WO2021031605A1 - System for predicting number of retrieved oocytes during ovarian stimulation of subject - Google Patents

Abstract

Provided is a system for predicting the number of retrieved oocytes during the ovarian stimulation of a subject receiving a standard GnRH antagonist regimen for ovulation induction treatment. The system comprises a data acquisition module used for obtaining data on the anti-Müllerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level and antrum follicle count (AFC) of the subject; and a module used for predicting the number of retrieved oocytes during the ovarian stimulation and calculating the information obtained from the data acquisition module in order to calculate the number of retrieved oocytes (NRO) of the subject.

Description

System for predicting the number of oocytes obtained during ovarian stimulation Technical field

The present invention relates to a system and method for predicting the number of oocytes obtained during ovarian stimulation in subjects receiving standard GnRH antagonist regimens for ovulation induction therapy.

Background technique

For women undergoing controlled ovarian stimulation (COS) and IVF/ICSI cycles, the number of retrieved oocytes (NROs) obtained is considered a powerful surrogate prognostic marker for successful pregnancy. The best NROs help increase the live birth rate (Live-birth-rate, LBR).

Predicting NROs before controlled ovarian stimulation (COS) is the only way to perform effective and safe treatment. A variety of markers have been used to assess ovarian response. These markers include, for example, age, basal follicle stimulating hormone (FSH), antral follicle count (AFC) and anti-Müllerian hormone (AMH). These markers have been widely used. Used to predict ovarian responsiveness. So far, no single marker of ovarian reserve can completely replace other indicators. Clinicians usually choose the starting dose of recombinant FSH (rFSH) based on the women's previous ovarian response history, age, AMH, AFC, basic FSH, body mass index (BMI) and other clinical experience.

Summary of the invention

In summary, due to the necessity of predicting NROs, the purpose of the present invention is to provide an effective system that can be used to predict the number of oocytes obtained if a subject receives a standard GnRH antagonist for ovulation induction. In the future, it can be combined with other systems to better guide the selection of ovulation induction programs and recombinant FSH doses. The present invention explores a reliable system to predict receiving NROs in a gonadotropin releasing hormone (GnRH) antagonist regimen. Furthermore, since the hormone level in the GnRH antagonist regimen is actually the basic hormone level of any person, the system of the present invention may have important significance for pre-COS evaluation and clinical consultation during ovarian stimulation in the general population. Utilizing the system or method of the present invention is beneficial to the pregnancy outcome of NROs and women receiving assisted reproductive technology (ART) treatment.

Predicting the number of retrieved oocytes (NROs) during ovarian stimulation is the only method for effective and safe treatment. Logistic regression analysis has been widely used to predict whether the ovarian response is bad or not. However, dividing NROs into two categories (ie, low response or not) is not specific and sufficient for individuals. At present, there are very few studies on predicting specific NROs, which hinders the development of individualized treatment in assisted reproductive technology.

In summary, the present invention involves the following contents:

A system for predicting the number of oocytes obtained in a subject's ovarian stimulation process, comprising: a data collection module, which is used to obtain the subject's anti-Mullerian hormone (AMH) level and basic follicle stimulation FSH levels, antral follicle count (AFC) data; and a module for predicting the number of oocytes obtained during ovarian stimulation, which is used to calculate the above-mentioned data obtained in the data acquisition module to calculate the The number of oocytes (NROs) obtained by the participant.

In a specific embodiment of the present invention, the subject is a subject who will receive a standard GnRH antagonist regimen for ovulation induction therapy.

In another specific embodiment of the present invention, in the module for predicting the number of oocytes obtained during ovarian stimulation, anti-Muller therapy for patients who have received standard GnRH antagonist regimens for ovulation induction therapy based on the existing database is stored in advance. The categorical data converted from the levels of AMH, basal follicle stimulating hormone (FSH), and antral follicle count (AFC), and fitting based on the pre-stored patient’s categorical data and negative binomial distribution The formula used to predict the number of oocytes (NROs) obtained during ovarian stimulation when subjects receive standard GnRH antagonist ovulation therapy.

In this article, a patient refers to a standard GnRH antagonist regimen for ovulation induction therapy, and during the treatment, his anti-Mullerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level, and antral follicle count ( AFC) data were collected and used to construct subjects for calculating NROs model.

In this article, the subject means that he will receive the standard GnRH antagonist regimen for ovulation induction therapy, by testing his anti-Mullerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level, and antral follicle count (AFC) Therefore, the system and method of the present invention can be used to predict the number of oocytes (NROs) obtained during ovarian stimulation.

In another specific embodiment of the present invention, in the data collection module, the collected anti-Mullerian hormone (AMH) level refers to the anti-Mullerian hormone (AMH) level in the venous blood of a female subject at any point in the menstrual period. The basal follicle stimulating hormone (FSH) level refers to the concentration of follicle stimulating hormone in the venous blood of a female subject during menstruation for 2-4 days, and the antral follicle count (AFC) refers to the vaginal B-ultrasound count The number of all visible follicles with a diameter of 2-10mm in the two ovaries of the female subjects during 2-4 days of menstruation

In another specific embodiment of the present invention, in the module for predicting the number of oocytes obtained during ovarian stimulation, when calculating with the formula, the subject's anti-Mullerian tube collected by the data collection module AMH classification data converted from hormone (AMH) levels are calculated,

The classification data of AMH is obtained by dividing the subjects' anti-Mullerian hormone (AMH) levels collected by the data acquisition module into five groups and assigning different classification data as follows:

When AMH is less than 0.5ng/ml, the classification data of AMH is 0;

When AMH is 0.5ng/ml and above and less than 1ng/ml, the classification data of AMH is 1;

When AMH is 1ng/ml and above and less than 2ng/ml, the classification data of AMH is 2;

When AMH is 2ng/ml and above and less than 4ng/ml, the classification data of AMH is 3; and

When AMH is 4ng/ml and above, the classification data of AMH is 4.

In another specific embodiment of the present invention, in the module for predicting the number of oocytes obtained during ovarian stimulation, when calculating with the formula, the subject’s basic follicle stimulating hormone collected by the data collection module (FSH) The basic FSH classification data converted from the level is calculated,

The basic FSH classification data is obtained by dividing the subjects’ Follicle Stimulating Hormone (FSH) levels collected by the data acquisition module into four groups and assigning different classification data as follows:

When the basic FSH is less than 3IU/L, the classification data of the basic FSH is 0;

When the basic FSH is 3IU/L and above and less than 5IU/L, the classification data of the basic FSH is 1;

When the basic FSH is 5IU/L and above and less than 8IU/L, the classification data of the basic FSH is 2;

When the basic FSH is 8IU/L and above, the classification data of the basic FSH is 3.

In another specific embodiment of the present invention, in the module for predicting the number of oocytes obtained during ovarian stimulation, when calculating with the formula, the count of antral follicles collected by the data acquisition module ( AFC) converted AFC classification data for calculation,

The classification data of AFC is obtained by dividing the subject's antral follicle count (AFC) data collected by the data acquisition module into four groups and assigning different classification data as follows:

When AFC is less than 4, the classification data of AFC is 0;

When AFC is 4 or more and less than 8, the classification data of AFC is 1;

When AFC is 8 or more and less than 12, the classification data of AFC is 2;

When AFC is 12 or more, the classification data of AFC is 3.

In another specific embodiment of the present invention, the formula for calculating the number of oocytes (NROs) obtained during ovarian stimulation is determined by using the AMH level of the subject collected by the data collection module The AMH classification data, the FSH classification data determined by the subject's basic FSH level, and the AFC classification data determined by the subject's AFC are calculated to obtain the formula for the number of oocytes (NROs).

In another specific embodiment of the present invention, the above formula is the following formula 1:

Log(NROs)=m+n*AMH classification data+j*basic FSH classification data+k*AFC classification data (formula 1);

Wherein n, j and k are determined based on the classification data of the AMH, basic FSH and AFC; wherein m is selected from any value in the range of 0.7435 to 1.2111, and m is preferably 0.9733;

When performing the calculation, the module for predicting the number of oocytes obtained during ovarian stimulation is based on the subject’s anti-Mullerian hormone (AMH) level and basal follicle stimulating hormone (FSH) collected by the data collection module Level, antral follicle count (AFC) data are judged, and the values of n, j and k are confirmed according to the following criteria;

When the subject's AMH level is less than 0.5ng/ml, n=0;

When the subject's AMH level is 0.5 ng/ml and above and less than 1 ng/ml, n is selected from any value from 0.1994 to 0.5153; n is preferably 0.3574;

When the subject's AMH level is 1 ng/ml and above and less than 2 ng/ml, n is selected from any value from 0.5007 to 0.7984; n is preferably 0.6496;

When the subject's AMH level is 2ng/ml and above and less than 4ng/ml, n is selected from any value in the range of 0.6883 to 0.9896; n is preferably 0.8390;

When the subject's AMH level is 4ng/ml and above, n is selected from any value from 0.8385 to 1.1557; n is preferably 0.9971;

When the subject’s basal FSH is less than 3IU/L, j is selected from any value from 0.0443 to 0.4112; j is preferably 0.2278;

When the subject's basal FSH is 3IU/L and above and less than 5IU/L, j is selected from any value from -0.0972 to 0.2526; j is preferably 0.0777;

When the subject's basal FSH is 5IU/L and above and less than 8IU/L, j is selected from any value from -0.2618 to 0.0947; j is preferably -0.0835;

When the subject's AFC is less than 4, k=0;

When the AFC of the subject is 4 or more and less than 8, k is selected from any value from 0.1599 to 0.4629; k is preferably 0.3114;

When the subject's AFC is 8 or more and less than 12, k is selected from any value in the range of 0.3553 to 0.6735; k is preferably 0.5144;

When the AFC of the subject is 12 or more, k is selected from any value in the range of 0.5027 to 0.8264; k is preferably 0.6645.

The present invention also relates to a method for predicting the number of oocytes obtained in a subject's ovarian stimulation process, which includes: a data collection step, which obtains the subject's anti-Mullerian hormone (AMH) level and basic Follicle stimulating hormone (FSH) level, antral follicle count (AFC) data; and the step of predicting the number of oocytes obtained during ovarian stimulation, which calculates the above-mentioned data obtained in the data acquisition module to calculate the The number of oocytes (NROs) obtained by the participant.

In the above method, the subject is a subject who will receive a standard GnRH antagonist regimen for ovulation induction therapy.

In the above method, in the step of predicting the number of oocytes obtained during ovarian stimulation, the anti-Mullerian hormone (AMH) stored in advance based on the existing database of patients who have received standard GnRH antagonist regimens for ovulation induction therapy is used. ) Level, basal follicle stimulating hormone (FSH) level, antral follicle count (AFC) data converted into categorical data, and based on the pre-stored patient’s categorical data and the negative binomial distribution fitted to predict the affected When the subjects received the standard GnRH antagonist regimen for ovulation induction therapy, the number of oocytes (NROs) obtained during ovarian stimulation was calculated using the formula.

In the above method, in the data collection step, the collected anti-Mullerian hormone (AMH) level refers to the concentration of anti-Mullerian hormone in the venous blood of the female subject at any point in the menstrual period, so The basal follicle stimulating hormone (FSH) level refers to the concentration of follicle stimulating hormone in the venous blood of a female subject after menstruation for 2-4 days, and the antral follicle count (AFC) refers to the vaginal B ultrasound count of the female subject’s menstrual period 2 -The number of all visible follicles with a diameter of 2-10 mm in the two ovaries at 4 days.

In the above method, in the step of predicting the number of oocytes obtained during ovarian stimulation, when calculating with the formula, the subject's anti-Mullerian hormone (AMH) level collected by the data collection module is used to convert Categorized data from AMH for calculation,

The classification data of AMH is obtained by dividing the subjects' anti-Mullerian hormone (AMH) levels collected by the data acquisition module into five groups and assigning different classification data as follows:

When AMH is less than 0.5ng/ml, the classification data of AMH is 0;

When AMH is 0.5ng/ml and above and less than 1ng/ml, the classification data of AMH is 1;

When AMH is 1ng/ml and above and less than 2ng/ml, the classification data of AMH is 2;

When AMH is 2ng/ml and above and less than 4ng/ml, the classification data of AMH is 3; and

When AMH is 4ng/ml and above, the classification data of AMH is 4.

In the above method, in the step of predicting the number of oocytes obtained in the process of ovarian stimulation, when calculating using the formula, the subject's basic follicle stimulating hormone (FSH) level collected by the data collection module is converted into Based on FSH classification data for calculation,

The basic FSH classification data is obtained by dividing the subjects’ Follicle Stimulating Hormone (FSH) levels collected by the data acquisition module into four groups and assigning different classification data as follows:

When the basic FSH is less than 3IU/L, the classification data of the basic FSH is 0;

When the basic FSH is 3IU/L and above and less than 5IU/L, the classification data of the basic FSH is 1;

When the basic FSH is 5IU/L and above and less than 8IU/L, the classification data of the basic FSH is 2;

When the basic FSH is 8IU/L and above, the classification data of the basic FSH is 3.

In the above method, in the step of predicting the number of oocytes obtained in the process of ovarian stimulation, when calculating with the formula, the classification of AFC converted by the subject's antral follicle count (AFC) collected by the data collection module Data to calculate,

The classification data of AFC is obtained by dividing the subject's antral follicle count (AFC) data collected by the data acquisition module into four groups and assigning different classification data as follows:

When AFC is less than 4, the classification data of AFC is 0;

When AFC is 4 or more and less than 8, the classification data of AFC is 1;

When AFC is 8 or more and less than 12, the classification data of AFC is 2;

When AFC is 12 or more, the classification data of AFC is 3.

In the above method, the formula for calculating the number of oocytes (NROs) obtained during ovarian stimulation is the AMH classification data determined by the subject's AMH level collected by the data collection module, and the test The FSH classification data determined by the subject’s basic FSH level and the AFC classification data determined by the subject’s AFC are calculated to obtain the formula for the number of oocytes (NROs).

In the above method, the above formula is the following formula 1:

Log(NROs)=m+n*AMH classification data+j*basic FSH classification data+k*AFC classification data (formula 1);

Wherein n, j and k are determined based on the classification data of the AMH, basic FSH and AFC;

Wherein m is selected from any value from 0.7435 to 1.2111, and m is preferably 0.9733;

When performing the calculation, in the step of predicting the number of oocytes obtained in the process of ovarian stimulation, based on the subject's anti-Mullerian hormone (AMH) level and basal follicle stimulating hormone collected by the data collection module (FSH) level, antral follicle count (AFC) data to determine, according to the following criteria to confirm the value of n, j and k;

When the subject's AMH level is less than 0.5ng/ml, n=0;

When the subject's AMH level is 0.5 ng/ml and above and less than 1 ng/ml, n is selected from any value from 0.1994 to 0.5153; n is preferably 0.3574;

When the subject's AMH level is 1 ng/ml and above and less than 2 ng/ml, n is selected from any value from 0.5007 to 0.7984; n is preferably 0.6496;

When the subject's AMH level is 2ng/ml and above and less than 4ng/ml, n is selected from any value in the range of 0.6883 to 0.9896; n is preferably 0.8390;

When the subject's AMH level is 4ng/ml and above, n is selected from any value from 0.8385 to 1.1557; n is preferably 0.9971;

When the subject’s basal FSH is less than 3IU/L, j is selected from any value from 0.0443 to 0.4112; j is preferably 0.2278;

When the subject's basal FSH is 3IU/L and above and less than 5IU/L, j is selected from any value from -0.0972 to 0.2526; j is preferably 0.0777;

When the subject's basal FSH is 5IU/L and above and less than 8IU/L, j is selected from any value from -0.2618 to 0.0947; j is preferably -0.0835;

When the subject's AFC is less than 4, k=0;

When the AFC of the subject is 4 or more and less than 8, k is selected from any value from 0.1599 to 0.4629; k is preferably 0.3114;

When the subject's AFC is 8 or more and less than 12, k is selected from any value in the range of 0.3553 to 0.6735; k is preferably 0.5144;

When the AFC of the subject is 12 or more, k is selected from any value in the range of 0.5027 to 0.8264; k is preferably 0.6645.

Effect of invention

Generally speaking, if the number of eggs obtained by the subject can be accurately predicted, the more the predicted number of eggs, the lower the amount of gonadotropin required in the process of ovulation induction treatment. On the contrary, the need to promote the process of ovulation induction The more gonadal hormones are used. The system and method of the present invention can more accurately predict the number of oocytes obtained during ovarian stimulation if the subject receives the standard GnRH antagonist regimen for ovulation induction therapy. Moreover, it can be combined with other systems to better guide the selection of ovulation induction programs and recombinant FSH doses to better realize individualized treatment.

Description of the drawings

By reading the detailed description in the following preferred embodiments, various other advantages and benefits of the present application will become clear to those of ordinary skill in the art. The drawings in the specification are only used for the purpose of illustrating the preferred embodiments, and are not considered as a limitation to the application. Obviously, the drawings described below are only some embodiments of the application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. Also, throughout the drawings, the same reference numerals are used to denote the same components.

Figure 1 shows the number of oocytes obtained by fitting Poisson distribution and negative binomial distribution respectively.

Figure 2 shows the variable selection process of the pruning forward method.

Figure 3 The prediction effect of the prediction model in the training set and validation set.

Figure 4 The residual distribution diagram of the prediction model in the training set and the validation set.

detailed description

Hereinafter, specific embodiments of the present invention will be described in more detail with reference to the accompanying drawings. Although specific embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

It should be noted that certain words are used in the description and claims to refer to specific components. Those skilled in the art should understand that they may use different terms to refer to the same component. This specification and claims do not use differences in terms as a way to distinguish components, but use differences in functions of components as a criterion for distinguishing. If "include" or "include" mentioned in the entire specification and claims is an open term, it should be interpreted as "include but not limited to". The following description of the specification is a preferred embodiment for implementing the present invention, but the description is based on the general principles of the specification and is not intended to limit the scope of the present invention. The protection scope of the present invention shall be subject to those defined by the appended claims.

Several infertility factors involved in this application are defined as follows. In this article, the first or first cause of infertility is male factor; the second or second factor is endometriosis; the third or third factor is fallopian tube factor; the fourth or fourth cause Factors are other factors.

Male factor refers to all infertility caused by male factors.

Endometriosis is a common gynecological disease in women that is formed when active endometrial cells are planted outside the endometrium. Endometrial cells should grow in the uterine cavity, but because the uterine cavity communicates with the pelvic cavity through the fallopian tube, the endometrial cells can enter the pelvic cavity through the fallopian tube to grow ectopic. The main pathological changes of endometriosis are periodic bleeding of the ectopic endometrium and fibrosis of surrounding tissues. The main symptoms are the formation of ectopic nodules, dysmenorrhea, chronic pelvic pain, abnormal menstruation and infertility. Lesions can affect all pelvic tissues and organs. The most common are the ovaries, uterine rectal depression, and uterosacral ligaments. It can also occur in the abdominal cavity, thoracic cavity, limbs, etc.

The fallopian tube factor refers to the fact that the fallopian tube has an important role in transporting sperm, picking up eggs, and transporting fertilized eggs to the uterine cavity. Obstruction or dysfunction of the fallopian tube becomes the main cause of female infertility. The cause of blocked fallopian tubes or dysfunction is acute and chronic inflammation of the fallopian tubes.

In this application, other factors include excluding male factors, endometrial factors, fallopian tube factors, and other infertility factors that are not the above three types of causes.

Variable types: In statistics, variable types can be divided into quantitative variables and qualitative variables (also called categorical variables).

Quantitative variables are variables used to describe the quantity and number of things, and can be divided into continuous and discrete types. Continuous variables refer to variables that can take values arbitrarily within a certain interval, and their values are continuous and can have decimal points. For example, blood pressure, blood sugar, body height, weight, chest circumference, etc. are continuous variables, and their values can only be obtained by measurement or measurement. Discrete variables refer to variables whose values can only be natural numbers or integer units. For example, the pain score, the number of metastatic lesions, the number of eggs harvested, etc., can only be positive numbers, not decimal points. The value of this variable is generally obtained by counting.

Categorical variables are variables used to describe the categories of things. Categorical variables can be divided into two categories: disordered categorical variables and ordinal categorical variables. Among them, unordered categorical variable (unordered categorical variable) refers to the difference in degree and order between the classified categories or attributes. It can be divided into ① two categories, such as gender (male, female), drug reaction (negative and positive), etc.; ② multiple categories, such as blood type (O, A, B, AB), occupation (work, agriculture, Business, learning, military) etc. However, there is a degree of difference between the categories of ordinal categorical variables. For example, urine glucose test results are classified by -, ±, +, ++, +++; curative effects are classified by cure, markedly effective, improved, and invalid. For ordinal categorical variables, you should first group them in rank order, count the number of observation units in each group, and compile a frequency table of ordinal variables (each rank). The data obtained is called rank data.

Variable types are not static. According to the needs of research purposes, various types of variables can be transformed. For example, the amount of hemoglobin (g/L) is originally a numerical variable. If hemoglobin is divided into two categories according to normal and low hemoglobin, it can be analyzed according to the two classification data; if according to severe anemia, moderate anemia, mild anemia, normal, hemoglobin When the increase is divided into five grades, it can be analyzed by grade data. Sometimes the categorical data can also be quantified. For example, the patient’s nausea response can be expressed as 0, 1, 2, 3, and then can be analyzed by numerical variable data (quantitative data).

Poisson distribution (Poisson distribution) is a discrete probability distribution (discrete probability distribution) commonly seen in statistics and probability. Poisson distribution is suitable for describing the number of random events in unit time (or space). For example, the number of disease cases in a certain fixed space and time, the number of recurrences of a certain disease, the number of parts of a certain disease metastasis, the number of vomiting times of a certain patient, etc.

The negative binomial distribution is a discrete probability distribution in statistics. The negative binomial distribution that meets the following conditions is called a negative binomial distribution: the experiment contains a series of independent experiments, each experiment has two results, success and failure, the probability of success is constant, the experiment continues until r successes, and r is a positive integer. The negative binomial distribution is similar to the Poisson distribution, and can also be used to describe the relative frequency of a rare event in a unit of time and space. It is different from the Poisson distribution in that the Poisson distribution can only be used to describe independent events, while the negative binomial distribution is often used to describe aggregate events, such as the distribution of snails in the soil, the distribution of an infectious disease, etc. Generally, if the count data finds the phenomenon that the mean value is greater than the variance, the Poisson distribution often does not fit well, and the negative binomial distribution can be considered.

In this application, anti-Mullerian hormone (AMH) refers to a hormone secreted by the granular cells of small ovarian follicles. Female babies in the fetal period begin to produce AMH. The more small follicles there are in the ovaries, The higher the concentration of AMH; on the contrary, when the follicles are gradually consumed with age and various factors, the concentration of AMH will also decrease, and the closer to menopause, the AMH gradually tends to zero.

In this application, Follicle Stimulating Hormone (FSH) refers to a hormone secreted by basophils in the anterior pituitary gland, which is composed of glycoproteins, and its main function is to promote follicle maturation. FSH can promote the proliferation and differentiation of follicular granulosa cells and promote the growth of the entire ovary. And its action on the seminiferous tubules of the testis can promote sperm formation. FSH is secreted in pulses in the human body, and women change with the menstrual cycle. Determination of FSH in serum is of great significance for the diagnosis and treatment of infertility and endocrine diseases, such as understanding pituitary endocrine function, indirect understanding of ovarian functional status, assessing ovarian reserve and ovarian responsiveness, and formulating ovulation-stimulating drug dosages.

In this application, the antral follicle count (AFC) refers to the number of all visible follicles with a diameter of 2-10 mm in the two ovaries in 2-4 days of menstruation. AFC can measure and count follicles by ultrasound.

The basal E2 level refers to the level of estradiol, which is a steroidal estrogen. There are two types of α and β, and the α type has a strong physiological effect. It has a strong sex hormone effect, so it is believed that it or its ester is actually the most important sex hormone secreted by the ovaries. The basal estradiol level detected in this application is the estradiol concentration in the venous blood serum sample of a female subject after menstruation for 2-4 days.

BMI is an important international standard to measure the degree of human obesity and health, and it is mainly used for statistical analysis. The degree of obesity cannot be judged by the absolute value of weight, it is naturally related to height. Therefore, BMI obtains a relatively objective parameter through the two values of human body weight and height, and uses the range of this parameter to measure body mass. BMI = weight/height square (international unit kg/㎡)

Luteinizing hormone (LH) is a glycoprotein gonadotropin secreted by pituitary gland cells, which can promote the conversion of cholesterol into sex hormones in gonadal cells. For women, it works with Follicle Stimulating Hormone (FSH) to promote the maturation of follicles, the secretion of estrogen, ovulation, the production and maintenance of the corpus luteum, and the secretion of progesterone and estrogen. For men, luteinizing hormone promotes the synthesis and release of testosterone by testicular stromal cells. The LH level refers to the LH concentration in the venous blood serum sample of a female subject during 2-4 days of menstruation.

In this article, rFSH refers to recombinant human follicle stimulating hormone. The starting dose of rFSH refers to the dose of recombinant FSH at the first injection for any ovulation induction program.

In this application, the level of anti-Mullerian hormone (AMH) refers to the concentration of anti-Mullerian hormone (FSH) in venous blood serum samples at any point in the menstrual cycle of female subjects, and the level of follicle stimulating hormone (FSH) is Refers to the concentration of follicle stimulating hormone in venous blood serum samples of female subjects during menstruation for 2-4 days. Antral follicle count (AFC) refers to the vaginal B-ultrasound count of the two ovaries of female subjects during menstruation for 2-4 days. The number of all visible follicles of 2-10mm.

The standard GnRH antagonist ovarian stimulation protocol described in this application is performed as follows: human recombinant FSH (human rFSH) (for example, Gonal-F alfa [Merck Serono, Germany], Puregon beta [MSD, USA], Urofollitropin [Livzon Pharmaceutical Group Inc ., China] or Menotrophins [Livzon Pharmaceutical] Group Inc., China]) start the administration on the second day of the menstrual cycle. The starting dose of human rFSH is selected based on age, AMH level, basal FSH level, AFC level, and BMI. The dose of rFSH was further adjusted according to the size and number of growing follicles observed by ultrasound and the _{level of serum E 2 during monitoring of ovarian stimulation.} When the diameter of the growing follicle reaches 10-12mm, GnRH antagonist treatment is started. When the diameter of at least two dominant follicles exceeds 18mm is observed by ultrasound, the dose of hCG (Choriogonadotropin alfa, Merck Serono) is injected at 5000-10000IU to trigger the final oocyte maturation. Oocyte recovery was performed 36-38 hours after hCG administration. Transfer one or two embryos or cryopreserve embryos. The subjects were then provided with luteal phase progesterone support (progesterone vaginal gel, Merck Serono).

In a specific embodiment of the present application, the system and method involved in the present application are for the subject who is receiving the standard GnRH antagonist regimen as described above for ovulation induction therapy.

This application relates to a system for predicting the number of oocytes obtained during ovarian stimulation of a subject, which includes: a data collection module for obtaining the level of anti-Mullerian hormone (AMH), Basic follicle stimulating hormone (FSH) level, antral follicle count (AFC) data; and a module for predicting the number of oocytes obtained during ovarian stimulation, which is used to calculate the above-mentioned data obtained in the data acquisition module, thereby Calculate the number of oocytes (NROs) obtained by the subject.

Those skilled in the art know that there are many factors that usually affect the number of oocytes obtained by a subject, such as BMI index, duration of infertility, previous in vitro fertilization/intracytoplasmic sperm injection-embryo transfer (IVF/ICSI- ET) number of attempts, serum basal E ₂ level, FSH level and LH level, serum AMH level, left and right ovarian AFCs, first, second, third, fourth and fifth causes of infertility, traditional or mild ovarian Stimulation cycle, ovarian stimulation type/COS regimen, starting dose and total dose of recombinant rFSH, duration of rFSH treatment (days), name of rFSH, endometrial thickness on the trigger day of human chorionic gonadotropin (hCG), etc. However, in this application, the inventors of this application have conducted in-depth research and finally confirmed the three data of anti-Mullerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level, and antral follicle count (AFC). An important parameter to confirm the subject’s NROs.

In this article, there are no restrictions on the data collection module, as long as it can be used to obtain the subject's anti-Mullerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level, and antral follicle count (AFC) data, Specifically, the level of anti-Mullerian hormone (AMH) acquired by the data collection module refers to the concentration of anti-Mullerian hormone (AMH) in the venous blood of a female subject at any point in the menstrual period, which is acquired by the data collection module The basal follicle stimulating hormone (FSH) level refers to the follicle stimulating hormone concentration in the venous blood of a female subject during menstruation for 2-4 days, and the antral follicle count (AFC) acquired by the data collection module refers to the vaginal B-ultrasound count The number of all visible follicles with a diameter of 2-10 mm in the two ovaries of female subjects during 2-4 days of menstruation. Subjects who need to predict the number of oocytes obtained in the process of ovarian stimulation can use the data within the given period mentioned above to predict the number of eggs obtained based on the method and system of the present application.

In this article, the module for predicting the number of oocytes obtained during ovarian stimulation is used to calculate the above-mentioned data obtained in the data acquisition module, so as to calculate the number of oocytes (NROs) obtained by the subject. First of all, it should be understood that the anti-Mullerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level, and sinus stimulating hormone (AMH) levels of patients who have received standard GnRH antagonist ovulation induction therapy based on the existing database are pre-stored in this module. The classification data converted from the data of follicle count (AFC), and the classification data based on the pre-stored patients and the negative binomial distribution fitting are used to predict that the subject will receive the standard GnRH antagonist regimen ovulation induction treatment , The formula for the number of oocytes (NROs) obtained during ovarian stimulation. Using such pre-stored formulas, calculations can be made for any subject.

Specifically, this pre-stored formula uses pre-stored anti-Mullerian hormone (AMH) levels, basal follicle stimulating hormone (FSH) levels, and basic follicle-stimulating hormone (FSH) levels in patients who have received standard GnRH antagonist ovulation induction therapy in the existing database. Antral follicle count (AFC) data is converted into classification data and fitted.

When calculating, this pre-stored formula is determined by the AMH classification data determined by the subject's AMH level collected by the data collection module, the FSH classification data determined by the subject's basic FSH level, and the subject's AFC. AFC classification data is used to calculate the number of oocytes (NROs) formula.

As mentioned above, when converting continuous variables into categorical variables, those skilled in the art will have different conversion methods, but the inventor of the present application has confirmed the following conversion methods through in-depth research. The classification data of AMH is obtained by dividing the subjects' anti-Mullerian hormone (AMH) levels collected by the data acquisition module into five groups and assigning different classification data as follows. When AMH is less than 0.5ng/ml, The classification data of AMH is 0; when AMH is 0.5ng/ml and above and less than 1ng/ml, the classification data of AMH is 1; when AMH is 1ng/ml and above and less than 2ng/ml, the classification data of AMH is 2; When AMH is 2ng/ml and above and less than 4ng/ml, the classification data of AMH is 3; and when AMH is 4ng/ml and above, the classification data of AMH is 4.

The basic FSH classification data is obtained by dividing the subjects’ follicle stimulating hormone (FSH) levels collected by the data collection module into four groups and assigning different classification data as follows. When the basic FSH is less than 3 IU/L, the basic FSH When the basic FSH is 3IU/L and above and less than 5IU/L, the basic FSH classification data is 1; when the basic FSH is 5IU/L and above and less than 8IU/L, the basic FSH classification data is 2; When the basic FSH is 8IU/L and above, the classification data of the basic FSH is 3.

The classification data of AFC is obtained by dividing the subject's antral follicle count (AFC) data collected by the data acquisition module into four groups and assigning different classification data as follows. When the AFC is less than 4, the classification data of AFC is 0 ; When AFC is 4 or more and less than 8, the classification data of AFC is 1; when AFC is 8 or more and less than 12, the classification data of AFC is 2; when AFC is 12 or more, the classification of AFC The data is 3.

Furthermore, the inventor of this application constructed a specific formula for predicting NROs, which is the following formula 1: Log(NROs)=m+n*AMH classification data+j*basic FSH classification data+k*AFC classification data (formula One);

Wherein n, j and k are determined based on the classification data of the AMH, basic FSH and AFC; wherein m is selected from any value in the range of 0.7435 to 1.2111, and m is preferably 0.9733; when the calculation is performed, ovarian stimulation is predicted The module of the number of oocytes obtained in the process is based on the data of the subject's anti-Mullerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level, and antral follicle count (AFC) collected by the data collection module Make a judgment and confirm the values of n, j and k according to the following criteria; when the subject’s AMH level is less than 0.5ng/ml, n=0; when the subject’s AMH level is 0.5 When ng/ml and above and less than 1ng/ml, n is selected from any value from 0.1994 to 0.5153; n is preferably 0.3574; when the subject's AMH level is 1ng/ml and above and less than 2ng/ml, n is selected from any value from 0.5007 to 0.7984; n is preferably 0.6496; when the subject's AMH level is 2ng/ml and above and less than 4ng/ml, n is selected from any value from 0.6883 to 0.9896; n is preferably When the subject’s AMH level is 4ng/ml and above, n is selected from any value from 0.8385 to 1.1557; n is preferably 0.9971; when the subject’s basic FSH is less than 3IU/L, j is selected from any value from 0.0443 to 0.4112; j is preferably 0.2278; when the subject's basic FSH is 3IU/L and above and less than 5IU/L, j is selected from any value from -0.0972 to 0.2526; j is preferably 0.0777; when the subject’s basal FSH is 5IU/L and above and less than 8IU/L, j is selected from any value from -0.2618 to 0.0947; j is preferably -0.0835; when the subject When the AFC of the subject is less than 4, k=0; when the AFC of the subject is 4 or more and less than 8, k is selected from any value from 0.1599 to 0.4629; k is preferably 0.3114; When the subject’s AFC is 8 or more and less than 12, k is selected from any value from 0.3553 to 0.6735; k is preferably 0.5144; when the subject’s AFC is 12 or more, k is selected from Any number from 0.5027 to 0.8264; k is preferably 0.6645.

Example

Example 1 Selection of subjects initially used to construct a model

Based on data obtained from patients treated at Peking University Third Hospital between January 2017 and December 2017, a preliminary model construction was carried out. For the patient used for preliminary model construction, collect the basic and clinical characteristics of the patient, including surname, medical record number, serial number, age, BMI index, duration of infertility, previous in vitro fertilization/intracytoplasmic sperm injection -Number of embryo transfer (IVF/ICSI-ET) attempts, serum basal E ₂ level, FSH level and LH level, serum AMH level, left and right ovarian AFCs, first, second, third, fourth and first infertility Five reasons, traditional or mild ovarian stimulation cycle, ovarian stimulation type/COS regimen, starting and total dose of recombinant rFSH, duration of rFSH treatment (days), name of rFSH, human chorionic gonadotropin (hCG) Endometrial thickness on trigger day, date of oocyte retrieval, and NROs. A total of 17,380 patients’ preliminary data were collected from January 2017 to December 2017, and patients suitable for the construction of the preliminary model were selected based on the following criteria, and the patient population for the construction of the model was confirmed.

The criteria included in model construction are:

1) Women between 20 and 45 years old;

2) BMI≤30;

3) The previously tried treatment cycle ≤ 2;

4) Test all hormone levels in the endocrine laboratory of Peking University Third Hospital;

5) The patient received a standard GnRH antagonist ovarian stimulation regimen.

The data of patients who meet the above 5 criteria are included in the patient population used to construct the model for subsequent model construction.

The criteria for exclusion from the model population is to exclude the patient if any of the following conditions are met: 1) Treated or untreated ovarian cysts; 2) Previous ovarian surgery; 3) Polycystic ovary syndrome (PCOS) or 3 Use oral contraception within one month; 4) Previously suffered from metabolic or endocrine diseases; 5) Previous tuberculosis; 6) History of pregnancy within 3 months; 7) Previous radiotherapy or chemotherapy; 8) Received PGD (preimplantation inheritance) Couples who have studied screening/PGS (preimplantation genetic diagnosis technology).

Based on the above exclusion and inclusion criteria, the data of 1523 patients were finally selected from the data of 17,380 patients for the construction of the system model of the present invention. Among the 1523 patients, 539 patients were due to male factor-induced infertility, 16 patients were due to endometriosis-induced infertility, 454 patients were due to fallopian tube factor-induced infertility, and 514 patients The patient has unexplained or mixed or other types of infertility. Table 1 below lists the median and quartile of basic characteristics and NVI.

COS treatment

The standard GnRH antagonist ovarian stimulation regimen is performed as follows: human rFSH (eg, Gonal-F alfa [Merck Serono, Germany], Puregon beta [MSD, USA], Urofollitropin [Livzon Pharmaceutical Group Inc., China] or Menotrophins [Livzon Pharmaceutical ] Group Inc., China]) started to do the drug on the second day of the menstrual cycle. The starting dose of human rFSH is selected based on age, AMH level, basal FSH level, AFC level, and BMI. The dose of rFSH was further adjusted according to the size and number of growing follicles observed by ultrasound and the _{level of serum E 2 during monitoring of ovarian stimulation.} When the diameter of the growing follicle reaches 10-12mm, GnRH antagonist treatment is started.

When the diameter of at least two dominant follicles exceeds 18mm is observed by ultrasound, the dose of hCG (Choriogonadotropin alfa, Merck Serono) is injected at 5000-10000IU to trigger the final oocyte maturation. Oocyte recovery was performed 36-38 hours after hCG administration. Transfer one or two embryos or cryopreserve embryos. Later, patients or subjects were provided with progesterone support during the luteal phase (progesterone vaginal gel, Merck Serono).

Antral follicle count measurement, sampling and endocrine determination

The two ovarian follicles with a diameter of 2-10 mm were measured on the second day of the menstrual cycle by transvaginal ultrasound scanning to calculate AFC. On the same day, venous blood samples were collected to determine _{the concentration of FSH, LH and E 2} in the serum. Blood is drawn on any day of the menstrual cycle for AMH detection. The collected blood samples were immediately inverted five times, and then after centrifugation and incubation for 30 minutes, the serum concentrations of these markers were evaluated.

Serum measurements of FSH, LH, and E ₂ were all performed using Siemens Immulite 2000 immunoassay system (Siemens Healthcare Diagnostics, Shanghai, PR China). The three-level quality control of FSH, LH and E ₂ was provided by Bio-RAD Laboratories (Lyphochek Immunoassay Plus Control, Trilevel, catalog number 370, lot number 40340). The serum AMH concentration was measured using an ultra-sensitive ELISA (Ansh Labs, USA) kit. The coefficient of variation for quality control AMH, FSH and LH less than 6%, less than 10% for E _2.

Table 1 The median of the clinical and basic characteristics of the 1523 patients selected

To	25% quantile	median	75% quantile
age	29	33	37
BMI(kg/m2)	20.2	twenty two	24.2
Basic FSH (IU/L)	5.5	6.9	8.8
Basic LH (IU/L)	2.4	3.5	4.9
Basic E 2 (pmol/L)	134.0	168.0	210.0
AMH(ng/ml)	1.1	2.2	4.0
AFC	6	9	13
Endometrial thickness on hCG trigger day (mm)	9	10	12
rFSH starting dose (IU)	150	225	300
Number of oocytes obtained (NROs)	5	9	12

Example 2 Model construction factor selection

Regression model selection

With regard to the data of the above 1523 patients, first determine the distribution of the number of oocytes obtained. Since the number of oocytes obtained is count data, Poisson distribution or negative binomial distribution can usually be considered. In this example, JMP Pro v.14 software was used to test the goodness of fit of the Poisson distribution and the negative binomial distribution. The results show that as shown in Figure 1, the data deviates from the Poisson distribution (χ ² =7026.46, P<0.001 ) Obey the negative binomial distribution (χ ² =1660.35, P=0.77). Figure 1 shows the fitting conditions when using Poisson distribution and negative binomial distribution respectively. From the results in Figure 1, it can be seen that using negative binomial distribution can better fit the number of oocytes (NROs) obtained. Since the acquired data of the number of oocytes obeys the negative binomial distribution, in this embodiment below, the negative binomial regression based on the negative binomial distribution is used to process the data.

Classification of influencing factors

Considering the following reasons, in this embodiment, the detected continuous variable analysis indicators are converted into categorical data. This is because there is obvious correlation between the various indicators in the construction model, which will lead to collinearity and reduce the model’s performance. Predictive performance, classification and division can better show the relationship between each index and the number of oocytes obtained; (2) The classification data is easier to interpret in practice and easier to apply. The assignment of each index is shown in Table 2, and the influencing factors in the following table are divided into 4 or 5 groups according to the assignment of Table 2. Among them, the age group is divided into four groups, namely less than 30 years old, at this time the classification data for age is 0; 30 years old and less than 35 years old, at this time the classification data for age is 1; 35 years old and less than 40 years old, at this time The categorical data for age is 2; over 40 years old, the categorical data for age at this time is 3. The BMI index is divided into four groups, which are less than 18.5, and the classification data of BMI is 0 at this time; 18.5 and less than 24, the classification data of BMI is 1 at this time; more than 24 and less than 27, the classification data of BMI is 2 at this time; And above 27, the classification data of BMI is 3. AMH is divided into 5 groups, respectively, AMH is less than 0.5ng/ml, the classification data of AMH is 0 at this time; AMH is above 0.5 and less than 1ng/ml, and the classification data of AMH is 1 at this time; AMH is more than 1 and less than 2ng /ml, the classification data of AMH is 2 at this time; when AMH is above 2 and less than 4ng/ml, the classification data of AMH is 3 at this time; and when AMH is above 4ng/ml, the classification data of AMH is 4. AFC is divided into 4 groups, respectively, AFC is less than 4, at this time the classification data of AFC is 0; AFC is more than 4 and less than 8, at this time, the classification data of AFC is 1; AFC is more than 8 and less than 12 , The classification data of AFC is 2 at this time; AFC is more than 12, and the classification data of AFC is 3. The basic FSH level is divided into 4 groups, respectively, the basic FSH is less than 3IU/L, and the classification data of the basic FSH is 0; the basic FSH is above 3IU/L and less than 5IU/L, and the classification data of the basic FSH is 1 at this time; When the basic FSH is above 5IU/L and less than 8IU/L, the classification data of the basic FSH is 2; when the basic FSH is above 8IU/L, the classification data of the basic FSH is 3. The basic LH level is divided into 4 groups, respectively, the basic LH level is less than 2IU/L, the classification data of the basic LH level at this time is 0; the basic LH is above 2IU/L and less than 5IU/L, the classification data of the basic LH level at this time When the basic LH level is above 5IU/L and less than 8IU/L, the classification data for the basic LH level is 2; and when the basic LH level is above 8IU/L, the classification data for the basic LH level is 3. E ₂ were divided into 4 basic groups, which are the basis of E ₂ level is less than 150pmol / L, E ₂ level at this time based classification data is 0; E ₂ level 150 based more and less than 200pmol / L, E ₂ case basis data classification level 1; E ₂ levels in the base 200 and less than 250pmol / L, E ₂ level at this time based classification data is 2; E ₂ levels based 250pmol / L or more, this time based classification level E ₂ The data is 3. The starting dose of rFSH is divided into 4 groups, respectively, the starting dose of rFSH is less than 150IU, the classification data of the starting dose of rFSH is 0; the starting dose of rFSH is above 150IU and less than 250IU, the classification data of the starting dose of rFSH at this time If the starting dose of rFSH is above 250IU and less than 300IU, the classification data of the starting dose of rFSH is 2; and the starting dose of rFSH is above 300IU, and the classification data of the starting dose of rFSH is 3.

Table 2 Assignment of indicators

Univariate analysis

Using the software JMP Pro v.14, applying negative binomial regression, analyze the influence of a single factor on the outcome variable (the number of eggs obtained, or NROs). It can be seen that in the univariate analysis, age, AMH, FSH, rFSH, AFC, BMI, LH, and infertility factors are all statistically significant. The basic E ₂ level is not statistically significant, and its RR values are very close to 1. Therefore, in the subsequent analysis, the basic E ₂ level is first excluded from the model construction.

Table 3 Results of single factor analysis

Example 3 Building a prediction model

As mentioned above, negative binomial regression is selected to construct the statistical model, the selection of predictive indicators adopts the pruning forward method and holdback verification, and the software JMP Pro v.14 is used to establish a predictive model, and the data set composed of the above 1523 patients is randomly divided There are two parts, one part is used as the training set (1066 data, 70%), and the other part is used as the validation set (457 data, 30%).

First, build a model in the training set, and verify the effect of the model in the verification set. The choice of prediction model is mainly based on the negative log likelihood in the validation set. The lower the negative log likelihood in the validation set, the better the model.

Figure 2 shows the variable selection process of the pruned forward method. Specifically, except for the excluded E ₂ , the other single factors are included in the multi-factor negative binomial regression model. After the pruned forward method and holdback verification, the figure is obtained The model of 2 can be seen from Figure 2. In the third step, the negative log likelihood value in the verification set is the lowest at this time, so the model at this time is taken as the optimal model. At this time, the variables included in the model are AMH, FSH, and AFC. At this time, the parameter estimation results of each variable in the prediction model are shown in Table 4, and Table 4 further shows the 95% confidence interval of each parameter.

Table 4 Parameter estimation results of the prediction model

Based on the above method, the following formula 1 is confirmed in this embodiment.

Log(NROs)=m+n*AMH classification data+j*basic FSH classification data+k*AFC classification data (formula 1)

Wherein n, j and k are determined based on the classification data of the AMH, basic FSH and AFC; wherein m is selected from any value in the range of 0.7435 to 1.2111, and m is preferably 0.9733;

When performing the calculation, the module for predicting the number of oocytes obtained during ovarian stimulation is based on the subject’s anti-Mullerian hormone (AMH) level and basal follicle stimulating hormone (FSH) collected by the data collection module Level, antral follicle count (AFC) data are judged, and the values of n, j and k are confirmed according to the following criteria;

When the subject's AMH level is less than 0.5ng/ml, n=0;

When the subject's AMH level is 0.5 ng/ml and above and less than 1 ng/ml, n is selected from any value from 0.1994 to 0.5153; n is preferably 0.3574;

When the subject's AMH level is 1 ng/ml and above and less than 2 ng/ml, n is selected from any value from 0.5007 to 0.7984; n is preferably 0.6496;

When the subject's AMH level is 2ng/ml and above and less than 4ng/ml, n is selected from any value in the range of 0.6883 to 0.9896; n is preferably 0.8390;

When the subject's AMH level is 4ng/ml and above, n is selected from any value from 0.8385 to 1.1557; n is preferably 0.9971;

When the subject’s basal FSH is less than 3IU/L, j is selected from any value from 0.0443 to 0.4112; j is preferably 0.2278;

When the subject's basic FSH is 3IU/L and above and

When it is less than 5IU/L, j is selected from any value from -0.0972 to 0.2526; j is preferably 0.0777;

When the subject's basal FSH is 5IU/L and above and less than 8IU/L, j is selected from any value from -0.2618 to 0.0947; j is preferably -0.0835;

When the subject's AFC is less than 4, k=0;

When the AFC of the subject is 4 or more and less than 8, k is selected from any value from 0.1599 to 0.4629; k is preferably 0.3114;

When the subject's AFC is 8 or more and less than 12, k is selected from any value in the range of 0.3553 to 0.6735; k is preferably 0.5144;

When the AFC of the subject is 12 or more, k is selected from any value in the range of 0.5027 to 0.8264; k is preferably 0.6645.

The prediction effect of the model built with the above method for the training set and the verification set is shown in Figure 3. In Figure 3, the abscissa shows the NROs predicted by the model, that is, the predicted number of oocytes obtained by the subject under the standard antagonist regimen, and the ordinate shows the actual detected acquisition of the subject The number of oocytes can be seen as shown in Figure 3. The model constructed above has achieved good prediction effects in both the training set and the verification set, and the predicted data is in good agreement with the actual detected number. Furthermore, the residual distributions of the training set and the validation set are shown in Figure 4. It can be seen that the residuals are normally distributed. It can be seen that the system constructed in this embodiment can be used to make a good prediction of the number of oocytes obtained by the subject.

Although the embodiments of the present invention are described above with reference to the accompanying drawings, the present invention is not limited to the above specific embodiments and application fields. The above specific embodiments are only illustrative, instructive, and not restrictive. . Under the enlightenment of this specification and without departing from the scope of protection of the claims of the present invention, those of ordinary skill in the art can also make many forms, which all belong to the protection of the present invention.

Claims (9)

1. A system for predicting the number of oocytes obtained during ovarian stimulation of a subject, which includes:

   A data collection module, which is used to obtain data of the subject's anti-Mullerian hormone (AMH) level, basal follicle stimulating hormone (FSH) level, and antral follicle count (AFC); and

   A module for predicting the number of oocytes obtained during ovarian stimulation, which is used to calculate the above-mentioned data obtained in the data collection module, so as to calculate the number of oocytes (NROs) obtained by the subject.
2. The system of claim 1, wherein:

   The subject is a subject who will receive a standard GnRH antagonist regimen for ovulation induction therapy.
3. The system according to claim 1 or 2, wherein:

   In the module for predicting the number of oocytes obtained during ovarian stimulation, the anti-Mullerian hormone (AMH) level and basic follicle stimulation are stored in advance based on the existing database of patients who have received standard GnRH antagonist ovulation therapy. Categorical data converted from the data of FSH (FSH) level and antral follicle count (AFC), and based on the pre-stored patient’s categorical data and the negative binomial distribution fitting to predict the subject’s acceptance of the standard GnRH The formula of the number of oocytes (NROs) obtained during ovarian stimulation during ovulation induction therapy with antagonist regimen.
4. The system according to any one of claims 1 to 3, wherein:

   In the data collection module, the collected anti-Mullerian hormone (AMH) level refers to the anti-Mullerian hormone concentration in the venous blood of a female subject at any point in the menstrual period. The basic follicle stimulating hormone (FSH) level refers to the concentration of follicle stimulating hormone in the venous blood of female subjects during menstruation for 2-4 days, and the antral follicle count (AFC) refers to the vaginal B-ultrasound count of female subjects during menstruation for two The number of all visible follicles with a diameter of 2-10mm in each ovary.
5. The system of claim 4, wherein:

   In the module for predicting the number of oocytes obtained during ovarian stimulation, when calculating with the formula, the AMH level converted from the subject's anti-Mullerian hormone (AMH) level collected by the data collection module Categorize data for calculations,

   The classification data of AMH is obtained by dividing the subjects' anti-Mullerian hormone (AMH) levels collected by the data acquisition module into five groups and assigning different classification data as follows:

   When AMH is less than 0.5ng/ml, the classification data of AMH is 0;

   When AMH is 0.5ng/ml and above and less than 1ng/ml, the classification data of AMH is 1;

   When AMH is 1ng/ml and above and less than 2ng/ml, the classification data of AMH is 2;

   When AMH is 2ng/ml and above and less than 4ng/ml, the classification data of AMH is 3; and

   When AMH is 4ng/ml and above, the classification data of AMH is 4.
6. The system of claim 4, wherein:

   In the module for predicting the number of oocytes obtained in the process of ovarian stimulation, the basic FSH classification converted from the subject's basic follicle stimulating hormone (FSH) level collected by the data acquisition module when calculating with the formula Data to calculate,

   The basic FSH classification data is obtained by dividing the subjects’ Follicle Stimulating Hormone (FSH) levels collected by the data acquisition module into four groups and assigning different classification data as follows:

   When the basic FSH is less than 3IU/L, the classification data of the basic FSH is 0;

   When the basic FSH is 3IU/L and above and less than 5IU/L, the classification data of the basic FSH is 1;

   When the basic FSH is 5IU/L and above and less than 8IU/L, the classification data of the basic FSH is 2;

   When the basic FSH is 8IU/L and above, the classification data of the basic FSH is 3.
7. The system of claim 4, wherein:

   In the module for predicting the number of oocytes obtained in the process of ovarian stimulation, when calculating with the formula, the classification data of AFC converted from the subject's antral follicle count (AFC) collected by the data acquisition module is used for calculation,

   The classification data of AFC is obtained by dividing the subject's antral follicle count (AFC) data collected by the data acquisition module into four groups and assigning different classification data as follows:

   When AFC is less than 4, the classification data of AFC is 0;

   When AFC is 4 or more and less than 8, the classification data of AFC is 1;

   When AFC is 8 or more and less than 12, the classification data of AFC is 2;

   When AFC is 12 or more, the classification data of AFC is 3.
8. The system according to any one of claims 3-7, wherein:

   The formula used to calculate the number of oocytes (NROs) obtained during ovarian stimulation is the AMH classification data determined by the subject's AMH level collected by the data collection module, and the subject's basic FSH level The determined FSH classification data and the subject's AFC determined AFC classification data are calculated to obtain the formula for the number of oocytes (NROs).
9. The system according to claim 8, wherein:

   The formula is the following formula one:

   Log(NROs)=m+n*AMH classification data+j*basic FSH classification data+k*AFC classification data (formula 1);

   Wherein n, j and k are determined based on the classification data of the AMH, basic FSH and AFC;

   Wherein m is selected from any value from 0.7435 to 1.2111, and m is preferably 0.9733;

   When performing the calculation, the module for predicting the number of oocytes obtained during ovarian stimulation is based on the subject’s anti-Mullerian hormone (AMH) level and basal follicle stimulating hormone (FSH) collected by the data collection module Level, antral follicle count (AFC) data are judged, and the values of n, j and k are confirmed according to the following criteria;

   When the subject's AMH level is less than 0.5ng/ml, n=0;

   When the subject's AMH level is 0.5 ng/ml and above and less than 1 ng/ml, n is selected from any value from 0.1994 to 0.5153; n is preferably 0.3574;

   When the subject's AMH level is 1 ng/ml and above and less than 2 ng/ml, n is selected from any value from 0.5007 to 0.7984; n is preferably 0.6496;

   When the subject's AMH level is 2ng/ml and above and less than 4ng/ml, n is selected from any value in the range of 0.6883 to 0.9896; n is preferably 0.8390;

   When the subject's AMH level is 4ng/ml and above, n is selected from any value from 0.8385 to 1.1557; n is preferably 0.9971;

   When the subject’s basal FSH is less than 3IU/L, j is selected from any value from 0.0443 to 0.4112; j is preferably 0.2278;

   When the subject's basal FSH is 3IU/L and above and less than 5IU/L, j is selected from any value from -0.0972 to 0.2526; j is preferably 0.0777;

   When the subject's basal FSH is 5IU/L and above and less than 8IU/L, j is selected from any value from -0.2618 to 0.0947; j is preferably -0.0835;

   When the subject's AFC is less than 4, k=0;

   When the AFC of the subject is 4 or more and less than 8, k is selected from any value from 0.1599 to 0.4629; k is preferably 0.3114;

   When the subject's AFC is 8 or more and less than 12, k is selected from any value in the range of 0.3553 to 0.6735; k is preferably 0.5144;

   When the AFC of the subject is 12 or more, k is selected from any value from 0.5027 to 0.8264; k is preferably 0.6645.

Images