A method for evaluating female reproductive aging

Abstract

The present invention relates to the technical field of female reproductive aging assessment, and discloses a method for female reproductive aging assessment. The method comprises the following steps: collecting female infertility-related data to obtain the cumulative live birth situation after a single controlled ovarian stimulation; using a random forest model to select age, anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone as the main predictive indicators for cumulative live birth, and confirming the non-linearizable curve characteristics of their correlations; based on the generalized additive model, using the above indicators to better predict cumulative live birth and mapping it to the corresponding age to obtain the reproductive aging assessment indicator - reproductive age. The prediction model still has a relatively high accuracy in the external dataset, and the reproductive age has universality and popularization for the differentiation of the population and the assessment of fertility. The beneficial effects of the present invention are: the constructed reproductive age model breaks through the linear framework of the traditional chronological age and effectively improves the accuracy of the assessment of reproductive aging and female fertility.

Description

Technical Field

[0001] The present invention relates to the technical field of female reproductive aging assessment, and specifically to a method for assessing female reproductive aging. Background Technique

[0002] With the development of social economy, the age of first childbirth for women has been postponed, and the proportion of advanced-age pregnancies has been increasing year by year. However, a woman's fertility gradually declines with age. Accurately assessing a woman's reproductive status and degree of reproductive aging is crucial for the timely diagnosis and treatment of infertility.

[0003] Currently, clinically, ovarian reserve indicators are usually used to evaluate female reproductive aging, such as age, anti-Müllerian hormone, antral follicle count, basal follicle-stimulating hormone, etc. Existing ovarian reserve assessment models mainly predict the risk of diminished ovarian reserve (DOR) and the age of menopause, and the assessment of fertility is relatively limited. In addition, existing clinical assessments mostly rely on the empirical integration of indicators, with subjective biases and a lack of an objective and quantitative comprehensive model. More complexly, age, ovarian reserve indicators, etc. are mostly curvilinearly related to fertility and among each other, and it is impossible to objectively and accurately assess through simple calculations.

[0004] To solve the above problems, a comprehensive and objective method for assessing female reproductive aging is proposed in this application. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for assessing female reproductive aging to solve the problem in the prior art that there is no reproductive age model constructed by reasonably integrating multiple indicators with fertility as the core as mentioned in the above background technique.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A method for assessing female reproductive aging, the method comprising the following steps:

[0007] Step 1, collect sample data and obtain sample characteristics;

[0008] Step 1.1, set the sample data collection criteria, patients meeting the criteria are included in the follow-up, and the final outcome - cumulative live birth of a single oocyte retrieval is obtained;

[0009] Step 1.2, select sample characteristics related to pregnancy outcomes from the sample data according to preset criteria;

[0010] Step 2, perform transformation and imputation on the sample characteristics described in Step 1.2, and the specific transformation and imputation processes are as follows:

[0011] Step 2.1, transform and encode the sample characteristics: perform standardization and normalization processing on the obtained data such as age, anti-Müllerian hormone, antral follicle count, basal follicle-stimulating hormone, etc. to make them conform to the input for fitting and training the model;

[0012] Step 2.2: If there are missing values in some of the sample features, for the null values of different features, use the multiple imputation method to fill in the features with missing values in the sample features. If there are no missing values, there is no need to fill in. Finally, a complete sample without missing values is formed and enters Step 3;

[0013] Step 3: Use the random forest model to rank the importance of candidate predictive variables for the complete sample formed in Step 2.2. The key variables selected are entered into Step 4 to construct a prediction model;

[0014] Step 4: Divide the data of the complete sample into a training set and a test set at a sample ratio of 8:2. Construct a female reproductive aging assessment model based on the generalized additive model for the training set samples formed in Step 2, Step 3, and Step 4: Use the processed data as the independent variable and the cumulative live birth rate within 2 years after a single oocyte retrieval as the dependent variable to construct the model. The model formula is , where y is the cumulative live birth, and x i are the age, anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone after normalization and standardization, f i is the smoothing function, g is the link function, and ε i is the error term;

[0015] Step 5: Based on the constructed model, calculate the predicted value of the cumulative live birth rate for each patient and map this value to the corresponding age to obtain the reproductive age;

[0016] Step 6: Use the female reproductive aging assessment model and reproductive age calculation based on the generalized additive model constructed in Step 4 and Step 5 to predict the degree of reproductive aging for the test set;

[0017] Step 7: Use the female reproductive aging assessment model based on the generalized additive model selected in Step 6 to validate in external samples: Compare the heterogeneity and discrimination of the cumulative live birth between the reproductive age and the actual age. If the cumulative live birth heterogeneity of the reproductive age is lower and the discrimination is higher, then the validation model is effective.

[0018] In the data processing step, it also includes using the age, anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone after normalization and standardization as independent variables, using the live birth / cumulative live birth of fresh embryo transfer as the dependent variable, and using the adjusted odds ratio to compare the efficacy of different outcome indicators in evaluating aging.

[0019] Before the model construction step, it also includes analyzing the correlation between age, anti-Müllerian hormone, antral follicle count, basal follicle-stimulating hormone and cumulative live birth rate, confirming that it is curve-related and cannot be linearized by exponential function, power function, logarithmic function, reciprocal transformation, and Box-Cox method: The correlation before and after processing is evaluated by a generalized additive model, and the degrees of freedom (edf values) are all greater than 1.5, and the significance values (p values) are all less than 0.05.

[0020] After the data acquisition step, it also includes calculating the quartile / median ratio of anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone indicators for women within 1 year of actual age. If the ratio is greater than 25%, it indicates strong ovarian reserve heterogeneity.

[0021] In the model verification step, compare the cumulative live birth heterogeneity and discrimination between reproductive age and actual age. Compared with actual age, the interquartile range of expected live births within 1 year of reproductive age is reduced by half, and the discrimination of live births is higher for advanced age, then it is determined that the model has robustness and extrapolability.

[0022] Compared with the prior art, the beneficial effects of the present invention are:

[0023] 1. The reproductive age model constructed by the present invention breaks through the limitations of the traditional chronological age linear framework. For the first time, the age corresponding to the expected live birth rate is used as the measurement dimension, which can accurately and intuitively describe the reproductive aging process and effectively improve the accuracy of the assessment of reproductive aging and female fertility.

[0024] 2. The present invention integrates multi-dimensional data such as age, ovarian reserve, and cumulative live birth rate, and is supported by external verification data, providing a more scientific and objective basis for clinicians to evaluate the reproductive health of women of childbearing age with fertility needs, helping to diagnose and treat infertility in a timely manner, and having important significance for improving the global fertility dilemma. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic flow chart of a method for evaluating female reproductive aging of the present invention;

[0026] Figure 2 It is a model diagram of a method for evaluating female reproductive aging of the present invention;

[0027] Figure 3 It is a comparison of the efficacy of different fertility outcomes of a method for evaluating female reproductive aging of the present invention;

[0028] Figure 4 It is a schematic diagram of the curve correlation of a method for evaluating female reproductive aging of the present invention;

[0029] Figure 5Schematic diagram of differences in ovarian reserve indicators among women of the same age (within 1 year) for a method for evaluating female reproductive aging according to the present invention;

[0030] Figure 6 Schematic diagram of heterogeneity in ovarian reserve and differences in pregnancy outcomes during reproductive aging for a method for evaluating female reproductive aging according to the present invention;

[0031] Figure 7 Schematic diagram of the fitted cumulative live birth rate for a method for evaluating female reproductive aging according to the present invention;

[0032] Figure 8 Schematic diagram of the number and cumulative live birth rate of women with decreased ovarian reserve, normal ovarian reserve but poor live birth, and normal ovarian reserve and good live birth for a method for evaluating female reproductive aging according to the present invention;

[0033] Figure 9 Schematic diagram of the predictive value of the generalized additive model for cumulative live birth in internal and external data sets for a method for evaluating female reproductive aging according to the present invention;

[0034] Figure 10 Schematic diagram of cumulative live birth fitting and mapping for a method for evaluating female reproductive aging according to the present invention;

[0035] Figure 11 Schematic diagram of the distinguishing features between reproductive aging defined by reproductive age and decreased ovarian reserve for a method for evaluating female reproductive aging according to the present invention;

[0036] Figure 12 Schematic diagram of the heterogeneity of cumulative live birth with reproductive age lower than the actual age in external data validation for a method for evaluating female reproductive aging according to the present invention;

[0037] Figure 13 Schematic diagram of the discrimination degree of cumulative live birth with reproductive age higher than the actual age in external data validation for a method for evaluating female reproductive aging according to the present invention. Detailed implementation manners

[0038] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0039] Please refer to Figures 1 - 13 , the present invention provides a technical solution: a method for evaluating female reproductive aging, the method comprising the following steps:

[0040] Step 1, collect sample data to obtain sample characteristics;

[0041] Step 1.1, set the sample data collection standard, patients meeting the standard are included in the follow-up, and the final outcome - the cumulative live birth of a single oocyte retrieval is obtained.

[0042] Step 1.2: Select sample features related to pregnancy outcomes from the sample data according to preset criteria;

[0043] Step 2: Transform and impute the sample features described in Step 1.2. The specific transformation and imputation processes are as follows:

[0044] Step 2.1: Transform and encode the sample features: Standardize and normalize the obtained data such as age, anti-Müllerian hormone (AMH), antral follicle count (AFC), and basal follicle-stimulating hormone (bFSH) to make them conform to the input for fitting and training the model;

[0045] Step 2.2: If there are missing values in some of the sample features, use the multiple imputation method to fill in the features with missing values for different features. If there are no missing values, no filling is required. Finally, form a complete sample without missing values and proceed to Step 3;

[0046] Step 3: Use the random forest model to rank the importance of candidate predictor variables for the complete sample formed in Step 2.2. The key variables selected are used in Step 4 to construct a prediction model;

[0047] Step 4: Split the data of the complete sample into a training set and a test set at a sample ratio of 8:2. Construct a female reproductive aging assessment model based on the generalized additive model using the training set samples formed in Steps 2, 3, and 4: Use the processed data as independent variables and the cumulative live birth rate within 2 years after a single oocyte retrieval as the dependent variable to construct the model. The model formula is , where y is the cumulative live birth, and x i are the age, anti-Müllerian hormone (AMH), antral follicle count (AFC), and basal follicle-stimulating hormone (bFSH) after normalization and standardization, f i is a smooth function, g is a link function, and ε i is the error term;

[0048] Step 5: Based on the constructed model, calculate the predicted value of the cumulative live birth rate for each patient and map this value to the corresponding age to obtain the reproductive age;

[0049] Step 6: Use the female reproductive aging assessment model and reproductive age calculation based on the generalized additive model constructed in Steps 4 and 5 to predict the degree of reproductive aging for the test set;

[0050] Step 7. Validate the female reproductive aging assessment model based on the generalized additive model selected in Step 6 in an external sample: Compare the heterogeneity and discrimination of reproductive age and actual age in cumulative live births. If the cumulative live birth heterogeneity of reproductive age is lower and the discrimination is higher, the validation model is effective.

[0051] Furthermore, in the data processing step, age, anti-Müllerian hormone (AMH), antral follicle count (AFC), and basal follicle-stimulating hormone (bFSH) after normalization and standardization are used as independent variables, and fresh embryo transfer live birth / cumulative live birth or not is used as the dependent variable. The odds ratios after correction are used to compare the efficacy of different outcome indicators in assessing aging.

[0052] Furthermore, before the model construction step, analyze the correlations between age, anti-Müllerian hormone (AMH), antral follicle count (AFC), basal follicle-stimulating hormone (bFSH), and cumulative live birth rate, and confirm that they are curve-related and cannot be linearized by exponential function, power function, logarithmic function, reciprocal transformation, and Box-Cox method: The correlations before and after processing are evaluated by the generalized additive model, and the degrees of freedom (edf values) are all greater than 1.5, and the significance values, as shown in the appendix Figure 4 shown, also known as p-values, are all less than 0.05.

[0053] Furthermore, after the data acquisition step, calculate the quartile / median ratio of anti-Müllerian hormone (AMH), antral follicle count (AFC), and basal follicle-stimulating hormone (bFSH) in women within 1 year of actual age. If the ratio is greater than 25%, it indicates strong ovarian reserve heterogeneity.

[0054] Furthermore, in the model validation step, compare the cumulative live birth heterogeneity and discrimination of reproductive age and actual age. If the interquartile range of expected live births within 1 year of reproductive age is reduced by half compared to actual age, and the discrimination of live births by advanced age is higher, the model is determined to have robustness and extrapolability.

[0055] Example

[0056] Data collection: According to the population inclusion criteria, collect relevant data of eligible patients from 2015 to 2021 in the Reproductive Hospital Affiliated to Shandong University and Shanghai Renji Hospital, including age, anti-Müllerian hormone (AMH), antral follicle count (AFC), basal follicle-stimulating hormone (bFSH), Gn dosage, HCG dosage, number of eggs retrieved, transplantation status, pregnancy outcome, etc.

[0057] Data processing: Normalize and standardize the collected data of anti-Müllerian hormone (AMH), antral follicle count (AFC), basal follicle-stimulating hormone (bFSH), and age to make them comparable.

[0058] Calculate the corrected OR value and evaluate the discrimination of commonly used clinical reproductive aging indicators for the live birth rate and cumulative live birth rate of fresh embryo transfer;

[0059] Use the generalized additive model to analyze the curvilinear correlation between commonly used clinical reproductive aging indicators and the cumulative live birth rate, and try various methods for linearization and evaluation;

[0060] Calculate the dispersion of ovarian reserve indicators in women of similar age and evaluate ovarian reserve heterogeneity;

[0061] Model construction and validation: Select the generalized additive model, with age, anti-Müllerian hormone (AMH), antral follicle count (AFC), and basal follicle-stimulating hormone (bFSH) after normalization and standardization as independent variables, and cumulative live birth as the dependent variable, to construct a model for curve fitting the cumulative live birth rate;

[0062] Obtain the fitted cumulative live birth of each patient according to the model, and obtain the corresponding reproductive age (rAGE) through mapping the data set;

[0063] Use external unit data to externally validate the model and evaluate the cumulative live birth heterogeneity and discrimination of reproductive age.

Claims

1. A method for evaluating female reproductive aging, characterized in that: The method includes the following steps: Step 1: Collect sample data and obtain sample characteristics; Step 1.1: Set the sample data collection criteria. Patients meeting the criteria are included in the follow-up to obtain the final outcome - cumulative live birth from a single oocyte retrieval; Step 1.2: Select sample characteristics related to pregnancy outcomes from the sample data according to the preset criteria; Step 2: Transform and impute the sample characteristics described in Step 1.

2. The specific transformation and imputation processes are as follows: Step 2.1: Transform and encode the sample characteristics: Standardize and normalize the obtained data such as age, anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone to make them conform to the input for fitting and training the model; Step 2.2: If there are missing values in some of the sample characteristics, for the null values of different characteristics, use the multiple imputation method to fill in the characteristics with missing values in the sample characteristics. If there are no missing values, no filling is required. Finally, form a complete sample without missing values and enter Step 3; Step 3: Select the commonly used ovarian reserve assessment indicators in clinical practice from the complete sample formed in Step 2.2 as key variables and enter Step 4 to construct a prediction model; Step 4: Divide the data of the complete samples into a training set and a test set at a sample ratio of 8:2, and construct a female reproductive aging assessment model based on the generalized additive model for the training set samples formed in Step 2, Step 3, and Step 4: Use the processed data as the independent variable and the cumulative live birth rate within 2 years after a single oocyte retrieval as the dependent variable to construct the model. The model formula is , where y is the cumulative live birth, and x i are the age, anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone after normalization and standardization, f i is the smoothing function, g is the link function, and ε i is the error term; Step 5: Based on the constructed model, calculate the predicted value of the cumulative live birth rate for each patient and map this value to the corresponding age to obtain the reproductive age; Step 6: Use the female reproductive aging assessment model and reproductive age calculation based on the generalized additive model constructed in Step 4 and Step 5 to predict the degree of reproductive aging of the test set; Step 7: Use the female reproductive aging assessment model based on the generalized additive model selected in Step 6 to verify in an external sample: Compare the heterogeneity and discrimination of cumulative live birth between the reproductive age and the actual age. If the cumulative live birth heterogeneity of the reproductive age is lower and the discrimination is higher, then the verification model is effective.

2. The female reproductive aging assessment method according to claim 1, characterized in that: In the data processing step, it also includes using the age, anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone after normalization and standardization as independent variables, the live birth from fresh embryo transfer / cumulative live birth or not as the dependent variable, and the adjusted odds ratio to compare the efficacy of different outcome indicators in assessing aging.

3. The female reproductive aging assessment method according to claim 1, wherein: Before the model construction step, analyze the correlation between age, anti-Müllerian hormone, antral follicle count, basal follicle-stimulating hormone and the cumulative live birth rate, and confirm that it is curvilinear correlation, and it cannot be linearized by exponential function, power function, logarithmic function, reciprocal transformation, Box-Cox method: The correlations before and after processing are evaluated by the generalized additive model, and the degrees of freedom are all greater than 1.5, and the significance values are all less than 0.

05.

4. The female reproductive aging assessment method according to claim 1, wherein: After the data acquisition step, calculate the interquartile range / median ratio of the anti-Müllerian hormone, antral follicle count, and basal follicle-stimulating hormone indicators for women within 1 year of actual age. If the ratio is greater than 25%, it indicates strong ovarian reserve heterogeneity.

5. The female reproductive aging assessment method according to claim 1, characterized in that: In the model verification step, by comparing the heterogeneity and discrimination of cumulative live birth between the reproductive age and the actual age, if the interquartile range of cumulative live birth within 1 year of the reproductive age is reduced by half compared to the actual age, and the discrimination of cumulative live birth by advanced age is higher, then it is determined that the model has robustness and extrapolability.

Images