CN111462897B - Patient similarity analysis method and system based on improved heterogeneous information network - Google Patents
Patient similarity analysis method and system based on improved heterogeneous information network Download PDFInfo
- Publication number
- CN111462897B CN111462897B CN202010249872.7A CN202010249872A CN111462897B CN 111462897 B CN111462897 B CN 111462897B CN 202010249872 A CN202010249872 A CN 202010249872A CN 111462897 B CN111462897 B CN 111462897B
- Authority
- CN
- China
- Prior art keywords
- information network
- heterogeneous information
- annotation
- patient
- annotated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a patient similarity analysis method and system based on an improved heterogeneous information network, which take patient hospitalization information as data input, construct an annotated heterogeneous information network and associate the relationship among patients, diseases and medicines; constructing a meta structure by using an expanded structure of the annotated heterogeneous information network as a directed graph of a template; and based on the meta structure, carrying out similarity calculation to obtain the similarity. In the connection of diseases and medicines, the notes of patient information are added, so that the problem that the classical heterogeneous information network loses the associated information between the patients and the medicines is solved, and the historical medical records can be well associated; the relationship among the patient, the disease and the medicine is related, and the accuracy of the similarity calculation of the patient is improved.
Description
Technical Field
The disclosure belongs to the technical field of data similarity analysis, and particularly relates to a patient similarity analysis method and system based on an improved heterogeneous information network.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The patient similarity analysis is based on the ubiquitous inter-patient distance assessment, and the general rules of disease development are obtained from a large amount of clinical practice data, so that the possibility of using a general computer-aided clinical decision support framework to achieve personalized diagnosis and treatment is provided. Generally, the analysis of patient similarity refers to the quantitative analysis of the distance between concepts in a complex concept semantic space by selecting clinical concepts (such as diagnosis, symptoms, examination, family history, past history, exposure environment, drugs, surgery, genes, etc.) as characteristic items of a patient in a specific medical environment. To date, the calculation of patient similarity has made significant progress, primarily in measuring the similarity between patients as represented by their key clinical indicators. However, clinical indexes cannot comprehensively measure the similarity of patients, and the heterogeneity and pleiotropic property of the clinical indexes are main factors for hindering the progress.
Patient similarity analysis is a simulation of a physician looking for similar or close patients, and is a systematic, computerized analysis of the mental process by which the physician makes clinical decisions. The computer uses an algorithm for calculating patient similarity, the information data used for which should characterize the patient as comprehensively as possible. In most patient similarity analysis methods, clinical indicators of patients are used to characterize patients. Firstly, the clinical indexes are various, the influence range of the clinical index change on patients is different, and it is difficult to determine which clinical indexes can best represent the patients; secondly, the influence of different clinical indicators on the patient is different, and it is difficult to determine the influence weight of different clinical indicators on the patient. Therefore, the calculated similarity is not accurate.
Disclosure of Invention
The invention aims to solve the problems and provides a patient similarity analysis method and system based on an improved heterogeneous information network.
According to some embodiments, the following technical scheme is adopted in the disclosure:
a patient similarity analysis method based on an improved heterogeneous information network comprises the following steps:
establishing an annotation heterogeneous information network by taking the hospitalization information of the patient as data input, and associating the relationship among the patient, the disease and the medicine;
constructing a meta structure by using an expanded structure of the annotated heterogeneous information network as a directed graph of a template;
and based on the meta structure, carrying out similarity calculation to obtain the similarity.
As an alternative embodiment, the annotated heterogeneous information network comprises three entities: patient (P), disease (D), and medication (M), for each disease D e D, its links have a set of patients, a set of medications, and the link type and annotation type are defined by the relationship between them.
As an alternative embodiment, there are one or more link types in the annotated heterogeneous information network corresponding to a set of < key, value > key-value pairs, each object type key e V belongs to a specific type object ψ (key) e a, value is a numerical value for recording the number of links, the set of < key, value > key-value pairs is referred to as an annotation of the heterogeneous information network and is denoted by C, and the number of key-value pairs in the set is referred to as the length of the annotation and is denoted by L; the set of key values is denoted by Keys.
As an alternative embodiment, the network schema of the annotated heterogeneous information network is denoted by SG ═ (a, R, I), and is a meta template of the annotated heterogeneous information network G ═ V, E, C, with an object type mapping ψ: V → a, a relationship type mapping
And an annotation type map θ I → C, which is a directed graph defined over the set of object types A, the set of relationship types R, and the set of annotation types I.
As an alternative implementation, the deployment of the annotated heterogeneous information network structure is to deploy the annotated heterogeneous information network into an annotated directed acyclic graph, divide one of the nodes with annotations into L nodes according to semantics, that is, the length of the annotations, and connect the nodes with the corresponding keys in the annotated key value set respectively; and the other node divides the other node into value according to the corresponding key values and is connected with the corresponding node respectively.
As an alternative embodiment, the meta-structure is a fixedA directed graph defined on the network model SG (a, R, I) of the annotated heterogeneous information network and using the expanded structure of the annotated heterogeneous information network as a template, which has a start node ns，nsAn in degree of 0, and a target node nt，ntOut degree is 0, S ═ N (N, M, N)s,nt) Wherein N is a point set, M is an edge set, and if x belongs to N, x belongs to A; if (x, y) ∈ M, (x, y) ∈ R.
As an alternative embodiment, the meta-structure based metric approach in using annotated heterogeneous information networks is: given AHIN G ═ V, E, C, meta structure S ═ N, M, Ns,nt) An initial node osAnd a target node otAnd then, firstly, constructing a subgraph expansion process of the expansion structure of the AHIN and tracking to form an ETree tree structure.
The similarity calculation process comprises the following steps:
with osAs a start node, otThe number of meta-structure instances that are target nodes;
or, for the start node osCan be extended to a target node otModeling the probability of the meta-structure instance;
or firstly changing the w function and then carrying out similarity calculation.
A patient similarity analysis system based on an improved heterogeneous information network, comprising:
the module is used for taking the hospitalization information of the patient as data input, constructing an annotation heterogeneous information network and associating the relationship among the patient, the disease and the medicine;
constructing a module of a meta structure by taking an expanded structure of the annotated heterogeneous information network as a directed graph of a template;
and based on the element structure, performing similarity calculation to obtain a module of similarity.
A computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the steps of the method for improved heterogeneous information network based patient similarity analysis.
A terminal device comprising a processor and a computer readable storage medium, the processor being configured to implement instructions; the computer readable storage medium is used for storing a plurality of instructions, which are suitable for being loaded by a processor and executing the steps of the patient similarity analysis method based on the improved heterogeneous information network.
Compared with the prior art, the beneficial effect of this disclosure is:
according to the method and the system, the notes of the patient information are added in the connection of the diseases and the medicines, so that the problem that the classical heterogeneous information network loses the associated information between the patients and the medicines is solved, and the historical medical records can be well associated.
The method and the device relate the relationship among the patient, the disease and the medicine, and improve the accuracy of similarity calculation of the patient.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and are not to limit the disclosure.
FIG. 1 is a network schematic diagram of a patient annotation information network of the present disclosure;
FIG. 2 is an example AHIN architecture development and meta-structure diagram of the present disclosure;
fig. 3 is an etre graphical illustration of the present disclosure.
The specific implementation mode is as follows:
the present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Annotated heterogeneous information networks are used to model for disease and drug data of patients. In the connection of diseases and medicines, the annotation of patient information is added, the association between the medicines of patients is ensured, and a patient similarity analysis method based on an improved heterogeneous information network is provided, in particular:
one is to build an Annotated Heterogeneous Information Network (AHIN).
And secondly, similarity calculation is carried out based on an AHIN meta-structure.
The method specifically comprises the following steps:
and the construction annotation heterogeneous information network module takes the hospitalization information of the patient as data input to construct an annotation heterogeneous information network. An annotated heterogeneous information network, a patient annotated information network, is constructed using patient medical record data and comprises three entities: patient (P), disease (D), and medication (M), for each disease D e D, its links have a set of patients, a set of medications, and the link type and annotation type are defined by the relationship between them.
(1) Construction AHIN G ═ (V, E, C)
Definition 1: an Annotated Heterogeneous Information Network (AHIN) is a special Heterogeneous Information Network G ═ V, E, C. In the classical heterogeneous information network, one or more link types corresponding to a set of key, value key value pairs exist, each object type key e V belongs to a specific type object psi (key) e A, and value is a numerical value used for recording the link times. We refer to the set of < key, value > key-value pairs as the annotation for the heterogeneous information network, denoted by C, and the number of key-value pairs in the set, denoted by L, as the length of the annotation. The set of key values is denoted by Keys.
FIG. 1 is a network schematic diagram of a patient annotation information network.
Definition 2: the Network model of the annotated heterogeneous information Network (Network Schema of AHIN) is denoted as (a, R, I) and isAHIN G ═ meta template of (V, E, C), with object type mapping ψ V → A, relationship type mapping
And an annotation type map θ I → C, which is a directed graph defined over the set of object types A, the set of relationship types R, and the set of annotation types I.
The AHIN structure expansion is to expand the AHIN into an annotated directed acyclic graph, divide one of the annotated connected nodes into L nodes according to semantics, namely the length of the annotation, and respectively connect the nodes with corresponding keys in an annotated key value set. And the other node divides the other node into value according to the corresponding key values and is connected with the corresponding node respectively.
(2) Construction of the Meta Structure S ═ N, M, Ns,nt)
Fig. 2 is an example of an AHIN architecture development and meta-architecture diagram.
Definition 3: the AHIN structure expansion is to expand the AHIN into an annotated directed acyclic graph, divide one of the annotated connected nodes into L nodes according to semantics, namely the length of the annotation, and respectively connect the nodes with corresponding keys in an annotated key value set. And the other node divides the other node into value according to the corresponding key values and is connected with the corresponding node respectively.
Definition 4: on the network mode SG ═ A, R, I of AHIN, using development structure of AHIN as template to construct directed graph, and having a starting node ns(in-degree of 0) and a target node nt(the out degree is 0). S ═ N (N, M, N)s,nt) Where N is the set of points and M is the set of edges. If x belongs to N, x belongs to A; if (x, y) ∈ M, (x, y) ∈ R.
Using meta-structure based metrics in annotated heterogeneous information networks:
given AHIN G ═ V, E, C, meta structure S ═ N, M, Ns,nt) An initial node osAnd a target node otAnd then, firstly, constructing a subgraph expansion process of the expansion structure of the AHIN and tracking to form an ETree tree structure.
Fig. 3 is an ETree chart constructed in this example.
Definition 5: given AHIN, meta-structure S and start node os, etre ═ is defined (T, L, w), where:
t represents the set of nodes of ETree, each node being a subgraph of the AHIN unfolded structure.
L is the set of edges;
the w () function maps the node v ∈ T of the tree to its weight w (v). When v ═ osW (v) ═ 1. Define u as the parent of v, i.e. (u, v) ∈ L, define v' as the child of u, then
(1) Measurement method StructCount:
the value of the structCount model is exactly osAs a start node, otAs the number of meta-structure instances of the target node.
(2) Measurement method AHIN Structure structured sub graph Expansion (ASCSE):
for the starting node osCan be extended to a target node otThe probabilities of the meta-structure instances of (a) are modeled.
(3) Measurement method binary AHIN Structure structured sub graph Expansion (BASCSE):
first, the w function is modified
Then, similarity calculation is carried out
In summary, according to the embodiment, the relationship among the patient, the disease and the drug is realized by improving the patient similarity analysis method of the heterogeneous information network, and the similarity calculation is more accurate by using the relationship among the three parts.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (7)
1. A patient similarity analysis method based on an improved heterogeneous information network is characterized by comprising the following steps: the method comprises the following steps:
establishing an annotation heterogeneous information network by taking the hospitalization information of the patient as data input, and associating the relationship among the patient, the disease and the medicine;
constructing a meta structure by using an expanded structure of the annotated heterogeneous information network as a directed graph of a template;
the annotated heterogeneous information network is a special heterogeneous information network G ═ (V, E, C), in the annotated heterogeneous information network, one or more link types exist corresponding to a set of key, value > key value pairs, each object type key E V belongs to a specific type object psi (key) E A, value is a numerical value and is used for recording the number of link times, the set of key, value > key value pairs is called an annotation of the heterogeneous information network and is represented by C, the number of key value pairs in the set is called the length of the annotation and is represented by L, the set of key value pairs is represented by Keys, and A is an object type set;
the method comprises the steps of expanding an annotation heterogeneous information network into an annotation-free directed acyclic graph, dividing one node of a connection with an annotation into L nodes according to semantics, namely the length of the annotation, and connecting the nodes with corresponding keys in an annotation key value set; the other node divides the other node into value according to the corresponding key value respectively and is connected with the corresponding node respectively;
and based on the meta structure, carrying out similarity calculation to obtain the similarity.
2. The method of claim 1, wherein the patient similarity analysis method based on the improved heterogeneous information network comprises: the annotated heterogeneous information network comprises three entities: patient (P), disease (D), and medication (M), for each disease D e D, its links have a set of patients, a set of medications, and the link type and annotation type are defined by the relationship between them.
3. The method of claim 1, wherein the patient similarity analysis method based on the improved heterogeneous information network comprises: the network model of the annotated heterogeneous information network is denoted by SG (a, R, I), and is a meta-template of the annotated heterogeneous information network G (V, E, C) having an object type mapping ψ V → a, a relationship type mapping
And an annotation type map θ C → I, which is a directed graph defined over the set of object types A, the set of relationship types R, and the set of annotation types I.
4. The method as claimed in claim 3, wherein the patient similarity analysis method based on the improved heterogeneous information network comprises: the meta structure is a directed graph defined on a network model SG (A, R, I) of the annotated heterogeneous information network and using an expanded structure of the annotated heterogeneous information network as a template, and the directed graph has a starting node ns，nsAn in degree of 0, and a target node nt，ntOut degree is 0, meta structure S ═ N (N, M, N)s,nt) Wherein N is a point set, M is an edge set, and if x belongs to N, x belongs to A; if (x, y) e M,then (x, y) e R.
5. A patient similarity analysis system based on an improved heterogeneous information network is characterized in that: the method comprises the following steps:
the module is used for taking the hospitalization information of the patient as data input, constructing an annotation heterogeneous information network and associating the relationship among the patient, the disease and the medicine;
constructing a module of a meta structure by taking an expanded structure of the annotated heterogeneous information network as a directed graph of a template;
the annotated heterogeneous information network is a special heterogeneous information network G ═ (V, E, C), in the annotated heterogeneous information network, one or more link types exist corresponding to a set of key, value > key value pairs, each object type key E V belongs to a specific type object psi (key) E A, value is a numerical value and is used for recording the number of link times, the set of key, value > key value pairs is called an annotation of the heterogeneous information network and is represented by C, the number of key value pairs in the set is called the length of the annotation and is represented by L, the set of key value pairs is represented by Keys, and A is an object type set;
the method comprises the steps of expanding an annotation heterogeneous information network into an annotation-free directed acyclic graph, dividing one node of a connection with an annotation into L nodes according to semantics, namely the length of the annotation, and connecting the nodes with corresponding keys in an annotation key value set; the other node divides the other node into value according to the corresponding key value respectively and is connected with the corresponding node respectively;
and based on the element structure, performing similarity calculation to obtain a module of similarity.
6. A computer-readable storage medium characterized by: a plurality of instructions are stored therein, the instructions being adapted to be loaded by a processor of a terminal device and to perform the steps of a method for improved heterogeneous information network based patient similarity analysis according to any one of claims 1 to 4.
7. A terminal device is characterized in that: the system comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; the computer readable storage medium is used for storing a plurality of instructions, which are suitable for being loaded by a processor and executing the steps of the patient similarity analysis method based on the improved heterogeneous information network of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010249872.7A CN111462897B (en) | 2020-04-01 | 2020-04-01 | Patient similarity analysis method and system based on improved heterogeneous information network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010249872.7A CN111462897B (en) | 2020-04-01 | 2020-04-01 | Patient similarity analysis method and system based on improved heterogeneous information network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111462897A CN111462897A (en) | 2020-07-28 |
| CN111462897B true CN111462897B (en) | 2021-05-11 |
Family
ID=71684385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010249872.7A Active CN111462897B (en) | 2020-04-01 | 2020-04-01 | Patient similarity analysis method and system based on improved heterogeneous information network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111462897B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192626B (en) * | 2021-04-13 | 2022-09-13 | 山东大学 | Medicine taking scheme recommendation system and method based on twin neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7917542B2 (en) * | 2008-03-04 | 2011-03-29 | Siemens Aktiengesellschaft | System and method for minimizing transmitted data between diverse institutions |
| CN103955535A (en) * | 2014-05-14 | 2014-07-30 | 南京大学镇江高新技术研究院 | Individualized recommending method and system based on element path |
| CN108596770A (en) * | 2017-12-29 | 2018-09-28 | 山大地纬软件股份有限公司 | Medicare fraud detection device and method based on outlier analysis |
| CN110322356A (en) * | 2019-04-22 | 2019-10-11 | 山东大学 | The medical insurance method for detecting abnormality and system of dynamic multi-mode are excavated based on HIN |
| CN110880362A (en) * | 2019-11-12 | 2020-03-13 | 南京航空航天大学 | Large-scale medical data knowledge mining and treatment scheme recommending system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105653846B (en) * | 2015-12-25 | 2018-08-31 | 中南大学 | Drug method for relocating based on integrated similarity measurement and random two-way migration |
| CN110310740B (en) * | 2019-04-15 | 2020-11-20 | 山东大学 | Re-hospitalizing information prediction method and system based on cross attention neural network |
-
2020
- 2020-04-01 CN CN202010249872.7A patent/CN111462897B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7917542B2 (en) * | 2008-03-04 | 2011-03-29 | Siemens Aktiengesellschaft | System and method for minimizing transmitted data between diverse institutions |
| CN103955535A (en) * | 2014-05-14 | 2014-07-30 | 南京大学镇江高新技术研究院 | Individualized recommending method and system based on element path |
| CN108596770A (en) * | 2017-12-29 | 2018-09-28 | 山大地纬软件股份有限公司 | Medicare fraud detection device and method based on outlier analysis |
| CN110322356A (en) * | 2019-04-22 | 2019-10-11 | 山东大学 | The medical insurance method for detecting abnormality and system of dynamic multi-mode are excavated based on HIN |
| CN110880362A (en) * | 2019-11-12 | 2020-03-13 | 南京航空航天大学 | Large-scale medical data knowledge mining and treatment scheme recommending system |
Non-Patent Citations (2)
| Title |
|---|
| Meta Structure: Computing Relevance in Large Heterogeneous Information Networks;Zhipeng Huang等;《KDD’16：Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining》;20161231;正文第1595-1600页 * |
| 医疗保险不合理用药检测方法的研究;彭锦峰;《中国优秀硕士学位论文全文数据库医药卫生科技辑》;20190115(第 01 期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111462897A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220043813A1 (en) | Method and system for ontology driven data collection and processing | |
| CN110459320B (en) | Knowledge graph-based auxiliary diagnosis and treatment system | |
| CN109712678B (en) | Relationship prediction method and device and electronic equipment | |
| Zhao et al. | EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning | |
| US20160132648A1 (en) | Data Processing System and Method for Computer-Assisted Coding of Natural Language Medical Text | |
| US20140149132A1 (en) | Adaptive medical documentation and document management | |
| CN103631847A (en) | Method and system for context-based search for a data store related to a graph node | |
| Beale | Archetypes and the EHR | |
| Xie et al. | Learning an expandable EMR-based medical knowledge network to enhance clinical diagnosis | |
| US20210202111A1 (en) | Method of classifying medical records | |
| Niu et al. | Fusion of sequential visits and medical ontology for mortality prediction | |
| Miller et al. | OptiPres: a distributed mobile agent decision support system for optimal patient drug prescription | |
| CN111462897B (en) | Patient similarity analysis method and system based on improved heterogeneous information network | |
| Singh et al. | Big Data in Oncology: Extracting Knowledge from Machine Learning | |
| Sarkar | Methods in biomedical informatics: a pragmatic approach | |
| Liu et al. | A few-shot disease diagnosis decision making model based on meta-learning for general practice | |
| CN113689924A (en) | Similar medical record retrieval method and device, electronic equipment and readable storage medium | |
| CN116737945B (en) | Mapping method for EMR knowledge map of patient | |
| CN115295165A (en) | Knowledge graph system for medical science and decision-making auxiliary method thereof | |
| Hodge et al. | Problem management module: an innovative system to improve problem list workflow | |
| Kerdprasop et al. | Bridging data mining model to the automated knowledge base of biomedical informatics | |
| Pfaff | Cohort identification using semantic web technologies: Ontologies and triplestores as engines for complex computable phenotyping | |
| EP3654339A1 (en) | Method of classifying medical records | |
| Kamdar | Mining the Web of Life Sciences Linked Open Data for Mechanism-Based Pharmacovigilance | |
| CN115938609B (en) | Drug repositioning method and system integrating curative effect comparison information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |