CN114550885A - Main diagnosis and main operation matching detection method and system based on federal association rule mining - Google Patents
Main diagnosis and main operation matching detection method and system based on federal association rule mining Download PDFInfo
- Publication number
- CN114550885A CN114550885A CN202111622583.8A CN202111622583A CN114550885A CN 114550885 A CN114550885 A CN 114550885A CN 202111622583 A CN202111622583 A CN 202111622583A CN 114550885 A CN114550885 A CN 114550885A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- frequency
- main
- mining
- matching
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 147
- 238000005065 mining Methods 0.000 title claims abstract description 81
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000001356 surgical procedure Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000003773 principal diagnosis Methods 0.000 claims 1
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010801 machine learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000002682 general surgery Methods 0.000 description 2
- FBOUIAKEJMZPQG-AWNIVKPZSA-N (1E)-1-(2,4-dichlorophenyl)-4,4-dimethyl-2-(1,2,4-triazol-1-yl)pent-1-en-3-ol Chemical compound C1=NC=NN1/C(C(O)C(C)(C)C)=C/C1=CC=C(Cl)C=C1Cl FBOUIAKEJMZPQG-AWNIVKPZSA-N 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013107 unsupervised machine learning method Methods 0.000 description 1
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
- 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
- G16H40/20—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 management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/252—Integrating or interfacing systems involving database management systems between a Database Management System and a front-end application
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system for detecting matching between main diagnosis and main operation based on federal mining, which comprises the following steps: performing the mining of the cross combination of the operation type projects and the diagnosis type projects at each medical institution terminal based on the operation frequency and the diagnosis frequency, and uploading the relevant data of the mining result to a central node terminal; analyzing the support degree, the confidence degree and the promotion degree of the mining result related data at the central node, and screening the matching rule pairs of the main diagnosis and the main operation from the mining result related data according to the analysis result to construct a rule database; when the method is applied, the matching rules in the rule database are used for carrying out clinical matching detection on main diagnosis and main operation. The method and the system can be used for mining and finding the association rule by efficiently, safely and compliantly using the mass medical record homepage data of a plurality of medical institutions, and further automatically detect the clinical matching of main diagnosis and main operation in the medical record homepage.
Description
Technical Field
The invention belongs to the field of case quality control, and particularly relates to a method and a device for main diagnosis and main operation matching detection based on federal mining.
Background
The association rule mining is a common unsupervised machine learning method, and the association relation in data is mined through measurement indexes such as support degree, confidence degree, promotion degree and the like, and is unknown in advance and hidden. Apriori and FP-growth are common association rule mining algorithms, but in the presence of large data or massive data, the space that they can exert is relatively small. In order to effectively use massive data, researchers have developed various Distributed Association algorithms, such as Parallel FP-growth (pfp), Fast Distributed Association rule Mining (FDM), Distributed Mining of Association rules (DMA), and the like.
However, none of these distributed association algorithms takes into account data security issues. In fact, in many application scenarios, even if massive amounts of data can be collected, the owners of the data are not the same subject. Considering that data usually contains sensitive information, private information of the data is prevented from being leaked for the safety of the data, and the data cannot be directly gathered together for training and modeling.
Federal Learning (Federal Learning) is an emerging artificial intelligence base technology, essentially a distributed machine Learning technology that is good at protecting data privacy. The federal learning aims to develop high-efficiency machine learning among multiple participants or multiple calculation nodes on the premise of ensuring information safety during big data exchange, protecting terminal data and personal data privacy and guaranteeing legal compliance, realize common modeling and improve model performance. The machine learning algorithm which can be used for federal learning is not limited to a neural network, and also comprises important algorithms such as a random forest.
In the medical field, the main diagnosis and the main operation matching analysis of doctors have very important significance, and because the data volume of a single medical institution is not large enough to obtain the accurate analysis result of the main diagnosis and the main operation matching, the analysis needs to be performed by combining the data of a plurality of medical structures. The main diagnosis and the main operation data generally exist in a medical record, and a large amount of privacy information is recorded in the medical record, so that the protection of the privacy information of the medical record is very important.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a method and an apparatus for matching and detecting main diagnosis and main surgery based on federal mining, which efficiently, safely and compliantly use massive medical record homepage data of multiple medical institutions to mine and find association rules, thereby automatically detecting clinical matching between main diagnosis and main surgery in the medical record homepage.
In order to achieve the above object, an embodiment of the present invention provides a method for matching a main diagnosis with a main operation based on federal mining, which includes the following steps:
performing the mining of the cross combination of the operation type projects and the diagnosis type projects at each medical institution terminal based on the operation frequency and the diagnosis frequency, and uploading the relevant data of the mining result to a central node terminal;
calculating support degree, confidence degree and promotion degree of the mining result related data at the central node side, and screening matching rule pairs of main diagnosis and main operation from the mining result related data according to the calculation result to construct a rule database;
when the method is applied, the matching rules in the rule database are used for carrying out clinical matching detection on main diagnosis and main operation.
Wherein the mining related data comprises operation frequency, diagnosis frequency, patient number and mining candidate rule pair frequency.
In one embodiment, the mining of the cross combination of the surgical items and the diagnostic items based on the surgical frequency and the diagnostic frequency comprises:
extracting an operation list and a diagnosis list from a first page of a medical record, and preprocessing operation codes and diagnosis codes in the operation list and the diagnosis list;
and performing statistics on the operation frequency and the diagnosis frequency of the preprocessed operation list and diagnosis list, and performing cross combination on the operation items and the diagnosis items with the screening frequency greater than a preset threshold value to form a candidate rule pair.
In an embodiment, the calculating of the support degree, the confidence degree and the promotion degree of the data related to the mining result includes:
counting the total number of patients, the total frequency of operation items, the total frequency of diagnosis items and the total frequency of candidate rule pairs according to the number of patients, the operation frequency, the diagnosis frequency and the candidate rule pairs of each medical institution;
and calculating the support degree, confidence degree and promotion degree of the candidate matching pairs according to the total number of patients, the total frequency of the surgical items, the total frequency of the diagnostic items and the total frequency of the candidate rule pairs.
In one embodiment, the support, confidence and boost are calculated using equations (1) - (3), respectively:
Sup(si,dj)＝Sumij/Numall (1)
wherein s isiAnd djRespectively represent the ith operation item and the jth diagnosis item, Sup(s)i,dj) Indicates the degree of support, Conf(s)i,dj) Indicates confidence, Lift(s)i,dj) Indicates the degree of lift, SumijIndicates the number of candidate rule pairs, NumallThe number of total patients is indicated,
representing surgical-like items siIs a probability of
SumiFor the total frequency of the ith surgical class item,
representing the probability of a diagnostic class item, i.e.
SumjThe total frequency of the jth diagnostic class item.
In one embodiment, the screening of matching rule pairs of the main diagnosis and the main operation from the data related to the mining result according to the analysis result to construct a rule database comprises:
and extracting candidate rule pairs which are simultaneously larger than the support degree threshold, the confidence degree threshold and the lifting degree threshold from the candidate rule pairs as matching rule pairs according to a preset support degree threshold, a preset confidence degree threshold and a preset lifting degree threshold to construct a rule database.
In one embodiment, the performing of the primary diagnosis to be detected and the primary surgical clinical matching detection by using the matching rules in the rule database includes:
and aiming at the main diagnosis to be detected and the corresponding main operation, when a matching rule pair consisting of the main diagnosis to be detected and the corresponding main operation can be found in the slave rule data, the main diagnosis and the main operation are considered to have clinical matching.
In order to achieve the above object, an embodiment of the present invention further provides a system for matching and detecting a main diagnosis and a main operation based on federal mining, which includes medical institution terminals and a central node terminal, wherein the medical institution terminals communicate with the central node terminal;
the medical institution ends perform mining of cross combination of operation items and diagnosis items based on operation frequency and diagnosis frequency, and upload mining result related data to the central node end, wherein the mining related data comprise the operation frequency, the diagnosis frequency, the number of patients and candidate rule pair frequency determined by mining;
the central node side calculates the support degree, the confidence degree and the promotion degree of the relevant data of the mining result, screens matching rule pairs of main diagnosis and main operation from the relevant data of the mining result according to the calculation result to construct a rule database, and transmits the rule database to each medical institution side;
and each medical institution terminal utilizes the matching rules in the rule database to carry out clinical matching detection on main diagnosis and main operation.
In one embodiment, each medical institution terminal extracts an operation list and a diagnosis list from a first page of a medical record, and preprocesses operation codes and diagnosis codes in the operation list and the diagnosis list;
and counting the operation frequency and the diagnosis frequency of the preprocessed operation list and diagnosis list, and performing cross combination on the operation items and the diagnosis items with the screening frequency being greater than a preset threshold value to form a candidate rule pair.
In one embodiment, the central node side counts the total number of patients, the total frequency of operation items, the total frequency of diagnosis items and the total frequency of candidate rule pairs according to the number of patients, the operation frequency, the diagnosis frequency and the candidate rule pairs of each medical institution;
and the central node end calculates the support degree, the confidence degree and the promotion degree of the candidate rule pair according to the total number of patients, the total operation type item frequency, the total diagnosis type item frequency and the total candidate rule pair frequency.
Compared with the prior art, the method and the system for main diagnosis and main operation matching detection based on federal mining provided by the embodiment simultaneously combine federal learning and distributed association algorithm, each medical institution end carries out statistics of operation frequency, diagnosis frequency and candidate rule pairs locally, the uploaded statistics data are the statistics data, namely the safety of the first page data of each case at the local end is protected, the central node end carries out distributed association algorithm analysis based on the uploaded data, namely the analysis of support degree, confidence degree and promotion degree, so that mining of the main diagnosis and main operation matching rules is realized, an accurate matching rule pair is obtained, a rule database is established, finally, the rule database is used for clinical matching detection of the main diagnosis and the main operation, and the efficiency and accuracy of matching detection are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method for detecting a match between a master diagnosis and a master surgery based on federated mining provided by an embodiment;
FIG. 2 is a block flow diagram of a method for detecting a match between a master diagnosis and a master surgery based on federated mining provided by an embodiment;
fig. 3 is a schematic structural diagram of a main diagnosis and main surgery matching detection system based on federated mining according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of a method for matching and detecting a main diagnosis and a main surgery based on federated mining provided in the embodiment, and fig. 2 is a flowchart of a method for matching and detecting a main diagnosis and a main surgery based on federated mining provided in the embodiment. As shown in fig. 1 and fig. 2, the embodiment provides a method for detecting matching between a main diagnosis and a main operation based on federal mining, which includes the following steps:
step 1, performing the mining of the cross combination of the operation type projects and the diagnosis type projects at each medical institution terminal based on the operation frequency and the diagnosis frequency, and uploading the relevant data of the mining results to a central node terminal.
Each medical institution has a diagnosis case of each patient, and the diagnosis case records basic information of the patient and diagnosis and treatment information, which relate to private data of the patient and cannot be published to the outside. Each medical institution is also provided with a force calculation device for data mining processing of the diagnosis and treatment information of each patient, and the specific process comprises the following steps:
extracting an operation list and a diagnosis list from each diagnosis case, wherein the operation list is expressed as S ═ Si,i∈[1,m]The list of diagnoses is denoted as D ═ Dj,j∈[1,n]In which S isiRepresents the ithSet of patients' operations, m represents the number of patients having an operation, DjRepresenting the diagnostic set for the jth patient, and n representing the number of patients with a diagnosis.
And each operation and diagnosis in the extracted operation list and the extracted diagnosis list is represented in a code form, and based on the codes, the operation codes and the diagnosis codes in the operation list and the diagnosis list are preprocessed, and in particular, the operation codes and the diagnosis codes are subjected to case unification and space deletion.
After the operation list and the diagnosis list are preprocessed, single-item statistics is carried out, namely, the operation frequency and the diagnosis frequency are counted. The method specifically comprises the following steps: counting the operation frequency, the diagnosis frequency and the number of patients from the operation list and the diagnosis list, and respectively recording the operation frequency, the diagnosis frequency and the number of patients as follows: CSki(k＝1,2,…,H；i＝1,2,…,M)，CDkj(k＝1,2,…,H；j＝1,2,…,N)，Numk(k ═ 1,2, …, H), where k is the index of the medical institution, i is the surgical index, i is the diagnostic index, CSkiIndicating class i surgery frequency, CD, of the kth medical facilitykjDenotes the class j diagnosis frequency, Num, of the kth medical institutionkThe number of patients at the kth medical institution is shown, and M, N, H shows the total number of surgical categories, the total number of diagnostic categories, and the total number of medical institutions.
In the embodiment, a surgical frequency screening threshold and a diagnosis frequency screening threshold are preset, and then the surgery and the diagnosis are screened based on the two screening thresholds to obtain surgical items and diagnosis items with the frequency greater than the screening threshold, and the surgical items and the diagnosis items participate in subsequent cross-combination statistics. In order to reduce data loss, the two thresholds cannot be set too high, and both thresholds are preferably set to 2 as experimentally explored. The operation items and the diagnosis items screened by the threshold value participate in the cross combination, that is, the operation items and the diagnosis items are combined, and it should be noted that the combination of the operation items and the combination of the diagnosis items are omitted in the combination process, which is beneficial to reducing the calculation amount and the memory occupation. The candidate rule pair composed of the operation items and the diagnosis items obtained by cross combination is marked as SDkijStatistical candidate rule pair SDkijThe frequency of occurrence is obtainedTo candidate rule versus frequency CSDkij。
After the cross combination is finished, the operation frequency CSkiCD with frequent diagnosiskjNum of patientskAnd candidate rule pair frequency CSD of miningkijAnd forming mining result related data, and uploading the mining result related data to the central node terminal. The uploaded mining result related data are mined from the medical records and do not concern the related information of the patients, so that the privacy data of the patients can be well protected.
And 2, calculating support degree, confidence degree and promotion degree of the mining result related data at the central node, and screening matching rule pairs of main diagnosis and main operation from the mining result related data according to the calculation result to construct a rule database.
The central node end also has certain computing power capability and is used for analyzing relevant data of mining results uploaded by all medical institutions to construct a rule database. The specific process comprises the following steps:
firstly, counting the total number of patients Num according to the number of patients, operation frequency, diagnosis frequency and candidate rule pair frequency of each medical institutionallSum frequency of general surgery category itemsiFrequency of total diagnostic items SumjAnd total candidate rule pair frequency Sumij：
Numall＝Num1+Num2+…+NumH (1)
Sumi＝CS1i+CS2i+…+CSHi (2)
Sumj＝CD1j+CD2j+…+CDHj (3)
Sumij＝CSD1ij+CSD2ij+…+CSDHij (4)
Then, according to the total number of patients NumallSum frequency of general surgery category itemsiFrequency of total diagnostic items SumjAnd total candidate rule pair frequency SumijCalculating support degree, confidence degree and promotion degree:
Sup(si,dj)＝Sumij/Numall (5)
wherein s isiAnd djRespectively represent the ith operation item and the jth diagnosis item, Sup(s)i,dj) Denotes the support, Conf(s)i,dj) Indicates confidence, Lift(s)i,dj) Indicates the degree of lift, SumijIndicates the number of candidate rule pairs, NumallThe number of total patients is indicated,
representing surgical items siIs a probability of
PdjRepresenting the probability of a diagnostic class item, i.e.
In the embodiment, a support degree threshold, a confidence degree threshold and a lifting degree threshold are preset, the three thresholds can be set manually or in a machine learning mode, and then, according to the preset support degree threshold, the confidence degree threshold and the lifting degree threshold, a candidate rule pair which is larger than the support degree threshold, the confidence degree threshold and the lifting degree threshold at the same time is extracted from the candidate rule pair to be used as a matching rule pair to construct a rule database. Each matching rule pair recorded in the rule database has accurate matching performance and can be used as a detection standard for main diagnosis and main operation clinical matching performance.
And 3, utilizing the matching rules in the rule database to carry out clinical matching detection on the main diagnosis and the main operation.
When the method is applied, aiming at the main diagnosis to be detected and the corresponding main operation extracted from the medical record homepage, when the matching rule pair consisting of the main diagnosis to be detected and the corresponding main operation can be found in the rule data, the main diagnosis and the main operation are considered to have clinical matching, otherwise, the main diagnosis and the main operation do not have clinical matching.
Fig. 3 is a schematic structural diagram of a main diagnosis and main surgery matching detection system based on federated mining according to an embodiment. As shown in fig. 3, the system for performing master diagnosis and master surgery matching detection based on federal mining according to the embodiment includes each medical institution terminal and a central node terminal, and each medical institution terminal communicates with the central node terminal.
Each medical institution terminal carries out mining of cross combination of operation type projects and diagnosis type projects based on operation frequency and diagnosis frequency, and uploads mining result related data to a central node terminal, wherein the mining related data comprises the operation frequency, the diagnosis frequency, the number of patients and candidate rule pair frequency determined by mining;
the central node end analyzes the support degree, the confidence degree and the promotion degree of the relevant data of the mining result, screens matching rules of main diagnosis and main operation from the relevant data of the mining result according to the analysis result to construct a rule database, and transmits the rule database to each medical institution end;
and each medical institution end utilizes the matching rules in the rule database to carry out clinical matching detection on main diagnosis and main operation.
It should be noted that the matching detection system provided in the embodiment and the matching detection method provided in the above embodiment belong to the same inventive concept, and the specific implementation process and effect are the same as those of the matching detection method provided in the embodiment, and are not described herein again.
The matching detection method and the matching system provided by the embodiment combine federal learning and a distributed association algorithm, each medical institution end carries out statistics of operation frequency, diagnosis frequency and candidate rule pairs locally, the uploaded statistical data also comprises statistical data, namely the safety of the first page data of each medical case at the local end is protected, the central node end carries out distributed association algorithm analysis based on the uploaded data, namely analysis support degree, confidence degree and promotion degree, so that mining of main diagnosis and main operation matching rules is realized, accurate matching rule pairs are obtained, a rule database is built, finally, clinical matching detection of the main diagnosis and the main operation is carried out by utilizing the rule database, and the efficiency and the accuracy of matching detection are improved.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only the most preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A main diagnosis and main operation matching detection method based on federal mining is characterized by comprising the following steps:
performing the mining of the cross combination of the operation type projects and the diagnosis type projects at each medical institution terminal based on the operation frequency and the diagnosis frequency, and uploading the relevant data of the mining result to a central node terminal;
calculating support degree, confidence degree and promotion degree of the mining result related data at the central node side, and screening matching rule pairs of main diagnosis and main operation from the mining result related data according to the calculation result to construct a rule database;
when the method is applied, the matching rules in the rule database are used for carrying out clinical matching detection on main diagnosis and main operation.
2. The method for detecting matching of main diagnosis and main operation based on federal mining as claimed in claim 1, wherein the mining of the cross combination of surgical items and diagnostic items based on the surgical frequency and the diagnostic frequency comprises:
extracting an operation list and a diagnosis list from a first page of a medical record, and preprocessing operation codes and diagnosis codes in the operation list and the diagnosis list;
and performing statistics on the operation frequency and the diagnosis frequency of the preprocessed operation list and diagnosis list, and performing cross combination on the operation items and the diagnosis items with the screening frequency greater than a preset threshold value to form a candidate rule pair.
3. The method for master diagnosis and master surgery match detection based on federated mining of claim 1 or 2, characterized in that the mining related data includes frequency of surgery, frequency of diagnosis, number of patients, and candidate rule pair frequency of mining.
4. The method for detecting matching of a principal diagnosis and a principal operation based on federated mining as claimed in claim 3, wherein the calculation of support, confidence and promotion for the data related to the mining result includes:
counting the total number of patients, the total operation item frequency, the total diagnosis item frequency and the total candidate rule pair frequency according to the number of patients, the operation frequency, the diagnosis frequency and the candidate rule pair frequency of each medical institution;
and calculating the support degree, confidence degree and promotion degree of the candidate rule pair according to the total number of patients, the total frequency of the surgical items, the total frequency of the diagnostic items and the total frequency of the candidate rule pair.
5. The method for detecting the matching of the main diagnosis and the main surgery based on the federal mining as claimed in claim 4, wherein the support degree, the confidence degree and the lift degree are respectively calculated by the following formulas (1) to (3):
Sup(si,dj)＝Sumij/Numall (1)
wherein s isiAnd djRespectively representing the ith operation class item and the jth diagnosis classItem, Sup(s)i,dj) Indicates the degree of support, Conf(s)i,dj) Indicates confidence, Lift(s)i,dj) Indicates the degree of lift, SumijIndicates the number of candidate rule pairs, NumallThe number of total patients is indicated,
representing surgical items siIs a probability of
SumiThe total frequency of the ith surgical category project,
representing the probability of a diagnostic class item, i.e.
SumjThe total frequency is the jth diagnosis class item.
6. The method for matching and detecting the main diagnosis and the main operation based on federated mining as claimed in claim 1, wherein the screening of the matching rule pairs of the main diagnosis and the main operation from the data related to the mining result according to the analysis result to construct the rule database comprises:
and extracting candidate rule pairs which are simultaneously larger than the support degree threshold, the confidence degree threshold and the lifting degree threshold from the candidate rule pairs as matching rule pairs according to a preset support degree threshold, a preset confidence degree threshold and a preset lifting degree threshold to construct a rule database.
7. The method for testing the clinical match between the master diagnosis and the master surgery based on federated mining as claimed in claim 1, wherein the testing the clinical match between the master diagnosis and the master surgery to be tested using the matching rules in the rules database comprises:
and aiming at the main diagnosis to be detected and the corresponding main operation, when a matching rule pair consisting of the main diagnosis to be detected and the corresponding main operation can be found in the slave rule data, the main diagnosis and the main operation are considered to have clinical matching.
8. A main diagnosis and main operation matching detection system based on federal mining is characterized by comprising medical institution terminals and a central node terminal, wherein the medical institution terminals are communicated with the central node terminal;
the medical institution terminals perform mining of cross combination of the operation type projects and the diagnosis type projects based on the operation frequency and the diagnosis frequency, and upload mining result related data to the central node terminal, wherein the mining related data comprises the operation frequency, the diagnosis frequency, the number of patients and candidate rule pair frequency determined by mining;
the central node side calculates the support degree, the confidence degree and the promotion degree of the mining result related data, screens matching rules of main diagnosis and main operation from the mining result related data according to the calculation result to construct a rule database, and transmits the rule database to each medical institution side;
and each medical institution terminal utilizes the matching rules in the rule database to carry out clinical matching detection on main diagnosis and main operation.
9. The federally mining based main diagnosis and main surgery match detect system of claim 8, wherein each medical institution terminal extracts a surgery list and a diagnosis list from a medical record top page and preprocesses surgery codes and diagnosis codes in the surgery list and the diagnosis list;
and performing statistics on the operation frequency and the diagnosis frequency of the preprocessed operation list and diagnosis list, and performing cross combination on the operation items and the diagnosis items with the screening frequency greater than a preset threshold value to form a candidate rule pair.
10. The system of claim 8, wherein the central node counts total patient count, total surgical item frequency, total diagnostic item frequency, and total candidate rule pair frequency according to patient count, surgical frequency, diagnostic frequency, and candidate rule pair frequency of each medical institution;
and the central node end calculates the support degree, the confidence degree and the promotion degree of the candidate rule pair according to the total number of patients, the total operation type item frequency, the total diagnosis type item frequency and the total candidate rule pair frequency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111622583.8A CN114550885A (en) | 2021-12-28 | 2021-12-28 | Main diagnosis and main operation matching detection method and system based on federal association rule mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111622583.8A CN114550885A (en) | 2021-12-28 | 2021-12-28 | Main diagnosis and main operation matching detection method and system based on federal association rule mining |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114550885A true CN114550885A (en) | 2022-05-27 |
Family
ID=81669854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111622583.8A Pending CN114550885A (en) | 2021-12-28 | 2021-12-28 | Main diagnosis and main operation matching detection method and system based on federal association rule mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114550885A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080201172A1 (en) * | 2006-04-25 | 2008-08-21 | Mcnamar Richard T | Method, system and computer software for using an xbrl medical record for diagnosis, treatment, and insurance coverage |
| US20100105989A1 (en) * | 2005-06-08 | 2010-04-29 | Akihiro Inokuchi | Medical guide system |
| JP2014119881A (en) * | 2012-12-14 | 2014-06-30 | Konica Minolta Inc | Information processor, label selection method and program |
| CN106202955A (en) * | 2016-07-19 | 2016-12-07 | 中电科软件信息服务有限公司 | Diagnosis associated packets method and system based on intellectual coded adaptation |
| JP2017215832A (en) * | 2016-06-01 | 2017-12-07 | 株式会社神戸製鋼所 | Diagnosis device for diagnosing operational state of rotary machine, and diagnosis method |
| CN109522551A (en) * | 2018-11-09 | 2019-03-26 | 天津新开心生活科技有限公司 | Entity link method, apparatus, storage medium and electronic equipment |
| CN111339126A (en) * | 2020-02-27 | 2020-06-26 | 平安医疗健康管理股份有限公司 | Medical data screening method and device, computer equipment and storage medium |
| CN111698322A (en) * | 2020-06-11 | 2020-09-22 | 福州数据技术研究院有限公司 | Medical data safety sharing method based on block chain and federal learning |
| CN112088379A (en) * | 2018-03-07 | 2020-12-15 | 莫维迪乌斯有限公司 | Method and apparatus for determining weights for convolutional neural networks |
| CN112863665A (en) * | 2021-01-13 | 2021-05-28 | 质美(北京)生物科技有限公司 | Disease type discrimination method based on pathology and living tissue clinical diagnosis big data |
| CN113626480A (en) * | 2021-08-13 | 2021-11-09 | 昆明理工大学 | Direct current converter station SER event set diagnosis method based on improved association rule |
| CN113656558A (en) * | 2021-08-25 | 2021-11-16 | 平安科技（深圳）有限公司 | Method and device for evaluating association rule based on machine learning |
| CN113823414A (en) * | 2021-08-23 | 2021-12-21 | 杭州火树科技有限公司 | Main diagnosis and main operation matching detection method and device, computing equipment and storage medium |
-
2021
- 2021-12-28 CN CN202111622583.8A patent/CN114550885A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100105989A1 (en) * | 2005-06-08 | 2010-04-29 | Akihiro Inokuchi | Medical guide system |
| US20080201172A1 (en) * | 2006-04-25 | 2008-08-21 | Mcnamar Richard T | Method, system and computer software for using an xbrl medical record for diagnosis, treatment, and insurance coverage |
| JP2014119881A (en) * | 2012-12-14 | 2014-06-30 | Konica Minolta Inc | Information processor, label selection method and program |
| JP2017215832A (en) * | 2016-06-01 | 2017-12-07 | 株式会社神戸製鋼所 | Diagnosis device for diagnosing operational state of rotary machine, and diagnosis method |
| CN106202955A (en) * | 2016-07-19 | 2016-12-07 | 中电科软件信息服务有限公司 | Diagnosis associated packets method and system based on intellectual coded adaptation |
| CN112088379A (en) * | 2018-03-07 | 2020-12-15 | 莫维迪乌斯有限公司 | Method and apparatus for determining weights for convolutional neural networks |
| CN109522551A (en) * | 2018-11-09 | 2019-03-26 | 天津新开心生活科技有限公司 | Entity link method, apparatus, storage medium and electronic equipment |
| CN111339126A (en) * | 2020-02-27 | 2020-06-26 | 平安医疗健康管理股份有限公司 | Medical data screening method and device, computer equipment and storage medium |
| CN111698322A (en) * | 2020-06-11 | 2020-09-22 | 福州数据技术研究院有限公司 | Medical data safety sharing method based on block chain and federal learning |
| CN112863665A (en) * | 2021-01-13 | 2021-05-28 | 质美(北京)生物科技有限公司 | Disease type discrimination method based on pathology and living tissue clinical diagnosis big data |
| CN113626480A (en) * | 2021-08-13 | 2021-11-09 | 昆明理工大学 | Direct current converter station SER event set diagnosis method based on improved association rule |
| CN113823414A (en) * | 2021-08-23 | 2021-12-21 | 杭州火树科技有限公司 | Main diagnosis and main operation matching detection method and device, computing equipment and storage medium |
| CN113656558A (en) * | 2021-08-25 | 2021-11-16 | 平安科技（深圳）有限公司 | Method and device for evaluating association rule based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sunitha et al. | A comparative analysis of deep neural network architectures for the dynamic diagnosis of COVID‐19 based on acoustic cough features | |
| CN106845147B (en) | Method for building up, the device of medical practice summary model | |
| CN112420187B (en) | Medical disease analysis method based on migratory federal learning | |
| CN107392109A (en) | A kind of neonatal pain expression recognition method based on deep neural network | |
| CN110974214A (en) | Automatic electrocardiogram classification method, system and equipment based on deep learning | |
| CN111785384A (en) | Abnormal data identification method based on artificial intelligence and related equipment | |
| CN112690802B (en) | Method, device, terminal and storage medium for detecting electrocardiosignals | |
| CN111612041A (en) | Abnormal user identification method and device, storage medium and electronic equipment | |
| CN114448657B (en) | Distribution communication network security situation awareness and abnormal intrusion detection method | |
| CN108766557A (en) | Automatic arrhythmia analysis method based on channel signal fused neural network | |
| CN114330572A (en) | Anomaly detection method and system based on contrast learning and computer storage medium | |
| CN113642672A (en) | Feature processing method and device of medical insurance data, computer equipment and storage medium | |
| Taherinezhad et al. | COVID-19 crisis management: Global appraisal using two-stage DEA and ensemble learning algorithms | |
| CN114191665A (en) | Method and device for classifying man-machine asynchronous phenomena in mechanical ventilation process | |
| CN114550885A (en) | Main diagnosis and main operation matching detection method and system based on federal association rule mining | |
| CN112017779A (en) | Human health early warning system based on physical examination data analysis | |
| CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
| CN114610748B (en) | Medical disease data safe, rapid, accurate and effective management system based on artificial intelligence and application | |
| CN117542540A (en) | Infectious disease risk prediction method, infectious disease risk prediction device, electronic equipment and storage medium | |
| CN115188490A (en) | Epidemic situation prevention and control trace traceability intelligent management platform based on big data analysis | |
| Pivithuru et al. | E-patient Card: An Integrated Electronic Health Recording System for Patient | |
| CN112989083B (en) | Personnel identity analysis method, device, equipment and storage medium | |
| CN111986815A (en) | Project combination mining method based on co-occurrence relation and related equipment | |
| CN114202530A (en) | Method, device, equipment and storage medium for analyzing damage degree | |
| CN114298330A (en) | Model parameter adjusting method, device, equipment and readable storage medium |
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 |