CN108447533A - A kind of Multifunctional smart medical system - Google Patents
A kind of Multifunctional smart medical system Download PDFInfo
- Publication number
- CN108447533A CN108447533A CN201810273867.2A CN201810273867A CN108447533A CN 108447533 A CN108447533 A CN 108447533A CN 201810273867 A CN201810273867 A CN 201810273867A CN 108447533 A CN108447533 A CN 108447533A
- Authority
- CN
- China
- Prior art keywords
- module
- data processing
- data
- sample
- smart medical
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
-
- 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)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
A kind of Multifunctional smart medical system, the Multifunctional smart medical system includes sensing layer, the sensing layer is connect with data interface tier, then data interface tier is connected with application layer, the application layer finally connects terminal system, data processing centre is equipped in the wherein described terminal system, human-computer interaction module, card reader module, it registers print module, bank note payment module, diagnosis report print module, Unionpay's payment module, UPS, indicating lamp module, voice output module and camera, wherein data processing centre has machine learning module, the machine learning module uses increment Bayesian learning function, all modules in the terminal system are connect with data processing centre respectively, it enters data into the minds of Data processing.One knows from experience to patient's memory service, while taking incremental model training method, and the disease intelligent diagnostics model with high generalization ability is established in intelligence learning.
Description
Technical field
The invention belongs to apparatus fields, and in particular to a kind of medical system is cured more particularly to a kind of function wisdom
Treatment system.
Background technology
Medical Multifunction self aid intelligent terminal is the important front end Intellisense unit of intelligent medical treatment, is practice on intelligent hospital
Front end equipment and with high in technological content in the unit of user's direct interaction and health industry, demand it is big, it is intelligent with
Hommization requires high product, is in the particularly significant link of industrial chain.To solving hospital " three length one are short " phenomenon, improving medical treatment clothes
Quality of being engaged in has important work with efficiency of service, reduction hospital services cost, improvement image of hospitals, raising patient satisfaction etc.
With.
Currently, hospital in the applying for card of outpatient service, register, charge, take most of links of the work such as survey report in certain journey
Manual service is also relied on degree, leads to that duplication of labour phenomenon is serious, working efficiency is low low with service satisfaction.Intelligence
The input of energy self-help terminal equipment, reduces the workload of artificial window banging personnel, makes equipment liberation artificial, provides safe and reliable
7*24 hour real time services, save cost of labor, improve efficiency of service.Meanwhile intelligent self-service terminal device provides to the user
Intelligentized Self-Service provides approach.Self-help serving system by sensitive touch screen interface and good human-computer interaction,
User oriented provides a kind of more free convenient method of service.Medical industry self-aided terminal is in Optimizing Out-patient flow, solution
Play an important roll on the problems such as the difficulty of getting medical service.Meanwhile can be lined up to avoid flocking together, it realizes the function of patient's shunting, high trouble is provided
Total satisfactory grade of the person to medical services.
With the continuous development of Hospital Informatization, computer technology is applied in industry of medical care in occupation of very
Consequence, hospital self-service terminal are own through becoming the essential infrastructure of hospital.The benefit of hospital self-service terminal has very
It is more, it is registered using hospital self-service registration machine, self-service reservation is registered, self-help charging is mutually tied with the multiple means such as manually register, pay the fees
The pressure that the artificial window of hospital registers, pays the fees can be effectively relieved in the mode of conjunction；The queuing during patient sees a doctor can be reduced, entirely
Face promotes hospital outpatient efficiency, provides more high-quality for medical patient and easily services；It is illegally falling in number problem using doctor
It protects card or my effective identity certificate does the mode of medical card, utmostly inhibit the illegal activities of " fall number "；Solving patient
The when of checking result of laboratory test is taken to ransack trouble, reveal in the problems of patient privacy, that improves patient takes single-action rate, and effective
Protect the privacy of patient.
With the rapid development of the technologies such as data mining, machine learning and pattern-recognition, hospital self-service terminal is not only
Only conduct is simply registered, payment tool exists, and can be completed such as intelligent medical diagnosis, medical image processing and machine vision
The smart machine of equal operations.Wherein, medical diagnosis be the main field that is benefited from data mining and machine learning techniques it
One.Many sorting techniques such as decision trees, most close to kernel method, all oneself certain success is achieved in the field.As hospital
The supplement of self-aided terminal service and extension, intelligent self-service hospital registration system are directed to the problem of being found in existing self-service machine use and newly need
It asks, among medical intelligent diagnostics are introduced Self-Service, illness description is provided for patient, section office are recommended and the work(such as expert info
Energy.It solves patient's medical treatment to feel uncertain, sufferer diagnosis and treatment is given and are utmostly facilitated.
Machine learning is to study the science for how improving computer own system using experience, it can actively study and
Analysis data information simultaneously makes high-precision intelligent decision from sample variable, so being obtained in medical intelligent diagnostics model
Extensive research and application.Model-naive Bayesian becomes the weight for the treatment of classification task with its good robustness and prediction effect
Want model.Scholar Gong Xiujun et al. has carried out detailed demonstration to the incremental learning based on bayesian theory, and gives complete
Increment Bayesian Classification Model.Although increment Bayesian Classification Model can solve the sample on the data set that classification balances very well
Incremental learning problem.But in applying, which faces 2 problems.First, the model there is no to emerging classification or
Feature increment gives description.Second, in Nonblanced training sets, grader cannot identify the classification representated by a few sample.Therefore it is right
Existing Bayes's incremental model makes optimization and adjustment, adapts to practical application scene, could establish the disease with high generalization ability
Sick intelligent diagnostics model.
Invention content
The object of the present invention is to provide a kind of intelligent hospital self-aided terminal, integrated hospital applies for card, registers, paying the fees, supplementing with money,
Under the premise of printing the conventional funcs such as survey report, real-name authentication and guarantor's certification, monitoring, gate inhibition's alarm, intelligence are realized
The functions such as medical, individual health data intellectual analysis.It is especially examined with intelligence point, laboratory test report is understood, online doctor seeks advice from, hospital
Doctor's inquiry, the inquiry of periphery trade company of hospital, hospital's geographical location navigation, the navigation of Yuan Nei section office, disease inquiry, drug use, are anxious
More hommization " one-stop " information services such as flow guidance, health information report are rescued, realizes and is controlled from uncomfortable to completion
It treats, by the function of machine learning, can also realize intelligent diagnostics patient disease, instruct patient assessment, incremental model is taken to instruct
Practice method, realizes the timely correction and optimization of disaggregated model.In use, the performance of control adjustment model prediction, enhances and builds
The accuracy and reasonability of view.
In order to achieve the goal above, the solution of the present invention is：
A kind of Multifunctional smart medical system, the Multifunctional smart medical system includes sensing layer, the sensing layer with
Data interface tier connects, and then data interface tier is connected with application layer, and the application layer finally connects terminal system, wherein described
In terminal system be equipped with data processing centre, human-computer interaction module, card reader module, print module of registering, bank note payment module,
Diagnosis report print module, Unionpay's payment module, UPS, indicating lamp module, voice output module and camera, wherein at data
Reason center has machine learning module, and the machine learning module uses increment Bayesian learning function, in the terminal system
All modules connect respectively with data processing centre, enter data into the minds of Data processing.
Further, the sensing layer be equipped with HIS medical informations module, EMR electronic health records module, LIS inspection modules,
RIS checks module.
Further, the data interface tier is equipped with sufferer information interface, clinical data interface, inspection information is examined to connect
Mouth, information for hospital interface.
Further, the application layer be equipped with health analysis module, laboratory test report solution read through model, recharging and paying module,
Section office's navigation module, expert info enquiry module, report print module.
Terminal includes that hardware components are formed with software section two parts.Hardware components include：Industrial personal computer, touch-control all-in-one machine,
Card reader module, printer, Certification of Second Generation module, camera, indicator light, gate inhibition, alarm control module, Unionpay's POS modules, sound
Sound, timed power on/off module, casing, wire rod open the light etc..It can support such as self-help registration, China second-generation identity card reading, electricity
Sub- case history printing, analysis report and survey report printing, recharging by cash are paid the fees, Unionpay's POS machine is transferred accounts payment, medical card and medical insurance
Block the functions such as reading, camera head monitor, timed power on/off, power supply.System is based on C/B/S frameworks, including：System function module is set
Meter, class library, database design three parts.System function module is divided into clinic system and in hospital system two parts.Outpatient service system
System major function：It is self-service the functions such as to handle medical card, prestore, pay the fees, preengaging, inquiring, printing；The major function of system in hospital：
The functions such as advance payment in hospital, day list print, hospitalization cost inquiry；And intelligentized service function：Such as personal health analysis, change
Test report deciphering etc..Class library, which is divided into, completes the visual user object designs that application program is exchanged with user-to-user information, with
Encapsulate and complete the Class User Object design of certain service logic.Database design includes data base normalization design, concept knot
Structure designs and Logic Structure Design.
Further, the data processing centre (5) carries out machine learning using increment Bayesian learning, will be in sample
New category and the obtained parameter of new feature be added in Bayesian model parameter, the distributed number of sample of all categories calculates
Cost matrix classifies to increment collection using "current" model, obtains all samples by mistake point and forms set, by mistake point set
Middle sample carries out ascending sort by its classification quantity present in training set, takes out first sample after ascending order
It practises, updates Bayesian model, then, update cost matrix, then will imitate originally to concentrate from increment and delete.This process is repeated, directly
It is that empty or not new error sample generates to increment collection.It makes full use of each section office of hospital to go to a doctor data, incremental model is taken to instruct
Practice method, realizes the timely correction and optimization of disaggregated model, realize intelligent diagnostics patient disease, instruct patient assessment so that from
Terminal more hommization is helped, facility is provided for patient.Simplify service procedure, reduce medical personnel's burden, save labour turnover,
The effect of working efficiency is improved, Intelligent Terminal degree is promoted.
Advantage of the present invention is：Integrated hospital applies for card, registers, paying the fees, supplementing with money, printing the premises of the conventional funcs such as survey report
Under, realize the work(such as real-name authentication and guarantor's certification, monitoring, gate inhibition's alarm, intelligent medical, individual health data intellectual analysis
Energy.Especially divided with intelligence and examines, laboratory test report deciphering, online doctor consulting, hospital doctor inquiry, the inquiry of periphery trade company of hospital, cures
The navigation of institute geographical location, the navigation of Yuan Nei section office, disease inquiry, drug use, first aid procedure guidance, health information are reported etc. more
Hommization " one-stop " information service, realize from it is uncomfortable to complete treatment.
Intelligent Service.Self-supporting medical terminal on the basis of people-oriented interaction, will according to patient's personal health archives with
And Data Centre in Hospital data realize intelligent medical diagnosis and analyze, is medical according to hospital admission history log data offer intelligence
Equal intelligences, personalized service.Intelligent terminal by as hospital, section office, doctor tie, patient is point-to-point with doctor
Docking is got up, and realizes the intelligent Service of " patient-centered health care ".
Incremental model training method is taken, realizes the timely correction and optimization of disaggregated model.In use, control adjustment mould
The performance of type prediction, enhances the accuracy and reasonability of suggestion.In addition, the new data of going to a doctor that intelligent hospital guide is obtained, also for
Hospital acquires valuable data, to further appreciate that patient profiles, preferably improves service and provides new approaches.
Description of the drawings
Fig. 1 is the structural diagram of the present invention, wherein：
1, sensing layer, 2, data interface tier, 3, application layer, 4, terminal system, 5, data processing centre, 6, human-computer interaction mould
Block, 7, card reader module, 8, print module of registering, 9, bank note payment module, 10, diagnosis report print module, 11, Unionpay's payment
Module, 12, UPS, 13, indicating lamp module, 14, voice output module, 15, HIS medical information modules, 16, EMR electronic health record moulds
Block, 17, LIS inspection modules, 18, RIS check module, 19, sufferer information interface, 20, clinical data interface, 21, examine and check
Information interface, 22, information for hospital interface, 23, health analysis module, 24, laboratory test report solution read through model, 25, recharging and paying module,
26, section office's navigation module, 27, expert info enquiry module, 28, report print module, 29, camera.
Specific implementation mode
The present invention is described further in conjunction with the embodiments below by way of attached drawing.
A kind of Multifunctional smart medical system, the Multifunctional smart medical system include sensing layer 1, the sensing layer 1
It is connect with data interface tier 2, then data interface tier 2 is connected with application layer 3, and the application layer finally connects terminal system 4,
Described in data processing centre 5, human-computer interaction module 6, card reader module 7, register print module 8, paper are equipped in terminal system 4
Coin payment module 9, diagnosis report print module 10, Unionpay's payment module 11, UPS12, indicating lamp module 13, voice output module
14 and camera 29, there is machine learning module, the machine learning module to use increment Bayes for wherein data processing centre 5
Learning functionality, all modules in the terminal system 4 connect with data processing centre 5, enter data at data respectively
In reason center 5.
The sensing layer 1 is equipped with HIS medical informations module 15, EMR electronic health records module 16, LIS inspection modules 17, RIS
Check module 18.
The data interface tier 2 be equipped with sufferer information interface 19, clinical data interface 20, examine check information interface 21,
Information for hospital interface 22.
The application layer 3 is equipped with health analysis module 23, laboratory test report solution read through model 24, recharging and paying module 25, section
Room navigation module 26, expert info enquiry module 27, report print module 28.
Based on Bayesian Estimation method, when to carrying new category mark and new feature in sample, the parameter in learning process
Estimation is proved with Modifying model formula.And give the mathematical expression of modification method.Towards category field and property field
Habit can be divided into following three kinds of situations.
(1) category field
The major reason that the sample of new category occurs often caused by the sample of acquisition feature distribution compared with true
The feature distribution of sample space wants sparse.New combination has been carried out by the feature value in existing property field and has represented new class
Not.To occur being denoted as with the sample of new category mark：And ym+1∈Y.First by ym+1It is added
To among the possible value of classification, and on the basis of original model, increase corresponding new parameter p (Y=ym+1) and p (xk|
ym+1), parameter Estimation then is carried out to it.
Due to having learnt new sample, the other parameters p (Y=y of modelm+1) and p (xk|ym+1) also to be repaiied accordingly
Just.For increasing parameter p (Y=y newlym+1) be estimated as follows.
It at the same time, should be to the p of other in model (Y=yi) parameter is modified, such as formula 2.
It hereafter, also will be to new parameterEstimated such as formula 3.
So that otherP (xk|ym+1) parameter is able to correct such as formula 4.
So far, the mathematical expression such as formula 5 for providing complete Class increment corrected parameter, to the sample with new category, study
Process be exactly to add new parameter to original model, and it is estimated, then the process that other relevant parameters are modified.
(2) property field
New characteristic dimension is introduced also to be necessary under many application scenarios.Such as facial characteristics not only with illumination, court
To related with expression etc., also growth or aging can occur with the age.But as long as increasing the characteristic dimension of description sample,
So that the problem of script linearly inseparable, conversion was for linear separability.In the case of category field is constant, by appearance with new special
The sample of sign is denoted asAnd yp∈ Y remember Sl+1Possible value number is tieed up for l+1.Due to new special
The introducing of sign need to increase m*S in original modell+1A new parameter p (xj+1|yi), and parameter Estimation, such as formula first are carried out to it
Shown in 6.
The mathematical expression such as formula 7 of complete characterization increment corrected parameter can be obtained.
(3) category field and property field
In increasingly complex situation, above two problem is simultaneous.It is of the same race especially in terms of disease identification
Disease can embody new symptom with the quick variation of virus, make a variation out if H7N1 viruses are in the short several months as many as 8 kinds.Newly
Disease be also to occur with the variation of human habitat.The new samples of appearance are denoted as
And yp∈ Y remember Sl+1Possible value number is tieed up for l+1.The expansion of classification and characteristic information need to increase in original model into three
Kind new parameter p (Y=ym+1)、p(xl+1|yi) and p (xi|ym+1).Parameter Estimation and amendment are divided into two parts first to ignore
The parameter that new feature introduces, is only considered as Class increment by problem.Learnt for new category knowledge, and to other parameters into
Row is corrected.Process is as shown in Equation 8.
The mathematic(al) representation (9) of complete characterization and Class increment corrected parameter can be obtained by formula (8).
Nicety of grading (accuracy) is the whole evaluation showed on test set grader, is indicated with formula 10,
Middle f (x) represents grader, and y indicates the concrete class of sample x, and I (z) is known as indicative function, and as f (x)=y, I values take 1,
Other situations I values are 0.NtestFor the sum of sample in test set.And recall rate (recall) is then grader to each mesh
Mark the evaluation such as formula 11 of the identification situation of classification, wherein count (yi) classification is represented in test set as yiTotal sample number, y 'iFor
Prediction of the grader to x, and yiFor the concrete class of sample x.
From the perspective of risk of policy making, traditional Bayes classifier is based on maximizing posterior probability progress decision,
Matter is equivalent to minimize risk in the case where 0-1 loses.This decision assumes that the risk of all erroneous decisions is all identical.Consider
To the disequilibrium of data set sample size, 0-1 losses are clearly unreasonable.Therefore default mistake divides cost function such as formula 12.Its
Middle count (yi) indicate that classification is y in current training setiNumber of samples, 0 ＜ α ＜ 1 are as a kind of punishment to decision error
Parameter.As α ＜ 0.5, reflects and the few classification of quantity in training set is predicted to be classification more than quantity, cost is more
It is high.So that the decision classification few to quantity focuses more on.
And then according to Bayesian decision theory, Risk Calculation at this time becomes in order to as shown in Equation 13.And decision is also by maximum
Change posterior probability to become to minimize risk.Therefore decision function is also accordingly adjusted to shown in formula 14.
R(yi| x)=∑ P (yj|x)*cost(yj,yi) (13)
F (x)=argminR (yi|x) (14)
Before carrying out incremental learning, first, according to the distributed number of current sample of all categories, cost matrix is calculated, is made
Classified to increment collection with "current" model, obtains all samples by mistake point and form set.In order to flat as possible in the training stage
Weigh sample size of all categories, the category information for taking preference learning a few sample to represent, therefore sample in mistake point set is pressed its class
The quantity present in training set does not carry out ascending sort.It takes out first sample after ascending order to be learnt, updates Bayes
Model.Then, cost matrix is updated.To imitate again, this concentrates deletion from increment.Repeat this process, until increment collection be it is empty or
Not new error sample generates.
Claims (5)
1. a kind of Multifunctional smart medical system, it is characterised in that：The Multifunctional smart medical system includes sensing layer (1),
The sensing layer (1) connect with data interface tier (2), and then data interface tier (2) is connected with application layer (3), the application layer
Finally connection terminal system (4), wherein in the terminal system (4) be equipped with data processing centre (5), human-computer interaction module (6),
Card reader module (7), print module of registering (8), bank note payment module (9), diagnosis report print module (10), Unionpay pay mould
Block (11), UPS (12), indicating lamp module (13), voice output module (14) and camera (29), wherein data processing centre
(5) there is machine learning module, the machine learning module uses increment Bayesian learning function, in the terminal system (4)
All modules connect respectively with data processing centre (5), enter data into data processing centre (5).
2. a kind of Multifunctional smart medical system according to claim 1, it is characterised in that：The sensing layer (1) is equipped with
HIS medical informations module (15), EMR electronic health records module (16), LIS inspection modules (17), RIS check module (18).
3. a kind of Multifunctional smart medical system according to claim 1, it is characterised in that：The data interface tier (2)
Equipped with sufferer information interface (19), clinical data interface (20), examine inspection information interface (21), information for hospital interface (22).
4. a kind of Multifunctional smart medical system according to claim 1, it is characterised in that：The application layer (3)
Equipped with health analysis module (23), laboratory test report solution read through model (24), recharging and paying module (25), section office's navigation module (26), specially
Family's information inquiry module (27), report print module (28).
5. a kind of Multifunctional smart medical system according to claim 1, it is characterised in that：The data processing centre
(5) machine learning is carried out using increment Bayesian learning, by sample new category and the obtained parameter of new feature be added to
In Bayesian model parameter, by the distributed number of sample of all categories, cost matrix is calculated, increment collection is carried out using "current" model
Classification obtains all samples by mistake point and forms set, by sample in mistake point set by its classification number present in training set
Amount carries out ascending sort, takes out first sample after ascending order and is learnt, updates Bayesian model, then, updates cost square
Battle array, then will imitate originally to concentrate from increment and delete.This process is repeated, is produced until increment collection is empty or not new error sample
It is raw.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810273867.2A CN108447533A (en) | 2018-03-29 | 2018-03-29 | A kind of Multifunctional smart medical system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810273867.2A CN108447533A (en) | 2018-03-29 | 2018-03-29 | A kind of Multifunctional smart medical system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108447533A true CN108447533A (en) | 2018-08-24 |
Family
ID=63197815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810273867.2A Pending CN108447533A (en) | 2018-03-29 | 2018-03-29 | A kind of Multifunctional smart medical system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108447533A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102965A (en) * | 2020-09-15 | 2020-12-18 | 深圳市联影医疗数据服务有限公司 | Medical information management system based on clinical assistance and regional collaboration |
| CN112582052A (en) * | 2020-11-27 | 2021-03-30 | 云南盛时迪安生物科技有限公司 | Hierarchical diagnosis and treatment system |
| CN113986890A (en) * | 2021-12-30 | 2022-01-28 | 四川华迪信息技术有限公司 | Joint hospital data migration method and system based on few-sample model learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778020A (en) * | 2016-12-31 | 2017-05-31 | 江苏顺源集团有限公司 | A kind of medical ward intelligent terminal based on technology of Internet of things |
| CN107644675A (en) * | 2017-09-19 | 2018-01-30 | 成都思杰聚典科技有限公司 | Medical treatment information exchange display system |
| CN207133909U (en) * | 2017-01-26 | 2018-03-23 | 浙江建达科技股份有限公司 | Intelligent medical treatment double screen self-service terminal |
-
2018
- 2018-03-29 CN CN201810273867.2A patent/CN108447533A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778020A (en) * | 2016-12-31 | 2017-05-31 | 江苏顺源集团有限公司 | A kind of medical ward intelligent terminal based on technology of Internet of things |
| CN207133909U (en) * | 2017-01-26 | 2018-03-23 | 浙江建达科技股份有限公司 | Intelligent medical treatment double screen self-service terminal |
| CN107644675A (en) * | 2017-09-19 | 2018-01-30 | 成都思杰聚典科技有限公司 | Medical treatment information exchange display system |
Non-Patent Citations (1)
| Title |
|---|
| 李杨: "基于增量贝叶斯模型的自助挂号系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102965A (en) * | 2020-09-15 | 2020-12-18 | 深圳市联影医疗数据服务有限公司 | Medical information management system based on clinical assistance and regional collaboration |
| CN112582052A (en) * | 2020-11-27 | 2021-03-30 | 云南盛时迪安生物科技有限公司 | Hierarchical diagnosis and treatment system |
| CN113986890A (en) * | 2021-12-30 | 2022-01-28 | 四川华迪信息技术有限公司 | Joint hospital data migration method and system based on few-sample model learning |
| CN113986890B (en) * | 2021-12-30 | 2022-03-11 | 四川华迪信息技术有限公司 | Joint hospital data migration method and system based on few-sample model learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12002553B2 (en) | Systems and methods for designing clinical trials | |
| CN105528526B (en) | A kind of life cycle dynamical health management system excavated based on traditional Chinese medicine succession with big data | |
| Liou et al. | Detecting hospital fraud and claim abuse through diabetic outpatient services | |
| CN103942432B (en) | Wisdom is health management system arranged | |
| Feeley et al. | A method for defining value in healthcare using cancer care as a model | |
| CN105260588A (en) | Health protection robot system and data processing method thereof | |
| CN108305690A (en) | The nervous system disease point examines the system for distribution of out-patient department of method and the nervous system disease | |
| CN109636632A (en) | Settlement of insurance claim method, apparatus, equipment and storage medium based on machine learning | |
| CN108447533A (en) | A kind of Multifunctional smart medical system | |
| US20140100878A1 (en) | System and method of integrating mobile medical data into a database centric analytical process, and clinical workflow | |
| Lin et al. | Predicting wait times in pediatric ophthalmology outpatient clinic using machine learning | |
| CN114117226A (en) | Product recommendation method, system, device and medium | |
| Connor et al. | The Gold Coast integrated care model | |
| Akimov et al. | Determination of significant behavioral parameters on COVID-19 diagnosis by artificial Neural Networks modeling | |
| Vitalari | Prospects for the future of the us healthcare industry: a speculative analysis | |
| US8762171B2 (en) | Medical resource estimation and simulation system | |
| Wang et al. | Deep learning models to predict pediatric asthma emergency department visits | |
| Seiber | Physician code creep: evidence in Medicaid and State Employee Health Insurance billing | |
| Espinosa-González et al. | The role of the state in financing and regulating primary care in Europe: a taxonomy | |
| Sinha et al. | Application of big data analytics and Internet of Medical Things (IoMT) in healthcare with view of explainable artificial intelligence: A survey | |
| CN112837781B (en) | Pharmacy management system and method based on hospital prescription information | |
| Shahin et al. | Deploying deep convolutional neural network to the battle against cancer: Towards flexible healthcare systems | |
| US20230317260A1 (en) | Systems and Methods for Medical Claims Analytics and Processing Support | |
| CN110168659A (en) | For improving clinical effectiveness and reducing the nursing always nursing the CNA of expense and guiding | |
| WO2020087970A1 (en) | Neural network-based disease type score verification method and computing device |
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: 20180824 |