CN107103201A - Generation method, device and the medical path air navigation aid of medical guidance path - Google Patents
Generation method, device and the medical path air navigation aid of medical guidance path Download PDFInfo
- Publication number
- CN107103201A CN107103201A CN201710325176.8A CN201710325176A CN107103201A CN 107103201 A CN107103201 A CN 107103201A CN 201710325176 A CN201710325176 A CN 201710325176A CN 107103201 A CN107103201 A CN 107103201A
- Authority
- CN
- China
- Prior art keywords
- state
- illness
- current
- medical
- action
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000009471 action Effects 0.000 claims abstract description 279
- 238000003745 diagnosis Methods 0.000 claims abstract description 40
- 230000000875 corresponding effect Effects 0.000 claims description 152
- 201000010099 disease Diseases 0.000 claims description 66
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 66
- 230000000694 effects Effects 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 description 47
- 210000000265 leukocyte Anatomy 0.000 description 18
- 238000003860 storage Methods 0.000 description 11
- 238000004820 blood count Methods 0.000 description 9
- 238000001574 biopsy Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 208000024891 symptom Diseases 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000998 lymphohematopoietic effect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000001575 pathological effect Effects 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 206010011224 Cough Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000003340 mental effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 206010067671 Disease complication Diseases 0.000 description 1
- 206010028813 Nausea Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000036528 appetite Effects 0.000 description 1
- 235000019789 appetite Nutrition 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 235000008216 herbs Nutrition 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007721 medicinal effect Effects 0.000 description 1
- 230000037323 metabolic rate Effects 0.000 description 1
- 230000008693 nausea Effects 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000035485 pulse pressure Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 230000009452 underexpressoin Effects 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of generation method of medical guidance path, device and medical path air navigation aid.Wherein, the generation method of medical guidance path includes：Obtain the description of each state of an illness in history case history sample and each action scheme associated with the description of each state of an illness；Dependence between each state of an illness description and each action scheme is determined according to the history case history sample；Medical navigation model is built according to the dependence, and medical guidance path is determined according to the medical navigation model.Technical scheme, the diagnostic experiences of medical worker during the medical diagnosis described in history case sample can effectively be summed up, and collect and describe corresponding each historical diagnostic path with each state of an illness, construct medical navigation model, and medical guidance path is determined according to medical navigation model, medical experience can not only be sorted out from history case history sample, moreover it is possible to provide medical guidance path assisted medical diagnosis, it is real to realize the shared of medical experience, promote medical advance.
Description
Technical field
The present embodiments relate to technical field of data processing, more particularly to a kind of generation method of medical guidance path,
Device and medical path air navigation aid.
Background technology
Case history is medical worker to the generation of patient disease, develops, lapses to, and the medical activity such as is checked, diagnosed, treated
The writing record that process is made.Case history is both the summary of clinical practice work, is to explore disease rule and processing medical science dispute again
Legal basis, be country treasure.
In clinical medicine, case history is effectively arranged, doctor's clinical medicine experience is therefrom excavated, has to medical advance great
Meaning.In actual diagnosis and treatment, there is the otherness in terms of stock of knowledge and clinical experience in itself due to medical worker, often not
Same medical worker is also not quite similar for same disease or the diagnostic mode of symptom and medication custom etc., and what is had produces effects
But taking effect for significantly having is little.And by organizing the carry out Couple herbs exchange of medical worker in the industry, not only need substantial amounts of people
Power material resources, and without real-time and universal sharing.Therefore, medical practice how is effectively sorted out from case history, is realized
Medical knowledge is shared to be particularly important.
The content of the invention
The embodiments of the invention provide a kind of generation method of medical guidance path, device and medical path air navigation aid,
Effectively to sort out medical experience from case history, the medical guidance path of generation realizes the shared of medical experience.
In a first aspect, the embodiments of the invention provide a kind of generation method of medical guidance path, this method includes：
Obtain the description of each state of an illness in history case history sample and each action scheme associated with the description of each state of an illness；
Dependence between each state of an illness description and each action scheme is determined according to the history case history sample；
Medical navigation model is built according to the dependence, and medical treatment navigation road is determined according to the medical navigation model
Footpath.
Second aspect, the embodiment of the present invention additionally provides a kind of generating means of medical guidance path, and the device includes：
Sample acquisition module, for obtaining the description of each state of an illness in history case history sample and describing what is associated with each state of an illness
Each action scheme；
Dependence determining module, for determining each state of an illness description and each action side according to the history case history sample
Dependence between case；
Medical guidance path determining module, for building medical navigation model according to the dependence, and according to described
Medical navigation model determines medical guidance path.
The third aspect, the embodiment of the present invention provides a kind of medical path air navigation aid again, and this method includes：
Obtain the patient data of user's input；Wherein, the patient data includes the current state of an illness description of patient；
The medical navigation path set up using the generation method in the medical navigation path described in any embodiment of the present invention
The patient data currently inputted is handled, path navigation result corresponding with presently described patient data is exported and carries out
Display；Wherein, the path navigation result includes the corresponding action scheme of the state of an illness description current with patient or disease type.
Fourth aspect, the embodiments of the invention provide a kind of terminal, the terminal includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes the generation method of the medical guidance path described in any embodiment of the present invention.
5th aspect, the embodiment of the present invention provides a kind of computer-readable recording medium, is stored thereon with computer again
Program, realizes the generation method of the medical guidance path described in any embodiment of the present invention when the program is executed by processor.
The technical scheme of the embodiment of the present invention, by obtain each state of an illness in history case history sample description and with each state of an illness
Describe each action scheme of association, sum up the medical experience in each history case history sample, it is then determined that go out the description of each state of an illness with
Dependence between each action scheme, sums up examining for medical worker during the medical diagnosis described in history case sample
Cracked ends is tested, and is then built medical navigation model according to dependence, is collected and describe corresponding each historical diagnostic path with each state of an illness,
Medical navigation model is constructed, and then medical guidance path is determined according to medical navigation model, can be effectively from history case history
Clinical treatment experience is sorted out in sample, the problems such as existing medical experience exchange is wasted time and energy is solved, realizes well to doctor
The summary for the treatment of experience, and medical guidance path assisted medical diagnosis is provided, the shared of medical experience is really realized, promotes medical science to enter
Step.
Brief description of the drawings
In order to clearly illustrate the technical scheme of exemplary embodiment of the present, below to needed for description embodiment
The accompanying drawing to be used does a simple introduction.Obviously, the accompanying drawing introduced is a part of embodiment of the invention to be described
Accompanying drawing, rather than whole accompanying drawings, for those of ordinary skill in the art, on the premise of not paying creative work, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is a kind of flow chart of the generation method for medical guidance path that the embodiment of the present invention one is provided；
Fig. 2 is a kind of flow chart of the generation method for medical guidance path that the embodiment of the present invention two is provided；
Fig. 3 is a kind of structure chart of the generating means for medical guidance path that the embodiment of the present invention three is provided；
Fig. 4 is a kind of structural representation for terminal that the embodiment of the present invention four is provided.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
A kind of flow chart of the generation method for medical guidance path that Fig. 1 is provided by the embodiment of the present invention one, this method
It can be performed by the generating means of medical guidance path, the device can be realized by way of hardware and/or software, and one
As can be independent the configuration method of realizing the present embodiment in the server or with terminal and server.
As shown in figure 1, the method for the present embodiment is specifically included：
Each action side that S110, each state of an illness obtained in history case history sample are described and associated with each state of an illness description
Case.
Exemplarily, the state of an illness description may include it is following at least one：The essential information of patient, vital sign, symptom,
Laboratory indexes and inspection mark etc..Specifically, the essential information of patient may include that sex, age, job specification, family live
Location and income etc.；The vital sign of patient may include height, body weight, body temperature, pulse and blood pressure etc.；Patient's
Symptom may include the subjective description uncomfortable to patient, the natural language expressing such as available conversations in history case history sample, for example head
Bitterly, nausea, dizziness and poor appetite etc.；The laboratory indexes of patient may include that platelet count is relatively low, white blood cell count(WBC) is higher,
Blood sugar concentration is higher and Urine proteins count higher etc.；The inspection mark of patient may include Characteristics of electrocardiogram, EEG Characteristics,
X-ray shows that certain region has shade, color ultrasound to show that the low echo nodules in certain region, CT show that streak shade and PET show certain
Region local metabolic rate is higher etc..
Corresponding each action scheme is described with the state of an illness it can be appreciated that obtain more rich state of an illness description method or
Medical procedure.Whether action scheme specifically may include the problem of doctor questions closely patient, such as " cough ", or suggestion patient does
Chemical examination and inspection project (pathologic finding and image check etc.) etc..
It is understood that history case history sample includes hand-written papery version case history and electronic history case history etc..Go through
State of an illness description has been recorded in history case history sample and corresponding a kind of, two kinds or more of action scheme has been described with the state of an illness, and
Describe and describe corresponding diagnostic result with each state of an illness.Wherein, diagnostic result includes a kind of, two kinds or more of disease types.
For example, describing corresponding disease type with the state of an illness potentially includes a kind of disease, it is also possible to also including each as caused by the disease
Complication is planted, or patient inherently suffers from a variety of diseases.
In the present embodiment, obtain each state of an illness description in history case history sample and describe what is associated with each state of an illness
Each action scheme can be specifically each state of an illness description obtained respectively in each history case history sample and be described with each state of an illness
Each action scheme of association, i.e. in units of a history case history sample, decibel is obtained per each in a history case history sample
Each action scheme that the state of an illness is described and associated with each state of an illness description.
S120, according to the history case history sample determine that the dependence between each state of an illness description and each action scheme is closed
System.
In history case history sample, usual doctor can combine the current state of an illness description of patient, provide rational therapeutic scheme,
Can there is the action scheme of response, until doctor can provide diagnostic result.Accordingly, it would be desirable to set up each state of an illness description and each row
Dependence between dynamic scheme.State of an illness description also can increasingly be enriched with the increase of action scheme, also can to a certain extent
Increasingly doctor is conducive to provide diagnostic result.And once current state of an illness description enables to doctor to provide safe diagnosis knot
Really, then current state of an illness description is follow-up can not have the action scheme for being used for obtaining more rich state of an illness description again.Therefore history is sick
Go through in sample and there is initial state of an illness description, and the state of an illness description associated with follow-up action scheme.
Usually, in order to preferably be patient carry out diagnosis and treatment, same patient the state of an illness description and with the state of an illness description pair
The action scheme answered often is documented in in a history case history sample.And same patient the state of an illness description with action scheme it
Between often there are very big dependence.It therefore, it can determine each state of an illness description and each row according to each history case history sample
Dependence between dynamic scheme.Can be specifically that the content according to described in each case history sample determines same history case history sample
The dependence between the description of each state of an illness and each action scheme in this.Wherein, dependence is it is to be understood that the current state of an illness is retouched
State, the further state of an illness for describing the action scheme of corresponding next step with the current state of an illness and being obtained according to this action scheme is retouched
Incidence relation between stating.Dependence is set up it needs to be determined that the description of each state of an illness and associating between each action scheme
System.Include the state of an illness description that initial patient gives an oral account, each action scheme just gone during by diagnosis, until last obtain among these
Go out the state of an illness that doctor can be aided in make a diagnostic result description.
S130, medical navigation model is built according to the dependence, and medical treatment is determined according to the medical navigation model
Guidance path.
Medical navigation model is built according to dependence, each state of an illness description can be recorded by medical navigation model and each
Incidence relation between action scheme, effectively sums up in each history case history sample and examines medical experience.According to dependence structure
Building medical navigation model specifically may include：Obtain current state of an illness description；The history case history sample is traveled through according to the dependence
This, judges whether the action scheme associated with the current state of an illness description；If being associated in the presence of with the current state of an illness description
Action scheme, then obtain and described with the current state of an illness description and the target state of an illness corresponding with the action scheme, and general
The target state of an illness description is described as next level state of an illness of the current state of an illness description；The target state of an illness is being described to make
After new current state of an illness description, return and perform according to the dependence traversal history case history sample, judge whether to deposit
In the operation of the action scheme associated with the current state of an illness description, until new current state of an illness description does not associate the dynamic side of any row
Case；If in the absence of action scheme associate with the current state of an illness description, the state of an illness for recording different levels is described, and with pass
The connection levels state of an illness describes corresponding action scheme, constructs medical navigation model.
Medical guidance path can be understood as the follow-up action scheme related to the description of each state of an illness and diagnostic result.Can be with
Understand, may include to describe corresponding one or more guidance path with each state of an illness in medical navigation model, according to the doctor
Treat navigation model and determine medical guidance path, can be specifically that one is selected from medical navigation model according to the rule of setting
Or multiple corresponding diagnosis path is described as medical guidance path with the current state of an illness；Or can also be incited somebody to action according to the rule of setting
The medical guidance path of this in medical navigation model, which is ranked up, to be shown, and then chooses instruction to determine according to what user inputted
Medical guidance path.
In embodiments of the present invention, medical guidance path is determined according to the medical navigation model, specifically may include：According to
Each state of an illness describes corresponding current income and each lower floor's state of an illness describes corresponding future action value, determines each action scheme
Corresponding current action value；Determine current optimal action scheme as current target row according to the current action value
Dynamic scheme, and determine that the medical treatment in the medical navigation model is led based on each the current goal action scheme and targeted yield
Bit path.
The technical scheme of the present embodiment, by obtaining the description of each state of an illness in history case history sample and being described with each state of an illness
Each action scheme of association, sums up the medical experience in each history case history sample, it is then determined that going out each state of an illness description and each row
Dependence between dynamic scheme, sums up the diagnosis warp of medical worker during the medical diagnosis described in history case sample
Test, medical navigation model is then built according to dependence, collects and describes corresponding each historical diagnostic path with each state of an illness, is built
Go out medical navigation model, and then medical guidance path is determined according to medical navigation model, can be effectively from history case history sample
In sort out clinical treatment experience, solve the problems such as existing medical experience exchange is wasted time and energy, realize well to medical treatment warp
The summary tested, and medical guidance path assisted medical diagnosis is provided, the shared of medical experience is really realized, promotes medical advance.
Embodiment two
The flow chart of the generation method for a kind of medical guidance path that Fig. 2 is provided by the embodiment of the present invention two, such as Fig. 2 institutes
Show, the present embodiment is on the basis of above-described embodiment, and optional is described to build medical navigation model, bag according to the dependence
Include：Obtain current state of an illness description；The history case history sample is traveled through according to the dependence, judges whether to work as with described
The action scheme of preceding state of an illness description association；If in the presence of action scheme associate with the current state of an illness description, acquisition with it is described
Current state of an illness description and the target state of an illness corresponding with action scheme description, and using target state of an illness description described in
Next level state of an illness description of current state of an illness description；The target state of an illness is being described as after new current state of an illness description, returned
Receipt row travels through the history case history sample according to the dependence, judges whether to associate with the current state of an illness description
Action scheme operation, until new current state of an illness description does not associate any row and moves scheme；If being not present and the current disease
The action scheme of feelings description association, then record the state of an illness description of different levels, and describe corresponding with the association levels state of an illness
Action scheme, constructs medical navigation model.
It is further, described that medical treatment navigation is determined according to the medical navigation model on the basis of above-mentioned technical proposal
Path, it may include：Corresponding current income is described according to each state of an illness and each lower floor's state of an illness describes corresponding future action value,
Determine the corresponding current action value of each action scheme；Current optimal action side is determined according to the current action value
Case determines that the medical treatment is led as current goal action scheme, and based on each the current goal action scheme and targeted yield
Medical guidance path in model plane type.
Each action side that S210, each state of an illness obtained in history case history sample are described and associated with each state of an illness description
Case.
S220, according to the history case history sample determine that the dependence between each state of an illness description and each action scheme is closed
System.
S230, the current state of an illness description of acquisition.
Obtaining current state of an illness description includes：Receive the state of an illness description that user currently inputs.Exemplarily, user currently inputs
State of an illness description can be doctor according to the state of an illness description of the oral account input of patient or doctor according to before patient just
The current state of an illness description that doctor's record is got from the case sample of patient；It can also be doctor according to the oral account input of patient
State of an illness description has carried out state of an illness description after state of an illness inquiry etc., does not limit herein.It is understood that the current state of an illness
Description can describe the identical state of an illness that can also be with being got in case sample with the state of an illness described in history case history sample and describe
It is different.
S240, the history case history sample traveled through according to the dependence, judged whether and the current state of an illness
The action scheme of association is described, if performing S250；Otherwise S270 is performed.
Scheme is put according to state of an illness description and the action related to state of an illness description, each moment or each stage is capable of determining that
State of an illness description, determine the medical diagnosis path described in the history case history sample, sum up the description of each state of an illness and each action
Incidence relation between scheme and diagnostic result, you can sum up medical diagnosis experience, base is established to set up medical guidance path
Plinth.In the present embodiment, get after current state of an illness description, the history case history sample where current state of an illness description can be traveled through, sentenced
It is disconnected to whether there is the action scheme associated with the description of the current state of an illness, can effectively it comb out complete described in history case history sample
Diagnosis scheme, preferably sum up medical practice knowledge
If S250, in the presence of action scheme associate with the current state of an illness description, obtain and the current state of an illness description
And target state of an illness description corresponding with the action scheme, and described target state of an illness description as the current state of an illness
Next level state of an illness description.
Exemplarily, it will can be associated using the current state of an illness being originally taken description as root node with the description of the current state of an illness
Each action scheme as each of the root node connect side, each target state of an illness corresponding with each action scheme description determined
It is used as each leaf node of root node.I.e. each node is state of an illness description, and each line is action scheme.If leaf section
Point also means that after the corresponding state of an illness description of the leaf node without follow-up line, does not have follow-up action scheme.
This operation can be described by the current state of an illness, and the action scheme related to the description of the current state of an illness, it is determined that currently
Next level state of an illness description of state of an illness description.It is understood that there may be in different history case history samples same
The state of an illness is described, and it is probably identical or different action scheme to be described corresponding with the same state of an illness, and therefore, the current state of an illness is retouched
State the state of an illness description that there may be one or more next levels.
S260, after the target state of an illness being described as new current state of an illness description, return to execution S240.
In the present embodiment, in order to sum up medical scheme complete in history case history sample, to the disease of each level
Feelings description is required for performing same operation, that is, needs to judge whether also there is follow-up action side after the state of an illness is described
Case.Accordingly, it would be desirable to after the target state of an illness being described as new current state of an illness description, it is necessary to repeat according to state of an illness description and
Dependence between action scheme travels through the history case history sample where current state of an illness description, judges whether and current disease
The operation of the action scheme of feelings description association, to determine whether the description of the current state of an illness is that the state of an illness of last level is described.
Can progressively it be determined from the description of the current state of an illness according to the description of the current state of an illness and each action scheme using the above method
Go out the state of an illness description of last level, so as to sum up the medical diagnostic method of complete set, effectively summarize each history disease
The medical practice knowledge gone through in sample.
S270, the state of an illness description for recording different levels, and corresponding action scheme, structure are described with the association levels state of an illness
Build out medical navigation model.
Exemplarily, tree structure can be built according to the description of each state of an illness and each action scheme, and then by constructed tree
Shape structure is used as medical navigation model.Can be specifically that each node as the tree structure is described using each state of an illness, each
Action scheme is as the company side of the tree structure, then then initial state of an illness description, can close as root node according to root node
Join each action scheme determine the next level of root node the state of an illness description as root node leaf node, will with root node and respectively
The action scheme of child node association determines that the leaf node of leaf node connects side with it as even side, and so on, by
Step determines each node and even side, and being recorded in the tree structure, so that each in each history case history sample
The state of an illness describes to build complete tree structure with each action scheme.
S280, corresponding current income is described according to each state of an illness and each lower floor's state of an illness describes corresponding future action valency
Value, determines the corresponding current action value of each action scheme.
The state of an illness that current income is appreciated that to be arrived according to current collection is described, and has much assurance to provide diagnostic result.
During actual diagnosis, state of an illness description is abundanter may to be more conducive to providing diagnostic result, but is likely to increase as well state of an illness description
Diagnostic result is not had much affect afterwards.Do not point out what user's next step should do in view of current income, be to question closely
More symptoms, still allow patient to do a certain chemical examination or inspection.Therefore, work as to preferably determine that each action scheme is corresponding
Preceding action value, can comprehensively be considered with reference to whole diagnosis process, not only need to consider each state of an illness describe it is corresponding currently
Income, in addition it is also necessary to consider that the state of an illness describes corresponding each lower floor's state of an illness and describes corresponding future action value.It can such as build
One action cost function is used to guide the follow-up optimal course of action of doctor.Specifically, can be first according to the description pair of each state of an illness
The current income and each lower floor's state of an illness answered describe corresponding future action value, and construction action cost function is then based on institute
State action cost function and calculate the corresponding current action value of each action scheme.
Alternatively, it is described corresponding current income to be described according to each state of an illness and each lower floor's state of an illness describes corresponding following row
Dynamic value, construction action cost function, including：In record result, since the state of an illness description of lowermost layer, calculate successively and each
The state of an illness describes corresponding current action cost function；Wherein, if lower floor's state of an illness description is not present in the state of an illness description currently calculated,
Then determine to describe corresponding current revenue function with the state of an illness currently calculated according to the state of an illness description currently calculated, will currently calculate
State of an illness description the current action cost function of state of an illness description that currently calculates as described of the current revenue function；If
There is lower floor's state of an illness description in current state of an illness description, then each state of an illness is described to the future action of corresponding current income and action scheme
The addition of discounting of value, is used as the current action cost function of the state of an illness description currently calculated.Wherein, future action is worth
Discount can be next level state of an illness describe it is corresponding action value weighting.
Wherein, the state of an illness description of lowermost layer is designated as the state of an illness description of last level, is also last level leaf
Node.It should be noted that last level leaf node is also described subsequently without action scheme in the absence of lower floor's state of an illness.
In record result, since the state of an illness description of lowermost layer, calculate describe corresponding current action value letter with each state of an illness successively
Number, it can be understood as, since the leaf node of the lowermost layer for the tree that each state of an illness is described and each action scheme is constituted,
Current action value is calculated, and is traced back successively, the current action value of father node is calculated, until calculating the current of root node
Action value.
If lower floor's state of an illness description is not present in the state of an illness description currently calculated, it can be understood as the state of an illness description currently calculated
Subsequently without action scheme, last level leaf node of as current tree structure, then according to the state of an illness currently calculated
Description determines to describe corresponding current revenue function with the state of an illness currently calculated, you can to calculate the last of current tree structure
The current revenue function of one level leaf node, and the current action of the current revenue function as the leaf node is worth
Function.Similarly, if the state of an illness description currently calculated has lower floor's state of an illness description, it can be understood as the state of an illness currently calculated
Description have follow-up action scheme, be the tree structure root node or intermediate node, then can by the node it is corresponding work as
Preceding income is added with the discounting for future action value of action scheme, is used as the current action cost function of the node.
Exemplarily, the state of an illness that might as well obtain t describes st, and according to current collection to the state of an illness s is describedt, traversal should
The corresponding all possible action scheme a of state of an illness descriptiont, it is expressed asSo as to obtain next
The individual moment is that the t+1 moment all possible state of an illness describes st+1, similarly, st+1It can be expressed asWherein, n represents total kind number (quantity) of the state of an illness description at t+1 moment.
Assuming that at the t=1 moment, for s1In the presence of 4 kinds of action scheme a1, the state of an illness describes s1For " neck has lump ", this hour hand
To s1There is k kind action schemes a1, it is respectivelyFor example,For " whether coughing ", question closely patient there is provided
More symptoms；For " doing venous blood chemical examination, especially consult white blood cell count(WBC) ", it is proposed that lab work；" to have in neck
Lump, does biopsy, takes pathological section ", carry out pathologic finding；" to be PET in neck, looking at lump whether be metabolized partially
It is high ", carry out the image check of positron e mission computed tomography.The doctor now diagnosed can be from 4 kinds of action schemes
a1In select an execution.
If, taken action scheme in t=1 moment doctor suggestion patient" there is lump in neck, do biopsy, take disease
Reason section ", at the t=2 moment, biopsy report is completed, and the state of an illness describes s2Content can add, now s2Content may be
One of three kinds of situations below：For " neck has lump, and neck biopsy is without exception "；For " neck has lump, lymphohematopoietic tissue delivered
There is benign tumour "；For " neck has lump, and lymphohematopoietic tissue delivered has malignant tumour ".Calculate and correspond to respectivelyAnd
Current incomeAnd
If finishing biopsy, biopsy results are " lymphohematopoietic tissue delivered have malignant tumour ", and whole diagnosis process terminates, and does not have
Follow-up action scheme, i.e. a2=null.So it can now takeValue described as the current state of an illnessCorresponding current action valency
ValueValue, i.e.,If biopsy results are " neck biopsy are without exception ", then also
Need to check white blood cell count(WBC), verified, i.e. a2For examination white blood cell count(WBC).And the result of white blood cell count(WBC) is checked, have three
Plant possible, " normal ", " higher ", " relatively low ".Corresponding state of an illness description and income are respectively：For " neck has lump ", " it is as good as
Often ", " white blood cell count(WBC) is normal "；For " neck has lump, without exception, and white blood cell count(WBC) is higher "；For " neck has lump,
Without exception, white blood cell count(WBC) is relatively low ".Calculate and correspond to respectivelyAndCurrent incomeAndIf examination is white
After cell count, result is " white blood cell count(WBC) is normal ", and diagnosis process terminates, i.e. a3=null, then
It should be noted that only working as at=null, i.e., when describing no follow-up action scheme for the current state of an illness, currently
The state of an illness describes corresponding current action value Q (st,at=null)=rt。
If have follow-up action scheme for the description of the current state of an illness, the current state of an illness describes corresponding current action value can be with
It is indicated using equation below：Wherein, stRepresent the disease of t
Feelings are described or the description of the t kinds state of an illness；atRepresent that the state of an illness description with t or the t kind state of an illness describe stThe action side of association
Case；Q(st,at) represent that the state of an illness description of t or the t kind state of an illness describe corresponding current action value；r(st) represent t when
The state of an illness description at quarter or the t kind state of an illness describe stCorresponding current income；st+1Represent state of an illness description or the t at t+1 moment
+ a kind of state of an illness description；Represent that the state of an illness description with the t+1 moment or the t+1 kind state of an illness describe st+1The jth kind action of association
Scheme, j value is to be less than or equal to more than or equal to 1 and stThe positive integer of total kind of number of the action scheme of association；Represent that the state of an illness description with the t+1 moment or the t+1 kind state of an illness describe st+1And each action schemeMaximum in corresponding each current action value, γ isWeight, can be default normal
Number, specific value can be configured according to actual conditions, not limit herein.
For the state of an illness description of t, at next moment t+1 moment, the action scheme of multiple associations might have
at+1, whereinIn order to ensure to reach best diagnostic result, it is necessary in various action
SchemeIn select optimal course of action, makeMaximize, can be expressed asγ
It is constant set in advance, the discount rate for expressing future profits.Therefore,For under expression
The future action value at one moment is equal to how many current incomes.The current state of an illness describes corresponding current action valueCurrent action value=current income+future can be simply expressed as
What action was worth discounts.
During actually diagnosis, different lab works is different with the financial cost of inspection project and stand-by period etc.
All it is not quite similar.For patient demand of preferably fitting, optimal therapeutic scheme is sought in the acceptable scope of patient, can
To introduce the cost of activities factor when calculating action value.Specifically, corresponding current income is described and each according to each state of an illness
Lower floor's state of an illness describes corresponding future action value, construction action cost function, it may include：Obtain the action of current state of an illness description
Cost, and psychological utility function is built according to the cost of activities；Each state of an illness is described into corresponding current income and each lower floor disease
Feelings are described after the addition of discounting of corresponding future action value, subtract the psychological utility function, to construct current action value
Function.
For example, it is assumed that the cost of each action, it is fixed, can preset., can be for convenience of calculation
The value stipulations of cost of activities are between 0 to 1., may not be linear due to psychological feelingses of the cost to patient.It therefore, it can use
Shape is similar to the curve of sigmoid functions, to construct the psychological utility function of cost of activities, more relevantly to describe patient
For the psychological feelingses of cost.Assuming that when cost is close to 0, change of the patient to cost is insensitive；When cost is more than one
Mental threshold, during close to 1, complaint of the patient to cost is very big.Wherein, the specific value of mental threshold can according to urban district and
Situation is set, for example, can be 0.5.Now, when may illustrate that cost is around 0.5, change of the patient to cost may
It is most sensitive, and cost continues to rise, patient may be numb.
Exemplarily, the psychological utility function Psychological Utility based on cost of activities in the present invention, specifically
It can be expressed with equation below：Wherein, α and β is default constant, Cost (at) represent t
Cost of activities corresponding to action scheme.After the psychological effectiveness factor for adding cost of activities, corresponding current action value can be with
It is expressed asWherein, γ is the current action at t+1 moment
ValueWeighted value, γ specific value can be configured according to actual conditions, not limit herein.
Corresponding current revenue function is described with the state of an illness currently calculated according to the state of an illness description determination currently calculated, specifically
It may include：Each state of an illness in history case history sample describes and describes corresponding medical diagnosis on disease result, structure with the state of an illness
Build medical practice and summarize model；Model is summarized based on the medical practice and determines that the state of an illness with currently calculating describes corresponding disease
Sick diagnostic result, and calculate the probability distribution of at least one disease；According to the probability distribution of the disease, calculate with currently
The state of an illness of calculating describes the entropy of corresponding diagnostic result, and builds current revenue function according to the entropy.
Specifically, each state of an illness in history case history sample describes and describes corresponding medical diagnosis on disease with the state of an illness
As a result, it can describe each state of an illness in history case history sample as input to build medical practice and summarize model, by history disease
The probability of various diseases included in corresponding medical diagnosis on disease result and diagnostic result is described in example sample with the state of an illness
Distribution is instructed as output to default generation confrontation network (Generative Adversarial Networks, GAN)
Practice, obtain building medical practice summary model, sum up the clinical diagnosis decision-making experience of senior doctor.Wherein, generation confrontation net
Network (Generative Adversarial Networks, GAN) includes production model and discriminative model.
Exemplarily, in history case history sample each state of an illness description and describe corresponding disease with the state of an illness and examine
Disconnected result, builds medical practice and summarizes model, it may include：Target data in history case history sample is to default production
Model is trained；First data falsification is generated according to the production model after the completion of training, and according to the number of targets
According to this and first data falsification is trained to default duscriminant model；According to the production mould after the completion of training
Type generates the second data falsification, and according to discriminating knot of the duscriminant model after the completion of training to second data falsification
Fruit is adjusted to the parameter of the production model, regard the production model that default equilibrium condition is met after adjustment as medical science
Summary of experience model.Wherein, the target data includes the description of each state of an illness and describes corresponding medical diagnosis on disease with the state of an illness
As a result；First data falsification includes the first forgery state of an illness description generated at random and forges state of an illness description with described first
Corresponding at least one first forges disease type；Second data falsification includes the second forgery state of an illness description generated at random
And corresponding at least one second forgery disease type is described with the described second forgery state of an illness.
Model is summarized based on the medical practice and determines that the state of an illness with currently calculating describes corresponding medical diagnosis on disease result,
And the probability distribution of at least one disease is calculated, can obtain current state of an illness description first, and the state of an illness is described
The medical practice that training completes is input to summarize in model, the medical practice summarize the state of an illness currently inputted is described into
Row processing, the output medical diagnosis on disease result corresponding with the state of an illness description currently calculated, and calculate the general of at least one disease
Rate distribution is shown.
In the present embodiment, current income rtOnly describe whether diagnostic result focuses on a few disease, it may also be said to
According to current collection to the state of an illness description have it is much assurance provide diagnostic result.Assuming that the disease quantity that is included in diagnostic result or
Person's species is fewer, and the probability for suffering from every kind of disease is higher, illustrates more sure to current diagnostic result, current income rtAlso
It is higher.Entropy is used in the embodiment of the present invention, to express current income rt.Wherein, the corresponding entropy of each disease type in diagnostic result
It can be calculated by below equation：Wherein, stRepresent t
State of an illness description collected by moment；dtRepresent that the state of an illness collected by t describes corresponding diagnostic result；Diagnostic result can
One or more diseases can be included,Represent that the state of an illness collected by t describes jth kind disease in corresponding diagnostic result；The probability of jth kind disease in diagnostic result is suffered from expression；Entropy(dt, st) represent with t collected by
The state of an illness describes the entropy of corresponding diagnostic result.
For example according to the limited state of an illness description being collected into, the diagnostic result of output shows that patient may suffer from five kinds
Disease type, wherein, the probability of every kind of disease type is 20% respectively.The entropy of this diagnostic result is Entropy (d1|s1)=-
1.0* (5*0.20*log0.20)=2.32, wherein logarithm log are bottom with 2.If then have collected more state of an illness descriptions, then
Diagnostic result, which is updated to patient, may suffer from two kinds of disease types, and probability corresponding with both disease types is respectively 20%
With 80%, at this moment the entropy corresponding to diagnostic result is Entropy (d2|s2)=- 1.0* (0.20*log0.20+0.80*
Log0.80)=0.72.In extreme circumstances, a kind of disease class may be only had by corresponding diagnostic result being described with the state of an illness of input
Type, probability is 100%, and at this moment the corresponding entropy of the disease type is 0.It follows that diagnostic result concentrates on a few
Disease type, entropy is lower.If diagnostic result only one of which disease, the assurance to diagnostic result is bigger, entropy is minimum, is
0。
If for the same state of an illness, we have collected a large amount of case histories.State of an illness description is extracted from these case histories
And diagnostic result, it is then based on medical practice and summarizes modeling statistics going out various related diseases in the diagnostic results of these case histories
The probability distribution of disease, calculates the entropy of the diagnostic result described for this state of an illness.Wherein, medical practice summarizes model
Output is to describe s with the state of an illnesstProbability p df (the d of each disease in corresponding diagnostic resultt|st), it can useRepresent, and then according to
pdf(dt|st) entropy of diagnostic result can be just calculated, in this, as current income rt。
It should be noted that entropy expression is meant that for the description of this state of an illness, there is much to the diagnostic result of output
Hold.In other words, if described for the same state of an illness, comprising a variety of diseases in the diagnostic result in history case history sample, or
Diagnostic result difference in the different history case history sample of person is very big, then illustrate the diagnosis described for this state of an illness, diagnosis
As a result difference is larger, and the assurance to diagnostic result is relatively low.But whether just the size of entropy is not offered as diagnostic result in itself
Really.Even if that is doctor is quite sure to diagnostic result, it must be just correct not ensure that diagnostic result.
The span of entropy is that, from 0 to+∞, entropy is smaller, and income is bigger.In order to rtSpan, be limited to
From 0 to 1 scope so that rtValue is bigger, and current income is bigger, can be rtIt is configured to minor function：
Exemplarily, clinical treatment path navigation table can be set, specifically can be by the row of navigational table point three, the content point of each column
It is not si、aiAnd Q (si,ai), that is, state of an illness description, action scheme and state of an illness description are corresponding with this action scheme
Current action value.Navigational table has some rows, a kind of s of correspondence per a lineiAnd aiCombination.Because the same state of an illness of correspondence is described
si, might have a variety of action scheme ai, specifically can be by aiIt is expressed as：Wherein, k is row
Total kind number (quantity) of dynamic scheme,Represent that i-th kind of state of an illness describes corresponding kth kind action scheme；Similarly,Represent the
The i kind state of an illness describes corresponding jth kind action scheme.So, strictly speaking, the content in navigational table per a line is s respectivelyi、
, can be based on the first training of medical experience of history case history sample after have collected a certain amount of history case history sample data
Model is summarized, has trained medical practice to summarize model, it is possible to the medical navigational table of filling.Specifically, can be from a case history
In, sort out the state of an illness and describe st, and diagnostic result dt.Wherein, diagnostic result dtIncluding one or more disease types.Remember that T is
The terminal in path is diagnosed, i.e., then current action value Q (sT,aT=null)=r (sT), wherein, aT=null represents whole diagnosis
Process terminates, and does not now have follow-up action scheme after corresponding state of an illness description；Current income can be formulated as：
It is then possible to according to the above-mentioned future action that corresponding current income and action scheme are described by each state of an illness
The calculation formula of current action value determined by valueOr
Consider the calculation formula of the current action value after the psychological factor of patient, the psychological utility function of additionInversely anti-upper moment was released from the terminal T moment
Action value, such as terminal T momentProgressively obtain
Corresponding current action is described with each state of an illness to be worth, until extrapolating the initial state of an illness describes corresponding current action value Q
(s1,a1)。
Same processing is all done to every a history case sample, first part of history case sample has been handled, has then handled
Second part of history case sample, and update the Q (s in navigational tablet,at), until having handled all history case samples.Can be with
Understand, with the development and the accumulation of clinical treatment experience of medical science, can constantly obtain new history case history Sample Refreshment
Medical navigational table.
S290, according to the current action value determine current optimal action scheme as current goal action side
Case, and determine based on each current goal action scheme and targeted yield the medical treatment navigation road in the medical navigation model
Footpath.
In the embodiment of the present invention, optimal action scheme can be understood as most suitable action scheme, for example, can be to do
Minimum inspection can rapidly and accurately determine the action scheme of diagnostic result or combine user's self-condition institute really
Fixed action scheme for being adapted to the user etc..
In the present embodiment, the value that will can currently take action is worth by the current action calculated and determined as reference
Go out current optimal action scheme.Specifically, it is described that current optimal action scheme is determined according to the current action value
It is used as current goal action scheme, it may include：Action maximum in each current action value calculated is worth institute right
The action scheme answered, is used as current goal action scheme.That is, s is described corresponding to the same state of an illnesst, have a variety of action schemesEvery kind of current action value of action correspondence oneTake a variety of action schemes it is corresponding eachIn most
Big person, corresponding action schemeIt is exactly optimal course of action.
If increasing continuing several current state of an illness descriptions next level resulting after the action scheme of next step
The current income of state of an illness description is calculated, and the change of each obtained current income less, then may explanation increase action side
The state of an illness description of each next level after case is little for the influence of diagnostic result.Therefore, it is described based on each state of an illness description,
The action scheme and targeted yield associated with each state of an illness description is determined before medical guidance path, can also be included：Calculate
Each state of an illness describes corresponding current income, if the amplitude of variation of the corresponding current income of the state of an illness description of predetermined number is small
In predetermined threshold value, then the current income is regard as targeted yield；Or, calculate each state of an illness and describe corresponding current income, such as
The current income that each state of an illness description of the continuous predetermined number of fruit is corresponding restrains, then regard current income as targeted yield.
Wherein, predetermined number can be understood as the state of an illness description quantity can in advance be set according to actual conditions, example
It can be such as 3,4 or 5, not limit herein.Meanwhile, predetermined threshold value can also rule of thumb default setting or by user according to
Actual conditions are configured, and are not limited herein.
For example, it is assumed that the state of an illness description of initial input, start time is designated as, is represented with t=1, through each action scheme
Obtained final state of an illness description afterwards, at the time of being designated as diagnosis end, is represented with t=T, during whole diagnosis, calculates every
Current income r corresponding to one momentt, can specifically be calculated by equation below：Wherein, Entropy (dt|st) represent to describe corresponding each disease with the state of an illness of t
The entropy of type, if rt, rt+1..., rt+ΔAmplitude of variation, constantly less than predetermined threshold value, such as default constant, τ, then should
Diagnosis process terminates, now T=t+ Δs.Wherein, Δ is the time window length of probation or pre- according to actual conditions
If constant.
It should be noted that the description such as " t " and " t+1 moment " in the embodiment of the present invention, is only applicable to distinguish
Different state of an illness descriptions and the action scheme that associate is described with the state of an illness, do not represent that the state of an illness is described or action scheme can be according to
Rely and change in the time, also be understood as t kinds or the description of the t+1 kinds state of an illness.
If current state of an illness description is different from state of an illness description described in history case history sample, then illustrate in history disease
Go through in sample and such state of an illness description do not occurred, i.e., no previous experiences may be referred to, and can now pass through medical practice
Summary model describes the probability of each disease in corresponding diagnostic result, and the diagnostic result to estimate with the current state of an illness, and then
Estimate that the current state of an illness describes corresponding current action value.
The technical scheme of the present embodiment, describes the dependence between each action scheme by each state of an illness and retouches each state of an illness
State and be divided into different levels, and record the state of an illness description of different levels, and corresponding action side is described with the association levels state of an illness
Case, constructs medical navigation model, can understand, accurately, systematically the medical experience in history case history sample is carried out always
Knot, and then each state of an illness of combination describes corresponding current income and each lower floor's state of an illness describes corresponding future action value, it is determined that
Go out the corresponding current action value of each action scheme, the description of each state of an illness is entered with each association action scheme as an overall plan
Row considers, and using current action value as reference, is conducive to determining current optimal action scheme, and then determine most
Good medical guidance path.
Embodiment three
A kind of structured flowchart of the generating means for medical guidance path that Fig. 3 is provided by the embodiment of the present invention three.The dress
Putting can be realized by way of hardware and/or software, and configuration that typically can be independent is in the server or by terminal kimonos
Business device coordinates the method for realizing the present embodiment.As shown in figure 3, the generating means of the medical guidance path of the present embodiment include：Sample
This acquisition module 310, dependence determining module 320 and medical guidance path determining module 330.
Wherein, sample acquisition module 310, for obtaining the description of each state of an illness in history case history sample and being retouched with each state of an illness
State each action scheme of association；Dependence determining module 320, for determining each state of an illness according to the history case history sample
Dependence between description and each action scheme；Medical guidance path determining module 330, for according to the dependence structure
Medical navigation model is built, and medical guidance path is determined according to the medical navigation model.
The technical scheme of the present embodiment, by obtaining the description of each state of an illness in history case history sample and being described with each state of an illness
Each action scheme of association, sums up the medical experience in each history case history sample, it is then determined that going out each state of an illness description and each row
Dependence between dynamic scheme, sums up the diagnosis warp of medical worker during the medical diagnosis described in history case sample
Test, medical navigation model is then built according to dependence, collects and describes corresponding each historical diagnostic path with each state of an illness, is built
Go out medical navigation model, and then medical guidance path is determined according to medical navigation model, can be effectively from history case history sample
In sort out clinical treatment experience, solve the problems such as existing medical experience exchange is wasted time and energy, realize well to medical treatment warp
The summary tested, and medical guidance path assisted medical diagnosis is provided, the shared of medical experience is really realized, promotes medical advance.
On the basis of above-mentioned technical proposal, the medical guidance path determining module can be used for：
Obtain current state of an illness description；
The history case history sample is traveled through according to the dependence, judges whether to close with the current state of an illness description
The action scheme of connection；
If in the presence of action scheme associate with the current state of an illness description, obtain described with the current state of an illness and with
The corresponding target state of an illness description of the action scheme, and the target state of an illness described to be used as the next of the current state of an illness description
The level state of an illness is described；
The target state of an illness is being described as after new current state of an illness description, returning and perform according to the dependence time
The history case history sample is gone through, the operation of action scheme associated with the current state of an illness description is judged whether, until new
The current state of an illness description do not associate any row move scheme；
If in the absence of the action scheme associated with the current state of an illness description, the state of an illness of record different levels is described, with
And corresponding action scheme is described with the association levels state of an illness, construct medical navigation model.
On the basis of above-mentioned each technical scheme, the medical guidance path determining module may include that current action value is true
Order member and medical guidance path determining unit.
Wherein, current action value determining unit, for describing corresponding current income and each lower floor according to each state of an illness
The state of an illness describes corresponding future action value, determines the corresponding current action value of each action scheme；Medical guidance path is true
Order member, for determining current optimal action scheme as current goal action scheme according to the current action value,
And the medical guidance path in the medical navigation model is determined based on each the current goal action scheme and targeted yield.
On the basis of above-mentioned each technical scheme, the current action value determining unit may include cost function structure of taking action
Make subelement and current action value calculation subelement.
Wherein, action cost function construction subelement, under describing corresponding current income according to each state of an illness and be each
The layer state of an illness describes corresponding future action value, construction action cost function；Current action value calculation subelement, for based on
The action cost function calculates the corresponding current action value of each action scheme.
On the basis of above-mentioned each technical scheme, it is described action cost function construction subelement specifically for：
In record result, since the state of an illness description of lowermost layer, calculate describe corresponding current line with each state of an illness successively
Dynamic cost function；
Wherein, if lower floor's state of an illness description is not present in the state of an illness description currently calculated, retouched according to the state of an illness currently calculated
State determination and describe corresponding current revenue function with the state of an illness currently calculated, the current receipts that the state of an illness currently calculated is described
The current action cost function that beneficial function is described as the state of an illness currently calculated；If there is lower floor's disease in current state of an illness description
Feelings are described, then each state of an illness is described into corresponding current income is added with the discounting for future action value of action scheme, is used as institute
State the current action cost function of the state of an illness description currently calculated.
On the basis of above-mentioned each technical scheme, the state of an illness description that the basis is currently calculated determines the disease with currently calculating
Feelings describe corresponding current revenue function, including：
Each state of an illness in history case history sample describes and describes corresponding medical diagnosis on disease result, structure with the state of an illness
Build medical practice and summarize model；
Model is summarized based on the medical practice and determines that the state of an illness with currently calculating describes corresponding medical diagnosis on disease result,
And calculate the probability distribution of at least one disease；
According to the probability distribution of the disease, the entropy that corresponding diagnostic result is described with the state of an illness currently calculated is calculated,
And current revenue function is built according to the entropy.
On the basis of above-mentioned each technical scheme, the medical guidance path determining unit is particularly used in：
By the action scheme corresponding to action value maximum in each current action value calculated, as current
Goal activity scheme.
On the basis of above-mentioned each technical scheme, the action cost function construction subelement can be additionally used in：
The cost of activities of current state of an illness description is obtained, and psychological utility function is built according to the cost of activities；
Each state of an illness is described into the phase of discounting that corresponding current income describes corresponding future action value with each lower floor's state of an illness
Plus after, the psychological utility function is subtracted, to construct current action cost function.
On the basis of above-mentioned each technical scheme, in addition to：
Targeted yield determining module, in the action for being described, being associated with each state of an illness description based on each state of an illness
Scheme and targeted yield are determined before medical guidance path, are calculated each state of an illness and are described corresponding current income, if predetermined number
The amplitude of variation of the corresponding current income of state of an illness description be respectively less than predetermined threshold value, then the current income is received as target
Benefit.
Said apparatus can perform the method that the embodiment of the present invention one and embodiment two are provided, and possess execution above method phase
The functional module and beneficial effect answered.Not ins and outs of detailed description in the present embodiment, reference can be made to the embodiment of the present invention one
The method provided with embodiment two.
In addition, the present embodiment additionally provides a kind of medical path air navigation aid, this method includes：
Obtain the patient data of user's input；Wherein, the patient data includes the current state of an illness description of patient；
The medical navigation path set up using the generation method in the medical navigation path described in any embodiment of the present invention
The patient data currently inputted is handled, path navigation result corresponding with presently described patient data is exported and carries out
Display；Wherein, the path navigation result includes the corresponding action scheme of the state of an illness description current with patient or disease type.
Above-mentioned technical proposal, the medical navigation path set up by the generation method in medical navigation path, being capable of basis
The patient data of user's input, outgoing route navigation results can describe according to the current state of an illness of patient, be according to medical experience
User provides diagnosis path, and auxiliary user is diagnosed, and is fully shared medical experience, is promoted medical development.
Example IV
Fig. 4 is a kind of structural representation for terminal that the embodiment of the present invention four is provided.Fig. 4 is shown suitable for being used for realizing this
The block diagram of the exemplary terminal 412 of invention embodiment.The terminal 412 that Fig. 4 is shown is only an example, should not be to the present invention
The function of embodiment and use range band come any limitation.
As shown in figure 4, terminal 412 is showed in the form of universal computing device.The component of terminal 412 can include but not limit
In：One or more processor or processor 416；And storage device 428, for storing one or more programs, even
Connect the bus 418 of different system component (including storage device 428 and processor 416).
Bus 418 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.Lift
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA (MAC)
Bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) bus.
Terminal 412 typically comprises various computing systems computer-readable recording medium.These media can be it is any can be by terminal
412 usable mediums accessed, including volatibility and non-volatile media, moveable and immovable medium.
Storage device 428 can include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 430 and/or cache memory 432.Terminal 412 may further include other removable/nonremovable
, volatile/non-volatile computer system storage medium.Only as an example, storage system 434 can be used for read-write it is not removable
Dynamic, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in Fig. 4, can provide
For the disc driver to may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to may move anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 418.Memory 428 can include the production of at least one program
Product, the program product has one group of (for example, at least one) program module, and these program modules are configured to perform of the invention each
The function of embodiment.
Program/utility 440 with one group of (at least one) program module 442, can be stored in such as memory
In 428, such program module 442 includes but is not limited to operating system, one or more application program, other program modules
And routine data, the realization of network environment is potentially included in each or certain combination in these examples.Program module 442
Generally perform the function and/or method in embodiment described in the invention.
Terminal 412 can also be logical with one or more external equipments 414 (such as keyboard, sensing equipment, display 424)
Letter, can also enable a user to the equipment communication interacted with the terminal 412 with one or more, and/or with causing the terminal 412
Any equipment (such as network interface card, modem etc.) communication that can be communicated with one or more of the other computing device.This
Planting communication can be carried out by input/output (I/O) interface 422.Also, terminal 412 can also by network adapter 420 with
One or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as internet) communicates.Such as
Shown in figure, network adapter 420 is communicated by bus 418 with other modules of terminal 412.Although it should be understood that not showing in figure
Go out, terminal 412 can be combined and use other hardware and/or software module, included but is not limited to：It is microcode, device driver, superfluous
Remaining processor, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processor 416 is stored in the program in storage device 428 by operation, so as to perform various function application and number
According to processing, for example, realize the generation method for the medical guidance path that the embodiment of the present invention is provided.
In addition, the embodiment of the present invention, which additionally provides one kind, includes computer-readable recording medium, computer is stored thereon with
Program, for performing a kind of generation method of medical guidance path when the program is executed by processor, this method includes：
Obtain the description of each state of an illness in history case history sample and each action scheme associated with the description of each state of an illness；
Dependence between each state of an illness description and each action scheme is determined according to the history case history sample；
Medical navigation model is built according to the dependence, and medical treatment navigation road is determined according to the medical navigation model
Footpath.
Optionally, the computer executable instructions can be also used for performing the present invention times when being performed by computer processor
The technical scheme of the generation method for the medical guidance path that meaning embodiment is provided.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered use
In the order list for the executable instruction for realizing logic function, it may be embodied in any computer-readable recording medium,
For instruction execution system, device or equipment (such as computer based system including the system of processor or other can be from finger
The system for making execution system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device
Or equipment and use.For the purpose of this specification, " computer-readable recording medium " can be it is any can include, store, communicating,
Propagate or transmission procedure is for instruction execution system, device or equipment or with reference to these instruction execution systems, device or equipment
The device used.
The more specifically example (non-exhaustive list) of computer-readable recording medium includes following：With one or more
The electrical connection section (electronic installation) of wiring, portable computer diskette box (magnetic device), random access memory (RAM) is read-only to deposit
Reservoir (ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk are only
Read memory (CDROM).In addition, computer-readable recording medium can even is that can thereon printing described program paper or its
His suitable medium, such as, by carrying out optical scanner to paper or other media, then enter edlin, interpretation or if necessary with it
His suitable method is handled electronically to obtain described program, and is stored it in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage or
Firmware hardware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array PGA, scene can
Program gate array FPGA etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or the spy that the embodiment or example are described
Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not
Necessarily refer to identical embodiment or example.Moreover, specific features, structure, material or the feature of description can be any
One or more embodiments or example in combine in an appropriate manner.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art it is various it is obvious change,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (11)
1. a kind of generation method of medical guidance path, it is characterised in that including：
Obtain the description of each state of an illness in history case history sample and each action scheme associated with each state of an illness description；
Dependence between each state of an illness description and each action scheme is determined according to the history case history sample；
Medical navigation model is built according to the dependence, and medical guidance path is determined according to the medical navigation model.
2. according to the method described in claim 1, it is characterised in that described that medical treatment navigation mould is built according to the dependence
Type, including：
Obtain current state of an illness description；
The history case history sample is traveled through according to the dependence, judges whether what is associated with the current state of an illness description
Action scheme；
If in the presence of action scheme associate with the current state of an illness description, obtain described with the current state of an illness and with it is described
The corresponding target state of an illness description of action scheme, and next level that target state of an illness description is described as the current state of an illness
The state of an illness is described；
The target state of an illness is being described as after new current state of an illness description, returning to execution and institute is traveled through according to the dependence
History case history sample is stated, the operation of action scheme associated with the current state of an illness description is judged whether, until new works as
Preceding state of an illness description does not associate any row and moves scheme；
If in the absence of the action scheme associated with the current state of an illness description, the state of an illness description of record different levels, Yi Jiyu
The association levels state of an illness describes corresponding action scheme, constructs medical navigation model.
3. method according to claim 2, it is characterised in that described that medical treatment navigation is determined according to the medical navigation model
Path, including：
Corresponding current income is described according to each state of an illness and each lower floor's state of an illness describes corresponding future action value, is determined each
The corresponding current action value of action scheme；
Current optimal action scheme is determined as current goal action scheme according to the current action value, and based on each
The current goal action scheme and targeted yield determine the medical guidance path in the medical navigation model.
4. method according to claim 3, it is characterised in that it is described according to each state of an illness describe corresponding current income and
Each lower floor's state of an illness describes corresponding future action value, determines the corresponding current action value of each action scheme, including：
Corresponding current income is described according to each state of an illness and each lower floor's state of an illness describes corresponding future action value, construction action
Cost function；
The corresponding current action value of each action scheme is calculated based on the action cost function.
5. method according to claim 4, it is characterised in that it is described according to each state of an illness describe corresponding current income and
Each lower floor's state of an illness describes corresponding future action value, constructs action cost function, including：
In record result, since the state of an illness description of lowermost layer, calculate describe corresponding current action valency with each state of an illness successively
Value function；
Wherein, it is true according to the state of an illness description currently calculated if lower floor's state of an illness description is not present in the state of an illness description currently calculated
The current income letter fixed to describe corresponding current revenue function with the state of an illness currently calculated, that the state of an illness currently calculated is described
The current action cost function that number is described as the state of an illness currently calculated；If there is lower floor's state of an illness and retouch in current state of an illness description
State, then each state of an illness is described into corresponding current income is added with the discounting for future action value of action scheme, works as described
The current action cost function of the state of an illness description of preceding calculating.
6. method according to claim 5, it is characterised in that the state of an illness description that the basis is currently calculated is determined and current
The state of an illness of calculating describes corresponding current revenue function, including：
Each state of an illness in history case history sample describes and describes corresponding medical diagnosis on disease result with the state of an illness, builds doctor
Learn summary of experience model；
Model is summarized based on the medical practice and determines that the state of an illness with currently calculating describes corresponding medical diagnosis on disease result, and is counted
Calculate the probability distribution of at least one disease；
According to the probability distribution of the disease, the entropy that corresponding diagnostic result is described with the state of an illness currently calculated, and root are calculated
Current revenue function is built according to the entropy.
7. method according to claim 3, it is characterised in that described to be determined currently most according to the current action value
Good action scheme as current goal take action scheme, including：
By the action scheme corresponding to action value maximum in each current action value calculated, current goal is used as
Action scheme.
8. method according to claim 4, it is characterised in that it is described according to each state of an illness describe corresponding current income and
Each lower floor's state of an illness describes corresponding future action value, constructs action cost function, in addition to：
The cost of activities of current state of an illness description is obtained, and psychological utility function is built according to the cost of activities；
Each state of an illness is described after the addition of discounting that corresponding current income describes corresponding future action value with each lower floor's state of an illness,
The psychological utility function is subtracted, to construct current action cost function.
9. according to any described methods of claim 3-8, it is characterised in that it is described based on the description of each state of an illness, with it is each described
Before the action scheme and the medical guidance path of targeted yield determination of state of an illness description association, in addition to：
Calculate each state of an illness and describe corresponding current income, if the change of the corresponding current income of the state of an illness description of predetermined number
Amplitude is respectively less than predetermined threshold value, then regard the current income as targeted yield.
10. a kind of generating means of medical guidance path, it is characterised in that including：
Sample acquisition module, for each row for obtaining the description of each state of an illness in history case history sample and being associated with the description of each state of an illness
Dynamic scheme；
Dependence determining module, for according to the history case history sample determine each state of an illness description and each action scheme it
Between dependence；
Medical guidance path determining module, for building medical navigation model according to the dependence, and according to the medical treatment
Navigation model determines medical guidance path.
11. a kind of medical path air navigation aid, it is characterised in that including：
Obtain the patient data of user's input；Wherein, the patient data includes the current state of an illness description of patient；
The medical navigation path set up using the generation method in any described medical navigation paths of claim 1-9 is to current
The patient data of input is handled, and is exported path navigation result corresponding with presently described patient data and is shown；
Wherein, the path navigation result includes the corresponding action scheme of the state of an illness description current with patient or disease type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710325176.8A CN107103201B (en) | 2017-05-10 | 2017-05-10 | Medical navigation path generation method and device and medical path navigation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710325176.8A CN107103201B (en) | 2017-05-10 | 2017-05-10 | Medical navigation path generation method and device and medical path navigation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107103201A true CN107103201A (en) | 2017-08-29 |
| CN107103201B CN107103201B (en) | 2020-11-24 |
Family
ID=59668772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710325176.8A Expired - Fee Related CN107103201B (en) | 2017-05-10 | 2017-05-10 | Medical navigation path generation method and device and medical path navigation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107103201B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108461130A (en) * | 2018-01-18 | 2018-08-28 | 邱堃 | Medical task intelligent dispatching method and system |
| CN108597579A (en) * | 2018-05-11 | 2018-09-28 | 北京爱康宜诚医疗器材有限公司 | The determination method and device of operating time, storage medium, electronic device |
| CN109473153A (en) * | 2018-10-30 | 2019-03-15 | 医渡云（北京）技术有限公司 | Processing method, device, medium and the electronic equipment of medical data |
| CN109545350A (en) * | 2018-11-21 | 2019-03-29 | 上海依智医疗技术有限公司 | A kind of hospital guide's method and device |
| CN109559788A (en) * | 2018-11-21 | 2019-04-02 | 上海依智医疗技术有限公司 | A kind of history-taking method and device |
| CN109599184A (en) * | 2018-11-09 | 2019-04-09 | 金色熊猫有限公司 | Screening technique, device, electronic equipment, the storage medium of patient's diagnosis and treatment data |
| CN110176311A (en) * | 2019-05-17 | 2019-08-27 | 北京印刷学院 | A kind of automatic medical proposal recommending method and system based on confrontation neural network |
| CN111326251A (en) * | 2020-02-13 | 2020-06-23 | 北京百度网讯科技有限公司 | Method and device for outputting inquiry questions and electronic equipment |
| CN111508611A (en) * | 2020-03-19 | 2020-08-07 | 平安国际智慧城市科技股份有限公司 | Intelligent selection method and device for multiple solutions and related equipment |
| CN111721310A (en) * | 2019-03-22 | 2020-09-29 | 北京京东尚科信息技术有限公司 | Method, device, medium and electronic equipment for determining navigation path to be optimized |
| CN111833680A (en) * | 2020-06-19 | 2020-10-27 | 上海长海医院 | Medical staff theoretical learning evaluation system and method and electronic equipment |
| CN111899844A (en) * | 2020-09-28 | 2020-11-06 | 平安科技（深圳）有限公司 | Sample generation method and device, server and storage medium |
| WO2021051496A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Diagnosis result identification and model training method, computer device, and storage medium |
| US20210098135A1 (en) * | 2019-09-30 | 2021-04-01 | Siemens Healthcare Gmbh | Healthcare network |
| CN114864098A (en) * | 2022-03-14 | 2022-08-05 | 北京融威众邦电子技术有限公司 | Data mining system, method and device |
| CN114864107A (en) * | 2021-02-03 | 2022-08-05 | 阿里巴巴集团控股有限公司 | Clinical pathway variation analysis method, equipment and storage medium |
| CN116127147A (en) * | 2023-04-04 | 2023-05-16 | 吉林大学 | Medical data storage method, system, computer device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020169771A1 (en) * | 2001-05-09 | 2002-11-14 | Melmon Kenneth L. | System & method for facilitating knowledge management |
| CN105005709A (en) * | 2015-08-19 | 2015-10-28 | 赵蒙海 | Process mining method based on single-disease treatment process |
| CN105260782A (en) * | 2015-09-23 | 2016-01-20 | 百度在线网络技术（北京）有限公司 | Method and device for processing reserved registration information |
| CN105608091A (en) * | 2014-11-21 | 2016-05-25 | 中国移动通信集团公司 | Construction method and device of dynamic medical knowledge base |
| CN106339587A (en) * | 2016-08-23 | 2017-01-18 | 浙江工业大学 | Clinical path modeling method based on time sequence network |
-
2017
- 2017-05-10 CN CN201710325176.8A patent/CN107103201B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020169771A1 (en) * | 2001-05-09 | 2002-11-14 | Melmon Kenneth L. | System & method for facilitating knowledge management |
| CN105608091A (en) * | 2014-11-21 | 2016-05-25 | 中国移动通信集团公司 | Construction method and device of dynamic medical knowledge base |
| CN105005709A (en) * | 2015-08-19 | 2015-10-28 | 赵蒙海 | Process mining method based on single-disease treatment process |
| CN105260782A (en) * | 2015-09-23 | 2016-01-20 | 百度在线网络技术（北京）有限公司 | Method and device for processing reserved registration information |
| CN106339587A (en) * | 2016-08-23 | 2017-01-18 | 浙江工业大学 | Clinical path modeling method based on time sequence network |
Non-Patent Citations (2)
| Title |
|---|
| 郑西川等: "基于医疗大数据分析的临床电子病历智能化研究", 《中国数字医学》 * |
| 韩冰宁: "医疗临床路径挖掘方法研究与应用", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108461130B (en) * | 2018-01-18 | 2020-09-18 | 邱堃 | Intelligent scheduling method and system for treatment tasks |
| CN108461130A (en) * | 2018-01-18 | 2018-08-28 | 邱堃 | Medical task intelligent dispatching method and system |
| CN108597579A (en) * | 2018-05-11 | 2018-09-28 | 北京爱康宜诚医疗器材有限公司 | The determination method and device of operating time, storage medium, electronic device |
| CN109473153A (en) * | 2018-10-30 | 2019-03-15 | 医渡云（北京）技术有限公司 | Processing method, device, medium and the electronic equipment of medical data |
| CN109599184A (en) * | 2018-11-09 | 2019-04-09 | 金色熊猫有限公司 | Screening technique, device, electronic equipment, the storage medium of patient's diagnosis and treatment data |
| CN109545350A (en) * | 2018-11-21 | 2019-03-29 | 上海依智医疗技术有限公司 | A kind of hospital guide's method and device |
| CN109559788A (en) * | 2018-11-21 | 2019-04-02 | 上海依智医疗技术有限公司 | A kind of history-taking method and device |
| CN111721310A (en) * | 2019-03-22 | 2020-09-29 | 北京京东尚科信息技术有限公司 | Method, device, medium and electronic equipment for determining navigation path to be optimized |
| CN111721310B (en) * | 2019-03-22 | 2024-04-16 | 北京京东乾石科技有限公司 | Determination method and device of navigation path to be optimized, medium and electronic equipment |
| CN110176311A (en) * | 2019-05-17 | 2019-08-27 | 北京印刷学院 | A kind of automatic medical proposal recommending method and system based on confrontation neural network |
| WO2021051496A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Diagnosis result identification and model training method, computer device, and storage medium |
| US20210098135A1 (en) * | 2019-09-30 | 2021-04-01 | Siemens Healthcare Gmbh | Healthcare network |
| CN111326251A (en) * | 2020-02-13 | 2020-06-23 | 北京百度网讯科技有限公司 | Method and device for outputting inquiry questions and electronic equipment |
| CN111326251B (en) * | 2020-02-13 | 2023-08-29 | 北京百度网讯科技有限公司 | Question output method and device and electronic equipment |
| WO2021184579A1 (en) * | 2020-03-19 | 2021-09-23 | 平安国际智慧城市科技股份有限公司 | Intelligent selection method and apparatus employing multiple solutions, computer device, and storage medium |
| CN111508611A (en) * | 2020-03-19 | 2020-08-07 | 平安国际智慧城市科技股份有限公司 | Intelligent selection method and device for multiple solutions and related equipment |
| CN111833680A (en) * | 2020-06-19 | 2020-10-27 | 上海长海医院 | Medical staff theoretical learning evaluation system and method and electronic equipment |
| WO2021159740A1 (en) * | 2020-09-28 | 2021-08-19 | 平安科技（深圳）有限公司 | Sample generation method and apparatus, and server and storage medium |
| CN111899844A (en) * | 2020-09-28 | 2020-11-06 | 平安科技（深圳）有限公司 | Sample generation method and device, server and storage medium |
| CN114864107A (en) * | 2021-02-03 | 2022-08-05 | 阿里巴巴集团控股有限公司 | Clinical pathway variation analysis method, equipment and storage medium |
| CN114864098A (en) * | 2022-03-14 | 2022-08-05 | 北京融威众邦电子技术有限公司 | Data mining system, method and device |
| CN116127147A (en) * | 2023-04-04 | 2023-05-16 | 吉林大学 | Medical data storage method, system, computer device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107103201B (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103201A (en) | Generation method, device and the medical path air navigation aid of medical guidance path | |
| Kagiyama et al. | Artificial intelligence: practical primer for clinical research in cardiovascular disease | |
| Nori et al. | Capabilities of gpt-4 on medical challenge problems | |
| Kwon et al. | Deep learning for predicting in‐hospital mortality among heart disease patients based on echocardiography | |
| Fendrick et al. | Clinical and economic effects of population-based Helicobacter pylori screening to prevent gastric cancer | |
| Star | Scientific work and uncertainty | |
| CN110222201A (en) | A kind of disease that calls for specialized treatment knowledge mapping construction method and device | |
| US20190139642A1 (en) | System and methods for medical image analysis and reporting | |
| Peissig et al. | Relational machine learning for electronic health record-driven phenotyping | |
| CN114496234A (en) | Cognitive-atlas-based personalized diagnosis and treatment scheme recommendation system for general patients | |
| CN106339593A (en) | Kawasaki disease classification and prediction method based on medical data modeling | |
| US12039420B2 (en) | System and method for generating a direction inquiry response from biological extractions using machine learning | |
| Chen et al. | A deep-learning based ultrasound text classifier for predicting benign and malignant thyroid nodules | |
| Webster et al. | The Functional Assessment of Chronic Illness Therapy (FACIT) measurement system: guidance for use in research and clinical practice | |
| CN113990502B (en) | ICU heart failure prediction system based on heterogeneous graph neural network | |
| De Winter et al. | Starting out in statistics: An introduction for students of human health, disease, and psychology | |
| Kumar et al. | Deep-learning-enabled multimodal data fusion for lung disease classification | |
| CN106354715A (en) | Method and device for medical word processing | |
| JP2022514206A (en) | A method for evaluating the risk of a subject and classifying the subject based on the risk, and a device using the method. | |
| CN110377698A (en) | Based on the task processing method and device, equipment and readable medium for reading understanding | |
| Grotenhuis et al. | Modest performance of text mining to extract health outcomes may be almost sufficient for high-quality prognostic model development | |
| CN115719329A (en) | Method and system for fusing RA ultrasonic modal synovial membrane scores based on deep learning | |
| Wang et al. | Deep‐learning‐based renal artery stenosis diagnosis via multimodal fusion | |
| Zhu et al. | Application of a computerized decision support system to develop care strategies for elderly hemodialysis patients | |
| Barelli et al. | Exploiting the interplay between cross-sectional and longitudinal data in Class III malocclusion patients |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201124 |