CN110115563A - A kind of TCM Syndrome Type forecasting system - Google Patents
A kind of TCM Syndrome Type forecasting system Download PDFInfo
- Publication number
- CN110115563A CN110115563A CN201910431824.7A CN201910431824A CN110115563A CN 110115563 A CN110115563 A CN 110115563A CN 201910431824 A CN201910431824 A CN 201910431824A CN 110115563 A CN110115563 A CN 110115563A
- Authority
- CN
- China
- Prior art keywords
- information
- disease
- patient
- tcm syndrome
- clinical data
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4854—Diagnosis based on concepts of traditional oriental medicine
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- 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
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Alternative & Traditional Medicine (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention discloses a kind of TCM Syndrome Type forecasting system, comprising: tag generation module, trained card type predict network model；The card type prediction network model includes: characteristic extracting module and categorization module: the tag generation module is used to the patient information received being converted to digitized label；The patient information includes: personal essential information, symptom information, living environment information；The characteristic extracting module is used to carry out feature extraction to the digitized label, obtains cause of disease information, sick position information, characteristic of disease information, patient's condition information；The categorization module is used to classify to the cause of disease information, sick position information, characteristic of disease information, patient's condition information, obtains TCM Syndrome Type.Technical solution provided by the invention, can the card type accurately to disease predict, so that doctor be assisted to diagnose.
Description
Technical field
The present invention relates to traditional Chinese medicine expert system technical field more particularly to a kind of TCM Syndrome Type forecasting systems.
Background technique
The dialectical treatmert process of Chinese medicine is that the features such as essential information, the sings and symptoms of patient are obtained by comprehensive analysis
To the process of disease card type.This process needs doctor to take some time the careful thinking of progress, and the disease card type obtained is quasi-
Whether really, the experience of doctor is fully relied at present.
However, clinical patient quantity is more at present, doctor's amount of seeing and treating patients is big, doctor has the interrogation time of each patient
Limit, can not comprehensively understand status of patient, and then cause to be inaccurate to the card type judgement of patient disease.It would therefore be desirable to
The new traditional Chinese medicine expert system of one kind is proposed to solve the above problems.
Summary of the invention
The present invention is intended to provide a kind of TCM Syndrome Type forecasting system, can the card type accurately to disease predict,
To assist doctor to diagnose.
In order to achieve the above objectives, The technical solution adopted by the invention is as follows:
A kind of TCM Syndrome Type forecasting system, comprising: tag generation module, trained card type predict network model；Institute
Stating card type prediction network model includes: characteristic extracting module and categorization module；What the tag generation module was used to receive
Patient information is converted to digitized label；The patient information includes: personal essential information, symptom information, living environment information；
The characteristic extracting module is used to carry out feature extraction to the digitized label, obtains cause of disease information, sick position information, characteristic of disease letter
Breath, patient's condition information；The categorization module is used to divide the cause of disease information, sick position information, characteristic of disease information, patient's condition information
Class obtains TCM Syndrome Type.
Preferably, the characteristic extracting module is BP neural network；The categorization module is that gradient promotes decision tree.
Further, the training data of the card type prediction network model includes: trained digitized label, the training
With the corresponding training TCM Syndrome Type of digitized label；The acquisition methods of the training digitized label include: to build from advance
In vertical clinical data knowledge base, trained patient information is obtained；The training patient information includes: personal essential information,
Symptom information, living environment information；The training is converted into trained digitized label with patient information.
Further, establishing the clinical data knowledge base includes: the clinical data for acquiring predetermined disease；To the clinic
Data are pre-processed, and standard clinical data are obtained；The standard clinical data are screened, modeling data is obtained；
The clinical data knowledge base of the predetermined disease is established according to the modeling data.
It is preferably, described that carry out pretreatment to the clinical data include: that data are successively carried out to the clinical data is clear
It washes and data normalization.
Preferably, the clinical data of predetermined disease is acquired from hospital information system；The hospital information system includes:
LIS system, PACS system, RIS system, emr system.
Further, further includes: optimization module, for being optimized to card type prediction network model.
Preferably, the personal essential information includes: gender, age, blood group, occupation, allergies；The symptom information packet
It includes: by prestige, the four methods of diagnosis symptom for hearing, asking, cutting acquisition, physical and chemical index, pathologic finding, heredity medication history；The living environment information
It include: living environment, weather conditions.
TCM Syndrome Type forecasting system provided in an embodiment of the present invention, by the way that patient information is automatically converted to digitlization mark
Label, and feature extraction is carried out to digitized label using trained card type prediction network model, obtain cause of disease information, sick position letter
After breath, characteristic of disease information, patient's condition information, then classify to cause of disease information, sick position information, characteristic of disease information, patient's condition information, obtains and suffer from
Card type information corresponding to person, enable fully rely at present the dialectical treatmert process of doctors experience by computer automatically into
Row.Since whole system comprehensively obtains patient information, and the dialectical treatmert process of doctor is simulated well, i.e., first obtain
After cause of disease information, sick position information, characteristic of disease information, patient's condition information, then classify to obtain card type information, therefore, whole system can be compared with
Accurately the card type of disease is predicted, so as to assist doctor to diagnose.
Detailed description of the invention
Fig. 1 is the system construction drawing one of the embodiment of the present invention one；
Fig. 2 is the system construction drawing two of the embodiment of the present invention one；
Fig. 3 is the system construction drawing of the embodiment of the present invention two；
Fig. 4 is the method flow diagram that clinical data knowledge base is established in the embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing, to the present invention into
Row is further described.
Fig. 1 is the system construction drawing one of the embodiment of the present invention one, comprising: tag generation module, trained card type are pre-
Survey network model；The card type prediction network model includes: characteristic extracting module and categorization module；The tag generation module is used
In the patient information received is converted to digitized label；The patient information includes: personal essential information, symptom information,
Living environment information；The characteristic extracting module is used to carry out feature extraction to the digitized label, obtains cause of disease information, disease
Position information, characteristic of disease information, patient's condition information；The categorization module is used for the cause of disease information, sick position information, characteristic of disease information, disease
Gesture information is classified, and TCM Syndrome Type is obtained.The data trend of whole system is as shown in Figure 2.
In the present embodiment, the characteristic extracting module is BP (back propagation) neural network；The classification mould
Block is that gradient promotes decision tree.BP neural network is one kind of deep neural network.Deep neural network is closed in the complexity of feature
There are advantages in system's extraction, and abstract representative feature can be excavated from high dimensional feature.And gradient promotes decision
(Gradient Boosting Decision Tree, GBDT) model is set by the way of integrated study, is by determining to more
The result of plan tree is integrated to obtain final prediction result, avoids single decision-tree model bring limitation, is equivalent to pair
The relationship of feature has carried out cross correlation.Deep neural network training process is complicated, the training time is long, and GBDT has in speed
It has a clear superiority, the two is complementary.
Therefore, it the present invention is based on the advantage that deep neural network has feature extraction, proposes its promoting decision with gradient
Tree combines the prediction for patient disease card type.Wherein, deep neural network is as feature extractor, for the number to patient
Word label carries out feature extraction, obtains cause of disease information, sick position information, characteristic of disease information, patient's condition information；GBDT is used as classifier
Classify in above-mentioned cause of disease information, sick position information, characteristic of disease information, patient's condition information, obtains TCM Syndrome Type.Also, GBDT collection
It is equivalent to the feature for carrying out after feature extraction deep neural network at the mode of study to be learnt again, the combination of the two
It is combination among the strong ones, improves the Accuracy and high efficiency that whole network model predicts patient disease card type.
As shown in Fig. 2, the input layer of system of the embodiment of the present invention is patient information, it is converted by tag generation module
Digitized label, these digitized labels are indicated by feature vector: O=(o1, o2, o3..., on), wherein oi=(oi1,
oi2, oi3..., oin), i=(1,2,3 ..., n) indicates the occurrence of each digitized label.Above-mentioned digitized label is passed through
After feature extraction, " cause of disease, sick position, characteristic of disease, patient's condition " calculated result of Chinese medicine is obtained, with matrix B=(B1, B2, B3, B4) indicate,
Wherein, B1=oi1, oi2, oi3..., oi13, B2=oi14, o115, oi16..., oi25, B3=oi26, oi27, oi28..., oi31, B4
=oi32, oi33, oi34..., oin, this result is the hidden layer of deep neural network.Later using above-mentioned calculated result as GBDT
Input, obtain final classification as a result, i.e. system of the embodiment of the present invention output layer, with Z=(z1, z2, z3..., zm) carry out table
Show.
Deep neural network in the embodiment of the present invention can extract the characteristic features of higher level of abstraction, reduce simultaneously
The dimension of feature obtains the cause of disease, sick position, characteristic of disease, patient's condition information by deep neural network, gradient is recycled to promote decision tree pair
Above- mentioned information are classified, and obtain final classification results, i.e. the card type result of patient disease.
It is its thought based on integrated study that gradient, which promotes the most prominent feature of decision tree, is presented as using successive ignition shape
It is combined at more decision trees, generates final decision, i.e. GBDT is the result of comprehensive all trees to carry out final conclusion really
It is fixed.The core concept that gradient promotes decision tree is exactly that every one tree learnt is the conclusion and residual error of all trees before, last
Prediction result is the synthesis to each decision tree predicted value.GBDT algorithm flow is as follows:
Input: training dataset T={ (x1, y1), (x2, y2) ..., (xN, yN), xi∈RnLoss function is L (y, f
(x))；Output: regression tree
(a) it initializes
To m=1,2 ..., M, to i=1,2 ... N is calculated
(b) to rmiIt is fitted a regression tree, so that the leaf node region R of the m treemj。
To j=1,2 ..., J, calculate
It updatesObtain regression tree:
GBDT algorithm is relative to other algorithms, and the arameter optimization time is short, precision of prediction is high, can be avoided by single decision
Set bring limitation.
In the present embodiment, the training data of the card type prediction network model includes: trained digitized label, the instruction
Practice the corresponding training TCM Syndrome Type of digitized label；The acquisition methods of the training digitized label include: from preparatory
In the clinical data knowledge base of foundation, trained patient information is obtained；The training patient information includes: personal basic letter
Breath, symptom information, living environment information；The training is converted into trained digitized label with patient information.
In the present embodiment, establishing the clinical data knowledge base includes: the clinical data for acquiring predetermined disease；Face described
Bed data are pre-processed, and standard clinical data are obtained；The standard clinical data are screened, modeling number is obtained
According to；The clinical data knowledge base of the predetermined disease is established according to the modeling data.Its specific implementation are as follows:
The clinical data of predetermined disease is acquired from hospital information system；The hospital information system includes: LIS system
(Laboratory lnformation Management System, Laboratory Information Management System), PACS system
(Picture archiving and communication systems, Picture Archiving and Communication System), RIS system
(Radioiogy information system, Radiology Information System), emr system (Electronic Medical
Record, electronic medical record system).The clinical data of about 10000 parts of some diseases, the clinical data are obtained from above system
It include: patient individual's population information, Electronic Health Record, electronic health record, physical examination report, health monitoring data etc..Later to this
A little clinical datas carry out the data structureds such as data cleansing, data normalization, standardization pretreatment, to obtain standard clinical number
According to.Later, feature distribution statistics, feature vacancy ration statistics, feature expansion and variable correlation are carried out to standard clinical data
Property analysis etc., therefrom select can participate in modeling clinical data.Clinical data knowledge base mould is established in modeling herein
Type.The clinical data knowledge base set up according to the clinical data filtered out, wherein containing general character knowledge, classification of diseases, doctor
It is more between technics, the cause of disease, association disease, pathogenesis, clinical manifestation, complication, adverse drug reaction and above- mentioned information
Tie up related information.
After establishing clinical data knowledge base, so that it may training patient information and trained TCM Syndrome Type are therefrom obtained,
For being trained to card type prediction network model.Wherein, trained patient information need to be further converted into trained number
Input of the word label as card type prediction network model, training use TCM Syndrome Type to predict network model as the card type
Output.In view of factors such as the disease of different patients, age, living habit, the disease incidence courses of disease, from clinical data knowledge
When extracting training patient information in library, need to comprehensively consider microcosmic, middle sight and the macroscopic information of patient.Microscopic information, that is, patient
Personal essential information, gender, age, blood group, occupation, allergies including patient etc..Middle sight information, that is, patient symptom letter
Breath, four methods of diagnosis symptom, physical and chemical index, pathologic finding, heredity medication history including patient etc..The four methods of diagnosis symptom by the prestige of doctor,
It hears, ask, the disconnected acquisition of diagnosis.Four methods of diagnosis symptom includes tired, out of strength mind, shortness of breath, palpitaition, spontaneous perspiration etc..Macroscopic information, that is, patient life
Environmental information, living environment, weather conditions, the twenty-four solar terms being presently in including patient etc..At large it is situated between in "Nei Jing"
Continued time phenology and Human Physiology, pathology and the relationship of health.Ancient physician passes through practice summary in traditional Chinese medical theory
A large amount of experimental medicine thought has been incorporated, has ideally been combined together disease to geographical, naturally relevant solar term season.Cause
This, the addition of these macroscopic informations can make patient information more comprehensive, and the card type after making training predicts the pre- of network model
It surveys result and has more accuracy.
In order to make card type prediction network model be continuously updated, optimize, perfect, the embodiment of the present invention further comprises: excellent
Change module, which is used to optimize card type prediction network model.During subsequent prediction, optimization is relied on
Module, with the increase of predicted quantity, the prediction result of entire model can be more and more accurate.
TCM Syndrome Type forecasting system provided in an embodiment of the present invention, by the way that patient information is automatically converted to digitlization mark
Label, and feature extraction is carried out to digitized label using trained card type prediction network model, obtain cause of disease information, sick position letter
After breath, characteristic of disease information, patient's condition information, then classify to cause of disease information, sick position information, characteristic of disease information, patient's condition information, obtains and suffer from
Card type information corresponding to person, enable fully rely at present the dialectical treatmert process of doctors experience by computer automatically into
Row.Since whole system comprehensively obtains patient information, and the dialectical treatmert process of doctor is simulated well, i.e., first obtain
After cause of disease information, sick position information, characteristic of disease information, patient's condition information, then classify to obtain card type information, therefore, whole system can be compared with
Accurately the card type of disease is predicted, so as to assist doctor to diagnose.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.
Claims (8)
1. a kind of TCM Syndrome Type forecasting system characterized by comprising tag generation module, the trained pre- survey grid of card type
Network model；The card type prediction network model includes: characteristic extracting module and categorization module；
The tag generation module is used to the patient information received being converted to digitized label；The patient information includes:
Personal essential information, symptom information, living environment information；
The characteristic extracting module is used to carry out feature extraction to the digitized label, obtains cause of disease information, sick position information, disease
Property information, patient's condition information；
The categorization module is used to classify to the cause of disease information, sick position information, characteristic of disease information, patient's condition information, in acquisition
Cure card type.
2. TCM Syndrome Type forecasting system according to claim 1, which is characterized in that the characteristic extracting module is BP nerve
Network；The categorization module is that gradient promotes decision tree.
3. TCM Syndrome Type forecasting system according to claim 2, which is characterized in that the instruction of the card type prediction network model
Practicing data includes: trained digitized label, the training corresponding training TCM Syndrome Type of digitized label；The training
Include: with the acquisition methods of digitized label
From the clinical data knowledge base pre-established, trained patient information is obtained；The training patient information includes:
People's essential information, symptom information, living environment information；
The training is converted into trained digitized label with patient information.
4. TCM Syndrome Type forecasting system according to claim 3, which is characterized in that establish the clinical data knowledge base packet
It includes:
Acquire the clinical data of predetermined disease；
The clinical data is pre-processed, standard clinical data are obtained；
The standard clinical data are screened, modeling data is obtained；
The clinical data knowledge base of the predetermined disease is established according to the modeling data.
5. TCM Syndrome Type forecasting system according to claim 4, which is characterized in that described to be carried out in advance to the clinical data
Processing includes:
Data cleansing and data normalization are successively carried out to the clinical data.
6. TCM Syndrome Type forecasting system according to claim 4, which is characterized in that acquired from hospital information system predetermined
The clinical data of disease；The hospital information system includes: LIS system, PACS system, RIS system, emr system.
7. TCM Syndrome Type forecasting system according to claim 1, which is characterized in that further include: optimization module, for institute
Card type prediction network model is stated to optimize.
8. TCM Syndrome Type forecasting system according to claim 1, which is characterized in that individual's essential information includes: property
Not, age, blood group, occupation, allergies；The symptom information includes: four methods of diagnosis symptom, physical and chemical index, pathologic finding, hereditary disease
History；The four methods of diagnosis symptom is by hoping, hearing, asking, cutting acquisition；The living environment information includes: living environment, weather conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431824.7A CN110115563A (en) | 2019-05-22 | 2019-05-22 | A kind of TCM Syndrome Type forecasting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431824.7A CN110115563A (en) | 2019-05-22 | 2019-05-22 | A kind of TCM Syndrome Type forecasting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110115563A true CN110115563A (en) | 2019-08-13 |
Family
ID=67523021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910431824.7A Pending CN110115563A (en) | 2019-05-22 | 2019-05-22 | A kind of TCM Syndrome Type forecasting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110115563A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110853764A (en) * | 2019-11-28 | 2020-02-28 | 成都中医药大学 | Diabetes syndrome prediction system |
| CN111105854A (en) * | 2019-12-12 | 2020-05-05 | 和宇健康科技股份有限公司 | Search engine system for health information system knowledge base |
| CN112617758A (en) * | 2020-12-31 | 2021-04-09 | 厦门越人健康技术研发有限公司 | Traditional Chinese medicine health state identification method based on artificial intelligence |
| CN112786191A (en) * | 2021-01-18 | 2021-05-11 | 吾征智能技术(北京)有限公司 | Disease cognition system, equipment and storage medium based on stool convention |
| CN113241173A (en) * | 2021-05-12 | 2021-08-10 | 华中科技大学 | Traditional Chinese medicine auxiliary diagnosis and treatment method and system for chronic obstructive pulmonary disease |
| CN113257410A (en) * | 2021-06-10 | 2021-08-13 | 南京大经中医药信息技术有限公司 | Interrogation method based on traditional Chinese medicine clinical medical knowledge base and deep learning model |
| CN113555086A (en) * | 2021-07-26 | 2021-10-26 | 平安科技（深圳）有限公司 | Dialectical analysis method, device, equipment and medium based on machine learning |
| CN115083628A (en) * | 2022-08-19 | 2022-09-20 | 成都中医药大学 | Medical education cooperative system based on traditional Chinese medicine inspection objectivity |
| CN116525100A (en) * | 2023-04-26 | 2023-08-01 | 脉景（杭州）健康管理有限公司 | Traditional Chinese medicine prescription reverse verification method and system based on label system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298662A (en) * | 2010-06-24 | 2011-12-28 | 上海中医药大学 | Neural network traditional Chinese medicinal syndrome diagnostic system based on self-adapting resonance theory |
| CN107016438A (en) * | 2017-04-14 | 2017-08-04 | 温川飙 | A kind of system based on Chinese medical discrimination artificial neural network algorithm model |
| CN107451407A (en) * | 2017-07-31 | 2017-12-08 | 广东工业大学 | A kind of traditional Chinese medical science intelligent diagnosing method, system and traditional medical system |
| CN108986911A (en) * | 2018-07-06 | 2018-12-11 | 成都中医药大学 | A kind of differential diagnosis in tcm opinion controls data processing method |
| CN109303559A (en) * | 2018-11-01 | 2019-02-05 | 杭州质子科技有限公司 | A kind of dynamic ECG beat classification method promoting decision tree based on gradient |
| CN109326350A (en) * | 2018-09-25 | 2019-02-12 | 福建中医药大学 | Cerebral infarction clinic diagnosis system |
-
2019
- 2019-05-22 CN CN201910431824.7A patent/CN110115563A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298662A (en) * | 2010-06-24 | 2011-12-28 | 上海中医药大学 | Neural network traditional Chinese medicinal syndrome diagnostic system based on self-adapting resonance theory |
| CN107016438A (en) * | 2017-04-14 | 2017-08-04 | 温川飙 | A kind of system based on Chinese medical discrimination artificial neural network algorithm model |
| CN107451407A (en) * | 2017-07-31 | 2017-12-08 | 广东工业大学 | A kind of traditional Chinese medical science intelligent diagnosing method, system and traditional medical system |
| CN108986911A (en) * | 2018-07-06 | 2018-12-11 | 成都中医药大学 | A kind of differential diagnosis in tcm opinion controls data processing method |
| CN109326350A (en) * | 2018-09-25 | 2019-02-12 | 福建中医药大学 | Cerebral infarction clinic diagnosis system |
| CN109303559A (en) * | 2018-11-01 | 2019-02-05 | 杭州质子科技有限公司 | A kind of dynamic ECG beat classification method promoting decision tree based on gradient |
Non-Patent Citations (3)
| Title |
|---|
| 曹继忠,赵亮,温川飙: "基于深度学习技术中医优势病种证候到治法方剂算法模型的构想", 《世界最新医学信息文摘》 * |
| 陈淑娇,李灿东: "论大健康背景下的中国特色的中医健康管理模式", 《中华中医药杂志》 * |
| 陈菊,杨殿兴,赵姝婷,曹悦,马艺艺,温川飙: "一种中医辨证人工神经网络算法模型", 《中国中医药信息研究会.第五届中国中医药信息大会——大数据标准化与智慧中医药论文集》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110853764A (en) * | 2019-11-28 | 2020-02-28 | 成都中医药大学 | Diabetes syndrome prediction system |
| CN110853764B (en) * | 2019-11-28 | 2023-11-14 | 成都中医药大学 | Diabetes syndrome prediction system |
| CN111105854A (en) * | 2019-12-12 | 2020-05-05 | 和宇健康科技股份有限公司 | Search engine system for health information system knowledge base |
| CN112617758A (en) * | 2020-12-31 | 2021-04-09 | 厦门越人健康技术研发有限公司 | Traditional Chinese medicine health state identification method based on artificial intelligence |
| CN112786191A (en) * | 2021-01-18 | 2021-05-11 | 吾征智能技术(北京)有限公司 | Disease cognition system, equipment and storage medium based on stool convention |
| CN112786191B (en) * | 2021-01-18 | 2023-12-05 | 吾征智能技术(北京)有限公司 | Disease cognition system, equipment and storage medium based on excrement convention |
| CN113241173B (en) * | 2021-05-12 | 2023-06-13 | 华中科技大学 | Traditional Chinese medicine auxiliary diagnosis and treatment method and system for chronic obstructive pulmonary disease |
| CN113241173A (en) * | 2021-05-12 | 2021-08-10 | 华中科技大学 | Traditional Chinese medicine auxiliary diagnosis and treatment method and system for chronic obstructive pulmonary disease |
| CN113257410A (en) * | 2021-06-10 | 2021-08-13 | 南京大经中医药信息技术有限公司 | Interrogation method based on traditional Chinese medicine clinical medical knowledge base and deep learning model |
| CN113555086A (en) * | 2021-07-26 | 2021-10-26 | 平安科技（深圳）有限公司 | Dialectical analysis method, device, equipment and medium based on machine learning |
| CN113555086B (en) * | 2021-07-26 | 2024-05-10 | 平安科技（深圳）有限公司 | Dialectical analysis method, device, equipment and medium based on machine learning |
| CN115083628A (en) * | 2022-08-19 | 2022-09-20 | 成都中医药大学 | Medical education cooperative system based on traditional Chinese medicine inspection objectivity |
| CN115083628B (en) * | 2022-08-19 | 2022-10-28 | 成都中医药大学 | Medical education cooperative system based on traditional Chinese medicine inspection objectivity |
| CN116525100A (en) * | 2023-04-26 | 2023-08-01 | 脉景（杭州）健康管理有限公司 | Traditional Chinese medicine prescription reverse verification method and system based on label system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110115563A (en) | A kind of TCM Syndrome Type forecasting system | |
| Kamalraj et al. | Interpretable filter based convolutional neural network (IF-CNN) for glucose prediction and classification using PD-SS algorithm | |
| CN107680676B (en) | Gestational diabetes prediction method based on electronic medical record data drive | |
| EP3234823B1 (en) | Differential medical diagnosis apparatus adapted in order to determine an optimal sequence of diagnostic tests for identifying a pathology by adopting diagnostic appropriateness criteria | |
| CN112133445A (en) | Cardiovascular disease management service method and system | |
| WO2006072011A2 (en) | Methods, systems, and computer program products for developing and using predictive models for predicting a plurality of medical outcomes, for evaluating intervention strategies, and for simultaneously validating biomarker causality | |
| CN109243567B (en) | Medicine recommendation method based on prescription data mining | |
| CN110046757B (en) | Outpatient clinic volume prediction system and prediction method based on LightGBM algorithm | |
| EP3382584A1 (en) | A system and a method to predict patient behaviour | |
| CN109558912A (en) | A kind of Alzheimer's disease classification method separating convolution based on depth | |
| WO2021151295A1 (en) | Method, apparatus, computer device, and medium for determining patient treatment plan | |
| KR101295785B1 (en) | Apparatus and Method for Constructing Gene-Disease Relation Database | |
| Ha et al. | Identifying new innovative services using M&A data: an integrated approach of data-driven morphological analysis | |
| EP2310969A1 (en) | A system method and computer program product for pedigree analysis | |
| Mirzajani | Prediction and diagnosis of diabetes by using data mining techniques | |
| CN114420279A (en) | Medical resource recommendation method, device, equipment and storage medium | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| Yamashita et al. | Machine learning for classification of postoperative patient status using standardized medical data | |
| Oğur et al. | Development of an artificial intelligence-supported hybrid data management platform for monitoring depression and anxiety symptoms in the perinatal period: Pilot-scale study | |
| Zhang et al. | Survival topic models for predicting outcomes for trauma patients | |
| CN113096795B (en) | Multi-source data-aided clinical decision support system and method | |
| Rasubala et al. | Digital twin roles in public healthcare | |
| Patel et al. | Predicting Heart Disease Using Machine Learning Algorithms | |
| Alghadier et al. | A study of various applications of artificial intelligence (AI) and machine learning (ML) for healthcare services | |
| Kamal et al. | Disease Symptoms Analysis Using Data Mining Techniques to Predict Diabetes Risk. |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190813 |