CN113688205A - Disease detection method based on deep learning - Google Patents
Disease detection method based on deep learning Download PDFInfo
- Publication number
- CN113688205A CN113688205A CN202110983314.8A CN202110983314A CN113688205A CN 113688205 A CN113688205 A CN 113688205A CN 202110983314 A CN202110983314 A CN 202110983314A CN 113688205 A CN113688205 A CN 113688205A
- Authority
- CN
- China
- Prior art keywords
- disease
- patient
- deep learning
- detection method
- method based
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- 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
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Animal Behavior & Ethology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a disease detection method based on deep learning, which comprises the following steps: extracting keywords from case descriptions input by a patient by using a natural language processing technology, and performing auxiliary disease judgment by adopting a system-user interaction mode; the maximum scale outbreak time and the number of people of the disease are calculated by crawling disease data in province and city ranges and an SIR infectious disease prediction model; and generating a knowledge map of the family genetic diseases by using neo4j software in the form of entity-relationship-attribute triples to give early warning to the genetic diseases. The disease detection method based on deep learning of the invention takes a patient as a center, gives the patient comprehensive, professional and personalized medical experience, and provides a safe and reliable treatment scheme for the patient by using advanced treatment experience in combination with big data, thereby being beneficial to relieving the problem of insufficient medical resources and effectively monitoring and preventing large infectious diseases.
Description
Technical Field
The invention belongs to the technical field of intelligent medical treatment, and particularly relates to a disease detection method based on deep learning.
Background
Improve the health level of people, realize the ideal of all diseases, and is the common pursuit of human society. The medical health is related to the health of hundreds of millions of people, and is a significant civil problem. However, the medical system is inefficient and the manner of queuing for a registration visit consumes a significant amount of time such that the patient may miss the optimal treatment time. The medical service quality is not good enough, the treatment level of doctors is irregular, and misdiagnosis and other situations happen occasionally. Difficult and expensive to see, inconvenient traffic in poor areas and remote mountain areas, difficult to see and unable to pay medical expenses. The problems that large hospitals are full of patients, community hospitals do not ask for extra fluid, the patient treatment procedures are complicated and the like are caused by unsmooth and incomplete medical information, dual polarization of medical resources and the like.
According to survey and display, people tend to know body index data of people in real time in daily life instead of going to a hospital for physical examination at intervals; when the patient is ill, the patient prefers to know the pathogeny of the patient to see a doctor in a hospital; when social diseases occur, the people prefer to master the latest trends of epidemic situations without going out of the house. Based on the above situation, in order to respond to the call of intelligent medical treatment, a disease detection system based on deep learning is constructed by combining multiple novel technologies such as medical big data, knowledge maps, data visualization, artificial intelligence field disease monitoring and the like. The system adopts an SSM framework and is based on Java, python, MySQL and the like, mainly analyzes diseases from three aspects,
the first is disease diagnosis: extracting patient condition description keywords through a KEA algorithm, searching in massive disease data by utilizing a database query technology according to the extracted keywords, and making a judgment by using a system-user response mode auxiliary system to finally obtain a predicted disease. The user can look up information such as the cause and symptom of the predicted disease, recommended drugs and the like, and can search a case database for a case with the same symptom as the user.
Secondly, infectious disease monitoring and prevention: predicting the disease as infectious disease, carrying out dynamic visual analysis on the system monitoring patient body temperature and heartbeat and other signs in a broken line graph mode, giving a comparison graph of the signs after taking medicines or treating for a period of time, extracting the regional distribution of people suffering from the disease for a period of time from a background database, labeling the regional distribution with opentreetmap, and analyzing whether the disease is a group infectious disease. The prevalence rate, the death rate, the cure rate and the like of the disease are crawled in the whole country by using a crawler technology of python, the AJAX updates the data in the graph in real time, and the SIR model is used for judging the maximum scale outbreak date and the number of people of the disease and giving an early warning.
Thirdly, monitoring and controlling genetic diseases: predicting the disease as genetic disease, monitoring the patient signs systematically and making disease prevention and treatment reminders for the patient by combining the patient family genetic history mapped by neo4 j.
Disclosure of Invention
Based on the defects of the prior art, the invention provides the disease detection method based on deep learning, which takes a patient as a center, gives the patient comprehensive, professional and personalized medical experience, combines big data to use advanced treatment experience for reference, provides a safe and reliable treatment scheme for the patient, is beneficial to relieving the problem of insufficient medical resources, and can effectively monitor and prevent large infectious diseases.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention provides a disease detection method based on deep learning, which comprises the following steps:
step 1: extracting keywords from case descriptions input by a patient by using a natural language processing technology, and performing auxiliary disease judgment by adopting a system-user interaction mode;
step 2: adopting OpenStreetMap to carry out geographic marking on the region where the sick personnel are located, calculating the disease incidence density by a clustering model so as to judge the disease as the clustered infectious disease, and calculating the maximum scale outbreak time and the number of the sick by crawling the disease data in the province and city range and an SIR infectious disease prediction model;
and step 3: the echarts chart visualizes basic signs and disease signs of a patient, and generates a family genetic disease knowledge map by using neo4j software in the form of entity-relation-attribute triples to give an early warning to genetic diseases.
Further, in step S1, a disease symptom vocabulary in a specific medical field is first constructed, and keyword extraction is performed on the disease description input by the user by using a KEA algorithm; and finding out phrases in disease description according to the disease symptom word list, using the phrases and other words as candidate keywords together, then selecting TF-IDF values of all the words by using a naive Bayes algorithm, using position information as characteristics, training and predicting to finally obtain disease keyword.
Further, in step S2, the basic physical signs of the patient are monitored, the regional distribution of the people with the infectious disease is retrieved over a period of time, the distribution of the people with the infectious disease is labeled on a map by using an OpenStreetMap, an infectious disease density threshold is set, the disease density is calculated by using an OPTICS algorithm, and if the disease density exceeds the threshold, the disease is determined to be an infectious disease with an aggregation.
Therefore, the disease detection method based on deep learning of the invention takes the patient as the center, gives the patient comprehensive, professional and personalized medical experience, and provides a safe and reliable treatment scheme for the patient by using advanced treatment experience in combination with big data, thereby being beneficial to relieving the problem of insufficient medical resources and effectively monitoring and preventing large infectious diseases.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following detailed description is given in conjunction with the preferred embodiments, together with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments will be briefly described below.
FIG. 1 is a flow chart of a disease detection method based on deep learning;
FIG. 2 is a diagram of a KEA algorithm training and prediction process;
FIG. 3 is a flow chart of the Bert Model;
FIG. 4 is a SSM framework access logic diagram.
Detailed Description
Other aspects, features and advantages of the present invention will become apparent from the following detailed description, taken in conjunction with the accompanying drawings, which form a part of this specification, and which illustrate, by way of example, the principles of the invention. In the referenced drawings, the same or similar components in different drawings are denoted by the same reference numerals.
As shown in fig. 1 to 4, the disease detection method based on deep learning of the present invention includes the following steps:
(1) the natural language processing technology is utilized to extract keywords from case descriptions input by patients, a system-user interaction mode is adopted to perform auxiliary disease judgment, and the distributed processing shortens the waiting time. And (5) the Bert carries out named entity identification to construct a small medical record database.
(2) The region where the sick people are located is labeled geographically by adopting an OpenStreetMap, the disease incidence density is calculated by a clustering model so as to be judged as the clustered infectious disease, the disease data in the province and city range is crawled, and the maximum scale outbreak time and the number of people of the disease are calculated by an SIR infectious disease prediction model so as to prompt people to take epidemic prevention measures in time.
(3) The echarts chart visualizes basic signs and disease signs of a patient, and generates a family genetic disease knowledge map by using neo4j software in the form of entity-relation-attribute triples to give an early warning to genetic diseases.
Construction of web projects
A complete Javaweb project is developed by using an overall three-layer framework of an ssm framework (ssm framework comprises MYBATIS, spring and SPRINGMVC) as a framework base. In the project, mybatis (dao) is used as an underlying framework, and is used for establishing a link with the database and realizing a loud operation on the database, so that support is provided for function calling of a service layer. In the service layer, the invocation of the method of the Dao layer is mainly completed, in the web layer, the layer is also the core layer of the whole javaweb project, the main point interaction logic and the service logic can be represented in the web layer, and the layer frame is the springmvc frame. For this framework, which is mainly completed by various components, it can complete some complex operations like encapsulation of front-end page input data, and under this framework can help encapsulation by default. When the project is exposed, JSP pages are mainly used, and for responding to the event, jQuery and ajax are mainly used for completing event triggering and responding operations.
Linking a python program in Java requires executing the python script file by using runtime. Firstly, a python script is placed in any directory, then the absolute path of the python script is placed in a runtime () method, a function is used for explaining the absolute path of a python running environment, the python script runs in the python environment, then the corresponding python script can be executed by calling, and after the execution is finished, a Java program intercepts an output result from the output stream of the python.
The flow chart of the disease detection method based on deep learning of the invention is shown in fig. 1, and the specific method is as follows:
step 1: collecting a description of a patient's physical condition
After logging in the system, the user inputs own symptoms, and the system extracts disease keywords by using a KEA algorithm. Compared with bert, the KEA algorithm belongs to supervised learning, more keywords are extracted in a specific field, and the keywords are more accurate, so that the KEA algorithm is more suitable for training and predicting data in a specific scene. And matching the disease condition description text with a dictionary to obtain candidate keywords, selecting TF-IDF values of all candidate words by using a naive Bayes algorithm, and training and predicting by using positions and the like as characteristics to obtain disease keywords. The model training process is shown in fig. 2.
The TF-IDF calculation formula is as follows:
naive Bayes formula of calculation is as follows:
step 2: system-user interaction to determine disease
The system feeds the keywords obtained in the step 1 back to a system page for reference of a user, meanwhile, the keywords are compared and searched in a background database, the disease symptoms with the highest comprehensive occurrence rate are fed back to the page to inquire the user, and the system judges the next step by capturing the answer of the user. The realization of the function firstly needs to clean the existing disease data, delete the dirty data by using the pandas library of python, establish a storage process in the database and transfer the data into the database. In the process of comparing and searching the keywords, because the data volume of the database is overlarge, a great deal of time is needed for direct searching, a B-tree index is established for the disease characteristics, and the final query return result contains information such as the name and the characteristics of the disease, the medicine recommendation department, the doctor department and the like. The process realizes the interaction of the user and the system, the inquiry of the system and the mode of the answer of the user can lead the system to more accurately analyze the disease suffered by the user, and simultaneously, the distributed processing mode is adopted, the result feedback is rapid, and the waiting time of the user is reduced.
And step 3: checking disease specific information and similar cases
And crawling hundreds of thousands of pieces of disease information by using a crawler, and storing the cleaned data into a database. Aiming at the diseases predicted by the system and possibly suffered from the diseases, the system calls the disease information in the database, and the user can check the symptoms, causes, recommends medicines, is suitable for eating food and the like by one key. According to survey, 70% of users tend to consult with opinions about people who suffer from the same disease or disease condition for discussion, so that the system collects partial case information, utilizes bert + crf for named entity identification, integrates and normalizes the case information, and stores the case information into a self-contained data table of the system.
The model adopts a traditional IOB labeling mode and marks each character with a label. The CRF model is defined by the formula:
the subscript i indicates the current node (token) location.
The index k indicates that this is the fourth characteristic function and that each characteristic function is attached with a weight λkIn each clique is tokeniM features are constructed, and Z (O) is used for normalization.
After successful modeling, the well-learned CRF model is used for new observation sequence (O)1,O2,O3....Oi) Finding out a most probable hidden state sequence i1,i2...iiThe path solving process adopts a viterbi algorithm, and the written DP transfer formula is as follows:
the user only needs to input the symptom related words or disease names in the query box, and the treatment information of the person with the same symptom or disease can be queried.
And 4, step 4: real-time monitoring of personal infectious disease signs
If the disease predicted by the system is an infectious disease, the physical signs of the user are monitored in real time, the heartbeat and body temperature information is visualized by adopting an echarts real-time line chart developed by a hundred degrees, and the user can check the heartbeat and body temperature information of the user in real time through the charts. Meanwhile, the system tracks the change of physical signs of the user after a period of treatment and visualizes the change in the form of a contrast graph.
And 5: determination of a group's infectious disease
The regional distribution of people suffering from the disease within a period of time is called, and marks are made on a map by using opentreeetmap and leafet. The user can visually see the gathering of the sick people of the disease.
The OpenStreetMap (OSM for short) is an online map cooperation plan, and aims to create a world map which is free in content and can be edited by all people. The map service is free, open-source and editable map service which is created by the public on the internet. The map-related geographic data is improved mainly by the public collective power and the gratuitous contribution. Maps for OSM are intelligently drawn by the user from hand-held GPS devices, aerial photographs, other free content, and even by local alone. As an open source software, the user can download data by himself, and edit and use it.
The leaf is a modern and open source JavaScript library developed for building a mobile device-friendly interactive map, and has most functions of developing an online map by developers. The Leaffet design adheres to the ideas of simplicity, high performance and usability, operates efficiently on all major desktop and mobile platforms, takes advantage of the advantages of HTML5 and CSS3 on modern browsers, and also supports old browser access. Plug-in extensions are supported, with a friendly, easy-to-use API document and a simple, readable source code.
The regional concentration of the affected people can be clearly seen by naked eyes, but the concentration degree is difficult to quantitatively analyze, so that the concentration degree of the affected people is calculated by adopting an OPTICS algorithm.
OPTIC Algorithm core distance expression:
sample(s)
For a given ε and MinPts, the minimum neighborhood radius that makes x the core point is called the core distance of x,
representative set N∈(x) The node in the neighbor of the ith of node x.
The OPTIC algorithm reachable distance expression:
and obtaining population density of the disease through an algorithm, comparing the population density with a threshold value, and judging the disease as a group infectious disease once the density value is higher than the threshold value. The system makes a guard alert.
Step 6: monitoring and prediction of infectious disease focus
And (5) judging the disease to be a group infectious disease by the step 5, crawling the information such as morbidity, mortality, cure rate and the like in the province and city range of the disease from the Weijian committee of the whole country by using a python crawler technology, and displaying the information on a page in real time by using an ajax technology. AJAX has the greatest advantage that data can be exchanged with the server and part of the web page content can be updated without reloading the entire page.
AJAX does not require any browser plug-ins, but requires the user to allow JavaScript to execute on the browser. Meanwhile, the data are fed back to a background, and the background predicts the date of the maximum scale outbreak of the disease and the number of the disease patients by using an SIR algorithm.
The SIR algorithm is specifically as follows:
susceptibility to human change:
infection of human changes:
and (3) recovering human changes:
n: total population of current environment
The number of susceptible people: s (t)
The number of infected persons: i (t)
The number of recovered people: r (T)
Susceptible persons refer to those who are not yet ill but lack immunity and who are susceptible to infection upon contact with an infected person. An infected person refers to a person who has already been infected with a disease and may be transmitted to a susceptible person. A convalescent person refers to a person who dies or has immunity due to illness. The number of persons infected per infected person per unit time is proportional to the number of persons susceptible to infection. The proportionality coefficient β is the infection intensity. In unit time, the number of recovery persons is in direct proportion to the number of infected persons, and the proportionality coefficient gamma is the recovery intensity.
And 7: monitoring and prediction of genetic diseases
If the disease predicted by the system is a genetic disease, the patient's underlying signs are presented in the form of a radar contrast chart. Meanwhile, different physical signs of the patient are monitored again aiming at different diseases, such as the blood sugar, the blood fat, the blood pressure and the blood oxygen content of the patient are monitored. Meanwhile, the system can record the medical condition of the patient within a period of time, such as the first time of expert visit and the like.
The knowledge graph is a mapping map of the knowledge field, and the potential connection effect among entities is obviously mined for expressing the relation among the entities, so that the knowledge graph of the family genetic disease is generated by using the neo4j software in the form of entity-relation-attribute triples according to the attributes and by taking the name of a person as a central node.
While the foregoing is directed to the preferred embodiment of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Claims (3)
1. A disease detection method based on deep learning is characterized by comprising the following steps:
step 1: extracting keywords from case descriptions input by a patient by using a natural language processing technology, and performing auxiliary disease judgment by adopting a system-user interaction mode;
step 2: adopting OpenStreetMap to carry out geographic marking on the region where the sick personnel are located, calculating the disease incidence density by a clustering model so as to judge the disease as the clustered infectious disease, and calculating the maximum scale outbreak time and the number of the sick by crawling the disease data in the province and city range and an SIR infectious disease prediction model;
and step 3: the echarts chart visualizes basic signs and disease signs of a patient, and generates a family genetic disease knowledge map by using neo4j software in the form of entity-relation-attribute triples to give an early warning to genetic diseases.
2. The disease detection method based on deep learning of claim 1, wherein in step S1, a disease symptom vocabulary in a specific medical field is first constructed, and keyword extraction is performed on the disease description inputted by the user by using a KEA algorithm; and finding out phrases in disease description according to the disease symptom word list, using the phrases and other words as candidate keywords together, then selecting TF-IDF values of all the words by using a naive Bayes algorithm, using position information as characteristics, training and predicting to finally obtain disease keyword.
3. The method for disease detection based on deep learning of claim 1, wherein in step S2, the basic signs of the patient are monitored, the regional distribution of the persons with the disease is retrieved over a period of time, the distribution of the persons with the disease is labeled on a map by using an OpenStreetMap, a threshold value of the density of the disease is set, the disease density is calculated by using an OPTICS algorithm, and if the disease density exceeds the threshold value, the disease is determined to be the infectious disease with the aggregation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110983314.8A CN113688205A (en) | 2021-08-25 | 2021-08-25 | Disease detection method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110983314.8A CN113688205A (en) | 2021-08-25 | 2021-08-25 | Disease detection method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113688205A true CN113688205A (en) | 2021-11-23 |
Family
ID=78582608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110983314.8A Pending CN113688205A (en) | 2021-08-25 | 2021-08-25 | Disease detection method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688205A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115831300A (en) * | 2022-09-29 | 2023-03-21 | 广州金域医学检验中心有限公司 | Detection method, device, equipment and medium based on patient information |
| CN117238452B (en) * | 2023-10-08 | 2024-05-17 | 中世康恺科技有限公司 | Regional medical image cloud and inspection result mutual recognition sharing platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182262A (en) * | 2018-01-04 | 2018-06-19 | 华侨大学 | Intelligent Answer System construction method and system based on deep learning and knowledge mapping |
| CN108305690A (en) * | 2018-02-07 | 2018-07-20 | 王博冉 | The nervous system disease point examines the system for distribution of out-patient department of method and the nervous system disease |
| 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 |
| CN111128398A (en) * | 2020-03-30 | 2020-05-08 | 广州地理研究所 | Epidemic disease infected person number estimation method based on population migration big data |
| CN112309581A (en) * | 2020-11-03 | 2021-02-02 | 辽宁工程技术大学 | Private medical intelligent auxiliary method based on machine learning |
-
2021
- 2021-08-25 CN CN202110983314.8A patent/CN113688205A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182262A (en) * | 2018-01-04 | 2018-06-19 | 华侨大学 | Intelligent Answer System construction method and system based on deep learning and knowledge mapping |
| CN108305690A (en) * | 2018-02-07 | 2018-07-20 | 王博冉 | The nervous system disease point examines the system for distribution of out-patient department of method and the nervous system disease |
| 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 |
| CN111128398A (en) * | 2020-03-30 | 2020-05-08 | 广州地理研究所 | Epidemic disease infected person number estimation method based on population migration big data |
| CN112309581A (en) * | 2020-11-03 | 2021-02-02 | 辽宁工程技术大学 | Private medical intelligent auxiliary method based on machine learning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115831300A (en) * | 2022-09-29 | 2023-03-21 | 广州金域医学检验中心有限公司 | Detection method, device, equipment and medium based on patient information |
| CN115831300B (en) * | 2022-09-29 | 2023-12-29 | 广州金域医学检验中心有限公司 | Detection method, device, equipment and medium based on patient information |
| CN117238452B (en) * | 2023-10-08 | 2024-05-17 | 中世康恺科技有限公司 | Regional medical image cloud and inspection result mutual recognition sharing platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Souri et al. | A new machine learning-based healthcare monitoring model for student’s condition diagnosis in Internet of Things environment | |
| Baclic et al. | Artificial intelligence in public health: Challenges and opportunities for public health made possible by advances in natural language processing | |
| CN111916215B (en) | Cluster/chronic disease early automatic alarm, preliminary feature analysis and risk assessment system | |
| CN112863630A (en) | Personalized accurate medical question-answering system based on data and knowledge | |
| CN112368782A (en) | Graphic database for epidemic tracking and management | |
| CN108010573A (en) | A kind of hospital data emerging system, method, electronic equipment and storage medium | |
| US20090259487A1 (en) | Patient Data Mining | |
| JP5977898B1 (en) | BEHAVIOR PREDICTION DEVICE, BEHAVIOR PREDICTION DEVICE CONTROL METHOD, AND BEHAVIOR PREDICTION DEVICE CONTROL PROGRAM | |
| CN109841282A (en) | A kind of Chinese medicine health control cloud system and its building method based on cloud computing | |
| CN110337645A (en) | The processing component that can be adapted to | |
| CN111666477A (en) | Data processing method and device, intelligent equipment and medium | |
| EP4002141A1 (en) | Question recommendation method, apparatus and system, and electronic device and readable storage medium | |
| KR102479692B1 (en) | Big data and cloud system based AI(artificial intelligence) emergency medical care decision-making and emergency patient transfer system and method thereof | |
| Cho et al. | The evolution of social health research topics: A data-driven analysis | |
| CN112420192A (en) | Disease typing method fusing multi-dimensional diagnosis and treatment information and related equipment | |
| JP2018014058A (en) | Medical information processing system, medical information processing device and medical information processing method | |
| CN115116612A (en) | Intelligent risk assessment system and method for child patient state of illness | |
| CN113688205A (en) | Disease detection method based on deep learning | |
| Sani et al. | Review on hypertension diagnosis using expert system and wearable devices | |
| Yang et al. | Predicting falls among community-dwelling older adults: a demonstration of applied machine learning | |
| WO2022141929A1 (en) | Health self-test system, server, and health testing system | |
| Wei et al. | Epidemic Guard: A COVID-19 detection system for elderly people | |
| CN112579790A (en) | Method and device for constructing severe disease knowledge base, storage medium and electronic equipment | |
| Usip et al. | PeNLP parser: an extraction and visualization tool for precise maternal, neonatal and child healthcare geo-locations from unstructured data | |
| Gupta et al. | Inclusive development using connected devices and data analysis |
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 |