CN113643809A - Human body component-based type 2 diabetes prediction method and system - Google Patents
Human body component-based type 2 diabetes prediction method and system Download PDFInfo
- Publication number
- CN113643809A CN113643809A CN202110898172.5A CN202110898172A CN113643809A CN 113643809 A CN113643809 A CN 113643809A CN 202110898172 A CN202110898172 A CN 202110898172A CN 113643809 A CN113643809 A CN 113643809A
- Authority
- CN
- China
- Prior art keywords
- diabetes
- type
- factor
- data
- model
- 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
- 208000001072 type 2 diabetes mellitus Diseases 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000000556 factor analysis Methods 0.000 claims abstract description 19
- 238000007477 logistic regression Methods 0.000 claims abstract description 11
- 230000001419 dependent effect Effects 0.000 claims abstract description 7
- 206010012601 diabetes mellitus Diseases 0.000 claims description 16
- 239000000203 mixture Substances 0.000 claims description 13
- 201000010099 disease Diseases 0.000 claims description 9
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000000585 Mann–Whitney U test Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000010832 independent-sample T-test Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims 2
- 230000009278 visceral effect Effects 0.000 claims 1
- 210000001596 intra-abdominal fat Anatomy 0.000 description 7
- 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 6
- 239000008280 blood Substances 0.000 description 5
- 210000004369 blood Anatomy 0.000 description 5
- 238000011088 calibration curve Methods 0.000 description 4
- 235000012000 cholesterol Nutrition 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 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 1
- 208000008589 Obesity Diseases 0.000 description 1
- 208000017442 Retinal disease Diseases 0.000 description 1
- 206010038923 Retinopathy Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 230000035487 diastolic blood pressure Effects 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000035488 systolic blood pressure Effects 0.000 description 1
- 230000006016 thyroid dysfunction Effects 0.000 description 1
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4869—Determining body composition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Abstract
The invention discloses a human body component-based type 2 diabetes prediction method and a system, wherein the method comprises the following steps: acquiring basic data of a patient and data related to human body components; whether the follow-up patients have type 2 diabetes is taken as a dependent variable, the obtained factors are taken as independent variables for single factor analysis, and the factors with statistical difference are screened out according to the P value of each factor; incorporating independent variables with statistical difference in a single-factor analysis result into the model for multi-factor Logistic regression analysis, selecting a model with the best fitting degree according to the magnitude of the red pond information criterion AIC value, determining the regression coefficient of the finally incorporated independent variables, and representing the regression coefficient by using a Nomogram array chart; and predicting the incidence risk of the type 2 diabetes of the patient according to the prediction cut-off value of the nomogram.
Description
Technical Field
The invention relates to the technical field of diabetes prediction, in particular to a method and a system for predicting type 2 diabetes based on human body components.
Background
Diabetes is recognized as a major public health problem worldwide. The incidence of type 2 diabetes has increased year by year in recent years, and the occurrence of type 2 diabetes and its complications imposes a significant economic burden on patients and is a leading cause of death.
In diabetic patients, a large part of the patients are not diagnosed (such as no symptoms) but still at high risk of suffering from serious complications such as cardiovascular diseases, kidney damage, retinopathy and the like, and several intervention studies find that the lifestyle improvement and the pharmaceutical intervention of people at high risk of diabetes can prevent and delay the occurrence of type 2 diabetes. In this case, it is important to identify the people at high risk and the patients with type 2 diabetes who are not diagnosed by a simple and effective method.
In recent years, some type 2 diabetes early-stage prediction scoring models are established abroad, and related models are established for Wuhan, Taiwan, Guangzhou and other areas domestically. However, due to differences in ethnicity, demographics, and lifestyle, these models are not necessarily suitable for other people. Most of models studied at present are based on demographic indexes (age, sex, family history of diabetes, etc.), life style (smoking, drinking, eating habits, etc.), anthropometry (height, weight, waist circumference, waist-hip ratio, systolic pressure, diastolic pressure, etc.), clinical test indexes (triglyceride, cholesterol, high-density cholesterol, low-density cholesterol, fasting blood, etc.), and most of models include the clinical test indexes, which may reduce the volunteering of patients to some extent. Relevant researches show that in the evaluation of obesity indexes, the visceral fat area has larger relevance with the occurrence of type 2 diabetes, so that a type 2 diabetes risk prediction model for discovering type 2 diabetes in a non-invasive, simple and practical mode can be established.
Disclosure of Invention
The invention aims to provide a method and a system for predicting type 2 diabetes based on human body components, and aims to solve the problems.
The invention provides a human body component-based type 2 diabetes mellitus prediction method, which comprises the following steps:
s1, acquiring basic data of a patient and relevant data of human body components;
s2, performing single-factor analysis by taking whether the follow-up patient has type 2 diabetes as a dependent variable and the factors obtained in the step S1 as independent variables, and screening out factors with statistical difference according to P values of the factors;
s3, incorporating independent variables with statistical difference in single-factor analysis results into a multi-factor Logistic regression analysis, selecting a model with the best fitting degree according to the magnitude of an information criterion AIC value of a Chichi pool, determining a final incorporating independent variable regression coefficient, and representing by adopting a Nomogram array line;
and S4, predicting the incidence risk of the type 2 diabetes of the patient according to the prediction cut-off value of the nomogram prediction model.
The invention provides a human body component-based type 2 diabetes prediction system, which comprises:
a data acquisition module: the system is used for acquiring basic data of a patient and data related to human body components;
a data analysis module: the method is used for performing single-factor analysis by taking whether the follow-up patients have type 2 diabetes as a dependent variable and taking the factors acquired by the data acquisition module as independent variables, and screening out factors with statistical difference according to P values of all the factors;
a model building module: incorporating independent variables with statistical difference in a single-factor analysis result into the model for multi-factor Logistic regression analysis, selecting a model with the best fitting degree according to the magnitude of the red pond information criterion AIC value, determining the regression coefficient of the finally incorporated independent variables, and representing the regression coefficient by using a Nomogram array chart;
a result prediction module: and predicting the incidence risk of the type 2 diabetes of the patient according to the prediction cut-off value of the nomogram.
By adopting the embodiment of the invention, the risk of the type 2 diabetes of the patient can be predicted by collecting simple basic information of the patient and monitoring data of the noninvasive and repeatedly measurable human body composition analyzer, and the noninvasive screening of the type 2 diabetes at the early stage can be carried out, and the noninvasive screening method has the advantages of easiness in operation, strong implementation, low cost, high efficiency and the like.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for predicting type 2 diabetes based on body composition according to an embodiment of the present invention;
FIG. 2 is a nomogram of a type 2 diabetes prediction model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a type 2 diabetes prediction model ROC curve according to an embodiment of the present invention;
FIG. 4 is a graph illustrating a calibration curve of a type 2 diabetes prediction model according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a human composition-based type 2 diabetes prediction system according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise. Furthermore, the terms "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Method embodiment
According to an embodiment of the present invention, a method for predicting type 2 diabetes based on human body components is provided, fig. 1 is a flowchart of the method for predicting type 2 diabetes based on human body components according to an embodiment of the present invention, as shown in fig. 1, the method for predicting type 2 diabetes based on human body components according to an embodiment of the present invention specifically includes:
s1, acquiring basic data of a patient and relevant data of human body components;
specifically, collecting patient baseline data includes: age, sex, family history and past history of diabetes, obtain the relevant data of human composition through the human composition analysis appearance, include: visceral fat area, height and weight, and blood sugar condition of a follow-up patient for three years continuously, and fasting blood sugar value and blood sugar value of the follow-up patient after 2 hours of oral glucose are obtained every year.
S2, performing single-factor analysis by taking whether the follow-up patient has type 2 diabetes as a dependent variable and the factors obtained in the step S1 as independent variables, and screening out factors with statistical difference according to P values of the factors;
specifically, the patients are divided into a type 2 diabetes group and a type 2 non-diabetes group according to whether the followed patients have type 2 diabetes, the factor values of the two groups of patients obtained in the step S1 are subjected to single factor analysis, the metering data conforming to normal distribution or approximating normal distribution in each factor are subjected to interclass comparison by adopting independent sample t test, the metering data conforming to non-normal distribution are subjected to interclass comparison by adopting Mann-Whitney U test, the counting data are subjected to interclass comparison by adopting Kafang test or Fisher accurate test, the P value of each factor is determined, and the variable with the P value less than 0.05 is screened out.
S3, incorporating independent variables with statistical difference in single-factor analysis results into a multi-factor Logistic regression analysis, selecting a model with the best fitting degree according to the magnitude of an information criterion AIC value of a Chichi pool, determining a final incorporating independent variable regression coefficient, and representing by adopting a Nomogram array line;
specifically, a variable with P <0.05 in the single-factor analysis is included in the multi-factor binary Logistic regression analysis, a model with the best fitting degree is selected according to the magnitude of an Akaichi information criterion AIC value, the variable finally included in a Logistic regression equation is introduced into R software, and a Nomogram prediction model is drawn.
S4, predicting the incidence risk of the type 2 diabetes of the patient according to the prediction cut-off value of the nomogram prediction model;
specifically, the prediction cutoff value of the nomogram prediction model is determined according to the john index.
Further, the discrimination and calibration evaluation is carried out on the nomogram prediction model: internally verifying the discrimination and calibration degree of the model by adopting a Bootstraps (B is 500); and comparing the disease incidence result predicted by the model with the actual disease incidence result to obtain a corresponding ROC curve and a Calibration curve, evaluating the discrimination of the nomogram prediction model by using AUCROC (autonomous underwater vehicle) of the area below the ROC curve, and evaluating the Calibration of the nomogram prediction model by using the Calibration curve.
The specific embodiment is as follows:
in this embodiment, the visceral fat area is obtained by using a human body composition instrument (model number 720), the study population selects the population who is 18-70 years old, does not have diabetes and is matched with the study population to complete questionnaire survey, the population suffering from malignant tumor, thyroid dysfunction, gastrointestinal tract disease postoperative, pregnant woman, lactating mother and secondary diabetes needs to be excluded, the population is subjected to blood sugar follow-up for 3 years, and the data which is lost or incomplete is removed during data arrangement to obtain the final data for analysis.
After the study population is compared according to the preliminary analysis of step S1 and step S2, the variables are screened according to the requirement of P value in step S3, and the results are shown in table 1:
TABLE 1
As shown in table 1, the group with type 2 diabetes was older, had a high proportion of family history of diabetes, had a large Body Mass Index (BMI) and Visceral Fat Area (VFA), and had a large number of males compared to the group with type 2 diabetes. From the results of Logistic regression analysis, the regression equation for the probability of a patient to predict P-value for type 2 diabetic patients or high risk groups by age, family history, Visceral Fat Area (VFA), gender calculation is:
logit (p) ═ 4.681+1.543 family history (with diabetes family history of 1, without diabetes family history of 0) +0.898 gender (women assigned a value of 1, men assigned a value of 0) +0.025 age +0.013 Visceral Fat Area (VFA);
and establishing a regression model according to the regression equation.
Variables in the Logistic regression equation are introduced into R software, and a drawn nomogram prediction model is shown in FIG. 2.
The incidence risk of type 2 diabetes is predicted for the patient according to the predicted cutoff value of the nomogram prediction model, as shown in fig. 3, the predicted cutoff value of the nomogram prediction model is judged by using a sensitivity and specificity graph in ROC curve research, the probability value corresponding to the intersection point of the sensitivity and specificity curves is the cutoff value, and the cutoff value is 0.15 according to the johnson index, so that the patient is identified as a type 2 diabetes patient or a high risk group when the predicted P value exceeds the cutoff value or the combination of the variable assignments is more than 120 minutes (in combination with fig. 2) according to age, family history, Visceral Fat Area (VFA) and gender.
Carrying out discrimination and calibration evaluation on the nomogram prediction model, and evaluating the discrimination of the nomogram prediction model by using the size of the Area (AUCROC) below an ROC curve, wherein the AUCROC value range is 0.5-1.0, and the higher the AUCROC value is, the higher the authenticity of the prediction is, the stronger the discrimination capability of the prediction model is; the calibration degree of the nomogram prediction model was evaluated using the calibration curve, the incidence of type 2 diabetes (actual type 2 diabetes/total number of cases) and the incidence of predicted type 2 diabetes (predicted type 2 diabetes/total number of cases) for each group were calculated, and a broken line graph was plotted as shown in fig. 4, where a good fit of the broken line to the reference line (y ═ x) indicates good calibration ability of the model.
By adopting the embodiment of the invention, the risk of the type 2 diabetes of the patient can be predicted by monitoring data of the noninvasive and repeatedly measurable human body composition analyzer and combining the collection of simple basic information of the patient, and the early screening of the type 2 diabetes is carried out, so that the operation is easy and the implementation is strong. The system is suitable for the relevant health medical industries such as community health service centers, hospital physical examination centers, health management companies and the like.
System embodiment
According to an embodiment of the present invention, a system for predicting type 2 diabetes based on body composition is provided, fig. 5 is a schematic diagram of the system for predicting type 2 diabetes based on body composition according to an embodiment of the present invention, as shown in fig. 5, the system for predicting type 2 diabetes based on body composition according to an embodiment of the present invention specifically includes:
the data acquisition module 50: used for obtaining basic data of patients and data related to human body components.
The data analysis module 52: the method is used for performing single-factor analysis by taking whether the followed patient has type 2 diabetes as a dependent variable and the factors acquired by the data acquisition module 50 as independent variables, and screening out the factors with statistical difference according to the P value of each factor.
The data analysis module 52 is specifically configured to: according to the type 2 diabetes group and the type 2 non-diabetes group which are divided by taking whether type 2 diabetes occurs in the follow-up period as a standard, single factor analysis is carried out on the factor values of the two groups of patients acquired by the data acquisition module, independent sample t test is adopted to carry out inter-group comparison according to metering data conforming to normal distribution or approximately normal distribution, Mann-Whitney U test is adopted to carry out inter-group comparison on the metering data of non-normal distribution, chi-square test or Fisher accurate test is adopted to carry out inter-group comparison on the counting data, the P value of each factor is determined, and a variable with the P value less than 0.05 is screened out.
The model building module 54: incorporating independent variables with statistical difference in a single-factor analysis result into the model for multi-factor Logistic regression analysis, selecting a model with the best fitting degree according to the magnitude of the red pond information criterion AIC value, determining the regression coefficient of the finally incorporated independent variables, and representing the regression coefficient by using a Nomogram array chart;
the outcome prediction module 56: and predicting the incidence risk of the type 2 diabetes of the patient according to the prediction cut-off value of the nomogram.
Specifically, the system further comprises an internal verification module, and the internal verification module is specifically configured to: and comparing the disease incidence result predicted by the model with the actual disease incidence result to obtain a corresponding ROC curve and a Calibration correction curve, and internally verifying and evaluating the discrimination and Calibration degree of the model.
The embodiment of the present invention is a system embodiment corresponding to the above method embodiment, and specific operations of each module may be understood with reference to the description of the method embodiment, which is not described herein again.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for predicting type 2 diabetes based on human body components is characterized by comprising the following steps:
s1, acquiring basic data of a patient and relevant data of human body components;
s2, performing single-factor analysis by taking whether the follow-up patient has type 2 diabetes as a dependent variable and the factors obtained in the step S1 as independent variables, and screening out factors with statistical difference according to P values of the factors;
s3, incorporating independent variables with statistical difference in single-factor analysis results into a multi-factor Logistic regression analysis, selecting a model with the best fitting degree according to the magnitude of an information criterion AIC value of a Chichi pool, determining a final incorporating independent variable regression coefficient, and representing by adopting a Nomogram array line;
and S4, predicting the incidence risk of the type 2 diabetes of the patient according to the prediction cut-off value of the nomogram.
2. The method of claim 1, wherein the patient profile of step S1 includes: age, sex, family history and the past history of diabetes, the relevant data of human composition is obtained through the human composition analysis appearance, mainly includes: visceral area, height, weight.
3. The method of claim 1, wherein the step S2 is performed by the following specific method: firstly, dividing the patients into a type 2 diabetes group and a type 2 non-diabetes group according to whether the followed patients have type 2 diabetes, carrying out single-factor analysis on the factor values of the two groups of patients obtained in the step S1, carrying out inter-group comparison on the measurement data which accord with normal distribution or approximate normal distribution in each factor by adopting independent sample t test, carrying out inter-group comparison on the measurement data which accord with normal distribution or approximate normal distribution by adopting Mann-Whitney U test on the non-normal distribution, carrying out inter-group comparison on the counting data by adopting Kafang test or Fisher accurate test, and determining the P value of each factor.
4. The method of claim 1, wherein the method for determining the predicted cutoff value in step S4 is: and determining a prediction cutoff value of the nomogram prediction model according to the Jordan index.
5. The method of claim 1, further comprising:
and comparing the disease incidence result predicted by the model with the actual disease incidence result to obtain a corresponding ROC curve and a Calibration correction curve, and internally verifying and evaluating the discrimination and Calibration degree of the model.
6. A system for predicting type 2 diabetes based on body composition, comprising:
a data acquisition module: the system is used for acquiring basic data of a patient and data related to human body components;
a data analysis module: the method is used for performing single-factor analysis by taking whether the follow-up patients have type 2 diabetes as a dependent variable and taking the factors acquired by the data acquisition module as independent variables, and screening out factors with statistical difference according to P values of all the factors;
a model building module: incorporating independent variables with statistical difference in a single-factor analysis result into the model for multi-factor Logistic regression analysis, selecting a model with the best fitting degree according to the magnitude of the red pond information criterion AIC value, determining the regression coefficient of the finally incorporated independent variables, and representing the regression coefficient by using a Nomogram array chart;
a result prediction module: and predicting the incidence risk of the type 2 diabetes of the patient according to the prediction cut-off value of the nomogram.
7. The system of claim 6, wherein the data analysis module is specifically configured to: dividing the patients into type 2 diabetes groups and non-type 2 diabetes groups according to the standard of whether type 2 diabetes occurs in the follow-up period, performing single-factor analysis on the factor values of the two groups of patients acquired by the data acquisition module, performing inter-group comparison on metering data conforming to normal distribution or approximately normal distribution by adopting independent sample t test, performing inter-group comparison on the metering data of non-normal distribution by adopting Mann-Whitney U test, performing inter-group comparison on the counting data by adopting Kafang test or Fisher accurate test, and determining the value of each factor P.
8. The system according to claim 6, further comprising an internal authentication module, the internal authentication module being specifically configured to: and comparing the disease incidence result predicted by the model with the actual disease incidence result to obtain a corresponding ROC curve and a Calibration correction curve, and internally verifying and evaluating the discrimination and Calibration degree of the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898172.5A CN113643809A (en) | 2021-08-05 | 2021-08-05 | Human body component-based type 2 diabetes prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898172.5A CN113643809A (en) | 2021-08-05 | 2021-08-05 | Human body component-based type 2 diabetes prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113643809A true CN113643809A (en) | 2021-11-12 |
Family
ID=78419743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110898172.5A Pending CN113643809A (en) | 2021-08-05 | 2021-08-05 | Human body component-based type 2 diabetes prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113643809A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114611919A (en) * | 2022-03-09 | 2022-06-10 | 广东产品质量监督检验研究院（国家质量技术监督局广州电气安全检验所、广东省试验认证研究院、华安实验室） | Risk assessment method for unqualified product |
| CN114974595A (en) * | 2022-05-13 | 2022-08-30 | 江苏省人民医院（南京医科大学第一附属医院） | Crohn's disease patient mucosa healing prediction model and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063568A (en) * | 2010-12-29 | 2011-05-18 | 中国疾病预防控制中心慢性非传染性疾病预防控制中心 | Individual diabetes mellitus prediction model |
| US20160042152A1 (en) * | 2014-08-05 | 2016-02-11 | Orb Health, Inc. | Dynamic Presentation of Goals and Therapies Including Related Devices and Applications |
| CN111539946A (en) * | 2020-04-30 | 2020-08-14 | 常州市第一人民医院 | Method for identifying early lung adenocarcinoma manifested as frosted glass nodule |
| CN112820406A (en) * | 2020-12-30 | 2021-05-18 | 复旦大学附属妇产科医院 | Method for predicting early pregnancy onset risk of epilepsy |
| CN113192637A (en) * | 2021-04-20 | 2021-07-30 | 山东大学齐鲁医院 | Risk prediction method and device for individual quantitative evaluation of progression to type 2diabetes |
-
2021
- 2021-08-05 CN CN202110898172.5A patent/CN113643809A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063568A (en) * | 2010-12-29 | 2011-05-18 | 中国疾病预防控制中心慢性非传染性疾病预防控制中心 | Individual diabetes mellitus prediction model |
| US20160042152A1 (en) * | 2014-08-05 | 2016-02-11 | Orb Health, Inc. | Dynamic Presentation of Goals and Therapies Including Related Devices and Applications |
| CN111539946A (en) * | 2020-04-30 | 2020-08-14 | 常州市第一人民医院 | Method for identifying early lung adenocarcinoma manifested as frosted glass nodule |
| CN112820406A (en) * | 2020-12-30 | 2021-05-18 | 复旦大学附属妇产科医院 | Method for predicting early pregnancy onset risk of epilepsy |
| CN113192637A (en) * | 2021-04-20 | 2021-07-30 | 山东大学齐鲁医院 | Risk prediction method and device for individual quantitative evaluation of progression to type 2diabetes |
| CN114724716A (en) * | 2021-04-20 | 2022-07-08 | 山东大学齐鲁医院 | Method, model training and apparatus for risk prediction of progression to type 2 diabetes |
Non-Patent Citations (1)
| Title |
|---|
| 王猛 等: "ＭＲＩ无创定量测量腹腔脂肪体积预测２型糖尿病", 中国医学影像技术, vol. 33, no. 12, 31 December 2017 (2017-12-31), pages 1844 - 1849 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114611919A (en) * | 2022-03-09 | 2022-06-10 | 广东产品质量监督检验研究院（国家质量技术监督局广州电气安全检验所、广东省试验认证研究院、华安实验室） | Risk assessment method for unqualified product |
| CN114974595A (en) * | 2022-05-13 | 2022-08-30 | 江苏省人民医院（南京医科大学第一附属医院） | Crohn's disease patient mucosa healing prediction model and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113643809A (en) | Human body component-based type 2 diabetes prediction method and system | |
| CA2655126A1 (en) | Systems and methods for analyzing and assessing dementia and dementia-type disorders | |
| Hirten et al. | Longitudinal autonomic nervous system measures correlate with stress and ulcerative colitis disease activity and predict flare | |
| Tapper | Predicting overt hepatic encephalopathy for the population with cirrhosis | |
| KR101989695B1 (en) | Predictive model for the accumulation of brain amyloid and predictive method using thereof | |
| CN114464322B (en) | Female pelvic floor dysfunction disease risk early warning model and construction method and system thereof | |
| US20140052008A1 (en) | Hypertension monitoring and notification device based on context information | |
| Chiu et al. | BMI trajectories as a harbinger of pre-diabetes or underdiagnosed diabetes: an 18-year retrospective cohort study in Taiwan | |
| CN115101199A (en) | Interpretable fair early death risk assessment model and device for critically ill elderly patients and establishment method thereof | |
| CN104698160B (en) | A kind of test kit for assessing male's twenty-four-hour urine sodium value | |
| CN111508584B (en) | Method for evaluating daily salt content of hypertensive patient by using random urine infusion | |
| CN115547495B (en) | System for comprehensively evaluating glycolipid metabolism level and application thereof | |
| CN104569437B (en) | For assessing the test kit of women twenty-four-hour urine sodium value | |
| CN114792567A (en) | Device for predicting fracture occurrence risk of type 2diabetes patient | |
| KR102418340B1 (en) | Apparatus for predicting rimpaired glucose metabolism using the blood glucose change pattern of standard foods method thereof | |
| Anggraini et al. | Correlation between Anthropometric Measurement and Kidney Function in the Elderly to Detection of Chronic Kidney Disease | |
| CN115223706A (en) | Sepsis early stage screening model suitable for mobile monitoring equipment | |
| CN111883248B (en) | Prediction system for childhood obesity | |
| CN113345586A (en) | Gestational disease evaluation system | |
| Mannucci et al. | Indexes of abdominal adiposity in patients with type 2 diabetes | |
| CN104569438B (en) | A kind of test kit for assessing women twenty-four-hour urine sodium value | |
| CN112086194A (en) | New-onset type 2diabetes scoring prediction system | |
| CN117577330B (en) | Device and storage medium for predicting liver fibrosis degree of nonalcoholic fatty liver disease | |
| CN114093518B (en) | Diabetes risk assessment system and method based on obesity degree | |
| CN116047082B (en) | Application of FGL1 protein in preparing kit for diagnosing chronic kidney disease |
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 |