CN116913506A - Expert treatment scheme matching system based on blockchain technology - Google Patents
Expert treatment scheme matching system based on blockchain technology Download PDFInfo
- Publication number
- CN116913506A CN116913506A CN202310918051.1A CN202310918051A CN116913506A CN 116913506 A CN116913506 A CN 116913506A CN 202310918051 A CN202310918051 A CN 202310918051A CN 116913506 A CN116913506 A CN 116913506A
- Authority
- CN
- China
- Prior art keywords
- treatment
- scheme
- module
- patient
- expert
- 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
- 238000011282 treatment Methods 0.000 title claims abstract description 122
- 238000005516 engineering process Methods 0.000 title claims abstract description 19
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 33
- 201000011510 cancer Diseases 0.000 claims abstract description 33
- 238000010606 normalization Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 21
- 239000003814 drug Substances 0.000 claims description 16
- 238000011269 treatment regimen Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 208000024891 symptom Diseases 0.000 claims description 11
- 230000036541 health Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 229940079593 drug Drugs 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 5
- 201000010099 disease Diseases 0.000 abstract description 4
- 208000017667 Chronic Disease Diseases 0.000 abstract description 2
- 238000010827 pathological analysis Methods 0.000 abstract description 2
- 206010058467 Lung neoplasm malignant Diseases 0.000 abstract 1
- 201000005202 lung cancer Diseases 0.000 abstract 1
- 208000020816 lung neoplasm Diseases 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 206010067484 Adverse reaction Diseases 0.000 description 2
- 230000006838 adverse reaction Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Pharmacology & Pharmacy (AREA)
- General Business, Economics & Management (AREA)
- Toxicology (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an expert treatment scheme matching system based on a blockchain technology, and particularly relates to the technical field of medical assistance, comprising the following steps of S1, collecting the treatment current situation of a patient and the related complications information of the patient; s2, carrying out normalization processing on the original data; s3, dividing the treatment plan into a treatment plan knowledge base unit and an auxiliary unit, wherein the knowledge base unit stores related treatment plans (such as lung cancer) based on medical guidelines of related disease types, and the auxiliary unit provides auxiliary functions for the knowledge base unit; s4, automatically matching a treatment scheme through known treatment information; s5, outputting the treatment scheme in the scheme matching module; s6, the structure based on the double blockchain is used for storing and taking medical records and corresponding treatment schemes, different expert workshops can adjust and output the treatment schemes, and corresponding adjustments can be recorded in the blockchain. According to the invention, the pathological analysis of patient data is performed by combining the expertise and experience of cancer diseases and chronic disease experts, and a full course management plan which is most suitable for the treatment of the diseases is recommended according to the expert knowledge.
Description
Technical Field
The invention relates to the technical field of medical assistance, in particular to an expert treatment scheme matching system based on a blockchain technology.
Background
In recent years, along with the sequential development of artificial intelligence technology in the medical field, accurate medical treatment gradually becomes a hot topic in the medical field, a great deal of complex data analysis is needed in the medical field to help doctors to carry out correct treatment, the new medical form is widely focused, cancer patients are paired with the most suitable treatment scheme through an internet medical health platform, the treatment scheme matching is that the doctors and the cancer patients simultaneously provide own demand information for a system, and the system immediately obtains the process of the optimal matching scheme according to the information provided by the two parties.
The existing system adopts a method of evidence analysis and a method of acquiring cancer patient data to analyze factors influencing the matching of a treatment scheme, the method of evidence analysis is adopted to rarely give out the design of a medical service matching mechanism, or the method of medical service matching is proposed, but the stability factors of the matching scheme in the real matching process are rarely considered, the method of acquiring the cancer patient data is firstly used for estimating the condition expectation of treatment reaction, then the condition average value is maximized, the condition average value is estimated through a regression model, the estimated scheme is derived through a punishable least square method, the algorithm is seriously dependent on the accuracy of model estimation, the model estimation is wrong, and the method can fail.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, embodiments of the present invention provide a system for matching expert treatment schemes based on blockchain technology, which solves the problems set forth in the background art above through a scheme matching module.
In order to achieve the above purpose, the present invention provides the following technical solutions: the system comprises a data acquisition module, a preprocessing module, an expert library module, a scheme matching module, a scheme output module and a blockchain sharing module, wherein the data acquisition module is used for collecting the current treatment situation of a patient and the related complications information of the patient, the preprocessing module is used for carrying out normalization processing on the original data of the patient, the expert library module is divided into a knowledge library unit and an auxiliary unit, the knowledge library unit is used for carrying out unit price calculation and retrieval of the reimbursement proportion of the treatment scheme according to the medicine of the knowledge library unit through the blockchain based on the medical guideline of the cancer, the scheme matching module is used for automatically matching the treatment scheme through the known treatment information, the scheme output module is used for outputting the treatment scheme in the scheme matching module, and the blockchain sharing module is used for storing and taking the medical record and the corresponding treatment scheme based on the structure of the double blockchain.
In a preferred embodiment, the data acquisition module collects the current treatment status of the patient and the related complication information of the patient, collects the gender, age, identification card number and medical insurance card number information of the patient, acquires the historical examination medical record of the historical patient set and the identification tag calibration, and forms the electronic health medical record of the cancer patient.
In a preferred embodiment, the data preprocessing module performs normalization processing on original data of a patient, converts the data into data in a (0, 1) range, converts the dimensional data into data without dimensions, improves accuracy of data analysis, shortens calculation time, and performs normalization processing on the original data as follows:
wherein in maxx ij Minux ij Wherein i is more than or equal to 1 and less than or equal to m, maxx ij And minx ij Respectively, the minimum value and the maximum value of each column of data, x ij Represents the j-th feature of the i-th sample input data.
In a preferred embodiment, the expert database module specifically includes a knowledge base unit and an auxiliary unit, and the construction of the knowledge base includes the following steps:
s31, constructing a knowledge base unit: the knowledge base unit is based on blockchain storage, the knowledge base unit contains specific symptoms of cancer patients, the specific symptoms are set as father types, the subclasses under the father types should contain routine examination related to the specific symptoms, the treatment scheme in each hospital, papers, books, newspapers and experimental data of the cancer are collected in a concentrated mode, relevant information of the cancer is aimed at, the basic components, molecular formulas, molecular weights, solubility and acting organs of relevant medicines, adverse reactions and interacted medicine information are recorded, and the information is classified: the method comprises the steps of cancer examination, a cancer diagnosis mode, a cancer treatment method, cancer symptoms and patient information, adding the classifications into a subclass set under a parent category directory, displaying a disease field concept structure through a structure of a tree diagram through classification operation, and clearly displaying a hierarchical relationship among concepts through the tree diagram;
s32, auxiliary unit construction: the auxiliary unit is responsible for searching the unit price of the medicine and the reimbursement proportion of the treatment scheme for the medicine needed in the treatment scheme of the patient in the knowledge base unit, and the auxiliary unit calculates the needed price according to the matched treatment scheme while searching the related knowledge;
s33, knowledge input: checking the existence state of the knowledge vocabulary entry to be input in the knowledge base, performing redundant detection on the knowledge base unit, detecting whether knowledge with the similarity of the knowledge vocabulary entry to be input larger than a threshold value set by a system exists in the knowledge base, wherein the knowledge vocabulary entry higher than the threshold value is regarded as a record with high similarity, and the knowledge vocabulary entry lower than the threshold value indicates that the knowledge vocabulary entry does not exist in the knowledge base, and inputting the knowledge base through auditing;
s34, symbol filtering: the symbol filtering is a process of dividing and deleting the character string input by the user according to the punctuation marks, and a reference set of the punctuation marks is established. ","? Inputting the character to be filtered, scanning the character string, generating a filter set according to the symbol segmentation in the character string reference set, deleting the terminal symbol of the character string in the filter set, scanning whether the character string has the symbol in the reference set, outputting the character string without detection, and scanning the symbol in the reference set again.
In a preferred embodiment, the specific operation steps of the scheme matching module are as follows:
s1, weighting the spatial position information by focus information features of different parts, and emphasizing the key feature information of the focus according to the height of the weight, wherein the calculation formula is as follows:
W=f(x it )
wherein C= [ C 1 ,C 2 ,...,C k ]Represents k feature maps in focus data, F is weighted feature map, x it To fuse multi-modal feature representations of images and text,representing the element product operation, ++>The method is characterized in that different weights are given to different positions of each focus characteristic by using W weights, positions of key information in a characteristic diagram are marked, and f (x it ) Is capable of fusing the features x it The calculated characteristic weight function;
s2, matching treatment schemes according to the calculated focus weights, wherein K is used as a representation method of the treatment schemes, and k=k 1 ,k 2 ,...,k n The efficacy of the treatment regimen is indicated by the size of the clinical outcome, with a larger clinical outcome indicating a better treatment efficacy, and the patient's historical health information is calculated as follows:
H k =(X k1 ,T k1 ,C (k1) ,...,T k1-1 ,X (kn) )
wherein X is (k) Representing the variables observed during the kth phase prior to treatment distribution, T (k) Representing treatment at the kth stage, T (k) ∈{-1,1},C k Indicated at the kth stageA treatment regimen representing a decision sequence, a= (a) 1 ,A 2 ,...,A n ) Wherein A is n Representing a mapping of patient historical health information to treatment options { -1,1}, each treatment regimen a having a corresponding value function V (a), representing the desired treatment effect given treatment regimen a, can be expressed as:
wherein E is A Is expressed by a random variable (X k1 ,T k1 ,C (k1) ,...,T k1-1 ,X (kn) ) The probability that is generated after a given treatment regimen, P (a) represents the expected value corresponding to this probability.
In a preferred embodiment, the blockchain sharing module is based on a treatment scheme and scheme sharing of a dual blockchain, and is respectively used for storing medical records and sharing the medical records, the medical record storage chain is used for storing medical records composed by medical institutions, the medical records are segmented before being stored, and the medical records are recorded as { R } 1 ,R 2 ,....,R n It can be split into smaller parts according to the size of the storage space,the medical record sharing chain is convenient for block filling, when a medical institution is interested in a certain treatment scheme, the medical institution serves as a requesting party, a medical institution issuing the treatment scheme receives the taking request at the medical record sharing chain, a data permission instruction is sent, the requesting party can check the medical record in the sharing pool, different expert workshops can adjust and output the treatment scheme, and corresponding adjustment can be tracked in the record blockchain.
In a preferred embodiment, the scheme output module outputs the scheme of the matching scheme with the highest expected value in the scheme matching module through an intelligent engine, wherein the scheme comprises recommendation prompt, metering calculation and risk early warning, calculates the dosage of the drug, and prompts contraindications and risk early warning with abnormal indexes in the matching scheme.
In a preferred embodiment, the method specifically comprises the following steps:
s1, collecting the current treatment state of a patient and the related complication information of the patient;
s2, carrying out normalization processing on the original data;
s3, dividing the cancer treatment system into a knowledge base unit and an auxiliary unit, wherein the knowledge base unit stores relevant data of the cancer, and the auxiliary unit provides auxiliary functions for the knowledge base unit;
s4, automatically matching a treatment scheme through known treatment information;
s5, outputting the treatment scheme in the scheme matching module;
s6, the structure based on the double blockchain is used for storing and taking medical records and corresponding treatment schemes, different expert workshops can adjust and output the treatment schemes, and corresponding adjustments can be recorded in the blockchain.
The invention has the technical effects and advantages that:
according to the invention, the pathological analysis of the patient data is carried out by combining the knowledge and experience of cancer and chronic disease specialists, various data such as clinical data, test report and image data of the patient are imported, and the treatment plan most suitable for the cancer is recommended according to the specialist knowledge, so that the personalized diagnosis of the patient and the selection of a treatment scheme can be supported, the effect and quality of the medical treatment of the cancer patient are improved, and the treatment scheme is more scientific and accurate.
Drawings
FIG. 1 is a system flow diagram of an expert treatment plan matching system based on blockchain technology.
Fig. 2 is a block diagram of a system architecture of a blockchain technology based expert treatment plan matching system.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
The present embodiment of fig. 1 provides an expert treatment scheme matching system based on a blockchain technique, which specifically includes the following steps:
s1, collecting the current treatment state of a patient and the related complication information of the patient;
s2, carrying out normalization processing on the original data;
s3, dividing the cancer treatment system into a knowledge base unit and an auxiliary unit, wherein the knowledge base unit stores relevant data of the cancer, and the auxiliary unit provides auxiliary functions for the knowledge base unit;
s4, automatically matching a treatment scheme through known treatment information;
s5, outputting the treatment scheme in the scheme matching module;
s6, the structure based on the double blockchain is used for storing and taking medical records and corresponding treatment schemes, different expert workshops can adjust and output the treatment schemes, and corresponding adjustments can be recorded in the blockchain.
The embodiment provides an expert treatment scheme matching system based on a blockchain technology as shown in fig. 2, which comprises a data acquisition module, a preprocessing module, an expert library module, a scheme matching module, a scheme output module and a blockchain sharing module, wherein the data acquisition module is used for collecting the treatment current situation of a patient and the related complications information of the patient, the preprocessing module is used for carrying out normalization processing on the original data of the patient, the expert library module is divided into a knowledge library unit and an auxiliary unit, the knowledge library unit carries out unit price calculation and treatment scheme reimbursement proportion retrieval according to medicines of the knowledge library unit, the scheme matching module is used for carrying out treatment scheme matching through weights of different focus information characteristics, and the scheme output module is used for outputting the treatment scheme in the scheme matching module, and the blockchain sharing module is used for storing and taking the corresponding treatment scheme based on the structure of a double-blockchain.
101. Focus cutting is carried out on medical images of patients, personal information of the patients is collected, and focus images are respectively stored in a blockchain;
in this embodiment, a specific description is provided of the data acquisition module, where the data acquisition module collects the current treatment status of the patient and the related complication information of the patient, collects the gender, age, identification card number and medical insurance card number information of the patient, and obtains the history examination medical record and the identification tag calibration of the history patient set, thereby forming the electronic health medical record of the cancer patient.
102. Normalizing the original data;
in this embodiment, a specific description is provided of a data preprocessing module, where the data preprocessing module performs normalization processing on original data of a patient, converts the data into data within a range of (0, 1), converts the data with dimensions into data without dimensions, improves accuracy of data analysis, and shortens calculation time, and the normalization processing of the original data is as follows:
wherein in maxx ij Minux ij Wherein i is more than or equal to 1 and less than or equal to m, and Mixx ij And minx ij Respectively, the minimum value and the maximum value of each column of data, x ij Represents the j-th feature of the i-th sample input data.
103. The system comprises a knowledge base unit and an auxiliary unit, wherein the knowledge base unit stores relevant data of cancer, and the auxiliary unit provides auxiliary functions for the knowledge base unit;
in this embodiment, an expert database module is specifically described, where the expert database module specifically includes a knowledge base unit and an auxiliary unit, and the construction of the knowledge base includes the following steps:
s31, constructing a knowledge base unit: the knowledge base unit is based on blockchain storage, the knowledge base unit contains specific symptoms of cancer patients, the specific symptoms are set as father types, the subclasses under the father types should contain routine examination related to the specific symptoms, the treatment scheme in each hospital, papers, books, newspapers and experimental data of the cancer are collected in a concentrated mode, relevant information of the cancer is aimed at, the basic components, molecular formulas, molecular weights, solubility and acting organs of relevant medicines, adverse reactions and interacted medicine information are recorded, and the information is classified: the method comprises the steps of cancer examination, a cancer diagnosis mode, a cancer treatment method, cancer symptoms and patient information, adding the classifications into a subclass set under a parent category directory, displaying a disease field concept structure through a structure of a tree diagram through classification operation, and clearly displaying a hierarchical relationship among concepts through the tree diagram;
s32, auxiliary unit construction: the auxiliary unit is responsible for searching the unit price of the medicine and the reimbursement proportion of the treatment scheme for the medicine needed in the treatment scheme of the patient in the knowledge base unit, and the auxiliary unit calculates the needed price according to the matched treatment scheme while searching the related knowledge;
s33, knowledge input: checking the existence state of the knowledge vocabulary entry to be input in the knowledge base, performing redundant detection on the knowledge base unit, detecting whether knowledge with the similarity of the knowledge vocabulary entry to be input larger than a threshold value set by a system exists in the knowledge base, wherein the knowledge vocabulary entry higher than the threshold value is regarded as a record with high similarity, and the knowledge vocabulary entry lower than the threshold value indicates that the knowledge vocabulary entry does not exist in the knowledge base, and inputting the knowledge base through auditing;
s34, symbol filtering: the symbol filtering is a process of dividing and deleting the character string input by the user according to the punctuation marks, and a reference set of the punctuation marks is established. ","? Inputting the character to be filtered, scanning the character string, generating a filter set according to the symbol segmentation in the character string reference set, deleting the terminal symbol of the character string in the filter set, scanning whether the character string has the symbol in the reference set, outputting the character string without detection, and scanning the symbol in the reference set again.
104. Automatically matching the treatment plan with known treatment information;
in this embodiment, a scheme matching module is specifically needed to be described, and the specific operation steps of the scheme matching module are as follows:
s1, weighting spatial position information by focus information feature maps of different parts, and emphasizing key feature information in focuses by the height of the weight, wherein the calculation formula is as follows:
W=f(x it )
wherein C= [ C 1 ,C 2 ,...,C k ]Represents k feature maps in focus data, F is weighted feature map, x it To fuse multi-modal feature representations of images and text,representing the element product operation, ++>The W weight is used to give different weights to different positions in each feature map, the positions of key information in the feature map are marked, f (x) it ) Is capable of fusing the features x it The calculated feature map weight function;
s2, matching treatment schemes according to the calculated focus weights, wherein K is used as a representation method of the treatment schemes, and k=k 1 ,k 2 ,...,k n The efficacy of the treatment regimen is indicated by the size of the clinical outcome, with a larger clinical outcome indicating a better treatment efficacy, and the patient's historical health information is calculated as follows:
H k =(X k1 ,T k1 ,C (k1) ,...,T k1-1 ,X (kn) )
wherein X is (k) Representing the variables observed during the kth phase prior to treatment distribution, T (k) Representing treatment at the kth stage, T (k) ∈{-1,1},C k Representing clinical outcome after treatment at phase k, a treatment regimen represents a decision sequence, a= (a) 1 ,A 2 ,...,A n ) Wherein A is n Representing a mapping of patient historical health information to treatment options { -1,1}, each treatment regimen a having a corresponding value function V (a), representing the desired treatment effect given treatment regimen a, can be expressed as:
wherein E is A Is expressed by a random variable (X k1 ,T k1 ,C (k1) ,...,T k1-1 ,X (kn) ) The probability that is generated after a given treatment regimen, P (a) represents the expected value corresponding to this probability.
105. Outputting the treatment scheme in the scheme matching module;
in this embodiment, a specific description needs to be provided of a scheme output module, where the scheme output module outputs a scheme to a matching scheme with a highest expected value in the scheme matching module through an intelligent engine, the scheme includes recommendation prompt, metering calculation and risk early warning, calculates a medication dose, and prompts contraindications and risk early warning with abnormal indexes in the matching scheme.
106. Based on the structure of the double-block chain, the medical record storage chain is used for storing medical records of medical institutions, and the medical record sharing chain views the medical records in the sharing pool by submitting a taking request.
In this embodiment, a blockchain sharing module is specifically described, where the blockchain sharing module is based on a treatment scheme and a scheme sharing of a dual blockchain, and is used for storing medical records and implementing sharing of medical records, respectively, and the medical record storage chain is used forStoring medical records composed by medical institutions, slicing the medical records before storing, and marking the medical records as { R } 1 ,R 2 ,....,R n It can be split into smaller parts according to the size of the storage space,the medical record sharing chain is convenient for block filling, when a medical institution is interested in a certain treatment scheme, the medical institution serves as a requesting party, a medical institution issuing the treatment scheme receives the taking request at the medical record sharing chain, a data permission instruction is sent, the requesting party can check the medical record in the sharing pool, different expert workshops can adjust and output the treatment scheme, and corresponding adjustment can be tracked in the record blockchain.
The formula in the invention is a formula which is obtained by removing dimension and taking the numerical calculation, and is closest to the actual situation by acquiring a large amount of data and performing software simulation, and the preset proportionality coefficient in the formula is set by a person skilled in the art according to the actual situation or is obtained by simulating the large amount of data.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. An expert treatment scheme matching system based on a blockchain technology, which is characterized in that: the system comprises a data acquisition module, a preprocessing module, an expert library module, a scheme matching module, a scheme output module and a blockchain sharing module, wherein the data acquisition module is used for collecting the current treatment situation of a patient and the related complications information of the patient, the preprocessing module is used for carrying out normalization processing on the original data of the patient, the expert library module is divided into a knowledge library unit and an auxiliary unit, the knowledge library unit is used for carrying out unit price calculation and retrieval of the reimbursement proportion of the treatment scheme according to the medicine of the knowledge library unit through the blockchain based on the medical guideline of the cancer, the scheme matching module is used for automatically matching the treatment scheme through the known treatment information, the scheme output module is used for outputting the treatment scheme in the scheme matching module, and the blockchain sharing module is used for storing and taking the medical record and the corresponding treatment scheme based on the structure of the double blockchain.
2. The expert treatment scheme matching system based on blockchain technology of claim 1, wherein: the data acquisition module collects the current treatment condition of the patient and the related complication information of the patient, collects the personal basic information of the patient, acquires the history examination medical record of the history patient set and the identity tag calibration, and forms the electronic health medical record of the cancer patient.
3. The expert treatment scheme matching system based on blockchain technology of claim 1, wherein: the data preprocessing module performs normalization processing on original data of a patient, and converts the data into data in a (0, 1) range, wherein the normalization processing of the original data is as follows:
wherein in maxx ij Minux ij Wherein i is more than or equal to 1 and less than or equal to m, maxx ij And minx ij Respectively, the minimum value and the maximum value of each column of data, x ij Represents the j-th feature of the i-th sample input data.
4. The expert treatment scheme matching system based on blockchain technology of claim 1, wherein: the expert database module specifically comprises a knowledge base unit and an auxiliary unit, wherein the knowledge base unit is stored based on a blockchain, the knowledge base unit contains specific symptoms of cancer patients, the specific symptoms are set as parents, the subordinate subclasses of the parents are gathered from medical data of various hospitals and medical institutions through conventional examination related to the specific symptoms, and the auxiliary unit is responsible for searching medicine unit price and reimbursement proportion of treatment schemes for medicines required to be used in treatment schemes of the patients in the knowledge base unit.
5. The expert treatment scheme matching system based on blockchain technology of claim 4, wherein: the knowledge input: checking the existence state of the knowledge vocabulary entry to be input in the knowledge base, carrying out redundant detection on the knowledge base unit, detecting whether knowledge with the similarity of the knowledge vocabulary entry to be input larger than a threshold value set by a system exists in the knowledge base, considering the knowledge vocabulary entry higher than the threshold value as a record with high similarity, and indicating that the knowledge vocabulary entry does not exist in the knowledge base when the knowledge vocabulary entry is lower than the threshold value, and carrying out input of the knowledge base through auditing.
6. The expert treatment scheme matching system based on blockchain technology of claim 1, wherein: the scheme matching module weights the focus information features of different parts according to the spatial position information, and emphasizes key feature information in the focus according to the height of the weight, wherein the calculation formula is as follows:
W=f(x it )
wherein C= [ C 1 ,C 2 ,...,C k ]Representing k features in focus data, F being a weighted feature, x it To fuse multi-modal feature representations of images and text,representing the element product operation, ++>Representing that different weights are given to different positions in each focus characteristic by using the W weight, and the positions of key information in the focus characteristic are marked, f (x it ) Is capable of fusing the features x it And (5) calculating a focus characteristic weight function.
7. The expert treatment scheme matching system based on blockchain technology of claim 7, wherein: the matching of the treatment scheme is carried out according to the calculated focus weight, K is taken as the representation method of the treatment scheme, and k=k 1 ,k 2 ,...,k n The efficacy of the treatment regimen is indicated by the size of the clinical outcome, with a larger clinical outcome indicating a better treatment efficacy, and the patient's historical health information is calculated as follows:
H k =(X k1 ,T k1 ,C (k1) ,...,T k1-1 ,X (kn) )
wherein X is (k) Representing the variables observed during the kth phase prior to treatment distribution, T (k) Representing treatment at the kth stage, T (k) ∈{-1,1},C k Clinical results after treatment at stage k are shown.
8. The expert treatment scheme matching system based on blockchain technology of claim 7, wherein: the one treatment regimen represents a decision sequence, a= (a) 1 ,A 2 ,...,A n ) Wherein A is n Representing a mapping of patient historical health information to treatment options { -1,1}, each treatment regimen a having a corresponding value function V (a), representing the desired treatment effect given treatment regimen a, can be expressed as:
wherein E is A Is expressed by a random variable (X k1 ,T k1 ,C (k1) ,...,T k1-1 ,X (kn) ) The probability that is generated after a given treatment regimen, P (a) represents the expected value corresponding to this probability.
9. The expert treatment scheme matching system based on blockchain technology of claim 1, wherein: the scheme output module outputs a scheme to a matching scheme with the highest expected value in the scheme matching module through the intelligent engine, wherein the scheme comprises recommendation prompt, metering calculation and risk early warning, calculates the dosage of the drug, and prompts contraindications and risk early warning with abnormal indexes in the matching scheme.
10. The expert treatment scheme matching system based on blockchain technology of claim 1, wherein: the block chain sharing module is used for storing medical records formed by medical institutions based on the treatment schemes and scheme sharing of the double block chains, the medical institutions are used as requesters when the medical institutions are interested in a certain treatment scheme, the medical institutions submit taking requests at the medical records sharing chains, the medical institutions issuing the treatment schemes receive the taking requests and send a data permission instruction, and the requesters can check the medical records in the sharing pool.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310918051.1A CN116913506A (en) | 2023-07-25 | 2023-07-25 | Expert treatment scheme matching system based on blockchain technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310918051.1A CN116913506A (en) | 2023-07-25 | 2023-07-25 | Expert treatment scheme matching system based on blockchain technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116913506A true CN116913506A (en) | 2023-10-20 |
Family
ID=88359987
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310918051.1A Pending CN116913506A (en) | 2023-07-25 | 2023-07-25 | Expert treatment scheme matching system based on blockchain technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116913506A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107767926A (en) * | 2017-11-15 | 2018-03-06 | 中国联合网络通信集团有限公司 | Medical data management system and access method based on block chain |
CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
CN110136838A (en) * | 2019-04-29 | 2019-08-16 | 平安科技(深圳)有限公司 | Data Matching decision-making technique and system based on multiple knowledge base reasoning |
CN110875093A (en) * | 2019-11-19 | 2020-03-10 | 泰康保险集团股份有限公司 | Treatment scheme processing method, device, equipment and storage medium |
CN111916193A (en) * | 2020-08-07 | 2020-11-10 | 平安科技(深圳)有限公司 | Intelligent medical seeking method and device, computer equipment and storage medium |
CN114664463A (en) * | 2022-03-18 | 2022-06-24 | 中南大学湘雅医院 | General practitioner diagnoses auxiliary system |
US20230031792A1 (en) * | 2021-08-02 | 2023-02-02 | Zhejiang Haixinzhihui Technology Co., Ltd. | Design Method of Oncological Computerized Physician Order Entry System with Intelligent Clinical Decision Recommendation Function |
-
2023
- 2023-07-25 CN CN202310918051.1A patent/CN116913506A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107767926A (en) * | 2017-11-15 | 2018-03-06 | 中国联合网络通信集团有限公司 | Medical data management system and access method based on block chain |
CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
CN110136838A (en) * | 2019-04-29 | 2019-08-16 | 平安科技(深圳)有限公司 | Data Matching decision-making technique and system based on multiple knowledge base reasoning |
CN110875093A (en) * | 2019-11-19 | 2020-03-10 | 泰康保险集团股份有限公司 | Treatment scheme processing method, device, equipment and storage medium |
CN111916193A (en) * | 2020-08-07 | 2020-11-10 | 平安科技(深圳)有限公司 | Intelligent medical seeking method and device, computer equipment and storage medium |
US20230031792A1 (en) * | 2021-08-02 | 2023-02-02 | Zhejiang Haixinzhihui Technology Co., Ltd. | Design Method of Oncological Computerized Physician Order Entry System with Intelligent Clinical Decision Recommendation Function |
CN114664463A (en) * | 2022-03-18 | 2022-06-24 | 中南大学湘雅医院 | General practitioner diagnoses auxiliary system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11922348B2 (en) | Generating final abnormality data for medical scans based on utilizing a set of sub-models | |
CN112037880B (en) | Medication recommendation method, device, equipment and storage medium | |
Wu et al. | Comparison of chest radiograph interpretations by artificial intelligence algorithm vs radiology residents | |
US20200243175A1 (en) | Health information system for searching, analyzing and annotating patient data | |
KR101873926B1 (en) | Method for providing medical counseling service between insurance organization and specialist based on bigdata | |
US11145059B2 (en) | Medical scan viewing system with enhanced training and methods for use therewith | |
KR102088980B1 (en) | System and Method for Providing personalized hospital information | |
WO2020243732A1 (en) | Systems and methods of clinical trial evaluation | |
CN112712879A (en) | Information extraction method, device, equipment and storage medium for medical image report | |
CN114026651A (en) | Automatic generation of structured patient data records | |
JP2014505950A (en) | Imaging protocol updates and / or recommenders | |
CN116312926A (en) | Health path recommending method and related device, electronic equipment and storage medium | |
CN111968740B (en) | Diagnostic label recommendation method and device, storage medium and electronic equipment | |
RU2752792C1 (en) | System for supporting medical decision-making | |
CN115036034B (en) | Similar patient identification method and system based on patient characterization map | |
CN116913506A (en) | Expert treatment scheme matching system based on blockchain technology | |
CN115700826A (en) | Receipt processing method, receipt display method, receipt processing device, receipt display device, computer equipment and storage medium | |
Sreenivasan et al. | PCPS: Personalized Care through Patient Similarity | |
CN113688854A (en) | Data processing method and device and computing equipment | |
CN116894125B (en) | Medical instrument recommendation method and system based on artificial intelligence | |
Wilson et al. | Medical imagery in case-based reasoning | |
Ooi et al. | A Healthcare Recommender System Framework. | |
CN117038026A (en) | Recommendation method, electronic equipment and medium for hospital specialists | |
CN116244492A (en) | Medical diagnosis guiding method, device and storage medium | |
Kemp | Unsupervised learning for anomaly detection in Australian medical payment data |
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 |