CN114628033A - Disease risk prediction method, device, equipment and storage medium - Google Patents
Disease risk prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114628033A CN114628033A CN202210161426.XA CN202210161426A CN114628033A CN 114628033 A CN114628033 A CN 114628033A CN 202210161426 A CN202210161426 A CN 202210161426A CN 114628033 A CN114628033 A CN 114628033A
- Authority
- CN
- China
- Prior art keywords
- risk
- risk factor
- data
- preset
- group
- 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
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
- G16H50/30—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
Abstract
After user data of a target user are obtained, risk factor data related to a preset disease in the user data are divided into N judgment standard group data according to preset associated conditions; predicting the risk factor data in each judgment standard group according to a preset risk factor assignment rule and a weight coefficient to obtain the risk probability of each judgment standard group; and comprehensively analyzing to obtain the risk probability of the preset diseases of the user according to the risk probability of each judgment standard group data. The risk probability that the user suffers from the preset disease is obtained by performing grouping prediction on the risk factor data of the user and then performing comprehensive prediction on the prediction results of the risk factor data of different groups, so that the risk probability that the user suffers from the preset disease is accurately predicted.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to a disease risk prediction method, apparatus, device, and storage medium.
Background
In recent years, under the influence of environmental pollution and life style change, together with the general lack of understanding of residents on risk factors influencing health, the health condition of residents in China is not optimistic, the proportion of chronic disease groups is increased year by year, chronic diseases are a large group of multifactorial diseases influenced by environmental factors and genetic factors, and are the results generated by the comprehensive action of various risk factors.
Because the chronic disease has hidden onset, long incubation period and fast disease progression, and many patients are difficult to find and treat in time, the risk of the disease needs to be predicted.
Disclosure of Invention
The embodiment of the application provides a disease risk prediction method, a disease risk prediction device, equipment and a storage medium, and accuracy of disease risk prediction is improved.
In a first aspect, an embodiment of the present application provides a disease risk prediction method, including:
acquiring user data of a user, wherein the user data comprises at least one of physiological characteristic data, behavior habit data and eating habit data;
grouping the user data to obtain N judgment standard group data, wherein the judgment standard group data comprise a plurality of first risk factor data, the first risk factor data are first risk factor data which are associated with a preset disease in the user data meeting preset associated conditions, and N is a positive integer;
processing the first risk factor data according to a preset assignment rule and a preset weight coefficient of a first risk factor aiming at each judgment standard group data to obtain a first risk probability of the judgment standard group data;
and predicting the risk probability of the user suffering from the preset disease according to the N first risk probabilities.
In a second aspect, an embodiment of the present application provides a disease risk prediction apparatus, including:
the acquisition module is used for acquiring user data of a user, wherein the user data comprises at least one of physiological characteristic data, behavior habit data and eating habit data;
the grouping module is used for grouping the user data to obtain N judgment standard group data, wherein the judgment standard group data comprise a plurality of first risk factor data, the plurality of first risk factor data are first risk factor data which are associated with a preset disease in the user data and meet preset associated conditions, and N is a positive integer;
the processing module is used for processing the first risk factor data according to a preset assignment rule and a preset weight coefficient of a first risk factor aiming at each judgment standard group data to obtain a first risk probability of the judgment standard group data;
and the prediction module is used for predicting the risk probability of the user suffering from the preset disease according to the N first risk probabilities.
In a third aspect, an embodiment of the present application provides an electronic device, where the device includes: a processor and a memory storing computer program instructions;
the processor when executing the computer program instructions implements a disease risk prediction method as shown in the first aspect,
in a fourth aspect, the present application provides a readable storage medium, on which computer program instructions are stored, and when executed by a processor, the computer program instructions implement the disease risk prediction method according to the first aspect.
According to the disease risk prediction method provided by the embodiment of the application, after the user data of the target user are obtained, risk factor data related to a preset disease in the user data are divided into N judgment standard group data according to preset associated conditions; predicting the risk factor data in each judgment standard group according to a preset risk factor assignment rule and a weight coefficient to obtain the risk probability of each judgment standard group; and comprehensively analyzing to obtain the risk probability of the preset diseases of the user according to the risk probability of each group of the judgment standard data. The risk probability that the user suffers from the preset disease is obtained by performing grouping prediction on the risk factor data of the user and then performing comprehensive prediction on the prediction results of the risk factor data of different groups, so that the risk probability that the user suffers from the preset disease is accurately predicted.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a disease risk prediction method provided in an embodiment of the present application;
FIG. 2 is another schematic flow chart of a disease risk prediction method provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a disease risk prediction apparatus provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
Features of various aspects and exemplary embodiments of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be 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 present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be 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. Also, 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 identical elements in a process, method, article, or apparatus that comprises the element.
In recent years, under the influence of environmental pollution and life style change, together with the general lack of understanding of residents on risk factors influencing health, the health condition of residents in China is not optimistic, the proportion of people with chronic diseases is increased year by year, the proportion of people in sub-health state is more than 70% of the total number of people, and the sub-health state is a physiological function imbalance state between health and diseases of human bodies. It is often manifested as fatigue, weakness, dizziness, headache, palpitation, chest distress, sleep disorder, and energy deficiency. When the physiological function imbalance of the human body continues to a certain critical point, the tissues and organs of the human body are pathologically changed and even develop organic damage, the corresponding diseases already occur, and the good opportunity for treating the diseases is missed. If the health information of residents can be regularly collected for evaluation and risk early warning, the factors influencing health are manually intervened, the residents pay attention to the health condition of the residents, necessary measures are taken to improve the living environment and change the life style, and the physiological functions of most of the sub-health state crowds can be recovered to be normal or chronic diseases can be delayed.
Most of the existing health prediction technologies adopt questionnaire survey to complete the collection of risk factors, physiological detection data are not collected in real time, subjective judgment is relied on, quantitative detection data support is lacked, actual physical conditions cannot be objectively reflected, and actual prediction effects are influenced. Secondly, the existing computer evaluation system cannot flexibly configure and adjust various disease risk models, and influences evaluation effect and working efficiency. Finally, the existing disease risk prediction method is to directly perform comprehensive analysis on all risk factors, set the same or fixed weight coefficients for the disease risk factors, and cannot truly reflect the influence degree of various risk factors on the disease risk in different groups, so that the disease risk prediction lacks objectivity and influences the accuracy of the prediction result.
Some of the terms referred to in this application are explained below:
the COX regression model, also known as proportional hazards regression model (COX), is a semi-parametric model, and, as the name suggests, is a regression method between parametric and non-parametric. The baseline function is not limited, and the influence of the prediction factors on the body health is estimated by only utilizing the partial likelihood function, so that the advantages of a parametric model and a non-parametric model are integrated, and the method is a multi-factor survival analysis method. The method can analyze the data with deleted survival time, can analyze the influence of a plurality of factors on the survival time, and does not require to estimate the distribution type of the survival function of the data.
In order to solve the problems of the prior art, embodiments of the present application provide a disease risk prediction method, apparatus, device, and storage medium. The method for predicting the risk of a disease provided in the embodiments of the present application will be described first.
Fig. 1 shows a schematic flow chart of a disease risk prediction method provided in an embodiment of the present application. As shown in fig. 1, the method includes steps 101 to 102:
In step 101, user data of a user is acquired. Wherein the user data comprises physiological characteristic data and at least one of behavior habit data and eating habit data. The physiological characteristic data may include: blood pressure, heart rate, blood lipid, blood glucose and other physiological index data.
In some embodiments, the physiological characteristic data may be collected by the health detection device, automatically uploaded, and stored in the health index database. The behavior habit data and the eating habit data can be displayed on a display screen of the equipment through setting questionnaires, and data such as living and exercise habits of individuals are collected through selecting questionnaire options and are automatically uploaded to a health questionnaire database through a network.
And 102, grouping the user data to obtain N judgment standard group data.
In step 102, grouping the user data to obtain N sets of decision criteria data. The judgment standard group data comprises a plurality of first risk factor data, the first risk factor data are first risk factor data which are associated with a preset disease in user data meeting preset associated conditions, and N is a positive integer.
Wherein the first risk factors associated with the preset diseases can quantify the disease risk factors affecting the preset diseases by referring to epidemiological statistics of the preset diseases, and collect a first risk factor set associated with the occurrence of the preset diseases.
Specifically, the acquired user data is grouped, first risk factor data associated with a preset disease in the user data is grouped into the same judgment standard group according to a preset associated condition, and N judgment standard group data are obtained. A set of decision criteria can be considered as a decision condition for disease risk prediction.
In some embodiments, the predetermined associated condition may be risk factors with similar attributes, that is, the predetermined associated condition may be a risk factor with similar attributes (e.g., risk factors with similar attributes such as body constitution, blood lipid, waist circumference) classified into a same decision criterion group with reference to clinical data of the predetermined disease, as a decision group for disease risk prediction, such as: judgment criteria A group and judgment criteria B group.
And 103, processing the first risk factor data according to the preset assignment rule and the preset weight coefficient of the first risk factor aiming at each judgment standard group data to obtain a first risk probability of the judgment standard group data.
Wherein, preset assignment rule can be set according to clinical experience and medical data according to actual conditions, for example: for the age data, the preset assignment rule can be set to a score of 1 below 50 years old; the definite score above age 50 was 2. The predetermined weighting factor may be determined by statistical analysis of historical data in epidemiological statistics of the predetermined disease, or may be set based on clinical experience.
In some embodiments, the risk probability value may be calculated by equation (2) according to a preset assignment rule and a weight coefficient (or a preset weight coefficient) of the first risk factor;
wherein Y is the risk probability, K is the number of first risk factors, XiIs the score, beta, of the first risk factor dataiα is an error value, which is a weight coefficient of the first risk factor.
The first risk probability of the determination criterion group data can be obtained by using the above formula (1) with the determination criterion group data including a plurality of first risk factor data.
And step 104, predicting the risk probability of the user suffering from the preset disease according to the N first risk probabilities.
Specifically, the risk probability of the user suffering from the preset disease is obtained through comprehensive analysis according to the risk probability of each judgment standard group data.
According to the disease risk prediction method provided by the embodiment of the application, after the user data of the target user are obtained, risk factor data related to a preset disease in the user data are divided into N judgment standard group data according to preset associated conditions; then, predicting the risk factor data in each judgment standard group according to a preset risk factor assignment rule and a preset weight coefficient to obtain the risk probability of each judgment standard group; and comprehensively analyzing to obtain the risk probability of the preset diseases of the user according to the risk probability of each judgment standard group data. The risk probability that the user suffers from the preset disease is obtained by performing grouping prediction on the risk factor data of the user and then performing comprehensive prediction on the prediction results of the risk factor data of different groups, so that the risk probability that the user suffers from the preset disease is accurately predicted.
In some embodiments, as shown in fig. 2, before S102, in order to determine the grouping criteria of the N decision criteria groups and the preset assignment rule and the preset weight coefficient of the first risk factor in each decision criteria group, the following S201 to S205 may further be included:
s201, determining first risk factors associated with the preset disease and sample data corresponding to each first risk factor according to epidemiological statistics of the preset disease;
s202, dividing the first risk factors into a plurality of first risk factor groups according to the types of the first risk factors;
s203, analyzing the sample data of each first risk factor group through a COX multi-factor regression model to obtain an assignment rule and a weight coefficient of each first risk factor;
s204, obtaining a second risk probability of the sample data in the first risk factor group according to the assignment rule and the weight coefficient of the first risk factor in the first risk factor group;
s205, adjusting the plurality of first risk factor groups according to the fitting degree of the second risk probability curve of the first risk factor group and the actual occurrence probability curve of the preset disease to obtain N judgment standard groups and the assignment rule and the weight coefficient of the first risk factor in each judgment standard group.
The N determination standard groups obtained in this embodiment and the assignment rule and the weight coefficient of the first risk factor in each determination standard group are the preset assignment rule and the preset weight coefficient in step 103.
In this embodiment, a method for grouping standard decision rules is designed, the first risk factors meeting preset associated conditions are grouped into the same decision standard group, and the decision standard groups can be flexibly combined according to the similarity between the disease risk probability under each decision standard group and the actual disease occurrence probability (i.e., the fitting degree between the second risk probability curve and the actual disease occurrence probability curve), so as to obtain the assignment rules and the weight coefficients of the first risk factors in the N decision standard groups and each decision standard group, so as to improve the accuracy of the prediction result. In the embodiment of the present application, preset associated conditions of a plurality of first risk factors in N determination criterion groups required for predicting a preset disease may be determined.
In S201, first risk factors associated with a preset disease and sample data corresponding to each first risk factor are determined according to epidemiological statistics of the preset disease.
Specifically, the epidemiological statistics of the preset disease are obtained, which may include clinical medical data, clinical trial data, and the like of the preset disease. For example: medical and health work records (medical records, medical examination records, birth death reports, etc.), health examination records, thematic survey or experimental research data, etc. After statistical analysis is performed on the acquired epidemiological statistical data of the preset disease, according to statistical data or clinical experience, determining risk factors affecting the probability of the preset disease as first risk factors, namely determining factors highly related to the occurrence probability of the preset disease as the first risk factors, wherein data corresponding to the risk factors are sample data.
In some embodiments, determining the first risk factors associated with the predetermined disease and the sample data corresponding to each first risk factor according to epidemiological statistics of the predetermined disease may include:
determining initial risk factors associated with the preset diseases and sample data corresponding to each initial risk factor according to epidemiological statistics of the preset diseases;
and analyzing the data of each initial risk factor through a COX single-factor regression model, determining the initial risk factors with the significance smaller than a second preset threshold value as first risk factors associated with the preset disease, and obtaining the first risk factors associated with the preset disease and sample data corresponding to each first risk factor.
Specifically, after performing a preliminary statistical analysis on epidemiological statistics of the preset disease, initial risk factors affecting the preset disease prevalence probability and corresponding initial sample data may be determined. For the obtained initial risk factors, there may be risk factors which have a smaller influence on the preset disease risk or are irrelevant, so in order to improve the accuracy of prediction, the initial sample data corresponding to the initial risk factors may be analyzed through a COX single-factor regression model, and the first risk factors significantly related to the preset disease risk are screened out, that is, for the initial sample data corresponding to each initial risk factor, the COX single-factor regression model is used for analyzing, and the initial risk factors with the significance smaller than a second preset threshold are determined as the first risk factors related to the preset disease.
In the embodiment of the application, the initial risk factors of the preset diseases are screened, so that the risk factors which are not obviously related to the preset diseases can be eliminated, and the prediction accuracy is further improved.
In S202, the first risk factors are classified into a plurality of first risk factor groups according to the type of the first risk factors.
In this embodiment, the risk factors with similar attributes can be classified into the same first risk factor group by referring to the clinical data of the predetermined disease, for example: risk factors with similar attributes such as physique, blood fat, waist circumference and the like are listed as a group.
In S203, the sample data of each first risk factor group is analyzed through the COX multi-factor regression model, so as to obtain an assignment rule and a weight coefficient of each first risk factor.
Specifically, sample data corresponding to each group of first risk factor groups is analyzed through a COX multi-factor regression model, first, the sample data corresponding to each first risk factor is assigned according to a preset assignment rule (for example, for age data in the sample data, the score of the sample data below 50 years old is determined to be 1, and the score of the sample data above 50 years old is determined to be 2), the assigned sample data is processed through the COX multi-factor regression model, the relative risk value of each first risk factor can be obtained, and the weight coefficient of the first risk factor can be determined through the relative risk value.
Wherein the relative risk value reflects the degree of influence of the independent variable on the outcome of the positive, and is indicative of the effect of exposure on the occurrence of the positive event relative to the control. Can be expressed visually as a multiple or ratio of the effect. Thus, the weight coefficient of the independent variable, i.e. the weight coefficient of the first risk factor of the present application, can be determined by the relative risk value.
In some embodiments, the weighting factor β for the first risk factor may be calculated by equation (2).
HR＝exp(β) (2)
Where HR is the relative risk value and β is the weighting factor.
In S204, a second risk probability of the sample data in the first risk factor group is obtained according to the assignment rule and the weight coefficient of the first risk factor in the first risk factor group.
Specifically, the risk probability value of each first risk factor group may be calculated based on the assignment rule and the weight coefficient of each first risk factor in each first risk factor group determined in S203. Namely, the sample data is assigned according to a preset assignment rule to obtain a score (i.e., an independent variable) of the sample data of each first risk factor, and a risk probability value (i.e., a second risk probability) of the data corresponding to each first risk factor group can be calculated according to the score and the weight coefficient of the data corresponding to the first risk factor in each first risk factor group.
In some embodiments, the second risk probability value may be calculated according to the preset assignment rule and the weight coefficient (or the preset weight coefficient) of the first risk factor by the above equation (1).
S205, adjusting the plurality of first risk factor groups according to the fitting degree of the second risk probability curve of the first risk factor group and the actual occurrence probability curve of the preset disease to obtain N judgment standard groups and the assignment rule and the weight coefficient of the first risk factor in each judgment standard group.
Specifically, a predicted risk probability curve (i.e., a second risk probability curve) of the sample data in the first risk factor group is obtained according to the second risk probability of the sample data in the first risk factor group obtained in S204; then according to the real data of the sample data, carrying out statistical analysis to obtain an actual occurrence probability curve of a preset disease; determining the similarity between the predicted risk probability curve and the actual occurrence probability curve according to the fitting goodness of the predicted risk probability curve and the actual occurrence probability curve; whether the weight coefficient obtained by COX multi-factor regression analysis of each first risk factor group is accurate or not can be judged according to the fitting degree of the data of the group, and then a plurality of first risk factor groups obtained by primary grouping are adjusted, so that N judgment standard groups obtained after adjustment meet preset associated conditions (the first risk factors in the judgment standard groups meet the conditions of similar types or the predicted risk probability curve meets the preset conditions).
Wherein the statistic for measuring goodness-of-fit (i.e., goodness-of-fit) is a coefficient of likelihood (also called a deterministic coefficient) R2。R2The maximum value is 1. R2The closer the value of (1) is, the better the fitting degree of the prediction risk probability curve to the actual occurrence probability curve is, and the greater the similarity is; conversely, a smaller value of R2 indicates a poorer degree of fitting of the predicted risk probability curve to the actual occurrence probability curve, and a smaller degree of similarity.
In this embodiment, when a group of first risk factor data is analyzed, a stepwise regression method is used to eliminate independent variables (i.e., first risk factors) without statistical significance, and the weight and error value of the risk factors are adjusted to improve the fitting degree between curves.
In some embodiments, adjusting the plurality of first risk factor groups according to the fitting degree of the second risk probability curve of the first risk factor group and the preset actual occurrence probability curve of the disease to obtain the N decision criterion groups and the assignment rule and the weight coefficient of the first risk factor in each decision criterion group may include:
for each first risk factor group, performing the following operations:
determining the first risk factor group as a second risk factor group under the condition that the fitting degree of a second risk probability curve of the first risk factor group and an actual occurrence probability curve of a preset disease is not larger than a second preset threshold;
and under the condition that the fitting degree of the second risk probability curve of the first risk factor group and the actual occurrence probability curve of the preset disease is greater than a first preset threshold value, determining the first risk factor group as a judgment standard group to obtain N judgment standard groups.
Specifically, if the goodness of fit between the predicted risk probability curve (i.e., the second risk probability curve) and the actual predetermined disease occurrence probability curve of the sample data in the first risk factor group is greater than a second predetermined threshold (e.g., R)2Less than 0.8)If the weight coefficient of the first risk factor in the first risk factor group is accurate, determining the first risk factor group as a judgment standard group; if the goodness-of-fit is greater than a second predetermined threshold (e.g., R)2Less than 0.8), which indicates that the weight coefficient of the first risk factor in the first risk factor group is inaccurate or the grouping is inaccurate, the first risk factor group is determined as the second risk factor group.
In this embodiment, by obtaining the goodness-of-fit value between the predicted risk probability curve (i.e., the second risk probability curve) of the sample data in the first risk factor group and the actual preset disease occurrence probability curve, the first risk factor group meeting the prediction standard can be screened out, and the group of the second risk probability curve meeting the prediction standard is determined as the determination standard group, so as to further improve the accuracy of prediction.
In some embodiments, adjusting the plurality of risk factor groups according to the fitting degree of the second risk probability curve of the first risk factor group and the preset actual occurrence probability curve of the disease to obtain N decision standard groups and the assignment rule and the weight coefficient of the risk factor in each decision standard group, may further include:
for each second risk factor group, performing the following operations:
combining the second risk factor group with the ith judgment standard group to form a third risk factor group, wherein i is a positive integer and is not more than N;
analyzing the data of the third risk factor group through a COX multi-factor regression model to obtain an assignment rule and a weight coefficient of each first risk factor in the third risk factor group;
obtaining a third risk probability of the sample data in the third risk factor group according to the assignment rule and the weight coefficient of the risk factors in the third risk factor group;
under the condition that the fitting degree of a third risk probability curve of a third risk factor group and an actual occurrence probability curve of a preset disease is not larger than a first preset threshold, updating i according to the mode that i is i +1, and returning to combine the second risk factor group and the ith judgment standard group to form a third risk factor group until the fitting degree of the third risk probability curve of the third risk factor group and the actual occurrence probability curve of the preset disease is larger than the first preset threshold;
and under the condition that the fitting degree of a third risk probability curve of the third risk factor group and an actual occurrence probability curve of a preset disease is greater than a first preset threshold value, updating the third risk factor group to an ith judgment standard group, or i is greater than or equal to N, and deleting the second risk factor group.
Specifically, in the present embodiment, for the second risk factor group, the grouping of the first risk factors may be adjusted by performing a merged analysis with the decision criterion group that meets the prediction criterion. That is, the second risk factor group is combined with the decision criterion group to be analyzed, that is, the second risk factor group is combined with one decision criterion that has been determined to constitute a third risk factor group, performing COX multi-factor regression analysis on the third risk factor group, performing COX multi-factor regression analysis by the same method as that of S203-S205 to obtain a third risk probability of the third risk factor group, then, whether the second risk factor group can be combined with the judgment standard group is determined according to the fitting degree of the third risk probability curve and the actual occurrence probability curve of the preset disease, if the preset condition is met, updating the combined third chalk line factor group as the judgment standard group, if the preset condition is not met, combining the second risk factor group with the next judgment standard and repeating the steps until the combined third risk factor group meets the preset condition; and if the second risk factor group and each judgment standard group can not meet the preset condition, deleting the second risk factor group.
In this embodiment, the plurality of risk factor groups are adjusted according to the fitting degree of the second risk probability curve of the first risk factor group and the preset disease actual occurrence probability curve, so that risk factors which are not significantly related to the preset disease risk can be further screened out, the obtained predicted risk probability value of the judgment standard group has higher similarity with the actual value, and the prediction accuracy is further improved.
In some embodiments, the predicting the risk probability of the user suffering from the predetermined disease according to the N first risk probabilities in step 104 may specifically include:
and calculating the average value of the N first risk probabilities to obtain the risk probability of the user suffering from the preset disease.
In the embodiment, the risk probability of the preset diseases suffered by the user is obtained by comprehensively predicting the grouped risk factor data prediction results, so that the prediction accuracy is further improved.
The embodiment of the present application is described below with reference to a specific application example, and the following steps may be adopted when predicting the preset disease risk according to the user data.
Step 1, referring to epidemiological statistics data of certain diseases, setting the risk of the diseases (risk probability of suffering from certain diseases) to four grades according to the actual occurrence probability of the diseases in the population, wherein the four grades are respectively extremely low risk (disease proportion below 25%), medium risk (disease proportion between 50% and 75%), high risk (disease proportion above 75%), and the higher the risk is, the higher the risk is. Quantifying disease risk factors affecting a certain disease, and collecting a risk factor set associated with the occurrence of the certain disease (i.e. determining first risk factors associated with the preset disease and sample data corresponding to each first risk factor according to epidemiological statistics of the preset disease).
Step 2, analyzing each risk factor by using a cox single-factor regression analysis method, and screening a disease risk factor data set which is obviously related to the disease; and each risk factor is assigned a different score depending on the degree of significance. (namely, the data of each initial risk factor is analyzed through a COX single-factor regression model, the initial risk factor with the significance smaller than a second preset threshold is determined as a first risk factor associated with the preset disease, and the first risk factor associated with the preset disease and the sample data corresponding to each first risk factor are obtained).
And 3, grouping the data sets. Referring to the clinical data of the diseases, the risk factors with similar attributes (such as the risk factors with similar attributes including constitution, blood fat and waist circumference) are classified into the same judgment standard group as a judgment condition of the disease risk grade, such as: judgment criteria A group and judgment criteria B group. Setting all judgment conditions of the disease risk level is sequentially and preliminarily completed (namely, the first risk factors are divided into a plurality of first risk factor groups according to the types of the first risk factors).
And 4, respectively carrying out cox multi-factor comprehensive regression analysis on the risk factors of each judgment standard group, and comparing the similarity of the predicted risk factor curve and the actual disease occurrence curve. The prediction function is: y ═ β 1X1+ … + β kXk + α, where Y is a dependent variable, i.e., a risk probability of developing a disease, X1 … Xk is an independent variable, i.e., an assessment score of disease risk factors affecting a disease, β 1 … β k is a weight coefficient of the assessment scores of the disease risk factors, and α is an error value. And (3) rejecting independent variables without statistical significance by using a stepwise regression method, adjusting the weight value and the error numerical value of the risk factor, and improving the fitting degree between curves. Merging and analyzing n judgment standard groups with the similarity smaller than a certain value (such as less than 0.8), namely, under the condition that the similarity of the judgment standard groups meets the n judgment standard groups simultaneously, verifying the similarity of the predicted occurrence rate and the actual occurrence rate of the disease risk by a COX multi-factor comprehensive regression analysis method again until the similarity of the predicted value and the actual value is larger than or equal to a certain value (such as more than or equal to 0.8), taking the merged n standard groups as a judgment condition, analogizing in sequence, and finally determining all prediction evaluation standards of the disease (namely, respectively analyzing the sample data of each first risk factor group by a COX multi-factor regression model to obtain an assignment rule and a weight coefficient of each first risk factor, obtaining a second risk probability of the sample data in the first risk factor group according to the assignment rule and the weight coefficient of the first risk factors in the first risk factor group, and presetting the actual occurrence of the disease according to a second risk probability curve of the first risk factor group And the fitting degree of the probability curve adjusts the plurality of first risk factor groups to obtain N judgment standard groups and the assignment rule and the weight coefficient of the first risk factor in each judgment standard group).
And 5, generating a computer prediction model of the diseases by using the grouping standard judgment rule and the prediction evaluation standard so as to complete automatic evaluation and prediction of the input disease risk factor data in a disease risk evaluation system.
And 6, collecting health information and detection data of the user, collecting physiological index data of the individual, such as blood pressure, heart rate, blood fat, blood sugar and the like by using health detection equipment, and automatically uploading and storing the physiological index data in a health index database. Setting a questionnaire according to the disease risk factors in the step 01, displaying questionnaire contents on a display screen of equipment, collecting data such as living and exercise habits of individuals by selecting questionnaire options, automatically uploading the data to a health questionnaire database through a network, and performing structured processing on the data by a system to obtain quantitative disease risk standard data (namely, obtaining user data of a user, wherein the user data comprises physiological characteristic data and at least one of behavior habit data and eating habit data).
Step 7, a data screening module of the disease risk assessment system automatically screens the disease risk standard data obtained in the step 5 according to a grouping standard of a disease prediction model, a data preprocessing module cleans the data and then converts the data into data meeting assessment requirements, a data analysis module groups the converted data and gives different scores and weights to index data in each group, a risk assessment module carries out comprehensive assessment on the grouping data to form assessment results (namely, aiming at each judgment standard group data, the first risk factor data is processed according to a preset assignment rule and a preset weight coefficient of a first risk factor to obtain a first risk probability of the judgment standard group data, the risk probability of a preset disease suffered by a user is predicted according to N first risk probabilities), a health report module matches the assessment results with disease risk grades, and outputting a final disease risk report.
According to the disease risk prediction method provided by the embodiment of the application, after the user data of the target user is obtained, risk factor data related to a preset disease in the user data can be divided into N judgment standard group data according to preset associated conditions; predicting the risk factor data in each judgment standard group according to a preset risk factor assignment rule and a weight coefficient to obtain the risk probability of each judgment standard group; and comprehensively analyzing to obtain the risk probability of the preset diseases of the user according to the risk probability of each judgment standard group data. The risk probability that the user suffers from the preset disease is obtained by performing grouping prediction on the risk factor data of the user and then performing comprehensive prediction on the prediction results of the risk factor data of different groups, so that the risk probability that the user suffers from the preset disease is accurately predicted.
As shown in fig. 3, an embodiment of the present application further provides a disease risk prediction apparatus 300, including: an acquisition module 301, a grouping module 302, a processing module 303, and a prediction module 304.
The acquiring module 301 is configured to acquire user data of a user, where the user data includes at least one of physiological characteristic data, behavior habit data, and eating habit data.
The first grouping module 302 is configured to group the user data to obtain N sets of determination standard data, where the sets of determination standard data include multiple first risk factor data, the multiple first risk factor data are first risk factor data associated with a preset disease in the user data that meets a preset associated condition, and N is a positive integer.
The processing module 303 is configured to, for each determination standard group data, process the first risk factor data according to the preset assignment rule and the preset weight coefficient of the first risk factor, so as to obtain a first risk probability of the determination standard group data.
And the predicting module 304 is used for predicting the risk probability of the user suffering from the preset disease according to the N first risk probabilities.
Optionally, the disease risk prediction apparatus 300 may further include:
a first determining module for determining first risk factors associated with the preset disease and sample data corresponding to each first risk factor according to epidemiological statistics of the preset disease
A second grouping module for grouping the first risk factors into a plurality of first risk factor groups according to the type of the first risk factors;
the first analysis module is used for analyzing the sample data of each first risk factor group through a COX multi-factor regression model to obtain an assignment rule and a weight coefficient of each first risk factor;
the calculation module is used for obtaining a second risk probability of the sample data in the first risk factor group according to the assignment rule and the weight coefficient of the first risk factor in the first risk factor group;
and the adjusting module is used for adjusting the plurality of first risk factor groups according to the fitting degree of the second risk probability curve of the first risk factor group and the actual occurrence probability curve of the preset disease to obtain the N judgment standard groups and the assignment rule and the weight coefficient of the first risk factor in each judgment standard group.
Optionally, the processing module 303 may be specifically configured to assign values to the first risk factor data in the determination standard group according to a preset assignment rule of the first risk factor, so as to obtain a score of each first risk factor data;
the first risk probability of the determination criterion group data is calculated by the above formula (1).
Optionally, the adjusting module may be specifically configured to, for each first risk factor group, respectively perform the following operations:
determining the first risk factor group as a second risk factor group under the condition that the fitting degree of a second risk probability curve of the first risk factor group and an actual occurrence probability curve of a preset disease is not larger than a second preset threshold;
and under the condition that the fitting degree of the second risk probability curve of the first risk factor group and the actual occurrence probability curve of the preset disease is greater than a first preset threshold value, determining the first risk factor group as a judgment standard group to obtain N judgment standard groups.
Optionally, the adjusting module may be further specifically configured to:
for each second risk factor group, performing the following operations:
combining the second risk factor group with the ith judgment standard group to form a third risk factor group, wherein i is a positive integer and is not more than N;
analyzing the data of the third risk factor group through a COX multi-factor regression model to obtain an assignment rule and a weight coefficient of each first risk factor in the third risk factor group;
obtaining a third risk probability of the sample data in the third risk factor group according to the assignment rule and the weight coefficient of the risk factors in the third risk factor group;
under the condition that the fitting degree of a third risk probability curve of a third risk factor group and an actual occurrence probability curve of a preset disease is not larger than a first preset threshold, updating i according to the mode that i is i +1, and returning to combine the second risk factor group and the ith judgment standard group to form a third risk factor group until the fitting degree of the third risk probability curve of the third risk factor group and the actual occurrence probability curve of the preset disease is larger than the first preset threshold;
and under the condition that the fitting degree of a third risk probability curve of the third risk factor group and an actual occurrence probability curve of a preset disease is greater than a first preset threshold value, updating the third risk factor group to the ith judgment standard group, or i is greater than or equal to N, and deleting the second risk factor group.
Optionally, the disease risk prediction apparatus 300 may further include:
the second determination module is used for determining initial risk factors associated with the preset diseases and sample data corresponding to each initial risk factor according to the epidemiological statistics data of the preset diseases;
and the second analysis module is used for analyzing the data of each initial risk factor through the COX single-factor regression model, determining the initial risk factors with the significance smaller than a second preset threshold value as first risk factors associated with the preset disease, and obtaining the first risk factors associated with the preset disease and sample data corresponding to each first risk factor.
Optionally, the processing module 303 may be specifically configured to calculate an average value of the N first risk probabilities, so as to obtain a risk probability that the user suffers from a preset disease.
According to the disease risk prediction device provided by the embodiment of the application, after the user data of the target user are obtained, risk factor data related to a preset disease in the user data can be divided into N judgment standard group data according to preset associated conditions; predicting the risk factor data in each judgment standard group according to a preset risk factor assignment rule and a weight coefficient to obtain the risk probability of each judgment standard group; and comprehensively analyzing to obtain the risk probability of the preset diseases of the user according to the risk probability of each judgment standard group data. The risk probability that the user suffers from the preset disease is obtained by performing grouping prediction on the risk factor data of the user and then performing comprehensive prediction on the prediction results of the risk factor data of different groups, so that the risk probability that the user suffers from the preset disease is accurately predicted.
Fig. 4 shows a hardware structure diagram of an electronic device provided in an embodiment of the present application.
The electronic device may include a processor 401 and a memory 402 storing computer program instructions.
Specifically, the processor 401 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory may include Read Only Memory (ROM), Random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to the methods according to an aspect of the present disclosure.
The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the human-vehicle weight recognition model training methods in the above embodiments, or to implement any one of the human-vehicle weight recognition methods in the above embodiments.
In one example, the electronic device can also include a communication interface 403 and a bus 404. As shown in fig. 4, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 404 to complete communication therebetween.
The communication interface 403 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application.
In addition, in combination with the disease risk prediction method in the foregoing embodiments, the embodiments of the present application may be implemented by providing a computer storage medium. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the disease risk prediction methods of the above embodiments.
It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above structural block diagrams may be implemented as 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, plug-in, function card, or the like. When implemented in software, the elements of the present 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 by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, 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 so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, 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, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present disclosure 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 disclosure. 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, 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 for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As will be apparent to those skilled in the art, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (10)
1. A method of disease risk prediction, the method comprising:
acquiring user data of a user, wherein the user data comprises physiological characteristic data and at least one of behavior habit data and eating habit data;
grouping the user data to obtain N judgment standard group data, wherein the judgment standard group data comprise a plurality of first risk factor data, the plurality of first risk factor data are first risk factor data which are associated with a preset disease in the user data and meet preset associated conditions, and N is a positive integer;
processing the first risk factor data according to a preset assignment rule and a preset weight coefficient of a first risk factor aiming at each judgment standard group data to obtain a first risk probability of the judgment standard group data;
and predicting the risk probability of the user suffering from the preset disease according to the N first risk probabilities.
2. The method of claim 1, wherein before grouping the user data into N sets of decision criteria data, further comprising:
determining first risk factors associated with the preset disease and sample data corresponding to each first risk factor according to the epidemiological statistics of the preset disease;
dividing the first risk factors into a plurality of first risk factor groups according to the type of the first risk factors;
respectively analyzing the sample data of each first risk factor group through a COX multi-factor regression model to obtain an assignment rule and a weight coefficient of each first risk factor;
obtaining a second risk probability of the sample data in the first risk factor group according to the assignment rule and the weight coefficient of the first risk factor in the first risk factor group;
and adjusting the plurality of first risk factor groups according to the fitting degree of the second risk probability curve of the first risk factor group and the actual occurrence probability curve of the preset disease to obtain the N judgment standard groups and the assignment rule and the weight coefficient of the first risk factor in each judgment standard group.
3. The method according to claim 2, wherein the obtaining, for each determination criterion group data, a first risk probability of the determination criterion group data according to a preset assignment rule and a preset weight coefficient of a first risk factor comprises:
assigning the first risk factor data in the judgment standard group according to a preset assignment rule of the first risk factor to obtain a score of each first risk factor data;
calculating a first risk probability of the set of decision criterion data by:
wherein Y is the first risk probability, K is the number of the first risk factors in the set of decision criteria, and XiIs a score, β, of said first risk factor dataiα is an error value, which is a weight coefficient of the first risk factor.
4. The method according to claim 2, wherein the adjusting the plurality of first risk factor groups according to the fitting degree of the second risk probability curve of the first risk factor group and the preset actual occurrence probability curve of the disease to obtain N decision criterion groups and the assignment rule and the weight coefficient of the first risk factor in each decision criterion group comprises:
for each first risk factor group, performing the following operations:
determining the first risk factor group as a second risk factor group under the condition that the fitting degree of a second risk probability curve of the first risk factor group and an actual occurrence probability curve of the preset disease is not greater than a second preset threshold;
and under the condition that the fitting degree of the second risk probability curve of the first risk factor group and the actual occurrence probability curve of the preset disease is greater than a first preset threshold value, determining the first risk factor group as the judgment standard group to obtain N judgment standard groups.
5. The method according to claim 3, wherein the adjusting the plurality of risk factor sets according to the fitting degree of the second risk probability curve of the first risk factor set and the preset actual occurrence probability curve of the disease to obtain N decision criterion sets and the assignment rule and the weight coefficient of the risk factor in each decision criterion set further comprises:
for each second risk factor group, performing the following operations:
combining the second risk factor group with the ith judgment standard group to form a third risk factor group, wherein i is a positive integer and is not more than N;
analyzing the data of the third risk factor group through a COX multi-factor regression model to obtain an assignment rule and a weight coefficient of each first risk factor in the third risk factor group;
obtaining a third risk probability of sample data in the third risk factor group according to the assignment rule and the weight coefficient of the risk factors in the third risk factor group;
under the condition that the fitting degree of a third risk probability curve of the third risk factor group and an actual occurrence probability curve of the preset disease is not larger than a first preset threshold, updating i according to a mode that i is i +1, returning to combine the second risk factor group and the ith judgment standard to form a third risk factor group until the fitting degree of the third risk probability curve of the third risk factor group and the actual occurrence probability curve of the preset disease is larger than the first preset threshold;
and under the condition that the fitting degree of a third risk probability curve of the third risk factor group and an actual occurrence probability curve of the preset disease is larger than a first preset threshold value, updating the third risk factor group to the ith judgment standard group, or i is larger than or equal to N, and deleting the second risk factor group.
6. The method of claim 2, wherein said determining first risk factors associated with the predetermined disease and sample data corresponding to each first risk factor from epidemiological statistics of the predetermined disease comprises:
determining initial risk factors associated with the preset disease and sample data corresponding to each initial risk factor according to the epidemiological statistics of the preset disease;
and analyzing the data of each initial risk factor through a COX single-factor regression model, determining the initial risk factors with the significance smaller than a second preset threshold value as first risk factors associated with the preset disease, and obtaining the first risk factors associated with the preset disease and sample data corresponding to each first risk factor.
7. The method according to claim 1, wherein predicting the risk probability of the user suffering from the predetermined disease according to the N first risk probabilities comprises:
and calculating the average value of the N first risk probabilities to obtain the risk probability of the user suffering from the preset disease.
8. A disease risk prediction device, comprising:
the acquisition module is used for acquiring user data of a user, wherein the user data comprises at least one of physiological characteristic data, behavior habit data and eating habit data;
the first grouping module is used for grouping the user data to obtain N judgment standard group data, wherein the judgment standard group data comprise a plurality of first risk factor data, the plurality of first risk factor data are first risk factor data which are associated with a preset disease in the user data and meet preset associated conditions, and N is a positive integer;
the processing module is used for processing the first risk factor data according to a preset assignment rule and a preset weight coefficient of a first risk factor aiming at each judgment standard group data to obtain a first risk probability of the judgment standard group data;
and the prediction module is used for predicting the risk probability of the user suffering from the preset disease according to the N first risk probabilities.
9. An electronic device comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the steps of the disease risk prediction method according to any one of claims 1-7.
10. A readable storage medium, storing thereon a program or instructions which, when executed by a processor, carry out the steps of the disease risk prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210161426.XA CN114628033A (en) | 2022-02-22 | 2022-02-22 | Disease risk prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210161426.XA CN114628033A (en) | 2022-02-22 | 2022-02-22 | Disease risk prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114628033A true CN114628033A (en) | 2022-06-14 |
Family
ID=81900367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210161426.XA Pending CN114628033A (en) | 2022-02-22 | 2022-02-22 | Disease risk prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114628033A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116386879A (en) * | 2023-06-07 | 2023-07-04 | 中国医学科学院阜外医院 | Risk level prediction device and computer storage medium |
-
2022
- 2022-02-22 CN CN202210161426.XA patent/CN114628033A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116386879A (en) * | 2023-06-07 | 2023-07-04 | 中国医学科学院阜外医院 | Risk level prediction device and computer storage medium |
| CN116386879B (en) * | 2023-06-07 | 2024-04-19 | 中国医学科学院阜外医院 | Risk level prediction device and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102930163A (en) | Method for judging 2 type diabetes mellitus risk state | |
| CN111539308B (en) | Embryo quality comprehensive evaluation device based on deep learning | |
| CN110739076A (en) | medical artificial intelligence public training platform | |
| CN107145715B (en) | Clinical medicine intelligence discriminating gear based on electing algorithm | |
| CN112633601A (en) | Method, device, equipment and computer medium for predicting disease event occurrence probability | |
| CN110706822B (en) | Health management method based on logistic regression model and decision tree model | |
| CN116344050B (en) | Evaluation method based on multidimensional health management model | |
| Atashi et al. | Breast Cancer Risk Assessment Using Adaptive Neuro-Fuzzy Inference System (ANFIS) and Subtractive Clustering Algorithm | |
| CN113593708A (en) | Sepsis prognosis prediction method based on integrated learning algorithm | |
| CN114628033A (en) | Disease risk prediction method, device, equipment and storage medium | |
| CN112331340B (en) | Intelligent prediction method and system for pregnancy probability of pregnant couple | |
| Bazilevych et al. | Determining the Probability of Heart Disease using Data Mining Methods. | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| CN116705310A (en) | Data set construction method, device, equipment and medium for perioperative risk assessment | |
| CN116631622A (en) | AI-based pregnant woman characteristic-related fetal weight prediction method and system | |
| CN116564521A (en) | Chronic disease risk assessment model establishment method, medium and system | |
| CN113537759B (en) | Weight self-adaption-based user experience measurement model | |
| CN114936204A (en) | Feature screening method and device, storage medium and electronic equipment | |
| CN113851221A (en) | Dynamic health evaluation method and system based on time sequence body measurement data | |
| CN114334157A (en) | Cerebral apoplexy risk prediction method and device | |
| TWI826081B (en) | Cancer progression assessment method and system thereof | |
| CN111755121A (en) | Method and device for evaluating physical development trend of juveniles | |
| CN113257380B (en) | Method and device for difference checking and difference checking rule making | |
| TWI817795B (en) | Cancer progression discriminant method and system thereof | |
| CN111430032B (en) | Old people disease modeling method based on APC model and genetic clustering algorithm |
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 |