic health record authorization sharing and management system based on medical block chain |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11250937B2 (en) * | 2019-04-12 | 2022-02-15 | International Business Machines Corporation | System and method to share and utilize healthcare data |
CN111444258A (en) * | 2020-02-11 | 2020-07-24 | 江苏荣泽信息科技股份有限公司 | Medical data sharing method based on block chain |
CN112951356B (en) * | 2021-03-23 | 2023-03-31 | 电子科技大学 | Cross-modal medical data joint sharing method based on alliance chain |
-
2021
- 2021-12-01 CN CN202111445433.4A patent/CN113851203B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103577707A (en) * | 2013-11-15 | 2014-02-12 | 上海交通大学 | Robot failure diagnosis method achieved by multi-mode fusion inference |
CN109326337A (en) * | 2018-09-06 | 2019-02-12 | 西安电子科技大学 | Electronic medical record storage and shared model and method based on block chain |
CN110910977A (en) * | 2019-11-12 | 2020-03-24 | 南京工业大学 | Medical data safe storage method integrated with block chain technology |
CN111209313A (en) * | 2020-01-03 | 2020-05-29 | 腾讯科技(深圳)有限公司 | Block chain-based medical item data query method and device |
CN112349368A (en) * | 2020-09-29 | 2021-02-09 | 福建西岸康健管理有限公司 | Electronic health record authorization sharing and management system based on medical block chain |
CN112331353A (en) * | 2020-11-10 | 2021-02-05 | 上海计算机软件技术开发中心 | Medical artificial intelligence model training system and method based on block chain |
Non-Patent Citations (1)
Title |
---|
"基于区块链的重大突发疫情防控***共识机制探析";史磊;《太原理工大学学报》;20201130;第51卷(第6期);第838-833页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113851203A (en) | 2021-12-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Huang et al. | A blockchain-based scheme for privacy-preserving and secure sharing of medical data | |
US20210067496A1 (en) | Method and System for Identity and Access Management for Blockchain Interoperability | |
CN112016105B (en) | Chain uplink and downlink data sharing method based on distributed prediction machine and homomorphic encryption | |
CN114513533B (en) | Classified and graded body-building health big data sharing system and method | |
US20230087557A1 (en) | System for privacy protection during iot secure data sharing and method thereof | |
CN109525671A (en) | Date storage method, electronic equipment and storage medium based on block chain | |
CN109326337A (en) | Electronic medical record storage and shared model and method based on block chain | |
CN110266817B (en) | Cross-channel data sharing model, method and device based on block chain | |
CN109741803A (en) | Medical data security cooperation system based on block chain | |
CN112989415A (en) | Private data storage and access control method and system based on block chain | |
CN108471350A (en) | Trust data computational methods based on block chain | |
CN108390891A (en) | Information protecting method based on privately owned block chain | |
WO2021139338A1 (en) | Data access permission verification method and apparatus, computer device, and storage medium | |
CN109753815A (en) | Data processing method, data processing network and electronic equipment based on block chain | |
CN108429759A (en) | Decentralization stores safety implementation method | |
US11258603B2 (en) | Access controls for question delegation environments | |
CN102073817B (en) | Dynamic access control improvement method on basis of RBAC (Role-Based policies Access Control) model | |
He et al. | Toward privacy-assured health insurance claims | |
CN111916217A (en) | Block chain-based medical data management method, system, storage medium and terminal | |
John et al. | Provably secure data sharing approach for personal health records in cloud storage using session password, data access key, and circular interpolation | |
CN113645195A (en) | Ciphertext access control system and method based on CP-ABE and SM4 | |
CN111414634B (en) | Information processing method and device | |
CN112908440A (en) | Health management data sharing method and device and remote medical platform | |
CN115567247A (en) | Decentralized multi-authority privacy protection data access control method and system | |
Khasim et al. | An improved fast and secure CAMEL based authenticated key in smart health care system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20221125 Address after: 210000 1st floor, block B, Dingye Baitai biological building, No.10 Xinghuo Road, Jiangbei new district, Nanjing City, Jiangsu Province Patentee after: Jiangsu Fuhan Medical Industry Development Co.,Ltd. Address before: Room 1515, Yingying building, 99 Tuanjie Road, research and Innovation Park, Nanjing area, China (Jiangsu) pilot Free Trade Zone, Nanjing 210031, Jiangsu Province Patentee before: Nanjing trusted blockchain and algorithm Economics Research Institute Co.,Ltd. |
|
TR01 | Transfer of patent right |