CN111489800A - Analysis method and system for identifying and storing medical record and report list images - Google Patents
Analysis method and system for identifying and storing medical record and report list images Download PDFInfo
- Publication number
- CN111489800A CN111489800A CN202010277002.0A CN202010277002A CN111489800A CN 111489800 A CN111489800 A CN 111489800A CN 202010277002 A CN202010277002 A CN 202010277002A CN 111489800 A CN111489800 A CN 111489800A
- Authority
- CN
- China
- Prior art keywords
- medical record
- data
- image
- occurrence probability
- client
- 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.)
- Withdrawn
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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Epidemiology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Multimedia (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a method and a system for identifying and storing medical record and report list images. The method comprises the following steps: 1: uploading medical record image data generated in medical treatment to a client in an image form; 2: the client acquires the uploaded medical record image data and identifies the image data; 3: performing natural language processing according to the identification data to obtain a keyword; 4: carrying out storage structuralization processing on the key words, and storing the key words into a database after identification and classification; 5: establishing a search engine at a server side to provide quick query response; 6: establishing a disease occurrence probability model through machine learning according to data stored in a database, and calculating related disease occurrence probability according to the disease occurrence probability model; 7: the client retrieves historical medical record data, current medical record and examination report pictures according to the patient information, and refers to physical examination suggestions and disease contraindication reminders for individuals. The invention converts the medical record and the image into the character information, thereby facilitating the information processing and storage.
Description
Technical Field
The invention belongs to the field of digital medical treatment, and particularly relates to an analysis system for image recognition and storage of medical records and report sheets, in particular to an intelligent client for personal self-management of medical records and report sheets. The invention is used for classifying and storing the character information converted from different medical records and inspection report images, establishing a search engine, modeling and analyzing and retrieving a database.
Background
The medical records summarize the real disease condition of the patient from before admission to after discharge and the treatment method. The file can thoroughly and objectively record the past medical history, the current state of illness, diagnosis and treatment data and the like of the patient. Nowadays, modern medical treatment is rapidly developed, an informatization system is complete, and a handwritten paper medical record is replaced by a digital medical record which is small in occupied space, environment-friendly, high in consulting efficiency and high in data sharing performance.
A digital medical record is an information medical record management system. The electronic equipment is used for storing, transmitting, arranging, calling and consulting the diagnosis and treatment information of the patient, has the advantages of easiness in storage, large capacity, high sharing speed, complete information and the like, can uniformly process the diagnosis and treatment records and subsequent related operations of the patient, has outstanding contribution to scientific research, clinical work and teaching work, and is a necessary product for the modern medical system to step into informatization. The digital medical record takes information as a carrier, and the shared value and the flowing target are realized. In the era of urgent need for information sharing, the digital medical records are rapidly and widely applied, and the multi-party profit-making and win-win tongs for doctors, patients and doctors are realized.
Disclosure of Invention
The invention aims to provide a method for storing and analyzing medical record images, which has the advantages of high speed, high convenience, systematization and good universality, aiming at the application requirements of digitalization and systematization storage, classification and analysis of medical record and report sheets, and provides an analysis system for identifying and storing the medical record and report sheet images based on the method.
In order to achieve the purpose, the invention adopts the following technical scheme to solve the problem:
an analysis method for identifying and storing medical record and report list images comprises the following steps:
step 1: a user uploads medical record image data generated in medical treatment to a client in an image form; the medical record image data comprises a medical record and an inspection and examination report;
step 2: after acquiring the uploaded medical record image data, the client identifies the image data;
and step 3: performing natural language processing according to the identified data to obtain keywords beneficial to classification;
and 4, step 4: performing storage structuring processing on the acquired keywords, and storing the extracted names, sexes, ages, hospital visits, departments of the visits, dates of the visits and diagnosis results in a database after identifying and classifying;
the storage structuring processing refers to storing the keywords through a table for formulating categories, and does not relate to an algorithm.
And 5: establishing a search engine at a server side to provide quick query response;
step 6: establishing a disease occurrence probability model through machine learning according to data stored in a database, and calculating related disease occurrence probability according to the disease occurrence probability model through a medical history record of a single patient to obtain a physical examination suggestion result and disease contraindication data;
and 7: the client retrieves historical medical record data, current medical record and examination report pictures according to the patient information, and refers to physical examination suggestions and disease contraindication reminders for individuals.
In the method, the mode of acquiring medical record image data is one of the following modes: the image stored in the client and the image collected by the client are transmitted by the common network protocol.
Further, the medical record and examination report in step 1 may be acquired in a manner that includes: handwriting paper, printing paper and electronic non-physical information data.
Further, the data identification of the image in the step 2 is based on TensorFlow and is trained by using an L STM (long and short time memory network) model, basic training data is picture data generated by changing the font, size, blur and stretch of a text by using a Chinese language library (news and Chinese), and extension training data is generated by using handwriting, mechanical typing of a medical record and a report form of a hospital.
The L STM (long and short time memory network) model of the recurrent neural network has the following structure:
l STM has a chain structure, an important structure in L STM model is three gates, the gate structure is used for controlling information flow, a combination of a Sigmoid neural network layer and a pointwise multiplication structure is arranged in the gate structure, Sigmoid is used for controlling the probability value of outputting 0 to 1 for describing how much information proportion passes, 1 represents complete passing, 0 represents complete discarding, pointwise is a subsequent multiplication operation for combining probability into calculation so as to play an information control effect, and another important structure of L STM module is a cell state line, which is similar to S generation in RNN, and a cell also plays a role in storing and memorizing so as to carry out propagation and generation of memory.
Further, the data identified in step 3 is subjected to natural language processing, which specifically includes: and splitting the content of the text in the basic training data and the expanded training data by using jieba word segmentation to obtain keywords, improving the ambiguity correction capability of word segmentation by enumerating dictionaries of hospitals and departments, and simultaneously carrying out primary classification on the keywords.
Further, the database used in step 4 is one of the following types: RDBMS, Nosql, the preferred database type is Nosql.
Further, the search engine middleware related to the step 5 is one of the following categories: elasticissearch, Splunk, Solr, the preferred search engine is Elasticissearch. Particularly, the existing search engine is implanted into the server, so that keyword query can be conveniently carried out on the server.
Further, the disease occurrence probability model is established through machine learning in step 6, and the specific disease occurrence probability model is established as follows:
firstly, preparing training data, and acquiring the training data corresponding to different diseases according to characteristic parameter indexes of the different diseases;
then, a Cox proportional risk model (probabilistic models) is adopted, training and verification are carried out on the Cox proportional risk model through training data, the model is continuously optimized in the training and verification, and a disease occurrence probability model is obtained, so that the increase of the accuracy is realized.
The Cox proportional risk model is a semi-parameter regression model provided by British statisticians D.R.Cox, takes survival outcome and survival time as dependent variables, can simultaneously analyze the influence of a plurality of factors on the survival period, can analyze data with deleted survival time, and does not require to estimate the survival distribution type of the data.
And 7, providing an input box by the client for inputting keywords, sending a request to the server, performing data query on the keywords in the database through the search engine, returning medical record related to the keywords, and displaying the medical record to a query result area in a list form.
The invention has the following beneficial effects:
the invention converts different medical records and inspection report images into text information, and facilitates information processing and storage by the method. And after the characters are classified, storing the characters into a database. Then, a search engine is established by extracting the key words, and quick query response is realized. Then, the related disease occurrence probability is calculated by establishing a model, and a physical examination suggestion result and disease contraindication data are obtained. The client retrieves the medical record data, the medical records and the examination report pictures of the history according to the patient information, and refers to physical examination suggestions and disease contraindication reminders for individuals.
Drawings
FIG. 1 is a flow diagram of an intelligent client and system for personal self-administration of medical records and reports;
FIG. 2 is a block diagram of an intelligent client and system for personal self-administration of medical records and reports;
FIG. 3 is a simplified flow diagram of a data model building block in the present invention;
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings and examples.
The invention belongs to the field of digital medical treatment, and particularly relates to an analysis method and system for identifying and storing medical record and report list images. The invention is used for classifying and storing the character information converted from different medical records and inspection report images, establishing a search engine, modeling and analyzing and retrieving a database.
As shown in fig. 1, a method for analyzing medical record and report image identification and storage includes the following steps:
step 1: a user uploads medical record image data generated in medical treatment to a client in an image form; the medical record image data comprises a medical record and an inspection and examination report;
step 2: after acquiring the uploaded medical record image data, the client identifies the image data;
and step 3: performing natural language processing according to the identified data to obtain keywords beneficial to classification;
and 4, step 4: performing storage structuring processing on the acquired keywords, and storing the extracted names, sexes, ages, hospital visits, departments of the visits, dates of the visits and diagnosis results in a database after identifying and classifying;
the storage structuring processing refers to storing the keywords through a table for formulating categories, and does not relate to an algorithm.
And 5: establishing a search engine at a server side to provide quick query response;
step 6: establishing a disease occurrence probability model through machine learning according to data stored in a database, and calculating related disease occurrence probability according to the disease occurrence probability model through a medical history record of a single patient to obtain a physical examination suggestion result and disease contraindication data;
and 7: the client retrieves historical medical record data, current medical record and examination report pictures according to the patient information, and refers to physical examination suggestions and disease contraindication reminders for individuals.
In the method, the mode of acquiring medical record image data is one of the following modes: the image stored in the client and the image collected by the client are transmitted by the common network protocol.
Further, the medical record and examination report in step 1 may be acquired in a manner that includes: handwriting paper, printing paper and electronic non-physical information data.
Further, the data identification of the image in the step 2 is based on TensorFlow and is trained by using an L STM (long and short time memory network) model, basic training data is picture data generated by changing the font, size, blur and stretch of a text by using a Chinese language library (news and Chinese), and extension training data is generated by using handwriting, mechanical typing of a medical record and a report form of a hospital.
The L STM (long and short time memory network) model of the recurrent neural network has the following structure:
l STM has a chain structure, an important structure in L STM model is three gates, the gate structure is used for controlling information flow, a combination of a Sigmoid neural network layer and a pointwise multiplication structure is arranged in the gate structure, Sigmoid is used for controlling the probability value of outputting 0 to 1 for describing how much information proportion passes, 1 represents complete passing, 0 represents complete discarding, pointwise is a subsequent multiplication operation for combining probability into calculation so as to play an information control effect, and another important structure of L STM module is a cell state line, which is similar to S generation in RNN, and a cell also plays a role in storing and memorizing so as to carry out propagation and generation of memory.
Further, the data identified in step 3 is subjected to natural language processing, which specifically includes: and splitting the content of the text in the basic training data and the expanded training data by using jieba word segmentation to obtain keywords, improving the ambiguity correction capability of word segmentation by enumerating dictionaries of hospitals and departments, and simultaneously carrying out primary classification on the keywords.
Further, the database used in step 4 is one of the following types: RDBMS, Nosql, the preferred database type is Nosql.
Further, the search engine middleware related to the step 5 is one of the following categories: elasticissearch, Splunk, Solr, the preferred search engine is Elasticissearch. Particularly, the existing search engine is implanted into the server, so that keyword query can be conveniently carried out on the server.
Further, the disease occurrence probability model is established through machine learning in step 6, and the specific disease occurrence probability model is established as follows:
firstly, preparing training data, and acquiring the training data corresponding to different diseases according to characteristic parameter indexes of the different diseases;
then, a Cox proportional risk model (probabilistic models) is adopted, training and verification are carried out on the Cox proportional risk model through training data, the model is continuously optimized in the training and verification, and a disease occurrence probability model is obtained, so that the increase of the accuracy is realized.
The Cox proportional risk model is a semi-parameter regression model provided by British statisticians D.R.Cox, takes survival outcome and survival time as dependent variables, can simultaneously analyze the influence of a plurality of factors on the survival period, can analyze data with deleted survival time, and does not require to estimate the survival distribution type of the data.
And 7, providing an input box by the client for inputting keywords, sending a request to the server, performing data query on the keywords in the database through the search engine, returning medical record related to the keywords, and displaying the medical record to a query result area in a list form.
As shown in fig. 3, an implementation system of an analysis method for identifying and storing images of medical records and report sheets includes a data acquisition module, an image identification module, an image-text conversion module, a text directory management module, a keyword search module, and a big data analysis module.
The data acquisition module: the medical record and the inspection report generated by the patient hospitalizing are collected; the image identification module: the system is used for identifying the uploaded medical record picture data and image data; the image-text conversion module: the system is responsible for carrying out natural language processing on the data after image conversion to obtain keywords beneficial to classification; the character directory management module: the database is used for storing and structuring the acquired keywords, and storing the extracted names, sexes, ages, treatment hospitals, treatment departments, treatment dates and diagnosis results in a database after identifying and classifying; the keyword searching module: the method is used for establishing a search engine at a server side and providing quick query response; the data model building module is used for: the system is used for establishing a disease occurrence probability model through machine learning according to data stored in a database, calculating related disease occurrence probability according to the disease occurrence probability model through a medical history record of a single patient, and obtaining a physical examination suggestion result and disease contraindication data; the big data analysis module: the system is used for the client to search the medical record data, the medical records and the examination report pictures of the previous times according to the patient information and to look up the physical examination suggestions and the disease contraindication reminders of individuals.
As shown in fig. 2, the modeling process of the disease occurrence probability model in the system is simply described as: feature preparation-Cox regression-model validation-model optimization. Aiming at various common disease types, machine learning models are established according to characteristic parameter indexes of different diseases. The data of the patient is judged through machine learning, the preliminary prediction of the disease is obtained, and the system sends a physical examination prompt to the corresponding user.
The above-described embodiments are merely preferred embodiments of the present invention, which should not be construed as limiting the invention. Various changes and modifications may be made by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present invention. Therefore, the technical scheme obtained by adopting the mode of equivalent replacement or equivalent transformation is within the protection scope of the invention.
Claims (8)
1. An analysis method for identifying and storing medical record and report list images is characterized by comprising the following steps:
step 1: a user uploads medical record image data generated in medical treatment to a client in an image form; the medical record image data comprises a medical record and an inspection and examination report;
step 2: after acquiring the uploaded medical record image data, the client identifies the image data;
and step 3: performing natural language processing according to the identified data to obtain keywords beneficial to classification;
and 4, step 4: performing storage structuring processing on the acquired keywords, and storing the extracted names, sexes, ages, hospital visits, departments of the visits, dates of the visits and diagnosis results in a database after identifying and classifying;
and 5: establishing a search engine at a server side to provide quick query response;
step 6: establishing a disease occurrence probability model through machine learning according to data stored in a database, and calculating related disease occurrence probability according to the disease occurrence probability model through a medical history record of a single patient to obtain a physical examination suggestion result and disease contraindication data;
and 7: the client retrieves historical medical record data, current medical record and examination report pictures according to the patient information, and refers to physical examination suggestions and disease contraindication reminders for individuals, specifically: the client provides an input box for inputting keywords, sends a request to the server, performs data query on the keywords in the database through the search engine, returns medical record records related to the keywords, and displays the medical record records in a list form in a query result area.
2. The method of claim 1, wherein the medical record image data is obtained by one of: the image stored in the client and the image collected by the client are transmitted by the common network protocol.
3. The method as claimed in claim 2, wherein the method for acquiring medical record and report form image in step 1 comprises: handwriting paper, printing paper and electronic non-physical information data.
4. The method for image recognition and storage analysis of medical records and report sheets according to claim 3, wherein the image data recognition in step 2 is based on TensorFlow and trained by using L STM model, the basic training data is image data generated by changing font, size, blur and stretch of text by using a Chinese language library, and the extension training data is image data generated by handwriting, mechanical typing of medical records and report sheets by using hospitals.
5. The method for analyzing medical record and report image recognition and storage according to claim 3 or 4, wherein the data recognized in step 3 is processed by natural language, specifically as follows: and splitting the content of the text in the basic training data and the expanded training data by using jieba word segmentation to obtain keywords, improving the ambiguity correction capability of word segmentation by enumerating dictionaries of hospitals and departments, and simultaneously carrying out primary classification on the keywords.
6. The method of claim 5, wherein the database used in step 4 is one of the following types: RDBMS, Nosql, the preferred database type is Nosql.
7. The method of claim 6, wherein the step 5 involves search engine middleware in one of the following categories: the method comprises the following steps of Elasticissearch, Splunk and Solr, wherein the preferred search engine is Elasticissearch, and particularly, the existing search engine is implanted into a server, so that keyword query is conveniently carried out on the server.
8. The method according to claim 7, wherein the disease occurrence probability model is created by machine learning in step 6, and the specific disease occurrence probability model is created as follows:
firstly, preparing training data, and acquiring the training data corresponding to different diseases according to characteristic parameter indexes of the different diseases;
then, the Cox proportional risk model is adopted, training and verification are carried out on the Cox proportional risk model through training data, the model is continuously optimized in the training and verification, and a disease occurrence probability model is obtained, so that the increase of the accuracy rate is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010277002.0A CN111489800A (en) | 2020-04-10 | 2020-04-10 | Analysis method and system for identifying and storing medical record and report list images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010277002.0A CN111489800A (en) | 2020-04-10 | 2020-04-10 | Analysis method and system for identifying and storing medical record and report list images |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111489800A true CN111489800A (en) | 2020-08-04 |
Family
ID=71797854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010277002.0A Withdrawn CN111489800A (en) | 2020-04-10 | 2020-04-10 | Analysis method and system for identifying and storing medical record and report list images |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111489800A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111899837A (en) * | 2020-08-17 | 2020-11-06 | 江苏达实久信数字医疗科技有限公司 | Operation report coordination method and system based on digital operating room |
CN111986814A (en) * | 2020-08-21 | 2020-11-24 | 南通大学 | Modeling method of lupus nephritis prediction model of lupus erythematosus patient |
CN112185520A (en) * | 2020-09-27 | 2021-01-05 | 志诺维思(北京)基因科技有限公司 | Text structured processing system and method for medical pathology report picture |
CN112331284A (en) * | 2020-10-27 | 2021-02-05 | 复旦大学附属儿科医院 | Admission medical history auxiliary acquisition system for hereditary metabolic disease |
CN112528009A (en) * | 2020-12-07 | 2021-03-19 | 北京健康有益科技有限公司 | Method, device and computer readable medium for generating user chronic disease conditioning scheme |
CN112582045A (en) * | 2020-12-22 | 2021-03-30 | 无锡慧方科技有限公司 | Electronic medical report sheet transmission system |
CN113569140A (en) * | 2021-07-13 | 2021-10-29 | 深圳Tcl新技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
CN113611380A (en) * | 2021-07-09 | 2021-11-05 | 喀什地区第一人民医院 | Data selection method for diagnostic prediction |
CN113724840A (en) * | 2021-08-12 | 2021-11-30 | 浙江卡易智慧医疗科技有限公司 | Design method and system based on medical image structured report |
CN116450727A (en) * | 2023-06-19 | 2023-07-18 | 中国人民解放军联勤保障部队第九八〇医院 | Medical data processing method, medical data processing device, terminal equipment and readable storage medium |
CN116628125A (en) * | 2023-04-14 | 2023-08-22 | 湘南学院 | Method and auxiliary device for extracting keywords of clinical image diagnosis report |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109659033A (en) * | 2018-12-18 | 2019-04-19 | 浙江大学 | A kind of chronic disease change of illness state event prediction device based on Recognition with Recurrent Neural Network |
CN109872784A (en) * | 2019-01-14 | 2019-06-11 | 平安科技(深圳)有限公司 | Intelligent case history generation method, device, computer equipment and storage medium |
CN109924965A (en) * | 2018-10-12 | 2019-06-25 | 王平 | A kind of cardiovascular and cerebrovascular rehabilitation training system |
CN110502607A (en) * | 2019-06-26 | 2019-11-26 | 中电万维信息技术有限责任公司 | A kind of electronic medical record system, the method and server for inquiring electronic health record |
CN110534206A (en) * | 2019-08-26 | 2019-12-03 | 北京好医生云医院管理技术有限公司 | A kind of working method of medical diagnosis auxiliary system |
-
2020
- 2020-04-10 CN CN202010277002.0A patent/CN111489800A/en not_active Withdrawn
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109924965A (en) * | 2018-10-12 | 2019-06-25 | 王平 | A kind of cardiovascular and cerebrovascular rehabilitation training system |
CN109659033A (en) * | 2018-12-18 | 2019-04-19 | 浙江大学 | A kind of chronic disease change of illness state event prediction device based on Recognition with Recurrent Neural Network |
CN109872784A (en) * | 2019-01-14 | 2019-06-11 | 平安科技(深圳)有限公司 | Intelligent case history generation method, device, computer equipment and storage medium |
CN110502607A (en) * | 2019-06-26 | 2019-11-26 | 中电万维信息技术有限责任公司 | A kind of electronic medical record system, the method and server for inquiring electronic health record |
CN110534206A (en) * | 2019-08-26 | 2019-12-03 | 北京好医生云医院管理技术有限公司 | A kind of working method of medical diagnosis auxiliary system |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111899837A (en) * | 2020-08-17 | 2020-11-06 | 江苏达实久信数字医疗科技有限公司 | Operation report coordination method and system based on digital operating room |
CN111986814B (en) * | 2020-08-21 | 2024-01-16 | 南通大学 | Modeling method of lupus nephritis prediction model of lupus erythematosus patient |
CN111986814A (en) * | 2020-08-21 | 2020-11-24 | 南通大学 | Modeling method of lupus nephritis prediction model of lupus erythematosus patient |
CN112185520A (en) * | 2020-09-27 | 2021-01-05 | 志诺维思(北京)基因科技有限公司 | Text structured processing system and method for medical pathology report picture |
CN112185520B (en) * | 2020-09-27 | 2024-06-07 | 志诺维思(北京)基因科技有限公司 | Text structuring processing system and method for medical pathology report picture |
CN112331284A (en) * | 2020-10-27 | 2021-02-05 | 复旦大学附属儿科医院 | Admission medical history auxiliary acquisition system for hereditary metabolic disease |
CN112528009A (en) * | 2020-12-07 | 2021-03-19 | 北京健康有益科技有限公司 | Method, device and computer readable medium for generating user chronic disease conditioning scheme |
CN112582045A (en) * | 2020-12-22 | 2021-03-30 | 无锡慧方科技有限公司 | Electronic medical report sheet transmission system |
CN113611380A (en) * | 2021-07-09 | 2021-11-05 | 喀什地区第一人民医院 | Data selection method for diagnostic prediction |
CN113569140A (en) * | 2021-07-13 | 2021-10-29 | 深圳Tcl新技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
CN113724840A (en) * | 2021-08-12 | 2021-11-30 | 浙江卡易智慧医疗科技有限公司 | Design method and system based on medical image structured report |
CN116628125A (en) * | 2023-04-14 | 2023-08-22 | 湘南学院 | Method and auxiliary device for extracting keywords of clinical image diagnosis report |
CN116628125B (en) * | 2023-04-14 | 2024-01-30 | 湘南学院 | Method and auxiliary device for extracting keywords of clinical image diagnosis report |
CN116450727B (en) * | 2023-06-19 | 2023-08-18 | 中国人民解放军联勤保障部队第九八〇医院 | Medical data processing method, medical data processing device, terminal equipment and readable storage medium |
CN116450727A (en) * | 2023-06-19 | 2023-07-18 | 中国人民解放军联勤保障部队第九八〇医院 | Medical data processing method, medical data processing device, terminal equipment and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111489800A (en) | Analysis method and system for identifying and storing medical record and report list images | |
CN110364234B (en) | Intelligent storage, analysis and retrieval system and method for electronic medical records | |
CN105139237A (en) | Information push method and apparatus | |
JPH07295989A (en) | Device that forms interpreter to analyze data | |
WO2020010834A1 (en) | Faq question and answer library generalization method, apparatus, and device | |
WO2021139343A1 (en) | Data analysis method and apparatus based on natural language processing, and computer device | |
CN111222340A (en) | Breast electronic medical record entity recognition system based on multi-standard active learning | |
CN113688248B (en) | Medical event identification method and system under condition of small sample weak labeling | |
CN112349369A (en) | Medical image big data intelligent analysis method, system and storage medium | |
CN113032552B (en) | Text abstract-based policy key point extraction method and system | |
CN113707307A (en) | Disease analysis method and device, electronic equipment and storage medium | |
CN113569023A (en) | Chinese medicine question-answering system and method based on knowledge graph | |
US20220292085A1 (en) | Systems and methods for advanced query generation | |
CN113409907A (en) | Intelligent pre-inquiry method and system based on Internet hospital | |
EP3994589A1 (en) | System, apparatus and method of managing knowledge generated from technical data | |
Pendyala et al. | Automated medical diagnosis from clinical data | |
CN113111159A (en) | Question and answer record generation method and device, electronic equipment and storage medium | |
CN114358001A (en) | Method for standardizing diagnosis result, and related device, equipment and storage medium thereof | |
CN112837772A (en) | Pre-inquiry case history generation method and device | |
CN115171871A (en) | Cardiovascular disease prediction method based on knowledge graph and attention mechanism | |
CN116501779A (en) | Big data mining analysis system for real-time feedback | |
WO2022171093A1 (en) | Method and apparatus for constructing personnel relational graph, and electronic device | |
CN111597330A (en) | Intelligent expert recommendation-oriented user image drawing method based on support vector machine | |
JP2017167738A (en) | Diagnostic processing device, diagnostic processing system, server, diagnostic processing method, and program | |
CN113343680A (en) | Structured information extraction method based on multi-type case history texts |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200804 |