CN110111886A - A kind of intelligent interrogation system and method based on XGBoost disease forecasting - Google Patents
A kind of intelligent interrogation system and method based on XGBoost disease forecasting Download PDFInfo
- Publication number
- CN110111886A CN110111886A CN201910407739.7A CN201910407739A CN110111886A CN 110111886 A CN110111886 A CN 110111886A CN 201910407739 A CN201910407739 A CN 201910407739A CN 110111886 A CN110111886 A CN 110111886A
- Authority
- CN
- China
- Prior art keywords
- disease
- module
- xgboost
- information
- patient
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—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)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Epidemiology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention discloses a kind of intelligent interrogation systems and method based on XGBoost disease forecasting, the system comprises the clients and server-side by network connection, the client includes interrogation module and display module, the server-side includes data processing module, data memory module and XGBoost disease forecasting module, through the patient symptom information input that obtains client into the more disaggregated models of trained XGBoost, export disease probabilistic forecasting value and predictive disease information, and patient can directly carry out checking relevant information in client, based on machine learning and big data technology, the self-service diagnostic service of patient may be implemented, support the intellectual analysis and prediction to magnanimity patient data, prediction has high accuracy and high-timeliness, it is easy to operate at low cost.
Description
Technical field
The present embodiments relate to disease forecastings and diagnostic techniques field, and in particular to one kind is pre- based on XGBoost disease
The intelligent interrogation system and method for survey.
Background technique
Due to the problems such as medical resource is nervous, matching is unevenly distributed, leads to ordinary people Expensive and hard to visit doctors, intelligently ask
Examine product be it is a kind of the artificial intelligence system of self-service consulting and diagnostic service can be provided for patient, can assist doctor to patient into
Row interrogation, the consultation time and money for effectively reducing patient are spent, and improve the diagnosis and treatment efficiency of doctor.Existing intelligence interrogation product
The stage for speculating disease for symptom is also rested on, a small amount of symptom and disease can also be dealt with, when in face of hundreds of
It just has no way of doing it when magnanimity big data, and mostly symptom is analyzed based on clinical experience data or database, prediction
Accuracy and timeliness are difficult to ensure.
Summary of the invention
For this purpose, the embodiment of the present invention provides a kind of intelligent interrogation system and method based on XGBoost disease forecasting, with solution
The problem of certainly existing intelligent interrogation product precisely can not be analyzed and be predicted to magnanimity patient data.
To achieve the goals above, the embodiment of the present invention provides the following technical solutions:
According to a first aspect of the embodiments of the present invention, a kind of intelligent interrogation system based on XGBoost disease forecasting is proposed
System, the system comprises the clients and server-side by network connection;
The client includes interrogation module and display module;
The interrogation module is used to carry out question and answer with patient by simulation doctor to interact, and obtains patient basis and symptom
Information;
The display module is used to receive the predictive disease information that server-side is sent and disease probabilistic forecasting value and shows;
The server-side includes data processing module, data memory module and XGBoost disease forecasting module;
The data processing module is used to obtain client patient basis and symptom information data are handled;
The data memory module is for storing data;
The XGBoost disease forecasting module is used for will treated that patient symptom information data is input to is trained
In the more disaggregated models of XGBoost, exports disease probabilistic forecasting value and predictive disease information and be sent to client.
Further, the data processing module includes standardized module;
The symptom information data that the standardized module is used to will acquire carry out 0-1 standardization.
Further, the data processing module further includes weight assignment module;
The weight assignment module be used for according to the uncertainty degree of the symptom information to the symptom information data into
Row weight assignment.
Further, the server-side further includes that incremental data obtains module and incremental learning module;
The incremental data obtains module and is used to obtain new cases data, the new cases data according to predetermined period
Including newly-increased disease information and newly-increased disease symptoms information data corresponding with the newly-increased disease information;
The incremental learning module is used to carry out week to the more disaggregated models of the XGBoost using the new cases data
The incremental learning training of phase property.
Further, the more disaggregated models of the XGBoost be based on XGBoost multi-classification algorithm, using gradient lift method into
Row training, iterator type are gbtree, and loss function uses mean square deviation MSE form.
Further, the server-side further includes related information module;
The related information module is used to provide disease association information according to the predictive disease information, and by the disease
Related information is sent to client and is shown, the disease association information includes disease associated with the predictive disease information
Sick recommended information, hospital guide department, medication suggestion and medical practitioner recommendation information.
Further, the client further includes feedback module;
Feedback information and the processing that the feedback module is used to receive patient terminate if patient feedback's problem has solved
Interrogation prompts the direct consulting profession doctor of patient if patient feedback's problem is unresolved.
Further, the essential information includes gender, age, pregnant state, medical history, the past medication history and drug
Allergies.
According to a second aspect of the embodiments of the present invention, a kind of intelligent interrogation side based on XGBoost disease forecasting is proposed
Method, which comprises
Client carries out question and answer with patient by simulation doctor and interacts, and obtains patient basis and symptom information;
Server-side obtains client patient basis and symptom information data are handled;
By treated, patient symptom information data is input in the more disaggregated models of trained XGBoost server-side, defeated
Disease probabilistic forecasting value and predictive disease information and it is sent to client out;
Client receives the predictive disease information that server-side is sent and disease probabilistic forecasting value and shows.
The embodiment of the present invention has the advantages that
A kind of intelligent interrogation system and method based on XGBoost disease forecasting that the embodiment of the present invention proposes, system packet
Client and server-side are included, client includes interrogation module and display module, and the server-side includes data processing module, data
Memory module and XGBoost disease forecasting module, by the patient symptom information input that obtains client to trained
In the more disaggregated models of XGBoost, exports disease probabilistic forecasting value and predictive disease information and patient can be directly in client
End carries out checking relevant information, which is based on machine learning and big data technology, and the self-service of patient may be implemented
Diagnostic service, supports intellectual analysis and prediction in time to magnanimity patient data, and prediction has high accuracy and high-timeliness, behaviour
It is at low cost to make simplicity, both can provide accurately medical diagnosis on disease service with patient, can also provide assistance in diagnosis and assist for doctor
Treatment reduces misdiagnosis rate, reduces the generation of malpractice, push the sound development of medical industry.
Detailed description of the invention
It, below will be to embodiment party in order to illustrate more clearly of embodiments of the present invention or technical solution in the prior art
Formula or attached drawing needed to be used in the description of the prior art are briefly described.It should be evident that the accompanying drawings in the following description is only
It is merely exemplary, it for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer, which is extended, obtains other implementation attached drawings.
Fig. 1 is that a kind of structure for intelligent interrogation system based on XGBoost disease forecasting that the embodiment of the present invention 1 provides is shown
It is intended to;
Fig. 2 is that a kind of process for intelligent way of inquisition based on XGBoost disease forecasting that the embodiment of the present invention 2 provides is shown
It is intended to.
Specific embodiment
Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation
Content disclosed by book is understood other advantages and efficacy of the present invention easily, it is clear that described embodiment is the present invention one
Section Example, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Embodiment 1
As shown in Figure 1, the present embodiment proposes a kind of intelligent interrogation system based on XGBoost disease forecasting, the system
Including the client 100 and server-side 200 by network connection.
Client 100 includes interrogation module 110 and display module 120.
Interrogation module 110 is used to carry out question and answer with patient by simulation doctor to interact, and obtains patient basis and symptom
Information.Essential information includes the information such as gender, age, pregnant state, medical history, the past medication history and drug allergy history.
Display module 120 is used to receive the predictive disease information that server-side 200 is sent and disease probabilistic forecasting value and shows
Show.
Server-side 200 includes data processing module 210, data memory module 220 and XGBoost disease forecasting module 230.
Data processing module 210 is used to obtain 100 patient basis of client and symptom information data are handled.
Further, data processing module 210 includes standardized module and weight assignment module;
The symptom information data that standardized module is used to will acquire carry out 0-1 standardization.Client 100 passes through simulation
The symptom information that question and answer obtain is text data, needs to carry out 0-1 standardization to it, text information is mapped to [0,1]
In section, for example, patient obtained certain symptom, then it is assigned a value of 1, the symptom, then be not assigned a value of 0.
Further, data processing module 210 further includes weight assignment module, and weight assignment module according to symptom for believing
The uncertainty degree of breath carries out weight assignment to symptom information data.For above-mentioned symptom determine with and without the case where can be with
Assignment 1 or 0 is carried out, and the case where for uncertain symptom, such as in following simulated scenario:
Doctor inquire patient: " may I ask your abdominal pain? "
Patient may answer there are three types of situation: A does not ache;B aches a little;C pain.
Example is so talked with by this section above, A and C option be obviously before introduction 0 with 1 the case where (A does not ache,
It is mapped to 0 state, C pain is mapped to 1 state), but B option aches a little, how does this judge? it is all with list in current technology
One disease and symptom are judged, can not be judged when there is such case, then the present embodiment is this uncertain by B option
Symptom, an initial random weighted value can be assigned according to the uncertainty degree of symptom information by medical practitioner, weight is reflected
Penetrate in [0,1] section, for example setting is mapped to 0.3, by weight assignment can to some uncertain conditions that sufferer occurs into
The reasonable assignment of row and quantization, the disease forecasting result of final output are also more accurate.
Data memory module 220 is for storing data.
XGBoost disease forecasting module 230 is used for will treated that patient symptom information data is input to is trained
In the more disaggregated models of XGBoost, exports disease probabilistic forecasting value and predictive disease information and be sent to client 100.
The more disaggregated models of XGBoost are based on XGBoost multi-classification algorithm, are trained using gradient lift method, iterator
Type is gbtree, and loss function uses mean square deviation MSE form.
XGBoost sorting algorithm is a kind of promotion tree-model, it is to integrate many CART regression tree models, shape
At a very strong classifier.The algorithm idea is continuous addition tree, constantly carries out feature division to grow one tree, often
One tree of secondary addition is one new function of study in fact, goes the residual error of fitting last time prediction.
It is assumed that training is completed to obtain k tree, to predict the score of a sample, in fact be exactly the spy according to this sample
Sign, as soon as falling on corresponding leaf node in each tree, each leaf node corresponds to a score, and last only needs will be every
The corresponding score of tree add up be exactly the sample predicted value, i.e., the linear adduction of a series of post-class processings, one is optional
Example can be denoted as:
Wherein,For post-class processing set, fkIt is in function spaceK-th of regression tree function of the inside, and Wq(x)For
The weight of leaf node q, R under single tree-modelTFor the leaf weight of tree, q indicates that the node of tree, T indicate the leaf number on tree.
The objective function formulated in training process are as follows:
Obj (θ)=L (θ)+Ω (θ);
Wherein:Training error is indicated, using mean square error, that is, between true value and predicted value
Error.Indicate regular terms,T indicates the leaf number on tree, γ expression pair
The control parameter of leaf node number.WjIndicate that square of leaf node j weighted value mould, i.e. L2 canonical, λ indicate L2 regularization term
Parameter, to prevent over-fitting.
As the supplementary explanation to CART regression tree, CART regression tree assumes that tree is binary tree, by constantly by feature
It is divided, for example current tree node is divided based on j-th of characteristic value, if sample of this feature value less than s divides
For left subtree, the sample greater than s is divided into right subtree:
R1(j, s)=and x | x(j)≤s}and R2(j, s)=and x | x(j)> s };
And CART regression tree substantially exactly divides sample space in this feature dimension, and what this space divided
Optimization is therefore a kind of NP-Hard problem is to be solved in decision-tree model using heuristic.Typical CART regression tree
The objective function of generation are as follows:
Therefore, so mesh is solved when translating into solve optimal cutting feature j and optimal cut-off s
Scalar functions:
As long as so traversing all cut-offs of all features optimal cutting feature and cut-off can be found, most
A regression tree is obtained eventually.
In the present embodiment, the building of the more disaggregated models of XGBoost will do it first, determine the input and output of model, it will
Input of the standardized data of patient symptom information as model, and final output disease probabilistic forecasting value, due to final disease
Type is greater than 2, therefore constructs more sorting machine learning models based on XGBoost, in original model parameter setting, learning rate
It is set as 0.1, the depth capacity of tree is 6, and least disadvantage function drop-out value needed for node split is 0.1, the number of iterations 100 times,
L2 canonical lambda parameter is 1, and parallel multithread number is 4, and other parameters are default value.
The training set established after model foundation using the standardized Primitive case data of 0-1 classifies mould to the XGBoost more
Type is trained, and Primitive case data include a variety of disease informations and symptom information corresponding with disease information, the present embodiment
In Primitive case data use 4920 case data, wherein the idagnostic logout of each patient be a data, share 132
Symptom, 41 kinds of diseases, the number of data of every kind of disease 120 carry out 0-1 standardization to Primitive case data and obtain sample
Data set, and sample data set can be cut into training set and test set according to the ratio of 7:3, cutting process is by random seed
It is set as fixed value, in order to parameter comparison.
After the completion of training, the more disaggregated models of trained XGBoost are tested using test set, export a variety of diseases
Corresponding disease probability value.The more disaggregated models of XGBoost can also be optimized according to user demand, determine optimal mould
Shape parameter.According to specific user demand, model parameter is adjusted, the probability distribution of meet demand is obtained.Finally by disease
Probability value carries out threshold value selection, exports disease probabilistic forecasting value.By the disease probability value of output according to descending sequence into
Row sequence, selected threshold, such as choose maximum value, export disease probabilistic forecasting value, complete the more disaggregated models of XGBoost training with
And test.
It can be using indexs such as accuracy rate, recall rate and F1-Score to the more disaggregated models of XGBoost after the completion of test
It is assessed, is packaged model after the completion of assessment, and be deployed to server, interface is provided and is called.
Further, server-side 200 further includes that incremental data obtains module 240 and incremental learning module 250.
Incremental data obtains module 240 and is used to obtain new cases data according to predetermined period, and new cases data include
Newly-increased disease information and newly-increased disease symptoms information data corresponding with newly-increased disease information.
Incremental learning module 250 is used to periodically increase the more disaggregated models of XGBoost using new cases data
Measure learning training.In order to allow the existing epidemic disease of the better control of model, can within the fixed cycle (such as one day, three days or
One week) the disease check results based on newly-increased case data and medical practitioner, sample set is updated, and re-start XGBoost
Model supervised learning training, obtain data more fully, the better prediction model of timeliness.
Further, server-side 200 further includes related information module 260, and related information module 260 is used for according to prediction disease
Sick information provides disease association information, and disease association information is sent to client 100 and is shown, disease association packet
Include disease recommended information associated with predictive disease information, hospital guide department, medication suggestion and medical practitioner recommendation information.Side
Help user that can also obtain targetedly basic diagnostic recommendations while obtaining disease forecasting result.
Further, client 100 further includes feedback module 130, and feedback module 130 is used to receive the feedback information of patient
And handle, if patient feedback's problem has solved, terminate interrogation, if patient feedback's problem is unresolved, patient is prompted directly to consult
Ask medical practitioner.
The intelligence interrogation system is based on machine learning and big data technology, and the self-service diagnostic service of patient may be implemented, and props up
Holding has high accuracy and high-timeliness, cost easy to operate to the intellectual analysis of magnanimity patient data and prediction in time, prediction
It is low, both accurately medical diagnosis on disease service can be provided with patient, and can also provide assistance in diagnosis and assist in the treatment of for doctor, reduce and miss
Rate is examined, the generation of malpractice is reduced, pushes the sound development of medical industry.
Embodiment 2
With above-described embodiment 1 correspondingly, the present embodiment proposes a kind of intelligent interrogation based on XGBoost disease forecasting
Method, this method comprises:
S100, client 100 carry out question and answer with patient by simulation doctor and interact, and obtain patient basis and symptom letter
Breath;
S200, server-side 200 obtain 100 patient basis of client and symptom information data are handled;
S300, server-side 200 will treated patient symptom information data is input to trained XGBoost classifies more moulds
In type, exports disease probabilistic forecasting value and predictive disease information and be sent to client 100;
S400, client 100 receive the predictive disease information and disease probabilistic forecasting value that server-side 200 is sent and show
Show.
Each step is specific in a kind of intelligent way of inquisition based on XGBoost disease forecasting provided in an embodiment of the present invention
Process has been discussed in detail in above-described embodiment 1, therefore does not do excessively repeat here.
Although above having used general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.
Claims (9)
1. a kind of intelligent interrogation system based on XGBoost disease forecasting, which is characterized in that the system comprises connected by network
The client and server-side connect;
The client includes interrogation module and display module;
The interrogation module is used to carry out question and answer with patient by simulation doctor to interact, and obtains patient basis and symptom letter
Breath;
The display module is used to receive the predictive disease information that server-side is sent and disease probabilistic forecasting value and shows;
The server-side includes data processing module, data memory module and XGBoost disease forecasting module;
The data processing module is used to obtain client patient basis and symptom information data are handled;
The data memory module is for storing data;
The XGBoost disease forecasting module is used for will treated that patient symptom information data is input to is trained
In the more disaggregated models of XGBoost, exports disease probabilistic forecasting value and predictive disease information and be sent to client.
2. a kind of intelligent interrogation system based on XGBoost disease forecasting according to claim 1, which is characterized in that institute
Stating data processing module includes standardized module;
The symptom information data that the standardized module is used to will acquire carry out 0-1 standardization.
3. a kind of intelligent interrogation system based on XGBoost disease forecasting according to claim 2, which is characterized in that institute
Stating data processing module further includes weight assignment module;
The weight assignment module is for weighing the symptom information data according to the uncertainty degree of the symptom information
Reassignment.
4. a kind of intelligent interrogation system based on XGBoost disease forecasting according to claim 1, which is characterized in that institute
Stating server-side further includes that incremental data obtains module and incremental learning module;
The incremental data obtains module and is used to obtain new cases data according to predetermined period, and the new cases data include
Newly-increased disease information and newly-increased disease symptoms information data corresponding with the newly-increased disease information;
The incremental learning module is used to carry out periodically the more disaggregated models of the XGBoost using the new cases data
Incremental learning training.
5. a kind of intelligent interrogation system based on XGBoost disease forecasting according to claim 1, which is characterized in that institute
It states the more disaggregated models of XGBoost and is based on XGBoost multi-classification algorithm, be trained using gradient lift method, iterator type is
Gbtree, loss function use mean square deviation MSE form.
6. a kind of intelligent interrogation system based on XGBoost disease forecasting according to claim 1, which is characterized in that institute
Stating server-side further includes related information module;
The related information module is used to provide disease association information according to the predictive disease information, and by the disease association
Information is sent to client and is shown, the disease association information includes that disease associated with the predictive disease information is situated between
Continue information, hospital guide department, medication suggestion and medical practitioner recommendation information.
7. a kind of intelligent interrogation system based on XGBoost disease forecasting according to claim 1, which is characterized in that institute
Stating client further includes feedback module;
Feedback information and the processing that the feedback module is used to receive patient terminate interrogation if patient feedback's problem has solved,
If patient feedback's problem is unresolved, the direct consulting profession doctor of patient is prompted.
8. a kind of intelligent interrogation system based on XGBoost disease forecasting according to claim 1, which is characterized in that institute
Stating essential information includes gender, age, pregnant state, medical history, the past medication history and drug allergy history.
9. a kind of intelligent way of inquisition based on XGBoost disease forecasting, which is characterized in that the described method includes:
Client carries out question and answer with patient by simulation doctor and interacts, and obtains patient basis and symptom information;
Server-side obtains client patient basis and symptom information data are handled;
By treated, patient symptom information data is input in the more disaggregated models of trained XGBoost server-side, exports disease
Sick probabilistic forecasting value and predictive disease information are simultaneously sent to client;
Client receives the predictive disease information that server-side is sent and disease probabilistic forecasting value and shows.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910407739.7A CN110111886A (en) | 2019-05-16 | 2019-05-16 | A kind of intelligent interrogation system and method based on XGBoost disease forecasting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910407739.7A CN110111886A (en) | 2019-05-16 | 2019-05-16 | A kind of intelligent interrogation system and method based on XGBoost disease forecasting |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110111886A true CN110111886A (en) | 2019-08-09 |
Family
ID=67490503
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910407739.7A Pending CN110111886A (en) | 2019-05-16 | 2019-05-16 | A kind of intelligent interrogation system and method based on XGBoost disease forecasting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110111886A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110797121A (en) * | 2019-10-29 | 2020-02-14 | 浪潮天元通信信息系统有限公司 | Remote intelligent health analysis system and method based on Internet of things |
CN110853760A (en) * | 2019-11-12 | 2020-02-28 | 好人生(上海)健康科技有限公司 | Interactive system for providing health guidance based on disease diagnosis |
CN110853764A (en) * | 2019-11-28 | 2020-02-28 | 成都中医药大学 | Diabetes syndrome prediction system |
CN110942180A (en) * | 2019-11-12 | 2020-03-31 | 广州泽沐信息科技有限责任公司 | Industrial design matching service party prediction method based on xgboost algorithm |
CN111428930A (en) * | 2020-03-24 | 2020-07-17 | 中电药明数据科技(成都)有限公司 | GBDT-based medicine patient using number prediction method and system |
CN111599489A (en) * | 2020-05-19 | 2020-08-28 | 万达信息股份有限公司 | Disease information acquisition method, terminal equipment and storage medium |
CN111833997A (en) * | 2020-07-16 | 2020-10-27 | 平安科技(深圳)有限公司 | Doctor allocation method and device based on risk prediction and computer equipment |
CN112102955A (en) * | 2020-09-07 | 2020-12-18 | 武汉科瓴智能科技有限公司 | Patient disease prediction control system and method based on Gaussian mixture model |
CN112786194A (en) * | 2021-01-28 | 2021-05-11 | 北京一脉阳光医学信息技术有限公司 | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence |
CN113057589A (en) * | 2021-03-17 | 2021-07-02 | 上海电气集团股份有限公司 | Method and system for predicting organ failure infection diseases and training prediction model |
CN113140314A (en) * | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Medical science popularization system, method and server |
CN113469469A (en) * | 2021-09-02 | 2021-10-01 | 杭州华网信息技术有限公司 | Student physical ability score prediction method based on sectional loss function |
CN113555118A (en) * | 2021-07-26 | 2021-10-26 | 内蒙古自治区人民医院 | Method and device for predicting disease degree, electronic equipment and storage medium |
CN113724867A (en) * | 2021-11-03 | 2021-11-30 | 北京大学第三医院(北京大学第三临床医学院) | Prompting system and method |
WO2022267678A1 (en) * | 2021-06-23 | 2022-12-29 | 康键信息技术(深圳)有限公司 | Video consultation method and apparatus, device and storage medium |
US12014284B2 (en) | 2019-12-27 | 2024-06-18 | Industrial Technology Research Institute | Question-answering learning method and question-answering learning system using the same and computer program product thereof |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164616A (en) * | 2013-02-02 | 2013-06-19 | 杭州卓健信息科技有限公司 | Intelligent hospital guide system and intelligent hospital guide method |
CN106777971A (en) * | 2016-12-15 | 2017-05-31 | 杭州卓健信息科技有限公司 | A kind of intelligent hospital guide's method and its device |
CN107066791A (en) * | 2016-12-19 | 2017-08-18 | 银江股份有限公司 | A kind of aided disease diagnosis method based on patient's assay |
CN108630312A (en) * | 2018-05-11 | 2018-10-09 | 北京诺道认知医学科技有限公司 | A kind of hypertension diagnosis rule base automatic generation method and device |
CN108877905A (en) * | 2018-06-12 | 2018-11-23 | 中南大学 | A kind of medical amount prediction technique of the hospital outpatient based on Xgboost frame |
CN109003679A (en) * | 2018-06-28 | 2018-12-14 | 众安信息技术服务有限公司 | A kind of cerebrovascular hemorrhage and ischemic prediction technique and device |
CN109524108A (en) * | 2018-11-21 | 2019-03-26 | 上海依智医疗技术有限公司 | A kind of method for building up and device of inquiry model |
-
2019
- 2019-05-16 CN CN201910407739.7A patent/CN110111886A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164616A (en) * | 2013-02-02 | 2013-06-19 | 杭州卓健信息科技有限公司 | Intelligent hospital guide system and intelligent hospital guide method |
CN106777971A (en) * | 2016-12-15 | 2017-05-31 | 杭州卓健信息科技有限公司 | A kind of intelligent hospital guide's method and its device |
CN107066791A (en) * | 2016-12-19 | 2017-08-18 | 银江股份有限公司 | A kind of aided disease diagnosis method based on patient's assay |
CN108630312A (en) * | 2018-05-11 | 2018-10-09 | 北京诺道认知医学科技有限公司 | A kind of hypertension diagnosis rule base automatic generation method and device |
CN108877905A (en) * | 2018-06-12 | 2018-11-23 | 中南大学 | A kind of medical amount prediction technique of the hospital outpatient based on Xgboost frame |
CN109003679A (en) * | 2018-06-28 | 2018-12-14 | 众安信息技术服务有限公司 | A kind of cerebrovascular hemorrhage and ischemic prediction technique and device |
CN109524108A (en) * | 2018-11-21 | 2019-03-26 | 上海依智医疗技术有限公司 | A kind of method for building up and device of inquiry model |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110797121A (en) * | 2019-10-29 | 2020-02-14 | 浪潮天元通信信息系统有限公司 | Remote intelligent health analysis system and method based on Internet of things |
CN110942180B (en) * | 2019-11-12 | 2023-07-04 | 广州泽沐信息科技有限责任公司 | Industrial design matching service side prediction method based on xgboost algorithm |
CN110853760A (en) * | 2019-11-12 | 2020-02-28 | 好人生(上海)健康科技有限公司 | Interactive system for providing health guidance based on disease diagnosis |
CN110942180A (en) * | 2019-11-12 | 2020-03-31 | 广州泽沐信息科技有限责任公司 | Industrial design matching service party prediction method based on xgboost algorithm |
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 |
US12014284B2 (en) | 2019-12-27 | 2024-06-18 | Industrial Technology Research Institute | Question-answering learning method and question-answering learning system using the same and computer program product thereof |
CN111428930A (en) * | 2020-03-24 | 2020-07-17 | 中电药明数据科技(成都)有限公司 | GBDT-based medicine patient using number prediction method and system |
CN111599489A (en) * | 2020-05-19 | 2020-08-28 | 万达信息股份有限公司 | Disease information acquisition method, terminal equipment and storage medium |
CN111833997A (en) * | 2020-07-16 | 2020-10-27 | 平安科技(深圳)有限公司 | Doctor allocation method and device based on risk prediction and computer equipment |
CN112102955A (en) * | 2020-09-07 | 2020-12-18 | 武汉科瓴智能科技有限公司 | Patient disease prediction control system and method based on Gaussian mixture model |
CN112102955B (en) * | 2020-09-07 | 2024-03-15 | 武汉科瓴智能科技有限公司 | Patient disease prediction control system and method based on Gaussian mixture model |
CN113140314A (en) * | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Medical science popularization system, method and server |
CN112786194A (en) * | 2021-01-28 | 2021-05-11 | 北京一脉阳光医学信息技术有限公司 | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence |
CN113057589A (en) * | 2021-03-17 | 2021-07-02 | 上海电气集团股份有限公司 | Method and system for predicting organ failure infection diseases and training prediction model |
WO2022267678A1 (en) * | 2021-06-23 | 2022-12-29 | 康键信息技术(深圳)有限公司 | Video consultation method and apparatus, device and storage medium |
CN113555118B (en) * | 2021-07-26 | 2023-03-31 | 内蒙古自治区人民医院 | Method and device for predicting disease degree, electronic equipment and storage medium |
CN113555118A (en) * | 2021-07-26 | 2021-10-26 | 内蒙古自治区人民医院 | Method and device for predicting disease degree, electronic equipment and storage medium |
CN113469469A (en) * | 2021-09-02 | 2021-10-01 | 杭州华网信息技术有限公司 | Student physical ability score prediction method based on sectional loss function |
CN113724867A (en) * | 2021-11-03 | 2021-11-30 | 北京大学第三医院(北京大学第三临床医学院) | Prompting system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110111886A (en) | A kind of intelligent interrogation system and method based on XGBoost disease forecasting | |
US11664097B2 (en) | Healthcare information technology system for predicting or preventing readmissions | |
CN110111888A (en) | A kind of XGBoost disease probability forecasting method, system and storage medium | |
US7917377B2 (en) | Patient data mining for automated compliance | |
US6450956B1 (en) | System and method for treatment and outcome measurement analysis | |
US6317700B1 (en) | Computational method and system to perform empirical induction | |
EP3895178A1 (en) | System and method for providing health information | |
US6230142B1 (en) | Health care data manipulation and analysis system | |
US20110295622A1 (en) | Healthcare Information Technology System for Predicting or Preventing Readmissions | |
Chen et al. | A parallel patient treatment time prediction algorithm and its applications in hospital queuing-recommendation in a big data environment | |
EP0917078A1 (en) | Disease management method and system | |
US20210151140A1 (en) | Event Data Modelling | |
KR20200022113A (en) | Oriental medicine prescription and health coordinator service system and method | |
US20210089965A1 (en) | Data Conversion/Symptom Scoring | |
US11537888B2 (en) | Systems and methods for predicting pain level | |
CN115858886A (en) | Data processing method, device, equipment and readable storage medium | |
CN114334179A (en) | Digital medical management method and system | |
CN113161016A (en) | Intelligent medical service system, method and storage medium | |
CN117216322A (en) | Method, device, equipment and storage medium for generating electronic medical record | |
US20230316095A1 (en) | Systems and methods for automated scribes based on knowledge graphs of clinical information | |
Bohada et al. | Automatic generation of clinical algorithms within the state-decision-action model | |
WO2023217737A1 (en) | Health data enrichment for improved medical diagnostics | |
CN116469534A (en) | Hospital number calling management system and method thereof | |
Prakash et al. | Random forest regression with hyper parameter tuning for medical insurance premium prediction | |
US20230317222A1 (en) | Machine learning-based electronic health record prediction |
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: 20190809 |
|
RJ01 | Rejection of invention patent application after publication |