System, methods, and applications for predicting live birth after intercourse in patients with polycystic ovary syndrome (PCOS) undergoing ovulation induction.

Abstract

This invention discloses a live birth prediction system for polycystic ovary syndrome (PCOS) patients after ovulation induction-guided intercourse. The system includes: a data acquisition module for acquiring basic data of PCOS patients; a preliminary screening module for calculating preliminary live birth rate predictors using a univariate Cox regression model based on the basic data; a final screening module for calculating final live birth rate predictors using a multivariate Cox regression model based on the preliminary live birth rate predictors; a live birth rate model construction module for constructing a live birth rate prediction model from the final live birth rate predictors; and a nomogram plotting module for plotting a live birth rate prediction nomogram based on the live birth rate prediction model to predict the live birth rate after ovulation induction-guided intercourse in PCOS patients. The system of this invention can accurately and effectively predict the live birth rate after ovulation induction-guided intercourse in PCOS patients.

Description

Technical Field

[0001] This invention belongs to the field of medical technology, specifically relating to a system, method, and application for predicting live birth after intercourse in patients with polycystic ovary syndrome (PCOS). Background Technology

[0002] Polycystic ovary syndrome (PCOS) is characterized by amenorrhea / oligoovulation, hyperandrogenism, and polycystic ovary morphology (PCOM). Approximately 80% of anovulatory infertility is caused by PCOS. Due to the accompanying ovulation disorders and irregular menstruation, PCOS patients experience decreased fertility in women of reproductive age. Furthermore, pregnancy outcomes in PCOS patients are affected by endocrine and metabolic disorders; when PCOS patients also have endocrine and metabolic disorders, the risk of miscarriage and embryonic arrest increases significantly.

[0003] Ovulation induction refers to the use of drugs or surgery to induce ovulation in patients with ovulation disorders, generally aiming to induce the development of a single follicle or a few follicles. Clomiphene citrate (CC) can be used, starting from day 2 to 6 of the menstrual cycle, with a recommended starting dose of 50 mg / day for 5 consecutive days. If there is no ovarian response, the dose should be gradually increased in the second cycle (incrementing by 50 mg / day), with a maximum dose of 150 mg / day. Letrozole (LE), an aromatase inhibitor, can also be used, starting from day 2 to 6 of the menstrual cycle, with a recommended starting dose of 2.5 mg / day for 5 consecutive days. If there is no ovarian response, the dose should be gradually increased in the second cycle (incrementing by 2.5 mg / day), with a maximum dose of 7.5 mg / day. Each time, transvaginal ultrasound is performed every 2-3 days to check the size of the follicles. When 1-2 follicles are larger than 18mm in diameter, or when urine LH test strips or basal body temperature monitoring are performed at home, it is recommended that the patient return home and have intercourse. The next day, the patient should return to the hospital for transvaginal ultrasound to check whether ovulation has occurred.

[0004] Inducing ovulation and then guiding intercourse can greatly help women of childbearing age with PCOS conceive, thereby reducing their economic and physical burden. Current international and domestic guidelines recommend ovulation induction and guided intercourse as the primary means of assisted conception for PCOS patients, but they do not specify the success rate of pregnancy or the influencing factors.

[0005] PCOS patients often experience endocrine disorders, primarily characterized by high luteinizing hormone (LH), high androgen levels, and insulin resistance. Women with PCOS exhibit a higher gonadotropin-releasing hormone (GnRH) pulse frequency, excessive LH secretion, and relatively lower follicle-stimulating hormone (FSH) secretion, with an LH / FSH ratio often greater than or equal to 2.5. This leads to excessive androgen production in the theca cells of the ovary, inhibiting follicle expansion and maturation, resulting in follicular growth arrest and the development of polycystic ovaries (PCOM). The relatively low FSH levels prevent ovarian granulosa cells from aromatizing androgens into estrogens, leading to elevated androgen levels, decreased estrogen levels, and anovulation. Insulin resistance may be secondary to post-binding defects in the insulin receptor signaling pathway. Insulin clamp studies show that 75-95% of PCOS patients have insulin resistance, hyperinsulinemia, and exacerbated obesity. Among numerous medications, metformin is an important drug for improving insulin resistance in PCOS patients. Weight loss is an important lifestyle change, and it is also the easiest lifestyle change to achieve for non-PCOS patients. Summary of the Invention

[0006] In view of the shortcomings of the prior art described above, the purpose of this invention is to solve the problem that the prior art cannot accurately and effectively predict the live birth rate after ovulation induction and intercourse guidance in patients with polycystic ovary syndrome, and to provide an accurate and effective prediction system for live birth after ovulation induction and intercourse guidance in patients with polycystic ovary syndrome.

[0007] To achieve the above objectives, the present invention provides a live birth prediction system for polycystic ovary syndrome patients after ovulation induction and intercourse, comprising: The data acquisition module is used to acquire basic data from multiple patients with polycystic ovary syndrome. The preliminary screening module, connected to the data acquisition module, is used to calculate, based on the basic data of patients with polycystic ovary syndrome, using a univariate Cox regression model to obtain multiple preliminary live birth rate predictors that may predict live birth. The final screening module, connected to the preliminary screening module, is used to calculate the multiple preliminary live birth rate predictors obtained by the preliminary screening module through a multi-factor Cox regression model to obtain the final live birth rate predictors used to predict live births. A live birth rate model building module, connected to the final screening module, is used to build a live birth rate prediction model from the final live birth rate prediction factors screened by the final screening module. The nomogram drawing module is connected to the live birth rate model construction module and is used to draw a live birth rate prediction nomogram based on the live birth rate prediction model to predict the live birth rate after ovulation induction and guided intercourse in patients with polycystic ovary syndrome.

[0008] Preferably, the basic data includes personal basic data and live birth outcomes.

[0009] Preferably, the personal basic data includes: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether weight has been lost.

[0010] Preferably, the preliminary screening module includes: The Cox regression model building unit is used to build a univariate Cox regression model for live birth rate prediction based on the basic data of patients with polycystic ovary syndrome. The preliminary screening unit, connected to the Cox regression model construction unit, is used to obtain multiple preliminary live birth rate predictors based on the single-factor Cox regression model.

[0011] Preferably, the Cox regression model building unit is used to build a univariate Cox regression model for predicting live birth rate based on the basic personal data of patients with polycystic ovary syndrome, and to obtain predictive factors with predictive value by comparing the p-value of the univariate proportional hazards regression model with the predictive value threshold.

[0012] Preferably, the final screening module performs a multi-factor Cox regression model on the preliminarily screened live birth predictors to obtain the P-value of each predictor and compares it with the high predictive value threshold to obtain multiple final live birth rate predictors.

[0013] Preferably, the predictors of the final live birth include: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether there is weight loss.

[0014] Preferably, the live birth rate model construction module performs multi-factor Cox regression on the obtained final live birth predictor factors to construct a live birth prediction model and obtain the weight parameter values ​​corresponding to each predictor factor.

[0015] Preferably, the nomogram drawing module is further used to: draw a live birth rate prediction nomogram based on the weight parameter values ​​corresponding to each final live birth prediction factor in the live birth rate prediction model, according to the basic data of patients with polycystic ovary syndrome, so as to predict the live birth rate of patients with polycystic ovary syndrome who have intercourse after ovulation induction.

[0016] Preferably, the live birth rate prediction nomogram includes: The scoring scale has a score range of 0 to 100; The predictor variables corresponding to each final live birth rate predictor include: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether there is weight loss. Each predictor variable includes multiple variable values, and each variable value corresponds to a score on the score scale. The total score scale ranges from 0 to 300. The live birth rate variable is a continuous variable, including one or more live birth rate variables, and each live birth rate sub-variable includes a range of variable values, and each range of variable values ​​corresponds to a range of scores on the total score scale.

[0017] On the other hand, the present invention also provides a method for predicting live birth after intercourse in patients with polycystic ovary syndrome (PCOS) undergoing ovulation induction, comprising the following steps: S1. Obtain basic data from multiple patients with polycystic ovary syndrome; S2. Based on the basic data of patients with polycystic ovary syndrome, a univariate Cox regression model was used to calculate and obtain multiple preliminary live birth rate predictors that may predict live birth. S3. The multiple preliminary live birth rate predictors obtained by the preliminary screening module are calculated using a multivariate Cox regression model to obtain the final clinical pregnancy rate predictors used to predict live births. S4. Construct a live birth rate prediction model using the final live birth rate prediction factors selected by the final screening module; S5. Based on the live birth rate prediction model, draw a live birth rate prediction nomogram to predict the live birth rate after ovulation induction and guided intercourse in patients with polycystic ovary syndrome.

[0018] On the other hand, the present invention also provides a nomogram, which is constructed by the method for predicting live birth after intercourse guided by ovulation induction in patients with polycystic ovary syndrome according to the present invention.

[0019] On the other hand, the present invention also provides the application of the nomogram in the preparation of a kit for predicting the live birth rate after ovulation induction in patients with polycystic ovary syndrome.

[0020] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a method for predicting live birth after intercourse guided by ovulation induction in patients with polycystic ovary syndrome; The steps of the method for predicting live birth after intercourse following ovulation induction in patients with polycystic ovary syndrome are as follows: S1. Obtain basic data from multiple patients with polycystic ovary syndrome; S2. Based on the basic data of patients with polycystic ovary syndrome, a univariate Cox regression model was used to calculate and obtain multiple preliminary live birth rate predictors that may predict live birth. S3. The multiple preliminary live birth rate predictors obtained by the preliminary screening module are calculated using a multi-factor Cox regression model to obtain the final live birth rate predictors used to predict live births. S4. Construct a live birth rate prediction model using the final live birth rate prediction factors selected by the final screening module; S5. Based on the live birth rate prediction model, draw a live birth pregnancy rate prediction nomogram to predict the live birth rate after ovulation induction and guided intercourse in patients with polycystic ovary syndrome.

[0021] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for predicting live birth after intercourse guided by ovulation induction in patients with polycystic ovary syndrome: The steps of the method for predicting live birth after intercourse following ovulation induction in patients with polycystic ovary syndrome are as follows: S1. Obtain basic data from multiple patients with polycystic ovary syndrome; S2. Based on the basic data of patients with polycystic ovary syndrome, a univariate Cox regression model was used to calculate and obtain multiple preliminary live birth rate predictors that may predict live birth. S3. The multiple preliminary live birth rate predictors obtained by the preliminary screening module are calculated using a multivariate Cox regression model to obtain the final live birth rate predictors used to predict live births; and the live birth clinical pregnancy rate prediction model. S5. Based on the live birth rate prediction model, draw a live birth rate prediction nomogram to predict the live birth rate after ovulation induction and guided intercourse in patients with polycystic ovary syndrome.

[0022] This invention provides a system for predicting live births after ovulation induction in patients with polycystic ovary syndrome (PCOS). The system collects extensive patient data, uses Cox regression to screen suitable predictive factors, and constructs a Cox model to generate a nomogram. The predictive factors selected in this invention are clinically common, easy to collect, and highly reliable, facilitating the widespread use of this patent. By constructing a proportional hazards model and generating a nomogram, the system can efficiently and accurately predict the live birth rate after ovulation induction in PCOS patients, solving the problems of existing technologies. Attached Figure Description

[0023] Figure 1 A schematic diagram of the structure of the predictive system for live birth after ovulation induction in patients with polycystic ovary syndrome of the present invention is shown.

[0024] Figure 2 A nomogram of live birth rate predictions is shown.

[0025] Figure 3 The inclusion process for patients with cystic ovary syndrome is shown. Detailed Implementation

[0026] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0027] It should be noted that in the following description, reference is made to the accompanying drawings, which illustrate several embodiments of the present invention. It should be understood that other embodiments may also be used, and changes in mechanical composition, structure, electrical system, and operation may be made without departing from the spirit and scope of the invention. The following detailed description should not be considered limiting, and the scope of the embodiments of the invention is defined only by the claims of the published patents. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. Spatially related terms, such as “upper,” “lower,” “left,” “right,” “below,” “below,” “lower part,” “above,” “upper part,” etc., may be used herein to illustrate the relationship between one element or feature shown in the figures and another element or feature.

[0028] Throughout this specification, when it is said that a part is "connected" to another part, this includes not only "direct connection" but also "indirect connection" by placing other elements in between. Furthermore, when it is said that a part "includes" a certain constituent element, unless otherwise stated otherwise, this does not exclude other constituent elements, but rather means that other constituent elements may also be included.

[0029] The present invention will now be described in detail with reference to the accompanying drawings, so that those skilled in the art can readily implement it. The present invention can be embodied in many different forms and is not limited to the embodiments described herein.

[0030] Figure 1 A schematic diagram of the structure of the predictive system for live birth after ovulation induction in patients with polycystic ovary syndrome of the present invention is shown.

[0031] The system includes: The data acquisition module 11 is used to acquire basic data of multiple patients with polycystic ovary syndrome; wherein, the basic data includes personal basic data and live birth outcome; The preliminary screening module 12 is connected to the data acquisition module 11. It is used to calculate based on the basic data of patients with polycystic ovary syndrome through a univariate Cox regression model to obtain multiple preliminary live birth pregnancy rate predictors that may predict live birth. The final screening module 13 is connected to the preliminary screening module 12 and is used to calculate the multiple preliminary live birth rate predictors obtained by the preliminary screening module 12 through a multi-factor Cox regression model to obtain the final live birth rate predictors used to predict live births. The live birth rate model building module 14 is connected to the final screening module 13 and is used to build a live birth rate prediction model from the final live birth rate prediction factors screened by the final screening module 13. The nomogram drawing module 15 is connected to the live birth rate model construction module 14 and is used to draw a live birth rate prediction nomogram based on the live birth rate prediction model to predict the live birth rate after ovulation induction and intercourse guidance for patients with polycystic ovary syndrome.

[0032] It should be noted that... Figure 1 The division of modules in the system embodiment is merely a logical functional division. In actual implementation, they can be fully or partially integrated onto a single physical entity, or they can be physically separated. These modules can be implemented entirely in software via processing element calls; they can be implemented entirely in hardware; or some modules can be implemented in software via processing element calls, while others are implemented in hardware. For example, each module can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. Furthermore, when a module is implemented via processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).

[0033] Optionally, the personal basic data includes: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether weight has been lost.

[0034] The luteinizing hormone (LH) concentration was measured by drawing venous blood on days 2-5 of the menstrual cycle, after the patient had rested for 15 minutes before the blood draw.

[0035] Follicle-stimulating hormone (FSH) concentration: Venous blood is drawn on days 2-5 of the menstrual cycle. The patient rests for 15 minutes before the blood is drawn.

[0036] The formula for calculating the free testosterone index (FAI) is as follows: FAI = Testosterone concentration / Sex hormone-binding globulin concentration * 100%.

[0037] The units for testosterone concentration and sex hormone-binding globulin concentration are nmol / L. The unit for testosterone concentration is converted to 1 ng / mL = 3.47 nmol / L.

[0038] High-density lipoprotein cholesterol (HDL-C): Patients fasted for ≥8 hours, and fasting venous blood was drawn at 8:00 AM to measure fasting HDL-C. The unit is mmol / L.

[0039] A live birth is defined as a delivery of the fetus via vaginal delivery or cesarean section after 22 weeks of gestation, provided that the fetus is able to breathe independently or exhibits any other vital signs, such as a heartbeat, umbilical cord pulsation, or obvious voluntary muscle movement, regardless of whether the umbilical cord has been cut or the placenta is attached.

[0040] Optionally, the preliminary screening module 12 includes: The Cox regression model building unit is used to build a univariate Cox regression model for live birth rate prediction based on the basic data of patients with polycystic ovary syndrome. The preliminary screening unit, connected to the Cox regression model construction unit, is used to obtain multiple preliminary live birth rate predictors based on the single-factor Cox regression model.

[0041] Optionally, the Cox regression model building unit is used to build a univariate Cox regression model for predicting live birth rate based on the basic personal data of patients with polycystic ovary syndrome, and to obtain predictive factors with predictive value by comparing the P-value of the univariate Cox regression model with the predictive value threshold.

[0042] Optionally, the final screening module 13 can be used to perform a multi-factor Cox regression model on the preliminarily screened live birth predictors to obtain the P-value of each predictor and compare it with the high predictive value threshold to obtain multiple live birth rate predictors.

[0043] The final clinical pregnancy predictors include: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether there is weight loss.

[0044] Optionally, the clinical pregnancy rate model construction module 14 performs multivariate Cox regression on the obtained final live birth predictor factors to construct a live birth prediction model and obtain the weight parameter values ​​corresponding to each predictor factor.

[0045] Optionally, the nomogram drawing module 15 is further configured to: draw a live birth rate prediction nomogram based on the weight parameter values ​​corresponding to each final live birth prediction factor in the live birth rate prediction model, according to the basic data of patients with polycystic ovary syndrome, so as to predict the live birth rate of patients with polycystic ovary syndrome who have intercourse after ovulation induction.

[0046] Optionally, the live birth rate prediction nomogram includes: The scoring scale has a score range of 0 to 100; The predictor variables corresponding to each final live birth rate predictor include: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether there is weight loss. Each predictor variable includes several variable values, and each variable value corresponds to a score on the scoring scale. For example, whether metformin is used includes whether metformin is used or not, where not using metformin corresponds to 0 points, and regular menstruation corresponds to 33 points.

[0047] The total score scale ranges from 0 to 300. The live birth rate variable is a continuous variable, comprising one or more live birth rate sub-variables. Each live birth rate sub-variable includes a range of values, and each range corresponds to a score range on the total score scale. For example, the live birth rate sub-variables include the live birth rate after the first ovulation induction-guided intercourse, the live birth rate after the second ovulation induction-guided intercourse, the live birth rate after the third ovulation induction-guided intercourse, the live birth rate after the fourth ovulation induction-guided intercourse, and the live birth rate after the fifth ovulation induction-guided intercourse. The score scale, the predictor variables corresponding to each final clinical pregnancy rate predictor, the total score scale, and each live birth rate sub-variable are each located in a row of the live birth rate prediction nomogram.

[0048] In one specific embodiment, such as Figure 2As shown, the live birth rate prediction nomogram has the following columns: First row: Score, ranging from 0 to 100; Second row: LH / FSH, score 6.08 * (73 - LH / FSH); Third row: FAI value, score 2.22 * (45 - FAI value); Fourth row: HDL-C concentration, score 33.33 * (HDL-0.4); Fifth row: Whether metformin was taken orally, score 0 for no metformin and 33 for taking metformin; Sixth row: Whether there was a change in weight, score 0 for no weight loss and 23 for weight loss. The seventh row is the total score, ranging from 0 to 300 points; the eighth row is the linear predictive value, ranging from -2.5 to 2 points; the ninth row is the probability of the first live birth, ranging from 0.02 to 0.2 points; the tenth row is the probability of the second cumulative live birth, ranging from 0.05 to 0.5 points; the eleventh row is the probability of the third cumulative live birth, ranging from 0.1 to 0.7 points; the twelfth row is the probability of the fourth cumulative live birth, ranging from 0.1 to 0.8 points; and the thirteenth row is the probability of the fifth cumulative clinical pregnancy. The probability ranges from 0.1 to 0.9. The fourteenth row represents the probability of the sixth cumulative clinical pregnancy, with a score range of 0.1 to 0.9; the fifteenth row represents the probability of the seventh cumulative clinical pregnancy, with a score range of 0.1 to 0.9; the sixteenth row represents the probability of the eighth cumulative clinical pregnancy, with a score range of 0.1 to 0.9; the seventeenth row represents the probability of the ninth cumulative clinical pregnancy, with a score range of 0.2 to 0.9; and the eighteenth row represents the probability of the tenth cumulative clinical pregnancy, with a score range of 0.2 to 0.9.

[0049] In the clinical pregnancy rate prediction nomogram, rows two through six represent the predictor variables for each final clinical pregnancy rate predictor. The score for a predictor variable is obtained where a vertical line drawn from the specific option of that predictor intersects with the score in the first row. The total score for the patient is obtained by summing the scores of all predictor variables. A vertical line drawn downwards from the total score in row seven intersects with the cumulative clinical pregnancy rates in rows nine, ten, eleven, twelfth, thirteenth, fourteenth, fifteenth, sixteenth, seventeenth, and eighteenth. This intersection yields the cumulative live birth rate for the patient after the first, second, third, fourth, fifth, sixth, seventh, eighth, ninth, and tenth ovulation-inducing guided intercourse.

[0050] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

[0051] Example 1 This embodiment provides a method for predicting live birth through ovulation induction in patients with polycystic ovary syndrome based on a Cox regression model, including the following steps: Step 1: Historical data of patients with polycystic ovary syndrome (PCOS) were obtained as a training cohort. The historical data consisted of information on pregnant women with PCOS who underwent ovulation induction-guided intercourse for live birth. The data source for Step 1 is as follows: A prospective study was conducted on 655 patients with polycystic ovary syndrome who underwent ovulation induction and guided intercourse between August 2020 and June 2023 as the training cohort (see inclusion process). Figure 3 Collect predictive variables and outcome indicators, including demographic characteristics, sex hormone levels, metabolic characteristics, clinical characteristics, and pregnancy outcomes.

[0052] The predictor variables are as follows: (1) Demographic characteristics: age, duration of infertility, type of infertility, history of childbirth, weight, body mass index (BMI), waist circumference, hip circumference, etc.; (2) Sex hormone levels: basal follicle-stimulating hormone (FSH), basal luteinizing hormone (LH), basal estrogen, basal progesterone, 17α-hydroxyprogesterone, anti-Müllerian hormone (AMH), testosterone concentration, sex hormone-binding globulin, free testosterone index (FAI), etc.; (3) Metabolic characteristics: fasting blood glucose, fasting insulin, insulin resistance (HOMA-IR) index, triglycerides, high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), total cholesterol, etc.; (4) Clinical characteristics: polycystic ovarian changes, clinical hyperandrogenism, whether metformin is taken orally, whether weight loss occurs, etc.

[0053] The specific outcome indicator is the pregnancy outcome (live birth or non-live birth) after ovulation induction and subsequent induction of intercourse.

[0054] Treatment plan: Ovulation is induced by clomiphene or letrozole. Once ovulation is indicated by transvaginal ultrasound monitoring (when the follicle diameter is >18mm), urine LH test strips, or body temperature monitoring, intercourse can be initiated.

[0055] Follow-up and results: After each cycle of ovulation induction and guided intercourse, follow-up was conducted to check for menstruation, HCG positivity, gestational sac observation under ultrasound, and whether a live birth occurred.

[0056] Step Two: Using R language, univariate Cox regression analysis was performed on the demographic characteristics, sex hormone levels, metabolic characteristics, and clinical characteristics of patients with polycystic ovary syndrome. Univariate predictive variables related to clinical pregnancy were initially screened out as follows: LH / FSH, FAI value, HDL-C value, whether metformin was used, and whether there was weight loss (P<0.05).

[0057] Step 3:Using R language, multivariate Cox regression analysis was conducted to identify differentially related variables in clinical pregnancy identified in univariate Cox regression analysis. The independent predictors of clinical pregnancy in polycystic ovary syndrome (PCOS) patients after ovulation induction-guided intercourse were LH / FSH, FAI, HDL-C, metformin use, and weight loss. The variables to be included in the final model were selected, and the optimal model was chosen based on the AIC (Akaike information criterion) value and the model's ease of clinical application.

[0058] Step Four: The "rms" package in R is used to plot nomograms and calibration curves; the C-index is used to evaluate the model's discrimination; calibration curves are used to evaluate the model's calibration accuracy; and time-dependent ROC curves are used. The dependent ROC is used to evaluate the model's ability to predict clinical pregnancy in a specific treatment cycle; the DCA curve is used to evaluate the model's net benefit at different thresholds.

[0059] Statistical Analysis: R language was used as the primary tool for analyzing all data in this patent. R packages, including "survival" and "rms", were used as needed in the study. All statistical tests were two-tailed, and P < 0.05 was considered statistically significant.

[0060] After the above steps, a nomogram was finally constructed to represent the final model (see...). Figure 2 ). Figure 2 In this model, the cumulative rate refers to the cumulative clinical pregnancy rate. Variables included in the final model include: LH / FSH ratio, FAI value, HDL-C value, whether metformin was used, and whether there was weight loss. See the table below:

[0061] The overall C-index of the model is 0.666. The final calculation formula for the model is (nomial graph): S(t) = 1 - S0(t)^exp[(β1×X1+…+βn×Xn)] S(t) = 1 - S0(t)^exp(K) K = -0.1462 × (LH / FSH) - 0.0532 × (FAI value) + 0.7980 × (HDL-C value) + 0.7866 × (Metformin use) + 0.5528 × (weight loss) S0(t) refers to the live birth rate at a specific point in time. This can be expressed through K... M-curve estimation.

[0062] In summary, this invention establishes a predictive model using a training cohort, comprising LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether weight loss has occurred. The model exhibits good discrimination and calibration in the training cohort, effectively predicting the cumulative live birth probability in polycystic ovary syndrome (PCOS) patients undergoing ovulation-inducing intercourse in the first, second, third, fourth, fifth, sixth, seventh, eighth, ninth, and tenth cycles. Among the variables included in the model, the FAI value has the greatest impact; a lower FAI value corresponds to a higher cumulative pregnancy probability, consistent with clinical experience and significant for guiding anti-androgen therapy. The predictive model established according to this invention can assess the probability of achieving a live birth through ovulation-inducing intercourse in different PCOS patients, resolving the problems raised in the background art.

[0063] If the method is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a read-only memory (ROM), etc. Various media that can store program code, such as single memory, random access memory (RAM), external hard drives, magnetic disks, or optical discs.

Claims

1. A live birth prediction system for polycystic ovary syndrome patients after ovulation induction and intercourse, characterized in that... include: The data acquisition module is used to acquire basic data from multiple patients with polycystic ovary syndrome. The preliminary screening module, connected to the data acquisition module, is used to calculate, based on the basic data of patients with polycystic ovary syndrome, using a univariate Cox regression model to obtain multiple preliminary live birth rate predictors that may predict live birth. The final screening module, connected to the preliminary screening module, is used to calculate the multiple preliminary live birth rate predictors obtained by the preliminary screening module through a multi-factor Cox regression model to obtain the final live birth rate predictors used to predict live births. A live birth rate model building module, connected to the final screening module, is used to build a live birth rate prediction model from the final live birth rate prediction factors screened by the final screening module. The nomogram drawing module is connected to the live birth rate model construction module and is used to draw a live birth rate prediction nomogram based on the live birth rate prediction model to predict the live birth rate after ovulation induction and guided intercourse in patients with polycystic ovary syndrome.

2. The system according to claim 1, characterized in that, The basic personal data includes: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether weight has been lost.

3. The system according to claim 1, characterized in that, The preliminary screening module includes: The Cox regression model building unit is used to build a univariate Cox regression model for live birth rate prediction based on the basic data of patients with polycystic ovary syndrome. The preliminary screening unit, connected to the Cox regression model construction unit, is used to obtain multiple preliminary live birth rate predictors based on the single-factor Cox regression model.

4. The system according to claim 1, characterized in that, The final screening module uses a multivariate Cox regression model to obtain the p-value of each predictor and compares it with the high predictive value threshold to obtain multiple final live birth rate predictors.

5. The system according to claim 1, characterized in that, The live birth rate prediction nomogram includes: The scoring scale has a score range of 0 to 100; The predictor variables corresponding to each final live birth rate predictor include: LH / FSH, FAI value, HDL-C value, whether metformin is used, and whether there is weight loss. Each predictor variable includes multiple variable values, and each variable value corresponds to a score on the score scale. The total score scale ranges from 0 to 300. The clinical pregnancy rate variable is a continuous variable, including one or more live birth rate variables, and each live birth rate sub-variable includes a range of variable values, and each range of variable values ​​corresponds to a range of scores on the total score scale.

6. A method for predicting live birth after ovulation induction and intercourse guidance in patients with polycystic ovary syndrome, comprising the following steps: S1. Obtain basic data from multiple patients with polycystic ovary syndrome; S2. Based on the basic data of patients with polycystic ovary syndrome, a univariate Cox regression model was used to calculate and obtain multiple preliminary live birth rate predictors that may predict live birth. S3. The multiple preliminary live birth rate predictors obtained by the preliminary screening module are calculated using a multi-factor Cox regression model to obtain the final live birth rate predictors used to predict live births. S4. Construct a live birth rate prediction model using the final live birth rate prediction factors selected by the final screening module; S5. Based on the live birth rate prediction model, draw a live birth rate prediction nomogram to predict the live birth rate after ovulation-inducing intercourse in patients with polycystic ovary syndrome.

7. A nomogram, constructed according to the method for predicting live birth after intercourse guided by ovulation induction in patients with polycystic ovary syndrome as described in claim 6.

8. The use of the nomogram of claim 7 in the preparation of a kit for predicting the live birth rate after ovulation induction in patients with polycystic ovary syndrome.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for predicting live birth after intercourse guided by ovulation induction in patients with polycystic ovary syndrome, the steps being as follows: S1. Obtain basic data from multiple patients with polycystic ovary syndrome; S2. Based on the basic data of patients with polycystic ovary syndrome, a univariate Cox regression model was used to calculate and obtain multiple preliminary live birth rate predictors that may predict live birth. S3. The multiple preliminary live birth rate predictors obtained by the preliminary screening module are calculated using a multi-factor Cox regression model to obtain the final live birth rate predictors used to predict live births. S4. Construct a live birth rate prediction model using the final live birth rate prediction factors selected by the final screening module; S5. Based on the live birth rate prediction model, draw a live birth rate prediction nomogram to predict the live birth rate after ovulation induction and guided intercourse in patients with polycystic ovary syndrome.

10. A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a method for predicting live birth after intercourse guided by ovulation induction in patients with polycystic ovary syndrome, the steps being as follows: S1. Obtain basic data from multiple patients with polycystic ovary syndrome; S2. Based on the basic data of patients with polycystic ovary syndrome, a univariate Cox regression model was used to calculate and obtain multiple preliminary live birth rate predictors that may predict live birth. S3. The multiple preliminary live birth rate predictors obtained by the preliminary screening module are calculated using a multi-factor Cox regression model to obtain the final live birth rate predictors used to predict live births. S4. Construct a live birth rate prediction model using the final live birth rate prediction factors selected by the final screening module; S5. Based on the clinical pregnancy rate prediction model, a live birth rate prediction nomogram is plotted to predict the live birth rate after ovulation induction-guided intercourse in patients with polycystic ovary syndrome.

Images