CN110491505B - System for predicting the number of oocytes obtained during ovarian stimulation of a subject - Google Patents
System for predicting the number of oocytes obtained during ovarian stimulation of a subject Download PDFInfo
- Publication number
- CN110491505B CN110491505B CN201910780793.6A CN201910780793A CN110491505B CN 110491505 B CN110491505 B CN 110491505B CN 201910780793 A CN201910780793 A CN 201910780793A CN 110491505 B CN110491505 B CN 110491505B
- Authority
- CN
- China
- Prior art keywords
- subject
- amh
- afc
- less
- fsh
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Bioethics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Surgery (AREA)
- Urology & Nephrology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention relates to a system for predicting the number of oocytes obtained during ovarian stimulation of a subject if the subject is undergoing a standard GnRH antagonist regimen for ovulation induction treatment, comprising: a data acquisition module for acquiring data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, Antral Follicle Count (AFC) of a subject; and a module for predicting the number of oocytes obtained during ovarian stimulation, for calculating the information obtained in the data acquisition module, thereby calculating the number of oocytes obtained (NROs) of the subject.
Description
Technical Field
The present invention relates to a system and method for predicting the number of oocytes obtained during ovarian stimulation in a subject undergoing standard GnRH antagonist protocol ovulation induction therapy.
Background
For women undergoing Controlled Ovarian Stimulation (COS) and IVF/ICSI cycles, The number of oocytes harvested (NROs) is considered a powerful surrogate prognostic marker for successful pregnancy. Optimal NROs help to improve Live-birth-rate (LBR).
Predicting NROs prior to Controlled Ovarian Stimulation (COS) is the only method to deliver effective and safe treatment. A variety of markers have been used to assess ovarian response, including, for example, age, basal Follicle Stimulating Hormone (FSH), Antral Follicle Count (AFC), and anti-mullerian hormone (AMH), which have been widely used to predict ovarian responsiveness. To date, no single marker of ovarian reserve could completely replace other indicators. The clinician will typically select a starting dose of recombinant FSH (rfsh) based on clinical experience with women, such as previous ovarian response history, age, AMH, AFC, basal FSH, Body Mass Index (BMI), etc.
Disclosure of Invention
In view of the above, and the necessity of predicting NROs, the present invention aims to provide an effective system which can be used to predict the number of oocytes obtained if a subject is subjected to ovulation induction with a standard GnRH antagonist, and which can be combined with other systems to better guide the ovulation induction protocol and the selection of recombinant FSH dosage in the future. The present invention explores a reliable system for predicting the acceptance of NROs in gonadotropin releasing hormone (GnRH) antagonist regimens. Further, since the hormone levels in the GnRH antagonist regimen are virtually any basic hormone level of humans, the system of the present invention may be of great significance in the general population for pre-COS assessment and clinical counseling during ovarian stimulation. The use of the systems or methods of the present invention is beneficial for pregnancy outcomes in NROs and women receiving Assisted Reproductive Technology (ART) therapy.
Predicting the Number of oocytes (NROs) during ovarian stimulation is the only method for effective and safe treatment. Logistic regression analysis has been widely used to predict the presence or absence of an adverse ovarian response. However, the classification of NROs into two categories (i.e., hypo-responsive or not) is not specific and sufficient for individuals. Currently, there is very little research directed at predicting specific NROs, which hampers the development of personalized treatments in assisted reproductive technologies.
In summary, the present invention relates to the following:
a system for predicting the number of oocytes obtained during ovarian stimulation in a subject, comprising: a data acquisition module for acquiring data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, Antral Follicle Count (AFC) of a subject; and a module for predicting the number of oocytes harvested during ovarian stimulation, for calculating the data captured in the data acquisition module to calculate the number of oocytes harvested (NROs) of the subject.
In a particular embodiment of the invention, the subject is one who is to be treated for ovulation induction with a standard GnRH antagonist regimen.
In another specific embodiment of the present invention, in the module for predicting the number of oocytes obtained during ovarian stimulation, classification data converted from data of anti-mullerian hormone (AMH), basal Follicle Stimulating Hormone (FSH) and sinus follicle count (AFC) of a patient who has undergone ovulation induction treatment by a standard GnRH antagonist regimen in an existing database, and a formula for predicting the number of oocytes (NROs) obtained during ovarian stimulation of a subject who has undergone ovulation induction treatment by a standard GnRH antagonist regimen, which is fitted based on the pre-stored classification data of the patient and the negative binomial distribution, are stored in advance.
In this context, a patient is a subject who has received standard GnRH antagonist regimens for ovulation induction therapy and during the course of treatment, data is collected for anti-mullerian hormone (AMH) levels, basal Follicle Stimulating Hormone (FSH) levels, and Antral Follicle Count (AFC) for constructing a model for calculating NROs.
In this context, the subject is intended to receive standard GnRH antagonist regimens for ovulation induction therapy, and by measuring data on anti-mullerian hormone (AMH) levels, basal Follicle Stimulating Hormone (FSH) levels, sinus follicle count (AFC) thereof, the number of oocytes (NROs) obtained during ovarian stimulation can be predicted using the systems and methods of the invention.
In another specific embodiment of the present invention, in the data collection module, the collected anti-mullerian hormone (AMH) level refers to the concentration of anti-mullerian hormone in venous blood of the female subject at any time point during the menstruation period, the basal Follicle Stimulating Hormone (FSH) level refers to the concentration of follicle stimulating hormone in venous blood of the female subject for 2-4 days during the menstruation period, and the Antral Follicle Count (AFC) refers to the number of all visible follicles with a diameter of 2-10mm in both ovaries of the female subject when they are super-counted in the vagina for 2-4 days during the menstruation period.
In another specific embodiment of the present invention, in the module for predicting the number of oocytes obtained during ovarian stimulation, the calculation is performed using classification data of subject anti-mullerian hormone (AMH) converted from AMH acquired by the data acquisition module when the calculation is performed using the formula,
classification data of AMH was obtained by classifying the anti-mullerian hormone (AMH) levels of the subjects collected by the data collection module into five groups and assigning different classification data, respectively, as follows,
when AMH is less than 0.5ng/ml, the classification data of AMH is 0;
when AMH is 0.5ng/ml or more and less than 1ng/ml, the classification data of AMH is 1;
when AMH is 1ng/ml or more and less than 2ng/ml, the classification data of AMH is 2;
when the AMH is 2ng/ml or more and less than 4ng/ml, the classification data of the AMH is 3; and
when AMH is 4ng/ml or above, the classification data of AMH is 4.
In another embodiment of the present invention, in the means for predicting the number of oocytes obtained during ovarian stimulation, the calculation is performed using classification data of basal Follicle Stimulating Hormone (FSH) obtained by converting the basal FSH level of the subject collected by the data collection means when the calculation is performed using the formula,
the classification data of the basal FSH is obtained by classifying the subject's Follicle Stimulating Hormone (FSH) levels collected by the data collection module into four groups and assigning different classification data to each group 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 or more and less than 5IU/L, the classification data of the basic FSH is 1;
when the basic FSH is 5IU/L or more and less than 8IU/L, the classification data of the basic FSH is 2;
the classification data of the basal FSH was 3 when the basal FSH was 8IU/L or more.
In another embodiment of the present invention, in the module for predicting the number of oocytes obtained during ovarian stimulation, the calculation is performed using classification data of subject sinus follicle count (AFC) transformed AFC acquired by the data acquisition module when the calculation is performed using the formula,
the classification data of AFC is obtained by classifying the subject's Antral Follicle Count (AFC) data collected by the data collection module into four groups and assigning different classification data to each group as follows,
when AFC is less than 4, the classification data of the AFC is 0;
when AFC is 4 or more and less than 8, the classification data of the 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 a formula for calculating the number of oocytes (NROs) obtained using classification data of AMH determined by AMH level of the subject, FSH classification data determined by basal FSH level of the subject and classification data of AFC determined by AFC of the subject collected by the data collection module.
In another specific embodiment of the present invention, the above formula is the following formula one:
log (nros) ═ m + n AMH classification data + j basic FSH classification data + k AFC classification data (formula one);
wherein n, j and k determine values based on the AMH, basal FSH and AFC classification data; wherein m is any value of 0.7435-1.2111, and m is preferably 0.9733;
in the calculating, the module for predicting the number of oocytes obtained during ovarian stimulation judges based on the data of anti-mullerian hormone (AMH), basal Follicle Stimulating Hormone (FSH), and Antral Follicle Count (AFC) of the subject collected by the data collecting module, and confirms 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 is 0;
when the subject's AMH level is 0.5ng/ml and above and less than 1ng/ml, n is selected from any of values 0.1994-0.5153; 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 number from 0.5007-0.7984; 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 of 0.6883-0.9896; n is preferably 0.8390;
when the subject has AMH levels of 4ng/ml and above, n is selected from any value of 0.8385-1.1557; n is preferably 0.9971;
j is selected from any of values 0.0443-0.4112 when the subject's basal FSH is less than 3 IU/L; j is preferably 0.2278;
j is selected from any of-0.0972-0.2526 when the subject's basal FSH is 3IU/L and above and less than 5 IU/L; j is preferably 0.0777;
when the subject's basal FSH is 5IU/L or more and less than 8IU/L, j is selected from any value of-0.2618-0.0947; j is preferably-0.0835;
when the subject has less than 4 AFCs, k is 0;
k is selected from any of 0.1599-0.4629 when the subject has AFC of 4 and more and less than 8; k is preferably 0.3114;
k is selected from any of 0.3553-0.6735 when the subject has AFC of 8 and more and less than 12; k is preferably 0.5144;
when the subject has AFC of 12 and above, k is selected from any value of 0.5027-0.8264; k is preferably 0.6645.
The present invention also relates to a method for predicting the number of oocytes obtained during ovarian stimulation of a subject comprising: a data acquisition step of acquiring data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, Antral Follicle Count (AFC) of the subject; and predicting the number of oocytes obtained during ovarian stimulation by calculating the data obtained from the data acquisition module to calculate the number of oocytes obtained (NROs) of the subject.
In the above method, the subject is one who is to be treated for ovulation induction by a standard GnRH antagonist regimen.
In the above method, in the step of predicting the number of oocytes obtained during ovarian stimulation, a formula for predicting the number of oocytes (NROs) obtained during ovarian stimulation of a subject undergoing ovulation induction treatment with a standard GnRH antagonist regimen is calculated using classification data obtained by converting data into pre-stored data based on the level of anti-mullerian hormone (AMH), the level of basal Follicle Stimulating Hormone (FSH), and the sinus follicle count (AFC) of a subject undergoing ovulation induction treatment with a standard GnRH antagonist regimen in an existing database, and a formula for predicting the number of oocytes (NROs) obtained during ovarian stimulation of a subject undergoing ovulation induction treatment with a standard GnRH antagonist regimen fitted to the pre-stored classification data of the subject.
In the above method, in the data collecting step, the collected anti-mullerian hormone (AMH) level refers to an anti-mullerian hormone concentration in venous blood of the female subject at any time point during the menstruation period, the basal Follicle Stimulating Hormone (FSH) level refers to a follicle stimulating hormone concentration in venous blood of the female subject for 2-4 days during the menstruation period, and the Antral Follicle Count (AFC) refers to the number of all visible follicles having a diameter of 2-10mm in both ovaries at which the female subject is hypercomputed for 2-4 days during the vaginal B-hypercomputation period.
In the above method, in the step of predicting the number of oocytes obtained during ovarian stimulation, the calculation is performed using classification data of subject anti-mullerian hormone (AMH) into which AMH levels are converted, collected by the data collection module, when the calculation is performed using the formula,
classification data of AMH was obtained by classifying the anti-mullerian hormone (AMH) levels of the subjects collected by the data collection module into five groups and assigning different classification data, respectively, as follows,
when AMH is less than 0.5ng/ml, the classification data of AMH is 0;
when AMH is 0.5ng/ml or more and less than 1ng/ml, the classification data of AMH is 1;
when AMH is 1ng/ml or more and less than 2ng/ml, the classification data of AMH is 2;
when the AMH is 2ng/ml or more and less than 4ng/ml, the classification data of the AMH is 3; and
when AMH is 4ng/ml or above, the classification data of AMH is 4.
In the above method, in the step of predicting the number of oocytes obtained during ovarian stimulation, the calculation is performed using classification data of basal Follicle Stimulating Hormone (FSH) obtained by converting the basal FSH level of the subject collected by the data collection module when the calculation is performed using the equation,
the classification data of the basal FSH is obtained by classifying the subject's Follicle Stimulating Hormone (FSH) levels collected by the data collection module into four groups and assigning different classification data to each group 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 or more and less than 5IU/L, the classification data of the basic FSH is 1;
when the basic FSH is 5IU/L or more and less than 8IU/L, the classification data of the basic FSH is 2;
the classification data of the basal FSH was 3 when the basal FSH was 8IU/L or more.
In the above method, in the step of predicting the number of oocytes obtained during ovarian stimulation, the calculation is performed using classification data of subject's Antral Follicle Count (AFC) transformed AFC acquired by the data acquisition module when the calculation is performed using the formula,
the classification data of AFC is obtained by classifying the subject's Antral Follicle Count (AFC) data collected by the data collection module into four groups and assigning different classification data to each group as follows,
when AFC is less than 4, the classification data of the AFC is 0;
when AFC is 4 or more and less than 8, the classification data of the 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 a formula for calculating the number of oocytes (NROs) obtained using classification data of AMH determined by the AMH level of the subject, FSH classification data determined by the basal FSH level of the subject, and AFC determined AFC classification data of the subject collected by the data collection module.
In the above method, the above formula is the following formula one:
log (nros) ═ m + n AMH classification data + j basic FSH classification data + k AFC classification data (formula one);
wherein n, j and k determine values based on the AMH, basal FSH and AFC classification data;
wherein m is any value of 0.7435-1.2111, and m is preferably 0.9733;
in the calculating, in the step of predicting the number of oocytes obtained during ovarian stimulation, judging based on data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, sinus follicle count (AFC) of the subject collected by the data collecting module, and confirming values of n, j, and k according to the following criteria;
when the subject's AMH level is less than 0.5ng/ml, n is 0;
when the subject's AMH level is 0.5ng/ml and above and less than 1ng/ml, n is selected from any of values 0.1994-0.5153; 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 number from 0.5007-0.7984; 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 of 0.6883-0.9896; n is preferably 0.8390;
when the subject has AMH levels of 4ng/ml and above, n is selected from any value of 0.8385-1.1557; n is preferably 0.9971;
j is selected from any of values 0.0443-0.4112 when the subject's basal FSH is less than 3 IU/L; j is preferably 0.2278;
j is selected from any of-0.0972-0.2526 when the subject's basal FSH is 3IU/L and above and less than 5 IU/L; j is preferably 0.0777;
when the subject's basal FSH is 5IU/L or more and less than 8IU/L, j is selected from any value of-0.2618-0.0947; j is preferably-0.0835;
when the subject has less than 4 AFCs, k is 0;
k is selected from any of 0.1599-0.4629 when the subject has AFC of 4 and more and less than 8; k is preferably 0.3114;
k is selected from any of 0.3553-0.6735 when the subject has AFC of 8 and more and less than 12; k is preferably 0.5144;
when the subject has AFC of 12 and above, k is selected from any value of 0.5027-0.8264; k is preferably 0.6645.
ADVANTAGEOUS EFFECTS OF INVENTION
Generally, if the number of eggs obtained from a subject can be accurately predicted, the more the number of eggs obtained is predicted, the lower the amount of gonadotropin to be used in the ovulation promoting treatment, and conversely, the more gonadotropin to be used in the ovulation promoting treatment. The system and method of the present invention can be used to more accurately predict the number of oocytes obtained during ovarian stimulation if a subject is undergoing standard GnRH antagonist regimen ovulation triggering therapy. And, it can be combined with other systems to better guide the ovulation induction protocol and the selection of recombinant FSH dosage to better achieve individualized treatment.
Drawings
Various other advantages and benefits of the present application will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. It is obvious that the drawings described below are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. Also, like parts are designated by like reference numerals throughout the drawings.
FIG. 1 shows the number of oocytes obtained from the fitting of the Poisson distribution and the negative binomial distribution, respectively.
FIG. 2 shows the variable screening process of the forward method of pruning.
FIG. 3 predicts the predictive effect of the model in the training set and validation set.
Fig. 4 residual distribution plots of the prediction model in the training set and the validation set.
Detailed Description
Specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While specific embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
It should be noted that certain terms are used throughout the description and claims to refer to particular components. As one skilled in the art will appreciate, various names may be used to refer to a component. This specification and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. The description which follows is a preferred embodiment of the invention, but is made for the purpose of illustrating the general principles of the invention and not for the purpose of limiting the scope of the invention. The scope of the present invention is defined by the appended claims.
Several factors involved in infertility in this application are defined below. The first cause or factor of infertility in this context is a male factor; the second cause or factor is endometriosis; the third cause or factor is an oviduct factor; the fourth cause or factor is the other factor.
Male factors refer to all infertility due to male causes.
Endometriosis refers to a common gynecological disease in women, wherein active endometrial cells are planted in a position except endometrium. The endometrial cells should grow in the uterine cavity, but because the uterine cavity is communicated with the pelvic cavity through the fallopian tube, the endometrial cells can enter the pelvic cavity through the fallopian tube to grow ectopically. The main pathological changes of endometriosis are ectopic intimal periodic hemorrhage and fibrosis of surrounding tissues, and the formation of ectopic nodules, dysmenorrhea, chronic pelvic pain, abnormal menstruation and infertility are the main symptoms. Lesions can spread to all pelvic tissues and organs, are most common in parts such as ovary, uterine rectum pouch, uterosacral ligament and the like, and can also occur in abdominal cavity, thoracic cavity, limbs and the like.
The fallopian tube factor means that fallopian tube obstruction or dysfunction becomes a major cause of female infertility because it has important functions of transporting sperm, picking up ovum, and transporting fertilized ovum to uterine cavity. The reasons for tubal obstruction or dysfunction are acute and chronic salpingitis.
In the present application, other factors include exclusion of male factors, endometrial factors, fallopian tube factors, and other infertility factors that are not etiologic in the three categories.
Variable types: in statistics, variable types can be divided into quantitative variables and qualitative variables (also called categorical variables).
The quantitative variables are variables for describing the number and quantity of things, and can be classified into a continuous type and a discrete type. The continuous variable refers to a variable which can be arbitrarily valued in a certain interval, and the value is continuous and can have decimal points. For example, blood pressure, blood sugar level, height, weight, chest circumference, etc. measured by a human body are continuous variables, and the values thereof can be obtained only by a measurement or measurement method. A discrete variable is a variable whose value can only be in natural or integer units. For example, pain scores, lesion metastasis counts, egg counts, etc. are positive numbers only, and decimal points are not available, and the numerical values of these variables are generally obtained by numerical methods.
A classification variable is a variable used to describe a category of things. Categorical variables can be divided into two broad categories, unordered categorical variables and ordered categorical variables. Wherein, unordered categorical variable (unordered categorical variable) refers to the degree and order of difference between the categories or attributes being classified. It can be classified into two categories, such as sex (male and female), drug reaction (negative and positive), etc.; ② a plurality of classifications, such as blood type (O, A, B, AB), occupation (worker, agriculture, business, school, soldier), etc. And there is a degree of difference between the categories of the ordered categorical variable (the ordered categorical variable). For example, the urine glucose assay results are classified according to-, + +; the curative effects are classified according to cure, obvious effect, improvement and ineffectiveness. For the ordered classification variables, the variables are firstly grouped according to the grade sequence, the number of observation units of each group is counted, a frequency table of the ordered variables (each grade) is compiled, and the obtained data is called grade data.
The variable types are not invariable and conversion between the various types of variables is possible depending on the needs of the study. For example, the hemoglobin (g/L) is a primary numerical variable, and if the hemoglobin is divided into two categories according to the normal hemoglobin and the low hemoglobin, the two categories can be analyzed according to the two categories; if the blood is classified into five grades according to severe anemia, moderate anemia, mild anemia, normal and hemoglobin increase, the analysis can be performed according to grade data. The classifier data may also be quantified, e.g., the patient's nausea response may be expressed as 0, 1, 2, 3, and may be analyzed as numerical variable data (quantitative data).
Poisson distribution (Poisson distribution) is a discrete probability distribution (discrete probability distribution) that is commonly found in statistics and probability. The poisson distribution is suitable for describing the number of times a random event occurs per unit time (or space). Such as the number of disease cases occurring in a certain fixed space and time, the number of times a certain disease recurs, the number of sites of metastasis of a certain lesion, the number of vomits of a certain patient, and the like.
The negative binomial distribution is a statistically discrete probability distribution. A distribution called negative binomial that satisfies the following condition: the experiment comprises a series of independent experiments, each experiment has success and failure results, the success probability is constant, the experiment lasts until r times of success, and r is a positive integer. The negative binomial distribution, similar to the Poisson distribution, can also be used to describe the relative frequency of a rare event in space per unit time. It differs 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 oncomelania in soil, the distribution of an infectious disease, etc. Generally, if the mean value of the counting data is larger than the variance, the Poisson distribution is not good in fitting effect, and the negative binomial distribution can be considered.
In this application, anti-mullerian hormone (AMH) refers to a hormone secreted by the granulosa cells of ovarian follicles, which is produced by a baby girl during the fetal period, and the higher the number of follicles in the ovary, the higher the AMH concentration; on the contrary, when the follicles are gradually consumed with age and various factors, the AMH concentration is also decreased, and the closer to the menopause, the AMH tends to be 0.
In the present application, Follicle Stimulating Hormone (FSH) refers to a hormone secreted by anterior pituitary basophils, and is composed of glycoproteins, which mainly function to promote follicle maturation. FSH promotes proliferative differentiation of follicular granular layer cells and promotes overall ovarian growth. And acting on the seminal tubules of testis to promote spermatogenesis. FSH is secreted in humans in pulses, and in women varies with the menstrual cycle. The determination of FSH in serum has important significance for diagnosing and treating infertility and endocrine diseases, such as understanding pituitary endocrine function, indirectly understanding ovarian functional state, evaluating ovarian reserve and ovarian reactivity, and making ovulation-promoting drug dosage.
In this application, Antral Follicle Count (AFC) refers to the number of all visible follicles with a diameter of 2-10mm in both ovaries on a 2-4 day menstrual period. AFC can be measured and counted by ultrasound on follicles.
The basal E2 level refers to the estradiol level, which is a steroidal estrogen. The alpha type and the beta type have two types, and the alpha type has strong physiological action. It has a strong sex hormone action, so it or its ester is considered to be actually the most important sex hormone secreted by the ovary. In the present application, the detection of a basal estradiol level is the concentration of estradiol in a venous blood serum sample of a female subject taken 2-4 days per month.
BMI is an important international standard for measuring the obesity and health of human body, and is mainly used for statistical analysis. The determination of the degree of obesity cannot be made using the absolute value of weight, which is naturally related to height. Therefore, BMI obtains a relatively objective parameter through two values of the weight and the height of a human body, and measures the body mass by using the range of the parameter. BMI weight/height square (international unit kg/square meter)
Luteinizing Hormone (LH), a glycoprotein gonadotropin secreted by adenohypophysis cells, promotes the conversion of cholesterol into sex hormones in gonadal cells. In women, it works in conjunction with Follicle Stimulating Hormone (FSH) to promote follicular maturation, secretion of estrogen, ovulation, and production and maintenance of the corpus luteum, secretion of progestin and estrogen. For men, luteinizing hormone promotes synthesis and release of testosterone by leydig cells. LH levels refer to the LH concentration in a venous blood serum sample of female subjects from 2 to 4 days of menstruation.
Herein, rFSH refers to recombinant human follicle stimulating hormone. Wherein the initial dose of rFSH refers to the dose of recombinant FSH at the first injection for any ovulation-promoting regimen.
In this application, anti-mullerian hormone (AMH) level refers to the concentration of anti-mullerian hormone in the venous blood serum sample at any time point in the menstrual cycle of a female subject, Follicle Stimulating Hormone (FSH) level refers to the concentration of follicle stimulating hormone in the venous blood serum sample at 2-4 days of menstruation of a female subject, and Antral Follicle Count (AFC) refers to the number of all visible follicles with a diameter of 2-10mm in both ovaries when the female subject is undergoing a vaginal B-super count for 2-4 days of menstruation.
The standard GnRH antagonist ovarian stimulation protocol described herein is performed as follows: human recombinant FSH (human rFSH) (e.g., Gonal-F alfa [ Merck Serono, Germany)]，Puregon beta[MSD，USA],Urofollitropin[Livzon Pharmaceutical Group Inc.，China]Or Menotropphins [ Livzon Pharmaceutical ]]Group Inc.，China]) Dosing began on day 2 of the menstrual cycle. The selection is based on age, AMH level, basal FSH level, AFC level and BMI etc. for the initial dose of human rFSH. Monitoring the size and number of growing follicles during ovarian stimulation from ultrasoundSerum E2The levels were further adjusted for rFSH dose. GnRH antagonist treatment was initiated when the growing follicle reached a diameter of 10-12 mm. hCG (Chonogonodotropina alfa, Merck Serono) was injected at a dose of 5000-. Oocyte retrieval was performed 36-38 hours after hCG administration. Transferring one or two embryos or performing embryo cryopreservation. The subject was then provided luteal phase progesterone support (progesterone vaginal gel, Merck Serono).
In a particular embodiment of the present application, the present application is directed to systems and methods for which the subject is a subject undergoing ovulation-promoting treatment with a standard GnRH antagonist regimen as described above.
The present application relates to a system for predicting the number of oocytes obtained during ovarian stimulation of a subject, comprising: a data acquisition module for acquiring data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, Antral Follicle Count (AFC) of a subject; and a module for predicting the number of oocytes harvested during ovarian stimulation, for calculating the data captured in the data acquisition module to calculate the number of oocytes harvested (NROs) of the subject.
Those skilled in the art will appreciate that there are many factors that generally affect the number of oocytes harvested from a subject, such as BMI index, duration of infertility, number of previous in vitro fertilization/intracytoplasmic sperm injection-embryo transfer (IVF/ICSI-ET) attempts, serum basal E2Levels, FSH and LH levels, serum AMH levels, left and right ovarian AFCs, first, second, third, fourth and fifth causes of infertility, conventional or mild ovarian stimulation cycles, ovarian stimulation type/COS regimens, initial and total doses of recombinant rFSH, duration of rFSH treatment (days), rFSH name, endometrial thickness on the day of human chorionic gonadotropin (hCG) triggering, etc., but in this application, the inventors of the present application have conducted extensive studies to finally confirm the data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, sinus follicle count (AFC) of three important factorsThe parameters of interest to identify the NROs of the subject.
Herein, the data acquisition module is not limited as long as it can be used to acquire data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level and Antral Follicle Count (AFC) of the subject, wherein, specifically, the anti-mullerian hormone (AMH) level acquired by the data acquisition module refers to the anti-mullerian hormone concentration in venous blood of the female subject at any time point during the menstruation period, the basal Follicle Stimulating Hormone (FSH) level acquired by the data acquisition module refers to the follicle stimulating hormone concentration in venous blood of the female subject for 2-4 days after the menstruation period, and the Antral Follicle Count (AFC) acquired by the data acquisition module refers to the number of all visible follicles with a diameter of 2-10mm in two ovaries of the female subject when the vagina B is super-counted for 2-4 days after the menstruation period. Based on the subject's need to predict the number of oocytes obtained during ovarian stimulation, the data for a given period as described above can be taken to predict the number of eggs obtained based on the methods and systems of the present application.
In this context, the above data acquired in the data acquisition module is calculated using a module for predicting the number of oocytes obtained during ovarian stimulation, thereby calculating the number of oocytes acquired (NROs) of the subject. First, it should be understood that classification data converted from data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, and Antral Follicle Count (AFC) of a subject who has received ovulation-promoting treatment using a standard GnRH antagonist regimen in an existing database, and a formula for predicting the number of oocytes (NROs) obtained during ovarian stimulation of the subject when receiving ovulation-promoting treatment using a standard GnRH antagonist regimen, which is fitted based on the pre-stored classification data of the subject and a negative binomial distribution, are pre-stored in the module. With such a pre-stored formula, calculations can be made for any subject.
Specifically, the pre-stored formula is fitted using classification data that is pre-stored based on data derived from the anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, and Antral Follicle Count (AFC) of a patient undergoing ovulation induction treatment using a standard GnRH antagonist regimen in an existing database.
In the calculating, the pre-stored formula is a formula for calculating the number of oocytes (NROs) obtained using classification data of AMH determined by the AMH level of the subject, FSH classification data determined by the basal FSH level of the subject, and classification data of AFC determined by the AFC of the subject, which are collected by the data collection module.
As described above, although there are different conversion methods by those skilled in the art when converting a continuous variable into a categorical variable, the inventors of the present application have confirmed the following conversion methods through intensive studies. Classification data of AMH is obtained by classifying the anti-mullerian hormone (AMH) levels of the subject collected by the data collection module into five groups and assigning different classification data, respectively, as follows, when AMH is less than 0.5ng/ml, the classification data of AMH is 0; when AMH is 0.5ng/ml or more and less than 1ng/ml, the classification data of AMH is 1; when AMH is 1ng/ml or more and less than 2ng/ml, the classification data of AMH is 2; when the AMH is 2ng/ml or more and less than 4ng/ml, the classification data of the AMH is 3; and when AMH is 4ng/ml or above, the classification data of AMH is 4.
The classification data of the basic FSH is obtained by dividing the Follicle Stimulating Hormone (FSH) levels of the subject collected by the data collection module into four groups and assigning different classification data to the four groups, respectively, wherein 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 or more and less than 5IU/L, the classification data of the basic FSH is 1; when the basic FSH is 5IU/L or more and less than 8IU/L, the classification data of the basic FSH is 2; the classification data of the basal FSH was 3 when the basal FSH was 8IU/L or more.
The classification data of the AFC is obtained by dividing the subject's Antral Follicle Count (AFC) data collected by the data collection module into four groups and assigning different classification data to the four groups, wherein when the number of AFCs is less than 4, the classification data of the AFC is 0; when AFC is 4 or more and less than 8, the classification data of the 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.
Further, the inventors of the present application constructed a specific formula for predicting NROs as the following formula one: log (nros) ═ m + n AMH classification data + j basic FSH classification data + k AFC classification data (formula one);
wherein n, j and k determine values based on the AMH, basal FSH and AFC classification data; wherein m is any value of 0.7435-1.2111, and m is preferably 0.9733; in the calculating, the module for predicting the number of oocytes obtained during ovarian stimulation judges based on the data of anti-mullerian hormone (AMH), basal Follicle Stimulating Hormone (FSH), and Antral Follicle Count (AFC) of the subject collected by the data collecting module, and confirms 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 is 0; when the subject's AMH level is 0.5ng/ml and above and less than 1ng/ml, n is selected from any of values 0.1994-0.5153; 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 number from 0.5007-0.7984; 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 of 0.6883-0.9896; n is preferably 0.8390; when the subject has AMH levels of 4ng/ml and above, n is selected from any value of 0.8385-1.1557; n is preferably 0.9971; j is selected from any of values 0.0443-0.4112 when the subject's basal FSH is less than 3 IU/L; j is preferably 0.2278; j is selected from any of-0.0972-0.2526 when the subject's basal FSH is 3IU/L and above and less than 5 IU/L; j is preferably 0.0777; when the subject's basal FSH is 5IU/L or more and less than 8IU/L, j is selected from any value of-0.2618-0.0947; j is preferably-0.0835; when the subject has less than 4 AFCs, k is 0; k is selected from any of 0.1599-0.4629 when the subject has AFC of 4 and more and less than 8; k is preferably 0.3114; k is selected from any of 0.3553-0.6735 when the subject has AFC of 8 and more and less than 12; k is preferably 0.5144; when the subject has AFC of 12 and above, k is selected from any value of 0.5027-0.8264; k is preferably 0.6645.
Examples
Example 1 selection of preliminary Subjects for model construction
Model construction was initially performed based on data obtained from patients receiving treatment at the third hospital of Beijing university between 2017 and 2017, month 12. For a patient for preliminary modeling, the patient's basic and clinical characteristics including surname, case history number, serial number, age, BMI index, duration of infertility, number of previous in vitro fertilization/intracytoplasmic sperm injection-embryo transfer (IVF/ICSI-ET) attempts, serum base E, were collected2Levels, FSH and LH levels, serum AMH levels, left and right ovarian AFCs, first, second, third, fourth and fifth causes of infertility, conventional or mild ovarian stimulation cycles, ovarian stimulation type/COS regimen, initial and total dose of recombinant rFSH, duration of rFSH treatment (days), rFSH name, endometrial thickness on the day of human chorionic gonadotropin (hCG) trigger, date of oocyte retrieval and NROs. A total of 17380 patients' preliminary data was collected between 2017, month 1 to 2017, month 12, and patients suitable for preliminary model construction were selected based on the following criteria, identifying the patient population for constructing the model.
The criteria for inclusion in the model construction were:
1) women between the ages of 20 and 45 years;
2)BMI≤30；
3) the treatment period previously attempted is ≦ 2;
4) all hormone levels were tested at the endocrine laboratory at third hospital, Beijing university;
5) the patient received a standard GnRH antagonist ovarian stimulation regimen.
Data for patients meeting the above 5 criteria was included in the patient population used to construct the model for subsequent model construction.
The criteria for exclusion from the model building population is to exclude the patient in accordance with any of the following: 1) treated or untreated ovarian cysts; 2) previous ovarian surgery; 3) polycystic ovarian syndrome (PCOS) or oral contraception used within the last 3 months; 4) previously suffering from a hypermetabolic or endocrine disease; 5) tuberculosis in the past; 6) a history of pregnancy within 3 months; 7) previous radiotherapy or chemotherapy; 8) couples who received PGD (Pre-embryo Implantation genetic screening/PGS (Pre-embryo Implantation genetic diagnostic techniques).
Based on the above exclusion and inclusion criteria, 1523 patients 'data were finally selected from 17380 patients' data for the system model building of the present invention. Of these, 539 patients were due to male factor-induced infertility, 16 were due to endometriosis-induced infertility, 454 were due to tubal factor-induced infertility, and 514 patients had unexplained or mixed or other types of infertility. The median and quartile of the basic characteristics and NVI are listed in table 1 below.
COS treatment
The standard GnRH antagonist ovarian stimulation protocol was performed as follows: human rFSH (e.g., Gonal-F alfa [ Merck Serono, Germany)]，Puregon beta[MSD，USA]，Urofollitropin[Livzon Pharmaceutical Group Inc.，China]Or Menotropphins [ Livzon Pharmaceutical ]]Group Inc.，China]) Dosing began on day 2 of the menstrual cycle. The selection is based on age, AMH level, basal FSH level, AFC level and BMI etc. for the initial dose of human rFSH. Size and number of growing follicles from ultrasound observation and monitoring of serum E during ovarian stimulation2The levels were further adjusted for rFSH dose. GnRH antagonist treatment was initiated when the growing follicle reached a diameter of 10-12 mm.
hCG (Chonogonodotropina alfa, Merck Serono) was injected at a dose of 5000-. Oocyte retrieval was performed 36-38 hours after hCG administration. Transferring one or two embryos or performing embryo cryopreservation. The patient or subject is then provided luteal phase progesterone support (progesterone vaginal gel, Merck Serono).
Antral follicle count measurement, sampling and endocrine determination
AFC was calculated by measuring follicles of 2-10mm diameter in both ovaries on day 2 of the menstrual cycle by transvaginal ultrasound scanning. On the same day, venous blood samples were collected for determination of FSH, LH and E2Concentration in serum. Blood was drawn on either day of the menstrual cycle for detection of AMH. 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.
FSH, LH and E2The serum measurements of (a) were all performed using the Siemens Immulite 2000 immunoassay system (Siemens healthcare Diagnostics, Shanghai, PR China). FSH, LH and E2The tertiary quality Control of (2) was provided by Bio-RAD laboratories (lymphochek Immunoassay Plus Control, Trilevel, Cat. No. 370, batch No. 40340). Serum AMH concentrations were measured using an ultrasensitive ELISA (Ansh Labs, USA) kit. The coefficient of variation for quality control is less than 6% for AMH, FSH and LH and for E2Less than 10%.
Table 1 median clinical and basic characteristics of 1523 patients selected
| |
Median number | 75% quantile | |
| Age (age) | 29 | 33 | 37 |
| BMI(kg/m2) | 20.2 | 22 | 24.2 |
| Basal FSH (IU/L) | 5.5 | 6.9 | 8.8 |
| Basic LH (IU/L) | 2.4 | 3.5 | 4.9 |
| Foundation E2(pmol/L) | 134.0 | 168.0 | 210.0 |
| AMH(ng/ml) | 1.1 | 2.2 | 4.0 |
| |
6 | 9 | 13 |
| hCG triggered daily endometrial thickness (mm) | 9 | 10 | 12 |
| Initial dose (IU) of rFSH | 150 | 225 | 300 |
| Number of oocytes harvested (NROs) | 5 | 9 | 12 |
Example 2 model construction factor selection
Regression model selection
For the 1523 patient data, the distribution of the number of oocytes harvested was first determined. Since the number of oocytes retrieved is count data, a Poisson distribution or a negative binomial distribution may be generally considered. In this example, the goodness-of-fit test of Poisson distribution and negative binomial distribution was performed on the data by using JMP Pro v.14 software, and the results show that the data deviate from Poisson distribution (χ) as shown in fig. 12＝7026.46，P<0.001) obeying to a negative binomial distribution (χ)21660.35, P0.77). FIG. 1 shows the fitting cases when Poisson distribution and negative binomial distribution are used, respectively, and it can be seen from the results of FIG. 1 that the number of oocytes (NROs) obtained can be better fitted using the negative binomial distribution. Since the data of the number of oocytes acquired obeys the negative binomial distribution, the data are processed by the following negative binomial regression based on the negative binomial distribution in the present embodiment.
Classification of influencing factors
In consideration of the following reasons, the detected continuous variable analysis indexes are converted into classification data in the embodiment, because the prediction efficiency of the model is reduced due to collinearity caused by obvious correlation among multiple indexes in the constructed model, and the classification can better display the relation between each index and the number of the obtained oocytes; (2) the classification data is easier to interpret and easier to apply in practice. The assignment of each index is shown in table 2, and the influencing factors in the table are divided into 4 groups or 5 groups according to the assignment of table 2. Wherein, the ages are divided into four groups, each group is less than 30 years old, and the classification data of the ages is 0; over 30 years and under 35 years, when the classification data of the ages is 1; over 35 years and under 40 years, when the age is divided intoThe class data is 2; above age 40, the classification data for this age is 3. Dividing BMI indexes into four groups, wherein the BMI indexes are respectively less than 18.5, and the classification data of the BMI is 0; 18.5 or more and less than 24, when the BMI classification data is 1; 24 or more and less than 27, when the BMI classification data is 2; and 27 or more, at this time, the classification data of the BMI is 3. AMH is divided into 5 groups, and the AMH is less than 0.5ng/ml respectively, and the classification data of the AMH is 0 at the moment; AMH is more than 0.5 and less than 1ng/ml, and the classification data of the AMH is 1; AMH is more than 1 and less than 2ng/ml, and the classification data of the AMH is 2; AMH is more than 2 and less than 4ng/ml, and the classification data of the AMH is 3; and AMH is above 4ng/ml, at which time the classification data of AMH is 4. The AFC is divided into 4 groups, the AFC is less than 4 respectively, and the classification data of the AFC is 0 at the moment; the number of AFC is more than 4 and less than 8, and the classification data of the AFC is 1; the number of AFC is more than 8 and less than 12, and the classification data of the AFC is 2; the number of AFC is more than 12, and the classification data of the AFC is 3 at this time. Basal FSH levels were divided into 4 groups, each with basal FSH less than 3IU/L, at which time the classification data for basal FSH was 0; the basic FSH is more than 3IU/L and less than 5IU/L, and the classification data of the basic FSH is 1; the basic FSH is more than 5IU/L and less than 8IU/L, and the classification data of the basic FSH is 2; basal FSH was above 8IU/L, at which time the classification data for basal FSH was 3. The basic LH levels are divided into 4 groups, wherein the basic LH levels are respectively less than 2IU/L, and the classification data of the basic LH levels are 0; the basic LH is more than 2IU/L and less than 5IU/L, and the classification data of the basic LH level is 1; the basic LH level is more than 5IU/L and less than 8IU/L, and the classification data of the basic LH level is 2; and a basal LH level of above 8IU/L, at which time the classification data for the basal LH level is 3. Foundation E2The levels were divided into 4 groups, each being basis E2Level less than 150pmol/L, at which time basis E2The horizontal classification data is 0; foundation E2Level above 150 and less than 200pmol/L, when basal E2The horizontal classification data is 1; foundation E2Level above 200 and less than 250pmol/L, when basal E2The horizontal classification data was 2; foundation E2Levels above 250pmol/L, when basal E2The horizontal classification data is 3. The initial dose of rFSH was divided into 4 groups, each of which was an rFSH initiatorThe amount is less than 150IU, and the classification data of the initial dose of rFSH is 0; the initial dose of rFSH is more than 150IU and less than 250IU, and the classification data of the initial dose of rFSH is 1; the initial dose of rFSH is more than 250IU and less than 300IU, and the classification data of the initial dose of rFSH is 2; and an initial dose of rFSH above 300IU, at which time the classification data for the initial dose of rFSH is 3.
Table 2 index assignment
One factor analysis
The effect of a single factor on outcome variable (number of eggs harvested, i.e., NROs) was analyzed using software JMP Pro v.14, applying negative binomial regression. It can be seen that age, AMH, FSH, rFSH, AFC, BMI, LH, infertility factors are statistically significant in the single factor analysis. Foundation E2Levels are not statistically significant and their RR values are all very close to 1, so in subsequent analyses, basis E is first analyzed2Levels are removed from the model construction.
TABLE 3 Single factor analysis results
Example 3 construction of a predictive model
As described above, a statistical model is constructed by selecting negative binomial regression, a forward method of pruning and a holdback verification are adopted for selection of prediction indexes, a prediction model is established by using software JMP Pro v.14, and a data set consisting of the 1523 patients is randomly divided into two parts, one part is used as a training set (1066 data, 70%), and the other part is used as a verification set (457 data, 30%).
Firstly, modeling is built in a training set, and the effect of the model is verified in a verification set. The prediction model is selected mainly according to the negative log-likelihood value in the verification set, and the lower the negative log-likelihood value in the verification set is, the better the prompt model is.
FIG. 2 shows the variable screening process of the forward method of pruning, specifically, except for culled E2Besides, the rest of the single factors are all included in a multi-factor negative binomial regression model, and the model of fig. 2 is obtained through a pruning forward method and a hardback verification, and as can be seen from fig. 2, in the third step, the negative log-likelihood value in the verification set is the lowest, so that the model at this time is taken as the optimal model. The variables included in the model at this time were AMH, FSH, AFC. The results of the parameter estimation of each variable in the prediction model at this time are shown in table 4, and the 95% confidence intervals of each parameter are further shown in table 4.
TABLE 4 results of parameter estimation of prediction models
Based on the above method, the following formula one is confirmed in the present embodiment.
Log (nros) ═ m + n × AMH classification data + j × basic FSH classification data + k × AFC classification data (formula one)
Wherein n, j and k determine values based on the AMH, basal FSH and AFC classification data; wherein m is any value of 0.7435-1.2111, and m is preferably 0.9733;
in the calculating, the module for predicting the number of oocytes obtained during ovarian stimulation judges based on the data of anti-mullerian hormone (AMH), basal Follicle Stimulating Hormone (FSH), and Antral Follicle Count (AFC) of the subject collected by the data collecting module, and confirms 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 is 0;
when the subject's AMH level is 0.5ng/ml and above and less than 1ng/ml, n is selected from any of values 0.1994-0.5153; 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 number from 0.5007-0.7984; 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 of 0.6883-0.9896; n is preferably 0.8390;
when the subject has AMH levels of 4ng/ml and above, n is selected from any value of 0.8385-1.1557; n is preferably 0.9971;
j is selected from any of values 0.0443-0.4112 when the subject's basal FSH is less than 3 IU/L; j is preferably 0.2278;
j is selected from any of-0.0972-0.2526 when the subject's basal FSH is 3IU/L and above and less than 5 IU/L; j is preferably 0.0777;
when the subject's basal FSH is 5IU/L or more and less than 8IU/L, j is selected from any value of-0.2618-0.0947; j is preferably-0.0835;
when the subject has less than 4 AFCs, k is 0;
k is selected from any of 0.1599-0.4629 when the subject has AFC of 4 and more and less than 8; k is preferably 0.3114;
k is selected from any of 0.3553-0.6735 when the subject has AFC of 8 and more and less than 12; k is preferably 0.5144;
when the subject has AFC of 12 and above, k is selected from any value of 0.5027-0.8264; k is preferably 0.6645.
The predicted effect of the model constructed for the training set and the validation set using the above method is shown in fig. 3. In fig. 3, the abscissa shows the number of oocytes obtained by using the NROs predicted by the model, that is, the number of oocytes obtained by predicting the subject to undergo ovulation induction in the standard antagonist regimen, and the ordinate shows the number of oocytes obtained by actually detecting the subject, it can be seen that as shown in fig. 3, the model constructed as described above obtains good prediction effects in both training and verification sets, and the predicted data has high degree of coincidence with the actually detected data. Further, the distribution of the residuals of the training set and the validation set is shown in fig. 4, and it can be seen that the residuals are normally distributed. It can be seen that the system constructed in this example can be used to make good predictions about the number of oocytes retrieved by a subject.
Although the embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to the above-described embodiments and application fields, and the above-described embodiments are illustrative, instructive, and not restrictive. Those skilled in the art, having the benefit of this disclosure, may effect numerous modifications thereto without departing from the scope of the invention as defined by the appended claims.
Claims (4)
1. A system for predicting the number of oocytes obtained during ovarian stimulation in a subject, comprising:
a data acquisition module for acquiring data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level, Antral Follicle Count (AFC) of a subject; and
a module for predicting the number of oocytes harvested during ovarian stimulation, for calculating the data captured in the data acquisition module to calculate the number of oocytes harvested (NROs) of the subject,
wherein the content of the first and second substances,
in the module for predicting the number of oocytes obtained in the ovarian stimulation process, classification data converted from data of anti-mullerian hormone (AMH) level, basal Follicle Stimulating Hormone (FSH) level and Antral Follicle Count (AFC) of a patient who is subjected to ovulation promotion treatment by a standard GnRH antagonist scheme in an existing database and a formula for predicting the number of oocytes (NROs) obtained in the ovarian stimulation process when the subject is subjected to ovulation promotion treatment by the standard GnRH antagonist scheme, wherein the formula is formed by fitting the pre-stored classification data of the patient and negative two-term regression;
in the calculating using the formula, classification data of an anti-mullerian hormone (AMH) of the subject into which AMH levels are converted, which is acquired by a data acquisition module, is used to calculate,
classification data of AMH was obtained by classifying the anti-mullerian hormone (AMH) levels of the subjects collected by the data collection module into five groups and assigning different classification data, respectively, as follows,
when AMH is less than 0.5ng/ml, the classification data of AMH is 0;
when AMH is 0.5ng/ml or more and less than 1ng/ml, the classification data of AMH is 1;
when AMH is 1ng/ml or more and less than 2ng/ml, the classification data of AMH is 2;
when the AMH is 2ng/ml or more and less than 4ng/ml, the classification data of the AMH is 3; and
when AMH is at 4ng/ml or above, the classification data of AMH is 4;
in the calculation using the formula, classification data of basal Follicle Stimulating Hormone (FSH) obtained by converting the basal FSH level of the subject collected by the data collection module is used for calculation,
the classification data of the basal FSH is obtained by classifying the subject's Follicle Stimulating Hormone (FSH) levels collected by the data collection module into four groups and assigning different classification data to each group 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 or more and less than 5IU/L, the classification data of the basic FSH is 1;
when the basic FSH is 5IU/L or more and less than 8IU/L, the classification data of the basic FSH is 2;
when the basic FSH is 8IU/L or above, the classification data of the basic FSH is 3;
when calculated using the formula, calculating using classification data of subject's Antral Follicle Count (AFC) transformed AFC acquired by the data acquisition module,
the classification data of AFC is obtained by classifying the subject's Antral Follicle Count (AFC) data collected by the data collection module into four groups and assigning different classification data to each group as follows,
when AFC is less than 4, the classification data of the AFC is 0;
when AFC is 4 or more and less than 8, the classification data of the 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 the AFC is 3;
the formula for calculating the number of oocytes (NROs) obtained during ovarian stimulation is a formula for calculating the number of oocytes (NROs) obtained using classification data of AMH determined by AMH level of the subject, FSH classification data determined by basal FSH level of the subject, and AFC determined AFC classification data of the subject collected by the data collection module;
the formula is the following formula one:
log (nros) ═ m + n AMH classification data + j basic FSH classification data + k AFC classification data (formula one);
wherein n, j and k determine values based on the AMH, basal FSH and AFC classification data;
wherein m is any value of 0.7435-1.2111;
in the calculating, the module for predicting the number of oocytes obtained during ovarian stimulation judges based on the data of anti-mullerian hormone (AMH), basal Follicle Stimulating Hormone (FSH), and Antral Follicle Count (AFC) of the subject collected by the data collecting module, and confirms 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 is 0;
when the subject's AMH level is 0.5ng/ml and above and less than 1ng/ml, n is selected from any of values 0.1994-0.5153;
when the subject's AMH level is 1ng/ml and above and less than 2ng/ml, n is selected from any number from 0.5007-0.7984;
when the subject's AMH level is 2ng/ml and above and less than 4ng/ml, n is selected from any of 0.6883-0.9896;
when the subject has AMH levels of 4ng/ml and above, n is selected from any value of 0.8385-1.1557;
j is selected from any of values 0.0443-0.4112 when the subject's basal FSH is less than 3 IU/L;
j is selected from any of-0.0972-0.2526 when the subject's basal FSH is 3IU/L and above and less than 5 IU/L;
when the subject's basal FSH is 5IU/L or more and less than 8IU/L, j is selected from any value of-0.2618-0.0947;
when the subject has less than 4 AFCs, k is 0;
k is selected from any of 0.1599-0.4629 when the subject has AFC of 4 and more and less than 8;
k is selected from any of 0.3553-0.6735 when the subject has AFC of 8 and more and less than 12;
when the subject has AFC of 12 and more, k is selected from any value of 0.5027-0.8264.
2. The system of claim 1, wherein,
the subject is one who is to be treated for ovulation induction with a standard GnRH antagonist regimen.
3. The system of claim 1 or 2,
in the data acquisition module, the collected anti-mullerian hormone (AMH) level refers to the anti-mullerian hormone concentration in venous blood of the female subject at any time point during the menstruation period, the basal Follicle Stimulating Hormone (FSH) level refers to the follicle stimulating hormone concentration in venous blood of the female subject for 2-4 days during the menstruation period, and the Antral Follicle Count (AFC) refers to the number of all visible follicles with a diameter of 2-10mm in both ovaries when the female subject is subjected to vaginal B-ultrasound counting for 2-4 days during the menstruation period.
4. The system of claim 1, wherein,
m is 0.9733;
when the subject's AMH level is 0.5ng/ml and above and less than 1ng/ml, n is 0.3574;
when the subject's AMH level is 1ng/ml and above and less than 2ng/ml, n is 0.6496;
when the subject has an AMH level of 2ng/ml and above and less than 4ng/ml, n is 0.8390;
when said subject has AMH levels of 4ng/ml and above, n is 0.9971;
when the subject's basal FSH is less than 3IU/L, j is 0.2278;
j is 0.0777 when the subject's basal FSH is at 3IU/L and above and less than 5 IU/L;
j is-0.0835 when the subject's basal FSH is 5IU/L and above and less than 8 IU/L;
k is 0.3114 when the subject has AFC of 4 and more and less than 8;
k is 0.5144 when the subject has AFC of 8 and more and less than 12;
when the subject had AFC of 12 and more, k was 0.6645.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910780793.6A CN110491505B (en) | 2019-08-22 | 2019-08-22 | System for predicting the number of oocytes obtained during ovarian stimulation of a subject |
| PCT/CN2020/087232 WO2021031605A1 (en) | 2019-08-22 | 2020-04-27 | System for predicting number of retrieved oocytes during ovarian stimulation of subject |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910780793.6A CN110491505B (en) | 2019-08-22 | 2019-08-22 | System for predicting the number of oocytes obtained during ovarian stimulation of a subject |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110491505A CN110491505A (en) | 2019-11-22 |
| CN110491505B true CN110491505B (en) | 2021-06-01 |
Family
ID=68553125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910780793.6A Active CN110491505B (en) | 2019-08-22 | 2019-08-22 | System for predicting the number of oocytes obtained during ovarian stimulation of a subject |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110491505B (en) |
| WO (1) | WO2021031605A1 (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110491505B (en) * | 2019-08-22 | 2021-06-01 | 北京大学第三医院（北京大学第三临床医学院） | System for predicting the number of oocytes obtained during ovarian stimulation of a subject |
| CN111524604B (en) * | 2020-04-07 | 2021-09-10 | 北京大学第三医院（北京大学第三临床医学院） | System for assessing ovarian reserve function of a subject |
| CN111785389B (en) * | 2020-07-10 | 2021-10-19 | 北京大学第三医院（北京大学第三临床医学院） | System and method for predicting age of a subject to develop new changes in ovarian reserve |
| CN111933290B (en) * | 2020-08-14 | 2023-10-10 | 北京赫雅智能科技有限公司 | Method and device for predicting artificial reproduction conception by machine learning model |
| CN113034448B (en) * | 2021-03-11 | 2022-06-21 | 电子科技大学 | Pathological image cell identification method based on multi-instance learning |
| CN112908475A (en) * | 2021-04-22 | 2021-06-04 | 北京大学第三医院（北京大学第三临床医学院） | System for assessing ovarian reserve function in a subject |
| CN114913972B (en) * | 2021-12-10 | 2023-12-01 | 北京大学第三医院（北京大学第三临床医学院） | System for predicting the number of oocytes obtained during ovarian stimulation of a subject |
| CN115019932B (en) * | 2022-07-26 | 2024-02-27 | 北京大学第三医院（北京大学第三临床医学院） | System and method for predicting COS period administration of exogenous follicle-stimulating hormone drug dose |
| CN115831382A (en) * | 2022-12-26 | 2023-03-21 | 北京大学第三医院（北京大学第三临床医学院） | Conversion method and system of hormone detection data |
| CN116798634B (en) * | 2023-08-25 | 2023-11-21 | 北京大学深圳医院 | FSH start dose prediction system, electronic equipment and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0161063B1 (en) * | 1984-04-03 | 1991-07-24 | Serono Laboratories, Inc. | Method of inducing ovulation |
| US8173592B1 (en) * | 1999-03-31 | 2012-05-08 | Zentaris Ivf Gmbh | Method for a programmed controlled ovarian stimulation protocol |
| US20080215353A1 (en) * | 2006-08-31 | 2008-09-04 | Akin James W | Method of Frozen Donor Egg Banking |
| EP2821502A1 (en) * | 2013-07-05 | 2015-01-07 | Centre National de la Recherche Scientifique (CNRS) | Method for evaluating developmental competence of an oocyte |
| JP7163027B2 (en) * | 2015-02-26 | 2022-10-31 | フェリング ベスローテン フェンノートシャップ | How to treat infertility |
| US10175252B2 (en) * | 2016-02-04 | 2019-01-08 | American Infertility Of New York, P.C. | Diagnosis, and anti-mullerian hormone (AMH) administration for treatment, of infertility for good-, intermediate- and poor-prognosis patients for in vitro fertilization in view of logistic regression models |
| CN109602394B (en) * | 2018-12-12 | 2020-01-17 | 北京大学第三医院 | System for assessing ovarian reserve function of a subject |
| CN110491505B (en) * | 2019-08-22 | 2021-06-01 | 北京大学第三医院（北京大学第三临床医学院） | System for predicting the number of oocytes obtained during ovarian stimulation of a subject |
-
2019
- 2019-08-22 CN CN201910780793.6A patent/CN110491505B/en active Active
-
2020
- 2020-04-27 WO PCT/CN2020/087232 patent/WO2021031605A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN110491505A (en) | 2019-11-22 |
| WO2021031605A1 (en) | 2021-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110491505B (en) | System for predicting the number of oocytes obtained during ovarian stimulation of a subject | |
| CN110570952B (en) | System for predicting the probability of hyporesponsiveness of a subject's ovary under an antagonist regimen and system for guiding the selection of initial dosage of gonadotropins | |
| Mumusoglu et al. | Preparation of the endometrium for frozen embryo transfer: a systematic review | |
| CN109602394B (en) | System for assessing ovarian reserve function of a subject | |
| Maheshwari et al. | Dynamic tests of ovarian reserve: a systematic review of diagnostic accuracy | |
| van Rooij et al. | Use of ovarian reserve tests for the prediction of ongoing pregnancy in couples with unexplained or mild male infertility | |
| CN111772682B (en) | System and method for predicting age of a subject to develop new changes in ovarian reserve | |
| CN110808099B (en) | System for detecting ectopic pregnancy | |
| CN111785389B (en) | System and method for predicting age of a subject to develop new changes in ovarian reserve | |
| Witz et al. | Randomized, assessor-blinded trial comparing highly purified human menotropin and recombinant follicle-stimulating hormone in high responders undergoing intracytoplasmic sperm injection | |
| WO2023103189A1 (en) | System and method for predicting number of retrieved oocytes in subject in process of ovarian stimulation | |
| CN111524604B (en) | System for assessing ovarian reserve function of a subject | |
| CN115019932B (en) | System and method for predicting COS period administration of exogenous follicle-stimulating hormone drug dose | |
| WO2023155399A1 (en) | System and method for predicting high ovarian response of subject | |
| CN110808098B (en) | System for predicting sustained pregnancy in a subject during a fresh transplant cycle | |
| Lawrenz et al. | Reintroducing serum FSH measurement during ovarian stimulation for ART | |
| Wei et al. | Effect of the ratios of estradiol increase on the outcome of in vitro fertilization-embryo transfer with antagonist regimens: a single center retrospective cohort study | |
| CN116798634B (en) | FSH start dose prediction system, electronic equipment and storage medium | |
| Thelmo et al. | P-149: Peak serum estradiol (E2) is a predictor of pregnancy outcome in in vitro fertilization (IVF) | |
| Wei et al. | Effect of the trends of estradiol level on the outcome of in vitro fertilization-embryo transfer with antagonist regimens: a single center retrospective cohort study | |
| Lavery | Subfertility | |
| WO2022222207A1 (en) | System for evaluating ovarian reserve function of subject | |
| Kassab et al. | Does measuring early basal serum follicular lutinising hormone assist in predicting In vitro fertilization (IVF)/Intracytoplasmic sperm injection (ICSI) outcome? | |
| Lee et al. | Comparing endometrial preparation methods in frozen embryo transfers–Does a previous live birth make a difference? | |
| El-Shawarby et al. | Age-specific serum FSH concentrations and their correlation with the outcome of ovarian stimulation for IVF |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220629 Address after: 511446 floor 13, building 9 (Building 6), No. 6, Nanjiang Second Road, Zhujiang street, Guangzhou, Guangdong Province Patentee after: GUANGZHOU KANGRUN BIOTECHNOLOGY Co.,Ltd. Address before: 100191 No. 49 Garden North Road, Beijing, Haidian District Patentee before: PEKING University THIRD HOSPITAL (PEKING UNIVERSITY THIRD CLINICAL MEDICAL College) |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221110 Address after: No. 203, 204, Floor 2, Building B3, Phase I, Changsha E Center, No. 18, Xiangtai Road, Liuyang Economic and Technological Development Zone, Changsha, Hunan 410300 Patentee after: Hunan Kangqing Biotechnology Co.,Ltd. Address before: 511446 floor 13, building 9 (Building 6), No. 6, Nanjiang Second Road, Zhujiang street, Guangzhou, Guangdong Province Patentee before: GUANGZHOU KANGRUN BIOTECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |