System and method for predicting menstrual cycle prolongation

By detecting hormones such as testosterone, 11-ketoandrostenedione, and androstenedione in patients with polycystic ovary syndrome using mass spectrometry, and using a logistic regression model to predict prolonged menstrual cycles, this approach overcomes the shortcomings of existing detection methods and enables more accurate menstrual cycle assessment and personalized treatment guidance.

WO2024229876A1PCT designated stage expired Publication Date: 2024-11-14PEKING UNIVERSITY THIRD HOSPITAL (THE THIRD CLINICAL MEDICAL SCHOOL OF PEKING UNIVERSITY)
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2023/094175
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-09
Filing Date
2023-05-15
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

Current technologies for diagnosing polycystic ovary syndrome (PCOS) lack the sensitivity and accuracy of conventional testing methods for high androgen levels, making it impossible to accurately assess the probability of prolonged menstrual cycles and affecting treatment outcomes.

Method used

A mass spectrometry (MS)-based detection method was developed to simultaneously detect classical and 11oxyC19 androgens, and a system and method for predicting prolonged menstrual cycles were established. By acquiring data on testosterone, 11-ketoandrostenedione, and androstenedione from subjects, the probability of prolonged menstrual cycles was calculated using a logistic regression model, and grouped risk assessments were performed.

Benefits of technology

It improves the accuracy of predicting prolonged menstrual cycles in patients with polycystic ovary syndrome, helps guide personalized treatment, improves the assessment of ovulation disorders and infertility risks, and provides more precise treatment options.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023094175_14112024_PF_FP_ABST
    Figure CN2023094175_14112024_PF_FP_ABST
Patent Text Reader

Abstract

The present application relates to a system and method for predicting menstrual cycle prolongation, which takes into account a T level, an 11KA4 level, and an A4 level, or takes into account an anti-mullerian hormone (AMH) level, an androstenedione (A4) level, a fasting blood glucose level, an inhibin B level, and age to predict the menstrual cycle prolongation of a patient with polycystic ovary syndrome. The present application can accurately predict the menstrual cycle prolongation of the patient with polycystic ovary syndrome, which has important significance in evaluating the infertility risk and guiding the treatment in the patient.
Need to check novelty before this filing date? Find Prior Art

Description

System and method for predicting menstrual cycle extension Technical Field

[0001] The present application relates to a system and method for assessing the probability of a prolonged menstrual cycle in a subject. Background Art

[0002] Polycystic ovary syndrome (PCOS) is a reproductive and metabolic disorder that is the most common cause of anovulatory infertility, affecting 5–20% of women of reproductive age. The disorder is diagnosed in adults when at least two of three features are present: androgen excess, menstrual irregularities, and polycystic ovarian changes (PCOM) in the absence of another specific diagnosis. Therefore, women with PCOS are categorized into four phenotypic groups based on a random combination of signs and symptoms. Most affected women also have other metabolic dysfunctions, such as obesity and insulin resistance. Primarily due to this phenotypic heterogeneity, the pathophysiology of PCOS remains poorly understood.

[0003] Hyperandrogenism is considered a potential driver of PCOS. A subset of girls with premature, particularly exaggerated, adrenarche are at increased risk for developing PCOS. Some studies suggest that hyperandrogenism during adolescence can be an early sign of PCOS. Furthermore, genetic aberrations in the androgen receptor have been found in women with PCOS, increasing circulating androgens and leading to abnormal folliculogenesis. There is also strong evidence that excessive androgen exposure in utero contributes to the development of PCOS in adulthood.

[0004] Despite these population-based findings and basic research, however, hyperandrogenism cannot be observed in all phenotypic groups of PCOS in clinical practice. To explore the role of hyperandrogenism in PCOS, two issues need to be clarified: (1) Due to the phenotypic heterogeneity of PCOS, hyperandrogenism may be the main cause of some features but not others. Therefore, evaluating the contribution of hyperandrogenism in PCOS may provide another perspective for understanding the etiology of PCOS. (2) In clinical practice, only typical androgens, especially testosterone (T) with or without androstenedione (A4), are routinely measured when diagnosing PCOS. In addition, the widely used measurement method, chemiluminescent immunoassay, may not be sensitive and accurate enough for relatively low circulating T levels, even in women with androgen excess. Mass spectrometry (MS)-based detection methods are necessary for studies reporting sex steroid measurements as important endpoints.

[0005] A group of nonclassical androgens, namely, adrenal-derived 11-oxidized C19 (11oxyC19) androgens, have recently been implicated as potentially involved in PCOS. The most abundant 11oxyC19 androgens, 11β-hydroxyandrostenedione (11OHA4), and 11β-hydroxytestosterone (11OHT), are primarily produced in the adrenal glands. These metabolites are then converted to 11-ketoandrostenedione (11KA4), 11-ketotestosterone (11KT), and 11-keto-5α-dihydrotestosterone (11KDHT), primarily in peripheral tissues. Evidence suggests that 11KT and 11KDHT are as potent as the classical androgens T and dihydrotestosterone (DHT) in activating the androgen receptor and its target genes, updating our understanding of androgen signaling. Therefore, quantification of these multiple androgens may expand our understanding of the hyperandrogenic profile of women with PCOS.

[0006] Summary of the Invention

[0007] The inventors of this application have developed a sensitive and accurate mass spectrometry (MS)-based detection method for the simultaneous detection of classical and 11oxyC19 androgens. Herein, the inventors have established a method and system for predicting menstrual cycle prolongation to more accurately predict menstrual cycle prolongation.

[0008] Specifically, this application involves the following:

[0009] 1. A system for predicting menstrual cycle prolongation, comprising:

[0010] a data acquisition module for acquiring data on the testosterone (T) level, 11-ketoandrostenedione (11KA4) level, and androstenedione (A4) level of the subject; and

[0011] The module for calculating the probability of menstrual cycle extension is used to calculate the above data information obtained in the data acquisition module, so as to calculate the probability (p) of the subject's menstrual cycle extension.

[0012] 2. The system according to claim 1, further comprising:

[0013] A grouping module is provided in which a default menstrual cycle prolongation grouping parameter is pre-stored, and the calculated probability (p) of menstrual cycle prolongation is grouped according to the grouping parameter, thereby grouping the risk of menstrual cycle prolongation of the subjects.

[0014] 3. A system according to item 1 or 2, wherein the subject is a patient with polycystic ovary syndrome.

[0015] 4. A system according to item 1 or 2, wherein

[0016] The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day during the subject's menstrual cycle.

[0017] The 11-ketoandrostenedione (11KA4) level refers to the 11-ketoandrostenedione concentration of the subject detected on any day during the subject's menstrual cycle.

[0018] The androstenedione (A4) level refers to the androstenedione concentration of a subject measured on any day during the subject's menstrual cycle.

[0019] 5. A system according to item 1 or 2, wherein:

[0020] In the module for calculating the probability of menstrual cycle extension, a formula for calculating the probability (p) of menstrual cycle extension is pre-stored, which is fitted based on the data of testosterone (T) levels, 11-ketoandrostenedione (11KA4) levels and androstenedione (A4) levels of subjects in an existing database.

[0021] 6. A system according to item 5, wherein:

[0022] The formula is as follows: p = 1 / (1 + e - (a + b * T + c * A4 + d * 11KA4)) (Formula 1)

[0023] Where p is the calculated probability of a prolonged menstrual cycle for the subject, a, b, c, and d are unitless parameters, T is the testosterone level, A4 is the androstenedione level, and 11KA4 is the 11-ketoandrostenedione androstenedione level.

[0024] 7. A system according to item 6, wherein

[0025] a is any value from -0.412767 to 1.3467466;

[0026] b is any value from -0.705432 to 0.8178207;

[0027] c is selected from any value between 0.045616 and 0.2747047;

[0028] d is selected from any value between -0.777462 and -0.030569. 8. The system according to item 2, wherein:

[0029] The grouping basis pre-stored in the grouping module is:

[0030] When the calculated probability of a subject having a prolonged menstrual cycle (p) is <50%, the risk of a subject having a prolonged menstrual cycle is low risk;

[0031] When 50% ≤ the calculated probability of a subject's menstrual cycle being prolonged (p) < 90%, the subject's risk of menstrual cycle prolongation is medium risk;

[0032] When the calculated probability (p) of a subject having a prolonged menstrual cycle is ≥ 90%, the risk of the subject having a prolonged menstrual cycle is high.

[0033] 9. A system for predicting a prolonged menstrual cycle, comprising:

[0034] a data collection module for acquiring data on the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level, and age; and

[0035] The module for calculating the probability of menstrual cycle extension is used to calculate the above data information obtained in the data acquisition module, so as to calculate the probability (p) of the subject's menstrual cycle extension.

[0036] 10. The system of clause 9, further comprising:

[0037] A grouping module is provided in which a default menstrual cycle prolongation grouping parameter is pre-stored, and the calculated probability (p) of menstrual cycle prolongation is grouped according to the grouping parameter, thereby grouping the risk of menstrual cycle prolongation of the subjects.

[0038] 11. The system of claim 9 or 10, wherein the subject is a patient with polycystic ovary syndrome.

[0039] 12. A system according to item 9 or 10, wherein

[0040] The anti-Mullerian hormone (AMH) level refers to the testosterone concentration of the subject detected on any day during the subject's menstrual cycle.

[0041] The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day during the subject's menstrual cycle.

[0042] Fasting blood glucose level refers to the fasting blood glucose concentration of the subject tested on any day during the subject's menstrual cycle.

[0043] The inhibin B level refers to the fasting blood glucose concentration of the subject measured on any day during the subject's menstrual cycle.

[0044] 13. A system according to item 9 or 10, wherein

[0045] In the module for calculating the probability of menstrual cycle extension, a formula for calculating the probability (p) of menstrual cycle extension is pre-stored, which is fitted based on the data of the subjects' anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age in an existing database.

[0046] 14. A system according to item 13, wherein

[0047] The formula is as follows: p=1 / (1+e-(a+b*AMH+c*inhibinB+d*A4+f*age+g*Gluc)) (Formula 2)

[0048] Where p is the calculated probability of a prolonged menstrual cycle for the subject, a, b, c, d, f, and g are unitless parameters, AMH is the anti-Mullerian hormone level, inhibinB is the inhibin B level, A4 is the androstenedione level, age is age, and Gluc is the fasting blood glucose level.

[0049] 15. A system according to item 14, wherein

[0050] a is any value from -0.206785 to 4.494194;

[0051] b is selected from any value between 0.040037 and 0.2484311;

[0052] c is any value from -0.001165 to 0.0052593;

[0053] d is selected from any value between -0.012917 and 0.1312465;

[0054] f is selected from any value between -0.125638 and 0.0011014;

[0055] g is selected from any value between -0.274834 and -0.020473.

[0056] 16. A system according to item 10, wherein:

[0057] The grouping basis pre-stored in the grouping module is:

[0058] When the calculated probability of a subject having a prolonged menstrual cycle (p) is <50%, the risk of a subject having a prolonged menstrual cycle is low risk;

[0059] When 50% ≤ the calculated probability of a subject's menstrual cycle being prolonged (p) < 90%, the subject's risk of menstrual cycle prolongation is medium risk;

[0060] When the calculated probability (p) of a subject having a prolonged menstrual cycle is ≥ 90%, the risk of the subject having a prolonged menstrual cycle is high.

[0061] 17. A method for predicting a prolonged menstrual cycle, comprising:

[0062] a data collection step of obtaining data on the testosterone (T) level, 11-ketoandrostenedione (11KA4) level, and androstenedione (A4) level of the subject; and

[0063] The step of calculating the probability of menstrual cycle extension is to calculate the above data information obtained in the data collection step, thereby calculating the probability (p) of the subject's menstrual cycle extension.

[0064] 18. The method of clause 17, further comprising:

[0065] A grouping step, in which a default menstrual cycle extension grouping parameter is pre-stored, and based on the grouping parameter, the calculated probability (p) of menstrual cycle extension is grouped, thereby grouping the risk of menstrual cycle extension of the subjects.

[0066] 19. The method of claim 17 or 18, wherein the subject is a patient with polycystic ovary syndrome.

[0067] 20. The method according to item 17 or 18, wherein

[0068] The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day during the subject's menstrual cycle.

[0069] The 11-ketoandrostenedione (11KA4) level refers to the 11-ketoandrostenedione concentration of the subject detected on any day during the subject's menstrual cycle.

[0070] The androstenedione (A4) level refers to the androstenedione concentration of a subject measured on any day during the subject's menstrual cycle.

[0071] 21. The method according to item 17 or 18, wherein

[0072] In the step of calculating the probability of menstrual cycle extension, a formula for calculating the probability (p) of menstrual cycle extension is pre-stored, which is fitted based on data of testosterone (T) levels, 11-ketoandrostenedione (11KA4) levels and androstenedione (A4) levels of subjects in an existing database.

[0073] 22. The method according to claim 21, wherein

[0074] The formula is as follows: p = 1 / (1 + e - (a + b * T + c * A4 + d * 11KA4)) (Formula 1)

[0075] Where p is the calculated probability of a prolonged menstrual cycle for the subject, a, b, c, and d are unitless parameters, T is the testosterone level, A4 is the androstenedione level, and 11KA4 is the 11-ketoandrostenedione androstenedione level.

[0076] 23. The method according to claim 22, wherein

[0077] a is any value from -0.412767 to 1.3467466;

[0078] b is any value from -0.705432 to 0.8178207;

[0079] c is selected from any value between 0.045616 and 0.2747047;

[0080] d is any value selected from -0.777462 to -0.030569.

[0081] 24. The method according to claim 18, wherein

[0082] The grouping basis pre-stored in the grouping step is:

[0083] When the calculated probability of a subject having a prolonged menstrual cycle (p) is <50%, the risk of a subject having a prolonged menstrual cycle is low risk;

[0084] When 50% ≤ the calculated probability of a subject's menstrual cycle being prolonged (p) < 90%, the subject's risk of menstrual cycle prolongation is medium risk;

[0085] When the calculated probability (p) of a subject having a prolonged menstrual cycle is ≥ 90%, the risk of the subject having a prolonged menstrual cycle is high.

[0086] 25. A method for predicting a prolonged menstrual cycle, comprising:

[0087] a data collection step of obtaining data on the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level, and age; and

[0088] The step of calculating the probability of menstrual cycle extension is to calculate the above data information obtained in the data collection step, thereby calculating the probability (p) of the subject's menstrual cycle extension.

[0089] 26. The method of clause 25, further comprising:

[0090] A grouping step, in which a default menstrual cycle extension grouping parameter is pre-stored, and based on the grouping parameter, the calculated probability (p) of menstrual cycle extension is grouped, thereby grouping the risk of menstrual cycle extension of the subjects.

[0091] 27. The method of claim 25 or 26, wherein the subject is a patient with polycystic ovary syndrome.

[0092] 28. The method according to item 25 or 26, wherein

[0093] The anti-Mullerian hormone (AMH) level refers to the testosterone concentration of the subject detected on any day during the subject's menstrual cycle.

[0094] The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day during the subject's menstrual cycle.

[0095] Fasting blood glucose level refers to the fasting blood glucose concentration of the subject tested on any day during the subject's menstrual cycle.

[0096] The inhibin B level refers to the fasting blood glucose concentration of the subject measured on any day during the subject's menstrual cycle.

[0097] 29. The method according to item 25 or 26, wherein

[0098] In the step of calculating the probability of menstrual cycle extension, a formula for calculating the probability (p) of menstrual cycle extension is pre-stored, which is fitted based on the data of the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age in an existing database.

[0099] 30. The method according to claim 29, wherein

[0100] The formula is as follows: p=1 / (1+e-(a+b*AMH+c*inhibinB+d*A4+f*age+g*Gluc)) (Formula 2)

[0101] Where p is the calculated probability of a prolonged menstrual cycle for the subject, a, b, c, d, f, and g are unitless parameters, AMH is the anti-Mullerian hormone level, inhibinB is the inhibin B level, A4 is the androstenedione level, age is age, and Gluc is the fasting blood glucose level.

[0102] 31. The method of claim 30, wherein:

[0103] a is any value from -0.206785 to 4.494194;

[0104] b is selected from any value between 0.040037 and 0.2484311;

[0105] c is any value from -0.001165 to 0.0052593;

[0106] d is selected from any value between -0.012917 and 0.1312465;

[0107] f is selected from any value between -0.125638 and 0.0011014;

[0108] g is selected from any value between -0.274834 and -0.020473.

[0109] 32. The method of claim 26, wherein:

[0110] The grouping basis pre-stored in the grouping step is:

[0111] When the calculated probability of a subject having a prolonged menstrual cycle (p) is <50%, the risk of a subject having a prolonged menstrual cycle is low risk;

[0112] When 50% ≤ the calculated probability of a subject's menstrual cycle being prolonged (p) < 90%, the subject's risk of menstrual cycle prolongation is medium risk;

[0113] When the calculated probability (p) of a subject having a prolonged menstrual cycle is ≥ 90%, the risk of the subject having a prolonged menstrual cycle is high.

[0114] Effects of the Invention

[0115] This application establishes two mathematical models for predicting menstrual cycle prolongation in patients with polycystic ovary syndrome, namely, considering T level, 11KA4 level and A4 level, or considering anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age to predict menstrual cycle prolongation in patients with polycystic ovary syndrome. Both models can accurately predict menstrual cycle prolongation in patients with polycystic ovary syndrome.

[0116] PCOS patients experience persistently prolonged menstrual cycles or even amenorrhea due to persistent ovulatory dysfunction or anovulation. Predicting a prolonged menstrual cycle in PCOS patients is essentially a matter of predicting whether the patient has ovulatory dysfunction, a cause of infertility in PCOS patients. Therefore, predicting a prolonged menstrual cycle in PCOS patients is crucial for assessing their infertility risk.

[0117] Furthermore, predicting menstrual cycle prolongation in PCOS patients can help guide treatment. Due to varying clinical manifestations, treatment for PCOS patients is highly personalized. Treatment principles and measures differ between PCOS patients whose primary manifestation is menstrual cycle prolongation and those without. For patients with a prolonged menstrual cycle, the principle of treatment is to regulate the menstrual cycle. Treatment methods include oral contraceptives and sequential estrogen-progestin cyclical therapy. Those seeking fertility can receive ovulation-inducing treatment with medications such as clomiphene and letrozole. For those without a prolonged menstrual cycle but characterized by hyperandrogenism, medications such as cyproterone acetate, spironolactone, and glucocorticoids are used to lower blood androgen levels. Therefore, predicting menstrual cycle prolongation in PCOS patients is of great value in guiding treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0118] Figure 1 shows the ROC curve for Model 1;

[0119] Figure 2 shows the ROC curve for Model 2. DETAILED DESCRIPTION

[0120] Anti-Müllerian hormone (AMH) is a hormone secreted by the granulosa cells of the ovarian follicles. Female babies begin producing AMH at 36 weeks of gestation. The more follicles there are in the ovaries, the higher the AMH concentration. Conversely, as follicles are gradually consumed with age and various factors, AMH concentrations also decrease, approaching zero as menopause approaches.

[0121] Testosterone (T) is a typical male hormone secreted by the testicles of men and the ovaries of women. The adrenal glands also secrete a small amount of testosterone. It has the functions of maintaining muscle strength and mass, maintaining bone density and strength, refreshing the mind and improving physical fitness.

[0122] Continuous variables: In statistics, variables are categorized as continuous or categorical, depending on whether their values ​​are continuous. A continuous variable is one that can take on any value within a certain interval. Its value is continuous, and two adjacent values ​​can be divided infinitely, resulting in an infinite number of values. For example, the specifications and dimensions of production parts, or the height, weight, and chest circumference of human measurements are continuous variables, whose values ​​can only be obtained through measurement or quantification. Conversely, discrete variables are those whose values ​​can only be calculated using natural numbers or integer units. For example, the number of enterprises, the number of employees, and the number of equipment can only be counted using the number of units of measurement, and the values ​​of such variables are generally obtained using counting methods.

[0123] Categorical variables refer to variables related to geographic location, demographics, and other factors, and their function is to group survey respondents. Descriptive variables describe the differences between one customer group and others. Most categorical variables are also descriptive variables. Categorical variables can be divided into two categories: unordered categorical variables and ordered categorical variables. Unordered categorical variables are those in which there is no degree or order difference between the categories or attributes. They can be further divided into: 1. Binary categories, such as gender (male vs. female) and drug response (negative vs. positive); 2. Multinomial categories, such as blood type (O, A, B, AB) and occupation (industry, agriculture, commerce, education, military). Ordinal categorical variables, on the other hand, have degree differences between categories. For example, urine glucose test results are categorized as -, ±, +, ++, and +++; and efficacy is categorized as cured, markedly effective, improved, and ineffective. For ordinal categorical variables, the groups should be grouped in rank order, the number of observations in each group should be counted, and a frequency table of the ordinal variable (each rank) should be compiled. The resulting data is called ordinal data.

[0124] Variable types are not fixed; they can be transformed based on the research objectives. For example, hemoglobin level (g / L) is a numerical variable. If it is categorized into two categories: normal and low hemoglobin, it can be analyzed as binary categorical data. If it is categorized into five levels: severe anemia, moderate anemia, mild anemia, normal, and elevated hemoglobin, it can be analyzed as ordinal data. Sometimes, categorical data can be quantified. For example, if a patient's nausea reaction is represented by 0, 1, 2, and 3, it can be analyzed as a numerical variable (quantitative data).

[0125] Logistic regression is a generalized linear regression analysis model commonly used in fields such as data mining, automated disease diagnosis, and economic forecasting. For example, it can be used to explore risk factors for a disease and predict the probability of disease development based on these factors. For example, in the case of gastric cancer, two groups of people are selected: one with gastric cancer and one without. These groups must have different physical characteristics and lifestyles. Therefore, the dependent variable is whether or not a person has gastric cancer, with a value of "yes" or "no." The independent variables can include a wide range of factors, such as age, gender, dietary habits, and Helicobacter pylori infection. Independent variables can be either continuous or categorical. Logistic regression analysis then derives weights for the independent variables, providing a rough understanding of which factors are risk factors for gastric cancer. Furthermore, these weights can be used to predict a person's likelihood of developing cancer based on the risk factors. The dependent variable in a logistic regression can be either binary or multi-categorical.

[0126] The data fitting model used in this article is a logistic regression model that penalizes the absolute size of the regression model's coefficients based on the value of lambda. A larger penalty pushes the estimates of weaker factors closer to zero, so only the strongest predictors remain in the model.

[0127] Least Absolute Shrinkage and Selection Operator Regression (often simply referred to as Lasso regression) is a compression estimation method based on reducing the set of variables (order reduction). It constructs a penalty function that compresses the coefficients of variables and reduces some regression coefficients to zero, thereby achieving variable selection. It is an algorithm that uses penalty functions to improve the predictive power of models. Using the 1-norm constraint, this algorithm not only addresses high dimensionality and collinearity issues but also imparts sparsity to the established model, effectively enabling the algorithm to automatically select wavelengths during modeling.

[0128] Five-fold cross-validation, also known as five-fold cross-validation, is a commonly used testing method for algorithm accuracy. During validation, the dataset is divided into five parts, with four of the parts used as training data and one as testing data. Each trial produces a corresponding accuracy rate (or error rate). The average of the five accuracy rates (or error rates) is used as an estimate of the algorithm's accuracy. Typically, multiple five-fold cross-validations are performed (for example, five 5-fold cross-validations), and the average of these results is used to estimate the algorithm's accuracy.

[0129] The receiver operating characteristic (ROC) curve, also known as the sensitivity curve, gets its name because each point on the curve reflects the same sensitivity—they all respond to the same stimulus, but the results are obtained under different judgment criteria. The ROC curve is a graph with the false alarm probability on the horizontal axis and the hit probability on the vertical axis, plotting the different results obtained by subjects using different judgment criteria under specific stimulus conditions.

[0130] A normal menstrual cycle for women is generally 21-35 days, with an average of 28 days. A menstrual cycle exceeding 35 days is considered to be prolonged. In this application, prolonged menstrual cycle refers to a menstrual cycle exceeding 35 days. For example, a menstrual cycle is 36 days, 37 days, 38 days, 39 days, 40 days, 41 days, 42 days, 43 days, 44 days, 45 days, 46 days, 47 days, 48 ​​days, 49 days, 50 days, 51 days, 52 days, 53 days, 54 days, 55 days, 56 days, 57 days, 58 days, 59 days, 60 days, etc.

[0131] The present application provides a system for predicting menstrual cycle extension, comprising:

[0132] a data acquisition module for acquiring data on the testosterone (T) level, 11-ketoandrostenedione (11KA4) level, and androstenedione (A4) level of the subject; and

[0133] The module for calculating the probability of menstrual cycle extension is used to calculate the above-mentioned data information obtained in the data acquisition module, so as to calculate the probability (p) of the subject's menstrual cycle extension. In the module for calculating the probability of menstrual cycle extension, the data of the subject's testosterone (T) level, 11-ketoandrostenedione (11KA4) level and androstenedione (A4) level are used to calculate the probability (p) of the subject's menstrual cycle extension. Specifically, in the module for calculating the probability of menstrual cycle extension, the subject's testosterone (T) level, 11-ketoandrostenedione (11KA4) level and androstenedione (A4) level are used as continuous variables.

[0134] Wherein, described testosterone (T) level refers to the testosterone concentration of the experimenter detected on any one day in experimenter's menstrual cycle.Described 11-keto-androstenedione (11KA4) level refers to the 11-keto-androstenedione concentration of the experimenter detected on any one day in experimenter's menstrual cycle.Described androstenedione (A4) level refers to the androstenedione concentration of the experimenter detected on any one day in experimenter's menstrual cycle.Testosterone concentration, 11-keto-androstenedione concentration, androstenedione concentration can be detected by any method known in the art, such as chromatography, chemical analysis.For example, the detection method of liquid chromatography coupled with tandem mass spectrometry can also be used to detect, and specific detection step can refer to the method described in CN115541776A.

[0135] The module for calculating the probability of menstrual cycle prolongation pre-stores a formula for calculating the probability (p) of menstrual cycle prolongation, which is fitted based on data on testosterone (T), 11-ketoandrostenedione (11KA4), and androstenedione (A4) levels of subjects in an existing database. The probability (p) of menstrual cycle prolongation for subjects is then grouped according to the grouping criteria.

[0136] In this application, the existing database refers to a database consisting of subjects who are currently receiving treatment or have previously received treatment and meet the following inclusion and exclusion criteria. There is no agreement on the sample size of the database. Of course, the larger the sample size of the database, the better. For example, it can be 100 subjects, 200 subjects, 300 subjects, preferably more than 400 subjects, and more preferably more than 500 subjects.

[0137] The module for calculating the probability of menstrual cycle extension uses the following formula (1) to calculate the probability (p) of the subject's menstrual cycle extension: p = 1 / (1+e-(a+b*T+c*A4+d*11KA4)) (Formula 1)

[0138] Where p is the calculated probability of a prolonged menstrual cycle for the subject, a, b, c, and d are unitless parameters, T is the testosterone level, A4 is the androstenedione level, and 11KA4 is the 11-ketoandrostenedione androstenedione level.

[0139] In the module for calculating the probability of prolonged menstrual cycle, the subject's testosterone (T) level, 11-ketoandrostenedione (11KA4) level, androstenedione (A4) level, as well as the values ​​of a, b, c, and d are entered into the formula for direct calculation.

[0140] Furthermore, a is selected from any value between -0.412767 and 1.3467466; b is selected from any value between -0.705432 and 0.8178207; c is selected from any value between 0.045616 and 0.2747047; and d is selected from any value between -0.777462 and -0.030569. A default menstrual cycle prolongation grouping parameter is pre-stored in the grouping module of the present application, and the grouping basis pre-stored in the grouping module is: when the calculated probability (p) of the subject's menstrual cycle prolongation is <50%, the subject's risk of menstrual cycle prolongation is low risk; when 50% ≤ the calculated probability (p) of the subject's menstrual cycle prolongation is <90%, the subject's risk of menstrual cycle prolongation is medium risk; when the calculated probability (p) of the subject's menstrual cycle prolongation is ≥90%, the subject's risk of menstrual cycle prolongation is high risk.

[0141] In another specific embodiment of the present application, the present application also relates to a method for predicting menstrual cycle prolongation in patients with polycystic ovary syndrome, which includes: a data collection step, which obtains data on the subject's testosterone (T) level, 11-ketoandrostenedione (11KA4) level and androstenedione (A4) level; and a step of calculating the probability of menstrual cycle prolongation, which calculates the above data information obtained in the data collection step to calculate the probability (p) of the subject's menstrual cycle prolongation.

[0142] As described above, the specific contents of the steps performed in the method of the present application, the acquisition, grouping and processing of data on the testosterone (T) level, 11-ketoandrostenedione (11KA4) level and androstenedione (A4) level of the subject can all refer to the steps performed by the various modules of the system involved in the above-mentioned present application.

[0143] The present application also provides another system for predicting menstrual cycle prolongation, which comprises:

[0144] a data collection module for acquiring data on the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level, and age; and

[0145] The module for calculating the probability of menstrual cycle extension is used to calculate the above-mentioned data information obtained in the data acquisition module, thereby calculating the probability (p) of the subject's menstrual cycle extension. In the module for calculating the probability of menstrual cycle extension, the data of the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age are used to calculate the probability (p) of the subject's menstrual cycle extension. Specifically, in the module for calculating the probability of menstrual cycle extension, the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age are used as continuous variables.

[0146] Wherein, the anti-Mullerian hormone (AMH) level refers to the anti-Mullerian hormone concentration in the venous blood of a female subject on any day of her menstrual cycle. For example, if the subject's menstrual cycle is 28 days, the anti-Mullerian hormone (AMH) level can be the anti-Mullerian hormone concentration in the venous blood on day 1 of the menstrual cycle, the anti-Mullerian hormone concentration in the venous blood on day 10 of the menstrual cycle, or the anti-Mullerian hormone concentration in the venous blood on day 28 of the menstrual cycle. The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day of the subject's menstrual cycle. The fasting blood glucose level refers to the fasting blood glucose concentration of the subject detected on any day of the subject's menstrual cycle. The inhibin B level refers to the fasting concentration of the subject detected on any day of the subject's menstrual cycle.

[0147] The module for calculating the probability of menstrual cycle prolongation pre-stores a formula for calculating the probability of menstrual cycle prolongation (p), which is fitted based on data from an existing database of subjects' anti-Mullerian hormone (AMH) levels, androstenedione (A4) levels, fasting blood glucose levels, inhibin B levels, and age. Subjects with a probable menstrual cycle prolongation (p) are grouped according to the grouping criteria.

[0148] In this application, the existing database refers to a database consisting of subjects who are currently receiving treatment or have previously received treatment and meet the following inclusion and exclusion criteria. There is no agreement on the sample size of the database. Of course, the larger the sample size of the database, the better. For example, it can be 100 subjects, 200 subjects, 300 subjects, preferably more than 400 subjects, and more preferably more than 500 subjects.

[0149] The module for calculating the probability of menstrual cycle extension uses the following formula (2) to calculate the probability (p) of the subject's menstrual cycle extension: p = 1 / (1 + e - (a + b*AMH + c*inhibinB + d*A4 + f*age + g*Gluc)) (Formula 2)

[0150] Where p is the calculated probability of a prolonged menstrual cycle for the subject, a, b, c, d, f, and g are unitless parameters, AMH is the anti-Mullerian hormone level, inhibinB is the inhibin B level, A4 is the androstenedione level, age is age, and Gluc is the fasting blood glucose level.

[0151] In the module for calculating the probability of prolonged menstrual cycle, the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age, as well as the values ​​of a, b, c, d, f, and g can be directly substituted into Formula 2 for calculation.

[0152] Furthermore, a is selected from any value between -0.206785 and 4.494194; b is selected from any value between 0.040037 and 0.2484311; c is selected from any value between -0.001165 and 0.0052593; d is selected from any value between -0.012917 and 0.1312465; f is selected from any value between -0.125638 and 0.0011014; and g is selected from any value between -0.274834 and -0.020473. The grouping module of the present application pre-stores default grouping parameters for menstrual cycle extension, and the grouping basis pre-stored in the grouping module is: when the calculated probability of menstrual cycle extension of the subject (p) is <50%, the risk of menstrual cycle extension of the subject is low risk; when 50%≤the calculated probability of menstrual cycle extension of the subject (p)<90%, the risk of menstrual cycle extension of the subject is medium risk; when the calculated probability of menstrual cycle extension of the subject (p)≥90%, the risk of menstrual cycle extension of the subject is high risk. In another specific embodiment of the present application, the present application also relates to a method for predicting menstrual cycle extension in patients with polycystic ovary syndrome, which includes: a data collection step, which obtains data on the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age; and a step of calculating the probability of menstrual cycle extension, which calculates the above data information obtained in the data collection step to calculate the probability (p) of menstrual cycle extension of the subject.

[0153] As described above, the specific contents of the steps performed in the method of the present application, the acquisition, grouping and processing of the data of the subject's anti-Mullerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age can all refer to the steps performed by the various modules of the system involved in the above-mentioned present application.

[0154] The system of the present application establishes two mathematical models for predicting the extension of the menstrual cycle in patients with polycystic ovary syndrome, namely, considering T level, 11KA4 level and A4 level, or considering AMH level, A4 level, fasting blood glucose level, inhibin B level and age to predict the extension of the menstrual cycle in patients with polycystic ovary syndrome. Among them, the testosterone (T) level, the 11-keto-androsterone androstenedione (11KA4) level and the androstenedione (A4) level are mainly detected by mass spectrometry. If there is a ready-made clinical mass spectrometry experimental equipment, mass spectrometry data on the testosterone (T) level, the 11-keto-androsterone androstenedione (11KA4) level and the androstenedione (A4) level can be obtained, but if the AMH index is not tested, the model established with the T level, 11KA4 level and A4 level can be used. If AMH testing is readily available and routine androstenedione (A4) testing is possible, a more accurate model based on AMH levels, fasting blood glucose levels, inhibin B levels, and age can be used to predict menstrual cycle prolongation.

[0155] Example

[0156] Selection of experimental data

[0157] In this example, data from infertile women seeking assisted reproductive technology (ART) treatment at Peking University Third Hospital were used. Patients diagnosed with PCOS and / or commonly associated metabolic disorders, namely obesity and insulin resistance, were included. A total of 462 women aged 20-44 years (30.1 ± 4.0 years) were enrolled. After excluding patients with AFC or undocumented menstrual cycles, 436 women were included in the analysis of menstrual cycle prolongation.

[0158] All participants underwent a routine oral glucose tolerance test (OGTT). AFC was measured using two-dimensional ultrasound (Hitachi Aloka, Tokyo, Japan). Follicles between 2 mm and 10 mm were considered antral follicles. All participants provided written informed consent. Approval was obtained from the Medical Ethics Committee of Peking University Third Hospital (2019-014-02).

[0159] Serum steroid analysis

[0160] Classical androgens and their precursors, including T, A4, dehydroepiandrosterone (DHEA), and 17OH-progesterone (17OHP), as well as four 11oxyC19 androgens (11OHA4, 11OHT, 11KA4, and 11KT), were determined and quantified using sensitive high-performance liquid chromatography-differential tandem mass spectrometry (HPLC-DMS / MS / MS) instrumentation. The method consisted of a 20A HPLC system (Shimadzu, Chiyoda-ku, Tokyo, Japan) and a 5500QTrap mass spectrometer (AB SCIEX, Framingham, MA, USA), with a SelexIon as the in-house DMS component.

[0161] Briefly, serum samples were prepared using dispersive magnetic solid-phase extraction (DMSPE) using magnetic graphene oxide core-shell nanoparticles (Fe3O4@GO) as an adsorbent. Prior to extraction, an isotopic internal standard was added to the sample to reduce extraction-induced errors. Following DMSPE, androgen levels were derivatized with Girard's Reagent P to enhance sensitivity.

[0162] Chromatographic separation was performed on an Agilent Poroshell EC C18 column. A gradient mobile phase consisting of methanol and ammonium formate buffer, both containing formic acid, was used. To further distinguish isomers and reduce background noise, a dimethylsulfoxide (DMS) was introduced, and parameters were optimized for each androgen. Tandem mass spectrometry (MS / MS) detection was performed using an electrospray source in positive ionization mode, and multiple reaction monitoring (MRM) conditions were optimized for each compound.

[0163] Biochemical analysis

[0164] Plasma glucose was measured using the glucose oxidase-phenol aminophenol method (Merit Choice Bioengineering, Beijing, China). Insulin was measured using a chemiluminescence assay (Beckman DxI800, Brea, CA, USA). The homeostasis model assessment of insulin resistance (HOMA-IR) was calculated using the following formula: fasting glucose (mmol / L) × fasting insulin (mU / L) / 22.5.

[0165] Statistical analysis

[0166] The outcome variable was menstrual cycle extension. Menstrual cycle extension is characterized by a menstrual cycle lasting more than 35 days. Normally distributed variables are expressed as mean and standard deviation, while non-normally distributed variables are expressed as median and interquartile range. Independent sample t-test or non-parametric test was used to analyze continuous variables. Least absolute shrinkage and selection operator (LASSO) logistic regression with five-fold cross validation was applied to construct a prediction model. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the model. All analyses in this embodiment were performed using SAS JMP Pro (Version 14.2; SAS Institute, Cary, NC, USA), and P < 0.05 was considered statistically significant.

[0167] Clinical characteristics of patients

[0168] Regarding the analysis of menstrual cycle prolongation, 317 patients (72.7% of 436 patients) experienced prolonged menstrual cycles. The basic characteristics of the two groups are shown in Table 1. Similarly, patients with prolonged menstrual cycles were slightly younger (29.6 ± 3.8 years vs 31.5 ± 4.2 years, P < 0.001). BMI and HOMA-IR did not differ significantly between the two groups (P > 0.05). AMH, inhibin B, and two classic androgens (T and A4) differed significantly between the two groups (P < 0.001).

[0169] The clinical characteristics of patients with or without prolonged menstrual cycles collected in the Examples are shown in Table 1.

[0170] Table 1 Clinical characteristics of patients with or without prolonged menstrual cycles

[0171] In Table 1, BMI denotes body mass index; AMH denotes anti-Mullerian hormone; SHBG denotes sex hormone-binding globulin; HOMA-IR denotes homeostatic model assessment of insulin resistance; T denotes testosterone; A4 denotes androstenedione; DHEA denotes dehydroepiandrosterone; 11OHA4 denotes 11β-hydroxyandrostenedione; 11OHT denotes 11β-hydroxytestosterone; 11KA4 denotes 11-ketoenedione; 11KT denotes 11-ketotestosterone; and 17OHP denotes 17OH-progesterone.

[0172] Model construction

[0173] This application constructed two models, Model 1 and Model 2.

[0174] In the construction of Model 1, the subjects' T levels, 11KA4 levels, and A4 levels were used as variables.

[0175] First, the data from 317 patients analyzed for menstrual cycle prolongation were split into a training set and a validation set at an 80%:20% ratio. In the training set, least absolute shrinkage and selection operator (LASSO) logistic regression with five-fold cross-validation was used to determine the optimal model. The raw data for the probability of menstrual cycle prolongation and its corresponding predicted value were calculated. Table 2 shows the contribution of each variable in the first model. The main effect refers to the contribution of a single variable to the model, while the total effect is the sum of the contributions of the variable itself and its interaction with other variables. The results in Table 2 show that among the eight androgens tested, A4, 11KA4, and T had the greatest impact on menstrual cycle prolongation, with weights of 77.5%, 17.7%, and 0.2%, respectively. As shown in Figure 1, the area under the curve (AUC) for this model was 0.719 (95% CI 0.672-0.766) in the training set and 0.625 (95% CI 0.523-0.727) in the validation set.

[0176] Table 2

[0177] Based on the confirmed model 1, a formula for calculating the probability (p) of a subject's menstrual cycle being prolonged can be obtained, namely Formula 1, which can calculate the probability (p) of a subject's menstrual cycle being prolonged based on the data of the subject's T level, 11KA4 level and A4 level.

[0178] Formula 1: p = 1 / (1 + e - (a + b * T + c * A4 + d * 11KA4)) where p is the calculated probability of the subject's menstrual cycle being prolonged, a is 0.4669899, ​​b is 0.0561942, c is 0.1601605, d is -0.404016, T is the testosterone level, A4 is the androstenedione level, and 11KA4 is the 11-ketoandrostenedione androstenedione level.

[0179] In model 2, AMH level, A4 level, fasting blood glucose level, inhibin B level and age were used as variables. The data of 317 patients used for menstrual cycle prolongation analysis were first divided into training set and validation set in a ratio of 80%:20%. In the training set, least absolute shrinkage and selection operator (LASSO) logistic regression with five-fold cross validation was used to determine the best model. The original data of the probability of menstrual cycle prolongation in subjects and their corresponding predicted data were calculated. The contribution of each variable in the second model is shown in Table 3. The variable that contributes most to menstrual cycle prolongation is AMH, with a weight of 46.2%. Other contributors, in descending order, are age, A4, fasting blood glucose and inhibin B, with weights of 13.3%, 13.2%, 12.5% ​​and 5.8%, respectively. As shown in FIG2 , the AUC of this model was 0.735 (95% CI 0.688-0.782) in the training set and 0.730 (95% CI 0.637-0.823) in the validation set.

[0180] Table 3

[0181] Based on the confirmed model 2, a formula for calculating the probability (p) of a subject's menstrual cycle being prolonged can be obtained, namely Formula 2, which can calculate the probability (p) of a subject's menstrual cycle being prolonged based on the subject's MH level, A4 level, fasting blood glucose level, inhibin B level and age data.

[0182] Formula 2: p = 1 / (1 + e - (a + b * AMH + c * inhibitor B + d * A4 + f * age + g * Gluc))

[0183] Where p is the calculated probability of the subject's menstrual cycle being prolonged, a is 2.1437043, b is 0.144234, c is 0.0020474, d is 0.0591647, f is -0.062269, g is -0.147653, AMH is the anti-Mullerian hormone level, inhibinB is the inhibin B level, A4 is the androstenedione level, age is age, and Gluc is the fasting blood glucose level.

[0184] Based on the grouping results of the constructed model in the validation set and combined with clinical experience, the following grouping criteria were obtained:

[0185] When the calculated probability of the subject's menstrual cycle being prolonged (p) is <50%, the risk of the subject's menstrual cycle being prolonged is low risk; when 50% ≤ the calculated probability of the subject's menstrual cycle being prolonged (p) <90%, the risk of the subject's menstrual cycle being prolonged is medium risk; when the calculated probability of the subject's menstrual cycle being prolonged (p) is ≥90%, the risk of the subject's menstrual cycle being prolonged is high risk.

[0186] The above specific embodiments are merely illustrative and instructive, and are not restrictive. A person skilled in the art, guided by this specification and without departing from the scope of protection of the claims of this application, may also make many other forms, all of which fall within the scope of protection of this application.

Claims

1. A system for predicting prolonged menstrual cycles, comprising: A data acquisition module for obtaining data on the testosterone (T) level, 11-ketotestosterone (11KA4) level, and androstenedione (A4) level of a subject; and A module for calculating the probability of a prolonged menstrual cycle, which is used to calculate the data information obtained in the data acquisition module to calculate the probability (p) of a prolonged menstrual cycle of the subject.

2. The system according to claim 1, further comprising: A grouping module in which default grouping parameters for prolonged menstrual cycles are pre-stored, and based on these grouping parameters, the calculated probability (p) of a prolonged menstrual cycle is grouped, thereby grouping the risk of a prolonged menstrual cycle of the subject.

3. The system according to claim 1 or 2, wherein The subject is a patient with polycystic ovary syndrome.

4. The system according to claim 1 or 2, wherein The androstenedione (A4) level refers to the concentration of androstenedione of the subject measured on any day during the subject's menstrual cycle, The 11-ketotestosterone (11KA4) level refers to the concentration of 11-ketotestosterone of the subject measured on any day during the subject's menstrual cycle, The androstenedione (A4) level refers to the concentration of androstenedione of the subject measured on any day during the subject's menstrual cycle.

5. The system according to claim 1 or 2, wherein In the module for calculating the probability of a prolonged menstrual cycle, a formula for calculating the probability (p) of a prolonged menstrual cycle, which is fitted based on the data of the testosterone (T) level, 11-ketotestosterone (11KA4) level, and androstenedione (A4) level of the subjects in the existing database, is pre-stored.

6. The system according to claim 5, wherein The formula is Formula 1 as follows: p = 1 / (1 + e^(-(a + b*T + c*A4 + d*11KA4))) (Formula 1) Wherein, p is the calculated probability of a prolonged menstrual cycle of the subject, a, b, c, and d are dimensionless parameters, T is the testosterone level, A4 is the androstenedione level, and 11KA4 is the 11-ketotestosterone level.

7. The system according to claim 6, wherein a is selected from any value in the range of -0.412767 to 1.3467466; b is selected from any value in the range of -0.705432 to 0.8178207; c is selected from any value in the range of 0.045616 to 0.2747047; d is selected from any value in the range of -0.777462 to -0.030569.

8. The system according to claim 2, wherein The grouping basis pre-stored in the grouping module is: When the calculated probability (p) of a prolonged menstrual cycle of the subject < 50%, the risk of a prolonged menstrual cycle of the subject is low risk; When 50% ≤ the calculated probability (p) of a prolonged menstrual cycle of the subject < 90%, the risk of a prolonged menstrual cycle of the subject is medium risk; When the calculated probability (p) of a prolonged menstrual cycle of the subject ≥ 90%, the risk of a prolonged menstrual cycle of the subject is high risk.

9. A system for predicting prolonged menstrual cycles, comprising: A data acquisition module, which is used to obtain data on the anti-Müllerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age of a subject; and A module for calculating the probability of menstrual cycle extension, which is used to calculate the above data information obtained in the data acquisition module to calculate the probability (p) of menstrual cycle extension of the subject.

10. The system according to claim 9, further comprising: A grouping module, in which default grouping parameters for menstrual cycle extension are pre-stored, and according to the grouping parameters, the calculated probability (p) of menstrual cycle extension is grouped, so as to group the risk of menstrual cycle extension of the subject.

11. The system according to claim 9 or 10, wherein, The subject is a patient with polycystic ovary syndrome.

12. The system according to claim 9 or 10, wherein The anti-Müllerian hormone (AMH) level refers to the testosterone concentration of the subject measured on any day of the subject's menstrual cycle, The androstenedione (A4) level refers to the androstenedione concentration of the subject measured on any day of the subject's menstrual cycle, The fasting blood glucose level refers to the fasting blood glucose concentration of the subject measured on any day of the subject's menstrual cycle, The inhibin B level refers to the fasting blood glucose concentration of the subject measured on any day of the subject's menstrual cycle.

13. The system according to claim 9 or 10, wherein In the module for calculating the probability of menstrual cycle extension, a formula for calculating the probability (p) of menstrual cycle extension, which is fitted based on data of the anti-Müllerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level and age of subjects in an existing database, is pre-stored.

14. The system according to claim 13, wherein The formula is Formula 2 as follows: p = 1 / (1 + e^-(a + b * AMH + c * inhibinB + d * A4 + f * age + g * Gluc)) (Formula 2) where p is the calculated probability of menstrual cycle extension of the subject, a, b, c, d, f, g are dimensionless parameters, AMH is the anti-Müllerian hormone level, inhibinB is the inhibin B level, A4 is the androstenedione level, age is the age, and Gluc is the fasting blood glucose level.

15. The system according to claim 14, wherein a is selected from any value in the range of -0.206785 to 4.494194; b is selected from any value in the range of 0.040037 to 0.2484311; c is selected from any value in the range of -0.001165 to 0.0052593; d is selected from any value in the range of -0.012917 to 0.1312465; f is selected from any value in the range of -0.125638 to 0.0011014; g is selected from any value in the range of -0.274834 to -0.020473.

16. The system according to claim 10, wherein The grouping basis pre-stored in the grouping module is: When the calculated probability (p) of menstrual cycle extension of the subject < 50%, the risk of menstrual cycle extension of the subject is low risk; When 50% ≤ the calculated probability (p) of the subject's menstrual cycle extension < 90%, the risk of the subject's menstrual cycle extension is medium risk; When the calculated probability (p) of the subject's menstrual cycle extension ≥ 90%, the risk of the subject's menstrual cycle extension is high risk.

17. A method for predicting menstrual cycle extension, comprising: A data collection step of obtaining data on the testosterone (T) level, 11-ketotestosterone (11KA4) level and androstenedione (A4) level of the subject; and A step of calculating the probability of menstrual cycle extension, which calculates the above data information obtained in the data collection step to calculate the probability (p) of the subject's menstrual cycle extension.

18. The method according to claim 17, further comprising: A grouping step, in which default grouping parameters for menstrual cycle extension are pre-stored, and based on the grouping parameters, the calculated probability (p) of menstrual cycle extension is grouped, so as to group the risk of the subject's menstrual cycle extension.

19. The method according to claim 17 or 18, wherein The subject is a patient with polycystic ovary syndrome.

20. The method according to claim 17 or 18, wherein The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day of the subject's menstrual cycle, The 11-ketotestosterone (11KA4) level refers to the 11-ketotestosterone concentration of the subject detected on any day of the subject's menstrual cycle, The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day of the subject's menstrual cycle.

21. The method according to claim 17 or 18, wherein In the step of calculating the probability of menstrual cycle extension, a formula for calculating the probability (p) of menstrual cycle extension, which is fitted based on the data of the testosterone (T) level, 11-ketotestosterone (11KA4) level and androstenedione (A4) level of the subjects in the existing database, is pre-stored.

22. The method according to claim 21, wherein The formula is Formula 1 as follows: p = 1 / (1 + e^-(a + b*T + c*A4 + d*11KA4)) (Formula 1) Wherein, p is the calculated probability of the subject's menstrual cycle extension, a, b, c, d are dimensionless parameters, T is the testosterone level, A4 is the androstenedione level, and 11KA4 is the 11-ketotestosterone level.

23. The method according to claim 22, wherein a is selected from any value in -0.412767 to 1.3467466; b is selected from any value in -0.705432 to 0.8178207; c is selected from any value in 0.045616 to 0.2747047; d is selected from any value in -0.777462 to -0.030569.

24. The method according to claim 18, wherein The grouping basis pre-stored in the grouping step is: When the calculated probability (p) of the subject's menstrual cycle extension < 50%, the risk of the subject's menstrual cycle extension is low risk; When 50% ≤ the calculated probability (p) of the subject's menstrual cycle extension < 90%, the risk of the subject's menstrual cycle extension is medium risk; When the calculated probability (p) of the subject's menstrual cycle extension ≥ 90%, the risk of the subject's menstrual cycle extension is high risk.

25. A method for predicting menstrual cycle extension, comprising: A data collection step of obtaining data on the subject's anti-Müllerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level, and age; and A step of calculating the probability of menstrual cycle extension, which calculates the above data information obtained in the data collection step to calculate the probability (p) of the subject's menstrual cycle extension.

26. The method according to claim 25, further comprising: A grouping step in which default menstrual cycle extension grouping parameters are pre-stored, and based on these grouping parameters, the calculated probability (p) of menstrual cycle extension is grouped, thereby grouping the risk of the subject's menstrual cycle extension.

27. The method according to claim 25 or 26, wherein, The subject is a patient with polycystic ovary syndrome.

28. The method according to claim 25 or 26, wherein The anti-Müllerian hormone (AMH) level refers to the testosterone concentration of the subject detected on any day of the subject's menstrual cycle, The androstenedione (A4) level refers to the androstenedione concentration of the subject detected on any day of the subject's menstrual cycle, The fasting blood glucose level refers to the fasting blood glucose concentration of the subject detected on any day of the subject's menstrual cycle, The inhibin B level refers to the fasting blood glucose concentration of the subject detected on any day of the subject's menstrual cycle.

29. The method according to claim 25 or 26, wherein In the step of calculating the probability of menstrual cycle extension, a formula for calculating the probability (p) of menstrual cycle extension, which is fitted based on data of the subject's anti-Müllerian hormone (AMH) level, androstenedione (A4) level, fasting blood glucose level, inhibin B level, and age in an existing database, is pre-stored.

30. The method according to claim 29, wherein The formula is formula two as follows: p = 1 / (1 + e^-(a + b*AMH + c*inhibinB + d*A4 + f*age + g*Gluc)) (formula two) Wherein, p is the calculated probability of the subject's menstrual cycle extension, a, b, c, d, f, g are dimensionless parameters, AMH is the anti-Müllerian hormone level, inhibinB is the inhibin B level, A4 is the androstenedione level, age is the age, and Gluc is the fasting blood glucose level.

31. The method according to claim 30, wherein a is selected from any value in the range of -0.206785 to 4.494194; b is selected from any value in the range of 0.040037 to 0.2484311; c is selected from any value in the range of -0.001165 to 0.0052593; d is selected from any value in the range of -0.012917 to 0.1312465; f is selected from any value in the range of -0.125638 to 0.0011014; g is selected from any value in the range of -0.274834 to -0.020473.

32. According to the method of claim 26, wherein The basis for grouping pre-stored in the grouping step is: When the calculated probability (p) of the subject's menstrual cycle extension < 50%, the risk of the subject's menstrual cycle extension is low risk; When 50% ≤ the calculated probability (p) of the subject's menstrual cycle extension < 90%, the risk of the subject's menstrual cycle extension is medium risk; When the calculated probability (p) of the subject's menstrual cycle extension ≥ 90%, the risk of the subject's menstrual cycle extension is high risk.

Citation Information

Patent Citations

  • Chinese herbal compound for treating pubertal polycystic ovary syndrome

    CN105596495A

  • System and method for diagnosing polycystic ovarian syndrome

    CN113035354A

  • System for the ovarian reserve function assessment of subjects

    US20220044822A1

  • System for predicting probability of poor ovarian response in a subject under antagonist regimen and system for guiding dose selection of gonadotropin initial medication

    WO2019233308A1