CN106295229A - Kawasaki disease hierarchical prediction method based on medical data modeling - Google Patents
Kawasaki disease hierarchical prediction method based on medical data modeling Download PDFInfo
- Publication number
- CN106295229A CN106295229A CN201610766242.0A CN201610766242A CN106295229A CN 106295229 A CN106295229 A CN 106295229A CN 201610766242 A CN201610766242 A CN 201610766242A CN 106295229 A CN106295229 A CN 106295229A
- Authority
- CN
- China
- Prior art keywords
- data
- modeling
- mucocutaneous lymphnode
- lymphnode syndrome
- sample
- 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
- 208000011200 Kawasaki disease Diseases 0.000 title claims abstract description 47
- 208000001725 mucocutaneous lymph node syndrome Diseases 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012360 testing method Methods 0.000 claims description 10
- 206010037660 Pyrexia Diseases 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000009795 derivation Methods 0.000 claims description 6
- 102100032752 C-reactive protein Human genes 0.000 claims description 4
- 235000011552 Rhamnus crocea Nutrition 0.000 claims description 4
- 206010051495 Strawberry tongue Diseases 0.000 claims description 4
- 241000759263 Ventia crocea Species 0.000 claims description 4
- 210000000265 leukocyte Anatomy 0.000 claims description 4
- 210000001165 lymph node Anatomy 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 claims description 2
- 108010082126 Alanine transaminase Proteins 0.000 claims description 2
- 108010074051 C-Reactive Protein Proteins 0.000 claims description 2
- 208000010201 Exanthema Diseases 0.000 claims description 2
- 108020004206 Gamma-glutamyltransferase Proteins 0.000 claims description 2
- 102000001554 Hemoglobins Human genes 0.000 claims description 2
- 108010054147 Hemoglobins Proteins 0.000 claims description 2
- LPQOADBMXVRBNX-UHFFFAOYSA-N ac1ldcw0 Chemical compound Cl.C1CN(C)CCN1C1=C(F)C=C2C(=O)C(C(O)=O)=CN3CCSC1=C32 LPQOADBMXVRBNX-UHFFFAOYSA-N 0.000 claims description 2
- 210000000222 eosinocyte Anatomy 0.000 claims description 2
- 210000003743 erythrocyte Anatomy 0.000 claims description 2
- 201000005884 exanthem Diseases 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 102000006640 gamma-Glutamyltransferase Human genes 0.000 claims description 2
- 210000003714 granulocyte Anatomy 0.000 claims description 2
- 210000002751 lymph Anatomy 0.000 claims description 2
- 210000004698 lymphocyte Anatomy 0.000 claims description 2
- 210000005087 mononuclear cell Anatomy 0.000 claims description 2
- 230000003448 neutrophilic effect Effects 0.000 claims description 2
- 210000003800 pharynx Anatomy 0.000 claims description 2
- 206010037844 rash Diseases 0.000 claims description 2
- 238000004062 sedimentation Methods 0.000 claims description 2
- 208000024891 symptom Diseases 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 abstract description 6
- 201000010099 disease Diseases 0.000 abstract description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000012216 screening Methods 0.000 abstract 2
- 238000011369 optimal treatment Methods 0.000 abstract 1
- 230000002265 prevention Effects 0.000 abstract 1
- 238000011282 treatment Methods 0.000 abstract 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 4
- 208000006011 Stroke Diseases 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 206010002329 Aneurysm Diseases 0.000 description 1
- 108060003951 Immunoglobulin Proteins 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 102000018358 immunoglobulin Human genes 0.000 description 1
- 230000002757 inflammatory effect Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a hierarchical prediction method for Kawasaki disease based on medical data modeling, which comprises the following steps of 1: selecting a data sample; extracting effective samples available for modeling from the sample data set; step 2: characteristic screening; screening 19 features which accord with the field medical auxiliary diagnosis application from the feature set of the constructed sample data for modeling; and step 3: and constructing and evaluating a Kawasaki disease hierarchical model. According to the invention, the data related to the Kawasaki disease is analyzed and modeled systematically, and an evaluation method for model prediction is provided, so that the Kawasaki disease of a patient can be diagnosed effectively and auxiliarily based on the Kawasaki disease data, and effective prevention intervention and treatment are carried out in the early stage of disease incidence, so that a basis is provided for achieving the optimal treatment effect.
Description
Technical field
The present invention relates to MEDICAL PREDICTION technical field, specifically, relate to a kind of mucocutaneous lymphnode syndrome based on medical data modeling
Grade predicting method.
Background technology
Mucocutaneous lymphnode syndrome (Kawasaki disease, KD) is a kind of acute, self limiting and agnogenic acute inflammatory blood
Guan Yan, has become as modal infant acquired heart disease at present.If mucocutaneous lymphnode syndrome baby could not be diagnosed in time with quiet
Arteries and veins injecting immune globulin (IVIG) is treated, and may result in coronary artery expansion or aneurysm.The morbidity machine of current mucocutaneous lymphnode syndrome
Reason the unknown, does not has effective diagnostic test method, it is easy to be misdiagnosed as commonly having a fever.Additionally, there is the river of cardiovascular sequela
Rugged sufferer youngster may be caused myocardial infarction and dead probability to be 25% by mistaken diagnosis.
Mucocutaneous lymphnode syndrome classification prediction model based on medical data modeling can assist diagnosis, contributes to reducing its misdiagnosis rate,
Improve its follow-up therapeutic process further.The mucocutaneous lymphnode syndrome disaggregated model many employings linear methods based on data that presently, there are, allusion quotation
Type is represented as linear discriminant analysis method.
The model of linear method structure is simple, and result is prone to be understood by doctor, but can not effectively utilize data sample special
The non-linear factor levied, improves model performance and accuracy.
Summary of the invention
For solving problem above, a kind of based on medical data the mucocutaneous lymphnode syndrome grade predicting method that the present invention provides, will treat
Diagnosis patient is divided into danger high-risk, middle, low danger three grades, the diagnosis knot that temporarily cannot determine with high confidence level due to reasons such as small samples
Fruit can be classified as middle danger rank to wait to further look at, and the forecast accuracy of high risk patient is also protected.It is concrete
Technical scheme is as follows:
A kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data modeling, it comprises the following steps:
Step 1: data sample selects；Extraction is concentrated to be available for the effective sample of modeling from sample data；
Step 2: Feature Selection；From build sample data characteristic set filter out meet live medical auxiliary diagnosis should
19 features be modeled；
Step 3: mucocutaneous lymphnode syndrome hierarchy model builds and evaluates, and its step is as follows:
(3.1) use the mode of random division, be training set Xtrain, test set Xtest and checking by Segmentation of Data Set
Collection Xderivation tri-part, ratio is 2:1:1；
(3.2) use SVM homing method matching Xtrain data set in training set, use gaussian kernel function, modeled
Journey uses ten folding cross validation Selection Model parameters, record optimal models parameter and support vector sequence number；
(3.3) derivation collection is used to calculate classification thresholds t according to regression modelcaseWith tcontrol；
(3.4) combine derivation collection classification thresholds, carry out the classification prediction of test set sample.
Further, in step 1, data sample selection course includes:
(1.1) to incomplete, wrong data, its value is set to sky；
(1.2) counterweight complex data is deleted；
(1.3) data nonstandard to form, are uniformly processed as numeric format by numeric coding mode.
Further, in step (3.3), tcaseFor positive label or the threshold value that is called case (case), tcontrolFor negative label
Or it is called the threshold value of comparison (control)；More than tcaseBe classified to high risk patient, less than tcontrolBe classified to low
Danger patient, remaining is divided into middle danger patient.
Further, in step (3.3), carry out as follows:
A. assuming that deriving intensive data number of samples is S, calculating according to regression model derives intensive data sample whether river
The Probability p of rugged disease,；
B. p is arranged according to order from big to small, it is assumed that whenTime, tcase=p；It is more than or equal under current order
All samples of this value are case；
C. p is arranged according to order from small to large, whenTime, tcontrol=p, less than or equal to this under current order
All samples of value are comparison.
Further, described in step 2 19 be characterized as:
(2.1) Clinical symptoms:
The most whether have a fever more than 38.3 degrees Celsius (Fever > 38.3 DEG C or 100.5 °F :)
The most whether there is erythra (Rash)
C. two (Red eyes) the most rubescent
The most whether swallow lip red, red or strawberry tongue (Red pharynx, red lips, or strawberry tongue)
The most whether cervical lymph node > 1.5 centimetres (Cervical lymph node > 1.5cm)
The reddest or swollen hands/foot or hands/foot decortication (Red or swollen hands/feet or peeling of
hands/feet)
The most ill natural law (Days of illness)
(2.2) experimental data:
A. white blood cell concentration (WBC × 103/mm3)
B. neutrophilic granulocyte concentration (POLYS%)
C. banding nuclear concentration (BANDS%)
D. lymphocyte concentration (Lymphs%)
E. mononuclear cell concentration (MONOS%)
F. eosinophilic granulocyte concentration (EOS%)
G. hemoglobin concentration (HGB mg/dl)
H. PC (PLTS × 103/mm3)
I. erythrocyte sedimentation rate (ESR mm/h)
J.C-reactive protein (CRP mg/dl)
K. alanine aminotransferase (ALT IU/L)
L. glutamyl transpeptidase (GGT IU/L).
A kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data provided by the present invention, has the advantage that
The present invention uses the medical data relevant to mucocutaneous lymphnode syndrome to carry out the analysis of system, modeling, and provides model evaluation side
Method, can effectively assist based on medical data mucocutaneous lymphnode syndrome to diagnose by this model, contribute to reducing its misdiagnosis rate, change further
Enter its follow-up therapeutic process.
Accompanying drawing explanation
Fig. 1 is the workflow diagrams of a kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data modeling of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawings and embodiments of the invention to the present invention a kind of based on medical data modeling mucocutaneous lymphnode syndrome divide
Level Forecasting Methodology is described in further detail.
The medical data that present invention is primarily based in electronic health record is modeled, and uses the information contained in data to patient
Whether suffer from mucocutaneous lymphnode syndrome to be predicted, and will predict the outcome and carry out randomization description.This invention includes carrying out for medical data
The flow chart of data processing of modeling and carry out mucocutaneous lymphnode syndrome classification important method and the result such as prediction, analysis, randomization.This invention combines
Medical data and data digging method, be a kind of innovation of being combined with big data analysing method of medical data, and this invention is one
Determine to have filled up in degree the blank of domestic medical data research, in terms of utilizing medical data to carry out mucocutaneous lymphnode syndrome classification forecast analysis
There is novelty.
This invention uses medical data to derive from the fever of children electron-like medical record information collected in hospital database, data
Middle main information includes clinical data and experimental data and patient's mucocutaneous lymphnode syndrome classification.As it is shown in figure 1, river based on medical data
Rugged sick grade predicting method specifically comprises the following steps that
1. samples selection
Raw data set is dataset1, and shortage of data serious patient is removed from data set, and now data set is
dataset2。
2. Feature Selection
For dataset2, carry out Feature Selection, calculate the variance of each feature character pair value, remove variance close to 0
Feature, now data set is dataset3.
3. mucocutaneous lymphnode syndrome disaggregated model builds
1) by Segmentation of Data Set be training set Xtrain, test set Xtest and derive collection X derivation tri-part, than
Example
For 2:1:1；
2) using SVM homing method to be modeled on Xtrain, modeling selects kernel function to be radial direction base core, regulates parameter
For sigma, C, carry out model evaluation by repeating the ten folding cross validations of ten times, choose optimal models.
4. according to deriving collection structure hierarchy model and to test set data prediction
1) use training set and SVM homing method to set up regressive prediction model, concentrate each patient to predict its point to deriving
Class scoring probability.
2) scoring probability of being classified by mucocutaneous lymphnode syndrome arranges according to ascending order, when classification score is more than a certain value, calculates more than being somebody's turn to do
Proportion in the record of value.Assuming to exist threshold value p, classification score is more than 90% more than mucocutaneous lymphnode syndrome number ratio in the crowd of p,
Now, obtaining the classification score patient more than p has the probability of more than 90% to suffer from mucocutaneous lymphnode syndrome, and its probability suffering from mucocutaneous lymphnode syndrome is
More than 90%.
3) test set is carried out mucocutaneous lymphnode syndrome classification prediction, calculates score of classifying accordingly.More than 90 points, it was predicted that it is Kawasaki
Sick high risk patient, is low danger patient less than 10%, and it is follow-up that remaining then needs doctor to do according to practical situation for middle danger patient again
Observe.
Randomization marking calculate detailed process: according in test set mucocutaneous lymphnode syndrome classification score, calculate a series of threshold value p1,
P2, p3 ..., p10, corresponding marking is 10,20,30 ..., 100, for deriving the patient concentrated, calculate its mucocutaneous lymphnode syndrome and classify
Point, this score must fall at certain interval [pi, p (i+1)], according to the corresponding probability of mucocutaneous lymphnode syndrome classification score value and pi, p (i+1)
Change marking, mucocutaneous lymphnode syndrome score value can be calculated by linear gauge.
Embodiment 1:
In order to verify the effectiveness of a kind of based on medical data modeling the mucocutaneous lymphnode syndrome grade predicting method of the present invention, this reality
Executing example scope access time is 894 patient datas in 2005.11-2013.6 electronic health record.
1, data process:
Use data set to have form according to the present invention to be: often row is expressed as the information of a patient, and each column represents one
Aspect information, such as ID, health check-up information, mucocutaneous lymphnode syndrome classification etc., data set format such as form 1.Raw data set comprises 918 patients
Data, 19 features, wherein 36 are repeated data record by removal from data set, 882 patient datas of final residue.
Being selected by data sample and Feature Selection, ultimately generate 882 row that data set comprises, 19 row features, such as table 1 institute
Show.
Table 1
2, optimal models parameter
Data set is randomly divided into training set (441), test set (220) and derivation collection (221), ratio 2:1:1, obtains mould
Shape parameter is as shown in table 2:
Table 2
3, randomization marking is carried out to predicting the outcome
Checking collection result is as shown in table 3, and in this experiment, checking collection includes 121 people.
Table 3
Note: about some index explanations of classification problem, for two classification problems, define two classifications be respectively positive class and
Negative class, each object of positive apoplexy due to endogenous wind is referred to as positive example, and each object of negative apoplexy due to endogenous wind is referred to as negative example.Generally, in prediction river
During rugged disease, mucocutaneous lymphnode syndrome sample is positive class, and common fever patient is negative class.Use disaggregated model that test sample is predicted, meeting
There are four kinds of situations, if an example is positive class and is predicted to be real class (True positive, TP), if example is negative
Class is predicted to be positive class, the most false positive class (False postive, FP).Accordingly, correspondingly, if example is negative class quilt
Predicting into negative class, referred to as really bear class (True negative, TN), it is then false negative class (false that positive example is predicted to negative class
negative,FN)。
TP: positive example is predicted as positive class number；
FN: positive example is predicted as negative class number；
FP: negative example is predicted as the number of positive class；
TN: negative example is predicted as the number of negative class；
Sensitivity (sensitivity): the positive correctly predicted example ratio for positive class of apoplexy due to endogenous wind, i.e. TP/ (TP+FN)
Specificity (specificity): negative apoplexy due to endogenous wind is predicted correctly the example ratio into negative class, i.e. TN/ (TN+FP)
Positive predictive value (Positive Predictive Value, PPV): being predicted as in the example of positive class, positive example accounts for
Ratio, i.e. TP/ (TP+FP).
The foregoing is only presently preferred embodiments of the present invention, all impartial changes made according to scope of the present invention patent with
Modify, all should belong to the covering scope of patent of the present invention.
Claims (6)
1. a mucocutaneous lymphnode syndrome grade predicting method based on medical data modeling, it is characterised in that: it comprises the following steps:
Step 1: data sample selects；Extraction is concentrated to be available for the effective sample of modeling from sample data；
Step 2: Feature Selection；Filter out from the characteristic set building sample data and meet live medical auxiliary diagnostic application
19 features are modeled；
Step 3: mucocutaneous lymphnode syndrome hierarchy model builds and evaluates, and its step is as follows:
(3.1) use the mode of random division, be training set Xtrain, test set Xtest and checking collection by Segmentation of Data Set
Xderivation tri-part, ratio is 2:1:1；
(3.2) using SVM homing method matching Xtrain data set in training set, use gaussian kernel function, modeling process makes
By ten folding cross validation Selection Model parameters, record optimal models parameter and support vector sequence number；
(3.3) derivation collection is used to calculate classification thresholds t according to regression modelcaseWith tcontrol；
(3.4) combine derivation collection classification thresholds, carry out the classification prediction of test set sample.
A kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data modeling the most according to claim 1, it is characterised in that:
In step 1, data sample selection course includes:
(1.1) to incomplete, wrong data, its value is set to sky；
(1.2) counterweight complex data is deleted；
(1.3) data nonstandard to form, are uniformly processed as numeric format by numeric coding mode.
A kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data modeling the most according to claim 1, it is characterised in that:
In step (3.3), tcaseFor positive label or the threshold value that is called case (case), tcontrolFor negative label or be called comparison
(control) threshold value；More than tcaseBe classified to high risk patient, less than tcontrolBe classified to low danger patient, remaining
It is divided into middle danger patient.
A kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data modeling the most according to claim 1, it is characterised in that:
In step (3.3), carry out as follows:
A. assuming that deriving intensive data number of samples is S, calculating according to regression model derives intensive data sample whether mucocutaneous lymphnode syndrome
Probabilityi∈S；
B. arrange according to order from big to smallAssume to work asTime,Under current order
It is case more than or equal to all samples of this value；
C. arrange according to order from small to largeWhenTime,Under current order little
In all samples equal to this value for compareing.
A kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data modeling the most according to claim 1, it is characterised in that:
In step (3.3), being theoretically split into high-risk patient has the probability of about 90% to be ill, and low danger patient then has about
The probability of 10% is ill, and middle danger patient then needs doctor to do later observation, the sensitivity of such algorithm again according to practical situation
(sensitivity) although can reduce, but True Positive Rate (true positive rate) and true negative rate (true
Negative rate) can be greatly promoted, it is unlikely in actual medical diagnoses, mislead doctor and makes false judgment.
A kind of mucocutaneous lymphnode syndrome grade predicting method based on medical data the most according to claim 3, it is characterised in that: step
Described in 2,19 are characterized as:
(2.1) Clinical symptoms:
The most whether have a fever more than 38.3 degrees Celsius (Fever > 38.3 DEG C or100.5 °F :)
The most whether there is erythra (Rash)
C. two (Red eyes) the most rubescent
The most whether swallow lip red, red or strawberry tongue (Red pharynx, red lips, or strawberry tongue)
The most whether cervical lymph node > 1.5 centimetres (Cervical lymph node > 1.5cm)
The reddest or swollen hands/foot or hands/foot decortication (Red or swollen hands/feet or peeling of
hands/feet)
The most ill natural law (Days of illness)
(2.2) experimental data:
A. white blood cell concentration (WBC × 103/mm3)
B. neutrophilic granulocyte concentration (POLYS%)
C. banding nuclear concentration (BANDS%)
D. lymphocyte concentration (Lymphs%)
E. mononuclear cell concentration (MONOS%)
F. eosinophilic granulocyte concentration (EOS%)
G. hemoglobin concentration (HGB mg/dl)
H. PC (PLTS × 103/mm3)
I. erythrocyte sedimentation rate (ESR mm/h)
J.C-reactive protein (CRP mg/dl)
K. alanine aminotransferase (ALT IU/L)
L. glutamyl transpeptidase (GGT IU/L).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610766242.0A CN106295229A (en) | 2016-08-30 | 2016-08-30 | Kawasaki disease hierarchical prediction method based on medical data modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610766242.0A CN106295229A (en) | 2016-08-30 | 2016-08-30 | Kawasaki disease hierarchical prediction method based on medical data modeling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106295229A true CN106295229A (en) | 2017-01-04 |
Family
ID=57675138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610766242.0A Pending CN106295229A (en) | 2016-08-30 | 2016-08-30 | Kawasaki disease hierarchical prediction method based on medical data modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106295229A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980757A (en) * | 2017-03-15 | 2017-07-25 | 重庆医科大学 | The concurrent coronary artery pathological changes hazards management system of Kawasaki disease and method for digging |
| CN107122598A (en) * | 2017-04-14 | 2017-09-01 | 刘建亚 | The data Classified optimization method and system cross-checked based on low diversity factor ordered series of numbers |
| CN107480436A (en) * | 2017-03-17 | 2017-12-15 | 苏州大学附属儿童医院 | The Forecasting Methodology and forecasting system of gamma globulin absorbing wave maker Kawasaki disease |
| CN109215781A (en) * | 2018-09-14 | 2019-01-15 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on logistic algorithm |
| CN109243604A (en) * | 2018-09-14 | 2019-01-18 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on neural network algorithm |
| CN109273094A (en) * | 2018-09-14 | 2019-01-25 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on Boosting algorithm |
| CN111755129A (en) * | 2020-06-30 | 2020-10-09 | 山东大学 | Multi-mode osteoporosis layering early warning method and system |
| CN113035346A (en) * | 2021-02-22 | 2021-06-25 | 北京信息科技大学 | Medical knowledge map-based disease category assessment device and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809335A (en) * | 2015-04-10 | 2015-07-29 | 上海卫生信息工程技术研究中心有限公司 | Analytical prediction module of disease incidence affected by environmental change |
| CN104866713A (en) * | 2015-05-12 | 2015-08-26 | 南京霁云信息科技有限公司 | Kawasaki disease and fever diagnosis system based on embedding of incremental local discrimination subspace |
| CN105447322A (en) * | 2015-12-11 | 2016-03-30 | 北京工业大学 | Support vector machine based antiviral inhibitor dissociation rate constant prediction method |
-
2016
- 2016-08-30 CN CN201610766242.0A patent/CN106295229A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809335A (en) * | 2015-04-10 | 2015-07-29 | 上海卫生信息工程技术研究中心有限公司 | Analytical prediction module of disease incidence affected by environmental change |
| CN104866713A (en) * | 2015-05-12 | 2015-08-26 | 南京霁云信息科技有限公司 | Kawasaki disease and fever diagnosis system based on embedding of incremental local discrimination subspace |
| CN105447322A (en) * | 2015-12-11 | 2016-03-30 | 北京工业大学 | Support vector machine based antiviral inhibitor dissociation rate constant prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 张萍等: "支持向量机在肝纤维化模型诊断中的应用", 《数理医药学杂志》 * |
| 张黎明等: "支持向量机预测结肠腺瘤高级别上皮内瘤变效果研究", 《中国实用内科杂志》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106980757A (en) * | 2017-03-15 | 2017-07-25 | 重庆医科大学 | The concurrent coronary artery pathological changes hazards management system of Kawasaki disease and method for digging |
| CN107480436A (en) * | 2017-03-17 | 2017-12-15 | 苏州大学附属儿童医院 | The Forecasting Methodology and forecasting system of gamma globulin absorbing wave maker Kawasaki disease |
| CN107122598A (en) * | 2017-04-14 | 2017-09-01 | 刘建亚 | The data Classified optimization method and system cross-checked based on low diversity factor ordered series of numbers |
| CN109215781A (en) * | 2018-09-14 | 2019-01-15 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on logistic algorithm |
| CN109243604A (en) * | 2018-09-14 | 2019-01-18 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on neural network algorithm |
| CN109273094A (en) * | 2018-09-14 | 2019-01-25 | 苏州贝斯派生物科技有限公司 | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on Boosting algorithm |
| CN109215781B (en) * | 2018-09-14 | 2021-11-12 | 道之精准医学科技(上海)有限公司 | Method and system for constructing risk assessment model of Kawasaki disease based on logistic algorithm |
| CN109243604B (en) * | 2018-09-14 | 2021-11-12 | 道之精准医学科技(上海)有限公司 | Neural network algorithm-based Kawasaki disease risk assessment model construction method and system |
| CN111755129A (en) * | 2020-06-30 | 2020-10-09 | 山东大学 | Multi-mode osteoporosis layering early warning method and system |
| CN111755129B (en) * | 2020-06-30 | 2023-12-19 | 山东大学 | Multi-mode osteoporosis layering early warning method and system |
| CN113035346A (en) * | 2021-02-22 | 2021-06-25 | 北京信息科技大学 | Medical knowledge map-based disease category assessment device and method |
| CN113035346B (en) * | 2021-02-22 | 2023-09-22 | 北京信息科技大学 | Disease category assessment device and method based on medical knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106295229A (en) | Kawasaki disease hierarchical prediction method based on medical data modeling | |
| CN106339593A (en) | Kawasaki disease classification and prediction method based on medical data modeling | |
| Ahmadi et al. | Diseases diagnosis using fuzzy logic methods: A systematic and meta-analysis review | |
| Sahu et al. | FINE_DENSEIGANET: Automatic medical image classification in chest CT scan using Hybrid Deep Learning Framework | |
| Gjoreski et al. | Machine learning and end-to-end deep learning for the detection of chronic heart failure from heart sounds | |
| Pathan et al. | Analyzing the impact of feature selection on the accuracy of heart disease prediction | |
| LaFreniere et al. | Using machine learning to predict hypertension from a clinical dataset | |
| CN109920547A (en) | A kind of diabetes prediction model construction method based on electronic health record data mining | |
| CN109273093B (en) | Construction method and construction system of risk assessment model for Kawasaki disease | |
| CN109243604B (en) | Neural network algorithm-based Kawasaki disease risk assessment model construction method and system | |
| CN106529110A (en) | Classification method and equipment of user data | |
| CN109273094A (en) | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on Boosting algorithm | |
| CN103678534A (en) | Physiological information and health correlation acquisition method based on rough sets and fuzzy inference | |
| Baidya et al. | A deep prediction of chronic kidney disease by employing machine learning method | |
| CN110874409A (en) | Disease grading prediction system, method, electronic device and readable storage medium | |
| CN109215781A (en) | A kind of construction method and building system of the Kawasaki disease risk evaluation model based on logistic algorithm | |
| CN112652361A (en) | High-risk myeloma screening method based on GBDT model and application thereof | |
| CN117116477A (en) | Construction method and system of prostate cancer disease risk prediction model based on random forest and XGBoost | |
| Praveen et al. | Chronic kidney disease prediction using ML-based neuro-fuzzy model | |
| CN116403714A (en) | Cerebral apoplexy END risk prediction model building method and device, END risk prediction system, electronic equipment and medium | |
| Bajpai et al. | Early prediction of cardiac arrest using hybrid machine learning models | |
| CN109192306A (en) | A kind of judgment means of diabetes, equipment and computer readable storage medium | |
| Zhang et al. | Exploring risk factors and predicting UPDRS score based on Parkinson's speech signals | |
| CN117116475A (en) | Method, system, terminal and storage medium for predicting risk of ischemic cerebral apoplexy | |
| Panda et al. | Role of Predictive Modeling in Healthcare Research: A Scoping Review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170104 |