CN110600123A - Clinical auxiliary diagnosis method for traditional Chinese medicine - Google Patents
Clinical auxiliary diagnosis method for traditional Chinese medicine Download PDFInfo
- Publication number
- CN110600123A CN110600123A CN201910805443.0A CN201910805443A CN110600123A CN 110600123 A CN110600123 A CN 110600123A CN 201910805443 A CN201910805443 A CN 201910805443A CN 110600123 A CN110600123 A CN 110600123A
- Authority
- CN
- China
- Prior art keywords
- chinese medicine
- data
- traditional chinese
- inquiry
- clinical
- 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
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
- 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
Abstract
The invention discloses a traditional Chinese medicine clinical auxiliary diagnosis method, and particularly relates to the field of traditional Chinese medicine clinical diagnosis, wherein the auxiliary diagnosis method comprises the following steps: s1, collecting Chinese medicine clinical inquiry data on the internet and in each traditional Chinese medicine department to obtain various symptoms and inquiry records in the Chinese medicine clinical records, and then arranging the inquiry records and the corresponding symptoms into text data to be classified and stored in a Chinese medicine clinical auxiliary diagnosis system; s2, representing the sorted Chinese medicine inquiry text data into a numerical data form which can be calculated by a computer through a data representation method; and S3, calculating the characterized data form through a multilayer perceptron model to judge the disease condition corresponding to the Chinese medicine inquiry data. The invention converts text data into numerical data through a data representation method, finally inputs the numerical data into a multilayer perceptron model, and can realize the assistance of traditional Chinese medicine medical personnel through multi-label classification task search, and particularly, the traditional Chinese medicine medical diagnosis is carried out under the condition of insufficient experience or rare medical resources.
Description
Technical Field
The invention relates to the technical field of traditional Chinese medicine clinical diagnosis, in particular to a traditional Chinese medicine clinical auxiliary diagnosis method.
Background
At present, Chinese traditional medicine clinical diagnosis greatly depends on theoretical knowledge storage and clinical experience mastered by doctors, and is greatly limited by the medical level of doctors, but Chinese medical development is unbalanced, which causes hospitals with insufficient medical experts, and the misdiagnosis rate of difficult and complicated diseases is much higher than that of central hospitals. Once misdiagnosis occurs, diagnosis and treatment cost of a patient is wasted, great pain is brought to the psychology and physiology of the patient, the optimal treatment time is delayed, the condition of the patient is worsened, and finally great damage is brought to the patient. In order to obtain relatively accurate diagnosis results, researchers have paid more and more attention to clinical auxiliary diagnosis of traditional Chinese medicine.
In recent years, due to the popularity of deep learning, the traditional Chinese medicine clinical auxiliary diagnosis research based on the deep neural network is also gradually developed, but most methods are improvement on the network structure, and no relevant report is found on the research on the data characterization method. The data characterization refers to a numerical value characterization processing on an original data form, and because a neural network model cannot directly calculate data in a form such as a character string or a plain text and needs to convert the original form of the data into a numerical value to be brought into model calculation, the data characterization is a basis for deep learning. The clinical auxiliary diagnosis of traditional Chinese medicine is based on the research of clinical record data of traditional Chinese medicine, wherein the clinical record of traditional Chinese medicine belongs to the form of short text data, so the data representation research of the clinical record of traditional Chinese medicine becomes the basis of the clinical auxiliary diagnosis research of traditional Chinese medicine based on the deep neural network.
The unbalanced development of medical resources makes the research of the clinical auxiliary diagnosis of traditional Chinese medicine more important in the areas with relatively deficient medical resources. In recent years, the traditional Chinese medicine clinical auxiliary diagnosis method based on deep learning is more researched. Data characterization is one of the most important factors to obtain better results. Therefore, different data representation forms of multi-class and multi-label TCM clinical auxiliary diagnosis tasks based on a multi-layer perceptron model are researched, and the traditional Chinese medicine medical staff are assisted by the data representation forms, and particularly, the traditional Chinese medicine medical diagnosis is carried out under the condition of insufficient experience or rare medical resources.
Disclosure of Invention
In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method for clinical auxiliary diagnosis of traditional Chinese medicine, in which a data characterization method is used to represent sorted text data for traditional Chinese medicine interrogation to a numerical data format that can be calculated by a computer, and then the characterized data format is used to calculate and judge the disease condition corresponding to the data for traditional Chinese medicine interrogation by using a multi-layer sensor model.
In order to achieve the purpose, the invention provides the following technical scheme: a clinical auxiliary diagnosis method of traditional Chinese medicine comprises the following specific auxiliary diagnosis methods:
s1, collecting Chinese medicine clinical inquiry data on the internet and in each traditional Chinese medicine department to obtain various symptoms and inquiry records in the Chinese medicine clinical records, and then arranging the inquiry records and the corresponding symptoms into text data to be classified and stored in a Chinese medicine clinical auxiliary diagnosis system;
s2, representing the sorted Chinese medicine inquiry text data into a computer-computable numerical data form by a data representation method, which specifically comprises the following steps:
s2.1, segmenting Chinese medicine inquiry text data into words, and calculating by a data representation method to obtain word vectors;
s2.2, words in the Chinese medicine inquiry data are replaced by word vectors, one word is represented by a vector with a fixed size, and a new vector is formed by one text, wherein the number of the words in the text is 30, the word vector size is 300, and the new vector size is 30 x 300;
s3, calculating and judging the disease condition corresponding to the Chinese medicine inquiry data through a multilayer perceptron model according to the characterized data form, and specifically comprising the following steps:
s3.1, firstly, regarding the symptoms in the clinical record of the traditional Chinese medicine as natural labels, and regarding the clinical auxiliary diagnosis of the traditional Chinese medicine as a multi-label classification task according to different clinical symptoms;
and S3.2, when traditional Chinese medicine inquiry is carried out in the traditional Chinese medicine clinical auxiliary diagnosis system, inputting the data vector of the new disease condition after data representation processing into the multilayer sensor model, carrying out data vector calculation, searching through a multi-label classification task, accessing a database in the traditional Chinese medicine clinical auxiliary diagnosis system by the multilayer sensor model, inquiring data, and finally searching out related disease condition and inquiry records to realize traditional Chinese medicine disease condition inquiry.
In a preferred embodiment, in the step S1, each disease and its corresponding solution are stored in the background database of the auxiliary diagnosis model, and the administrator terminal can edit and input a new disease and its solution.
In a preferred embodiment, in step S1, the data of traditional Chinese medicine clinical inquiry may further include a solution corresponding to each disease condition.
In a preferred embodiment, the data characterization method in step S2 is specifically a vector space characterization and distributed characterization method.
In a preferred embodiment, the data vectors stored in the background database of the TCM assisted clinical diagnosis system serve as data support for the multi-label classification task.
In a preferred embodiment, in step S3, each disease label corresponds to a data vector, and after the multi-label classification task search is performed, the type, the inquiry record and the solution of the corresponding disease are displayed in the form of a subdirectory.
The invention has the technical effects and advantages that:
1. the method comprises the steps of representing sorted Chinese medicine inquiry text data into a numerical data form which can be calculated by a computer through a data representation method, calculating and judging the disease condition corresponding to the Chinese medicine inquiry data through a multilayer sensor model in the represented data form, searching disease keywords in a disease auxiliary diagnosis system, converting the text data into numerical data through the data representation method, inputting the numerical data into the multilayer sensor model, and searching through a multi-label classification task to obtain subdirectories corresponding to the disease condition, namely the type of the disease condition, the inquiry record and a solution, so that the method can assist Chinese medicine medical personnel to perform Chinese medicine medical diagnosis especially under the condition of insufficient experience or rare medical resources;
2. in the invention, each disease, inquiry record and corresponding solution are stored in the background database of the auxiliary diagnosis model, new disease, inquiry record and solution can be edited and input through the administrator terminal, and old inaccurate disease solution can be adjusted, so that the diagnosis accuracy can be improved under the condition of insufficient doctor experience or rare medical resources, and the smooth diagnosis of traditional Chinese medicine is ensured.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
the invention provides a clinical auxiliary diagnosis method of traditional Chinese medicine, which comprises the following specific steps:
s1, firstly, traditional Chinese medicine clinical inquiry data are collected on line and in each traditional Chinese medicine department to obtain various symptoms and inquiry records in the traditional Chinese medicine clinical records, then the inquiry records and the corresponding symptoms are arranged into text data to be classified and stored in the traditional Chinese medicine clinical auxiliary diagnosis system, and data vectors stored in a background database of the traditional Chinese medicine clinical auxiliary diagnosis system are used as data support of a multi-label classification task;
s2, representing the sorted Chinese medicine inquiry text data into a computer-computable numerical data form by a data representation method, wherein the data representation method specifically comprises a vector space representation method and a distributed representation method, and specifically comprises the following steps:
s2.1, segmenting Chinese medicine inquiry text data into words, and calculating by a data representation method to obtain word vectors;
s2.2, words in the Chinese medicine inquiry data are replaced by word vectors, one word is represented by a vector with a fixed size, and a new vector is formed by one text, wherein the number of the words in the text is 30, the word vector size is 300, and the new vector size is 30 x 300;
s3, calculating and judging the disease condition corresponding to the Chinese medicine inquiry data through a multilayer perceptron model according to the characterized data form, and specifically comprising the following steps:
s3.1, firstly, regarding the symptoms in the clinical record of the traditional Chinese medicine as natural labels, and regarding the clinical auxiliary diagnosis of the traditional Chinese medicine as a multi-label classification task according to different clinical symptoms, which is shown in a table 1;
s3.2, when traditional Chinese medicine inquiry is carried out in the traditional Chinese medicine clinical auxiliary diagnosis system, inputting the data vector of the new disease condition after data representation processing into a multilayer sensor model, carrying out data vector calculation, searching through a multi-label classification task, accessing a database in the traditional Chinese medicine clinical auxiliary diagnosis system by the multilayer sensor model, inquiring data, and finally searching out related disease conditions and inquiry records to realize traditional Chinese medicine disease inquiry;
TABLE 1 Chinese medicine interrogation data
Each disease label corresponds to one data vector, and after multi-label classification task searching is carried out, the corresponding disease solution is displayed in a subdirectory mode.
The disease keywords are searched in the disease auxiliary diagnosis system, at the moment, text data are converted into numerical data through a data representation method, and finally the numerical data are input into a multilayer perceptron model and are searched through a multi-label classification task to obtain subdirectories corresponding to diseases, namely the types of the diseases and the inquiry records, so that the traditional Chinese medicine medical personnel can be assisted, and especially under the condition of insufficient experience or rare medical resources, the traditional Chinese medicine medical diagnosis can be carried out.
Example 2:
the traditional Chinese medicine clinical inquiry data can also comprise a solution corresponding to each disease;
each disease, inquiry record and corresponding solution are stored in a background database of the auxiliary diagnosis model, new disease, inquiry record and solution can be edited and input through the administrator terminal, and old inaccurate disease solution can be adjusted;
therefore, under the condition that the experience of a doctor is insufficient or medical resources are rare, the diagnosis accuracy is improved, and the smoothness of traditional Chinese medicine diagnosis is ensured.
And finally: the above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that are within the spirit and principle of the present invention are intended to be included in the scope of the present invention.
Claims (6)
1. A clinical auxiliary diagnosis method of traditional Chinese medicine is characterized in that the specific auxiliary diagnosis method is as follows:
s1, collecting Chinese medicine clinical inquiry data on the internet and in each traditional Chinese medicine department to obtain various symptoms and inquiry records in the Chinese medicine clinical records, and then arranging the inquiry records and the corresponding symptoms into text data to be classified and stored in a Chinese medicine clinical auxiliary diagnosis system;
s2, representing the sorted Chinese medicine inquiry text data into a computer-computable numerical data form by a data representation method, which specifically comprises the following steps:
s2.1, segmenting Chinese medicine inquiry text data into words, and calculating by a data representation method to obtain word vectors;
s2.2, replacing vocabularies in the traditional Chinese medicine inquiry data by word vectors, wherein one vocabulary is represented by a vector with a fixed size, and one text forms a new vector;
s3, calculating and judging the disease condition corresponding to the Chinese medicine inquiry data through a multilayer perceptron model according to the characterized data form, and specifically comprising the following steps:
s3.1, firstly, regarding the symptoms in the clinical record of the traditional Chinese medicine as natural labels, and regarding the clinical auxiliary diagnosis of the traditional Chinese medicine as a multi-label classification task according to different clinical symptoms;
and S3.2, when traditional Chinese medicine inquiry is carried out in the traditional Chinese medicine clinical auxiliary diagnosis system, inputting the data vector of the new disease condition after data representation processing into the multilayer sensor model, carrying out data vector calculation, searching through a multi-label classification task, accessing a database in the traditional Chinese medicine clinical auxiliary diagnosis system by the multilayer sensor model, inquiring data, and finally searching out related disease condition and inquiry records to realize traditional Chinese medicine disease condition inquiry.
2. The clinical auxiliary diagnosis method of traditional Chinese medicine according to claim 1, wherein: in step S1, each disease and its corresponding solution are stored in the background database of the auxiliary diagnosis model, and the administrator terminal can edit and input new disease and its inquiry records.
3. The clinical auxiliary diagnosis method of traditional Chinese medicine according to claim 1, wherein: in step S1, the data of the traditional Chinese medicine clinical inquiry may further include a solution corresponding to each disease condition.
4. The clinical auxiliary diagnosis method of traditional Chinese medicine according to claim 1, wherein: the data characterization method in step S2 is specifically a vector space characterization method and a distributed characterization method.
5. The clinical auxiliary diagnosis method of traditional Chinese medicine according to claim 1, wherein: the data vectors stored in the background database of the traditional Chinese medicine clinical auxiliary diagnosis system are used as data support of a multi-label classification task.
6. The clinical auxiliary diagnosis method of traditional Chinese medicine according to claim 3, wherein: in step S3, each disease label corresponds to a data vector, and after multi-label classification task search is performed, the type of the corresponding disease, the inquiry records, and the solution are displayed in the form of a subdirectory.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910805443.0A CN110600123A (en) | 2019-08-29 | 2019-08-29 | Clinical auxiliary diagnosis method for traditional Chinese medicine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910805443.0A CN110600123A (en) | 2019-08-29 | 2019-08-29 | Clinical auxiliary diagnosis method for traditional Chinese medicine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110600123A true CN110600123A (en) | 2019-12-20 |
Family
ID=68856137
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910805443.0A Pending CN110600123A (en) | 2019-08-29 | 2019-08-29 | Clinical auxiliary diagnosis method for traditional Chinese medicine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110600123A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111445995A (en) * | 2020-03-30 | 2020-07-24 | 崔书克 | Artificial intelligence auxiliary diagnosis method and system based on traditional Chinese medicine big data analysis |
CN111986782A (en) * | 2020-07-15 | 2020-11-24 | 中国中医科学院中医药信息研究所 | Integrated multi-platform traditional Chinese medicine diagnosis and treatment system |
CN112002409A (en) * | 2020-07-27 | 2020-11-27 | 山东师范大学 | Traditional Chinese medicine auxiliary diagnosis system |
CN112837810A (en) * | 2021-03-03 | 2021-05-25 | 湖南中医药大学 | Informatization comprehensive processing method for special medical treatment of traditional Chinese medicine |
CN115631852A (en) * | 2022-11-02 | 2023-01-20 | 北京大学重庆大数据研究院 | Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium |
CN116825304A (en) * | 2023-06-25 | 2023-09-29 | 湖南大学 | Online medical method and system based on deep interconnection |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105740612A (en) * | 2016-01-27 | 2016-07-06 | 北京国医精诚科技有限公司 | Traditional Chinese medicine clinical medical record based disease diagnose and treatment method and system |
CN107368547A (en) * | 2017-06-28 | 2017-11-21 | 西安交通大学 | A kind of intelligent medical automatic question-answering method based on deep learning |
CN109460473A (en) * | 2018-11-21 | 2019-03-12 | 中南大学 | The electronic health record multi-tag classification method with character representation is extracted based on symptom |
CN109947901A (en) * | 2019-02-20 | 2019-06-28 | 杭州师范大学 | Prescription Effect prediction technique based on multi-layer perception (MLP) and natural language processing technique |
-
2019
- 2019-08-29 CN CN201910805443.0A patent/CN110600123A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105740612A (en) * | 2016-01-27 | 2016-07-06 | 北京国医精诚科技有限公司 | Traditional Chinese medicine clinical medical record based disease diagnose and treatment method and system |
CN107368547A (en) * | 2017-06-28 | 2017-11-21 | 西安交通大学 | A kind of intelligent medical automatic question-answering method based on deep learning |
CN109460473A (en) * | 2018-11-21 | 2019-03-12 | 中南大学 | The electronic health record multi-tag classification method with character representation is extracted based on symptom |
CN109947901A (en) * | 2019-02-20 | 2019-06-28 | 杭州师范大学 | Prescription Effect prediction technique based on multi-layer perception (MLP) and natural language processing technique |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111445995A (en) * | 2020-03-30 | 2020-07-24 | 崔书克 | Artificial intelligence auxiliary diagnosis method and system based on traditional Chinese medicine big data analysis |
CN111986782A (en) * | 2020-07-15 | 2020-11-24 | 中国中医科学院中医药信息研究所 | Integrated multi-platform traditional Chinese medicine diagnosis and treatment system |
CN112002409A (en) * | 2020-07-27 | 2020-11-27 | 山东师范大学 | Traditional Chinese medicine auxiliary diagnosis system |
CN112837810A (en) * | 2021-03-03 | 2021-05-25 | 湖南中医药大学 | Informatization comprehensive processing method for special medical treatment of traditional Chinese medicine |
CN115631852A (en) * | 2022-11-02 | 2023-01-20 | 北京大学重庆大数据研究院 | Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium |
CN115631852B (en) * | 2022-11-02 | 2024-04-09 | 北京大学重庆大数据研究院 | Certificate type recommendation method and device, electronic equipment and nonvolatile storage medium |
CN116825304A (en) * | 2023-06-25 | 2023-09-29 | 湖南大学 | Online medical method and system based on deep interconnection |
CN116825304B (en) * | 2023-06-25 | 2024-02-23 | 湖南大学 | Online medical method and system based on deep interconnection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110600123A (en) | Clinical auxiliary diagnosis method for traditional Chinese medicine | |
CN110222201B (en) | Method and device for constructing special disease knowledge graph | |
CN107731269B (en) | Disease coding method and system based on original diagnosis data and medical record file data | |
CN107705839B (en) | Disease automatic coding method and system | |
CN108182262A (en) | Intelligent Answer System construction method and system based on deep learning and knowledge mapping | |
CN110990590A (en) | Dynamic financial knowledge map construction method based on reinforcement learning and transfer learning | |
CN107993724A (en) | A kind of method and device of medicine intelligent answer data processing | |
CN107368547A (en) | A kind of intelligent medical automatic question-answering method based on deep learning | |
CN112542223A (en) | Semi-supervised learning method for constructing medical knowledge graph from Chinese electronic medical record | |
CN106776711A (en) | A kind of Chinese medical knowledge mapping construction method based on deep learning | |
CN111949759A (en) | Method and system for retrieving medical record text similarity and computer equipment | |
CN113505243A (en) | Intelligent question-answering method and device based on medical knowledge graph | |
CN112614565A (en) | Traditional Chinese medicine classic famous prescription intelligent recommendation method based on knowledge-graph technology | |
CN106934069A (en) | Data retrieval method and system | |
CN108121739A (en) | Method of data capture and data gathering system | |
CN113254609B (en) | Question-answering model integration method based on negative sample diversity | |
CN109841285B (en) | Clinical research collaboration system and method | |
CN113435200A (en) | Entity recognition model training and electronic medical record processing method, system and equipment | |
CN111062193B (en) | Medical data labeling method and device, storage medium and electronic equipment | |
CN111178047A (en) | Ancient medical record prescription extraction method based on hierarchical sequence labeling | |
CN116719840A (en) | Medical information pushing method based on post-medical-record structured processing | |
CN116227594A (en) | Construction method of high-credibility knowledge graph of medical industry facing multi-source data | |
CN105956362B (en) | A kind of believable case history structural method and system | |
Qin | Research on the application of intelligent speech recognition technology in medical big data fog computing system | |
CN114372143A (en) | Hierarchical prediction method and system for electronic medical record and computer equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191220 |
|
RJ01 | Rejection of invention patent application after publication |