CN104392085A - Drug effect evaluation method based on kernel principal component TOPSIS - Google Patents
Drug effect evaluation method based on kernel principal component TOPSIS Download PDFInfo
- Publication number
- CN104392085A CN104392085A CN201410452228.4A CN201410452228A CN104392085A CN 104392085 A CN104392085 A CN 104392085A CN 201410452228 A CN201410452228 A CN 201410452228A CN 104392085 A CN104392085 A CN 104392085A
- Authority
- CN
- China
- Prior art keywords
- centerdot
- matrix
- inspection
- patient
- evaluation
- 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
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a drug effect evaluation method based on kernel principal component TOPSIS (Technique for Order Preference by Similarity to Ideal Solution). The method is characterized by comprising the following steps: based on an existing information system in a hospital, analyzing a specific drug related index in a check index table of a patient; taking an index change condition of the patient after using a drug as a starting point and adopting a kernel principal component TOPSIS method for establishing an evaluation index system for the drug curative effect of the patient; realizing the evaluation for the drug curative effect by adopting a weighting kernel principal component analysis method and a TOPSIS method. According to the method, an evaluation system for the drug curative effect can be established, a clinician can be assisted in evaluating the drug curative effect and adjusting the dose scheme, and the medical service level is increased.
Description
Technical field
The present invention relates to a kind of assessment system and methodology to certain drug clinical effectiveness.
Background technology
At present after medicine enters the clinical practice stage, lack the effective evaluation means to clinical effectiveness and system.Distinct issues have: mostly (1) patient's process be long-term, complicated, need the tracking continued, and need to consider the generation of other illnesss and development and the situation that influences each other between them; (2) therapeutic evaluation of patient all comes from the subjective assessment of clinician according to inspection Index for examination substantially, relatively unilateral.Therefore, there is very large drawback based on such result of study when exploring clinical drug therapeutic evaluation.
Summary of the invention
The object of the invention is to set up clinical drug therapeutic efficacy assessment, make Evaluation of Drug Efficacy truer, objective.
In order to achieve the above object, technical scheme of the present invention there is provided a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS, and it is characterized in that, step is:
Step 1, the history medicining condition of I patient is organized into data mode; The J of the history of patient inspection is checked that data target is organized into data mode simultaneously;
The situation of change of twice inspection Index for examination data before and after step 2, more each patient medication, builds initialization decision matrix X,
x in formula
ijrepresent that the jth item inspection of i-th patient checks the situation of change of data target;
Step 3, decision matrix X to be normalized;
Step 4, by nonlinear mapping function, the decision matrix X after normalized is mapped to high-dimensional feature space and obtains nuclear matrix K,
Step 5, ask for the correlation matrix R of nuclear matrix K,
r
ijrepresent that i-th inspection checks that data target and jth item check the related coefficient checking data target, and r
ij=r
ji;
Step 6, ask for J characteristic root corresponding to correlation matrix R and the proper vector corresponding to each characteristic root, each characteristic root is defined as a major component, and each proper vector has J element;
Step 7, calculate each major component variance contribution degree after, then calculate accumulative major component variance contribution degree, wherein, the variance contribution degree of i-th major component is
then accumulative major component variance contribution degree is
get the major component that cumulative variance contribution degree is more than or equal to specified threshold, then from J major component, filter out p major component, be designated as λ
1, λ
2..., λ
pand p the proper vector that p major component is corresponding, be designated as e
1, e
2..., e
p, p major component is defined as core principle component;
Step 8, set up the capable p of J arrange initial Factor load-matrix l,
in initial Factor load-matrix l, p element of the i-th row is respectively i-th inspection and checks corresponding p the core principle component weight of data target;
Step 9, every inspection is checked that the core principle component weight of data target is directly combined into the evaluation criterion weight vector that has the one dimension of p column element, then obtain J evaluation criterion weight vectorial;
Decision matrix X after step 10, the normalized that J evaluation criterion weight vector and step 3 obtained is multiplied thus obtains weighting standard matrix V;
Step 11, the optimum solution calculating weighting standard matrix V and the poorest solution;
Step 12, utilize step 1, to step 3 identical method, the situation of change of doctor to twice J inspection Index for examination data before and after the current administration scheme of I patient and medication is organized into the decision matrix X ' relevant to current administration scheme after normalized, decision matrix X ' and the weight vectors of J the evaluation index that step 9 obtains are multiplied obtain the weighting standard matrix V relevant with current administration scheme ';
Step 13, respectively the calculating current administration scheme of weighting standard matrix V ' middle doctor to each patient and the distance of optimum solution and the poorest solution, and calculate the relative similarity degree of two distances, when relative similarity degree exceedes the threshold value preset, then early warning is provided to the current administration scheme of doctor to respective patient.
Preferably, in described step 3, the jth item inspection of i-th patient in initialization decision matrix X is checked to the situation of change x of data target
ijz is obtained after being normalized
ij, then
in formula, x ' and σ is respectively x
ijexpectation and variance.
Preferably, in described step 4, described nonlinear mapping function selects gaussian radial basis function kernel function, then the i-th row jth column element in nuclear matrix K
in formula, x ' and σ is respectively x
ijexpectation and variance.
Preferably, in described step 4,
in formula,
Preferably, be located in described step 10, described weighting standard matrix V is the capable p column matrix of I, and in weighting standard matrix V, the i-th row jth column element is v
ij, then, in described step 11, the set expression of optimum solution is V
+,
The set expression of the poorest solution is V
-,
In described step 12, weighting standard matrix V ' be the capable p column matrix of I, weighting standard matrix V ' in the i-th row jth column element be v
ij', then the current administration scheme of doctor to i-th patient and the distance of optimum solution
for:
The current administration scheme of doctor to i-th patient and the distance of the poorest solution
for:
Distance
with distance
relative similarity degree
if relative similarity degree ξ
iwhen exceeding the threshold values of specifying, then early warning is provided to the current administration scheme of doctor to i-th patient.
Preferably, also have after described step 8 and before described step 9:
Every inspection of same level checks that data target checks the importance of data target to every inspection that last layer is secondary to use analytical hierarchy process to judge, structure multilevel iudge matrix, and give certain metric, finally, by carrying out consistency check and test for randomness to comparing judgment matrix, try to achieve the level weight that the inspection of each level checks data target, the core principle component weight calculation that integrating step 8 obtains again obtains the combining weights that every inspection checks data target, then the combining weights of i-th inspection inspection data target
in formula, ω
ibe the core principle component weight that i-th inspection checks data target, e
ibe the level weight that i-th inspection checks data target, now, step 9 is:
Every inspection is checked the combining weights of data target is as evaluation criterion weight vector, then obtain J evaluation criterion weight vector.
Preferably, the situation of change of doctor to twice J inspection Index for examination data before and after the current administration scheme of I patient and medication is added in the corresponding historical data of step 1 and re-executes step 1 to step 11, upgrade the optimum solution and the poorest solution that calculate weighting standard matrix V
The present invention is by analyzing medicine coupling index specific in the inspection Index for examination table of patient, with patient using the index situation of change after medicine for starting point, core principle component TOPSIS method is adopted to build the assessment indicator system of patient medication curative effect, by Weighted Kernel principal component analysis (PCA) and the evaluation approaching desirable ranking method and realize curative effect of medication, the deficiency in background technology effectively can be solved.
Embodiment
For making the present invention become apparent, be hereby described in detail below with preferred embodiment.
The present invention relates to a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS, the steps include:
Step 1, the history medicining condition of I patient is organized into data mode, as shown in the table.
The J of the history of patient inspection is checked that data target is organized into data mode according to Annual distribution simultaneously, as shown in the table.
The situation of change of twice inspection Index for examination data before and after step 2, more each patient medication, the sample data of situation of change is as shown in the table.
Build initialization decision matrix X,
x in formula
ijrepresent that the jth item inspection of i-th patient checks the situation of change of data target.
Step 3, decision matrix X to be normalized.The jth item inspection of i-th patient in initialization decision matrix X is checked to the situation of change x of data target
ijz is obtained after being normalized
ij, then
in formula, x ' and σ is respectively x
ijexpectation and variance.
Step 4, by nonlinear mapping function, the decision matrix X after normalized is mapped to high-dimensional feature space and obtains nuclear matrix K, by this conversion, calculating is expanded to nonlinear transportation field.
In the present embodiment, nonlinear mapping function selects gaussian radial basis function kernel function, then the i-th row jth column element in nuclear matrix K
in formula, x ' and σ is respectively x
ijexpectation and variance.
Step 5, ask for the correlation matrix R of nuclear matrix K,
r
ijrepresent that i-th inspection checks that data target and jth item check the related coefficient checking data target, and r
ij=r
ji,
in formula,
In the present embodiment, correlation matrix R is as shown in table 1.
Table 1
Step 6, ask for J characteristic root corresponding to correlation matrix R, and it is arranged from large to small, obtain λ
1, λ
2..., λ
j, and the proper vector corresponding to each characteristic root, i.e. e
1, e
2..., e
j, each characteristic root is defined as a major component, and each proper vector has J element.
λ
1, λ
2..., λ
jby separating secular equation | λ I-R| obtains, e
1, e
2..., e
jin any one proper vector e meet | e|=1.
Step 7, calculate each major component variance contribution degree after, then calculate accumulative major component variance contribution degree, wherein, the variance contribution degree of i-th major component is
then accumulative major component variance contribution degree is
get the major component that cumulative variance contribution degree is more than or equal to specified threshold, then from J major component, filter out p major component, be designated as λ
1, λ
2..., λ
pand p the proper vector that p major component is corresponding, be designated as e
1, e
2..., e
p, p major component is defined as core principle component.
In the present embodiment, the characteristic root corresponding to correlation matrix R, variance contribution degree and cumulative variance contribution degree, as shown in table 2.
Table 2
In the present embodiment, the principle being more than or equal to 80% according to cumulative variance contribution degree extracts major component, extracts 8 core principle components altogether, shown in these core principle components and characteristic of correspondence vector table 3 thereof.
Table 3
Step 8, set up the capable p of J arrange initial Factor load-matrix l,
in initial Factor load-matrix l, p element of the i-th row is respectively i-th inspection and checks corresponding p the core principle component weight of data target.
In the present embodiment, the initial Factor load-matrix l obtained is as shown in table 4.
Table 4
Step 9, every inspection of same level checks that the every inspection of data target to last layer time checks the importance of data target to use analytical hierarchy process to judge, structure multilevel iudge matrix, and give certain metric, finally, by carrying out consistency check and test for randomness to comparing judgment matrix, try to achieve the level weight that the inspection of each level checks data target, the core principle component weight calculation that integrating step 8 obtains again obtains the combining weights that every inspection checks data target, then the combining weights of i-th inspection inspection data target
in formula, ω
ibe the core principle component weight that i-th inspection checks data target, e
iit is the level weight that i-th inspection checks data target.
Step 10, every inspection is checked that the combining weights of data target is as evaluation criterion weight vector, then obtain J evaluation criterion weight vectorial.
In the present embodiment, J evaluation criterion weight vector is as shown in table 5.
Table 5
Decision matrix X after step 11, the normalized that J evaluation criterion weight vector and step 3 obtained is multiplied thus obtains weighting standard matrix V.
In the present embodiment, weighting standard matrix V is as shown in table 6.
Table 6
Step 12, the optimum solution calculating weighting standard matrix V and the poorest solution.Weighting standard matrix V is the capable p column matrix of I, and in weighting standard matrix V, the i-th row jth column element is v
ij, the set expression of optimum solution is V
+,
The set expression of the poorest solution is V
-,
In the present embodiment, optimum solution and the poorest solution as shown in table 7.
Table 7
Step 13, utilize step 1, to step 3 identical method, the situation of change of doctor to twice J inspection Index for examination data before and after the current administration scheme of I patient and medication is organized into the decision matrix X ' relevant to current administration scheme after normalized, decision matrix X ' and the weight vectors of J the evaluation index that step 10 obtains are multiplied obtain the weighting standard matrix V relevant with current administration scheme '.
Step 14, respectively the calculating current administration scheme of weighting standard matrix V ' middle doctor to each patient and the distance of optimum solution and the poorest solution, and calculate the relative similarity degree of two distances, when relative similarity degree exceedes the threshold value preset, then early warning is provided to the current administration scheme of doctor to respective patient.
Weighting standard matrix V ' be the capable p column matrix of I, weighting standard matrix V ' in the i-th row jth column element be v
ij', then the current administration scheme of doctor to i-th patient and the distance of optimum solution
for:
The current administration scheme of doctor to i-th patient and the distance of the poorest solution
for:
Distance
with distance
relative similarity degree
if relative similarity degree ξ
iwhen exceeding the threshold values of specifying, then early warning is provided to the current administration scheme of doctor to i-th patient.
In the present embodiment, relative similarity degree is as shown in table 8.
Table 8
Doctor can also check the situation of change of Index for examination data add in the corresponding historical data of step 1 to twice J before and after the current administration scheme of I patient and medication and re-execute step 1 to step 12 by those skilled in the art, upgrades the optimum solution and the poorest solution that calculate weighting standard matrix V.
Claims (7)
1. based on an Evaluation of Drug Efficacy method of core principle component TOPSIS, it is characterized in that, step is:
Step 1, the history medicining condition of I patient is organized into data mode; The J of the history of patient inspection is checked that data target is organized into data mode simultaneously;
The situation of change of twice inspection Index for examination data before and after step 2, more each patient medication, builds initialization decision matrix X,
Step 3, decision matrix X to be normalized;
Step 4, by nonlinear mapping function, the decision matrix X after normalized is mapped to high-dimensional feature space and obtains nuclear matrix K,
Step 5, ask for the correlation matrix R of nuclear matrix K,
Step 6, ask for J characteristic root corresponding to correlation matrix R and the proper vector corresponding to each characteristic root, each characteristic root is defined as a major component, and each proper vector has J element;
Step 7, calculate each major component variance contribution degree after, then calculate accumulative major component variance contribution degree, wherein, i-th major component λ
ivariance contribution degree be
then accumulative major component variance contribution degree is
get the major component that cumulative variance contribution degree is more than or equal to specified threshold, then from J major component, filter out p major component, be designated as λ
1, λ
2..., λ
pand p the proper vector that p major component is corresponding, be designated as e
1, e
2..., e
p, p major component is defined as core principle component;
Step 8, set up the capable p of J arrange initial Factor load-matrix l,
in initial Factor load-matrix l, p element of the i-th row is respectively i-th inspection and checks corresponding p the core principle component weight of data target;
Step 9, every inspection is checked that the core principle component weight of data target is directly combined into the evaluation criterion weight vector that has the one dimension of p column element, then obtain J evaluation criterion weight vectorial;
Decision matrix X after step 10, the normalized that J evaluation criterion weight vector and step 3 obtained is multiplied thus obtains weighting standard matrix V;
Step 11, the optimum solution calculating weighting standard matrix V and the poorest solution;
Step 12, utilize step 1, to step 3 identical method, the situation of change of doctor to twice J inspection Index for examination data before and after the current administration scheme of I patient and medication is organized into the decision matrix X ' relevant to current administration scheme after normalized, decision matrix X ' and the weight vectors of J the evaluation index that step 9 obtains are multiplied obtain the weighting standard matrix V relevant with current administration scheme ';
Step 13, respectively the calculating current administration scheme of weighting standard matrix V ' middle doctor to each patient and the distance of optimum solution and the poorest solution, and calculate the relative similarity degree of two distances, when relative similarity degree exceedes the threshold value preset, then early warning is provided to the current administration scheme of doctor to respective patient.
2. a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS as claimed in claim 1, is characterized in that, in described step 3, the jth item inspection of i-th patient in initialization decision matrix X is checked to the situation of change x of data target
ijz is obtained after being normalized
ij, then
in formula, x ' and σ is respectively x
ijexpectation and variance.
3. a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS as claimed in claim 1, it is characterized in that, in described step 4, described nonlinear mapping function selects gaussian radial basis function kernel function, then the i-th row jth column element in nuclear matrix K
in formula, x ' and σ is respectively x
ijexpectation and variance.
4. a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS as claimed in claim 1, is characterized in that, in described step 4,
In formula,
5. a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS as claimed in claim 1, it is characterized in that, be located in described step 10, described weighting standard matrix V is the capable p column matrix of I, and in weighting standard matrix V, the i-th row jth column element is v
ij, then, in described step 11, the set expression of optimum solution is V
+,
The set expression of the poorest solution is V
-,
In described step 12, weighting standard matrix V ' be the capable p column matrix of I, weighting standard matrix V ' in the i-th row jth column element be v
ij', then the current administration scheme of doctor to i-th patient and the distance of optimum solution
for:
The current administration scheme of doctor to i-th patient and the distance of the poorest solution
for:
Distance
with distance
relative similarity degree
if relative similarity degree ξ
iwhen exceeding the threshold values of specifying, then early warning is provided to the current administration scheme of doctor to i-th patient.
6. a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS as claimed in claim 1, is characterized in that, also has after described step 8 and before described step 9:
Every inspection of same level checks that data target checks the importance of data target to every inspection that last layer is secondary to use analytical hierarchy process to judge, structure multilevel iudge matrix, and give certain metric, finally, by carrying out consistency check and test for randomness to comparing judgment matrix, try to achieve the level weight that the inspection of each level checks data target, the core principle component weight calculation that integrating step 8 obtains again obtains the combining weights that every inspection checks data target, then the combining weights of i-th inspection inspection data target
in formula, ω
ibe the core principle component weight that i-th inspection checks data target, e
ibe the level weight that i-th inspection checks data target, now, step 9 is:
Every inspection is checked the combining weights of data target is as evaluation criterion weight vector, then obtain J evaluation criterion weight vector.
7. a kind of Evaluation of Drug Efficacy method based on core principle component TOPSIS as claimed in claim 1, it is characterized in that, the situation of change of doctor to twice J inspection Index for examination data before and after the current administration scheme of I patient and medication is added in the corresponding historical data of step 1 and re-executes step 1 to step 11, upgrade the optimum solution and the poorest solution that calculate weighting standard matrix V.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410452228.4A CN104392085A (en) | 2014-09-05 | 2014-09-05 | Drug effect evaluation method based on kernel principal component TOPSIS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410452228.4A CN104392085A (en) | 2014-09-05 | 2014-09-05 | Drug effect evaluation method based on kernel principal component TOPSIS |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104392085A true CN104392085A (en) | 2015-03-04 |
Family
ID=52609988
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410452228.4A Pending CN104392085A (en) | 2014-09-05 | 2014-09-05 | Drug effect evaluation method based on kernel principal component TOPSIS |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104392085A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915561A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Intelligent disease attribute matching method |
CN108766587A (en) * | 2018-05-11 | 2018-11-06 | 北京诺道认知医学科技有限公司 | A kind of method and device based on specific drug structure administration data library |
CN109559831A (en) * | 2018-10-26 | 2019-04-02 | 山东省立医院 | A kind of method for estimating curative effect based on anticancer drug clinical laboratory data |
CN110223786A (en) * | 2019-06-13 | 2019-09-10 | 重庆亿创西北工业技术研究院有限公司 | Drug-drug interactions prediction technique and system based on non-negative tensor resolution |
CN115240800A (en) * | 2022-09-26 | 2022-10-25 | 北京泽桥医疗科技股份有限公司 | Medical data intelligent analysis execution method based on big data platform |
CN117236796A (en) * | 2023-11-13 | 2023-12-15 | 天津市城市规划设计研究总院有限公司 | CS-TOPSIS algorithm-based hospital logistics operation and maintenance evaluation method and system |
-
2014
- 2014-09-05 CN CN201410452228.4A patent/CN104392085A/en active Pending
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915561A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Intelligent disease attribute matching method |
CN104915561B (en) * | 2015-06-11 | 2018-10-16 | 万达信息股份有限公司 | Genius morbi intelligent Matching method |
CN108766587A (en) * | 2018-05-11 | 2018-11-06 | 北京诺道认知医学科技有限公司 | A kind of method and device based on specific drug structure administration data library |
CN108766587B (en) * | 2018-05-11 | 2022-05-03 | 北京诺道认知医学科技有限公司 | Method and device for constructing drug administration database based on specified drugs |
CN109559831A (en) * | 2018-10-26 | 2019-04-02 | 山东省立医院 | A kind of method for estimating curative effect based on anticancer drug clinical laboratory data |
CN110223786A (en) * | 2019-06-13 | 2019-09-10 | 重庆亿创西北工业技术研究院有限公司 | Drug-drug interactions prediction technique and system based on non-negative tensor resolution |
CN115240800A (en) * | 2022-09-26 | 2022-10-25 | 北京泽桥医疗科技股份有限公司 | Medical data intelligent analysis execution method based on big data platform |
CN117236796A (en) * | 2023-11-13 | 2023-12-15 | 天津市城市规划设计研究总院有限公司 | CS-TOPSIS algorithm-based hospital logistics operation and maintenance evaluation method and system |
CN117236796B (en) * | 2023-11-13 | 2024-02-02 | 天津市城市规划设计研究总院有限公司 | CS-TOPSIS algorithm-based hospital logistics operation and maintenance evaluation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104392085A (en) | Drug effect evaluation method based on kernel principal component TOPSIS | |
Deepika et al. | Predictive analytics to prevent and control chronic diseases | |
CN108335755B (en) | Data analysis method and device | |
AU2016273897B2 (en) | Pathway analysis for identification of diagnostic tests | |
Pourbasheer et al. | QSAR study of IKKβ inhibitors by the genetic algorithm: multiple linear regressions | |
Mane | Smart heart disease prediction system using Improved K-means and ID3 on big data | |
US20140207478A1 (en) | Physician composite quality scoring and rating methodology | |
Martins et al. | Bayesian joint modeling of longitudinal and spatial survival AIDS data | |
CN110956626A (en) | Image-based prognosis evaluation method and device | |
Yun et al. | Prediction of critical care outcome for adult patients presenting to emergency department using initial triage information: an XGBoost algorithm analysis | |
Matsouaka et al. | Power and sample size calculations for the Wilcoxon–Mann–Whitney test in the presence of death‐censored observations | |
CN109509549B (en) | Diagnosis and treatment service provider evaluation method, diagnosis and treatment service provider evaluation device, computer equipment and storage medium | |
Penny‐Dimri et al. | Machine learning to predict adverse outcomes after cardiac surgery: A systematic review and meta‐analysis | |
Li et al. | The analysis of plantar pressure data based on multimodel method in patients with anterior cruciate ligament deficiency during walking | |
CN105354414A (en) | Hierarchical analysis-based human body health condition assessment method | |
Rogalewicz et al. | Multiple-criteria decision making: application to medical devices. | |
Wang et al. | Random effects models for assessing diagnostic accuracy of traditional Chinese doctors in absence of a gold standard | |
Yang et al. | Composite marginal quantile regression analysis for longitudinal adolescent body mass index data | |
Leite et al. | Surgical planning of horizontal strabismus using multiple output regression tree | |
Perin et al. | Regression analysis of correlated ordinal data using orthogonalized residuals | |
Low et al. | Understanding the effect of changes to natural turf hardness on lower extremity loading | |
Tang et al. | Least squares regression methods for clustered ROC data with discrete covariates | |
Sanaei et al. | Designing and implementation of fuzzy expert system for diagnosis of Herpes zoster | |
van der Sar et al. | Evaluation of different classification methods using electronic nose data to diagnose sarcoidosis | |
Barreto | Multivariate statistical analysis for dermatological disease diagnosis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150304 |
|
RJ01 | Rejection of invention patent application after publication |