CN108091399A - A kind of analysis method and system of dynamic diseases model library - Google Patents
A kind of analysis method and system of dynamic diseases model library Download PDFInfo
- Publication number
- CN108091399A CN108091399A CN201711424873.5A CN201711424873A CN108091399A CN 108091399 A CN108091399 A CN 108091399A CN 201711424873 A CN201711424873 A CN 201711424873A CN 108091399 A CN108091399 A CN 108091399A
- Authority
- CN
- China
- Prior art keywords
- symptom
- disease
- list
- model
- dynamic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 297
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 297
- 238000004458 analytical method Methods 0.000 title claims abstract description 44
- 208000024891 symptom Diseases 0.000 claims abstract description 319
- 238000009795 derivation Methods 0.000 claims abstract description 27
- 238000003745 diagnosis Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 18
- 239000000284 extract Substances 0.000 claims description 9
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 7
- BALXUFOVQVENIU-KXNXZCPBSA-N pseudoephedrine hydrochloride Chemical compound [H+].[Cl-].CN[C@@H](C)[C@@H](O)C1=CC=CC=C1 BALXUFOVQVENIU-KXNXZCPBSA-N 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 20
- 230000003068 static effect Effects 0.000 abstract description 6
- 238000005457 optimization Methods 0.000 abstract description 2
- 230000001737 promoting effect Effects 0.000 abstract description 2
- 230000010354 integration Effects 0.000 abstract 1
- 206010019280 Heart failures Diseases 0.000 description 33
- 238000007689 inspection Methods 0.000 description 10
- 206010051448 Hepatojugular reflux Diseases 0.000 description 8
- 210000004731 jugular vein Anatomy 0.000 description 8
- 208000006029 Cardiomegaly Diseases 0.000 description 7
- 206010031123 Orthopnoea Diseases 0.000 description 7
- 206010037660 Pyrexia Diseases 0.000 description 7
- 208000001871 Tachycardia Diseases 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 7
- 208000012144 orthopnea Diseases 0.000 description 7
- 230000006794 tachycardia Effects 0.000 description 7
- 206010030113 Oedema Diseases 0.000 description 6
- 210000003141 lower extremity Anatomy 0.000 description 5
- 210000004072 lung Anatomy 0.000 description 5
- 206010020772 Hypertension Diseases 0.000 description 4
- 206010037423 Pulmonary oedema Diseases 0.000 description 4
- 208000037656 Respiratory Sounds Diseases 0.000 description 4
- 208000029078 coronary artery disease Diseases 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 208000005333 pulmonary edema Diseases 0.000 description 4
- 206010037833 rales Diseases 0.000 description 4
- 208000000059 Dyspnea Diseases 0.000 description 3
- 206010013975 Dyspnoeas Diseases 0.000 description 3
- 208000002151 Pleural effusion Diseases 0.000 description 3
- 206010019842 Hepatomegaly Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 206010012601 diabetes mellitus Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000035487 diastolic blood pressure Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000556 factor analysis Methods 0.000 description 2
- 208000013220 shortness of breath Diseases 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 208000005641 Adenomyosis Diseases 0.000 description 1
- 240000008574 Capsicum frutescens Species 0.000 description 1
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 description 1
- 208000014094 Dystonic disease Diseases 0.000 description 1
- 101001072091 Homo sapiens ProSAAS Proteins 0.000 description 1
- 206010020565 Hyperaemia Diseases 0.000 description 1
- 208000031226 Hyperlipidaemia Diseases 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 description 1
- 206010048858 Ischaemic cardiomyopathy Diseases 0.000 description 1
- 102100036366 ProSAAS Human genes 0.000 description 1
- 230000007815 allergy Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 208000010118 dystonia Diseases 0.000 description 1
- 201000009274 endometriosis of uterus Diseases 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000302 ischemic effect Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 210000002307 prostate Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 210000002966 serum Anatomy 0.000 description 1
- 229910052708 sodium Inorganic materials 0.000 description 1
- 239000011734 sodium Substances 0.000 description 1
- 230000000392 somatic effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention relates to a kind of analysis methods and system of dynamic diseases model library, are as follows：S1, symptom establish disease model；S2, effective case history collection is input to disease model analyzing and processing；S3, disease model is updated according to effective case history, finally obtains new disease model；S4, patient's related diseases are levied in data input model, the list of diseases of strong relation symptom in disease model is met according to the selection of symptom information, calculated various diseases and probability using the disease derivation formula of corresponding list of diseases afterwards, and result is pushed to clinician；System, including Dynamic Inference machine, Dynamic Inference machine is connected respectively with data input end and user's end communication.The present invention is converted into medical data the factor for promoting disease model optimization at any time by the way that static clinical knowledge storehouse and big data method effective integration are gone out dynamic disease model, and disease model storehouse is adjusted into Mobile state.The present invention promotes the speed and accuracy rate of diagnosis, and clinical data is converted into experience immediately.
Description
Technical field
The present invention relates to Analysis of Medical Treatment Data technical field, it is related to the analysis method and system of dynamic diseases model library.
Background technology
It is investigated according to document, the 3 of mistaken diagnosis big main causes are doctors experience deficiency respectively, do not carry out most effectively during clinical diagnosis and treatment
Inspection item and in terms of interrogation and inspection without obtaining common recognition.Doctors experience deficiency has several performances, doctor's seniority compared with
Shallow or professional domain is very strong but other field is unfamiliar with；It is before making a definite diagnosis not carry out most strong inspection, and the doctor in charge has one
When a first impression or tentative diagnosis, in order to further determine as a result, can add inspection item verifies preliminary supposition, at this time
Because of the complexity of disease, the inspection application easily assigned is not badly in need of most, so as to cause economic waste and time
Delay；It is then relation more difficult judgement in state of an illness complexity between inspection result and disease not obtain common recognition, between each expert
Opinion also disunity, finally generally require more sections' consultation of doctors to determine diagnosis.
In view of the above-mentioned problems, at present it is clinical mostly divided using intelligence examine or clinical decision support in terms of Information software come
It supports, the method that this two classes system is based primarily upon the processing of two category informations：First, based on static clinical knowledge processing method, that is, use
By the performance of disease, risk factor table is established, the method compareed one by one proposes first visit opinion, and the method is similar to clinical expert
Micro-judgment method；Second is that history case history is handled with the multinomial logistic regression method of big data, by all diseases
The relevant symptom of disease carries out dynamic analysis, obtains corresponding predictor formula, then inputs conditions of patients data, carries out prediction point
Analysis.
Above-mentioned two methods static state clinical knowledge storehouse method and big data method have its own advantage under specific occasion,
But also there are certain limitation is specific as follows：
The method of static knowledge base, although more effective to the common disease for partly having easily identification symptom, also more diseases
Symptom performing combination pattern and indefinite, while as human society continues to develop the understanding of disease with detection means, know
Knowledge is also being enriched constantly, and by clinical summary, popularization, timeliness often were reapplied after then tying academic discussion for static knowledge base
Property is low.
Multifactor homing method natively there are certain requirements the quality of data and quantity according to the analysis for overweighting big data,
Because Domestic Medicine information development process is quick, information system is also numerous and diverse various, and it is of low quality to cause historical data instantly, together
When information also incomplete present situation, so to most middle-size and small-size medical institutions, it is extremely difficult to be carried out using this kind of method and implement work
Make, therefore in terms of objective condition, not all hospital all possesses this condition, in clinical practice level, current popularization and
Availability is had a greatly reduced quality.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of analysis methods and its system of dynamic diseases model library.
The present invention adopts the following technical scheme that：
The present invention provides a kind of analysis methods of dynamic diseases model library, are as follows：
S1, expert group establish disease model according to disease type and corresponding symptom；
Establish list of diseases, while symptom list be established below in list of diseases, the symptom list according to strong relation symptom S,
Middle relation symptom M and weak relation symptom W three classes distinguish；
The disease derivation formula that rule establishes disease and symptom is made a definite diagnosis according to disease：
O（x）=f(m1,m2,…,mn,w1,w2,…,wi)=b1X1+b2X2+…+bnXn+p1W1+p2w2…+piwi；
mnThere is n symptom m in representative in relation symptom sequence, middle relation symptom sequence is expressed as in a manner of array（m1,m2…
mn）, represented with M, wiRepresenting weak relation symptom sequence has j symptom w, and weak symptom sequence is expressed as in a manner of array（w1,
w2…wn）, represented with W；b1…bnIt is represented as being included in the middle corresponding weighted value of relation symptom of formula, value in diagnosed disease
Between 0 to 1, p1, p2…piRefer to formula quoting to the coefficient of weak relation symptom, coefficient value is between 0 to 1；
S2, all suitable case histories are selected form effective case history collection, and effective case history collection is input in disease model；
S3, disease model is updated when effective case history collection reaches certain amount, finally obtains new disease model；
S4, patient's related diseases are levied in data input model, symptom information and list of diseases are carried out discriminatory analysis by model, are used in combination
The various diseases and probability that the calculating of disease derivation formula is likely to occur, and various diseases and corresponding probability are pushed to clinical doctor
Raw user terminal.
Further, it is described to select effective case history collection specific steps and include：
1）It extracts the symptom occurred in all disease models respectively from case history content, forms the list of every part of case history extraction result
Q；
2）The symptom list of disease is obtained from disease model；
3）Then with 1）List Q and 2）The symptom list of acquisition is compared, when the strong relation symptom in symptom list should all
When appearing in list Q, which can just enter subsequent processing；Otherwise it is invalid case history；
4）Then the node in list Q is substituted into disease derivation formula and carries out reckoning probability of illness, when probability is more than setting most
During low valve valve, this case history can be included into effective case history collection of the disease.
Further, the value range of the minimum threshold values is 0-1.
Further, the step S3 disease models are updated specifically such as：
1）Corresponding symptom the results list Q of every part of case history in effective case history is concentrated in together and is carried out as parameter at analysis
Reason；
2）The correlation of symptom and disease is obtained after above-mentioned analyzing and processing, and is ranked up from high to low by the degree of correlation, is obtained
Get the symptom sequence Y of cum rights weight values；
Symptom sequence Y is expressed as（y1：r1, y2：r1, y3：r3……yk:rk）, wherein y is symptom title, and r is correlative weight weight values,
The correlation of installation disease arranges from high to low, and wherein k represents the sum of all symptom in case history model；
3）The symptom list of corresponding disease is obtained in disease model, with middle each symptom of relation symptom in symptom list and disease
Symptom in sign sequence Y is compared one by one, excludes the strong relation symptom of the disease first, rear as found to have in symptom sequence Y
It does not appear in the middle relation symptom in disease model and sequence has been located at any one in the middle relation symptom in disease model
When having before symptom, add it to and form Sino-Singaporean relations symptom M in original in relation symptomnew, and from the disease of disease model
Corresponding symptom is removed in weak relation symptom list；
4）Use 3）The M of middle acquisitionnewAnd WnewIt is compared with the node of the symptom list Q of all effective case histories of corresponding disease, it will be every
Symptom and M in a QnewMiddle symptom and WnewIn come top n symptom intersection Node extraction out form new list L,
Wherein N can be configured in systems, form list L collection；
5）New list L collection is substituted into disease derivation formula can obtain new derivation formula, thus new derivation formula and bag
Containing new MnewList of diseases constitute new disease model.
Further, the step S3 disease models are updated specifically such as：The step S3 reaches certain when effective case history collection
Disease model is updated during quantity, the quantitative range is more than 1000.
A kind of dynamic clinical disease model system is also disclosed, including Dynamic Inference machine, the Dynamic Inference is recorded respectively with information
Enter end to connect with user's end communication, be used for, the medical record information that receive information typing end is sent, the medical record information is believed including patient
The clinical data of breath and symptom information；For not yet diagnosed medical record information, derived according to the disease model in Dynamic Inference machine
Disease that may be present and probabilistic information, then disease and probabilistic information are sent to corresponding user terminal, as the corresponding doctor that sees and treat patients
Raw diagnosis reference；For the medical record information made a definite diagnosis, Dynamic Inference machine judges the validity of case history according to disease model, and will
It is judged as that effective case history is passed to medical records storage storehouse；
The dynamic clinical disease model system further includes medical records storage storehouse, and the medical records storage storehouse is used for receive information typing end
All medical record informations made a definite diagnosis and be judged as effective case history through Dynamic Inference machine being collected into；
Dynamic Inference machine extracts the case history collection of corresponding disease from medical records storage storehouse, and extracts the corresponding symptom in each case history, often
When case history collection reaches specified magnitude, Dynamic Inference machine starts the analysis to corresponding disease and the symptom degree of correlation, Dynamic Inference machine
According to the new symptom list of the symptom relevancy ranking after analysis, disease mould is adjusted according to new symptom list Dynamic Inference machine
Type.
Further, the Dynamic Inference machine includes Dynamic Inference module, disease model memory module, symptom extraction module and disease
Example analysis module, Dynamic Inference module are two-way with disease model memory module, symptom extraction module and analysis of cases module respectively
Communication connection；
Dynamic Inference module, the symptom list for symptom extraction module to be obtained are updated to disease model memory module and obtain disease
The probability of relevant disease is calculated in disease model；
Disease model memory module, for storing disease model, the disease model includes list of diseases, symptom list and disease
Derivation formula model；
Symptom extraction module goes through middle extraction disease for diagnosing a disease really out of the medical record information for the patient that sees and treat patients or the medical records storage storehouse
The symptom information processing is the symptom list Q for analysis of cases module analysis by the related symptom information of disease；
Analysis of cases module compares for the symptom list of symptom list Q and the disease model of corresponding disease, when disease model
The strong relation symptom of symptom list appears at symptom list Q, then calculates the probability of the disease；And for being carried out to each disease
Symptom Controlling UEP obtains symptom sequence Y, and symptom sequence Y is reached weight adjuster.
Further, the dynamic clinical disease model system further includes weight adjuster, for receiving analysis of cases module
Symptom sequence Y, and the weighted value in disease model is corrected, and compared one by one with symptom list and the symptom in symptom sequence Y,
Form new disease model.
Further, the symptom list Q represents specific as follows with array mode：
Q (disease name, case history sequence number)=（Symptom 1, value 1）,（Symptom 2, value 2）...,（Symptom n, value n）}；
Each node is made of title and value two parts in symptom list, and the form of wherein value is divided into three classes：（1）Have/
Without,（2）Numerical value,（3）Text sequence.
Further, the list Q interior nodes number is equal with the symptom number in the symptom storehouse of disease model.
Further, the strong relation symptom S, middle relation symptom M and weak relation symptom W are existed by the form of symptom list
It is embodied in disease model, it is as follows：
Symptom list be expressed as with array mode（Symptom 1, value 1）,（Symptom 2, value 2）…（Symptom i, value i）…（Symptom n, value
n）}；
Each node is made of title and value two parts in symptom list, and the form of wherein value is divided into three classes：（1）Have/
Without,（2）Numerical value,（3）Text sequence.
Compared with prior art, the beneficial effects of the present invention are：
The present invention is provided for clinician from the angle for breaking the limitation of solo practitioner experience and faced to reduce mistaken diagnosis probability as starting point
Bed auxiliary can improve diagnosis and treatment accuracy and patient satisfaction is promoted while speed, reduction patient sees a doctor a kind of information of cost
Treatment technology method and equipment.
The present invention is effectively melted in static clinical knowledge storehouse with big data method by a set of general dynamic diseases model library
Close out dynamic disease model, reach no matter hospital's size and no matter historical data how much may be employed the method carry out work
Make, while the factor for promoting disease model optimization can be converted at any time to existing and newly-increased medical data, to disease
Model library is adjusted into Mobile state.
The present invention can break through doctors experience limitation, promote the speed and accuracy rate of diagnosis, while beneficial to newly-increased clinical data
Clinical data is converted into experience by the promotion of quality immediately, makes the data of hospital really become available wealth.
【Description of the drawings】
Fig. 1 is dynamic diseases model analysis method flow schematic diagram；
Fig. 2 is dynamic clinical disease model system module diagram.
【Specific embodiment】
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, to this hair
It is bright to be further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and it is unlimited
The fixed present invention.
In addition, term " first ", " second " are only used for description purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include one or more this feature.In the description of the present invention, " multiple " are meant that two or more,
Unless otherwise specifically defined.
Shown in refer to the attached drawing 1, the above method is described in detail below：
Step 1：Expert group establishes disease model according to disease type and corresponding symptom；
Establish list of diseases, while symptom list be established below in list of diseases, the symptom list according to strong relation symptom, in
Relation symptom and weak relation symptom three classes distinguish.
In the present embodiment：
List of diseases includes heart failure, ischemic cardiomyopathy, adenomyosis and prostate etc., forms a complete disease
List, while symptom list is established below in corresponding disease specific, symptom list here refer to the definition with relevant disease
With the relevant feature of diagnosis, detailed includes medical history, history of operation, allergies, symptom, sign, inspection, inspection, habits and customs, property
Not, the information such as social living environment.Exemplified by heart failure：
The symptom list of heart failure includes：It is age, age bracket, diabetic history, hyperlipidemia, ischemic cerebrovascular disease, chronic
Obstructive lung disease, diastolic pressure, haemocyanin, serum sodium, Ln cholesterolemias, fever, dystonia and chilly etc.
Strong relation symptom：The fact that represented with S, there must be when referring to diagnosed disease, such as the trouble such as symptom, sign that there must be
The somatic reaction of person, it is also possible to such as the attribute of natural person, such as gender.Such as：From disease definition,
For example andropathy, patient must be males, it is impossible to be female patient；
Middle relation symptom：It is represented with M, refers to that clinical expert has reached common recognition, symptom need to confirm when making a definite diagnosis, essential, but
Each specific patient is directed to, may only have part symptom to occur, also be not excluded for the possibility all occurred；
Weak relation symptom：It is represented with W, then refers to it is possible that there is this symptom, without this symptom, in diagnosed disease, can also to make
To refer to, but not as pressure index.
It notes that simultaneously, as the mankind understand disease in depth, the relationship strength of symptom and disease is can be with
Conversion, particularly under different crowd, different geographical, different times or different habits and customs, though it is not received when defining disease
Enter strong relation symptom or middle relation symptom, it is likely that higher transformation.Therefore needs one being capable of dynamic disease
Model can contribute to clinician to be quickly diagnosed to be relevant disease according to what the conversion of relation symptom changed in real time, increase
Accuracy rate.
Strong relation symptom, middle relation symptom and weak relation symptom such as heart failure are distinguished：
Strong relation symptom：Coronary heart disease, hypertension
Middle relation symptom：Orthopnea difficulty, hepatojugular reflux, tachycardia, distension of jugular vein, lung's rale, heart
Hypertrophy, pulmonary edema, double lower limb oedema
Weak relation symptom：Shortness of breath, pleural effusion, hilus pulumonis increase, third heart sound gallop, hepatomegaly after activity
The present embodiment is as follows with being described in detail exemplified by heart failure：
S lists, M lists and W lists are represented as symptom list, be expressed as with array mode（Symptom 1, value 1）,（Symptom 2, value
2）…（Symptom i, value i）…（Symptom n, value n）, each node is by title in list（Symptom n）And value（Value n）Two parts
It forms, the form of wherein value is divided into three classes：（1）With/without,（2）Numerical value,（3）Text sequence（Dictionary value）, such as：Heart failure
Strong relation symptom symptom list, S（Heart failure）={（History of Coronary Heart Disease has）,（History of hypertension has）}
The symptom list of middle relation symptom, M（Heart failure）={（Orthopnea is difficult, has）,（Hepatojugular reflux has）,
（Tachycardia has）,（Distension of jugular vein has）,（Lung's rale, has）,（Cardiomegaly has）,（Cardiomegaly has）,（Edema with the lung involved
It is swollen, have）,（Double lower limb oedema, has）}
The symptom list of weak relation symptom, W（Heart failure）={（Shortness of breath after activity, has）,（Pleural effusion has）,（Hilus pulumonis increases
Greatly, have）,（Third heart sound gallop has）,（Hepatomegaly has）}.
The disease derivation formula that rule establishes disease and symptom is made a definite diagnosis according to disease：
O（x）=f(m1,m2,…,mn；w1,w2,…,wi)=b1X1+b2X2+…+bnXn+p1W1+p2w2…+piwi；
mnThere is n symptom m in representative in relation symptom sequence, middle relation symptom sequence is expressed as in a manner of array（m1,m2…
mn）, wiRepresenting weak relation symptom sequence has j symptom w, and middle relation symptom sequence is expressed as in a manner of array（w1,w2,…,wi）；
b1…bnIt is represented as being included in the middle corresponding weighted value of relation symptom of formula in diagnosed disease, value is between 0 to 1, p1,
p2…piRefer to formula quoting to the coefficient of weak relation symptom, coefficient value is between 0 to 1；
Such as one of heart failure case history, middle relation symptom sequence and weak relation symptom sequence are substituted into disease derivation formula
In：
O（It suffers from heart failure）=0.50 * hepatojugular reflux+0.25* orthopnea difficulty+0.15* pleural effusions+0.1*
Double lower limb oedema=0.50*1+0.25*1+ 0.15*1+0.1*1=1
S2, all suitable case histories are selected form effective case history collection, and effective case history collection is input in disease model；
It is described to select effective case history collection specific steps and include：
1）It is extracted respectively from case history content and occurs the description information of symptom and value in all disease models, form every part of case history
Extract the list Q of result；
Detailed list Q array modes here be expressed as Q (disease name, case history sequence number)=（Symptom 1, value 1）,（Symptom 2,
Value 2）...,（Symptom n, value n）}；List Q interior nodes number is equal with the symptom number in the symptom storehouse of disease model, symptom
Value form have three classes：（1）Numerical value（2）With/without/do not occur（3）Text sequence, numerical value refer to value table in digital form
It reaches, for example weight is 57kg, weight is symptom, and 57 be value, and it can be that the symptom that each result be numerical value specifies mark to establish before array
The unit of note presses unit conversion data during value；With/without/do not occur expression be whether symptom finds, by taking fever as an example, not
Possible situation is that have in same case history：There are this symptom, nothing corresponding to patient：Symptom is clearly denied in expression, does not occur：It represents
It is not described in case history；Text sequence refers to end value as textual form, similar to the expression of dictionary, such as in some case histories,
When Gender is levied for disease, male is one of its value, then may be that Gender value is female in other case histories
Property.By taking heart failure as an example, every part of case history we can obtain a vector table.
Such as：It is expressed as the 100th part of case history of heart failure, Q (heart failure, 100)=（Orthopnea is difficult,
Have）,（Hepatojugular reflux, nothing）,（Tachycardia has）,（Distension of jugular vein has）,（Fever, nothing）,（Age bracket, always
Year）... ....
2）The symptom list of disease is obtained from disease model；
That is S lists, M lists and W lists.
3）Then with 1）List Q and 2）The symptom list of acquisition is compared, when the strong relation symptom in symptom list
When should all appear in list Q, which can just enter subsequent processing；Otherwise it is invalid case history；
Noted here is that list Q is compared with S lists, when list Q does not occur the symptom in the S lists of the disease, then
The case history is not effective case history of the disease, will abandon the processing of next step；Otherwise, list Q and all there is the S of the disease
During symptom in list, then the case history is effective case history of the disease, just carries out the processing of next step
It is detailed by Q (heart failure, 100)=（Orthopnea is difficult, has）,（Hepatojugular reflux, nothing）,（Tachycardia,
Have）,（Distension of jugular vein has）,（Fever, nothing）,（Age bracket, it is old）... ... and S（Heart failure）={（History of Coronary Heart Disease,
Have）,（History of hypertension has）Comparison, the 100th part of case history contains History of Coronary Heart Disease and history of hypertension, therefore can carry out step
4）Work.
4）Then the node in list Q is substituted into disease derivation formula and carries out reckoning probability of illness, when probability is more than setting most
During low valve valve, the value range of the minimum threshold values is 0-1, this case history can be included into effective case history collection of the disease.
The minimum threshold values set in the present embodiment as 0.6, list Q's (heart failure, 100) at this time and in the present embodiment
Calculate that probability of illness is more than 0.6, therefore case history can be included into effective case history collection of heart failure.
S3, disease model is updated when effective case history collection reaches certain amount, finally obtains new disease model；
In the present embodiment, disease model is updated when effective case history collection reaches certain amount and refers to finger and heart failure
When exhausting associated effective case history quantity and reaching certain amount, aftermentioned update process flow can be started, quantity is equipped with initial here
Two class of magnitude and incremental magnitude, can adjust.Such as, the present embodiment sets Initial Quantity Order as 10000 parts, and it is 1000 to be incremented by magnitude
Part, then when suitable case history reaches 10000 parts, start the more new technological process of the derivation formula of the disease for the first time, when reach 11000,
12000th, 13000 parts, and so on, it is lasting to start more new technological process.
Step S3 disease models described in the present embodiment are updated specifically such as：
1）By the corresponding symptom result of every part of case history in effective case history（Heart failure）List Q is concentrated in together to be divided as parameter
Analysis is handled；
Here analyzing and processing mainly uses the processing equipment of software or interface service with single-factor analysis therapy computational algorithm, such as
Server with SPSS softwares or other Data Analysis Software.
2）The correlation of symptom and disease is obtained after above-mentioned analyzing and processing, and is arranged from high to low by the degree of correlation
Sequence gets the symptom sequence Y of cum rights weight values；
Symptom sequence Y is expressed as（y1：r1, y2：r1, y3：r3……yk:rk）, wherein y is symptom title, and r is correlative weight weight values,
It is arranged from high to low according to the correlation of disease, wherein k represents the sum of all symptom in case history model；
Different according to the analysis software used in the present embodiment, wherein k is the sum of all symptom in case history model, and r represents phase
Its value range of weighted value is closed as 0-1.Such as heart failure, the symptom sequence of heart failure is to be illustrated as Y（Heart failure）=（Year
Age：0.8, diastolic pressure：0.7, pulmonary edema 0.45, diabetes：0.5, distension of jugular vein：0.2, fever：0.01…）.
3）The symptom list of corresponding disease is obtained from disease model, with each disease of the middle relation symptom in symptom list
Sign is compared one by one with the symptom in symptom sequence Y, excludes the strong relation symptom of the disease first, rear as found symptom sequence
Have in Y and do not appear in the middle relation symptom in disease model and sort any one in the middle relation symptom in disease model
When before a existing symptom, add it to and form Sino-Singaporean relations symptom M in original in relation symptomnew, and being somebody's turn to do from disease model
Corresponding symptom is removed in the weak relation symptom list of disease；
As by taking heart failure as an example, in disease model, the original middle relationship characteristic of heart failure is M in the present embodiment（Mental and physical efforts
Failure）={（Orthopnea is difficult, has）,（Hepatojugular reflux has）,（Tachycardia has）,（Distension of jugular vein has）,
（Lung's rale, has）,（Cardiomegaly has）,（Cardiomegaly has）,（Pulmonary edema has）,（Double lower limb oedema, has）, it is now discovered that
Age bracket is located at before distension of jugular vein, so it is special to add it to middle relation, is updated to Mnew（Heart failure）={（It sits up straight
Expiratory dyspnea, has）,（Age bracket, it is old）,（Hepatojugular reflux has）,（Tachycardia has）,（Distension of jugular vein has）,
（Lung's rale, has）,（Cardiomegaly has）,（Cardiomegaly has）,（Pulmonary edema has）,（Double lower limb oedema, has）}；It sends out simultaneously
Now fever symptom is not above relation symptom in any one in M, so fever to be included into the weak relation symptom of heart failure
WnewIn.
4）Use 3）The M of middle acquisitionnewAnd WnewIt is compared with the node of the symptom list Q of all effective case histories of corresponding disease, it will be every
Symptom and M in a QnewMiddle symptom and WnewIn come top n symptom intersection Node extraction out form new list L,
Wherein N can be configured in systems, form list L collection；
Such as above-mentioned steps 3）In Mnew（Heart failure）With the section of the Q (heart failure, 100) of the 100th part of effective case history of heart failure
Point comparison, by all Mnew（Heart failure）The symptom that middle symptom is appeared in Q (heart failure, 100) is selected, while is added in and referred to
Determine the weak relation symptom of number, form new table L.New list L is as follows：
L (heart failure, 100)=（Orthopnea is difficult, has）,（Hepatojugular reflux, nothing）,（Tachycardia has）,（Neck
Venous engorgement has）,（Age bracket, it is old）... ....
By software or the processing equipment of interface service of the new list Q collection with single-factor analysis therapy computational algorithm, such as
Server with SPSS softwares or other Data Analysis Software is analyzed and processed, and symptom finally is reanalysed arrangement, tool
The relation of the centering again symptom of body and weak relation symptom distinguish, and finally obtain new disease derivation formula：
O（x）=f(m1,m2,…,mn；w1,w2,…,wi)=b1X1+b2X2+…+bnXn+p1W1+p2w2…+piwi；
Conversion here according to relation symptom changes in real time, therefore disease model derives public affairs according to the situation of conversion to disease in real time
Formula is updated effective guarantee accuracy rate.Symptom such as above-mentioned age bracket is converted into middle relation symptom by weak relation symptom, because
This influences the result that derivation formula derives very big.
It needs exist for illustrating, the relationship strength of symptom and disease can convert, particularly in different crowd, no
Under same region, different times or different habits and customs, though do not include strong relation symptom or middle relation symptom when defining disease,
It is possible that higher transformation.Therefore needs one can dynamically disease model can be according to the conversion reality of relation symptom
When the clinician that contributes to that changes quickly be diagnosed to be relevant disease, increase accuracy rate.
5）New list Q collection is substituted into disease derivation formula can obtain new derivation formula, thus new derivation formula
With include new MnewList of diseases constitute new disease model.
S4, patient's related diseases to be levied in data input model, symptom information and list of diseases are carried out discriminatory analysis by model,
And the various diseases being likely to occur and probability are calculated with disease derivation formula, and various diseases and corresponding probability are pushed to and faced
The user terminal of bed doctor.
After clinician sees and treat patients patient, collect patient's related diseases references breath first, including patient's medical history outside,
Present illness history, and pass through after the patient information that the means such as inquiry, inspection and inspection will be understood that summarizes all related symptom of patient, it will
In these related diseases sign data input disease model, disease model will be calculated according to the symptom information inputted it is possible that depositing
Disease and disease probability, disease that may be present mentioned here is more than one, and the probability of the disease and disease supplies
Reference for clinicians.
Shown in refer to the attached drawing 2, a kind of dynamic clinical disease model system is also disclosed, it is described dynamic including Dynamic Inference machine
State inference machine is connected respectively with data input end and user's end communication, is used for,
The medical record information that receive information typing end is sent, the medical record information include patient information and the clinical number of symptom information
According to；For not yet diagnosed medical record information, disease that may be present and probability are derived according to the disease model in Dynamic Inference machine
Information, then disease and probabilistic information are sent to corresponding user terminal, the diagnosis as the doctor that accordingly sees and treat patients refers to；For really
The medical record information examined, Dynamic Inference machine judge the validity of case history according to disease model, and will be deemed as effective case history and be passed to
Medical records storage storehouse；
The dynamic clinical disease model system further includes medical records storage storehouse, and the medical records storage storehouse is used for receive information typing end
All medical record informations made a definite diagnosis and be judged as effective case history through Dynamic Inference machine being collected into；
Dynamic Inference machine extracts the case history collection of corresponding disease from medical records storage storehouse, and extracts the corresponding symptom in each case history, often
When case history collection reaches specified magnitude, Dynamic Inference machine starts the Controlling UEP to corresponding disease and symptom, Dynamic Inference machine
According to the new symptom list of the symptom relevancy ranking after analysis, disease mould is adjusted according to new symptom list Dynamic Inference machine
Type.
Here data input end is generally referred to as hospital can communicate the computer or intelligent handhold of connection with the system
Equipment, such as the computer of doctor workstation.The PC ends or intelligent handheld device that the when clinician that user's end communication refers to uses, it is main
It is used to receive Dynamic Inference machine by calculating the result obtained.Dynamic Inference machine is it is also assumed that be the system service on backstage
Device.
It is to be noted that communication connection mentioned here includes wire communication connection and invalid communication connects, the present embodiment
Middle Dynamic Inference machine employs terminal device communication connection relevant with hospital, and terminal device includes the display screen and PC of hospital
The equipment such as end.
Further, the Dynamic Inference machine includes Dynamic Inference module, disease model memory module, symptom extraction module
With analysis of cases module, Dynamic Inference module respectively with disease model memory module, symptom extraction module and analysis of cases module
Both-way communication connects；
Dynamic Inference module, the symptom list for symptom extraction module to be obtained are updated to disease model memory module and obtain disease
The probability of relevant disease is calculated in disease model；
Disease model memory module, for storing disease model, the disease model includes list of diseases, symptom list and disease
Derivation formula model；
Symptom extraction module goes through middle extraction disease for diagnosing a disease really out of the medical record information for the patient that sees and treat patients or the medical records storage storehouse
The symptom information processing is the symptom list Q for analysis of cases module analysis by the related symptom information of disease；
Analysis of cases module compares for the symptom list of symptom list Q and the disease model of corresponding disease, when disease model
The strong relation symptom of symptom list appears at symptom list Q, then calculates the probability of the disease；And for being carried out to each disease
Symptom Controlling UEP obtains symptom sequence Y, and symptom sequence Y is reached weight adjuster.
Further, the dynamic clinical disease model system further includes weight adjuster, for receiving analysis of cases module
Symptom sequence Y, and the weighted value in disease model is corrected, and compared one by one with symptom list and the symptom in symptom sequence Y,
Form new disease model.
Further, the symptom extraction module, analysis of cases module, weight adjuster and Dynamic Inference machine, should all
It runs at least one CPU, but is not excluded for being applied to distributed arithmetic, such as the deployment of SAAS patterns.
Further, disease model memory module and medical records storage storehouse be using independent DB storage modes, can also be used point
The storage device of cloth stores.
The medical auxiliary system that the present invention is built is implemented from medical institutions' scale, opened for business time and the past information-based water
Flat limitation, the original state based on disease model can be applied to clinic, and can be used during medical institutions subsequently open for business
The historical data of medical institutions and newly-increased data carry out disease model to continue amendment, and model can be applied to clinic again after amendment,
So as to form closed-loop data chain, make the production of data with using harmony has been reached, can use immediately, while this data-link
It is open data-link, can be included in the data of external hospital.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
All any modification, equivalent and improvement made within principle etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of analysis method of dynamic diseases model library, it is characterised in that：It is as follows：
S1, expert group establish disease model according to disease type and corresponding symptom；
Establish list of diseases, while symptom list be established below in list of diseases, the symptom list according to strong relation symptom S,
Middle relation symptom M and weak relation symptom W three classes distinguish；
The disease derivation formula that rule establishes disease and symptom is made a definite diagnosis according to disease：
O（x）=f(m1,m2,…,mn,w1,w2,…,wi)=b1X1+b2X2+…+bnXn+p1W1+p2w2…+piwi；
mnThere are n symptom m, middle relation symptom sequence M to be expressed as in a manner of array in representative in relation symptom sequence（m1,m2…
mn）, wiRepresenting weak relation symptom sequence has i symptom w, weak relation symptom sequence W to be expressed as in a manner of array（w1,w2…wi）；
b1…bnIt is represented as being included in the middle corresponding weighted value of relation symptom of formula in diagnosed disease, value is between 0 to 1, p1,
p2…piRefer to formula quoting to the coefficient of weak relation symptom, coefficient value is between 0 to 1；
S2, all suitable case histories are selected form effective case history collection, and effective case history collection is input in disease model；
S3, the disease model of corresponding disease is updated when effective case history collection reaches certain amount, finally obtains new disease
Model；
S4, patient's related diseases are levied in data input model, model meets strong in disease model according to the selection of symptom information first
The list of diseases of relation symptom uses the disease derivation formula various diseases that are likely to occur of calculating of corresponding list of diseases and general afterwards
Rate, and various diseases and corresponding probability are pushed to the user terminal of clinician.
2. the analysis method of dynamic diseases model library as described in claim 1, it is characterised in that：It is described to select effective case history collection
Specific steps include：
1）It extracts the symptom occurred in all disease models respectively from case history content, forms the symptom of every part of case history extraction result
List Q；
2）The symptom list of the diagnosed disease of corresponding case history and corresponding derivation formula are obtained from disease model；
3）Then with 1）List Q and 2）The symptom list of acquisition is compared, when the strong relation symptom in model symptom list
When should all appear in list Q, which can just enter subsequent processing；Otherwise it is invalid case history；
4）Then the symptom node in list Q is substituted into disease derivation formula and carries out reckoning probability of illness, when probability is more than setting
Minimum threshold values when, this case history can be included into effective case history collection of the disease.
3. the analysis method of dynamic diseases model library as claimed in claim 2, it is characterised in that：The scope of the minimum threshold values
It is worth for 0-1.
4. the analysis method of dynamic diseases model library as described in claim 1, it is characterised in that：The step S3 disease models
It is updated specific as follows：
1）Every part of symptom the results list Q in the effective case history of same disease is concentrated in together and is analyzed and processed as parameter；
2）The correlation of symptom and disease is obtained after above-mentioned analyzing and processing, and is ranked up from high to low by the degree of correlation, is obtained
Get the symptom sequence Y of cum rights weight values；Symptom sequence Y is expressed as（y1：r1, y2：r1, y3：r3……yk:rk）, wherein y is symptom,
R is correlative weight weight values, is arranged from high to low according to the correlation with disease, and wherein k represents the total of all symptom in case history model
Number；
3）The symptom list of corresponding disease is obtained from disease model, with the middle relation symptom in symptom list and symptom sequence Y
In symptom compared one by one, exclude the strong relation symptom of the disease first, it is rear as found not appearing in symptom sequence Y
In middle relation symptom in disease model and sequence be located at disease model in middle relation symptom in any one have symptom it
When preceding, add it to and form Sino-Singaporean relations symptom M in original in relation symptomnew, and it is sick from the weak relation of the disease of disease model
Corresponding symptom is removed in sign list W and forms new weak relation symptom Wnew；
4）Use 3）The M of middle acquisitionnewAnd WnewIt is compared one by one with the node of the symptom list Q of all effective case histories of corresponding disease,
By each Q and MnewMiddle symptom and and WnewIn come top n symptom intersection symptom Node extraction out form new row
Table L, wherein N can be configured in systems, form list L collection；
5）New list L collection is substituted into disease derivation formula can obtain new derivation formula, thus new derivation formula and bag
Containing new MnewAnd WnewSymptom list constitute new disease model.
5. the analysis method of dynamic diseases model library as described in claim 1, it is characterised in that：The step S3 disease models
It is updated specifically such as：The step S3 is updated disease model when effective case history collection reaches certain amount, the number
It is more than 1000 to measure scope.
6. a kind of dynamic clinical disease model system, it is characterised in that：
Including Dynamic Inference machine, the Dynamic Inference machine is connected respectively with data input end and user's end communication, is used for,
The medical record information that receive information typing end is sent, the medical record information include patient information and the clinical number of symptom information
According to；For not yet diagnosed medical record information, disease that may be present and probability are derived according to the disease model in Dynamic Inference machine
Information, then disease and probabilistic information are sent to corresponding user terminal, the diagnosis as the doctor that accordingly sees and treat patients refers to；For really
The medical record information examined, Dynamic Inference machine judge the validity of case history according to disease model, and will be deemed as effective case history and be passed to
Medical records storage storehouse；
The dynamic clinical disease model system further includes medical records storage storehouse, and the medical records storage storehouse is used for receive information typing end
All medical record informations made a definite diagnosis and be judged as effective case history through Dynamic Inference machine being collected into；
Dynamic Inference machine extracts the case history collection of corresponding disease from medical records storage storehouse, and extracts the corresponding symptom in each case history, often
When case history collection reaches specified magnitude, Dynamic Inference machine starts the analysis to corresponding disease and the symptom degree of correlation, Dynamic Inference machine
According to the new symptom list of the symptom relevancy ranking after analysis, disease mould is adjusted according to new symptom list Dynamic Inference machine
Type.
7. dynamic clinical disease model system as claimed in claim 6, it is characterised in that：The Dynamic Inference machine includes dynamic
Reasoning module, disease model memory module, symptom extraction module and analysis of cases module, Dynamic Inference module respectively with disease mould
Type memory module, symptom extraction module are connected with analysis of cases module both-way communication；
Dynamic Inference module, the symptom list for symptom extraction module to be obtained are updated to disease model memory module and obtain disease
The probability of relevant disease is calculated in disease model；
Disease model memory module, for storing disease model, the disease model includes list of diseases, symptom list and disease
Derivation formula model；
Symptom extraction module goes through middle extraction disease for diagnosing a disease really out of the medical record information for the patient that sees and treat patients or the medical records storage storehouse
The symptom information processing is the symptom list Q for analysis of cases module analysis by the related symptom information of disease；
Analysis of cases module compares for the symptom list of symptom list Q and the disease model of corresponding disease, when disease model
The strong relation symptom of symptom list appears at symptom list Q, then calculates the probability of the disease；And for being carried out to each disease
Symptom Controlling UEP obtains symptom sequence Y, and symptom sequence Y is reached weight adjuster.
8. dynamic clinical disease model system as claimed in claim 6, it is characterised in that：The dynamic clinical disease model system
System further includes weight adjuster, for receiving the symptom sequence Y of analysis of cases module, and corrects the weight number in disease model
Value, and compared one by one with symptom list and the symptom in symptom sequence Y, form new disease model.
9. dynamic clinical disease model system as claimed in claim 7, it is characterised in that：The symptom list Q array sides
Formula represents specific as follows：
Q (disease name, case history sequence number)=（Symptom 1, value 1）,（Symptom 2, value 2）...,（Symptom n, value n）}；
Each node is made of title and value two parts in symptom list, and the form of wherein value is divided into three classes：（1）Have/
Without,（2）Numerical value,（3）Text sequence.
10. dynamic clinical disease model system as described in claim 1, it is characterised in that：The strong relation symptom S, middle pass
It is that symptom M and weak relation symptom W are embodied by the form of symptom list in disease model, it is as follows：
Symptom list be expressed as with array mode（Symptom 1, value 1）,（Symptom 2, value 2）…（Symptom i, value i）…（Symptom n, value
n）}；
Each node is made of title and value two parts in symptom list, and the form of wherein value is divided into three classes：（1）Have/
Without,（2）Numerical value,（3）Text sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711424873.5A CN108091399A (en) | 2017-12-25 | 2017-12-25 | A kind of analysis method and system of dynamic diseases model library |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711424873.5A CN108091399A (en) | 2017-12-25 | 2017-12-25 | A kind of analysis method and system of dynamic diseases model library |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108091399A true CN108091399A (en) | 2018-05-29 |
Family
ID=62179320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711424873.5A Pending CN108091399A (en) | 2017-12-25 | 2017-12-25 | A kind of analysis method and system of dynamic diseases model library |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108091399A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492107A (en) * | 2018-11-21 | 2019-03-19 | 上海依智医疗技术有限公司 | A kind of method and device of hospital guide |
| 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 |
| CN109840932A (en) * | 2019-01-23 | 2019-06-04 | 平安科技（深圳）有限公司 | Cardiovascular and cerebrovascular disease methods of exhibiting, device, equipment and storage medium |
| CN110232977A (en) * | 2019-06-12 | 2019-09-13 | 吉林大学第一医院 | Patients with lung cancer and its living environment correlation research method based on big data |
| WO2019237888A1 (en) * | 2018-06-15 | 2019-12-19 | 朱一帆 | Disease state information research method and system, and storage medium |
| CN111724873A (en) * | 2020-06-18 | 2020-09-29 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
| CN111899870A (en) * | 2020-08-05 | 2020-11-06 | 山东劳动职业技术学院（山东劳动技师学院） | Meridian and prescription diagnosis program based on typhoid fever and miscellaneous disease theory |
| CN117116497A (en) * | 2023-10-16 | 2023-11-24 | 长春中医药大学 | Clinical care management system for gynecological diseases |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001331581A (en) * | 2000-05-22 | 2001-11-30 | Yusuke Tsukamoto | System and method for automatic diagnosis, system and method for automatically determining medically treating method, and recording medium |
| CN1423789A (en) * | 2000-02-14 | 2003-06-11 | 第一咨询公司 | Automated diagnostic system and method |
| CN102110192A (en) * | 2011-04-02 | 2011-06-29 | 中国医学科学院医学信息研究所 | Auxiliary disease judgment method based on diagnostic element data association |
| CN102184315A (en) * | 2011-04-02 | 2011-09-14 | 中国医学科学院医学信息研究所 | Department triage system based on diagnostic element analysis |
| US20150169833A1 (en) * | 2013-12-16 | 2015-06-18 | Ulli Waltinger | Method and System for Supporting a Clinical Diagnosis |
| CN106886677A (en) * | 2017-01-13 | 2017-06-23 | 深圳市前海安测信息技术有限公司 | The system and method for aiding in doctor's diagnosis and treatment |
| CN106951719A (en) * | 2017-04-10 | 2017-07-14 | 荣科科技股份有限公司 | The construction method and constructing system of clinical diagnosis model, clinical diagnosing system |
| CN107038343A (en) * | 2017-04-10 | 2017-08-11 | 荣科科技股份有限公司 | Construction method and constructing system, the clinical diagnosing system of clinical diagnosis model |
| CN107463783A (en) * | 2017-08-16 | 2017-12-12 | 安徽影联乐金信息科技有限公司 | A kind of Clinical Decision Support Systems and decision-making technique |
-
2017
- 2017-12-25 CN CN201711424873.5A patent/CN108091399A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1423789A (en) * | 2000-02-14 | 2003-06-11 | 第一咨询公司 | Automated diagnostic system and method |
| JP2001331581A (en) * | 2000-05-22 | 2001-11-30 | Yusuke Tsukamoto | System and method for automatic diagnosis, system and method for automatically determining medically treating method, and recording medium |
| CN102110192A (en) * | 2011-04-02 | 2011-06-29 | 中国医学科学院医学信息研究所 | Auxiliary disease judgment method based on diagnostic element data association |
| CN102184315A (en) * | 2011-04-02 | 2011-09-14 | 中国医学科学院医学信息研究所 | Department triage system based on diagnostic element analysis |
| US20150169833A1 (en) * | 2013-12-16 | 2015-06-18 | Ulli Waltinger | Method and System for Supporting a Clinical Diagnosis |
| CN106886677A (en) * | 2017-01-13 | 2017-06-23 | 深圳市前海安测信息技术有限公司 | The system and method for aiding in doctor's diagnosis and treatment |
| CN106951719A (en) * | 2017-04-10 | 2017-07-14 | 荣科科技股份有限公司 | The construction method and constructing system of clinical diagnosis model, clinical diagnosing system |
| CN107038343A (en) * | 2017-04-10 | 2017-08-11 | 荣科科技股份有限公司 | Construction method and constructing system, the clinical diagnosing system of clinical diagnosis model |
| CN107463783A (en) * | 2017-08-16 | 2017-12-12 | 安徽影联乐金信息科技有限公司 | A kind of Clinical Decision Support Systems and decision-making technique |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019237888A1 (en) * | 2018-06-15 | 2019-12-19 | 朱一帆 | Disease state information research method and system, and storage medium |
| CN109492107A (en) * | 2018-11-21 | 2019-03-19 | 上海依智医疗技术有限公司 | A kind of method and device of hospital guide |
| 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 |
| CN109840932A (en) * | 2019-01-23 | 2019-06-04 | 平安科技（深圳）有限公司 | Cardiovascular and cerebrovascular disease methods of exhibiting, device, equipment and storage medium |
| CN110232977A (en) * | 2019-06-12 | 2019-09-13 | 吉林大学第一医院 | Patients with lung cancer and its living environment correlation research method based on big data |
| CN111724873A (en) * | 2020-06-18 | 2020-09-29 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
| CN111724873B (en) * | 2020-06-18 | 2024-01-09 | 北京嘉和海森健康科技有限公司 | Data processing method and device |
| CN111899870A (en) * | 2020-08-05 | 2020-11-06 | 山东劳动职业技术学院（山东劳动技师学院） | Meridian and prescription diagnosis program based on typhoid fever and miscellaneous disease theory |
| CN117116497A (en) * | 2023-10-16 | 2023-11-24 | 长春中医药大学 | Clinical care management system for gynecological diseases |
| CN117116497B (en) * | 2023-10-16 | 2024-01-12 | 长春中医药大学 | Clinical care management system for gynecological diseases |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108091399A (en) | A kind of analysis method and system of dynamic diseases model library | |
| CN107239665B (en) | Medical information query system and method | |
| CN109830303A (en) | Clinical data mining analysis and aid decision-making method based on internet integration medical platform | |
| CN110249392A (en) | Intelligent assisting in diagnosis and treatment system and method | |
| CN111666477A (en) | Data processing method and device, intelligent equipment and medium | |
| US20080021288A1 (en) | Method and system for generating personalized health information with accommodation for consumer health terminology | |
| KR20020077671A (en) | System and method of decision making | |
| CN114639479A (en) | Intelligent diagnosis auxiliary system based on medical knowledge map | |
| CN114003734B (en) | Knowledge system and knowledge map system of breast cancer risk factors and construction method | |
| CN112786198A (en) | Diagnosis and treatment information recommendation model construction method, diagnosis and treatment information recommendation method and device | |
| JP6908977B2 (en) | Medical information processing system, medical information processing device and medical information processing method | |
| CN114072782A (en) | Question recommendation method, device and system, electronic equipment and readable storage medium | |
| CN110019410A (en) | For the big data digging system of tcm clinical case information | |
| US20210192365A1 (en) | Computer device, system, readable storage medium and medical data analysis method | |
| US20240312575A1 (en) | System and method for automatically determining serious adverse events | |
| US20060106744A1 (en) | Apparatus and method for establishing knowledge database used in expert system and recording medium therefor | |
| WO2021169203A1 (en) | Monogenic disease name recommendation method and system based on multi-level structural similarity | |
| CN108206056A (en) | A kind of nasopharyngeal carcinoma artificial intelligence assisting in diagnosis and treatment decision terminal | |
| US20230316095A1 (en) | Systems and methods for automated scribes based on knowledge graphs of clinical information | |
| CN115938565A (en) | Tumor assistant decision support system based on intelligent reasoning and evidence correlation | |
| CN114743647A (en) | Medical data processing method, device, equipment and storage medium | |
| Nasiri et al. | A medical case-based reasoning approach using image classification and text information for recommendation | |
| US20240145054A1 (en) | Ontological Standards Based Approach To Charting Utilizing A Generic Concept Content Based Framework Across Multiple Localized Proprietary Domains | |
| CN118262933A (en) | Personalized patient treatment suggestion system based on large language model | |
| US20150169833A1 (en) | Method and System for Supporting a Clinical Diagnosis |
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 |