CN110911009A - Clinical diagnosis aid decision-making system and medical knowledge map accumulation method - Google Patents
Clinical diagnosis aid decision-making system and medical knowledge map accumulation method Download PDFInfo
- Publication number
- CN110911009A CN110911009A CN201911114104.4A CN201911114104A CN110911009A CN 110911009 A CN110911009 A CN 110911009A CN 201911114104 A CN201911114104 A CN 201911114104A CN 110911009 A CN110911009 A CN 110911009A
- Authority
- CN
- China
- Prior art keywords
- medical
- module
- data
- diagnosis
- diagnosed
- 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
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
- 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
- G06N3/045—Combinations of networks
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of clinical diagnosis, and discloses a clinical diagnosis aid decision-making system and a medical knowledge map accumulation method, wherein the clinical diagnosis aid decision-making system comprises: the medical treatment system comprises a vital sign acquisition module, a medical image acquisition module, a central control module, a diagnosis and analysis module, a treatment scheme recommendation module, a medical knowledge retrieval module, a map creation module, a data storage module and a display module. The invention can reach the effect that a plurality of disease species can be pre-diagnosed by only one model by using the historical data of each disease species to train the model through the diagnosis and analysis module, is very suitable for clinical diagnosis management and maintenance, and has accurate diagnosis and analysis results; meanwhile, the medical knowledge map is created through the map creation module, and medical data are managed through the medical knowledge map, so that when the medical data are used, the medical data can be extracted through the medical knowledge map, and convenience in using the medical data can be improved to a certain extent.
Description
Technical Field
The invention belongs to the technical field of clinical diagnosis, and particularly relates to a clinical diagnosis aid decision-making system and a medical knowledge map accumulation method.
Background
The clinical diagnosis refers to the examination of disease by doctors, and the classification and identification of the etiology and pathogenesis of the disease are used as the method and approach for making a treatment plan. The first step in diagnosis is to collect medical history data by asking the patient for subjective symptoms. The medical history can play a role in directing the diagnosis and can prompt clues of the diagnosis. However, existing clinical diagnosis aid decision-making systems are inaccurate for diagnostic analysis; meanwhile, because the medical data are huge, the efficiency is low when the data are processed in the existing scheme, so that the difficulty of data management is increased, and the convenience in using the medical data is low.
In summary, the problems of the prior art are as follows: the existing clinical diagnosis assistant decision-making system is inaccurate in diagnosis and analysis; meanwhile, because the medical data are huge, the efficiency is low when the data are processed in the existing scheme, so that the difficulty of data management is increased, and the convenience in using the medical data is low.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a clinical diagnosis aid decision-making system and a medical knowledge map accumulation method.
The invention is realized in such a way that a clinical diagnosis assistant decision system comprises:
the system comprises a vital sign acquisition module, a medical image acquisition module, a central control module, a diagnosis and analysis module, a treatment scheme recommendation module, a medical knowledge retrieval module, a map creation module, a data storage module and a display module;
the central control module is connected with the vital sign acquisition module, the medical image acquisition module, the diagnosis and analysis module, the treatment scheme recommendation module, the medical knowledge retrieval module, the map creation module, the data storage module and the display module and is used for controlling the modules to normally work through the main control computer;
the vital sign acquisition module is connected with the central control module and is used for acquiring vital sign data of the patient through the medical equipment;
the medical image acquisition module is connected with the central control module and is used for acquiring a patient diagnosis image through medical imaging equipment;
the diagnosis analysis module is connected with the central control module and is used for analyzing the patient diagnosis data through an analysis program;
the treatment scheme recommending module is connected with the central control module and is used for recommending a treatment scheme according to the diagnosis and analysis result through a recommending program;
the medical knowledge retrieval module is connected with the central control module and is used for detecting related medical knowledge through a retrieval program;
the map creation module is connected with the central control module and used for creating a medical knowledge map through a creation program;
the data storage module is connected with the central control module and used for storing the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map through the memory;
and the display module is connected with the central control module and used for displaying the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map through the display.
A medical knowledge map accumulation method of a clinical diagnosis aid decision-making system comprises the following steps:
acquiring vital sign data of a patient by using medical equipment through a vital sign acquisition module; acquiring a patient diagnosis image by using medical imaging equipment through a medical image acquisition module;
step two, the central control module analyzes the patient diagnosis data by using an analysis program through a diagnosis analysis module;
recommending a treatment scheme according to the diagnosis and analysis result by using a recommendation program through a treatment scheme recommendation module;
step four, detecting related medical knowledge by a medical knowledge retrieval module by utilizing a retrieval program;
step five, a medical knowledge map is created by a map creation module through a creation program;
step six, the data storage module is used for storing the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map by using a memory; and the collected data is displayed by the display module through the display.
Further, the diagnostic analysis module analysis method is as follows:
(1) acquiring a word vector matrix corresponding to the electronic medical record to be diagnosed through an analysis program;
(2) inputting the word vector matrix corresponding to the electronic medical record to be diagnosed into a pre-constructed deep convolutional neural network model to obtain a characteristic vector corresponding to the electronic medical record to be diagnosed;
(3) and classifying the feature vectors of the electronic medical record to be diagnosed by using a classifier to obtain the disease probability of each disease corresponding to the electronic medical record to be diagnosed.
Further, the acquiring a word vector matrix corresponding to the electronic medical record to be diagnosed includes:
performing at least one operation of information filtering, screening, word segmentation and statistics on the electronic medical record to be diagnosed to obtain each medical vocabulary of the medical record to be diagnosed;
acquiring a word vector corresponding to the medical vocabulary of the medical record to be diagnosed in the preset word vector database, wherein the preset word vector database stores the corresponding relation between the medical vocabulary and the word vector;
and generating a word vector matrix corresponding to the electronic disease to be diagnosed according to the word vector corresponding to the medical vocabulary of each electronic medical record to be diagnosed.
Further, before the obtaining of the word vector matrix corresponding to the electronic medical record to be diagnosed, the method includes:
acquiring each medical vocabulary in a medical word bank;
inputting the medical vocabulary in the medical lexicon into a Word2Vec model established in advance, and acquiring Word vectors corresponding to the medical vocabulary;
and forming a word vector sample by using the word vectors corresponding to the medical vocabulary, and storing the word vector sample in a preset word vector database.
Further, before the obtaining of each medical vocabulary in the medical lexicon, the method includes:
acquiring a plurality of diagnosed electronic medical records;
information filtering is carried out on each diagnosed electronic medical record by utilizing an information filtering technology, and a medical vocabulary set is obtained;
and counting the word frequency of each medical word in the medical word set, screening each medical word according to a set screening rule, and establishing the medical word bank according to a screening result.
Further, before the obtaining of the word vector matrix corresponding to the electronic medical record to be diagnosed, the method includes:
acquiring word vector matrixes corresponding to a plurality of diagnosed electronic medical records, and taking the word vector matrixes corresponding to the diagnosed electronic medical records as training samples;
and training the training sample to construct the deep convolutional neural network model.
Further, the map creation module is created by the following method:
1) acquiring medical data in a hospital system of at least one hospital in a target region through a picture creation program;
2) extracting a plurality of medical entities from the medical data;
3) establishing an incidence relation among the plurality of medical entities through a preset incidence relation establishment method among the medical entities;
4) and creating the medical knowledge graph according to a preset knowledge graph creating method according to the incidence relation among the medical entities.
Further, the creating a medical knowledge graph according to a preset knowledge graph creating method according to the association relationship among the plurality of medical entities includes:
extracting features of the medical entities to obtain feature data of each medical entity in the medical entities, wherein the feature data comprise keywords, and the keywords comprise medicine names, disease names and/or symptom names;
classifying the medical entities according to the characteristic data of the medical entities to obtain a plurality of medical entity categories;
constructing category identifications of the medical entity categories to obtain category identifications of the medical entity categories;
constructing a medical knowledge graph framework through the category identifications of the medical entities;
and storing the incidence relation among the plurality of medical entities in the medical knowledge map framework to obtain the medical knowledge map.
Further, the creating a medical knowledge graph according to a preset knowledge graph creating method according to the association relationship among the plurality of medical entities includes:
performing data transformation processing on the incidence relations among the plurality of medical entities to obtain relation identifications of the incidence relations among the plurality of medical entities;
classifying the medical entities by adopting a preset classification method to obtain a plurality of medical entity categories;
carrying out data transformation processing on the medical entity categories to obtain category identifications of the medical entity categories;
performing hash transformation on the category identifications of the medical entity categories to obtain hash values of the category identifications of the medical entity categories;
taking the hash value of the category identification of the medical entity categories as an index of a medical knowledge data linked list, and creating the medical knowledge data linked list;
and storing the incidence relation among the medical entities in the medical knowledge data linked list to obtain the medical knowledge map.
Further, the establishing of the association relationship between the plurality of medical entities by the preset association relationship establishing method between the medical entities includes:
performing feature extraction on the CT picture to obtain a plurality of feature values of the CT picture;
determining disease information corresponding to the CT picture according to the characteristic values;
determining a disease corresponding to the disease information according to the disease information;
determining that the disease corresponding to the disease information is associated with the CT picture.
The invention has the advantages and positive effects that: the invention applies the convolutional neural network to the text semantic understanding of the medical electronic medical record and performs auxiliary medical diagnosis through the diagnostic analysis module, and can effectively overcome the defects of the rule extraction and matching based method. The method can effectively solve the problem of semantic gap and effectively eliminate the influence caused by synonymy different words in electronic medical records such as writing; the method can be used for the conditions of various diseases and large differences in various departments without constructing corresponding rules and matching algorithms for the various diseases, a unified model frame can be constructed, and then the model is trained by using historical data of the various diseases, so that the effect of pre-diagnosing the various diseases by only one model can be achieved, the method is very suitable for management and maintenance, and the diagnosis and analysis are accurate; meanwhile, medical data in a hospital system of at least one hospital in a target region is acquired through a map creation module, a plurality of medical entities are extracted from the medical data, establishing the incidence relation among the plurality of medical entities through a preset incidence relation establishing method among the medical entities, and creating a medical knowledge graph according to a preset knowledge graph creation method according to the incidence relation among the plurality of medical entities, so that, extracting medical data in at least one hospital in a target region to obtain a plurality of medical entities, and establishing an incidence relation between medical entities according to the medical entities, sequentially establishing a medical knowledge graph, managing medical data through the medical knowledge graph, therefore, when medical data are used, the medical data can be extracted through the medical knowledge graph, and convenience in the process of using the medical data can be improved to a certain extent.
Drawings
Fig. 1 is a flowchart of a medical knowledge map accumulation method of a clinical diagnosis assistant decision-making system according to an embodiment of the present invention.
Fig. 2 is a block diagram of a clinical diagnosis assistant decision system according to an embodiment of the present invention.
In fig. 2: 1. a vital sign acquisition module; 2. a medical image acquisition module; 3. a central control module; 4. a diagnostic analysis module; 5. a treatment protocol recommendation module; 6. a medical knowledge retrieval module; 7. a map creation module; 8. a data storage module; 9. and a display module.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the medical knowledge map accumulation method of the clinical diagnosis assistant decision-making system provided by the invention comprises the following steps:
step S101, acquiring vital sign data of a patient by using medical equipment through a vital sign acquisition module; acquiring a patient diagnosis image by using medical imaging equipment through a medical image acquisition module;
step S102, the central control module analyzes the patient diagnosis data by using an analysis program through a diagnosis analysis module;
step S103, recommending a treatment scheme according to the diagnosis and analysis result by using a recommending program through a treatment scheme recommending module;
step S104, detecting related medical knowledge by a medical knowledge retrieval module by utilizing a retrieval program;
step S105, creating a medical knowledge map by using a creation program through a map creation module;
s106, storing the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map by using a memory through a data storage module; and the collected data is displayed by the display module through the display.
The step S104 of retrieving medical knowledge is to construct an atlas for reference.
As shown in fig. 2, the clinical diagnosis assistant decision system provided by the embodiment of the present invention includes: the system comprises a vital sign acquisition module 1, a medical image acquisition module 2, a central control module 3, a diagnosis and analysis module 4, a treatment scheme recommendation module 5, a medical knowledge retrieval module 6, a map creation module 7, a data storage module 8 and a display module 9.
The vital sign acquisition module 1 is connected with the central control module 3 and is used for acquiring vital sign data of a patient through medical equipment;
the medical image acquisition module 2 is connected with the central control module 3 and is used for acquiring a patient diagnosis image through medical imaging equipment;
the central control module 3 is connected with the vital sign acquisition module 1, the medical image acquisition module 2, the diagnosis and analysis module 4, the treatment scheme recommendation module 5, the medical knowledge retrieval module 6, the map creation module 7, the data storage module 8 and the display module 9 and is used for controlling each module to normally work through a main control computer;
the diagnosis and analysis module 4 is connected with the central control module 3 and is used for analyzing the patient diagnosis data through an analysis program;
the treatment scheme recommending module 5 is connected with the central control module 3 and is used for recommending a treatment scheme according to the diagnosis and analysis result through a recommending program;
a medical knowledge retrieval module 6 connected with the central control module 3 for detecting relevant medical knowledge through a retrieval program;
the map creation module 7 is connected with the central control module 3 and used for creating a medical knowledge map through a creation program;
the data storage module 8 is connected with the central control module 3 and used for storing the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map through a memory;
and the display module 9 is connected with the central control module 3 and used for displaying the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map through a display.
The diagnostic analysis module 4 provided by the invention has the following analysis method:
(1) acquiring a word vector matrix corresponding to the electronic medical record to be diagnosed through an analysis program;
(2) inputting the word vector matrix corresponding to the electronic medical record to be diagnosed into a pre-constructed deep convolutional neural network model to obtain a characteristic vector corresponding to the electronic medical record to be diagnosed;
(3) and classifying the feature vectors of the electronic medical record to be diagnosed by using a classifier to obtain the disease probability of each disease corresponding to the electronic medical record to be diagnosed.
The invention provides a method for acquiring a word vector matrix corresponding to an electronic medical record to be diagnosed, which comprises the following steps:
performing at least one operation of information filtering, screening, word segmentation and statistics on the electronic medical record to be diagnosed to obtain each medical vocabulary of the medical record to be diagnosed;
acquiring a word vector corresponding to the medical vocabulary of the medical record to be diagnosed in the preset word vector database, wherein the preset word vector database stores the corresponding relation between the medical vocabulary and the word vector;
and generating a word vector matrix corresponding to the electronic disease to be diagnosed according to the word vector corresponding to the medical vocabulary of each electronic medical record to be diagnosed.
Before the obtaining of the word vector matrix corresponding to the electronic medical record to be diagnosed, the method provided by the invention comprises the following steps:
acquiring each medical vocabulary in a medical word bank;
inputting the medical vocabulary in the medical lexicon into a Word2Vec model established in advance, and acquiring Word vectors corresponding to the medical vocabulary;
and forming a word vector sample by using the word vectors corresponding to the medical vocabulary, and storing the word vector sample in a preset word vector database.
Before each medical vocabulary in the medical lexicon is obtained, the method provided by the invention comprises the following steps:
acquiring a plurality of diagnosed electronic medical records;
information filtering is carried out on each diagnosed electronic medical record by utilizing an information filtering technology, and a medical vocabulary set is obtained;
and counting the word frequency of each medical word in the medical word set, screening each medical word according to a set screening rule, and establishing the medical word bank according to a screening result.
Before the obtaining of the word vector matrix corresponding to the electronic medical record to be diagnosed, the method provided by the invention comprises the following steps:
acquiring word vector matrixes corresponding to a plurality of diagnosed electronic medical records, and taking the word vector matrixes corresponding to the diagnosed electronic medical records as training samples;
and training the training sample to construct the deep convolutional neural network model.
The method for creating the map creation module 7 provided by the invention comprises the following steps:
1) acquiring medical data in a hospital system of at least one hospital in a target region through a picture creation program;
2) extracting a plurality of medical entities from the medical data;
3) establishing an incidence relation among the plurality of medical entities through a preset incidence relation establishment method among the medical entities;
4) and creating the medical knowledge graph according to a preset knowledge graph creating method according to the incidence relation among the medical entities.
The invention provides a method for creating a medical knowledge graph according to a preset knowledge graph creation method and according to the incidence relation among a plurality of medical entities, which comprises the following steps:
extracting features of the medical entities to obtain feature data of each medical entity in the medical entities, wherein the feature data comprise keywords, and the keywords comprise medicine names, disease names and/or symptom names;
classifying the medical entities according to the characteristic data of the medical entities to obtain a plurality of medical entity categories;
constructing category identifications of the medical entity categories to obtain category identifications of the medical entity categories;
constructing a medical knowledge graph framework through the category identifications of the medical entities;
and storing the incidence relation among the plurality of medical entities in the medical knowledge map framework to obtain the medical knowledge map.
The invention provides a method for creating a medical knowledge graph according to a preset knowledge graph creation method and according to the incidence relation among a plurality of medical entities, which comprises the following steps:
performing data transformation processing on the incidence relations among the plurality of medical entities to obtain relation identifications of the incidence relations among the plurality of medical entities;
classifying the medical entities by adopting a preset classification method to obtain a plurality of medical entity categories;
carrying out data transformation processing on the medical entity categories to obtain category identifications of the medical entity categories;
performing hash transformation on the category identifications of the medical entity categories to obtain hash values of the category identifications of the medical entity categories;
taking the hash value of the category identification of the medical entity categories as an index of a medical knowledge data linked list, and creating the medical knowledge data linked list;
and storing the incidence relation among the medical entities in the medical knowledge data linked list to obtain the medical knowledge map.
The invention provides a plurality of medical entities comprising diseases and CT pictures, wherein the incidence relation among the medical entities is established by a preset incidence relation establishing method among the medical entities, and the method comprises the following steps:
performing feature extraction on the CT picture to obtain a plurality of feature values of the CT picture;
determining disease information corresponding to the CT picture according to the characteristic values;
determining a disease corresponding to the disease information according to the disease information;
determining that the disease corresponding to the disease information is associated with the CT picture.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (10)
1. A clinical diagnostic aid decision system, comprising:
the system comprises a vital sign acquisition module, a medical image acquisition module, a central control module, a diagnosis and analysis module, a treatment scheme recommendation module, a medical knowledge retrieval module, a map creation module, a data storage module and a display module;
the central control module is connected with the vital sign acquisition module, the medical image acquisition module, the diagnosis and analysis module, the treatment scheme recommendation module, the medical knowledge retrieval module, the map creation module, the data storage module and the display module and is used for controlling the modules to normally work through the main control computer;
the vital sign acquisition module is connected with the central control module and is used for acquiring vital sign data of the patient through the medical equipment;
the medical image acquisition module is connected with the central control module and is used for acquiring a patient diagnosis image through medical imaging equipment;
the diagnosis analysis module is connected with the central control module and is used for analyzing the patient diagnosis data through an analysis program;
the treatment scheme recommending module is connected with the central control module and is used for recommending a treatment scheme according to the diagnosis and analysis result through a recommending program;
the medical knowledge retrieval module is connected with the central control module and is used for detecting related medical knowledge through a retrieval program;
the map creation module is connected with the central control module and used for creating a medical knowledge map through a creation program;
the data storage module is connected with the central control module and used for storing the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map through the memory;
and the display module is connected with the central control module and used for displaying the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map through the display.
2. A medical knowledge base accumulation method of a clinical diagnosis assistant decision system according to claim 1, wherein the medical knowledge base accumulation method of the clinical diagnosis assistant decision system comprises the steps of:
acquiring vital sign data of a patient by using medical equipment through a vital sign acquisition module; acquiring a patient diagnosis image by using medical imaging equipment through a medical image acquisition module;
step two, the central control module analyzes the patient diagnosis data by using an analysis program through a diagnosis analysis module;
recommending a treatment scheme according to the diagnosis and analysis result by using a recommendation program through a treatment scheme recommendation module;
step four, detecting related medical knowledge by a medical knowledge retrieval module by utilizing a retrieval program;
step five, a medical knowledge map is created by a map creation module through a creation program;
step six, the data storage module is used for storing the acquired vital signs of the patient, the medical image data, the diagnosis and analysis result, the recommendation scheme, the retrieval result and the medical map by using a memory; and the collected data is displayed by the display module through the display.
3. The clinical diagnostic aid decision making system according to claim 1, wherein the diagnostic analysis module analyzes the method as follows:
(1) acquiring a word vector matrix corresponding to the electronic medical record to be diagnosed through an analysis program;
(2) inputting the word vector matrix corresponding to the electronic medical record to be diagnosed into a pre-constructed deep convolutional neural network model to obtain a characteristic vector corresponding to the electronic medical record to be diagnosed;
(3) and classifying the feature vectors of the electronic medical record to be diagnosed by using a classifier to obtain the disease probability of each disease corresponding to the electronic medical record to be diagnosed.
4. The clinical diagnosis assistant decision system according to claim 3, wherein the obtaining of the word vector matrix corresponding to the electronic medical record to be diagnosed comprises:
performing at least one operation of information filtering, screening, word segmentation and statistics on the electronic medical record to be diagnosed to obtain each medical vocabulary of the medical record to be diagnosed;
acquiring a word vector corresponding to the medical vocabulary of the medical record to be diagnosed in the preset word vector database, wherein the preset word vector database stores the corresponding relation between the medical vocabulary and the word vector;
and generating a word vector matrix corresponding to the electronic disease to be diagnosed according to the word vector corresponding to the medical vocabulary of each electronic medical record to be diagnosed.
5. The clinical diagnosis assistant decision system according to claim 4, wherein before the obtaining the word vector matrix corresponding to the electronic medical record to be diagnosed, the method comprises:
acquiring each medical vocabulary in a medical word bank;
inputting the medical vocabulary in the medical lexicon into a Word2Vec model established in advance, and acquiring Word vectors corresponding to the medical vocabulary;
and forming a word vector sample by using the word vectors corresponding to the medical vocabulary, and storing the word vector sample in a preset word vector database.
6. The clinical diagnosis assistant decision system as claimed in claim 5, wherein before the obtaining of each medical vocabulary in the medical lexicon, the clinical diagnosis assistant decision system comprises:
acquiring a plurality of diagnosed electronic medical records;
information filtering is carried out on each diagnosed electronic medical record by utilizing an information filtering technology, and a medical vocabulary set is obtained;
and counting the word frequency of each medical word in the medical word set, screening each medical word according to a set screening rule, and establishing the medical word bank according to a screening result.
7. The clinical diagnosis assistant decision system according to claim 3, wherein before the obtaining the word vector matrix corresponding to the electronic medical record to be diagnosed, the system comprises:
acquiring word vector matrixes corresponding to a plurality of diagnosed electronic medical records, and taking the word vector matrixes corresponding to the diagnosed electronic medical records as training samples;
and training the training sample to construct the deep convolutional neural network model.
8. The clinical diagnostic aid decision making system according to claim 1, wherein the atlas creation module is created by:
1) acquiring medical data in a hospital system of at least one hospital in a target region through a picture creation program;
2) extracting a plurality of medical entities from the medical data;
3) establishing an incidence relation among the plurality of medical entities through a preset incidence relation establishment method among the medical entities;
4) and creating the medical knowledge graph according to a preset knowledge graph creating method according to the incidence relation among the medical entities.
9. The clinical diagnosis assistant decision system according to claim 8, wherein the medical knowledge-graph is created according to a preset knowledge-graph creation method based on the association relationship between the plurality of medical entities, comprising:
extracting features of the medical entities to obtain feature data of each medical entity in the medical entities, wherein the feature data comprise keywords, and the keywords comprise medicine names, disease names and/or symptom names;
classifying the medical entities according to the characteristic data of the medical entities to obtain a plurality of medical entity categories;
constructing category identifications of the medical entity categories to obtain category identifications of the medical entity categories;
constructing a medical knowledge graph framework through the category identifications of the medical entities;
and storing the incidence relation among the plurality of medical entities in the medical knowledge map framework to obtain the medical knowledge map.
10. The clinical diagnosis assistant decision system according to claim 8, wherein the medical knowledge-graph is created according to a preset knowledge-graph creation method based on the association relationship between the plurality of medical entities, comprising:
performing data transformation processing on the incidence relations among the plurality of medical entities to obtain relation identifications of the incidence relations among the plurality of medical entities;
classifying the medical entities by adopting a preset classification method to obtain a plurality of medical entity categories;
carrying out data transformation processing on the medical entity categories to obtain category identifications of the medical entity categories;
performing hash transformation on the category identifications of the medical entity categories to obtain hash values of the category identifications of the medical entity categories;
taking the hash value of the category identification of the medical entity categories as an index of a medical knowledge data linked list, and creating the medical knowledge data linked list;
storing the incidence relation among the medical entities in the medical knowledge data linked list to obtain a medical knowledge map;
the method for establishing the incidence relation among the medical entities comprises the following steps:
performing feature extraction on the CT picture to obtain a plurality of feature values of the CT picture;
determining disease information corresponding to the CT picture according to the characteristic values;
determining a disease corresponding to the disease information according to the disease information;
determining that the disease corresponding to the disease information is associated with the CT picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911114104.4A CN110911009A (en) | 2019-11-14 | 2019-11-14 | Clinical diagnosis aid decision-making system and medical knowledge map accumulation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911114104.4A CN110911009A (en) | 2019-11-14 | 2019-11-14 | Clinical diagnosis aid decision-making system and medical knowledge map accumulation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110911009A true CN110911009A (en) | 2020-03-24 |
Family
ID=69817344
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911114104.4A Pending CN110911009A (en) | 2019-11-14 | 2019-11-14 | Clinical diagnosis aid decision-making system and medical knowledge map accumulation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110911009A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111933306A (en) * | 2020-08-19 | 2020-11-13 | 泰康保险集团股份有限公司 | Medical consultation system and method, storage medium and electronic equipment |
CN112509688A (en) * | 2020-09-25 | 2021-03-16 | 卫宁健康科技集团股份有限公司 | Automatic analysis system, method, equipment and medium for pressure sore picture |
CN112530584A (en) * | 2020-12-15 | 2021-03-19 | 贵州小宝健康科技有限公司 | Medical diagnosis assisting method and system |
CN112992317A (en) * | 2021-05-10 | 2021-06-18 | 明品云(北京)数据科技有限公司 | Medical data processing method, system, equipment and medium |
CN112992362A (en) * | 2021-04-19 | 2021-06-18 | 北京妙医佳健康科技集团有限公司 | Body state evaluation device, electronic equipment and storage medium |
CN113035346A (en) * | 2021-02-22 | 2021-06-25 | 北京信息科技大学 | Medical knowledge map-based disease category assessment device and method |
CN113641784A (en) * | 2021-06-25 | 2021-11-12 | 合肥工业大学 | Medical knowledge recommendation method and system integrating medical teaching and research |
CN113808731A (en) * | 2020-06-11 | 2021-12-17 | 中国中医科学院中医药信息研究所 | Intelligent medical diagnosis system and method |
WO2022012687A1 (en) * | 2020-07-17 | 2022-01-20 | 武汉联影医疗科技有限公司 | Medical data processing method and system |
CN114155962A (en) * | 2022-02-10 | 2022-03-08 | 北京妙医佳健康科技集团有限公司 | Data cleaning method and method for constructing disease diagnosis by using knowledge graph |
CN116612892A (en) * | 2023-07-17 | 2023-08-18 | 天津市疾病预防控制中心 | Health monitoring method and system of wearable device |
WO2023186051A1 (en) * | 2022-03-31 | 2023-10-05 | 深圳市帝迈生物技术有限公司 | Auxiliary diagnosis method and apparatus, and construction apparatus, analysis apparatus and related product |
CN117476218A (en) * | 2023-12-27 | 2024-01-30 | 长春中医药大学 | Clinical knowledge graph-based traditional Chinese medicine gynecological nursing auxiliary decision-making system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107122612A (en) * | 2017-05-04 | 2017-09-01 | 王恩亭 | Chronic Non-Communicable Diseases intelligence diagnosis and treatment Computer Aided Analysis System |
CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
CN107863147A (en) * | 2017-10-24 | 2018-03-30 | 清华大学 | The method of medical diagnosis based on depth convolutional neural networks |
CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
CN109635121A (en) * | 2018-11-07 | 2019-04-16 | 平安科技(深圳)有限公司 | Medical knowledge map creation method and relevant apparatus |
-
2019
- 2019-11-14 CN CN201911114104.4A patent/CN110911009A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107122612A (en) * | 2017-05-04 | 2017-09-01 | 王恩亭 | Chronic Non-Communicable Diseases intelligence diagnosis and treatment Computer Aided Analysis System |
CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
CN107863147A (en) * | 2017-10-24 | 2018-03-30 | 清华大学 | The method of medical diagnosis based on depth convolutional neural networks |
CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
CN109635121A (en) * | 2018-11-07 | 2019-04-16 | 平安科技(深圳)有限公司 | Medical knowledge map creation method and relevant apparatus |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113808731A (en) * | 2020-06-11 | 2021-12-17 | 中国中医科学院中医药信息研究所 | Intelligent medical diagnosis system and method |
WO2022012687A1 (en) * | 2020-07-17 | 2022-01-20 | 武汉联影医疗科技有限公司 | Medical data processing method and system |
CN111933306A (en) * | 2020-08-19 | 2020-11-13 | 泰康保险集团股份有限公司 | Medical consultation system and method, storage medium and electronic equipment |
CN112509688A (en) * | 2020-09-25 | 2021-03-16 | 卫宁健康科技集团股份有限公司 | Automatic analysis system, method, equipment and medium for pressure sore picture |
CN112509688B (en) * | 2020-09-25 | 2024-06-11 | 卫宁健康科技集团股份有限公司 | Automatic analysis system, method, equipment and medium for pressure sore picture |
CN112530584A (en) * | 2020-12-15 | 2021-03-19 | 贵州小宝健康科技有限公司 | Medical diagnosis assisting method and system |
CN113035346B (en) * | 2021-02-22 | 2023-09-22 | 北京信息科技大学 | Disease category assessment device and method based on medical knowledge graph |
CN113035346A (en) * | 2021-02-22 | 2021-06-25 | 北京信息科技大学 | Medical knowledge map-based disease category assessment device and method |
CN112992362A (en) * | 2021-04-19 | 2021-06-18 | 北京妙医佳健康科技集团有限公司 | Body state evaluation device, electronic equipment and storage medium |
CN112992362B (en) * | 2021-04-19 | 2021-09-14 | 北京妙医佳健康科技集团有限公司 | Body state evaluation device, electronic equipment and storage medium |
CN112992317A (en) * | 2021-05-10 | 2021-06-18 | 明品云(北京)数据科技有限公司 | Medical data processing method, system, equipment and medium |
CN112992317B (en) * | 2021-05-10 | 2021-11-02 | 明品云(北京)数据科技有限公司 | Medical data processing method, system, equipment and medium |
CN113641784A (en) * | 2021-06-25 | 2021-11-12 | 合肥工业大学 | Medical knowledge recommendation method and system integrating medical teaching and research |
CN114155962A (en) * | 2022-02-10 | 2022-03-08 | 北京妙医佳健康科技集团有限公司 | Data cleaning method and method for constructing disease diagnosis by using knowledge graph |
WO2023186051A1 (en) * | 2022-03-31 | 2023-10-05 | 深圳市帝迈生物技术有限公司 | Auxiliary diagnosis method and apparatus, and construction apparatus, analysis apparatus and related product |
CN116612892A (en) * | 2023-07-17 | 2023-08-18 | 天津市疾病预防控制中心 | Health monitoring method and system of wearable device |
CN116612892B (en) * | 2023-07-17 | 2023-09-26 | 天津市疾病预防控制中心 | Health monitoring method and system of wearable device |
CN117476218A (en) * | 2023-12-27 | 2024-01-30 | 长春中医药大学 | Clinical knowledge graph-based traditional Chinese medicine gynecological nursing auxiliary decision-making system |
CN117476218B (en) * | 2023-12-27 | 2024-03-08 | 长春中医药大学 | Clinical knowledge graph-based traditional Chinese medicine gynecological nursing auxiliary decision-making system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110911009A (en) | Clinical diagnosis aid decision-making system and medical knowledge map accumulation method | |
JP5952835B2 (en) | Imaging protocol updates and / or recommenders | |
Carchiolo et al. | Medical prescription classification: a NLP-based approach | |
Marsh et al. | Development and validation of a deep learning model to quantify glomerulosclerosis in kidney biopsy specimens | |
CN113808738B (en) | Disease identification system based on self-identification image | |
WO2011048812A1 (en) | Medical work supporting system | |
CN112466462B (en) | EMR information association and evolution method based on deep learning of image | |
Giacalone et al. | BIG DATA: ISSUES AND AN OVERVIEW IN SOME STRATEGIC SECTORS. | |
CN111476772B (en) | Focus analysis method and device based on medical image | |
CN111524570A (en) | Ultrasonic follow-up patient screening method based on machine learning | |
CN113223734A (en) | Disease diagnosis and big health management platform based on algorithm, medical image and big data | |
CN116844733A (en) | Medical data integrity analysis method based on artificial intelligence | |
CN116913549A (en) | Adverse reaction event early warning method, device, system and electronic equipment | |
WO2023108155A1 (en) | Computer-implemented segmented numeral character recognition and reader | |
CN116110542A (en) | Data analysis method based on trusted multi-view | |
CN113643825B (en) | Medical case knowledge base construction method and system based on clinical key feature information | |
CN110223760B (en) | Medical image information acquisition and fusion method and system | |
CN114550930A (en) | Disease prediction method, device, equipment and storage medium | |
RU2609737C1 (en) | Automated system of distributed cognitive support of making diagnostic decisions in medicine | |
CN115700826A (en) | Receipt processing method, receipt display method, receipt processing device, receipt display device, computer equipment and storage medium | |
CN113314217A (en) | Common disease auxiliary self-diagnosis system based on inspection medical big data | |
CN111724873A (en) | Data processing method and device | |
CN111709946A (en) | Image data analysis method and device, terminal equipment and storage medium | |
CN111696677A (en) | Information management system for supporting clinical scientific research by using medical big data | |
CN110889836A (en) | Image data analysis method and device, terminal equipment and 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 |