CN117292839A - Health management system and method based on genetic markers - Google Patents
Health management system and method based on genetic markers Download PDFInfo
- Publication number
- CN117292839A CN117292839A CN202310063631.7A CN202310063631A CN117292839A CN 117292839 A CN117292839 A CN 117292839A CN 202310063631 A CN202310063631 A CN 202310063631A CN 117292839 A CN117292839 A CN 117292839A
- Authority
- CN
- China
- Prior art keywords
- genetic marker
- health management
- identification feature
- key identification
- feature
- 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
- 230000002068 genetic effect Effects 0.000 title claims abstract description 92
- 230000036541 health Effects 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims description 9
- 239000003550 marker Substances 0.000 claims abstract description 78
- 238000007726 management method Methods 0.000 claims abstract description 73
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 238000010276 construction Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000011156 evaluation Methods 0.000 claims description 10
- 235000005911 diet Nutrition 0.000 description 4
- 230000037213 diet Effects 0.000 description 3
- 235000016709 nutrition Nutrition 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000001351 cycling effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 230000035764 nutrition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 208000022602 disease susceptibility Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 102000054765 polymorphisms of proteins Human genes 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention provides a health management system and a health management method based on genetic markers, and relates to the technical field of health management; the model construction unit constructs a genetic marker identification model and outputs identification characteristics; the feature eliminating unit adopts a feature selection algorithm to eliminate the identification features with low correlation degree; the category data set forming unit takes the identification features in the identification feature set after deleting the identification features as key identification features to construct a category data set; the health management item output unit takes a preconfigured target class data sequence as a matching rule sequence to extract a required health management item.
Description
Technical Field
The invention relates to the technical field of health management, in particular to a health management system and method based on genetic markers.
Background
The correlation between health characteristics, disease susceptibility, lifestyle and diet may all be related to a specific genetic constitution of a person. Polymorphisms and other genetic characteristics in the genetic code are sometimes associated with metabolic manifestations, including eating, nutritional and motor responses. Genetic studies have shown that people with specific genetic components can avoid the opportunity for disease by taking certain lifestyle actions, i.e. diet, nutrition and exercise related actions.
However, these studies are quite complex, and time constraints and other factors greatly limit its application and practical use, even where a skilled medical practitioner can access this information. Genetic testing has not heretofore been provided to doctors and patients seeking improved health, and therefore, there is a great need for a machine and system by which patients submit only DNA or other genetic samples and obtain health recommendations to provide advice regarding dietary nutrition and exercise. Is suitable for the specific genetic composition and individual.
Big data based health management is a leading trend for personalized medicine and future medicine. The health management of genetic markers based on clinical data is an important research hotspot, and has a wide application prospect. Under the trend of the current personal health management mode, individuals commonly acquire own genetic information from hospitals, acquire health management information, and make and implement health management plans. However, genetic marker data which accurately reflects individual characteristics are not available in the prior art, so that robust management is difficult, and the purpose of health management cannot be well achieved. Furthermore, conventional health management methods related to health management and disease prevention only have guidelines for general management methods such as diet control and exercise, and do not consider individual-specific sensitivity.
Disclosure of Invention
In order to solve the technical problems, the invention provides a health management method based on genetic markers, which comprises the following steps:
s1, collecting genetic marker data, constructing a genetic marker recognition model, and outputting recognition features;
s2, removing identification features with low correlation degree by using a feature selection algorithm to form an identification feature set K;
s3, taking the identification features in the identification feature set K as key identification features, and constructing a category data set;
s4, taking the pre-configured target class data sequence as a matching rule sequence, and extracting the required health management items.
Further, in the step S1, a genetic marker recognition model is constructed by the following formula:
wherein S is ij Representing the j-th marker data in the i-th genetic marker sample, wherein i=1, 2, …, m, m is the total number of genetic marker samples; j=1, 2, …, n, n is the total number of tag data; x is x j For the jth recognition feature recognized by the genetic marker recognition model, ε is the genetic marker recognition model parameter, γ i Is a marker variable; k is an identification feature set; k= { x 1 、x 2 …、x j …、x n }。
Further, the step S2 includes the steps of:
s2.1, respectively calculating the distance between the target genetic marker samples;
s2.2, forming a genetic marker sample distance matrix, and searching a similar set and a non-similar set for each genetic marker sample;
s2.3, calculating each identification feature x in the identification feature set K j Weights w [ x ] j ]Identifying features having weights below a weight threshold are deleted.
Further, the step S2.3 includes the steps of:
s2.3.1, initializing identification feature weights;
s2.3.2, cycling through each identification feature x in the identification feature set K j The identification feature weights are calculated and updated by the following weight formulas:
w′[x j ]＝w[x j ]-Diff(x j ，S i ，H)+Diff(x j ，S i ，M)；
wherein w' [ x ] j ]The new feature weight is used; h is a genetic marker sample S i M is the genetic marker sample S i Is a non-class set of (2);
Diff(x j ，S i h) is the identification feature x j In the genetic marker sample S i And the degree of difference of the expression values in the same class set H; diff (x) j ，S i M) is the identification feature x j In the genetic marker sample S i And the degree of difference in the expression values in non-collection M thereof;
s2.3.3 all identification features x j According to the characteristic weight w x j ]And sorting from large to small, deleting the identification features with the identification feature weights lower than the weight threshold.
Further, the step S3 includes the following steps:
s3.1, constructing a target data matrix and a category column according to key identification features to be analyzed;
s3.2, according to the target data matrix and the category column, calculating a fuzzy value U of each key identification feature;
s3.3, performing descending order arrangement on all key identification features according to the fuzzy value U to obtain an ordered key identification feature sequence to be selected, and adding the key identification feature with the maximum fuzzy value U into the constructed key identification feature subset which is initially empty;
s3.4, solving a fuzzy value U of the key identification features in the key identification feature subset and multi-entropy variable values MU of the fuzzy value U and the multi-class values in the class columns aiming at each remaining key identification feature in the key identification features to be selected;
s3.5, evaluating the key identification features by utilizing an evaluation function corresponding to each key identification feature, adding T-1 key identification features with the highest evaluation values into a key identification feature subset, wherein T is the number of the key identification feature subsets;
s3.6, selecting corresponding T category values from the target data matrix G according to the obtained key identification feature subset to construct a category data set.
Further, in the step S3.1, a target data matrix G e R is set a×(b+1) The method comprises the steps of carrying out a first treatment on the surface of the a is the total number of key identification features, b is the category dimension; the first column of the target data matrix G is a category column, and the vector Y epsilon R is used a×1 Representing the part of the target data matrix G divided by the first column as a matrix formed by key identification features, and using the matrix X epsilon R a×b A representation; the ith row of the key identification feature matrix represents the key identification feature corresponding to the ith category value, and the jth column represents the jth key identification feature corresponding to the different category values.
The invention also provides a health management system based on the genetic marker, which is used for realizing a health management method based on the genetic marker, and comprises the following steps: the system comprises a data acquisition unit, a model construction unit, a characteristic rejection unit, a category data set forming unit and a health management item output unit;
the data acquisition unit is used for collecting genetic marker data;
the model construction unit is used for constructing a genetic marker identification model and outputting identification characteristics;
the characteristic eliminating unit is used for eliminating the identification characteristics with low correlation degree by adopting a characteristic selection algorithm;
the category data set forming unit is used for constructing a category data set by taking the identification features in the identification feature set after deleting the identification features as key identification features;
the health management item output unit is used for taking a pre-configured target class data sequence as a matching rule sequence to extract a required health management item.
Further, the health management item output unit queries the health management item corresponding to the target class data sequence in a preset database, compares the health management item with the health risk model, determines the similarity between the health management item and the health risk model, and generates and displays a health management report.
Compared with the prior art, the invention has the following beneficial technical effects:
collecting genetic mark data, constructing a genetic mark recognition model, and outputting recognition features; removing the identification features with low correlation degree by using a feature selection algorithm; taking the identification features in the identification feature set K after deleting the identification features as key identification features, and constructing a category data set; inquiring a health management item corresponding to the target class data sequence in a preset database, comparing the health management item with a health risk model, determining the similarity between the health management item and the health risk model, generating a health management report and displaying the health management report. The invention can accurately reflect the genetic marker data of individual characteristics, and well achieve the purpose of health management.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of a genetic marker-based health management method of the present invention.
FIG. 2 is a flow chart of a method for removing low-correlation recognition features by using a feature selection algorithm to form a recognition feature set;
FIG. 3 is a flow chart of a method of constructing a category dataset using identification features in an identification feature set as key identification features in the present invention;
FIG. 4 is a schematic diagram of the structure of the genetic marker-based health management system of the present invention.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
In the drawings of the specific embodiments of the present invention, in order to better and more clearly describe the working principle of each element in the system, the connection relationship of each part in the device is represented, but only the relative positional relationship between each element is clearly distinguished, and the limitations on the signal transmission direction, connection sequence and the structure size, dimension and shape of each part in the element or structure cannot be constructed.
As shown in fig. 1, a flowchart of a health management method based on genetic markers includes the following steps:
s1, collecting genetic marker data, constructing a genetic marker recognition model, and outputting recognition features.
Constructing a genetic marker recognition model by:
wherein Sij represents the j-th marker data in the i-th genetic marker sample, i=1, 2, …, m, m being the total number of genetic marker samples; j=1, 2, …, n, n is the total number of tag data; xj is the j-th recognition feature recognized by the genetic marker recognition model, ε is the genetic marker recognition model parameter, Y i Is a marker variable; k is an identification feature set; k= { x 1 、x 2 …、x j …、x n }。
S2, removing identification features with low correlation degree by using a feature selection algorithm to form an identification feature set K, wherein the specific steps are shown in FIG. 2.
S2.1, respectively calculating the distance between the target genetic marker samples.
Genetic marker sample S i And S is t Distance Dis (S) i ，S t ) The calculation formula is as follows:
wherein x is j A j-th identification feature identified by the genetic marker identification model; diff (x) j ，S i ，S t ) To identify the characteristic x j In the genetic marker sample S i And S is t The degree of difference in the expression values.
S2.2, forming a genetic marker sample distance matrix, and searching a similar set and a non-similar set for each genetic marker sample.
Genetic marker sample S i Is: and sample S i Is a recognition feature x of (2) j Identical and degree of difference Diff (x j ，S i ，S t ) Samples within a threshold range;
genetic marker sample S i The non-generic set M of (2) is: and sample S i Is a recognition feature x of (2) j Different and different degree Diff (x j ，S i ，S t ) Samples that are not within the threshold range.
S2.3, calculating each identification feature x in the identification feature set K j Weights w [ x ] j ]Identifying features having weights below a weight threshold are deleted.
S2.3.1, initializing the identification feature weight.
S2.3.2, cycling through each identification feature x in the identification feature set K j The identification feature weights are calculated and updated by the following weight formulas:
w′[x j ]＝w[x j ]-Diff(x j ，S i ，H)+Diff(x j ，S i ，M)；
wherein w' [ x ] j ]The new feature weight is used; h is a genetic marker sample S i M is the genetic marker sample S i Is not a class set.
Diff(x j ，S i H) is the identification feature x j In the genetic marker sample S i And the degree of difference of the expression values in the same class set H; diff (x) j ，S i M) is the identification feature x j In the genetic marker sample S i And the degree of difference in the expression values in non-collection M thereof.
S2.3.3 all identification features x j According to the characteristic weight w x j ]And sorting from large to small, deleting the identification features with the identification feature weights lower than the weight threshold.
S3, taking the identification features in the identification feature set K as key identification features, and constructing a category data set, wherein the specific steps are shown in FIG. 3.
S3.1, constructing a target data matrix and a category column according to the key identification features to be analyzed.
Setting a target data matrix G epsilon R a×(b+1) The method comprises the steps of carrying out a first treatment on the surface of the a is the total number of key identification features, b is the category dimension;the first column of the target data matrix G is a category column, and the vector Y epsilon R is used a×1 Representing the part of the target data matrix G divided by the first column as a matrix formed by key identification features, and using the matrix X epsilon R a×b A representation; the ith row of the key identification feature matrix represents the key identification feature corresponding to the ith category value, and the jth column represents the jth key identification feature corresponding to the different category values.
S3.2, according to the target data matrix and the category column, calculating a fuzzy value U of each key identification feature;
wherein X is k Represents the kth column key identification feature in the target data matrix G, Y represents the category column, I (X) k Y) represents X k Loss information with Y, H (X k ) H (Y) represents X k Entropy of Y, H (X) k Y) represents X under the condition of the Y category column k Is used for the residual entropy value of (a). The residual entropy is x after determining Y information k The information amount H (X k Y). The loss information is given to X after determining Y k The amount of loss due to the amount of information in (a).
S3.3, performing descending order arrangement on all key identification features according to the fuzzy value U to obtain an ordered key identification feature sequence to be selected, and adding the key identification feature with the maximum fuzzy value U into the constructed key identification feature subset which is initially empty.
S3.4, solving a fuzzy value U of the key identification features in the key identification feature subset and multi-entropy variable values MU of the fuzzy value U and the multi-class values in the class columns aiming at each remaining key identification feature in the key identification features to be selected.
And combining the fuzzy value U and the multi-entropy variable value MU of each key identification feature to construct an evaluation function corresponding to the key identification feature.
Assuming that t key identification features added into the key identification feature subset exist, the multi-entropy variable X corresponding to the key identification features 1：t The value MU of (2) is:
wherein H (X) 1∶t Y) is joint entropy, H (X) i ) H (Y) represents X i Information entropy of Y, X i Representing the ith column of key identification features in the target data matrix G.
Combining the fuzzy value U and the multi-entropy variable value MU of each key identification feature to construct an evaluation function J (X i )：
J(X i )＝U(X i ，Y)-MU(X 1：t ，Y)。
S3.5, evaluating the key identification features by utilizing an evaluation function corresponding to each key identification feature, adding T-1 key identification features with the highest evaluation value into the key identification feature subset, wherein T is the number of the key identification feature subsets.
S3.6, selecting corresponding T category values from the target data matrix G according to the obtained key identification feature subset to construct a category data set.
S4, taking the pre-configured target class data sequence as a matching rule sequence, and extracting the required health management items.
Inquiring a health management item corresponding to the target class data sequence in a preset database, comparing the health management item with the health risk model, determining the similarity between the health management item and the health risk model, generating a health management report and displaying the health management report.
As shown in fig. 4, which is a schematic structural diagram of a health management system based on genetic markers according to the present invention, the health management system includes: the system comprises a data acquisition unit, a model construction unit, a characteristic rejection unit, a category data set forming unit and a health management item output unit.
And the data acquisition unit is used for collecting the genetic marker data. Preferably, the genetic marker data may be collected by a health detection device. After the related data acquisition is completed, the data information needs to be subjected to security screening and encryption processing, so that the security of the data and the privacy security of a user are ensured. The invention carries out auditing on the user identity and the collected data through the safety management module and is also used for data encryption.
And the model construction unit is used for constructing a genetic marker identification model and outputting identification characteristics.
And the feature eliminating unit is used for eliminating the identification features with low correlation degree by adopting a feature selection algorithm. Specifically, the distance between every two genetic marker samples is calculated to form a genetic marker sample distance matrix, a similar set and a non-similar set are searched for each genetic marker sample, and the weight of the identification feature is calculated.
And the category data set forming unit takes the identification features in the identification feature set K after deleting the identification features as key identification features to construct a category data set. Specifically, constructing a target data matrix and a category column according to key identification features to be analyzed; according to the target data matrix and the category column, calculating the fuzzy value of each key identification feature; according to the fuzzy values, descending order is carried out on all key identification features, an ordered key identification feature sequence to be selected is obtained, the key identification feature with the largest fuzzy value is added into a built key identification feature subset which is initially empty, and the fuzzy values of the key identification features in the key identification feature subset and the multi-entropy variable values of the key identification features and a plurality of category values in the category columns are obtained aiming at each key identification feature remained in the key identification features to be selected; and evaluating the key identification features by utilizing an evaluation function corresponding to each key identification feature, adding the T-1 key identification features with the highest evaluation values into a key identification feature subset, and selecting corresponding T category values from a target data matrix according to the obtained key identification feature subset to construct a category data set.
And the health management item output unit is used for extracting the required health management item by taking a pre-configured target class data sequence as a matching rule sequence.
Preferably, according to the health management items corresponding to the target class data sequence are queried in a preset database, the health management items are compared with the health risk models, the similarity between the health management items and the health risk models is determined, and a health management report is generated and displayed.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted across a computer-readable storage medium. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (8)
1. A method of health management based on genetic markers, comprising the steps of:
s1, collecting genetic marker data, constructing a genetic marker recognition model, and outputting recognition features;
s2, removing identification features with low correlation degree by using a feature selection algorithm to form an identification feature set K;
s3, taking the identification features in the identification feature set K as key identification features, and constructing a category data set;
s4, taking the pre-configured target class data sequence as a matching rule sequence, and extracting the required health management items.
2. The genetic marker-based health management method according to claim 1, wherein in the step s1, a genetic marker recognition model is constructed by the following formula:
wherein S is ij Representing the j-th marker data in the i-th genetic marker sample, wherein i=1, 2, …, m, m is the total number of genetic marker samples; j=1, 2, …, n, n is the total number of tag data; x is x j For the jth recognition feature recognized by the genetic marker recognition model, ε is the genetic marker recognition model parameter, γ i Is a marker variable; k is an identification feature set; k= { x 1 、x 2 …、x j …、x n }。
3. The genetic marker-based health management method according to claim 2, wherein the step S2 comprises the steps of:
s2.1, respectively calculating the distance between the target genetic marker samples;
s2.2, forming a genetic marker sample distance matrix, and searching a similar set and a non-similar set for each genetic marker sample;
s2.3, calculating each identification feature x in the identification feature set K j Weights w [ x ] j ]Identifying features having weights below a weight threshold are deleted.
4. The genetic marker-based health management method according to claim 3, wherein the step S2.3 comprises the steps of:
s2.3.1, initializing identification feature weights;
s2.3.2 and cycle traversal identification feature setEach identification feature x in the set K j The identification feature weights are calculated and updated by the following weight formulas:
w′[x j ]＝w[x j ]-Diff(x j ，S i ，H)+Diff(x j ，S i ，M)；
wherein w' [ x ] j ]The new feature weight is used; h is a genetic marker sample S i M is the genetic marker sample S i Is a non-class set of (2);
Diff(x j ，S i h) is the identification feature x j In the genetic marker sample S i And the degree of difference of the expression values in the same class set H; diff (x) j ，S i M) is the identification feature x j In the genetic marker sample S i And the degree of difference in the expression values in non-collection M thereof;
s2.3.3 all identification features x j According to the characteristic weight w x j ]And sorting from large to small, deleting the identification features with the identification feature weights lower than the weight threshold.
5. The genetic marker-based health management method according to claim 1, wherein the step S3 comprises the steps of:
s3.1, constructing a target data matrix and a category column according to key identification features to be analyzed;
s3.2, according to the target data matrix and the category column, calculating a fuzzy value U of each key identification feature;
s3.3, performing descending order arrangement on all key identification features according to the fuzzy value U to obtain an ordered key identification feature sequence to be selected, and adding the key identification feature with the maximum fuzzy value U into the constructed key identification feature subset which is initially empty;
s3.4, solving a fuzzy value U of the key identification features in the key identification feature subset and multi-entropy variable values MU of the fuzzy value U and the multi-class values in the class columns aiming at each remaining key identification feature in the key identification features to be selected;
s3.5, evaluating the key identification features by utilizing an evaluation function corresponding to each key identification feature, adding T-1 key identification features with the highest evaluation values into a key identification feature subset, wherein T is the number of the key identification feature subsets;
s3.6, selecting corresponding T category values from the target data matrix G according to the obtained key identification feature subset to construct a category data set.
6. The genetic marker-based health management method according to claim 5, wherein in the step S3.1, a target data matrix G εR is set a×(b+1) The method comprises the steps of carrying out a first treatment on the surface of the a is the total number of key identification features, b is the category dimension; the first column of the target data matrix G is a category column, and the vector Y epsilon R is used a×1 Representing the part of the target data matrix G divided by the first column as a matrix formed by key identification features, and using the matrix X epsilon R a×b A representation; the ith row of the key identification feature matrix represents the key identification feature corresponding to the ith category value, and the jth column represents the jth key identification feature corresponding to the different category values.
7. A genetic marker based health management system for implementing the genetic marker based health management method according to any one of claims 1 to 6, comprising: the system comprises a data acquisition unit, a model construction unit, a characteristic rejection unit, a category data set forming unit and a health management item output unit;
the data acquisition unit is used for collecting genetic marker data;
the model construction unit is used for constructing a genetic marker identification model and outputting identification characteristics;
the characteristic eliminating unit is used for eliminating the identification characteristics with low correlation degree by adopting a characteristic selection algorithm;
the category data set forming unit is used for constructing a category data set by taking the identification features in the identification feature set after deleting the identification features as key identification features;
the health management item output unit is used for taking a pre-configured target class data sequence as a matching rule sequence to extract a required health management item.
8. The genetic marker-based health management method according to claim 7, wherein the health management item output unit queries the health management item corresponding to the target class data sequence in a preset database, compares the health management item with the health risk model, determines the similarity between the health management item and the health risk model, and generates and displays a health management report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310063631.7A CN117292839A (en) | 2023-01-12 | 2023-01-12 | Health management system and method based on genetic markers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310063631.7A CN117292839A (en) | 2023-01-12 | 2023-01-12 | Health management system and method based on genetic markers |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117292839A true CN117292839A (en) | 2023-12-26 |
Family
ID=89239644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310063631.7A Pending CN117292839A (en) | 2023-01-12 | 2023-01-12 | Health management system and method based on genetic markers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117292839A (en) |
-
2023
- 2023-01-12 CN CN202310063631.7A patent/CN117292839A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220375611A1 (en) | Determination of health sciences recommendations | |
| Wang et al. | Medical prognosis based on patient similarity and expert feedback | |
| Ahmed | Implementing relevance feedback for content-based medical image retrieval | |
| CN110299209B (en) | Similar medical record searching method, device and equipment and readable storage medium | |
| Afshar et al. | Taste: temporal and static tensor factorization for phenotyping electronic health records | |
| CN109935337B (en) | Medical record searching method and system based on similarity measurement | |
| Lakshmi et al. | Utilization of data mining techniques for prediction and diagnosis of tuberculosis disease survivability | |
| Bhuyan et al. | Wide-ranging approach-based feature selection for classification | |
| CN109997201A (en) | For the accurate clinical decision support using data-driven method of plurality of medical knowledge module | |
| Kumar et al. | A case study on machine learning and classification | |
| CN117292839A (en) | Health management system and method based on genetic markers | |
| US20210271924A1 (en) | Analyzer, analysis method, and analysis program | |
| CN110033862B (en) | Traditional Chinese medicine quantitative diagnosis system based on weighted directed graph and storage medium | |
| Vinutha et al. | EPCA—enhanced principal component analysis for medical data dimensionality reduction | |
| CN110033835B (en) | Device for patient record identification | |
| Rout et al. | Identification of similar gastrointestinal images through content based image retrieval system based on analytical hierarchical process | |
| Dilli Babu et al. | Heart disease prognosis and quick access to medical data record using data lake with deep learning approaches | |
| CN109002442B (en) | Device and method for searching diagnosis cases based on doctor related attributes | |
| CN113688854A (en) | Data processing method and device and computing equipment | |
| Oliveira et al. | Towards an intelligent systems to predict nosocomial infections in intensive care | |
| El-Magd et al. | An interpretable deep learning based approach for chronic obstructive pulmonary disease using explainable artificial intelligence | |
| EP4111942A1 (en) | Methods and systems for identifying slices in medical image data sets | |
| Singh et al. | A study of gaps in cbmir using different methods and prospective | |
| Zannat et al. | Disease Prediction Through Syndromes by Clustering Algorithm | |
| Tomović | Patient length of stay analysis with machine learning algorithms |
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 |