Children obesity data analysis and prediction method and model

Abstract

The invention discloses a child obesity data analysis and prediction method and model, and the method comprises the steps: introducing the recent BMI data of a child, analyzing the change condition of the recent BMI, combining the BMI data of a direct family of the child, and carrying out a series of analysis and calculation, thereby analyzing and obtaining a result whether the child has an obesity risk or not. Factors such as the BMI change trend of the children in recent years and the BMI of parents of the children are fully and comprehensively considered to predict the obesity risk of the children, the prediction result is more accurate, timely intervention, scientific management of the stature of the children and healthy growth of the children are facilitated, a scientific basis and an effective method are provided for preventing and controlling obesity of people in China, and great social and economic benefits are achieved.

Description

[Technical field]

[0001] The present invention relates to the technical field of children's health management, in particular to the technical field of children's obesity data analysis and prediction methods and models. [Background technology]

[0002] At present, obesity has become a major public health challenge that transcends national boundaries. Not only are developed countries facing an overweight and obesity rate of more than 40%, but my country is also deeply trapped in it, with the number of overweight and obese adults jumping to 200 million. Obesity is not only the number one culprit for cardiovascular and metabolic diseases such as type 2 diabetes, hypertension and metabolic syndrome, but also indicates the intensification of health risks in the future. China not only bears the heavy burden of the largest obese population in the world, but also has the largest number of diabetes patients. It is predicted that by 2045, the number of diabetes patients will surge to 150 million. What is particularly worrying is that the obesity problem is rapidly spreading to younger groups. In the past 30 years, the obesity rate of school-age children in my country has soared 13 times, far exceeding the growth rate of adults, and the number of overweight and obese children has approached 35 million. This phenomenon has led to the increasing prevalence of adult chronic diseases such as hypertension, type 2 diabetes, metabolic syndrome and fatty liver in children and adolescents. Taking Beijing as an example, an epidemiological study covering 20,000 school-age children showed that the prevalence of metabolic syndrome in obese children and adolescents has reached nearly 30%. Obesity in childhood is not only continuous, that is, metabolic abnormalities that appear early are more likely to persist into adulthood, exacerbating the early occurrence of chronic diseases in adults, but also has a profound impact on adolescent development and bone health, and has long-term negative impacts on psychological, behavioral and cognitive abilities. Therefore, obesity prevention and control is imminent.

[0003] Further studies have shown that there is significant metabolic heterogeneity within the obese childhood group. Surprisingly, 21% to 65% of obese children, although their body mass index has reached the obesity standard, do not have metabolic abnormalities such as hypertension, hyperglycemia, hyperlipidemia or insulin resistance. These children are called "metabolic healthy obesity" (MHO). Compared with metabolic dysregulation obesity (MUO), MHO children have a lower risk of cardiovascular disease and a significantly lower risk of all-cause mortality. What's more interesting is that even if the weight is normal, it is not completely worry-free. About 30% of children with normal weight also show characteristics of cardiovascular metabolic abnormalities, namely "metabolic obesity of normal weight" (MONW), and their risk of cardiovascular metabolic diseases in the future may even be higher than that of MHO children.

[0004] Therefore, starting from childhood or even earlier developmental stages, accurately identifying those potentially high-risk children and implementing targeted intervention measures can not only correct children's metabolic imbalances in a timely manner, but is also the key to preventing the occurrence of metabolic diseases such as obesity and diabetes in adults.

[0005] Currently, there is a lack of corresponding indicators and methods for weight and obesity risk assessment. The most widely used indicator, BMI, is a common standard for measuring the degree of fatness and health of the human body. However, BMI is an outcome evaluation indicator that can only reflect the current state of the test subject and cannot predict whether the currently healthy test subject will have obesity risks in the future. In the field of adolescent weight and obesity assessment, there are large differences in the physical health of adolescents of different genders and at different growth stages, making it difficult to uniformly and effectively screen potential obese people and thus provide early warning and early intervention for early obesity weight risks.

[0006] In this regard, a Chinese invention patent with publication number CN111883248B proposes a prediction system for childhood obesity, including: a data sample collection module, which collects metabolic type data of children with different birth weights to form baseline samples of different strata; a model factor extraction module, which is used to perform omics feature tests from the metabolic type data of baseline samples of each stratum group, and extract and analyze fat factor markers and characteristic data that are respectively related to intrauterine factors and / or acquired factors to distinguish different subtypes of obesity; a model prediction construction module, which converts the screened fat factor markers and characteristic data into obesity results and their different metabolic subtype conversion results to generate a risk prediction model.

[0007] For another example, a Chinese invention patent with publication number CN111508607B proposes an obesity prediction system based on a BP neural network, including: a data acquisition module collects the fat thickness of the tester's biceps and abdomen through an ultrasonic diagnostic device to obtain the tester's physical fitness information corresponding to the fat thickness; an influencing factor screening module constructs a BP neural network, takes a training set and a reference set constructed with fat thickness and the tester's physical fitness information as input, uses a back propagation method to obtain the weight of each indicator in the training set and the reference set, and screens the indicators to obtain obesity influencing factors; a model construction and prediction module weights and reconstructs obesity influencing factors, constructs a fat thickness prediction model, predicts the fat thickness of the acquired test data, and obtains obesity prediction results based on the comparison of the fat thickness prediction value with the fat thickness threshold.

[0008] However, the problem with the above prediction methods is that they are all based on the child’s current body shape and current physical data, which is not comprehensive enough and cannot take into account issues such as parents’ genetics and whether the child already has a trend of weight gain, resulting in inaccurate and incomplete predictions. [Summary of the invention]

[0009] The purpose of the present invention is to solve the problems in the prior art and to propose a method and model for analyzing and predicting child obesity data, which can comprehensively consider factors such as the BMI change trend of children in recent years and the BMI of children's parents to give a child obesity risk prediction, and the prediction result is more accurate.

[0010] To achieve the above object, the present invention proposes a method for analyzing and predicting childhood obesity data, comprising:

[0011] Step 1: Obtain the child's current and recent N-year historical basic physical data;

[0012] Step 2: Collect the current basic physical data of the child’s immediate family members;

[0013] Step 3, processing the current and historical basic physical data of the child and the current basic physical data of the child's related immediate relatives, and calculating the current and historical BMI values ​​of the child and the BMI values ​​of the child's related immediate relatives respectively;

[0014] Step 4, arrange the children's BMI data in order by year, analyze whether the children's BMI data is in an increasing state, and record the analysis result as A3; if it is not in an increasing state or is in a decreasing state, A3 is recorded as 0; if it is in an increasing state, calculate the average annual growth rate in the past N years, and obtain the A3 value by multiplying the average annual growth rate in the past N years by the third ratio;

[0015] Step 5, analyzing whether the BMI value of the child's related immediate relatives is higher than the normal standard value, and recording the analysis result as A2. If the BMI value of the child's related immediate relatives is lower than or equal to the normal standard value, the A2 value is recorded as 0; if the BMI value of the child's related immediate relatives is higher than the normal standard value, the A2 value is obtained according to the excess amount * the second ratio;

[0016] Step 6, establish a prediction standard value, add the A2 value and the A3 value to obtain the prediction value A0, compare the A0 value with the prediction standard value, and give a result on whether the child has obesity risk based on the comparison result.

[0017] Preferably, the normal standard value for the child's related immediate relatives is 24.

[0018] Preferably, the child's related immediate relatives include the child's biological father and the child's biological mother, and the A2 value = A father + A mother;

[0019] Wherein, the A-father is the amount by which the BMI of the child's biological father exceeds the normal standard value*the second ratio;

[0020] The mother A is the child's biological mother whose BMI exceeds the normal standard value * the second ratio.

[0021] Preferably, if only one of the biological father and the biological mother of the child has a BMI exceeding the normal standard value, the second ratio is reduced to;

[0022] If the BMI of both the biological father and the biological mother of the child exceeds the normal standard value, the second ratio will be increased.

[0023] Preferably, if only one of the biological father and the biological mother of the child has a BMI exceeding the normal standard value, the second ratio is 0.2;

[0024] If the BMI of both the biological father and the biological mother of the child exceeds the normal standard value, the second ratio is 0.3.

[0025] Preferably, the third ratio in step 6 is 2.

[0026] Preferably, the prediction standard value is in the range of 4-6;

[0027] When the predicted value A0 is less than the predicted standard value interval, a low risk result of childhood obesity is given;

[0028] When the predicted value A0 is within the predicted standard value interval, a medium risk result of childhood obesity is given;

[0029] When the predicted value A0 is greater than the predicted standard value interval, a high risk result of childhood obesity is given.

[0030] Preferably, in step 1, the child's current and recent three-year historical basic physical data are obtained.

[0031] Preferably, the child's current and N-year historical basic physical data and the child's related immediate relatives' current basic physical data include height, weight, age, and gender.

[0032] Another object of the present invention is to provide a child obesity data analysis and prediction model, which is used to execute the child obesity data analysis and prediction method as described in any of the above items.

[0033] The beneficial effects of the child obesity data analysis and prediction method and model of the present invention are as follows: the present invention introduces the BMI data of children in recent years, analyzes the changes in BMI in recent years, and then combines the BMI data of the children's immediate relatives and performs a series of analysis and calculations to analyze and obtain the results of whether the children have obesity risk. The present invention fully and comprehensively considers factors such as the BMI change trend of the children in recent years and the BMI of the children's parents to give a prediction of the child's obesity risk. The prediction result is more accurate, which is convenient for timely intervention, scientific management of children's body shape, and healthy growth of children. It provides a scientific basis and effective method for preventing and controlling obesity in the Chinese population, and has significant social and economic benefits.

[0034] The features and advantages of the present invention will be described in detail through embodiments in conjunction with the accompanying drawings.

Brief Description of the Drawings

[0035] Figure 1 It is a flow chart of a method and model for analyzing and predicting childhood obesity data according to the present invention. [Specific implementation method]

[0036] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below through the accompanying drawings and embodiments. However, it should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the scope of the present invention. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0037] In the description of the present invention, it should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it may be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or indirectly connected to the other element.

[0038] In the description of the present invention, it should be noted that the terms "center", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the invention product is usually placed when in use, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. "Several" means one or more, unless otherwise clearly and specifically defined.

[0039] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0040] Embodiment 1:

[0041] See also Figure 1 The present invention provides a method for analyzing and predicting childhood obesity data, comprising:

[0042] Step 1: Obtain the child’s current and past three-year historical basic physical data, including height, weight, age, and gender;

[0043] Step 2: Collect the current basic physical data of the child's immediate family members, including height, weight, age, and gender; wherein the child's immediate family members include the child's biological father and mother;

[0044] Step 3, processing the current and historical basic physical data of the child and the current basic physical data of the child's related immediate relatives according to the BMI calculation formula, and calculating the current and historical BMI values ​​of the child and the BMI values ​​of the child's related immediate relatives respectively;

[0045] Step 4, arrange the children's BMI data in order by year, analyze whether the children's BMI data is in an increasing state, and record the analysis result as A3; if it is not in an increasing state or is in a decreasing state, A3 is recorded as 0; if it is in an increasing state, calculate the average annual growth rate in the past three years, and obtain the A3 value by multiplying the average annual growth rate in the past three years by the third ratio;

[0046] Step 5: Analyze whether the BMI value of the child's direct relatives is higher than the normal standard value, and record the analysis result as A2. If the BMI value of the child's direct relatives is lower than or equal to the normal standard value, the A2 value is recorded as 0; if the BMI value of the child's direct relatives is higher than the normal standard value, the A2 value is obtained by the excess amount * 2;

[0047] Specifically, the child's related immediate family members include the child's biological father and the child's biological mother, and the A2 value = A father + A mother;

[0048] Wherein, the A-father is the amount by which the BMI of the child's biological father exceeds the normal standard value*the second ratio;

[0049] The mother A is the amount by which the BMI of the child's biological mother exceeds the normal standard value*the second ratio;

[0050] If only one of the child's biological father and mother has a BMI that exceeds the normal standard value, the second ratio is 0.2; if the BMI of both the child's biological father and mother exceeds the normal standard value, the second ratio is 0.3.

[0051] Step 6: The predicted standard value is in the range of 4-6. The A2 value and the A3 value are added to obtain the predicted value A0. The A0 value is compared with the predicted standard value in the range of 4-6. The result of whether the child has obesity risk is given according to the comparison result.

[0052] Specifically, when the predicted value A0 is less than the predicted standard value interval, a low risk result of childhood obesity is given; when the predicted value A0 is within the predicted standard value interval, a medium risk result of childhood obesity is given;

[0053] When the predicted value A0 is greater than the predicted standard value interval, a high-risk result for childhood obesity is given. This method introduces the BMI data of children in recent years, analyzes the changes in BMI in recent years, and then combines the BMI data of children's immediate family members and performs a series of analysis and calculations to analyze whether the child has obesity risk results. It fully considers the BMI change trend of children in recent years, the BMI of children's parents and other factors to give a prediction of childhood obesity risk. The prediction results are more accurate, which is convenient for timely intervention, scientific management of children's body shape, and healthy growth of children. It provides a scientific basis and effective methods for preventing and controlling obesity in the Chinese population, and has significant social and economic benefits. The specific test results introduced are as follows:

[0054] The current and past three-year historical basic physical data of test subject 1 Zhang are as follows:

[0055] BMI 2022 BMI 2023 BMI 2024 Tester 1 Zhang 18 20 24

[0056] Then Zhang's BMI data over the years is in an increasing state, and the analysis result is recorded as A3; the average annual growth of tester 1 Zhang in the past three years is 2, and the average annual growth in the past three years is 2*2 to obtain the A3 value of 4;

[0057] The BMI value of the biological father of test subject 1, Zhang, was 29, which was 4 units higher than the normal standard value;

[0058] Test subject 1 Zhang’s biological mother’s BMI value was 23;

[0059] The BMI value of Zhang's biological father is higher than the normal standard value, and the BMI value of Zhang's biological mother is normal. Only one of the biological father and the biological mother has a BMI value higher than the normal standard value, so the second ratio is 0.2; therefore, the A2 value is 5*0.2=1;

[0060] The predicted value A0 is obtained by adding the A2 value to the A3 value, that is, the A0 value is 1+4=5, which is within the predicted standard value interval of 4-6, giving a medium risk result for childhood obesity.

[0061] The current and past three-year historical basic physical data of test subject 2, Mr. Li, are as follows:

[0062] BMI 2022 BMI 2023 BMI 2024 Tester 2: Li 19 19 19

[0063] Therefore, Zhang's BMI data over the years has not been in a growth state, and the value of A3 is 0;

[0064] Test subject 2 Li’s biological father’s BMI value is 24;

[0065] Test subject 2 Li’s biological mother’s BMI value was 23;

[0066] The BMI values ​​of Li's biological father and mother are both normal, so the A2 value is 0;

[0067] The predicted value A0 is obtained by adding the A2 value to the A3 value, that is, the A0 value is 0+0=0, which is smaller than the predicted standard value interval of 4-6, giving a low risk result for childhood obesity.

[0068] The current and past three-year historical basic physical data of test subject 3, Mr. Sun, are as follows:

[0069] BMI 2022 BMI 2023 BMI 2024 Tester 3: Sun 16 20 29

[0070] The BMI data of tester 3 Sun is in an increasing state over the years, and the analysis result is recorded as A3; the average annual growth of tester 3 Sun in the past three years is 3, and the average annual growth in the past three years is 3*2 to obtain the A3 value of 6;

[0071] Tester 3: Sun's biological father's BMI value is 26, which is 2 units higher than the normal standard value

[0072] Tester 3: Sun's biological mother's BMI is 27, which is 3 units above the normal standard.

[0073] The BMI values ​​of Zhang's biological father and mother are both higher than the normal standard value, and the BMI values ​​of the child's biological father and mother are both higher than the normal standard value, so the second ratio is 0.3; therefore, the A2 value is 5*0.3=1.5;

[0074] The predicted value A0 is obtained by adding the A2 value to the A3 value, that is, the A0 value is 6+1.5=7.5, which is larger than the predicted standard value interval of 4-6, giving a high risk result for childhood obesity.

[0075] The current and past three-year historical basic physical data of test subject 4 Niu are as follows:

[0076] BMI 2022 BMI 2023 BMI 2024 Tester 4 Niu 20 20 18

[0077] The BMI data of test subject 4 Niu Mou has been decreasing over the years, and the A3 value is 0;

[0078] Test subject 4 Niu's biological father's BMI value is 32, which is 8 units higher than the normal standard value

[0079] Test subject 4 Niu's mother's BMI value is 33, which is 9 units higher than the normal standard value

[0080] The BMI values ​​of Niu's biological father and mother are both higher than the normal standard value, and the BMI of the child's biological father and mother are both higher than the normal standard value, so the second ratio is 0.3; therefore, the A2 value is 17*0.3=5.1;

[0081] The predicted value A0 is obtained by adding the A2 value to the A3 value, that is, the A0 value is 0+5.1=5.1, which is within the range of the predicted standard value of 4-6, giving a medium risk result for childhood obesity.

[0082] The current and past three-year historical basic physical data of test subject 5 Zhu are as follows:

[0083] BMI 2022 BMI 2023 BMI 2024 Tester 4 Niu 18 20 21

[0084] Tester 5 Zhu's BMI data has been increasing over the years, and the analysis result is recorded as A3; Tester 1 Zhang's average annual growth in the past three years is 1, and the average annual growth in the past three years is 1*2 to obtain the A3 value of 2;

[0085] Tester 5 Zhu's biological father's BMI value is 22;

[0086] Test subject 5 Zhu’s biological mother’s BMI value was 21;

[0087] The BMI values ​​of the biological father and mother of test subject 5 Zhu are within the normal standard value, so the A2 value is 0;

[0088] The predicted value A0 is obtained by adding the A2 value to the A3 value, that is, the A0 value is 0+2=2, which is lower than the predicted standard value interval of 4-6, giving a low risk result for childhood obesity.

[0089] Embodiment 2:

[0090] A child obesity data analysis and prediction model, characterized in that the model is used to execute the child obesity data analysis and prediction method as described in the above embodiment. The model can predict the child's future obesity risk, facilitate timely intervention, scientific management of the child's body shape, and healthy growth of the child.

[0091] The standard parts used in this application document can all be purchased from the market, and the specific connection methods of each part adopt mature conventional means such as bolts, rivets, welding, etc. in the prior art. The electric slide rail slide, cylinder, welding machine, electric telescopic rod and internal components of the controller all adopt conventional models in the prior art, and their internal structures belong to the prior art structure. Workers can complete normal operation of them according to the existing technical manual. In addition, the circuit connection adopts the conventional connection method in the prior art, and no specific description is given here.

[0092] It should be noted that, although the above embodiments have been described in this article, the scope of patent protection of the present invention is not limited thereby. Therefore, based on the innovative concept of the present invention, changes and modifications made to the embodiments described herein, or equivalent structures or equivalent process changes made using the contents of the present specification and drawings, directly or indirectly applying the above technical solutions to other related technical fields are all included in the scope of protection of the patent of the present invention.

Claims

1. A method for analyzing and predicting childhood obesity data, It is characterized in that include: Step 1: Obtain the child's current and recent N-year historical basic physical data; Step 2: Collect the current basic physical data of the child’s immediate family members; Step 3, processing the current and historical basic physical data of the child and the current basic physical data of the child's related immediate relatives, and calculating the current and historical BMI values ​​of the child and the BMI values ​​of the child's related immediate relatives respectively; Step 4, arrange the children's BMI data in order by year, analyze whether the children's BMI data is in an increasing state, and record the analysis result as A3; if it is not in an increasing state or is in a decreasing state, A3 is recorded as 0; if it is in an increasing state, calculate the average annual growth rate in the past N years, and obtain the A3 value by multiplying the average annual growth rate in the past N years by the third ratio; Step 5, analyzing whether the BMI value of the child's related immediate relatives is higher than the normal standard value, and recording the analysis result as A2. If the BMI value of the child's related immediate relatives is lower than or equal to the normal standard value, the A2 value is recorded as 0; if the BMI value of the child's related immediate relatives is higher than the normal standard value, the A2 value is obtained according to the excess amount * the second ratio; Step 6, establish a prediction standard value, add the A2 value and the A3 value to obtain the prediction value A0, compare the A0 value with the prediction standard value, and give a result on whether the child has obesity risk based on the comparison result.

2. A method for analyzing and predicting childhood obesity data as claimed in claim 1, Features: The normal standard value for the child’s immediate relatives is 24.

3. A method for analyzing and predicting childhood obesity data as claimed in claim 1, Features: The child's related immediate family members include the child's biological father and the child's biological mother, and the A2 value = A father + A mother; Wherein, the A-father is the amount by which the BMI of the child's biological father exceeds the normal standard value*the second ratio; The mother A is the child's biological mother whose BMI exceeds the normal standard value * the second ratio.

4. A method for analyzing and predicting childhood obesity data as claimed in claim 3, Features: If only one of the biological father and the biological mother of the child has a BMI exceeding the normal standard value, the second ratio is reduced; If the BMI of both the biological father and the biological mother of the child exceeds the normal standard value, the second ratio will be increased.

5. A method for analyzing and predicting childhood obesity data as claimed in claim 4, Features: If only one of the biological father and mother has a BMI exceeding the normal standard value, the second ratio is 0.2; If the BMI of both the biological father and the biological mother of the child exceeds the normal standard value, the second ratio is 0.

3.

6. A method for analyzing and predicting childhood obesity data as claimed in claim 1, Features: In step 6, the third ratio is 2.

7. A method for analyzing and predicting childhood obesity data as claimed in claim 1, Features: The predicted standard value is between 4 and 6; When the predicted value A0 is less than the predicted standard value interval, a low risk result of childhood obesity is given; When the predicted value A0 is within the predicted standard value interval, a medium-risk result for childhood obesity is given; when the predicted value A0 is greater than the predicted standard value interval, a high-risk result for childhood obesity is given.

8. A method for analyzing and predicting childhood obesity data as claimed in claim 1, Features: In the step 1, the child's current and past three-year historical basic physical data are obtained.

9. A method for analyzing and predicting childhood obesity data as claimed in claim 1, Features: The child's current and N-year historical basic physical data and the child's related immediate relatives' current basic physical data include height, weight, age, and gender.

10. A data analysis and prediction model for childhood obesity, Features: The model is used to execute the child obesity data analysis and prediction method as described in any one of claims 1-9.

Images