Age estimation method based on phenotypic data

Abstract

The invention relates to an age estimation method based on phenotypic data, in particular to a data set establishing method, an age estimation model training method, an age estimation method, an age estimation model or device, electronic equipment, a nonvolatile computer readable storage medium and application thereof. The method can more accurately estimate the age of Asian people, especially the age of East Asia or Southeast Asia, and can be used for evaluating senescence-related information.

Description

Technical Field

[0001] The present invention relates to the field of biomedicine, and in particular to an age estimation method based on phenotypic data. Background Art

[0002] In recent years, population aging has gradually become an increasingly serious social problem facing the world. The continuous aggravation of the problem of population aging will bring huge challenges to the development of a series of fields in my country, such as medical care, social security, pension, and economy. How to delay aging and promote the health and longevity of the elderly is a necessary condition to ensure social stability and prosperity and sustainable economic development, and a reliable aging rate quantification system is a decisive prerequisite for evaluating the effectiveness of aging intervention measures. Aging is a highly heterogeneous process both in the population and within individuals, and has no absolute correlation with chronological age (i.e., the year from birth to the time of recording), that is, the biological age of humans is not equal to the chronological age. Therefore, the accurate assessment of the aging rate has become an emerging key scientific issue in aging research.

[0003] At present, the methods based on clinical detection indicators to indicate physiological age can be roughly divided into two categories: 1) single phenotypic aging markers; 2) the combined use of multiple markers to establish a prediction model. There are many studies on the assessment of aging rate by single phenotypic aging markers, but this method has low accuracy in heterogeneous populations. [1,2] The phenotypic age prediction model based on multiple phenotypic markers was first proposed by Steve Horvath's team at the University of California, Los Angeles in 2018. The phenotypic age model is a mathematical model established for 9 blood routine test indicators, which can predict biological age. [3] . This study first used the clinical test and living habits data of nearly 10,000 people from the third National Health and Nutrition Survey of the United States, screened 42 of the most commonly used clinical test indicators, and finally selected 9 blood routine test indicators with high age correlation, including albumin, creatinine, glucose (serum), C-reactive protein, lymphocyte percentage, mean cell volume, red blood cell distribution width, alkaline phosphatase and white blood cell count, and verified it with data from more than 6,000 people from the fourth National Health and Nutrition Survey of the United States. However, the above model parameters are based on population data from European and American countries, and aging may be affected by environmental, ethnic and other factors, resulting in different aging rates and aging-sensitive parameters among different populations. If the existing model is directly applied to the Asian population, it may affect the accuracy of the prediction results. Secondly, the information used to establish the prediction model is single, and aging cannot be evaluated from multiple perspectives at the same time, which has certain limitations. For example, the phenotypic age prediction model developed in 2018 only uses 9 marker parameters, and the original parameters are only 42. Therefore, a new set of accurate biological age calculation models for Asian populations is very important. Summary of the invention

[0004] The present invention establishes an age estimation method by collecting, processing and screening clinical test data and mobility-related data of people of different age groups. The method can be used to estimate the biological age of an individual, measure the degree of physiological aging of an individual, evaluate the aging rate, evaluate the effect of aging intervention and predict the risk of aging-related diseases.

[0005] In a first aspect, the present invention provides a method for establishing a data set, comprising:

[0006] (1) performing clinical phenotype testing on multiple subjects to obtain a clinical phenotype measurement data set;

[0007] (2) Using age as a training label, the dataset is constructed for training an age estimation model.

[0008] In some embodiments, the clinical phenotype test data are divided into seven categories indicating mobility, lipids, hormones, blood component content, blood cells, body measurements and tissue function (e.g., lung, cardiovascular, muscle, kidney, liver, eye and bone).

[0009] In some embodiments, the clinical phenotype detection includes physical examination, for example, general examination, internal medicine examination, surgical examination, B-ultrasound examination, body composition analysis, blood routine, glycosylated hemoglobin, six items of sex hormones, urine routine, stool routine, lung function test, bone density test, electrocardiogram and biochemical analysis, as listed in Table 2; preferably, the clinical phenotype detection also includes mobility test, for example, single-leg standing, grip strength, 30-second sit-stand test, Purdue pegboard test and stepping test.

[0010] The above-mentioned partial clinical phenotype detection objects are the subject's blood, urine, feces, etc. Therefore, in some embodiments, before performing the clinical phenotype detection, a step of collecting a biological sample of the subject is also included. In some embodiments, the biological sample is selected from blood (e.g., whole blood, plasma or serum), urine, and feces.

[0011] In some embodiments, before step (2), the method further includes performing a correlation analysis between the clinical phenotype measurement dataset and age to screen for age-related features.

[0012] In some embodiments, the clinical phenotype measurement dataset is subjected to a Pearson correlation analysis with age, with BMI used as a covariate, the P value is corrected by the BH method, and the result with P<0.05 is selected as the age-related feature.

[0013] The results showed that 32 parameters in the clinical phenotype measurement data set of the present invention were positively correlated with age, such as waist-to-hip ratio, visceral fat level, waist circumference, body fat rate, cholesterol, etc., which are related to body fat distribution and lipid metabolism; 54 parameters were negatively correlated with age, such as bone density and lung function related parameters. The results were screened, and only the results with BH corrected P value less than 0.05 were selected as age-related phenotypic parameters. The indicators that increased with age included a variety of fat and lipid related parameters, such as waist-to-hip ratio, visceral fat level, cholesterol and body fat rate, etc. The indicators that decreased with age were mainly related to lung function and bone density related parameters. In addition, the levels of multiple hormones also changed dramatically with age, including increased follicle-stimulating hormone, luteinizing hormone, and reduced anti-Mullerian hormone.

[0014] In some embodiments, the age-related characteristics are selected from height, body composition test-left upper limb (value), body composition test-left upper limb (ECW / TBW), body composition test-right upper limb (ECW / TBW), waist-to-hip ratio, lung function-VCMAX, lung function-FEV1, lung function-MEF 25, lung function-FEV1*30, pulse, glycosylated hemoglobin, systolic blood pressure, blood glucose, alanine aminotransferase, alkaline phosphatase, globulin, urea, triglycerides, cholesterol, lactate dehydrogenase, apolipoprotein A and anti-Mullerian hormone.

[0015] In some embodiments, the dataset is split into a training set and a test set, for example, in a 1:1 ratio.

[0016] In some embodiments, the subjects are Asian (eg, East Asian or Southeast Asian), such as Chinese; preferably, the subjects are ≥100, eg, ≥500, ≥1000, or ≥10000.

[0017] In some embodiments, the subject is over 18 years old, preferably 18-70 years old. In some embodiments, the subject age distribution is balanced. In some embodiments, the difference in the number of subjects in each age group (for example, divided into 18-44 years old age group, 45-59 years old age group and 60 years old age group) is less than 50%, less than 40%, less than 30%, less than 20%, less than 10%, less than 5% or less than 2%.

[0018] In a second aspect, the present invention provides an age estimation model training method, comprising:

[0019] (1) establishing a data set according to any method described in the first aspect;

[0020] (2) estimating the age of the subject corresponding to the data using the age estimation model according to the data set;

[0021] (3) Training the age estimation model based on the difference between the estimation result and the age label of the data.

[0022] In some embodiments, the training is performed using the glmnet package (version 4.1.4). In some embodiments, the alpha value in the glamnet is selected from 0.1-0.9, for example, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8 or 0.9.

[0023] In some embodiments, the estimated age y of the subject can be calculated by the following formula:

[0024] A x represents the age-related features in the dataset, a x Represents the corresponding A x The coefficient of , b represents a constant (i.e., the intercept mentioned in this article);

[0025] Through the training, each age-related feature A can be determined x The coefficient a x and the constant b.

[0026] In some embodiments, the age-related characteristics are selected from height, body composition test-left upper limb (value), body composition test-left upper limb (ECW / TBW), body composition test-right upper limb (ECW / TBW), waist-to-hip ratio, lung function-VC MAX, lung function-FEV 1, lung function-MEF 25, lung function-FEV 1*30, pulse, glycosylated hemoglobin, systolic blood pressure, blood glucose, alanine aminotransferase, alkaline phosphatase, globulin, urea, triglycerides, cholesterol, lactate dehydrogenase, apolipoprotein A and anti-Mullerian hormone.

[0027] In some embodiments, the coefficient a and the constant b of each age-related feature in the age estimation model are:

[0028]

[0029]

[0030] In a third aspect, the present invention provides an age estimation model, which is trained by the method described in any one of the second aspects.

[0031] In a fourth aspect, the present invention provides an age estimation device, comprising:

[0032] An input unit, used for inputting age-related characteristics of the subject, wherein the age-related characteristics are as defined in any one of the second aspect;

[0033] An estimation unit, configured to calculate the estimated age of the subject according to the input age-related features using the age estimation model described in the third aspect;

[0034] and an optional output unit for outputting the estimated age of the subject.

[0035] In a fifth aspect, the present invention provides an age estimation method, comprising:

[0036] Providing a subject with age-related characteristics, wherein the age-related characteristics are as defined in any one of the second aspect;

[0037] The age-related features are input into the age estimation model described in any one of the third aspect or the age estimation device described in any one of the fourth aspect to estimate the age of the subject.

[0038] For the clinical phenotype measurement data, the units can refer to those listed in Table 2 of the Examples.

[0039] In a sixth aspect, the present invention provides an electronic device, comprising:

[0040] Memory; and

[0041] A processor coupled to the memory, the processor being configured to execute, based on instructions stored in the memory, the training method for the age estimation model described in any one of the second aspects, or the age estimation method described in any one of the fifth aspects.

[0042] In a seventh aspect, the present invention provides a non-volatile computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the training method for the age estimation model described in any one of the second aspect, or the age estimation method described in any one of the fifth aspect.

[0043] In an eighth aspect, the present invention provides a method for establishing a data set according to any one of the first aspect, a training method for an age estimation model according to any one of the second aspect, an age estimation model according to any one of the third aspect, an age estimation device according to any one of the fourth aspect, an age estimation method according to any one of the fifth aspect, an electronic device according to any one of the sixth aspect, or a non-volatile computer-readable storage medium according to any one of the seventh aspect, in the preparation of a kit, wherein the kit is used for one or more of the following:

[0044] 1) Estimate the age of the subjects;

[0045] 2) Evaluate the aging rate or degree of the subjects;

[0046] 3) Evaluate the effectiveness of aging interventions;

[0047] 4) Assess the risk of aging-related diseases;

[0048] 5) Evaluate or assist in evaluating the therapeutic effects of aging-related diseases.

[0049] The aging-related diseases described in the present invention are selected from cardiovascular diseases (such as hypertension, coronary heart disease, heart failure or stroke), neurodegenerative diseases (such as Alzheimer's disease or Parkinson's disease), diabetes, chronic obstructive pulmonary disease, etc.

[0050] Definition of terms

[0051] In the present invention, unless otherwise specified, the scientific and technical terms used herein have the meanings commonly understood by those skilled in the art. In addition, the molecular genetics, nucleic acid chemistry, immunology, and bioinformatics laboratory operation steps used herein are conventional steps widely used in the corresponding fields. At the same time, in order to better understand the present invention, the definitions and explanations of the relevant terms are provided below.

[0052] As used herein, the term "aging" has the meaning commonly understood by those skilled in the art, and is a common biological phenomenon in the growth and development of the body. Aging can be considered as a process of body function decline accompanied by aging, which is usually accompanied by a continuous decline in physical health and an increase in the risk of aging-related diseases, functional disorders and death.

[0053] As used herein, the term "aging-related diseases" refers to aging-related diseases whose risk of occurrence increases significantly with aging of the body. In certain embodiments, the aging-related diseases include, but are not limited to, neurodegenerative diseases (such as Alzheimer's disease), diabetes, heart disease, cardiovascular and cerebrovascular diseases, hypertension, hyperlipidemia, osteoporosis, osteoarthritis, chronic kidney disease, cancer, and vision loss. In certain embodiments, the aging-related diseases are cardiovascular diseases, neurodegenerative diseases, diabetes, or chronic obstructive pulmonary disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 :The process of establishing phenotypic age model.

[0055] Figure 2 : Classification of phenotypic parameter functional annotations, which are divided into 7 categories: mobility, lipids, hormones, blood component content, blood cells, body measurements and tissue function (e.g., lung, cardiovascular, muscle, kidney, liver, eye, bone). The final number of parameters is in brackets.

[0056] Figure 3 : Phenotypic parameters up- and down-regulated with age identified by correlation analysis.

[0057] Figure 4: The phenotypic age prediction model (R is the Pearson correlation coefficient, MAE is the mean absolute error value), the correlation coefficient between the predicted age and the actual age is 0.88 (with BMI as a covariate), the average absolute error is 4.76 years, and it has high accuracy. DETAILED DESCRIPTION

[0058] The embodiments of the present invention will be described in detail below in conjunction with the examples, but those skilled in the art will appreciate that the following examples are only used to illustrate the present invention and should not be considered to limit the scope of the present invention. If no specific conditions are specified in the examples, they are carried out according to normal conditions or the conditions recommended by the manufacturer. If the manufacturer is not specified for the reagents or instruments used, they are all conventional products that can be obtained commercially.

[0059] The main implementation route of the present invention involves cohort establishment, phenotypic parameter collection (physical examination, mobility testing), data processing and model establishment ( Figure 1 ).

[0060] Example 1: Queue establishment

[0061] The "Preliminary Screening Questionnaire" was published through the WeChat Mini Program to collect basic information of potential volunteers who are interested in joining this study based on the inclusion criteria, and to screen volunteers who meet the inclusion criteria; the inclusion criteria are as follows:

[0062] 1) Enrollment conditions

[0063] a) Aged 18 or above, with no major bad habits;

[0064] b) The applicant is in good health and has not undergone any major surgery within the past six months. Routine conditions related to the normal aging process are permitted, including:

[0065] i. Hypertension, well controlled (taking no more than 3 medications);

[0066] ii. Osteoporosis, osteopenia and / or osteoarthritis;

[0067] iii. Benign prostatic hypertrophy;

[0068] iv. Cataract, glaucoma, macular degeneration;

[0069] v.Dyslipidemia;

[0070] vi. Hypothyroidism;

[0071] vii. Prediabetes or abnormal fasting blood sugar (fasting blood sugar 100-126 mg / dL).

[0072] c) The subjects can communicate well with the researchers and cooperate with all tasks during the study;

[0073] i. Subjects must voluntarily sign a written informed consent.

[0074] 2) Exclusion criteria

[0075] a) Age does not meet the inclusion criteria;

[0076] b) Participants are currently undergoing other clinical trials or are receiving any research drugs or devices for treatment within 30 days prior to enrollment;

[0077] c) The investigator reports a history or current diagnosis of significant chronic medical conditions, including:

[0078] i. Any cancer (except polycythemia vera, basal cell or squamous cell skin cancer);

[0079] ii. Coronary artery disease / myocardial infarction / clinically significant congestive heart failure;

[0080] iii. Stroke / transient ischemic attack;

[0081] iv. Deep vein thrombosis / pulmonary embolism;

[0082] v. Serum creatinine>1.5mg / dl (male);

[0083] vi. poorly controlled hypertension (significant hypertension (systolic blood pressure > 160 mmHg, or diastolic blood pressure > 100 mmHg) despite treatment);

[0084] vii. History of active liver disease or metabolic acidosis;

[0085] viii. Chronic kidney disease / hemodialysis treatment, history of severe renal damage and / or eGFR≤45ml / min / 1.73m2;

[0086] ix. Severe autoimmune / inflammatory diseases, such as rheumatoid arthritis, lupus, Crohn's disease, etc.;

[0087] x. Neurological diseases such as dementia, such as Alzheimer's / Parkinson's, etc.;

[0088] xi. Diabetes (hemoglobin A1C>6.5% or fasting blood glucose>126 mg / dL or taking diabetes medication or insulin treatment);

[0089] xii. Recent (within 3 months) cardiovascular disease events (myocardial infarction, coronary artery intervention, coronary artery bypass grafting);

[0090] xiii. Infectious diseases such as HIV, hepatitis, tuberculosis, etc.

[0091] d) Currently taking the following medications regularly:

[0092] i. Chemotherapy drugs (such as tamoxifen, doxorubicin, mitoxantrone, bleomycin);

[0093] ii. Antiplatelet drugs (e.g. clopidogrel / Plavix, dipyridamole / Angeleno, ticlopidine / Ticlopidine, excluding aspirin);

[0094] iii. Cholinesterase inhibitors for Alzheimer's disease (donepezil / alicept).

[0095] e) Continuous alcohol or drug abuse;

[0096] f) Unable to provide informed consent;

[0097] g) The researcher believes that the physical factors of the participants may have an adverse effect on the research process or results.

[0098] 3) Termination criteria

[0099] a) Failure to follow the diet, work and rest schedule and physical examination requirements in accordance with the research content;

[0100] b) Experiencing abnormal physical conditions such as colds or fever during the study;

[0101] c) Accidental injury or physical discomfort during the research process;

[0102] d) Comply with the subject’s subjective wishes to terminate the program.

[0103] All volunteers who meet the inclusion criteria and are confirmed to be included in the group signed an informed consent form and joined the volunteer WeChat group for management and information communication. Within one month before the start of the project, volunteers need to maintain a normal schedule, eat a proper diet, avoid strenuous exercise, and refrain from excessive smoking or drinking. The day before the project, volunteers received a unified standardized diet (menu see Table 1) at the implementation hospital and were no longer allowed to eat other foods.

[0104] On the day of sample collection and physical examination, volunteers are required to wear clothes and shoes that are convenient for movement, are not allowed to wear makeup, and must bring identification documents (such as ID cards, etc.) to the hospital for physical examination and biological sample collection.

[0105] Table 1 Unified standardized diet menu

[0106]

[0107] Example 2: Phenotypic parameter collection

[0108] Phenotypic parameters include 180 parameters in 7 categories, including mobility, lipids, hormones, blood component content, blood cells, body measurements, and tissue function (lung, cardiovascular, muscle, kidney, liver, eye, bone). Figure 2).

[0109] 1. Physical examination

[0110] The physical examination included general examination, internal medicine examination, surgical examination, B-ultrasound examination, body composition analysis, blood routine test, glycosylated hemoglobin, six items of sex hormones, urine routine test, stool routine test, lung function test, bone density test, electrocardiogram and biochemical analysis. The specific indicators are shown in Table 2.

[0111] Table 2 Detailed indicators of physical examination

[0112]

[0113]

[0114]

[0115]

[0116]

[0117]

[0118]

[0119]

[0120]

[0121]

[0122]

[0123]

[0124]

[0125]

[0126] 2. Mobility test

[0127]

[0128] Example 3. Data processing and model building 1. Analysis of age correlation of phenotypic parameters.

[0129] a) after collecting all the measurement data in Example 2, summarizing the data to obtain a two-dimensional phenotypic parameter matrix of individual-measurement parameters;

[0130] b) Perform age-related analysis on the phenotypic parameters obtained in a), that is, perform Pearson correlation analysis on the value of each parameter and the individual's age, and use BMI as a covariate. Among them, 32 parameters are positively correlated with age, such as waist-to-hip ratio, visceral fat level, waist circumference, body fat percentage, cholesterol, etc., which are related to body fat distribution and lipid metabolism; 54 parameters are negatively correlated with age, such as bone density, lung function-related parameters ( Figure 2 );

[0131] c) The results were screened and only the results with a BH-corrected P value less than 0.05 were selected as age-related phenotypic parameters. The results showed that the indicators that increased with age included a variety of fat and lipid-related parameters, such as waist-to-hip ratio, visceral fat level, cholesterol, and body fat percentage, while the indicators that decreased with age were mainly related to lung function and bone density. In addition, the levels of multiple hormones also changed dramatically with age, including increased follicle-stimulating hormone and luteinizing hormone, and decreased anti-Mullerian hormone ( Figure 3 ).

[0132] 2. Establishment of phenotypic age model.

[0133] a) First, the phenotypic parameter matrix is ​​screened for features, and only age-related parameters are retained;

[0134] b) splitting the screened phenotypic parameter matrix according to the 1:1 training and test sets randomly assigned in advance;

[0135] c) Age was used as the training label and the glmnet package (version 4.1.4) was used to build the model. Nine alpha values ​​between 0.1 and 0.9 were used for modeling and tested in the test set. Finally, the alpha with the highest accuracy was selected as the parameter of the final model. The final alpha value was 0.1. The final model is shown in Table 3.

[0136] Table 3. Phenotypic age model

[0137]

[0138]

[0139] 3. Evaluation of the phenotypic age model

[0140] The final model was applied to the test set to obtain the predicted age of the individuals in the test set and compared with their corresponding actual age. The results showed that the correlation coefficient between the predicted age and the actual age reached 0.88 (Pearson correlation, with BMI as a covariate), and the average absolute error was 4.76 years, which was highly accurate ( Figure 4 ).

[0141] [1]Belsky DW, Caspi A, Houts R, et al. Quantification of biological aging in young adults. Proc Natl Acad Sci USA 2015;112:E4104-4110.

[0142] [2] Sebastiani P, Thyagarajan B, Sun F, et al. Biomarker signatures ofaging. Aging Cell 2017;16:329-338.

[0143] [3] Levine ME, Lu AT, Quach A, et al. An epigenetic biomarker of aging for lifespan and healthspan. Aging (Albany NY) 2018; 10:573-591.

[0144] Although the specific embodiments of the present invention have been described in detail, it will be understood by those skilled in the art that various modifications and substitutions may be made to those details based on all the teachings disclosed, and these changes are within the scope of protection of the present invention. The full scope of the present invention is given by the attached claims and any equivalents thereof.

Claims

1. A method for establishing a data set, comprising: (1) performing clinical phenotype testing on multiple subjects to obtain a clinical phenotype measurement data set; (2) Using age as a training label, the dataset is constructed for training an age estimation model.

2. The method of claim 1, wherein the clinical phenotype test data is divided into seven categories: indicating mobility, lipids, hormones, blood component content, blood cells, body measurements and tissue function (e.g., lung, cardiovascular, muscle, kidney, liver, eye and bone); Preferably, the clinical phenotype detection includes physical examination, for example, general examination, internal medicine examination, surgical examination, B-ultrasound examination, body composition analysis, blood routine, glycosylated hemoglobin, six items of sex hormones, urine routine, stool routine, lung function test, bone density test, electrocardiogram and biochemical analysis; preferably, the clinical phenotype detection also includes mobility test, for example, single-leg standing, grip strength, 30-second sit-stand test, Purdue pegboard test and stepping test.

3. The method according to claim 1 or 2, further comprising the step of collecting a biological sample from the subject before performing the clinical phenotype detection. Preferably, the biological sample is selected from blood (eg, whole blood, plasma or serum) and urine.

4. The method according to any one of claims 1 to 3, before step (2), further comprising the step of performing a correlation analysis between the clinical phenotype measurement data set and age to screen for age-related features; Preferably, the clinical phenotype measurement data set is subjected to Pearson correlation analysis with age, BMI is used as a covariate, the P value is corrected by the BH method, and the result with P<0.05 is selected as the age-related feature.

5. The method according to any one of claims 1 to 4, wherein the data set is split into a training set and a test set, for example, in a 1:1 ratio.

6. The method according to any one of claims 1 to 5, wherein the subject is an Asian (eg, East Asian or Southeast Asian) person, such as a Chinese person; preferably, the number of the subjects is ≥100, for example, ≥500, ≥1000, or ≥10000.

7. A method for training an age estimation model, comprising: (1) establishing a data set according to the method according to any one of claims 1 to 6; (2) calculating the estimated age of the subject corresponding to the data using the age estimation model according to the data set; (3) Training the age estimation model based on the difference between the estimation result and the age label of the data.

8. The method of claim 7, wherein the training is performed using the glmnet package.

9. The training method of claim 7 or 8, wherein the subject estimates age A x represents the age-related features in the dataset, a x Represents the corresponding A x The coefficient of , b represents a constant; Through the training, each age-related feature A is determined x The coefficient a x and the constant b.

10. The training method according to any one of claims 7 to 9, wherein the age-related characteristics are selected from height, body composition test-left upper limb (value), body composition test-left upper limb (ECW / TBW), body composition test-right upper limb (ECW / TBW), waist-to-hip ratio, lung function-VC MAX, lung function-FEV 1, lung function-MEF 25, lung function-FEV 1*30, pulse, glycosylated hemoglobin, systolic blood pressure, blood glucose, alanine aminotransferase, alkaline phosphatase, globulin, urea, triglycerides, cholesterol, lactate dehydrogenase, apolipoprotein A and anti-Mullerian hormone.

11. The training method according to claim 9 or 10, wherein the coefficient a and the constant b of each age-related feature in the age estimation model are:

12. An age estimation model, which is trained by the method according to any one of claims 7 to 11.

13. An age estimation device, comprising: An input unit, for inputting age-related characteristics of a subject, wherein the age-related characteristics are as defined in claim 10; an estimation unit, configured to calculate the estimated age of the subject based on the input age-related features using the age estimation model according to claim 12; and an optional output unit for outputting the estimated age of the subject.

14. A method for estimating age, comprising: Providing a subject with an age-related characteristic, wherein the age-related characteristic is as defined in claim 10; The age-related features are input into the age estimation model described in claim 12 or the age estimation device described in claim 13 to estimate the age of the subject.

15. An electronic device, comprising: Memory; and A processor coupled to the memory, the processor being configured to execute the training method of the age estimation model according to any one of claims 7 to 11, or the age estimation method according to claim 14, based on instructions stored in the memory.

16. A non-volatile computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the program implements the training method of the age estimation model described in any one of claims 7 to 11, or the age estimation method described in claim 14.

17. Use of the method for establishing a data set according to any one of claims 1 to 6, the method for training an age estimation model according to any one of claims 7 to 11, the age estimation model according to claim 12, the age estimation device according to claim 13, the age estimation method according to claim 14, the electronic device according to claim 15, or the non-volatile computer-readable storage medium according to claim 16 in preparing a kit, wherein the kit is used for one or more of the following: 1) Estimate the age of the subjects; 2) Evaluate the aging rate or degree of the subjects; 3) Evaluate the effectiveness of aging interventions; 4) Assess the risk of aging-related diseases (such as cardiovascular disease, neurodegenerative disease, diabetes or chronic obstructive pulmonary disease) 5) Evaluate or assist in evaluating the therapeutic effects of aging-related diseases.

Images