CN112991075A - Package type medicine purchasing abnormity detection method based on FP-growth and graph network - Google Patents
Package type medicine purchasing abnormity detection method based on FP-growth and graph network Download PDFInfo
- Publication number
- CN112991075A CN112991075A CN202110155145.9A CN202110155145A CN112991075A CN 112991075 A CN112991075 A CN 112991075A CN 202110155145 A CN202110155145 A CN 202110155145A CN 112991075 A CN112991075 A CN 112991075A
- Authority
- CN
- China
- Prior art keywords
- medicine
- graph
- package type
- growth
- network
- 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
- 239000003814 drug Substances 0.000 title claims abstract description 91
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 230000007246 mechanism Effects 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 201000010099 disease Diseases 0.000 claims description 24
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 24
- 229940079593 drug Drugs 0.000 claims description 19
- 230000008520 organization Effects 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000007418 data mining Methods 0.000 abstract description 9
- 238000005065 mining Methods 0.000 description 13
- 238000011160 research Methods 0.000 description 4
- 235000013405 beer Nutrition 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 239000008267 milk Substances 0.000 description 1
- 210000004080 milk Anatomy 0.000 description 1
- 235000013336 milk Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Chemical & Material Sciences (AREA)
- Medical Informatics (AREA)
- Medicinal Chemistry (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of medical data mining, and particularly relates to a package type medicine purchasing abnormity detection method based on FP-growth and graph network. A package type medicine purchase abnormity detection method based on FP-growth and graph network comprises the following steps: s1, preprocessing data; s2, establishing a medicine relation graph; s3, training a network; s4, digging a medicine combination; s5, establishing a medicine relation diagram of a single mechanism; s6, predicting results; and S7, acquiring a final result, and repeating the iteration steps S4 to S6 to obtain all abnormal detail results of the specific area. The invention provides a package type medicine purchasing abnormity detection method based on FP-growth and graph network, which solves the problem of mechanism package type medicine purchasing and medical insurance fund collection.
Description
Technical Field
The invention belongs to the technical field of medical data mining, and particularly relates to a package type medicine purchasing abnormity detection method based on FP-growth and graph network.
Background
The current situation of cheating medical insurance funds is severe.
The detection of cheating insurance organizations/crowds by using an automatic technology is a main means except for manual spot check at present, and meanwhile, a regular detection mode is a mainstream method, so that the method has the advantages of simple logic, high consistency of detected objects, but also has the defects of poor algorithm migration capability, high space-time overhead, complex data preprocessing, weak detection capability of disguised behaviors and the like.
In order to overcome the deficiencies of the rule-based algorithm, a package-based medicine purchase anomaly detection method based on FP-growth and graph network is proposed, and the following is the technical background of the related art.
Frequent patterns are sets, sub-sequences or sub-structures of items that appear in the data set with a frequency not less than a user-specified threshold, such as the well-known diaper and beer examples. For example, frequency itemset, such as diapers and beer, is a frequent itemset. Subsequence, such as purchasing a PC first, then a digital camera, then a memory card, is a (frequent) sequential pattern if it is often present in a shopping history database. The sub-structure may refer to different structural forms, such as subgraphs, subtrees or sub-lattices, which may be combined with a set or subsequence of items. If a sub-structure is frequently present in a graphic database, it is called the (frequent) structural pattern. Finding frequent patterns plays an important role in mining associations, and many other interesting relationships between associations and data. In addition, it also facilitates data indexing, classification, clustering, and other data mining tasks. Thus, frequent pattern mining has become an important data mining task and a focused topic in data mining research.
For more than twenty years, frequent pattern mining has been the focus of data mining research. Of course, this research has made tremendous progress, as well as the extensive use of such research fronts in transactional databases from efficient and scalable frequent itemset mining algorithms, such as sequential pattern mining, structured pattern mining, association classification, and frequent pattern-based clustering.
Frequent pattern mining was first proposed by Agrawal in 1993 and was used to study the correlation between sales of commodities in a supermarket. For example, when a customer purchases milk, the customer may also purchase some goods.
Since the first proposal, the application of the algorithm is also derived, and the algorithm becomes one of the basic practical methods for data mining from a scalable data mining method, a wide range of data types, various extended mining tasks and various new applications.
The comparison is typically carried out by three algorithms, Apriori, FP-growth and Eclat, and Agrawal and Srikant discovered an interesting down-closed characteristic, also called Apriori, in 1994. He finds that the set of k items occurs frequently only if all the sets of sub-items are frequent. Later, improvements to the apriori algorithm also arose. Apriori, however, has two problems (1) generating a large number of candidate sets, (2) iteratively scanning the database and examining the pattern matching pair candidates. Han. (2000) proposes the FP-growth algorithm to mine the complete set of frequent item sets without candidate sets. FP-growth is a new method that only requires scanning the data set twice. The FP-growth contains two parts of contents, and firstly, an FP-tree needs to be constructed, the FP-tree highly compresses information in a database, and then frequent patterns are mined on the FP-tree.
A graph (graph) is a data format that can be used to represent a social network, a communication network, a protein molecular network, etc., where nodes in the graph represent individuals in the network and edges represent connection relationships between individuals. Graph structure data is required for many machine learning tasks such as community discovery, link prediction and the like, so the appearance of graph convolutional neural networks provides a new idea for solving the problems. The invention just combines the two strategies for use.
Disclosure of Invention
The invention aims to solve the technical problem of providing a package type medicine purchasing abnormity detection method based on FP-growth and graph network, which solves the problem of mechanism package type medicine purchasing and medical insurance fund collection. Therefore, the invention adopts the following technical scheme:
a package type medicine purchase abnormity detection method based on FP-growth and graph network comprises the following steps:
s1, preprocessing data, namely processing a plurality of prescription data of a single visit of a single person in a specific area into a single record of the single person;
s2, establishing a medicine relation graph, and establishing a medicine relation graph of a specific area according to the data obtained in the step S1;
s3, training a network, constructing a graph convolution neural network, and training the graph neural network by using labeled data to obtain a network model;
s4, excavating a medicine combination, and excavating the medicine combination by using an FP-growth algorithm on the result obtained in the step S1;
s5, establishing a medicine relation diagram of the single organization, and establishing the medicine relation diagram of the single organization according to the result obtained in the step S1;
s6, predicting the result, and analyzing and predicting the result obtained in the step S5 according to the network model obtained in the step S3;
and S7, acquiring a final result, and repeating the iteration steps S4 to S6 to obtain all abnormal detail results of the specific area.
The present invention is based on real institutional prescription data. Firstly, processing a plurality of prescription data of a single doctor in a certain area into a single doctor record, establishing a medicine relation graph of the area, and training a neural network by using labeled data to obtain a network model. And then, each time of mechanism processing, a single person in the mechanism uses an FP-growth algorithm to mine the medicine combination and establish a medicine relation graph of the single mechanism, a network model obtained by global training is used for predicting whether the medicine combination is abnormal in the medicine network, and if the medicine combination is predicted to be abnormal, the medicine combination is determined to be bought in a package mode. And repeating the processing flow of the single mechanism continuously to obtain package type medicine purchasing abnormal results of all mechanisms in the area.
On the basis of the technical scheme, the invention can also adopt the following further technical scheme:
the pieces of prescription data for a single visit by a single person in step S1 include at least institution information, disease information, prescription information, and personal information.
The organization information at least comprises an organization code, an organization name and an organization address;
the disease information at least comprises a disease code, a disease name and a disease onset age interval;
the prescription information at least comprises a medicine code and a medicine name;
the personal information at least comprises age, gender and region.
In the graph of the drug relationship graph obtained in the step S2, the nodes include two types, i.e., drug and disease, the drug nodes include drug information, the disease nodes include disease information, and a part of relationship weight is added to the connection edge in the relationship graph if each record is recorded for each of the disease and the drug, or for each record for each of the drug and the drug.
The labeled data in step S3 is the relationship between drugs and whether the drugs are abnormal or not.
Further, in the process of training the graph convolutional neural network, it is found that the labeled data is not enough to train the network, that is, there is a problem of too little data. In order to obtain a neural network model with certain prediction capability, a Semi-supervised graph convolutional network (Semi-GCN) is used in the model aspect, the topological structure of the graph and the self information of the nodes are fully utilized, and the actual effect is better than the prediction effect of a fully-supervised network model.
In the step S4, the minimum support degree is 0.10-0.15, and the minimum confidence degree is 0.40-0.50.
Further, the FP-growth algorithm is used for mining the medicine combinations in the mechanism, but in practical application, too many medicine combinations are obtained by algorithm mining, and the similarity of partial medicine combinations is extremely high, so that the data quantity to be processed by the model is too large, and the overall operation efficiency of the invention is influenced. In order to solve the problem, the maximum similarity and minimum support degree principle is used for carrying out aggregation processing on the medicine combination, namely, a frequent item set with high similarity is aggregated into a larger frequent item set, but the support degree is still larger than the minimum support degree threshold value.
The topological logic of the drug relationship diagram of the single mechanism in the step S5 is consistent with the drug relationship diagram in the step S2.
Compared with the prior art, the invention has the following beneficial effects:
1) the method and the device have the advantages that the FP-growth algorithm is utilized to accelerate the mining speed of the frequent item set, and compared with the method and the device which use Apriori, the method and the device have higher efficiency. The FP-growth algorithm is optimized, the frequent item set obtained by the algorithm is further compressed by using the maximum similarity minimum support principle, the space-time overhead is further reduced, and the data volume of ten million levels can still be applied.
2) The Semi-GCN method is used, the self information of the constructed graph network is fully utilized, and the model can further improve the prediction accuracy rate under the condition that the manual marking work is not increased.
3) The invention is an original idea of applying FP-growth and graph convolution to the field of data mining, and compared with a rule base establishing mode (a plurality of rules among medicines are easy to consume a large amount of manpower and material resources), the efficiency is higher, less resources are consumed, and the performance of a model is better.
Drawings
FIG. 1 is an iterative labeling flowchart of a package-type medicine-purchasing abnormality detection method based on FP-growth and graph networks.
Detailed Description
For further understanding of the present invention, the following describes a package type medicine purchasing abnormality detection method based on FP-growth and graph network in detail with reference to specific embodiments, but the present invention is not limited thereto, and those skilled in the art can make insubstantial improvements and modifications under the core guidance of the present invention, and still fall within the scope of the present invention.
The embodiment provides a package type medicine purchasing abnormity detection method based on FP-growth and graph network, which comprises the following steps:
and S1, preprocessing data, and processing a plurality of prescription data of a single visit of a single person in a specific area into a single record of the single person.
Specifically, multiple pieces of prescription data of single-person single-time visit of all institutions in a certain region are processed into a single-person single-time record, and fields contained in the record comprise institution codes, institution names, visit serial numbers, information of insured persons, medicine purchasing codes, medicine purchasing names, diagnosis disease codes, diagnosis disease names and the like.
S2, establishing a medicine relation graph, and establishing a medicine relation graph of the specific area according to the data obtained in the step S1.
Specifically, a drug relationship graph of the region is established according to the data obtained in step S1, and nodes in the graph contain two types, i.e., drug and disease. The medicine node contains medicine information, the disease node contains disease information, and each record of the disease and the medicine or the medicine and the medicine increases a part of relation weight on the connecting edge in the relation graph, and the graph is marked as G.
And S3, training a network, constructing a graph convolution neural network, and training the graph neural network by using the labeled data to obtain a network model.
Specifically, a graph convolution neural network is constructed, and the graph network is trained by using labeled data to obtain a network model which is marked as M.
And S4, mining the medicine combination, and mining the medicine combination by using an FP-growth algorithm on the result obtained in the step S1.
Specifically, an FP tree is built according to single-person single record in a single organization, a conditional FP tree of each data item is built, frequent patterns meeting the minimum support degree and the minimum confidence degree are mined, and all frequent patterns in the organization are recorded as S.
S5, establishing a medicine relation graph of the single organization, and establishing the medicine relation graph of the single organization according to the result obtained in the step S1.
Specifically, a drug relationship graph network of the single organization is established according to the single record of the single person in the single organization, and the network node attribute, the topology logic of the graph network are consistent with the relationship graph in the step S2, which is denoted as G'.
S6, predicting the result, and analyzing and predicting the result obtained in the step S5 according to the network model obtained in the step S3.
Specifically, G' is analyzed by using the trained model M, the abnormal degree of each medicine combination of the S set is predicted, and the combination with the abnormal probability exceeding a certain threshold (such as 0.90) is defined as an abnormal group. And searching all the treatment records containing the medicine combination in the mechanism, and obtaining a screened record which is the final abnormal result and is marked as A.
And S7, acquiring a final result, and repeating the iteration steps S4 to S6 until all mechanisms in the region are processed, and finally obtaining all exception details of the region.
While the invention has been shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the appended claims.
Claims (7)
1. A package type medicine purchasing abnormity detection method based on FP-growth and graph network is characterized by comprising the following steps:
s1, preprocessing data, namely processing a plurality of prescription data of a single visit of a single person in a specific area into a single record of the single person;
s2, establishing a medicine relation graph, and establishing a medicine relation graph of a specific area according to the data obtained in the step S1;
s3, training a network, constructing a graph convolution neural network, and training the graph neural network by using labeled data to obtain a network model;
s4, excavating a medicine combination, and excavating the medicine combination by using an FP-growth algorithm on the result obtained in the step S1;
s5, establishing a medicine relation diagram of the single organization, and establishing the medicine relation diagram of the single organization according to the result obtained in the step S1;
s6, predicting the result, and analyzing and predicting the result obtained in the step S5 according to the network model obtained in the step S3;
and S7, acquiring a final result, and repeating the iteration steps S4 to S6 to obtain all abnormal detail results of the specific area.
2. The package type medicine purchase abnormality detection method according to claim 1, wherein the plurality of pieces of prescription data for a single visit by a single person in step S1 include at least institution information, disease information, prescription information, and personal information.
3. The package type medicine purchase abnormality detection method based on the FP-growth and graph network as claimed in claim 2, wherein said organization information at least includes organization code, organization name, organization address;
the disease information at least comprises a disease code, a disease name and a disease onset age interval;
the prescription information at least comprises a medicine code and a medicine name;
the personal information at least comprises age, gender and region.
4. The package type medicine purchasing abnormality detection method based on the FP-growth and graph network as claimed in claim 1, wherein the nodes in the graph of the medicine relationship graph obtained in the step S2 include two types of medicine and disease, the medicine nodes include medicine information, the disease nodes include disease information, and a part of relationship weight is added to the connection edge in the relationship graph if there is one record for each of disease and medicine or medicine and medicine.
5. The package type abnormality detection method for drug purchase based on FP-growth and graph network as claimed in claim 1, wherein said step S3 is executed with the annotation data of drug relationship and whether it is abnormal or not.
6. The method for detecting abnormality in package type medicine purchase according to claim 1, wherein the minimum support degree in step S4 is 0.10-0.15, and the minimum confidence degree is 0.40-0.50.
7. The method for detecting abnormality in package type medicine purchase according to claim 1, wherein the topological logic of the drug relationship diagram of a single mechanism in step S5 is consistent with the drug relationship diagram in step S2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155145.9A CN112991075A (en) | 2021-02-04 | 2021-02-04 | Package type medicine purchasing abnormity detection method based on FP-growth and graph network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155145.9A CN112991075A (en) | 2021-02-04 | 2021-02-04 | Package type medicine purchasing abnormity detection method based on FP-growth and graph network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112991075A true CN112991075A (en) | 2021-06-18 |
Family
ID=76347023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110155145.9A Pending CN112991075A (en) | 2021-02-04 | 2021-02-04 | Package type medicine purchasing abnormity detection method based on FP-growth and graph network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991075A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116108906A (en) * | 2023-04-06 | 2023-05-12 | 北京亚信数据有限公司 | Disease drug relation mapping model training and related recommendation and detection methods and devices |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985483A (en) * | 2017-06-05 | 2018-12-11 | 易先威 | A kind of method of drug Method for Sales Forecast |
| CN109545316A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | Purchase the processing method and Related product of medicine data |
| CN109636061A (en) * | 2018-12-25 | 2019-04-16 | 深圳市南山区人民医院 | Training method, device, equipment and the storage medium of medical insurance Fraud Prediction network |
| CN109635113A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Abnormal insured people purchases medicine data detection method, device, equipment and storage medium |
| CN111105317A (en) * | 2019-12-28 | 2020-05-05 | 哈尔滨工业大学 | Medical insurance fraud detection method based on medicine purchase record |
| CN112070277A (en) * | 2020-08-17 | 2020-12-11 | 杭州电子科技大学 | Hypergraph neural network-based drug-target interaction prediction method |
| CN112216396A (en) * | 2020-10-14 | 2021-01-12 | 复旦大学 | Method for predicting drug-side effect relationship based on graph neural network |
-
2021
- 2021-02-04 CN CN202110155145.9A patent/CN112991075A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985483A (en) * | 2017-06-05 | 2018-12-11 | 易先威 | A kind of method of drug Method for Sales Forecast |
| CN109545316A (en) * | 2018-10-30 | 2019-03-29 | 平安科技（深圳）有限公司 | Purchase the processing method and Related product of medicine data |
| CN109635113A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Abnormal insured people purchases medicine data detection method, device, equipment and storage medium |
| CN109636061A (en) * | 2018-12-25 | 2019-04-16 | 深圳市南山区人民医院 | Training method, device, equipment and the storage medium of medical insurance Fraud Prediction network |
| CN111105317A (en) * | 2019-12-28 | 2020-05-05 | 哈尔滨工业大学 | Medical insurance fraud detection method based on medicine purchase record |
| CN112070277A (en) * | 2020-08-17 | 2020-12-11 | 杭州电子科技大学 | Hypergraph neural network-based drug-target interaction prediction method |
| CN112216396A (en) * | 2020-10-14 | 2021-01-12 | 复旦大学 | Method for predicting drug-side effect relationship based on graph neural network |
Non-Patent Citations (1)
| Title |
|---|
| 尚庆生: "基于频繁项集挖掘的零售医药企业药品关联研究", 《重庆科技学院学报（自然科学报）》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116108906A (en) * | 2023-04-06 | 2023-05-12 | 北京亚信数据有限公司 | Disease drug relation mapping model training and related recommendation and detection methods and devices |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Graph summarization methods and applications: A survey | |
| US11244765B2 (en) | Systems and methods for topological data analysis using nearest neighbors | |
| Roddick et al. | A survey of temporal knowledge discovery paradigms and methods | |
| Frawley et al. | Knowledge discovery in databases: An overview | |
| Pears et al. | Weighted association rule mining via a graph based connectivity model | |
| Berger et al. | Data mining as a tool for research and knowledge development in nursing | |
| Enriko | Comparative study of heart disease diagnosis using top ten data mining classification algorithms | |
| Paidi | Data mining: Future trends and applications | |
| Mak et al. | A financial data mining model for extracting customer behavior | |
| Zimmermann | Method evaluation, parameterization, and result validation in unsupervised data mining: A critical survey | |
| Makridis et al. | A deep learning approach using natural language processing and time-series forecasting towards enhanced food safety | |
| Banait et al. | An efficient clustering technique for big data mining | |
| Wei et al. | Knowledge discovery and data mining | |
| CN112991075A (en) | Package type medicine purchasing abnormity detection method based on FP-growth and graph network | |
| Kaushik et al. | Evaluating frequent-set mining approaches in machine-learning problems with several attributes: a case study in healthcare | |
| Thangaraj et al. | Big data Analytics: Concepts, Techniques, Tools and Technologies | |
| Jalali et al. | Event mining for explanatory modeling | |
| Kumbhar et al. | Web mining: A Synergic approach resorting to classifications and clustering | |
| Schlüter | Knowledge discovery from time series | |
| Sumathi et al. | Data warehousing, data mining, and OLAP | |
| Zhao | An empirical study of data mining in performance evaluation of HRM | |
| Singh et al. | Maximum spanning tree based redundancy elimination for feature selection of high dimensional data. | |
| Islam | Multi-layer hybrid balancing technique to remove data imbalance | |
| Shrivastava et al. | Literature review on tools & applications of data mining | |
| Singh | Cognitive Social Mining Analysis Using Data Mining Techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |