Metabolic aging biological age assessment method and device based on AIP index

Abstract

The invention relates to a metabolic aging biological age assessment method and device based on an AIP index. The method comprises the following steps: carrying out source determination and preprocessing on metabolic syndrome related evaluation data; based on the preprocessed AIP index and other clinical indexes, adopting a machine learning PCA algorithm to construct a metabolic aging biological age (MS-BA) model; and calculating individual MS-BA according to the model, evaluating the health state in combination with the social age, and generating an intervention scheme. According to the method, an exclusive model is constructed for people with metabolic syndromes, and the metabolic aging degree is accurately reflected through quantitative calculation.

Description

Technical Field

[0001] This application relates to the field of metabolic aging biological age assessment technology, and in particular to a method and apparatus for metabolic aging biological age assessment based on the AIP index. Background Technology

[0002] With global economic development, increasing population aging, and changing lifestyles, the incidence of metabolic syndrome is on the rise globally, becoming a serious chronic disease threatening human health. Statistics show that the prevalence of metabolic syndrome among Chinese adults is 33.9%, reaching as high as 58.1% in people aged 60 and above, with an estimated number exceeding 450 million. Furthermore, the disease control rate is low, particularly in areas with rapid urbanization and unhealthy lifestyles. Patients with metabolic syndrome have a three times higher risk of cardiovascular and cerebrovascular diseases and a five to six times higher risk of death compared to non-patients. It also increases the incidence and mortality of type 2 diabetes, placing a heavy burden on patients, families, and society.

[0003] Currently, one of the core indicators for assessing an individual's health status and aging is biological age (BA), which more accurately reflects the degree of physiological aging than social age (CA). However, existing biological age assessment methods have significant shortcomings: First, they are mostly based on general models constructed from healthy individuals, failing to consider the accelerated aging effect of metabolic disorder patterns specific to individuals with metabolic syndrome, and thus failing to accurately reflect the "true rate of aging" in this population; second, the diagnostic criteria for metabolic syndrome (MetS) are only qualitative (whether the disease is present) or roughly stratified (meeting the required number of diagnostic criteria), lacking continuous and quantitative indicators to assess the severity of the disease and its overall impact on aging; third, there is a lack of clinically applicable assessment tools specifically for individuals with metabolic syndrome, and methods such as telomere length and epigenetic testing are costly and difficult to popularize. Therefore, there is an urgent need for a technical solution that can accurately and cost-effectively assess the biological age of metabolic aging in individuals with metabolic syndrome. Summary of the Invention

[0004] Therefore, it is necessary to provide a method and device for assessing metabolic aging biological age based on the AIP index to address the above-mentioned technical problems.

[0005] A method for assessing metabolic aging biological age based on the AIP index, the method comprising: Source identification and preprocessing of assessment data related to metabolic syndrome; Based on the pre-processed AIP index and other clinical indicators, a metabolic aging biological age model was constructed using the machine learning PCA algorithm. The individual's metabolic aging biological age is calculated based on the MS-BA model, and health assessment and intervention plans are generated by combining it with social age.

[0006] In one embodiment, the method further includes: determining that the training queue is the NHANES dataset, and the inclusion criteria are people who are older than 18 years and meet more than 3 of the 5 diagnostic criteria for metabolic syndrome, while excluding people with metabolic disorders caused by disease and people with missing demographic characteristics and major biological indicators. The core indicator was selected as the AIP index, and other clinical indicators included waist circumference, blood pressure, fasting blood glucose, triglycerides, high-density lipoprotein cholesterol, mean arterial pressure, triglyceride glucose, gender, and social age. The gender, marital status, smoking status, and drinking status of the training queue are standardized, and missing values ​​in the dataset are filled in or removed to complete the data preprocessing.

[0007] In one embodiment, the method further includes: performing a person correlation analysis on social age with core indicators and other clinical indicators, using the AIP index and other clinical indicators as model input variables; The machine learning PCA algorithm was used to estimate MS-BA. By setting the KMO and Bartlett's sphericity test to be greater than 0.8, PCA was performed with AIP index, blood pressure, waist circumference and fasting blood glucose as variables, and the factor with the highest eigenvalue was determined as the principal component. Based on the PCA results of the AIP index and other biomarkers, the BA score corresponding to the first principal component was obtained as an indicator of health and aging status. A regression model was then constructed using selected biomarkers as independent variables, yielding MS-BA=f. Based on biological age theory, social age was used as the target variable, and the equation Y=BA+Z was applied, where Z=(Y-Ymean)×(1-b), Ymean is the social average age, b is the slope of the regression model, and Y is the social age. MS-BA was then corrected to complete the model construction. Biomarkers for men and women were selected based on person-to-person correlation analysis and the differences in biomarkers between genders.

[0008] In one embodiment, it further includes: for males: The calculation rule for MS-BA is: a1 + a2 × AIP + a3 × SBP + a4 × DBP + a5 × WC + a6 × AGE + a7 × FBS; where a1 is a negative value, and a2, a3, a4, a5, a6, and a7 are positive values. For women: The calculation rule for MS-BA is: b1+b2×AIP+b3×WC+b4×SBP+b5×DBP+b6×FBS+b7×AGE, where b1 is a negative value and b2, b3, b4, b5, b6, and b7 are positive values.

[0009] In one embodiment, it further includes: when MS-BA > CA, it prompts that the individual's metabolic biological age is faster than the social age, and the aging risk related to metabolic syndrome is high; when MS-BA < CA, it prompts that the individual's metabolic status is better than the actual age, and the existing lifestyle or health intervention is effective; when MS-BA = CA, it prompts that the individual's aging rate conforms to the current social age level.

[0010] In one embodiment, the intervention plan includes at least one of an exercise plan, a diet plan, and a sleep plan.

[0011] A metabolic aging biological age assessment device based on the AIP index, the device includes: A data processing module for determining the source and preprocessing the assessment data related to metabolic syndrome; A model construction module for constructing a metabolic aging biological age model using the machine learning PCA algorithm based on the preprocessed AIP index and other clinical indicators; An age prediction module for calculating the individual's metabolic aging biological age according to the MS-BA model, and generating a health assessment and intervention plan in combination with the social age.

[0012] In one embodiment, the data processing module is further used to determine that the source of the training cohort is the NHANES dataset, the inclusion criteria are people over 18 years old and meeting more than 3 abnormalities in 5 diagnostic criteria for metabolic syndrome, excluding people with metabolic disorders caused by diseases and people with missing demographic characteristics and major biological indicators; Select the core index as the AIP index, and at the same time select other clinical indicators including waist circumference, blood pressure, fasting blood glucose, triglycerides, high-density lipoprotein cholesterol, mean arterial pressure, triglyceride glucose, gender, and social age; Standardize the gender, marital status, smoking status, and drinking status of the training cohort, and complete or eliminate the missing values in the dataset to complete the data preprocessing.

[0013] A computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: Determine the source and preprocess the assessment data related to metabolic syndrome; Construct a metabolic aging biological age model using the machine learning PCA algorithm based on the preprocessed AIP index and other clinical indicators; Calculate the individual's metabolic aging biological age according to the MS-BA model, and generate a health assessment and intervention plan in combination with the social age.

[0014] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Source identification and preprocessing of assessment data related to metabolic syndrome; Based on the pre-processed AIP index and other clinical indicators, a metabolic aging biological age model was constructed using the machine learning PCA algorithm. The individual's metabolic aging biological age is calculated based on the MS-BA model, and health assessment and intervention plans are generated by combining it with social age.

[0015] The aforementioned method and device for assessing metabolic aging based on the AIP index, by using the AIP index as the core indicator and constructing a dedicated MS-BA model for people with metabolic syndrome, solves the problem of insufficient targeting of existing methods; it adopts the PCA algorithm and quantitative calculation to achieve continuous quantitative assessment of the degree of metabolic aging, breaking through the limitations of traditional qualitative stratification; at the same time, it avoids high-cost technologies such as telomere detection, reducing application costs, and can combine lifestyle to generate intervention plans, providing a precise and practical tool for the health management of people with metabolic syndrome. Attached Figure Description

[0016] Figure 1 This is an application scenario diagram of a metabolic aging biological age assessment method based on the AIP index in one embodiment; Figure 2 This is a flowchart illustrating a metabolic aging biological age assessment method based on the AIP index in one embodiment. Figure 3 This is a structural block diagram of a metabolic aging biological age assessment device based on the AIP index in one embodiment; Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] The metabolic aging biological age assessment method based on the AIP index provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal device 102 (such as a doctor's workstation or a user health management APP) communicates with server 104 (a cloud server or local medical server deploying the MS-BA model) via a network. The terminal device inputs the user's physical examination data (AIP index, waist circumference, blood pressure, etc.). After receiving the data, the server performs data preprocessing and model calculations, and then feeds back the MS-BA results and intervention plan to the terminal device. The terminal device can be a personal computer, laptop, smartphone, tablet, etc., and the server can be a standalone server or a cluster of multiple servers.

[0019] In one embodiment, such as Figure 2 As shown, a method for assessing metabolic aging biological age based on the AIP index is provided, and this method is applied to... Figure 1 Taking the server in the example, the following steps are included: Step 202: Identify the source and preprocess the assessment data related to metabolic syndrome.

[0020] Step 204: Based on the preprocessed AIP index and other clinical indicators, a metabolic aging biological age model is constructed using the PCA machine learning algorithm.

[0021] Step 206: Calculate the individual's metabolic aging biological age based on the MS-BA model, and combine it with social age to generate a health assessment and intervention plan.

[0022] The aforementioned bio-age assessment method for metabolic aging based on the AIP index addresses the lack of specificity in existing methods by constructing a dedicated MS-BA model for individuals with metabolic syndrome using the AIP index as the core indicator. Employing the PCA algorithm and quantitative calculations, it achieves continuous quantitative assessment of the degree of metabolic aging, overcoming the limitations of traditional qualitative stratification. Furthermore, it avoids the use of expensive technologies such as telomere detection, reducing application costs, and can be combined with lifestyle modifications to generate intervention plans, providing a precise and practical tool for health management of individuals with metabolic syndrome.

[0023] In one embodiment, for step 202, the training queue is determined to be from the NHANES dataset. The inclusion criteria are individuals older than 18 years who meet more than three of the five diagnostic criteria for metabolic syndrome. Individuals with metabolic disorders caused by disease, or those lacking demographic characteristics or key biological indicators, are excluded. The core indicator is the AIP index, and other clinical indicators include waist circumference, blood pressure, fasting blood glucose, triglycerides, high-density lipoprotein cholesterol, mean arterial pressure, triglyceride glucose, gender, and social age. The gender, marital status, smoking status, and alcohol consumption of the training queue are standardized, and missing values ​​in the dataset are either filled in or removed, completing the data preprocessing. In this embodiment, rigorous sample selection and data standardization ensure the accuracy and relevance of the subsequent model input data, laying the foundation for accurate modeling.

[0024] The formula for calculating AIP is as follows:

[0025] AIP stands for Atherosclerosis Index. This indicates the concentration of triglycerides. The concentration of high-density lipoprotein cholesterol is expressed; The calculation method for triglycerides and glucose is as follows:

[0026] In one embodiment, for step 204, a person correlation analysis is performed on social age, core indicators, and other clinical indicators. The AIP index and other clinical indicators are used as input variables for the model. The machine learning PCA algorithm is used to estimate MS-BA. By setting the KMO and Bartlett's sphericity test to be greater than 0.8, PCA is performed with AIP index, blood pressure, waist circumference, and fasting blood glucose as variables. The factor with the highest eigenvalue is determined as the principal component. Based on the PCA results of AIP index and other biomarkers, the BA score corresponding to the first principal component is obtained as an indicator of health and aging status. Then, a regression model is constructed with selected biomarkers as independent variables to obtain MS-BA=f. According to the biological age theory, social age is used as the target variable and the equation Y=BA+Z is used to correct MS-BA, thus completing the model construction.

[0027] Specifically, the person correlation analysis is performed using SPSS software, and the indicators with a correlation coefficient |r| > 0.3 with social age are selected as input variables, while weakly correlated indicators are excluded to reduce interference. PCA is performed through the sklearn library in Python, and the n_components parameter is set to automatically select the principal components, ensuring that the cumulative variance explanation rate of the principal components > 80%. A linear regression model is used to construct the MS-BA prediction model, with the principal component scores as independent variables and social age as the dependent variable for training, and then corrected by the Dubina theory to make the mean BA of individuals of the same age predicted by the model coincide with the social age at the regression center. This implementation method improves the model construction efficiency and prediction accuracy through software tools and parameter optimization.

[0028] In one embodiment, for step 206, for men: The calculation rule of MS-BA is: a1 + a2×AIP + a3×SBP + a4×DBP + a5×WC + a6×AGE + a7×FBS; where a1 is negative, and a2, a3, a4, a5, a6, a7 are positive; For women: The calculation rule of MS-BA is: b1 + b2×AIP + b3×WC + b4×SBP + b5×DBP + b6×FBS + b7×AGE, where b1 is negative, and b2, b3, b4, b5, b6, b7 are positive.

[0029] In one embodiment, the health assessment rule is: when MS-BA > CA, it indicates that the individual's metabolic biological age is faster than the social age, and the aging risk related to metabolic syndrome is high; when MS-BA < CA, it indicates that the individual's metabolic status is better than the actual age, and the existing lifestyle or health intervention is effective; when MS-BA = CA, it indicates that the individual's aging speed conforms to the current social age level.

[0030] In one embodiment, the intervention plan includes at least one of an exercise plan, a diet plan, and a sleep plan.

[0031] It should be understood that although Figure 2 the steps in the flowchart of Figure 2At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0032] In one embodiment, such as Figure 3 As shown, a metabolic aging biological age assessment device based on the AIP index is provided, including: a data processing module 302, a model building module 304, and an age prediction module 306, wherein: Data processing module 302 is used to determine the source and preprocess metabolic syndrome-related assessment data; Model building module 304 is used to construct a metabolic aging biological age model based on the preprocessed AIP index and other clinical indicators using the machine learning PCA algorithm. The age prediction module 306 is used to calculate an individual's metabolic aging biological age based on the MS-BA model, and to generate a health assessment and intervention plan by combining it with social age.

[0033] Specific limitations regarding the AIP-based metabolic aging biological age assessment device can be found in the above-mentioned limitations on the AIP-based metabolic aging biological age assessment method, and will not be repeated here. Each module in the aforementioned AIP-based metabolic aging biological age assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0034] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores NHANES training cohort data, individual physical examination data, MS-BA model parameters, and intervention protocol library data. The network interface communicates with external terminals via a network connection, receives individual data sent by the terminals, and provides feedback on MS-BA assessment results. When executed by the processor, the computer program implements a metabolic aging biological age assessment method based on the AIP index.

[0035] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0036] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described above.

[0037] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0038] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0039] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0040] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for assessing metabolic aging biological age based on the AIP index, characterized in that, The method includes: Source identification and preprocessing of assessment data related to metabolic syndrome; Based on the pre-processed AIP index and other clinical indicators, a metabolic aging biological age model was constructed using the machine learning PCA algorithm. The individual's metabolic aging biological age is calculated based on the MS-BA model, and health assessment and intervention plans are generated by combining it with social age.

2. The method according to claim 1, characterized in that, The process of identifying the source and preprocessing metabolic syndrome-related assessment data includes: The training cohort was determined to be from the NHANES dataset. The inclusion criteria were individuals older than 18 years who met more than 3 of the 5 diagnostic criteria for metabolic syndrome. Individuals with metabolic disorders caused by disease and those with missing demographic characteristics or major biological indicators were excluded. The core indicator was selected as the AIP index, and other clinical indicators included waist circumference, blood pressure, fasting blood glucose, triglycerides, high-density lipoprotein cholesterol, mean arterial pressure, triglyceride glucose, gender, and social age. The gender, marital status, smoking status, and drinking status of the training queue are standardized, and missing values ​​in the dataset are filled in or removed to complete the data preprocessing.

3. The method according to claim 1, characterized in that, The metabolic aging biological age model, constructed using the PCA algorithm based on the preprocessed AIP index and other clinical indicators, includes: Person correlation analysis was performed on social age with core indicators and other clinical indicators, and AIP index and other clinical indicators were used as input variables for the model. The machine learning PCA algorithm was used to estimate MS-BA. By setting the KMO and Bartlett's sphericity test to be greater than 0.8, PCA was performed with AIP index, blood pressure, waist circumference and fasting blood glucose as variables, and the factor with the highest eigenvalue was determined as the principal component. Based on the PCA results of the AIP index and other biomarkers, the BA score corresponding to the first principal component was obtained as an indicator of health and aging status. Then, a regression model was constructed with selected biomarkers as independent variables, resulting in MS-BA=f. According to the biological age theory, social age was used as the target variable through the equation Y=BA+Z, where Z=(Y-Ymean)×(1-b), Ymean is the social average age, b is the slope of the regression model, and Y is the social age. MS-BA was then corrected to complete the model construction.

4. The method according to any one of claims 1 to 3, characterized in that, The individual's metabolic aging biological age is calculated based on the MS-BA model, including: For men: The calculation rule for MS-BA is: a1 + a2 × AIP + a3 × SBP + a4 × DBP + a5 × WC + a6 × AGE + a7 × FBS; where a1 is a negative value, and a2, a3, a4, a5, a6, and a7 are positive values. For women: The calculation rule for MS-BA is: b1+b2×AIP+b3×WC+b4×SBP+b5×DBP+b6×FBS+b7×AGE, where b1 is a negative value and b2, b3, b4, b5, b6, and b7 are positive values.

5. The method according to claim 4, characterized in that, The health assessment rules are as follows: When MS-BA > CA, it indicates that the individual's metabolic biological age is faster than the social age, and the aging risk related to metabolic syndrome is high; when MS-BA < CA, it indicates that the individual's metabolic status is better than the actual age, and the existing lifestyle or health intervention is effective; When MS-BA = CA, it indicates that the individual's aging rate conforms to the current social age level.

6. The method according to claim 1, characterized in that, The intervention plan includes at least one of an exercise plan, a diet plan, and a sleep plan.

7. A metabolic aging biological age assessment device based on the AIP index, characterized in that, The device includes: A data processing module for determining the source and preprocessing the assessment data related to metabolic syndrome; A model construction module for constructing a metabolic aging biological age model using the machine learning PCA algorithm based on the preprocessed AIP index and other clinical indicators; An age prediction module for calculating the individual's metabolic aging biological age according to the MS-BA model and generating a health assessment and intervention plan in combination with the social age.

8. The apparatus according to claim 7, characterized in that, The data processing module is further used to determine that the source of the training cohort is the NHANES dataset, and the inclusion criteria are people over 18 years old and meeting more than 3 abnormalities among the 5 diagnostic criteria for metabolic syndrome, excluding people with metabolic disorders caused by diseases and people with missing demographic characteristics and main biological indicators; The core index is selected as the AIP index, and other clinical indicators are also selected, including waist circumference, blood pressure, fasting blood glucose, triglyceride, high-density lipoprotein cholesterol, mean arterial pressure, triglyceride glucose, gender, and social age; Standardize the gender, marital status, smoking status, and drinking status of the training cohort, and complete or remove the missing values in the dataset to complete the data preprocessing.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method described in any one of claims 1 to 6.

Images