CN111696662A - Disease prediction method, device and storage medium - Google Patents
Disease prediction method, device and storage medium Download PDFInfo
- Publication number
- CN111696662A CN111696662A CN202010458696.8A CN202010458696A CN111696662A CN 111696662 A CN111696662 A CN 111696662A CN 202010458696 A CN202010458696 A CN 202010458696A CN 111696662 A CN111696662 A CN 111696662A
- Authority
- CN
- China
- Prior art keywords
- data set
- data
- prediction
- model
- disease
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 86
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000001575 pathological effect Effects 0.000 claims abstract description 58
- 238000013507 mapping Methods 0.000 claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 26
- 206010019280 Heart failures Diseases 0.000 claims description 50
- 208000029078 coronary artery disease Diseases 0.000 claims description 42
- 230000006870 function Effects 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 20
- 230000007170 pathology Effects 0.000 claims description 15
- 238000003745 diagnosis Methods 0.000 claims description 14
- 230000000875 corresponding effect Effects 0.000 claims description 13
- 238000013075 data extraction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 39
- 208000026106 cerebrovascular disease Diseases 0.000 description 38
- 230000002526 effect on cardiovascular system Effects 0.000 description 38
- 230000036541 health Effects 0.000 description 14
- 238000012886 linear function Methods 0.000 description 12
- 239000008280 blood Substances 0.000 description 6
- 210000004369 blood Anatomy 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000002790 cross-validation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 239000003181 biological factor Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003907 kidney function Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 210000004185 liver Anatomy 0.000 description 2
- 230000003908 liver function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 210000002700 urine Anatomy 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006806 disease prevention Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a big data technology in artificial intelligence, and discloses a disease prediction method, which comprises the following steps: acquiring a pathological data set, a model data set and a prediction nonlinear relation of a user, and establishing a mapping relation between the pathological data set and the model data set; traversing and matching the pathological data set and the model data set based on the mapping relation to obtain a filtered data set; filling the filtered data set by using a filling algorithm to obtain a standard data set; training and generalizing the standard data set by utilizing a prediction nonlinear relation to obtain a prediction data set; and extracting the prediction data contained in the prediction data set, and determining the disease prediction result of the user according to the prediction data. The invention also provides a disease prediction device, an electronic device and a computer readable storage medium. The invention can solve the problem of low reliability of the disease prediction result.
Description
Technical Field
The invention relates to the technical field of big data in artificial intelligence, is applied to an intelligent medical scene, and relates to a disease prediction method, a disease prediction device, electronic equipment and a readable storage medium.
Background
As the living standard of people is improved, more and more people pay attention to the physical health condition, and the evaluation of the health condition is an increasingly common scene requirement in life, such as physical examination report analysis, health education, disease prevention and the like.
Currently, evaluation tests and reports about various diseases are on the market, but the health evaluation modes are general and general, specific cause sources and reliable prediction results of the diseases cannot be obtained, and the health evaluation modes are not related to specific health evaluation models, so that whether an individual has a disease risk or not cannot be reliably predicted.
Disclosure of Invention
The invention provides a disease prediction method, a disease prediction device, an electronic device and a computer readable storage medium, and mainly aims to improve the reliability of disease prediction.
In order to achieve the above object, the present invention provides a disease prediction method, including:
acquiring a pathological data set of a user;
acquiring a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set;
establishing a mapping relation between the pathological data set and the model data set;
traversing and matching the pathological data set and the model data set based on the mapping relation to obtain a filtered data set;
filling the filtering data set by using a filling algorithm to obtain a standard data set;
training and generalizing the standard data set by using the prediction nonlinear relation to obtain a prediction data set;
extracting prediction data contained in the prediction data set;
and determining a disease prediction result of the user according to the prediction data.
Optionally, before the obtaining the model dataset and the predicting the non-linear relationship, the method further comprises:
acquiring the sample data set;
performing loss calculation on the sample data set through a loss function to obtain a sample function set;
performing iterative computation on the sample function set through a target function to obtain a sample iterative set;
and performing regularization calculation on the sample iteration set to obtain a model data set.
Optionally, after obtaining the model data set, the method further includes:
and carrying out hyper-parameter adjustment on the model data set by a grid search method to obtain the prediction nonlinear relation.
Optionally, the mapping the pathology data set and the model data set includes:
creating a user diagnosis data table corresponding to the pathological data set of the user, wherein the user diagnosis data table comprises heart failure data items, coronary heart disease data items and stroke data items;
creating a model data table corresponding to the model data set, wherein the model data table comprises the heart failure data item, the coronary heart disease data item and the stroke data item;
and establishing association between the pathological data set and the model data set through the heart failure data item, the coronary heart disease data item and the stroke data item to obtain a mapping relation.
Optionally, the populating the filtered data set with a population algorithm to obtain a standard data set includes:
performing missing classification on the filtering data set to obtain a classified data set;
and performing data interpolation on the classified data set through a filling function in a filling algorithm to obtain a standard data set, wherein the standard data set can be stored in a block chain.
Optionally, the training and generalization of the standard data set by using the predictive nonlinear relationship to obtain a predictive data set includes:
equally dividing the standard data set to obtain at least two groups of divided data sets;
correlating the at least two groups of divided data sets by utilizing the prediction nonlinear relation to obtain a correlated data set;
and performing mean calculation on the associated data sets to obtain a prediction data set, wherein the prediction data set can be stored in a block chain.
Optionally, the extracting the prediction data included in the prediction data set includes:
and extracting the prediction data contained in the prediction data set by using a regular expression.
In order to solve the above problem, the present invention also provides a disease prediction apparatus, comprising:
the system comprises a first data acquisition module, a second data acquisition module and a third data acquisition module, wherein the first data acquisition module is used for acquiring a pathological data set of a user;
the second data acquisition module is used for acquiring a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set;
the mapping relation establishing module is used for establishing a mapping relation between the pathological data set and the model data set;
the data matching module is used for performing traversal matching on the pathological data set and the model data set based on the mapping relation to obtain a filtering data set;
the data filling module is used for filling the filtering data set by using a filling algorithm to obtain a standard data set;
the data calculation module is used for training and generalizing the standard data set by utilizing the prediction nonlinear relation to obtain a prediction data set;
the data extraction module is used for extracting the prediction data contained in the prediction data set;
and the determining module is used for determining a disease prediction result of the user according to the prediction data.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
a processor executing instructions stored in the memory to implement a disease prediction method as described in any of the above.
In order to solve the above problems, the present invention also provides a computer-readable storage medium including a storage data area storing data created according to use of blockchain nodes and a storage program area storing at least one computer program instruction; the at least one instruction is executable by a processor in an electronic device to implement a disease prediction method as in any above.
The method is mainly applied to an artificial intelligence intelligent medical scene, realizes disease prediction based on big data, and obtains a pathological data set of a user; acquiring a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set; establishing a mapping relation between the pathological data set and the model data set, and performing traversal matching on the pathological data set and the model data set based on the mapping relation to obtain a filtered data set; filling the filtering data set by using a filling algorithm to obtain a standard data set; training and generalizing the standard data set by using the prediction nonlinear relation to obtain a prediction data set; extracting prediction data contained in the prediction data set; and determining a disease prediction result of the user according to the prediction data. By means of the filling algorithm, the prediction nonlinear relation and the data extraction of the prediction data set, the accuracy and the reliability of the prediction result can be further improved. Therefore, the embodiment of the invention can achieve the aim of improving the reliability of disease prediction. Further, the related data in the invention can be stored in a block chain to improve the security of the data.
Drawings
FIG. 1 is a schematic flow chart of a disease prediction method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a disease prediction apparatus according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an internal structure of an electronic device implementing a disease prediction method according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a disease prediction method. Fig. 1 is a schematic flow chart of a disease prediction method according to an embodiment of the present invention. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In an embodiment of the present invention, a disease prediction method comprises:
and S1, acquiring a pathological data set of the user.
In an alternative embodiment, the pathology data set of the user includes at least two items of heart failure data, coronary heart disease data, and stroke data, and the disease prediction method according to this embodiment can predict cardiovascular and cerebrovascular diseases.
Further, in other optional embodiments of the present invention, the pathology data set of the user may further include other data related to the physical condition of the user, and other diseases may be predicted by the disease prediction method described in this embodiment.
For example, in the prior art, if it is required to identify whether mr. zhanghai has cardiovascular and cerebrovascular diseases, the mr. zhanghai has been checked by electrocardiogram, head CT, liver and kidney function, blood routine, urine routine, blood fat and blood sugar, etc., and the occurrence of cardiovascular and cerebrovascular diseases and the degree of the disease are determined according to the data indexes, and the cause of the cardiovascular and cerebrovascular diseases is evaluated, however, different results may be obtained according to the experience of the doctor.
When the method is used for prediction, a morningmansia pathological data set is obtained, wherein the pathological data set comprises at least two of heart failure data, coronary heart disease data and stroke data, and the cardiovascular and cerebrovascular diseases are predicted.
S2, obtaining a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set.
In detail, the sample data set includes heart failure data, coronary heart disease data and stroke data of a sample user, and the disease prediction model may be a cardiovascular and cerebrovascular disease prediction model.
Preferably, the model data set may be obtained in the following manner.
Before the obtaining the model dataset and the predicting the non-linear relationship, the method further comprises:
acquiring a sample data set;
performing loss calculation on the sample data set through a loss function to obtain a sample function set;
performing iterative computation on the sample function set through a target function to obtain a sample iterative set;
and performing regularization calculation on the sample iteration set to obtain a model data set.
Further, after obtaining the model data set, the method further includes: and carrying out hyper-parameter adjustment on the model data set by a grid search method to obtain a prediction nonlinear relation.
In the embodiment of the invention, the grid searching method is an exhaustive searching method for specified parameter values, and is an optimal learning algorithm obtained by optimizing the parameters of the estimation function through a cross validation method.
In the embodiment of the invention, the super-parameter adjustment of the model data set by a grid search method comprises the following steps: arranging and combining various parameter values in the model data set; listing all possible combination results; evaluating all possible combination results by using cross validation to obtain an optimal combination result; and generating a prediction nonlinear relation of the optimal combination result through a fitting function.
And S3, establishing a mapping relation between the pathological data set and the model data set.
Preferably, the mapping the pathology data set and the model data set includes:
creating a user diagnosis data table corresponding to the pathological data set of the user, wherein the user diagnosis data table comprises heart failure data items, coronary heart disease data items and stroke data items;
creating a model data table corresponding to the model data set, wherein the model data table comprises the heart failure data, coronary heart disease data and stroke data;
and establishing association between the pathological data set and the model data set through the heart failure data item, the coronary heart disease data item and the stroke data item to obtain a mapping relation.
For example, a diagnosis data table corresponding to a morningmankind pathological data set is created, the diagnosis data table comprises at least two data of a morningmankind heart failure data item, a coronary heart disease data item and a stroke data item, a model data table corresponding to the model data set is created, the model data table comprises the heart failure data item, the coronary heart disease data item and the stroke data item, based on the diagnosis data table, the model data table is searched for the heart failure data item, the coronary heart disease data item and the stroke data item, and the association between the morningmankind pathological data set and the model data set is completed to obtain a mapping relation.
And S4, traversing and matching the pathological data set and the model data set based on the mapping relation to obtain a filtering data set.
Through traversal matching, data in the model dataset that is related to the pathology dataset may be obtained.
For example, the pathological data set of mr. zhangsheng is transmitted to the model data set, and according to the mapping relation, the heart failure data item, coronary heart disease data item and stroke data item of mr. zhangsheng in the model data set are searched in a traversing way. And obtaining a sample pathological data set which is the same as the heart failure data item, the coronary heart disease data item and the stroke data item of mr. zhang in the model data set through the data value matching of the heart failure data item, the coronary heart disease data item and the stroke data item, wherein the sample pathological data set is a filtering data set obtained by traversing and matching the pathological data set of mr. zhang with the model data set.
And S5, filling the filtering data set by using a filling algorithm to obtain a standard data set.
In the embodiment of the invention, the filtering data set is filled, so that the data integrity can be improved, and the influence of data missing on the accuracy of the prediction result is avoided.
Preferably, the padding the filtered data set by using a padding algorithm to obtain a standard data set includes:
performing missing classification on the filtering data set to obtain a classified data set;
and performing data interpolation on the classified data set through a filling function in a filling algorithm to obtain a standard data set.
For example, if the heart failure data item is missing in the pathological data set of mr, the heart failure data item is marked, the missing data in the heart failure data item is supplemented by an unknown number (such as X) to obtain a classified data set, and then the unknown number in the missing heart failure data item is subjected to data interpolation through a filling function in a filling algorithm to obtain a standard data set.
In an embodiment, the standard data set may be stored in a block chain. The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
And S6, training and generalizing the standard data set by utilizing the prediction nonlinear relation to obtain a prediction data set.
In the embodiment of the present invention, the prediction data set obtained by generalization of training includes prediction data of the physical condition of the user, for example, heart failure prediction data and coronary heart disease prediction data.
Preferably, the training and generalization of the standard data set by using the predictive nonlinear relationship to obtain a predictive data set includes:
equally dividing the standard data set to obtain at least two groups of divided data sets;
correlating at least two groups of divided data sets by utilizing the prediction nonlinear relation to obtain a correlated data set;
and carrying out mean value calculation on the associated data set to obtain a prediction data set.
In an embodiment, the prediction data set may be stored in a block chain.
In the embodiment of the invention, the standard data set is equally divided into N groups, wherein N is more than or equal to 2.
In the embodiment of the present invention, the at least two groups of partitioned data sets are associated by using the predictive nonlinear relationship, specifically, data conforming to the predictive nonlinear relationship in the at least two groups of partitioned data sets are associated.
And S7, extracting the prediction data contained in the prediction data set.
Preferably, the extracting data included in the prediction data set comprises: and extracting data contained in the prediction data set by using a regular expression.
For example, the prediction dataset comprises: the heart failure data 420, the coronary heart disease data 132 and the stroke data 150 are obtained by extracting data of a prediction data set by using a Python regular expression to obtain numerical data 420132150 and text data, namely the heart failure data, the coronary heart disease data and the stroke data.
Specifically, the Python code is: findall (r'd +', 'heart failure data 420 coronary heart disease data 132 stroke data 150').
And S8, determining the disease prediction result of the user according to the prediction data.
In the embodiment of the invention, the disease prediction result of the user is the identification result of whether the user has the cardiovascular and cerebrovascular diseases and the cardiovascular and cerebrovascular disease conditions.
For example, the prediction result is classified into one of four grades of sick, high-risk, medium-risk and low-risk.
Further, determining a disease prediction outcome for the user from the prediction data comprises: and performing division calculation on the prediction data to determine a disease prediction result of the user.
Specifically, the prediction result can be obtained by performing division calculation through the following formula:
h＝ax+by+cz
the method comprises the steps of obtaining a heart failure prediction coefficient, a coronary heart disease prediction coefficient, a stroke prediction coefficient, a heart failure prediction data, a coronary heart disease prediction data and a stroke prediction data.
In the embodiment of the invention, when h is more than or equal to a first preset value, the user is determined to be suffering from cardiovascular and cerebrovascular diseases; when h is greater than a first preset value and less than or equal to a second preset value, determining that the severity level of the cardiovascular and cerebrovascular diseases of the user is a low risk; when h is greater than the second preset value and less than or equal to a third preset value, determining that the severity level of the cardiovascular and cerebrovascular diseases of the user is an intermediate risk; and when h is larger than a third preset value, determining that the severity level of the cardiovascular and cerebrovascular diseases of the user is a high risk.
For example, when h is more than or equal to 40, the user is suffered from the cardiovascular and cerebrovascular diseases, when 40 is less than or equal to h is less than or equal to 60, the severity grade of the cardiovascular and cerebrovascular diseases of the user is low risk, when 60 is less than or equal to h is less than or equal to 80, the severity grade of the cardiovascular and cerebrovascular diseases of the user is medium risk, when h is more than 80, the severity grade of the cardiovascular and cerebrovascular diseases of the user is high risk, and when the prediction result of Zhang Sheng is 78, the severity grade of the cardiovascular and cerebrovascular diseases of Zhang Sheng is medium risk.
Further, in another embodiment of the present invention, the prediction is combined with F1Linear function, F2Linear function sum F3The linear function is calculated to output a health index which is used for identifying specific horizontal positions in the severity grade disease grade of the cardiovascular and cerebrovascular diseases of the patient, for example: the prediction result of Zhang Mr. shows that the severity level of cardiovascular and cerebrovascular diseases of Zhang Mr. is the middle risk, and the specific horizontal position of Zhang Mr. in the high risk can be determined through the health index.
In detail, said F1The linear function is expressed as:
F1＝W/H2
wherein W represents weight and H represents height.
Further, F2The linear function is expressed as:
F2＝f(E)+ACHS+B+LS+h
the system comprises a health facility, a living point, a biological factor coefficient, a secondary linear relation function, an environment coefficient, an ACHS (adaptive coordination high speed high.
Further, F3The linear function is expressed as:
wherein L represents temperature value, E (L) represents linear interpolation standard error determined by structural function of gas temperature field and humidity field of meteorological observation station, bfRepresents the average value, σ, of the concentration of pollutants in the air2And/2 represents the random error of the monitored air index.
Further, the health index is calculated by the following method:
Score＝X0*(F1+F2+F3)
wherein x is0Is a preset initial fraction value.
The embodiment of the invention obtains a pathological data set of a user; acquiring a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set; establishing a mapping relation between the pathological data set and the model data set, and performing traversal matching on the pathological data set and the model data set based on the mapping relation to obtain a filtered data set; filling the filtering data set by using a filling algorithm to obtain a standard data set; training and generalizing the standard data set by using the prediction nonlinear relation to obtain a prediction data set; extracting prediction data contained in the prediction data set; and determining a disease prediction result of the user according to the prediction data. By means of the filling algorithm, the prediction nonlinear relation and the data extraction of the prediction data set, the accuracy and the reliability of the prediction result can be further improved. Therefore, the embodiment of the invention can achieve the aim of improving the reliability of disease prediction.
FIG. 2 is a functional block diagram of the disease prediction apparatus of the present invention.
The disease prediction apparatus 100 according to the present invention may be installed in an electronic device. According to the realized functions, the disease prediction apparatus may include a first data acquisition module 101, a second data acquisition module 102, a mapping relationship establishment module 103, a data matching module 104, a data filling module 105, a data calculation module 106, a data extraction module 107, and a determination module 108. A module according to the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the embodiment of the present invention, the functions of the modules/units are as follows:
a first data acquisition module 101, configured to acquire a pathological data set of a user;
the second data acquisition module 102 is configured to acquire a model data set and a prediction nonlinear relationship, where the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relationship is obtained by performing hyper-parameter adjustment on the model data set;
a mapping relationship establishing module 103, configured to establish a mapping relationship between the pathology data set and the model data set;
the data matching module 104 is configured to perform traversal matching on the pathology data set and the model data set based on the mapping relationship to obtain a filtered data set;
a data filling module 105, configured to fill the filtered data set with a filling algorithm to obtain a standard data set;
the data calculation module 106 is configured to train and generalize the standard data set by using the prediction nonlinear relationship to obtain a prediction data set;
a data extraction module 107, configured to extract prediction data included in the prediction data set;
a determining module 108 for determining a disease prediction result of the user according to the prediction data.
In detail, the specific implementation steps of each module of the disease prediction device are as follows:
the first data acquisition module 101 acquires a pathology data set of a user.
In an alternative embodiment, the pathology data set of the user includes at least two items of heart failure data, coronary heart disease data, and stroke data, and the disease prediction method according to this embodiment can predict cardiovascular and cerebrovascular diseases.
Further, in other optional embodiments of the present invention, the pathology data set of the user may further include other data related to the physical condition of the user, and other diseases may be predicted by the disease prediction method described in this embodiment.
For example, in the prior art, if it is required to identify whether mr. zhanghai has cardiovascular and cerebrovascular diseases, the mr. zhanghai has been checked by electrocardiogram, head CT, liver and kidney function, blood routine, urine routine, blood fat and blood sugar, etc., and the occurrence of cardiovascular and cerebrovascular diseases and the degree of the disease are determined according to the data indexes, and the cause of the cardiovascular and cerebrovascular diseases is evaluated, however, different results may be obtained according to the experience of the doctor.
When the method is used for prediction, a morningmansia pathological data set is obtained, wherein the pathological data set comprises at least two of heart failure data, coronary heart disease data and stroke data, and the cardiovascular and cerebrovascular diseases are predicted.
The second data obtaining module 102 obtains a model data set obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and a prediction nonlinear relation obtained by performing hyper-parameter adjustment on the model data set.
In detail, the sample data set includes heart failure data, coronary heart disease data and stroke data of a sample user, and the disease prediction model may be a cardiovascular and cerebrovascular disease prediction model.
Preferably, the model data set may be obtained in the following manner.
Before the obtaining the model dataset and the predicting the non-linear relationship, the method further comprises:
acquiring a sample data set;
performing loss calculation on the sample data set through a loss function to obtain a sample function set;
performing iterative computation on the sample function set through a target function to obtain a sample iterative set;
and performing regularization calculation on the sample iteration set to obtain a model data set.
Further, after obtaining the model data set, the method further includes: and carrying out hyper-parameter adjustment on the model data set by a grid search method to obtain a prediction nonlinear relation.
In the embodiment of the invention, the grid searching method is an exhaustive searching method for specified parameter values, and is an optimal learning algorithm obtained by optimizing the parameters of the estimation function through a cross validation method.
In the embodiment of the invention, the super-parameter adjustment of the model data set by a grid search method comprises the following steps: arranging and combining various parameter values in the model data set; listing all possible combination results; evaluating all possible combination results by using cross validation to obtain an optimal combination result; and generating a prediction nonlinear relation of the optimal combination result through a fitting function.
The mapping relationship establishing module 103 establishes a mapping relationship between the pathology data set and the model data set.
Preferably, the mapping the pathology data set and the model data set includes:
creating a user diagnosis data table corresponding to the pathological data set of the user, wherein the user diagnosis data table comprises heart failure data items, coronary heart disease data items and stroke data items;
creating a model data table corresponding to the model data set, wherein the model data table comprises the heart failure data, coronary heart disease data and stroke data;
and establishing association between the pathological data set and the model data set through the heart failure data item, the coronary heart disease data item and the stroke data item to obtain a mapping relation.
For example, a diagnosis data table corresponding to a morningmankind pathological data set is created, the diagnosis data table comprises at least two data of a morningmankind heart failure data item, a coronary heart disease data item and a stroke data item, a model data table corresponding to the model data set is created, the model data table comprises the heart failure data item, the coronary heart disease data item and the stroke data item, based on the diagnosis data table, the model data table is searched for the heart failure data item, the coronary heart disease data item and the stroke data item, and the association between the morningmankind pathological data set and the model data set is completed to obtain a mapping relation.
The data matching module 104 performs traversal matching on the pathology data set and the model data set based on the mapping relationship to obtain a filtered data set.
Through traversal matching, data in the model dataset that is related to the pathology dataset may be obtained.
For example, the pathological data set of mr. zhangsheng is transmitted to the model data set, and according to the mapping relation, the heart failure data item, coronary heart disease data item and stroke data item of mr. zhangsheng in the model data set are searched in a traversing way. And obtaining a sample pathological data set which is the same as the heart failure data item, the coronary heart disease data item and the stroke data item of mr. zhang in the model data set through the data value matching of the heart failure data item, the coronary heart disease data item and the stroke data item, wherein the sample pathological data set is a filtering data set obtained by traversing and matching the pathological data set of mr. zhang with the model data set.
The data population module 105 populates the filtered data set with a population algorithm to obtain a standard data set.
In the embodiment of the invention, the filtering data set is filled, so that the data integrity can be improved, and the influence of data missing on the accuracy of the prediction result is avoided.
Preferably, the padding the filtered data set by using a padding algorithm to obtain a standard data set includes:
performing missing classification on the filtering data set to obtain a classified data set;
and performing data interpolation on the classified data set through a filling function in a filling algorithm to obtain a standard data set.
For example, if the heart failure data item is missing in the pathological data set of mr, the heart failure data item is marked, the missing data in the heart failure data item is supplemented by an unknown number (such as X) to obtain a classified data set, and then the unknown number in the missing heart failure data item is subjected to data interpolation through a filling function in a filling algorithm to obtain a standard data set.
The data calculation module 106 trains and generalizes the standard data set by using the prediction nonlinear relation to obtain a prediction data set.
In the embodiment of the present invention, the prediction data set obtained by generalization of training includes prediction data of the physical condition of the user, for example, heart failure prediction data and coronary heart disease prediction data.
Preferably, the training and generalization of the standard data set by using the predictive nonlinear relationship to obtain a predictive data set includes:
equally dividing the standard data set to obtain at least two groups of divided data sets;
correlating at least two groups of divided data sets by utilizing the prediction nonlinear relation to obtain a correlated data set;
and carrying out mean value calculation on the associated data set to obtain a prediction data set.
In the embodiment of the invention, the standard data set is equally divided into N groups, wherein N is more than or equal to 2.
In the embodiment of the present invention, the at least two groups of partitioned data sets are associated by using the predictive nonlinear relationship, specifically, data conforming to the predictive nonlinear relationship in the at least two groups of partitioned data sets are associated.
The data extraction module 107 extracts the prediction data contained in the prediction data set.
Preferably, the extracting data included in the prediction data set comprises: and extracting data contained in the prediction data set by using a regular expression.
For example, the prediction dataset comprises: the heart failure data 420, the coronary heart disease data 132 and the stroke data 150 are obtained by extracting data of a prediction data set by using a Python regular expression to obtain numerical data 420132150 and text data, namely the heart failure data, the coronary heart disease data and the stroke data.
Specifically, the Python code is: findall (r'd +', 'heart failure data 420 coronary heart disease data 132 stroke data 150').
The determination module 108 determines a disease prediction result of the user from the prediction data.
In the embodiment of the invention, the disease prediction result of the user is the identification result of whether the user has the cardiovascular and cerebrovascular diseases and the cardiovascular and cerebrovascular disease conditions.
For example, the prediction result is classified into one of four grades of sick, high-risk, medium-risk and low-risk.
Further, determining a disease prediction outcome for the user from the prediction data comprises: and performing division calculation on the prediction data to determine a disease prediction result of the user.
Specifically, the prediction result can be obtained by performing division calculation through the following formula:
h＝ax+by+cz
the method comprises the steps of obtaining a heart failure prediction coefficient, a coronary heart disease prediction coefficient, a stroke prediction coefficient, a heart failure prediction data, a coronary heart disease prediction data and a stroke prediction data.
In the embodiment of the invention, when h is more than or equal to a first preset value, the user is determined to be suffering from cardiovascular and cerebrovascular diseases; when h is greater than a first preset value and less than or equal to a second preset value, determining that the severity level of the cardiovascular and cerebrovascular diseases of the user is a low risk; when h is greater than the second preset value and less than or equal to a third preset value, determining that the severity level of the cardiovascular and cerebrovascular diseases of the user is an intermediate risk; and when h is larger than a third preset value, determining that the severity level of the cardiovascular and cerebrovascular diseases of the user is a high risk.
For example, when h is more than or equal to 40, the user is suffered from the cardiovascular and cerebrovascular diseases, when 40 is less than or equal to h is less than or equal to 60, the severity grade of the cardiovascular and cerebrovascular diseases of the user is low risk, when 60 is less than or equal to h is less than or equal to 80, the severity grade of the cardiovascular and cerebrovascular diseases of the user is medium risk, when h is more than 80, the severity grade of the cardiovascular and cerebrovascular diseases of the user is high risk, and when the prediction result of Zhang Sheng is 78, the severity grade of the cardiovascular and cerebrovascular diseases of Zhang Sheng is medium risk.
Further, in another embodiment of the present invention, the prediction is combined with F1Linear function, F2Linear function sum F3The linear function is calculated to output a health index which is used for identifying specific horizontal positions in the severity grade disease grade of the cardiovascular and cerebrovascular diseases of the patient, for example: the prediction result of Zhang Mr. shows that the severity level of cardiovascular and cerebrovascular diseases of Zhang Mr. is the middle risk, and the specific horizontal position of Zhang Mr. in the high risk can be determined through the health index.
In detail, said F1The linear function is expressed as:
F1＝W/H2
wherein W represents weight and H represents height.
Further, F2The linear function is expressed as:
F2＝f(E)+ACHS+B+LS+h
the system comprises a health facility, a living point, a biological factor coefficient, a secondary linear relation function, an environment coefficient, an ACHS (adaptive coordination high speed high.
Further, F3The linear function is expressed as:
wherein L represents temperature value, E (L) represents linear interpolation standard error determined by structural function of gas temperature field and humidity field of meteorological observation station, bfRepresents the average value, σ, of the concentration of pollutants in the air2And/2 represents the random error of the monitored air index.
Further, the health index is calculated by the following method:
Score＝X0*(F1+F2+F3)
wherein x is0Is a preset initial fraction value.
In the embodiment of the invention, a first data acquisition module acquires a pathological data set of a user; the second data acquisition module acquires a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set; the mapping relation establishing module establishes a mapping relation between the pathological data set and the model data set; the data matching module is used for performing traversal matching on the pathological data set and the model data set based on the mapping relation to obtain a filtering data set; the data filling module fills the filtered data set by using a filling algorithm to obtain a standard data set; the data calculation module trains and generalizes the standard data set by using the prediction nonlinear relation to obtain a prediction data set; the data extraction module extracts the prediction data contained in the prediction data set; a determination module determines a disease prediction result of the user based on the prediction data. By means of the filling algorithm, the prediction nonlinear relation and the data extraction of the prediction data set, the accuracy and the reliability of the prediction result can be further improved. Therefore, the embodiment of the invention can achieve the aim of improving the reliability of disease prediction.
Fig. 3 is a schematic structural diagram of an electronic device for implementing the disease prediction method according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a cardiovascular disease prediction program 12 based on pathological data, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes for disease prediction, etc., but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., performing disease prediction, etc.) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The memory 11 in the electronic device 1 stores a disease prediction 12 that is a combination of instructions that, when executed in the processor 10, may effect:
acquiring a pathological data set of a user;
acquiring a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set;
establishing a mapping relation between the pathological data set and the model data set;
traversing and matching the pathological data set and the model data set based on the mapping relation to obtain a filtered data set;
filling the filtering data set by using a filling algorithm to obtain a standard data set;
training and generalizing the standard data set by using the prediction nonlinear relation to obtain a prediction data set;
extracting prediction data contained in the prediction data set;
and determining a disease prediction result of the user according to the prediction data.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method of disease prediction, the method comprising:
acquiring a pathological data set of a user;
acquiring a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set;
establishing a mapping relation between the pathological data set and the model data set;
traversing and matching the pathological data set and the model data set based on the mapping relation to obtain a filtered data set;
filling the filtering data set by using a filling algorithm to obtain a standard data set;
training and generalizing the standard data set by using the prediction nonlinear relation to obtain a prediction data set;
extracting prediction data contained in the prediction data set;
and determining a disease prediction result of the user according to the prediction data.
2. The disease prediction method of claim 1, wherein prior to obtaining the model dataset and predicting the non-linear relationship, the method further comprises:
acquiring the sample data set;
performing loss calculation on the sample data set through a loss function to obtain a sample function set;
performing iterative computation on the sample function set through a target function to obtain a sample iterative set;
and performing regularization calculation on the sample iteration set to obtain a model data set.
3. The method of disease prediction according to claim 2, wherein after obtaining the model dataset, the method further comprises: and carrying out hyper-parameter adjustment on the model data set by a grid search method to obtain the prediction nonlinear relation.
4. A disease prediction method as claimed in any one of claims 1 to 3, wherein the mapping the pathology data set to the model data set comprises:
creating a user diagnosis data table corresponding to the pathological data set of the user, wherein the user diagnosis data table comprises heart failure data items, coronary heart disease data items and stroke data items;
creating a model data table corresponding to the model data set, wherein the model data table comprises the heart failure data item, the coronary heart disease data item and the stroke data item;
and establishing association between the pathological data set and the model data set through the heart failure data item, the coronary heart disease data item and the stroke data item to obtain a mapping relation.
5. A disease prediction method as claimed in any one of claims 1 to 3 wherein said populating said filtered data set with a population algorithm to obtain a standard data set comprises:
performing missing classification on the filtering data set to obtain a classified data set;
and performing data interpolation on the classified data set through a filling function in a filling algorithm to obtain a standard data set, wherein the standard data set can be stored in a block chain.
6. A disease prediction method as claimed in any one of claims 1 to 3 wherein said training said normative dataset using said predictive non-linear relationship to produce a predictive dataset comprises:
equally dividing the standard data set to obtain at least two groups of divided data sets;
correlating the at least two groups of divided data sets by utilizing the prediction nonlinear relation to obtain a correlated data set;
and performing mean calculation on the associated data sets to obtain a prediction data set, wherein the prediction data set can be stored in a block chain.
7. A disease prediction method as claimed in any one of claims 1 to 3 wherein the extracting of prediction data contained in the prediction data set comprises:
and extracting the prediction data contained in the prediction data set by using a regular expression.
8. A disease prediction apparatus, characterized in that the apparatus comprises:
the system comprises a first data acquisition module, a second data acquisition module and a third data acquisition module, wherein the first data acquisition module is used for acquiring a pathological data set of a user;
the second data acquisition module is used for acquiring a model data set and a prediction nonlinear relation, wherein the model data set is obtained by training a pre-constructed disease prediction model through an extreme gradient lifting algorithm and a sample data set, and the prediction nonlinear relation is obtained by carrying out hyper-parameter adjustment on the model data set;
the mapping relation establishing module is used for establishing a mapping relation between the pathological data set and the model data set;
the data matching module is used for performing traversal matching on the pathological data set and the model data set based on the mapping relation to obtain a filtering data set;
the data filling module is used for filling the filtering data set by using a filling algorithm to obtain a standard data set;
the data calculation module is used for training and generalizing the standard data set by utilizing the prediction nonlinear relation to obtain a prediction data set;
the data extraction module is used for extracting the prediction data contained in the prediction data set;
and the determining module is used for determining a disease prediction result of the user according to the prediction data.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a disease prediction method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium comprising a storage data area storing data created according to use of a blockchain node and a storage program area storing a computer program; the computer program, when executed by a processor, implements a disease prediction method as claimed in any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010458696.8A CN111696662A (en) | 2020-05-26 | 2020-05-26 | Disease prediction method, device and storage medium |
| PCT/CN2020/098967 WO2021151273A1 (en) | 2020-05-26 | 2020-06-29 | Disease prediction method and apparatus, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010458696.8A CN111696662A (en) | 2020-05-26 | 2020-05-26 | Disease prediction method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111696662A true CN111696662A (en) | 2020-09-22 |
Family
ID=72478450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010458696.8A Pending CN111696662A (en) | 2020-05-26 | 2020-05-26 | Disease prediction method, device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111696662A (en) |
| WO (1) | WO2021151273A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233737A (en) * | 2020-11-19 | 2021-01-15 | 吾征智能技术(北京)有限公司 | Disease cognitive system based on urine conventional information |
| CN113724878A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Medical risk information pushing method and device based on machine learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717867A (en) * | 2018-05-02 | 2018-10-30 | 中国科学技术大学苏州研究院 | Disease forecasting method for establishing model and device based on Gradient Iteration tree |
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| CN110838366A (en) * | 2019-10-15 | 2020-02-25 | 平安科技（深圳）有限公司 | Method and device for predicting disease risk |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6280997B1 (en) * | 2016-10-31 | 2018-02-14 | 株式会社Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ | Disease onset determination device, disease onset determination method, disease feature extraction device, and disease feature extraction method |
| CN109003679B (en) * | 2018-06-28 | 2021-06-08 | 众安信息技术服务有限公司 | Method and device for predicting cerebral hemorrhage and ischemia |
| CN109616205A (en) * | 2018-12-04 | 2019-04-12 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN110197720A (en) * | 2019-03-12 | 2019-09-03 | 平安科技（深圳）有限公司 | Prediction technique and device, storage medium, the computer equipment of diabetes |
-
2020
- 2020-05-26 CN CN202010458696.8A patent/CN111696662A/en active Pending
- 2020-06-29 WO PCT/CN2020/098967 patent/WO2021151273A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108717867A (en) * | 2018-05-02 | 2018-10-30 | 中国科学技术大学苏州研究院 | Disease forecasting method for establishing model and device based on Gradient Iteration tree |
| CN109117864A (en) * | 2018-07-13 | 2019-01-01 | 华南理工大学 | Coronary heart disease risk prediction technique, model and system based on heterogeneous characteristic fusion |
| CN110838366A (en) * | 2019-10-15 | 2020-02-25 | 平安科技（深圳）有限公司 | Method and device for predicting disease risk |
Non-Patent Citations (2)
| Title |
|---|
| 何龙: "《深入理解XGBoost 高效机器学习算法与进阶》", vol. 1, 31 January 2020, 机械工业出版社, pages: 319 * |
| 菅小艳: "《贝叶斯网基础及应用》", vol. 1, 31 May 2019, 第122页, pages: 122 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112233737A (en) * | 2020-11-19 | 2021-01-15 | 吾征智能技术(北京)有限公司 | Disease cognitive system based on urine conventional information |
| CN113724878A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Medical risk information pushing method and device based on machine learning |
| CN113724878B (en) * | 2021-08-31 | 2024-05-10 | 平安科技（深圳）有限公司 | Medical risk information pushing method and device based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021151273A1 (en) | 2021-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113592019B (en) | Fault detection method, device, equipment and medium based on multi-model fusion | |
| JPWO2019187341A1 (en) | Index calculator, forecasting system, progress forecast evaluation method and program | |
| CN114496264B (en) | Health index analysis method, device, equipment and medium based on multidimensional data | |
| CN113674858B (en) | Intelligent inspection method, device, equipment and storage medium for on-line medical prescription medication | |
| CN111696662A (en) | Disease prediction method, device and storage medium | |
| CN114783618A (en) | Traditional Chinese medicine model training method and device based on knowledge structure and four-diagnosis character | |
| CN113516417A (en) | Service evaluation method and device based on intelligent modeling, electronic equipment and medium | |
| CN114399212A (en) | Ecological environment quality evaluation method and device, electronic equipment and storage medium | |
| CN112885423A (en) | Disease label detection method and device, electronic equipment and storage medium | |
| CN112489747A (en) | Chronic patient supervision method, device, equipment and medium based on analysis model | |
| CN114240874A (en) | Bone age assessment method and device based on deep convolutional neural network and feature fusion and computer readable storage medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| CN117151655B (en) | Comprehensive analysis management system and method for multiple project detection results | |
| CN117373580A (en) | Performance analysis method and system for realizing titanium alloy product based on time sequence network | |
| CN116403693A (en) | Method, device, equipment and storage medium for dispatching questionnaire | |
| CN111460293A (en) | Information pushing method and device and computer readable storage medium | |
| CN111652282A (en) | Big data based user preference analysis method and device and electronic equipment | |
| CN116779184A (en) | Method, system and equipment for quasi-real-time monitoring of vaccine safety and storage medium | |
| CN113657546B (en) | Information classification method, device, electronic equipment and readable storage medium | |
| CN113066580A (en) | Medical score determining method and device, electronic equipment and storage medium | |
| CN116936103B (en) | User health prediction management method and system based on homodromous network | |
| Van Houtte et al. | Acute admission risk stratification of New Zealand primary care patients using demographic, multimorbidity, service usage and modifiable variables | |
| CN114391806A (en) | Disease early warning method, device, equipment and storage medium | |
| CN115938524A (en) | Health evaluation method and device, electronic equipment and medium | |
| CN116831527A (en) | Diabetes complication risk prediction method, device, equipment and storage medium |
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 |