CN116386879B - Risk level prediction device and computer storage medium - Google Patents
Risk level prediction device and computer storage medium Download PDFInfo
- Publication number
- CN116386879B CN116386879B CN202310667536.8A CN202310667536A CN116386879B CN 116386879 B CN116386879 B CN 116386879B CN 202310667536 A CN202310667536 A CN 202310667536A CN 116386879 B CN116386879 B CN 116386879B
- Authority
- CN
- China
- Prior art keywords
- prediction
- risk level
- risk
- prediction model
- index data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 claims description 21
- 238000012795 verification Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 abstract description 38
- 208000017667 Chronic Disease Diseases 0.000 description 19
- 238000010586 diagram Methods 0.000 description 11
- 239000008280 blood Substances 0.000 description 6
- 210000004369 blood Anatomy 0.000 description 6
- 230000036541 health Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 208000006011 Stroke Diseases 0.000 description 5
- 208000024172 Cardiovascular disease Diseases 0.000 description 4
- 206010008190 Cerebrovascular accident Diseases 0.000 description 4
- 230000002490 cerebral effect Effects 0.000 description 4
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 235000005911 diet Nutrition 0.000 description 4
- 230000037213 diet Effects 0.000 description 4
- 230000002526 effect on cardiovascular system Effects 0.000 description 4
- 230000037081 physical activity Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 208000020832 chronic kidney disease Diseases 0.000 description 3
- 208000029078 coronary artery disease Diseases 0.000 description 3
- 206010012601 diabetes mellitus Diseases 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012502 risk assessment Methods 0.000 description 3
- 208000014882 Carotid artery disease Diseases 0.000 description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 2
- 102000015779 HDL Lipoproteins Human genes 0.000 description 2
- 108010010234 HDL Lipoproteins Proteins 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 208000037876 carotid Atherosclerosis Diseases 0.000 description 2
- 208000026106 cerebrovascular disease Diseases 0.000 description 2
- 235000012000 cholesterol Nutrition 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000035487 diastolic blood pressure Effects 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 230000035488 systolic blood pressure Effects 0.000 description 2
- 230000002537 thrombolytic effect Effects 0.000 description 2
- 150000003626 triacylglycerols Chemical class 0.000 description 2
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 206010000891 acute myocardial infarction Diseases 0.000 description 1
- 239000003472 antidiabetic agent Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000000502 dialysis Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000002008 hemorrhagic effect Effects 0.000 description 1
- 229940126904 hypoglycaemic agent Drugs 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 208000028867 ischemia Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000002604 ultrasonography 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
- G16H50/30—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
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application discloses a risk level prediction device and a computer storage medium, wherein the device comprises: the first acquisition module is used for acquiring the physiological index data of the target object, wherein the physiological index data comprises first index data and second index data; the first prediction module is used for predicting a first risk value of the target physiological indication of the target object according to the first index data by using the first prediction model, and determining an initial risk level corresponding to the target object according to the first risk value; the first determining module is used for determining a second prediction model corresponding to the initial risk level under the condition that the initial risk level is greater than or equal to a preset risk level; and the second prediction module is used for predicting a second risk value of the target physiological indication of the target object according to the second index data by using a second prediction model, and determining a risk level corresponding to the target object according to the second risk value. According to the embodiment of the application, the screening cost can be reduced and the accuracy of risk level prediction can be improved.
Description
Technical Field
The application belongs to the technical field of data processing, and particularly relates to a risk level prediction device and a computer storage medium.
Background
When screening a target physiological indication of a target object, in order to improve screening accuracy, a prediction model is generally used for risk assessment, and the risk level of the target object is determined so as to perform intervention early.
In general, a large amount of index data support is required for constructing the risk level prediction model, and the wider the index data coverage range is, the more reliable the index data source is, the higher the reliability of the prediction result of the risk level prediction model is. However, when risk screening and risk level prediction are currently performed by using a risk level prediction model, screening is generally required from multiple aspects related to physiological indications due to the influence of factors such as limitation of screening range, data sources, screening capability and the like, and target objects are not distinguished, and each target object needs to be subjected to multiple screening and risk evaluation. Therefore, the screening cost is increased, accurate screening cannot be performed, and the accuracy of the risk level prediction result is low.
Disclosure of Invention
The embodiment of the application provides a risk level prediction device and a computer storage medium, which can reduce screening cost and improve the accuracy of a prediction result of a risk level obtained by prediction by the prediction device.
In a first aspect, an embodiment of the present application provides a risk level prediction apparatus, including:
the first acquisition module is used for acquiring the physiological index data of the target object, wherein the physiological index data comprises first index data and second index data;
The first prediction module is used for predicting a first risk value of the target physiological indication of the target object according to the first index data by using the first prediction model, and determining an initial risk level corresponding to the target object according to the first risk value;
The first determining module is used for determining a second prediction model corresponding to the initial risk level under the condition that the initial risk level is greater than or equal to a preset risk level;
And the second prediction module is used for predicting a second risk value of the target physiological indication of the target object according to the second index data by using a second prediction model, and determining a risk level corresponding to the target object according to the second risk value.
In some implementations of the first aspect, the predicting apparatus further includes:
The second obtaining module is used for obtaining coefficients of model prediction factors respectively corresponding to a plurality of preset risk levels before determining a second prediction model corresponding to the initial risk level;
The first adjusting module is used for respectively adjusting the coefficients of the prediction factors in the preset prediction models to the coefficients of the model prediction factors corresponding to each preset risk level to obtain a second prediction model corresponding to each preset risk level.
In some implementations of the first aspect, the first prediction module includes:
The first determination submodule is used for determining the value of a first prediction factor in the first prediction model based on the physiological index data of the target object;
the first computing sub-module is used for computing a first probability of the occurrence of the target physiological indication of the target object according to the value of the first prediction factor by using the first prediction model to obtain a first risk value;
the second determining submodule is used for determining the risk level where the first risk value is located according to the risk value ranges corresponding to the preset risk levels respectively, and the risk level is used as an initial risk level corresponding to the target object.
In some implementations of the first aspect, the second prediction module includes:
The third determination submodule is used for determining the value of a second prediction factor in the second prediction model based on the physiological index data of the target object;
the second calculation sub-module is used for calculating a second probability of the occurrence of the target physiological indication of the target object according to the value of the second prediction factor by using the second prediction model to obtain a second risk value;
and the fourth determining submodule is used for determining the risk level where the second risk value is located according to the risk value ranges respectively corresponding to the plurality of preset risk levels as the risk level corresponding to the target object.
In some implementations of the first aspect, the second predictor in the second prediction model includes a first predictor and a third predictor.
In some implementations of the first aspect, the predicting apparatus further includes:
The verification module is used for verifying the first prediction model and the second prediction model to obtain a verification result;
And the second adjusting module is used for adjusting the coefficients of the first predictive factor in the first predictive model and the coefficients of the second predictive factor in the second predictive model under the condition that the first predictive model and the second predictive model meet the preset conditions according to the verification result.
In some implementations of the first aspect, the verification module includes:
The acquisition sub-module is used for acquiring a plurality of sample sets, wherein the sample sets comprise a plurality of sample objects and corresponding physiological index data samples thereof;
the prediction sub-module is used for respectively predicting a risk value of each sample object in the plurality of sample sets for generating a target physiological indication according to the physiological index data samples by using the first prediction model and the second prediction model;
A fifth determining submodule, configured to determine a risk value distribution curve corresponding to the target sample set based on a risk value corresponding to each sample object in the target sample set;
a sixth determining submodule, configured to determine areas under curves of risk value distribution curves corresponding to the plurality of sample sets respectively;
A seventh determining submodule, configured to determine a verification result according to differences between areas under curves corresponding to the plurality of sample sets respectively;
the preset condition comprises that the difference value is larger than a preset threshold value.
In some implementations of the first aspect, the predicting apparatus further includes:
And the second determining module is used for determining the initial risk level as the risk level of the target object under the condition that the initial risk level is smaller than the preset risk level.
In a second aspect, embodiments of the present application provide a computer storage medium having stored thereon computer program instructions which, when executed by a processor, perform the following method:
Acquiring the physiological index data of a target object, wherein the physiological index data comprises first index data and second index data;
Predicting a first risk value of the target physiological indication of the target object according to the first index data by using a first prediction model, and determining an initial risk level corresponding to the target object according to the first risk value;
Determining a second prediction model corresponding to the initial risk level under the condition that the initial risk level is greater than or equal to a preset risk level;
And predicting a second risk value of the target physiological indication of the target object according to the second indication data by using a second prediction model, and determining a risk level corresponding to the target object according to the second risk value.
According to the risk level prediction device and the computer storage medium, the first acquisition module is used for acquiring the physiological index data of the target object, wherein the physiological index data comprise the first index data and the second index data, the first prediction module is used for predicting and obtaining the initial risk level corresponding to the target object according to the first index data, the first determination module is used for determining the second prediction model corresponding to the initial risk level under the condition that the initial risk level is greater than or equal to the preset risk level, and the second prediction module is used for further predicting and obtaining the risk level corresponding to the target object according to the second index data. Therefore, not all target objects need to be predicted by the second prediction model, but whether the target objects need to be predicted again by the second prediction model is determined according to the initial risk level of the target objects, so that screening cost is reduced. In addition, the first prediction model predicts according to the first index data, and the second prediction model predicts according to the second index data, so that the risk level of the target object can be predicted more comprehensively, and the accuracy of a risk level prediction result is improved.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings that are needed to be used in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.
Fig. 1 is a schematic structural diagram of a risk level prediction apparatus according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of another risk level prediction apparatus according to an embodiment of the present application;
Fig. 3 is a schematic structural diagram of another risk level prediction apparatus according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail below with reference to the accompanying drawings and the detailed embodiments. It should be understood that the particular embodiments described herein are meant to be illustrative of the application only and not limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the application by showing examples of the application.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the medical field, in order to reduce the probability of a target object having a certain physiological sign as much as possible, a risk assessment is usually performed by using a prediction model, so as to determine the risk level of the target object, so as to perform an early intervention. For example, in recent years, the incidence rate of four kinds of chronic diseases mainly including coronary heart disease, cerebral apoplexy, chronic kidney disease and diabetes is high, and the number of patients is in a continuously rising state, which seriously threatens the health of people and causes a heavy economic burden.
For early intervention, a series of researches are carried out for a middle-long-term prediction model of the serious chronic diseases at home and abroad. Taking the aspect of cardiovascular and cerebrovascular diseases as an example, the existing SCORE model for predicting the death risk of ten-year cardiovascular diseases, QRISK cardiovascular disease risk SCOREs, WHO/ISH risk prediction graphs, a summarized queue formula PCE and the like all contribute to the risk assessment of cardiovascular and cerebrovascular diseases. However, most of the existing prediction models are established based on data of European and American populations, the population specificity is not strong, the method is not suitable for the Chinese population, and even if the prediction models suitable for the Chinese population exist, the age of the population queue adopted in the model development process is long. Therefore, it is necessary to build comprehensive screening tools for four broad categories of chronic diseases using newly built nationwide crowd queues to be more suitable for chronic disease risk prediction both currently and for a period of time in the future.
The previous researches on risk prediction models of the four chronic diseases show that the four chronic diseases such as age, hypertension, obesity, blood sugar rise and the like are common risk factors of the four chronic diseases. However, in view of the large number of disease occurrence of the four kinds of chronic diseases, the screening range for the four kinds of chronic diseases should be widely covered. However, when risk screening and risk level prediction are currently performed by using a risk level prediction model, due to the influence of factors such as limitation of screening scope, data sources, screening capability and the like, for example, insufficient configuration of medical staff of a basic medical and health institution, education level and capability to be improved, limited detection capability of the basic medical and health institution and the like, screening from multiple aspects related to physiological indications is generally required, and target objects are not distinguished, and each target object needs to be subjected to multiple screening and risk evaluation. Therefore, if each disease is screened separately, not only the screening cost is increased, but also the available information is limited, the accurate screening may not be performed, and the accuracy of the risk level prediction result is low.
In view of the above, there is no comprehensive screening tool suitable for people in China and aimed at four major chronic diseases.
In order to solve the problems in the prior art, the embodiment of the application provides a risk level prediction device and a computer storage medium. The following first describes a risk level prediction apparatus provided by an embodiment of the present application.
Fig. 1 shows a schematic structural diagram of a risk level prediction apparatus according to an embodiment of the present application. As shown in fig. 1, the risk level prediction apparatus 100 specifically includes the following modules:
A first obtaining module 101, configured to obtain physiological index data of a target object, where the physiological index data includes first index data and second index data;
The first prediction module 102 is configured to predict, according to the first index data, a first risk value of the target physiological indicator of the target object by using the first prediction model, and determine an initial risk level corresponding to the target object according to the first risk value;
A first determining module 103, configured to determine a second prediction model corresponding to the initial risk level if the initial risk level is greater than or equal to a preset risk level;
The second prediction module 104 is configured to predict, according to the second index data, a second risk value of the target physiological index of the target object according to the second index data, and determine a risk level corresponding to the target object according to the second risk value.
Thus, according to the risk level prediction device of the embodiment of the application, an initial risk level corresponding to a target object is predicted by using a first prediction model according to first index data based on a first prediction module, a second prediction model corresponding to the initial risk level is determined by using a first determination module when the initial risk level is greater than or equal to a preset risk level, and then the risk level corresponding to the target object is further predicted by using a second prediction model according to second index data based on a second prediction module. Therefore, not all target objects need to be predicted by the second prediction model, but whether the target objects need to be predicted again by the second prediction model is determined according to the initial risk level of the target objects, so that screening cost is reduced. In addition, the first prediction model predicts according to the first index data, and the second prediction model predicts according to the second index data, so that the risk level of the target object can be predicted more comprehensively, and the accuracy of a risk level prediction result is improved.
In some embodiments, the target object may be one or more, and the physiological index data may be used to characterize whether the target object is presenting with the target physiological indication. As an example, the target physiological indication is, for example, carotid atherosclerosis, and if the risk level of the target subject for developing carotid atherosclerosis is to be predicted by the prediction means 100, the first index data may include gender, age, body mass index, location type, smoking history, systolic pressure, diastolic pressure, blood glucose, total cholesterol, triglycerides, high density lipoprotein, location province, cardiovascular family history and family annual income, and the second index data may include, in addition to the first index data described above, physical activity, diet, whether carotid ultrasound has plaque, whether carotid intima is thickened or not. For example, the first obtaining module 101 may obtain the physiological index data in a query manner based on a data platform such as a web page. As shown in tables 1 and 2 below, the first index data and the second index data may be collected as follows:
table 1 first index data acquisition topic table
Table 2 second index data acquisition table
It should be noted that the second predictors in the second prediction model include the first predictors and the third predictors, and the first predictors are in the first prediction model, that is, the second prediction model is capable of making further predictions with respect to the first prediction model. While the first predictor in the first predictive model and the second predictor in the second predictive model correspond to the first index data and the second index data, the first predictor includes, illustratively, a female, an age, a body mass index, whether the locus is rural, whether smoking, systolic pressure, diastolic pressure, blood glucose, total cholesterol, triglycerides, high density lipoprotein, whether the locus province is north, a cardiovascular family history, and a household annual income greater than fifty thousand yuan, the second predictor includes the first predictor and a third predictor, wherein the third predictor includes: whether the physical activity of the target object reaches the standard, whether the diet is healthy, whether carotid plaque exists or not, and whether carotid intima is thickened or not.
As an example, the predictors are obtained by screening, under the condition of facing a data set containing a plurality of predictors, firstly, the numerical value corresponding to each predictor is standardized to enable each predictor to have a mean value zero and a unit variance, then, the plurality of predictors are screened by using a LASSO algorithm, and a punishment function is introduced on the basis of the LASSO algorithm, different predictor coefficients can be obtained when punishment parameters in the punishment function select different values, and when the punishment function is small enough, more and more predictor coefficients are compressed to be zero and then are eliminated.
And obtaining the average error of the prediction model under the corresponding penalty parameters and the area under the working curve by cross-validation for different penalty parameters, wherein when the average error is smaller or the area under the working curve is larger, the corresponding penalty parameters are optimal, and the prediction factors corresponding to the penalty parameters are reserved. On the basis, the prediction factors in the embodiment of the application are finally determined by further comprehensively considering the past research results and the clinical significance of the prediction factors.
Therefore, the prediction factors are all economic and simple prediction factors which are easily obtained by basic medical and health institutions of communities or villages and towns, community residents can be conveniently screened at the basic medical and health institutions, and four high-risk groups common to chronic diseases can be screened.
In some embodiments, the first prediction module 102 includes the following sub-modules:
The first determination submodule is used for determining the value of a first prediction factor in the first prediction model based on the physiological index data of the target object;
the first computing sub-module is used for computing a first probability of the occurrence of the target physiological indication of the target object according to the value of the first prediction factor by using the first prediction model to obtain a first risk value;
the second determining submodule is used for determining the risk level where the first risk value is located according to the risk value ranges corresponding to the preset risk levels respectively, and the risk level is used as an initial risk level corresponding to the target object.
As an example, in combination with table 1, the first determination submodule determines the value of the first predictor in the first prediction model based on the physiological index data of the target object acquired by the first acquisition module 101. For example, if the sex in the first index data of the target object is female, the value of the first predictor female is 1, and if the sex is male, the value of the first predictor is 0; if the location is rural, the value of the first prediction factor is 1, and if the location of the target object is urban, the value of the first prediction factor is 0; if the local province belongs to the north, the value of the first prediction factor is 1, and if the local province belongs to the south, the value of the first prediction factor is 0; and if the annual income of the family is more than fifty thousand yuan, the value of the first predictive factor is 1, and if the annual income of the family is less than fifty thousand yuan, the value of the first predictive factor is 0.
As an example, the first calculation submodule calculates a first probability of the target physiological indicator of the target object to appear according to the value of the first prediction factor by using the first prediction model, wherein the target physiological indicator is, for example, four major chronic diseases. Illustratively, the first predictive model is shown in equation (1) below:
The first calculating submodule calculates a first probability that the target object appears the target physiological indicator by using the formula (1) as a first risk value of the target object that the target object appears the physiological indicator event such as four major chronic diseases, so that the second determining submodule determines the initial risk level of the target object according to the first risk value.
As an example, the plurality of preset risk levels are, for example, a low risk level, a medium risk level, and a high risk level. For example, if the risk values are ranked, the risk value ranges are divided according to 16% and 24% as rank cut points, if the first risk value of the target object falls in a section smaller than 16%, the initial risk level of the target object is a low risk level; the first risk value of the target object falls in a section of more than 16% and less than 24%, and the initial risk level of the target object is a medium risk level; and if the first risk value of the target object falls in the interval of more than 24%, the initial risk level of the target object is a high-risk level.
Based on the risk, a first risk value of the target object is calculated through the first calculation submodule, and the risk level of the first risk value is determined through the second determination submodule according to the risk value ranges corresponding to the preset risk levels, so that the initial risk level of the target object is accurately determined. Therefore, the first step in the step-by-step design is realized, namely, the risk level of the target object is primarily divided based on the simple and easily-obtained predictive factors.
In some embodiments, as shown in fig. 2, the prediction apparatus 100 may further include the following modules:
a second obtaining module 201, configured to obtain coefficients of model predictors corresponding to a plurality of preset risk levels, respectively, before determining a second prediction model corresponding to the initial risk level;
the first adjustment module 202 is configured to adjust coefficients of predictors in the preset prediction model to coefficients of model predictors corresponding to each preset risk level, respectively, to obtain a second prediction model corresponding to each preset risk level.
As an example, the second prediction models used for the target object with different initial risk levels are different, and the different second prediction models are all converted based on the preset prediction models, and the same prediction factors are still used, but the coefficients of the prediction factors are not the same. Based on this, the coefficients of the predictors in the preset prediction model are adjusted based on the second acquisition module 201 and the first adjustment module 202 in the face of different initial risk levels of different target objects, so as to obtain second prediction models corresponding to the low-risk level, the medium-risk level and the high-risk level respectively, so that whether the target physiological indication occurs to the target object can be accurately predicted.
Illustratively, the second prediction model corresponding to the low risk level is shown in the following formula (2):
The second prediction model corresponding to the medium risk level is shown in the following formula (3):
illustratively, the second prediction model corresponding to the high risk level is shown in the following formula (4):
As an example, the predicted outcome of the first and second prediction models refers to the complex endpoint of four major classes of chronic diseases, i.e. the diagnosis of coronary heart disease, stroke, chronic kidney disease, diabetes during follow-up. Wherein coronary heart disease is defined as myocardial infarction, or is treated by coronary stent implantation, coronary bypass grafting, acute myocardial infarction thrombolysis and the like, cerebral apoplexy is defined as ischemia or hemorrhagic cerebral apoplexy, or is treated by cerebral apoplexy thrombolysis, chronic kidney disease comprises treatment by dialysis, diabetes comprises taking hypoglycemic agent, or blood sugar of a survey subject measured by fasting blood sugar is more than 7mmol/L, but the blood sugar does not reach the level before.
Therefore, under the condition that the prediction factors which are easily obtained by the basic medical institution are adopted, according to the initial risk level of the target object, the corresponding second prediction models are adopted to realize risk screening prediction, the relatively complex and more specific detection models are adopted to conduct accurate prediction, the method has better distinction degree and accuracy, the second step in the step-by-step design is also realized, namely, on the basis of the initial prediction, the more accurate prediction factors are utilized, the second prediction models corresponding to the initial risk level are adopted, and people with different risk levels are screened in a specific manner.
Based on the method, the screening prediction is performed in a targeted manner by utilizing a step-by-step design, and an applicable, convenient and efficient screening tool is provided for the base layer, so that the base layer requirement can be met, the cost benefit is considered, and the screening prediction cost is saved.
In some embodiments, the second prediction model 104 includes the following submodules:
The third determination submodule is used for determining the value of a second prediction factor in the second prediction model based on the physiological index data of the target object;
the second calculation sub-module is used for calculating a second probability of the occurrence of the target physiological indication of the target object according to the value of the second prediction factor by using the second prediction model to obtain a second risk value;
and the fourth determining submodule is used for determining the risk level where the second risk value is located according to the risk value ranges respectively corresponding to the plurality of preset risk levels as the risk level corresponding to the target object.
As an example, in combination with the tables 1 and 2, the third determination submodule determines the value of the second prediction factor in the second prediction model based on the physiological index data of the target object acquired by the first acquisition module 101. For example, if the physical activity of the target object in the second index data of the target object meets the standard, the value of the second prediction factor is 1, and if the physical activity does not meet the standard, the value of the second prediction factor is 0; if the diet of the target object in the second index data of the target object is healthy, the value of the second prediction factor is 1, and if the diet is unhealthy, the value of the second prediction factor is 0; if the target object has carotid plaque in the second index data of the target object, the value of the second predictive factor is 1, and if the target object does not have carotid plaque, the value of the second predictive factor is 0; and if the carotid intima of the target object is not thickened, the value of the second predictive factor is 0.
As an example, the second calculating submodule calculates a second probability that the target object appears as a second risk value of the target object that a physiological indication event such as four major chronic diseases occurs as the target object according to the initial risk level of the target object from the above-mentioned formulas (2), (3) and (4) by selecting a second prediction model corresponding to the initial risk level, so that the fourth determining submodule determines the risk level of the target object according to the second risk value.
As an example, as shown in table 3 below, by calculating the reclassification ratio of the first prediction model and the second prediction model, it is determined that in the case where the initial risk level is greater than or equal to the preset risk level, for example, the preset risk level is a medium risk level, the risk prediction is performed by using the second prediction model, so as to reduce the number of times of re-performing the risk prediction.
Table 3 reclassifying schematic table
Illustratively, as shown in connection with Table 3, in the target objects classified into low risk levels in the first predictive model, 81% are still predicted as low risk levels in the second predictive model, while about 19% are reclassified into medium risk levels; of the target objects classified into medium risk levels in the first predictive model, only 71% remain predicted as medium risk levels in the second predictive model, while about 7% are reclassified into low risk levels and about 22% are reclassified into high risk levels; of the target objects classified into high risk levels in the first predictive model, about 92% remain predicted as high risk levels in the second predictive model, while about 8% are reclassified into medium risk levels. That is, the relative risk of the target object with the initial risk level being the low-risk level is not high, and the secondary risk prediction is not needed to be performed by using the second prediction model, but the specific situation is determined according to the screening prediction requirement of the target object.
In some embodiments, the prediction apparatus 100 may further include:
And the second determining module is used for determining the initial risk level as the risk level of the target object under the condition that the initial risk level is smaller than the preset risk level.
As an example, if the initial risk level of the target object is a low-risk level, and the actual demand of the target object is combined, the second-step risk prediction may be performed without using the second prediction model, that is, the initial risk level predicted by the first prediction model is used as the final risk level, so that the screening prediction cost may also be saved.
For example, if there are multiple target objects, after determining the initial risk level of each target object, the multiple target objects are divided into three groups of low risk level, medium risk level and high risk level according to the initial risk level of each target object, and then for the group of medium risk levels, new prediction factors are supplemented, and more accurate prediction is performed by using a second prediction model corresponding to the medium risk level. If the low-risk level and the high-risk level are also conditional and willing to further conduct accurate risk prediction, the embodiment of the application also provides a second prediction model corresponding to the low-risk level and the high-risk level respectively.
And the first prediction module is used for preliminarily determining the risk level of the target object, and determining whether secondary risk prediction is carried out or not according to the initial risk level of the target object. Specifically, under the condition that the initial risk level is greater than or equal to the preset risk level, accurate prediction is further carried out by utilizing the corresponding second prediction model, so that the screening cost is greatly saved, the screening efficiency is effectively improved, and the accuracy of risk level prediction is further improved.
In some embodiments, as shown in fig. 3, the prediction apparatus 100 may further include the following modules:
The verification module 301 is configured to verify the first prediction model and the second prediction model to obtain a verification result;
And a second adjustment module 302, configured to adjust the coefficient of the first predictor in the first prediction model and the coefficient of the second predictor in the second prediction model when the first prediction model and the second prediction model are determined to satisfy the preset condition according to the verification result.
As an example, the verification module 301 verifies the first prediction model and the second prediction model by using a bootstrap method, and establishes a new data sample based on the replaced random sample to verify, so that the second adjustment module 302 adjusts the coefficient of the first prediction factor in the first prediction model and the coefficient of the second prediction factor in the second prediction model when determining that the first prediction model and the second prediction model meet the preset condition according to the verification result, thereby ensuring the stability and the accuracy of the first prediction model and the second prediction model.
In some embodiments, the verification module 301 includes the following sub-modules:
The acquisition sub-module is used for acquiring a plurality of sample sets, wherein the sample sets comprise a plurality of sample objects and corresponding physiological index data samples thereof;
the prediction sub-module is used for respectively predicting a risk value of each sample object in the plurality of sample sets for generating a target physiological indication according to the physiological index data samples by using the first prediction model and the second prediction model;
A fifth determining submodule, configured to determine a risk value distribution curve corresponding to the target sample set based on a risk value corresponding to each sample object in the target sample set;
a sixth determining submodule, configured to determine areas under curves of risk value distribution curves corresponding to the plurality of sample sets respectively;
A seventh determining submodule, configured to determine a verification result according to differences between areas under curves corresponding to the plurality of sample sets respectively;
the preset condition comprises that the difference value is larger than a preset threshold value.
As an example, the obtaining submodule obtains a plurality of sample objects and corresponding physiological index data samples thereof, and it should be noted that the number of sample objects should be the same as the number of target objects, and physiological index data contained in the physiological index data samples is the same as the index in the physiological index data of the target objects, except that the source objects of the index data are different. And respectively predicting the risk value of the target physiological indication of each sample object in the plurality of sample sets based on the same first prediction model and second prediction model to determine a corresponding risk value distribution curve according to the risk value, and then judging whether the difference value of the risk value distribution curves respectively corresponding to the plurality of sample sets is larger than a preset threshold value or not to adjust and adjust the coefficient of the first prediction factor in the first prediction model and the coefficient of the second prediction factor in the second prediction model, wherein the preset threshold value can be taken according to actual conditions.
As an example, as shown in table 4, the verification result includes the area under the curve of the risk partition curve of the corresponding outputs of the first prediction model and the second prediction model, that is, the area under the ROC curve, that is, the AUC value, the index such as the mean value, the median, the 5 th and 95 th percentiles of the parameters such as the calibration degree chi-square, the calibration degree slope, and the like, so as to display the stability of the first prediction factor and the second prediction factor and the coefficients thereof in the first prediction model and the second prediction model.
TABLE 4 schematic representation of model performance results
As an example, the same stepwise predictive model is used for different target objects, and the change in the difference in predictive probabilities between the first predictive model and the second predictive model is reflected by calculating a net reclassification index (Net Reclassification Index, NRI) and a comprehensive discrimination improvement index (INTEGRATED DISCRIMINATION IMPROVEMENT, IDI) under different risk level cut-off points, the number of target objects, and target objects of different sexes, as shown in table 5 below.
TABLE 5 schematic table of model performance results under different factors
The prediction device according to the embodiment of the application is a step-by-step prediction device constructed by a step-by-step method according to the first prediction model and the second prediction model, and can correspondingly develop a web page version prediction model, the target object inputs basic information and related detection results to preliminarily evaluate the disease risk values of four major chronic diseases of the target object, and preliminarily judge the initial risk level of the target object, so as to determine whether the target object belongs to a low-risk, medium-risk or high-risk group, so as to give evaluation suggestions.
In summary, the prediction device provided by the embodiment of the application is suitable for the comprehensive risk prediction screening tool for four major chronic diseases of basic medical and health institutions, the step-by-step design can save the crowd screening cost, is suitable for the current situation of China, has better differentiation degree and accuracy, is beneficial to effectively screening out high-risk crowds of the four major chronic diseases based on limited resources, and is used for early intervention and reducing the occurrence risk of the four major chronic diseases.
According to the risk level prediction device provided by the embodiment of the application, based on simple and easily acquired index data, the first prediction module is used for carrying out preliminary risk prediction on the target object to obtain the initial risk level of the target object, the initial risk level is divided into low, medium and high risk levels, the second prediction module is used for further screening, and compared with the first prediction model, the index with more representative and technical content is incorporated, and finally the risk level of the target object is obtained. Based on the method, the screening cost is reduced, screening prediction is not limited by the available information, the risk level can be predicted more conveniently and efficiently, and the accuracy of risk level prediction can be improved on the basis of step-by-step prediction.
It should be noted that, the application scenario described in the foregoing embodiment of the present application is for more clearly describing the technical solution of the embodiment of the present application, and does not constitute limitation of the technical solution provided by the embodiment of the present application. As known to those skilled in the art, with the appearance of new application scenarios, the technical solution provided by the embodiment of the present application is applicable to similar technical problems.
In addition, embodiments of the present application provide a computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement the method of:
Acquiring the physiological index data of a target object, wherein the physiological index data comprises first index data and second index data;
Predicting a first risk value of the target physiological indication of the target object according to the first index data by using a first prediction model, and determining an initial risk level corresponding to the target object according to the first risk value;
Determining a second prediction model corresponding to the initial risk level under the condition that the initial risk level is greater than or equal to a preset risk level;
And predicting a second risk value of the target physiological indication of the target object according to the second indication data by using a second prediction model, and determining a risk level corresponding to the target object according to the second risk value.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. The present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the foregoing, only the specific embodiments of the present application are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present application is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present application, and they should be included in the scope of the present application.
Claims (7)
1. A risk level prediction apparatus, comprising:
the first acquisition module is used for acquiring the physiological index data of the target object, wherein the physiological index data comprise first index data and second index data, and the second index data comprise the first index data;
The first prediction module is used for determining the value of a first prediction factor in the first prediction model based on the physiological index data of the target object; predicting a first risk value of the target physiological indication of the target object according to the value of the first prediction factor by using the first prediction model, and determining an initial risk level corresponding to the target object according to the first risk value;
The first determining module is used for determining a second prediction model corresponding to the initial risk level under the condition that the initial risk level is greater than or equal to a preset risk level, and the preset risk level is determined by calculating the reclassification proportion of the first prediction model and the second prediction model; determining a value of a second prediction factor in the second prediction model based on the physiological index data of the target object;
The second prediction module is used for predicting a second risk value of the target physiological indicator of the target object according to the value of the second prediction factor by using the second prediction model, and determining a risk level corresponding to the target object according to the second risk value; wherein the second predictor includes a first predictor and a third predictor, the first predictor corresponding to the first index data and the second predictor corresponding to the second index data;
the second obtaining module is used for obtaining coefficients of model predictors respectively corresponding to a plurality of initial risk levels before determining a second prediction model corresponding to the initial risk level;
The first adjusting module is used for respectively adjusting the coefficients of the prediction factors in the preset prediction model to the coefficients of the model prediction factors corresponding to each initial risk level to obtain a second prediction model corresponding to each initial risk level;
wherein the first predictor, the second predictor, and the third predictor are determined according to penalty parameters in penalty functions corresponding to predictors in a dataset comprising a plurality of predictors.
2. The apparatus of claim 1, wherein the first prediction module comprises:
The first calculation sub-module is used for calculating a first probability of the target object appearing the target physiological indication according to the value of the first prediction factor by using the first prediction model to obtain the first risk value;
The first determining submodule is used for determining the risk level where the first risk value is located according to the risk value ranges corresponding to the preset risk levels respectively, and the risk level is used as the initial risk level corresponding to the target object.
3. The apparatus of claim 2, wherein the second prediction module comprises:
the second calculation sub-module is used for calculating a second probability of the target object appearing the target physiological indication according to the value of the second prediction factor by using the second prediction model to obtain the second risk value;
And the second determining submodule is used for determining the risk level where the second risk value is located according to the risk value ranges respectively corresponding to the preset risk levels as the risk level corresponding to the target object.
4. The apparatus of claim 1, wherein the predicting means further comprises:
The verification module is used for verifying the first prediction model and the second prediction model to obtain a verification result;
and the second adjusting module is used for adjusting the coefficient of the first prediction factor in the first prediction model and the coefficient of the second prediction factor in the second prediction model under the condition that the first prediction model and the second prediction model meet the preset condition according to the verification result.
5. The apparatus of claim 4, wherein the verification module comprises:
The acquisition sub-module is used for acquiring a plurality of sample sets, wherein the sample sets comprise a plurality of sample objects and corresponding physiological index data samples thereof;
the prediction submodule is used for respectively predicting a risk value of each sample object in the plurality of sample sets for generating a target physiological indication according to the physiological index data samples by using the first prediction model and the second prediction model;
a third determining submodule, configured to determine a risk value distribution curve corresponding to a target sample set based on a risk value corresponding to each sample object in the target sample set;
a fourth determining submodule, configured to determine areas under curves of risk value distribution curves corresponding to the plurality of sample sets respectively;
a fifth determining submodule, configured to determine the verification result according to differences between areas under curves corresponding to the plurality of sample sets respectively;
Wherein the preset condition includes the difference being greater than a preset threshold.
6. The apparatus of claim 1, wherein the predicting means further comprises:
And the second determining module is used for determining the initial risk level as the risk level of the target object under the condition that the initial risk level is smaller than the preset risk level.
7. A computer readable storage medium having stored thereon computer program instructions which when executed by a processor perform the method of:
Acquiring physiological index data of a target object, wherein the physiological index data comprises first index data and second index data, and the second index data comprises the first index data;
Determining a value of a first prediction factor in a first prediction model based on the physiological index data of the target object; predicting a first risk value of the target physiological indication of the target object according to the value of the first prediction factor by using the first prediction model, and determining an initial risk level corresponding to the target object according to the first risk value;
Determining a second prediction model corresponding to the initial risk level when the initial risk level is greater than or equal to a preset risk level, wherein the preset risk level is determined by calculating the reclassification proportion of the first prediction model and the second prediction model; determining a value of a second prediction factor in the second prediction model based on the physiological index data of the target object;
Predicting a second risk value of the target physiological indicator of the target object according to the value of the second prediction factor by using the second prediction model, and determining a risk level corresponding to the target object according to the second risk value; wherein the second predictor includes a first predictor and a third predictor, the first predictor corresponding to the first index data and the second predictor corresponding to the second index data;
before determining a second prediction model corresponding to the initial risk level, acquiring coefficients of model predictors corresponding to a plurality of initial risk levels respectively;
Respectively adjusting the coefficients of the prediction factors in the preset prediction model to the coefficients of the model prediction factors corresponding to each initial risk level to obtain a second prediction model corresponding to each initial risk level;
wherein the first predictor, the second predictor, and the third predictor are determined according to penalty parameters in penalty functions corresponding to predictors in a dataset comprising a plurality of predictors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310667536.8A CN116386879B (en) | 2023-06-07 | 2023-06-07 | Risk level prediction device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310667536.8A CN116386879B (en) | 2023-06-07 | 2023-06-07 | Risk level prediction device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116386879A CN116386879A (en) | 2023-07-04 |
| CN116386879B true CN116386879B (en) | 2024-04-19 |
Family
ID=86979184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310667536.8A Active CN116386879B (en) | 2023-06-07 | 2023-06-07 | Risk level prediction device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116386879B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技（深圳）有限公司 | Risk prediction processing method and apparatus, computer device and medium |
| CN113658704A (en) * | 2021-09-17 | 2021-11-16 | 平安国际智慧城市科技股份有限公司 | Diabetes risk prediction device, apparatus and storage medium |
| CN114121270A (en) * | 2020-08-28 | 2022-03-01 | 华为技术有限公司 | Disease risk grade prediction method and device |
| CN114300141A (en) * | 2021-12-29 | 2022-04-08 | 天津开心生活科技有限公司 | Disease risk grade prediction method and device, readable storage medium and electronic equipment |
| CN114628033A (en) * | 2022-02-22 | 2022-06-14 | 湖南新云网科技有限公司 | Disease risk prediction method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859847A (en) * | 2019-02-15 | 2019-06-07 | 京东方科技集团股份有限公司 | Electronic equipment, Weight management earnings forecast device and storage medium |
-
2023
- 2023-06-07 CN CN202310667536.8A patent/CN116386879B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020037942A1 (en) * | 2018-08-20 | 2020-02-27 | 平安科技（深圳）有限公司 | Risk prediction processing method and apparatus, computer device and medium |
| CN114121270A (en) * | 2020-08-28 | 2022-03-01 | 华为技术有限公司 | Disease risk grade prediction method and device |
| CN113658704A (en) * | 2021-09-17 | 2021-11-16 | 平安国际智慧城市科技股份有限公司 | Diabetes risk prediction device, apparatus and storage medium |
| CN114300141A (en) * | 2021-12-29 | 2022-04-08 | 天津开心生活科技有限公司 | Disease risk grade prediction method and device, readable storage medium and electronic equipment |
| CN114628033A (en) * | 2022-02-22 | 2022-06-14 | 湖南新云网科技有限公司 | Disease risk prediction method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张雨萌.《医疗服务资源调度优化及应用 基于供需匹配视角》.成都：四川大学出版社,2022,45-46页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116386879A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Application of machine learning techniques for clinical predictive modeling: a cross-sectional study on nonalcoholic fatty liver disease in China | |
| CN111292853B (en) | Multi-parameter-based cardiovascular disease risk prediction network model and construction method thereof | |
| CN112633601B (en) | Method, device, equipment and computer medium for predicting disease event occurrence probability | |
| CN110634563A (en) | Differential diagnosis device for diabetic nephropathy and non-diabetic nephropathy | |
| CN114724716A (en) | Method, model training and apparatus for risk prediction of progression to type 2 diabetes | |
| López‐Ratón et al. | Confidence intervals for the symmetry point: An optimal cutpoint in continuous diagnostic tests | |
| CN116386879B (en) | Risk level prediction device and computer storage medium | |
| CN113113143A (en) | Myocardial infarction risk degree evaluation system considering delayed enhancement nuclear magnetic image | |
| CN110414562B (en) | X-ray film classification method, device, terminal and storage medium | |
| Abd-Elsalam et al. | Early diagnosis of esophageal varices using Boosted-Naïve Bayes Tree: A multicenter cross-sectional study on chronic hepatitis C patients | |
| CN115602319B (en) | Noninvasive hepatic fibrosis assessment device | |
| JP2023087100A (en) | Systems and methods for improving disease diagnosis using measured analytes | |
| CN116703880A (en) | Immune state prediction model construction method, prediction method and construction device | |
| CN114649094B (en) | Breast cancer multi-parameter clinical decision auxiliary device based on nuclear magnetic resonance | |
| CN108346471B (en) | Pathological data analysis method and device | |
| CN115116615A (en) | Method and system for analyzing and predicting risk of non-alcoholic fatty liver disease | |
| Nordin et al. | Determination of the obesity prevalence and its associated factors among community in Selangor, Malaysia: an ordinal logistic regression approach | |
| CN112259231A (en) | High-risk gastrointestinal stromal tumor patient postoperative recurrence risk assessment method and system | |
| Setyawati et al. | Feature selection for the classification of clinical data of stroke patients | |
| CN114612255B (en) | Insurance pricing method based on electronic medical record data feature selection | |
| RU2782359C2 (en) | Systems and methods for improvement of diagnostics of diseases, using measured analytes | |
| Priya et al. | Prediction of Arterial Stiffness Risk in Diabetes Patients through Deep Learning Techniques. | |
| Badvath et al. | ONBLR: An effective optimized ensemble ML approach for classifying liver cirrhosis disease | |
| Rao et al. | Stroke Risk Assessment Decision-Making Using a Machine Learning Model: Logistic-AdaBoost. | |
| Sande | Statistical Inference for Decision Curve Analysis and Decision Threshold for Statistical Learning in Medical Research |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |