Embryo formation-based blastocyst formation prediction method, system, and apparatus

Abstract

The application discloses a blastocyst formation prediction method, system and device based on embryo formation score, relates to the field of assisted reproductive technology, and comprises the following steps: collecting embryo morphological information of a patient, and constructing a training set and a verification set; based on the training set, a generalized estimating equation is used for modeling to obtain a blastocyst formation prediction model; the blastocyst formation prediction model is verified and calibrated based on the verification set; and whether the blastocyst is formed is predicted through the calibrated blastocyst formation prediction model. The application can quantitatively generate the blastocyst formation opportunity of a single embryo and a patient individual, and provides a basis for clinical decision-making.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of assisted reproductive technology, in particular to a blastocyst formation prediction method, system and device based on embryonic morphokinetics scoring. BACKGROUND

[0002] Multiple pregnancy and related complications are important risks that threaten the health of mother and infant. The main solution to this is to promote single blastocyst transfer (SBT). SBT requires that the fertilized embryo be cultured in vitro to the 5th or 6th day to obtain a blastocyst for transplantation. In this process, the patient may not have a blastocyst to transplant due to low blastocyst formation rate, while missing the opportunity to transplant cleavage stage embryos on the third day after fertilization. Therefore, it is necessary to make a clinical decision on the third day after fertilization to assess the feasibility of SBT by predicting the blastocyst formation rate for the progress of ART.

[0003] Currently, the decision to determine whether an ART patient undergoes SBT mainly relies on clinical experience, the number of third-day formed embryos and other relatively vague indicators, which lack repeatability and reliability. SUMMARY

[0004] To solve the above problems, the present application provides a blastocyst formation prediction method, system and device based on embryonic morphokinetics scoring.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] A blastocyst formation prediction method based on embryonic morphokinetics scoring, comprising:

[0007] Collecting embryonic morphological information of a patient and constructing a training set and a validation set;

[0008] Based on the training set, a generalized estimating equation is used for modeling to obtain a blastocyst formation prediction model;

[0009] The blastocyst formation prediction model is verified and calibrated based on the validation set;

[0010] Whether a blastocyst is formed is predicted by the calibrated blastocyst formation prediction model.

[0011] Optionally, before collecting the embryonic morphological information of the patient, it further comprises:

[0012] Determining whether the patient is a patient meeting the inclusion criteria; the patient meeting the inclusion criteria is a patient who is free of any contraindication for assisted reproductive technology and decides to undergo blastocyst culture.

[0013] Optionally, the embryo morphological information includes: whether early cleavage occurs on the first day after fertilization, the number of cells on the third day after fertilization, the cell fragmentation grade on the third day after fertilization, and the cell symmetry on the third day after fertilization.

[0014] Optionally, the expression for the blastocyst formation prediction model is as follows:

[0015] p = exp(y) / (1-exp(y))

[0016] y = β1X1 + ... + β n X n +Intercept

[0017] Where p represents the predicted value of blastocyst formation, y represents the intermediate value, and X represents the intermediate value. n This represents the morphological information of the nth embryo of the current patient.

[0018] Optionally, the blastocyst formation prediction model is validated and calibrated based on the validation set, specifically including:

[0019] The accuracy of the blastocyst formation prediction model in the validation set was verified using receiver operating characteristic (ROC) curves.

[0020] The validation set is input into the blastocyst formation prediction model to obtain the predicted value;

[0021] A calibration curve is constructed using the predicted values ​​as the x-axis and the observed values ​​corresponding to the validation set as the y-axis.

[0022] The calibration curve is linearly and smoothly fitted to obtain the fitted curve;

[0023] The blastocyst formation prediction model is calibrated based on the slope and intercept of the fitted curve.

[0024] Optionally, after predicting whether a blastocyst will form using a calibrated blastocyst formation prediction model, the method further includes:

[0025] The cumulative probability of no blastocyst formation in the current patient is calculated based on the predicted value of blastocyst formation output by the blastocyst formation prediction model.

[0026] This invention also provides a blastocyst formation prediction system based on embryogenesis scoring, comprising:

[0027] The training and validation set construction module is used to collect patients' embryo morphology information and construct training and validation sets;

[0028] The model building module is used to build a model based on the training set using a generalized estimation equation to obtain a blastocyst formation prediction model.

[0029] a model verification and calibration module configured to verify and calibrate the blastocyst formation prediction model based on the verification set;

[0030] a prediction module configured to predict whether a blastocyst is formed by the calibrated blastocyst formation prediction model.

[0031] The present application also provides an electronic device comprising a memory and a processor, wherein the memory is configured to store a computer program, and the processor is configured to execute the computer program to enable the electronic device to perform the blastocyst formation prediction method based on embryo morphology score.

[0032] The present application also provides a computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the blastocyst formation prediction method based on embryo morphology score.

[0033] According to the embodiments of the present application, the following technical effects are achieved:

[0034] The present application provides a blastocyst formation prediction method, system and device based on embryo morphology score, which models by using generalized estimating equation based on embryo morphology information of a patient, obtains a blastocyst formation prediction model, verifies and calibrates the model, and predicts whether a blastocyst is formed by the calibrated blastocyst formation prediction model. The present application can quantitatively generate blastocyst formation opportunities of individual embryos and patients, and provide a basis for clinical decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0036] Figure 1 A flowchart of the blastocyst formation prediction method based on embryo morphology score provided by the present application;

[0037] Figure 2 A performance diagram of the blastocyst formation prediction model in predicting blastocyst transfer cycles. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0039] Embryo morphology scoring is an important part of ART, with high reliability and repeatability. The purpose of the present application is to provide a blastocyst formation prediction method, system and device based on embryo morphology scoring, which can quantitatively generate the blastocyst formation opportunities of individual embryos and patients after morphology scoring is completed, and provide a basis for clinical decision-making.

[0040] In order to make the above-mentioned purposes, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below in combination with the drawings and specific embodiments.

[0041] Embodiment one

[0042] As shown in the figure, the blastocyst formation prediction method based on embryo morphology scoring provided by the present embodiment comprises the following steps: Figure 1

[0043] S1: Collect embryo morphology information of patients, and construct a training set and a validation set.

[0044] Collect the embryo morphology information of IVF patients, and perform preliminary data screening and filtering, confirm the inclusion criteria, construct a data set, and divide the data set into a training set (development set) and a validation set (external validation set). The division basis can be factors such as data collection time and place. The inclusion criteria for the subjects are to exclude any contraindications for assisted reproductive technology, and to determine patients who decide to perform blastocyst culture.

[0045] The embryo morphology information includes whether early cleavage occurs on the first day after fertilization, the number of cells on the third day after fertilization, the grade of cell fragments on the third day after fertilization, and the symmetry of cells on the third day after fertilization. All cell morphology information is based on single microscopy observation results at a specific time point. The definition of the time point and the technical standard of observation follow the Istanbul consensus published by the European Society of Human Reproduction and Embryology (ESHRE).

[0046] S2: Based on the training set, a generalized estimating equation is used for modeling to obtain a blastocyst formation prediction model.

[0047] The generalized estimating equation (GEE) is a statistical model developed on the basis of the generalized linear model, which is specifically used to process repeated measurement data such as longitudinal data. In the present application, it is used to process morphology measurement data from different embryos of the same patient.

[0048] GEE introduces the concept of working correlation matrix on the basis of generalized linear model. First, assume that the repeated measurements are independent, calculate β according to the generalized linear model, then modify the estimation of β according to the current working covariance matrix, and repeat this process until convergence.​

[0049] where the blastulation (the outcome variable) measured for the jth embryo of the ith patient has:

[0050] Y i = (Y i1 , Y i2, ,..., Y ij ), (i = 1, 2,..., k; j = 1, 2,..., t)

[0051] The marginal expectation of Y ij is a known function of the covariates X ij :

[0052] E(Y ij ) = μ ij , g(μ ij ) = β0+ β1X ij1 + β2X ij2 +... + β p X ijp

[0053] where: g() is called the link function, the link function in this application is logit link; β = (β1... β p ) is the parameter vector to be estimated in the model.

[0054] The marginal variance of Y ij is a known function of the marginal expectation:

[0055] Var(Y ij ) = V(μ ij )* Φ

[0056] where: V(.) is a known function; Φ is the scale parameter, representing the part of the variance of Y that cannot be explained by V(μ ij ). For binomial distribution, Φ = 1.

[0057] A P*P dimensional working correlation matrix R ij (Φ) is constructed for Y i to represent the size of the correlation between each repeated measurement of the dependent variable.

[0058] Let A i be a P*P dimensional diagonal matrix, whose working covariance matrix is V i = ΦA i 1 / 2 R i (α)A i 1 / 2

[0059] The β estimation equation obtained accordingly is:

[0060]

[0061] Modeling is performed according to the training set in step S1. Embryo morphological information is converted into dummy variables when incorporated into the model. The cell number on the third day after fertilization is a continuous variable, which is first converted into the following classification variable: 8-cell (control level), 2-3-cell, 4-6-cell, 7-cell, 9-11-cell, 12-15-cell and compaction; and then converted into a dummy variable with 8-cell as the control level. The cell fragment level on the third day after fertilization is incorporated into the model as a continuous variable.

[0062] y = β1X1+... + β n X n + intercept

[0063] Wherein, n is the nth variable screened in step S1, i.e. embryo morphological information; β is the coefficient of the nth variable. The specific formula is:

[0064] Y = 1.101 + 0.682*(whether early cleavage occurs, yes == 1) + (-4.327)*(2-3-cell embryo, yes == 1) + (-1.768)*(4-6-cell embryo, yes == 1) + (-0.665)*(7-cell embryo, yes == 1) + (-0.583)*(9-11-cell embryo, yes == 1) + (-0.303)*(12-15-cell embryo, yes == 1) + (-0.456)*(compaction embryo, yes == 1) + (-0.053)*(embryo fragment rate, percentage) + (-0.518)*(unequal cleavage, yes == 1);

[0065] The final prediction value is p = exp(y) / (1-exp(y).

[0066] The single embryo blastocyst formation rate of all embryos of a specific patient is calculated, and then the cumulative probability of no blastocyst formation of the patient is calculated: cumulative probability = 1-∏(1-single embryo blastocyst formation rate); wherein ∏ is a Greek letter representing multiplication.

[0067] S3: verifying and calibrating the blastocyst formation prediction model based on the verification set.

[0068] The discriminatory power of the blastulation prediction model in the validation set was tested by the Receiver Operator Characteristic (ROC) curve. The consistency of the predicted value and the observed value in the validation set was tested by the calibration curve. The specific method is: taking the predicted value as the abscissa and the observed value as the ordinate, linear and smooth fitting is performed on each individual data (observation) in the validation set. According to the results of linear fitting, the slope and intercept of the fitted curve are obtained. According to the slope and intercept, the predicted value is calibrated. The method is p' = slope * p + intercept. Where p' is the calibrated predicted value, p is the predicted value before calibration; slope is the slope obtained by linear fitting of the calibration curve; intercept is the intercept obtained by linear fitting of the calibration curve.

[0069] S4: Predicting whether a blastocyst is formed by the calibrated blastulation prediction model.

[0070] The application examples are as follows:

[0071] A retrospective analysis was performed on patients who underwent blastocyst culture at the Affiliated Hospital of Xiamen University from 2013 to 2019. According to the time of treatment, the training data (before 2019) and the validation data (in and after 2019) were divided. The training data included 13657 patients. The median age of the patients was 30 years [28-33]. 3010 (23.1%) cycles received ICSI, and 10038 (76.9%) received IVF treatment. A total of 96378 embryos were cultured for blastocyst culture. Early cleavage occurred in 42669 (44.3%) embryos. Finally, 55323 (57.4%) embryos developed into blastocysts. In the validation data including 1956 patients, the median age of the patients was 31 years [29-34]. 506 (25.9%) cycles received ICSI, and 1450 (74.1%) received IVF treatment. A total of 11770 embryos were cultured for blastocyst culture. Early cleavage occurred in 5961 (50.6%) embryos. Finally, 7024 (59.7%) embryos developed into blastocysts, as shown in Tables 1 and 2.

[0072] Table 1 Characteristics of patients

[0073]

[0074]

[0075] Table 2 Characteristics of embryos for blastocyst culture

[0076]

[0077]

[0078] Based on the predictive model of the present application, the AUC in the training set was 0.771 (95% CI: 0.768-0.774) and the AUC in the validation set was 0.779 (95% CI: 0.77-0.787). The threshold value was 0.51 according to the Youden index. The prediction accuracy according to the threshold value was 74.7% (95% confidence interval: 73.9%-75.5%) in the validation set.

[0079] As a comparison, to estimate whether the inclusion of features related to patient characteristics and cycle parameters could improve the predictive ability, a model including an additional 27 features was also built, which were: female age, male age, GnRH analogue, insemination protocol, TESA / PESA, mother's height, mother's weight, mother's BMI, mother's basal FSH, mother's basal LH, mother's basal PRL, mother's basal E2, mother's basal T, basal AFC, gonadotropin dose, gonadotropin duration, HMG dose, HMG duration, starting dose, FSH on stimulation day, LH on stimulation day, E2 on stimulation day, E2 on trigger day, LH on trigger day, P on trigger day, oocyte yield and intra-cycle oocyte maturation rate.

[0080] Two strategies were used to incorporate these features into the predictive model. First, a least absolute shrinkage and selection operator (LASSO) model was used for feature selection, and the resulting features and morphological parameters were used to predict blast formation (LASSO model). Second, an extreme gradient boosting (XGboost) algorithm was used to build a gradient boosting tree with features (XGboost model).

[0081] The LASSO regression model and the XGboost model based on cycle features and embryo morphology combined produced similar AUCs of 0.78 (95% CI: 0.771-0.789) and 0.754 (95% CI: 0.745-0.763) in the validation set, respectively. There was no significant difference in the efficacy shown by different models in predicting AUC, as shown in Table 3.

[0082] Table 3 Discriminatory ability of different models for blast formation

[0083]

[0084]

[0085] The present application further explores the critical value of the GEE model in different patient subgroups for blast formation, as shown in Table 4. The predictive ability of AUC is similar in general.

[0086] Table 4. Discriminative power of morphological models for different subgroups of patients

[0087]

[0088]

[0089]

[0090] In clinical practice, whether a blastocyst transfer cycle is cancelled can depend on the availability of all blastocyst-forming embryos in the cycle. To mimic this situation, the present invention further generated a prediction of blastocyst yield per cycle based on the model. The predicted number of blastocysts per cycle was the sum of the individual embryo predictions. For the blastocyst yield per cycle, the predicted number of blastocysts using only morphological parameters was strongly correlated with the observed number of blastocysts (r = 0.897, P < 0.0001) with a mean absolute error (MAE) of 0.95 (95% CI: 0.92-0.99).

[0091] MAE = (1 / n) *∑|observed - predicted|, i.e. the mean of the absolute values of the difference between each observed value and the corresponding predicted value in a sample containing n observations.

[0092] The predicted number of blastocysts was also used to predict the chance of blastocyst transfer, with an AUC of 0.926 (95% CI: 0.911-0.94). In comparison, the present invention built a cycle prediction model based on 29 features using Xgboost, with an AUC of 0.885 (95% CI: 0.867-0.903). The blastocyst number prediction outperformed the XGBoost model. Figure 2 The AUC and calibration curves of both models are shown in Figure 6, Figure 2 Figure 6 (a) is a scatter plot indicating the correlation between the observed number of blastocysts and the predicted number of blastocysts based on embryo morphology. Figure 2 Figure 6 (b) is the ROC curve predicting blastocyst cycles based on the embryo-based model and the cycle-based model. Figure 2 Figure 6 (c) is the calibration curve relating the predicted probability and the observed proportion of blastocyst transfer according to the embryo-based and cycle-based models. The cycle-based model seems to overestimate the chance of blastocyst transfer (slope = 1.01, intercept = -0.009), while the predicted number of blastocysts brings the prediction closer to the observed probability (slope = 1.15, intercept = -0.185).

[0093] In Table 5, the prediction of blastocyst transfer was stratified according to patient subgroups. There was no significant difference in the predictive ability of the ROC curve AUC in patients over 34 years of age or in patients with respect to the unselected population. On the other hand, the AUC was reduced in patients without good quality embryos. However, the AUC in patients without good quality embryos still indicated moderate discriminative power, with a value of 0.74 (95% CI: 0.68-0.79).

[0094] Table 5 Performance of the model for predicting the chance of blastocyst transfer in different subgroups of patients

[0095]

[0096]

[0097]

[0098]

[0099] Embodiment Two

[0100] In order to perform the method corresponding to the above-mentioned embodiment one, to realize the corresponding functions and technical effects, a blastocyst formation prediction system based on embryo morphological score is provided below.

[0101] The system comprises:

[0102] A training set and a validation set construction module is configured to collect embryo morphological information of patients and construct a training set and a validation set.

[0103] A model establishment module is configured to model based on the training set by using a generalized estimating equation to obtain a blastocyst formation prediction model.

[0104] A model verification and calibration module is configured to verify and calibrate the blastocyst formation prediction model based on the validation set.

[0105] A prediction module is configured to predict whether a blastocyst is formed by the calibrated blastocyst formation prediction model.

[0106] Embodiment Three

[0107] Embodiment three of the present application provides an electronic device comprising a memory and a processor, the memory being configured to store a computer program, and the processor being configured to run the computer program to enable the electronic device to perform the blastocyst formation method based on embryo morphological score provided by embodiment one.

[0108] In practical applications, the above-mentioned electronic device can be a server.

[0109] In practical applications, the electronic device comprises at least one processor, a memory, a bus and a communications interface.

[0110] The processor, the communications interface and the memory communicate with each other through the communications bus.

[0111] The communications interface is configured to communicate with other devices.

[0112] The processor is configured to execute a program, and specifically can execute the method described in the above embodiments.

[0113] Specifically, the program can comprise program code comprising computer operation instructions.

[0114] The processor can be a central processing unit (CPU) or an application specific integrated circuit (ASIC) or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the electronic device can be processors of the same type, such as one or more CPUs, or processors of different types, such as one or more CPUs and one or more ASICs.

[0115] The memory is configured to store the program. The memory can include a high-speed RAM memory and can also include a non-volatile memory, such as at least one disk memory.

[0116] Embodiment four

[0117] Based on the description of embodiment three, embodiment four of the present application provides a storage medium having a computer program stored thereon, which can be executed by a processor to implement the blastocyst formation method based on embryo formation science scoring of embodiment one.

[0118] The blastocyst formation system based on embryo formation science scoring provided by embodiment two of the present application exists in various forms, including but not limited to:

[0119] (1) Mobile communication device: This type of device is characterized by having mobile communication function and providing voice and data communication as the main target. This type of terminal includes smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.

[0120] (2) Ultra-mobile personal computer device: This type of device belongs to the category of personal computers and has computing and processing functions, and generally also has mobile Internet access performance. This type of terminal includes PDA, MID and UMPC devices, such as iPad.

[0121] (3) Portable entertainment device: This type of device can display and play multimedia content. This type of device includes audio, video players (e.g., iPod), hand-held game consoles, electronic books, and smart toys and portable car navigation devices.

[0122] (4) Other electronic devices with data interaction function.

[0123] So far, specific embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0124] The systems, apparatuses, modules or units illustrated by the above embodiments can be specifically implemented by a computer chip or entity, or a product with some functions. A typical implementation device is a computer. Specifically, the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0125] For the sake of description, the above apparatuses are described with various units functionally divided. Of course, in implementing the present application, the functions of the units can be implemented in one or more software and / or hardware. Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatuses (systems) and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a machine that implements the functions described in the flowcharts and / or block diagrams.Figure 1 one or more processes and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0127] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 one or more processes and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 one or more processes and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0129] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0130] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, such as read-only memory (ROM), EPROM, and / or flash memory, etc. The memory is an example of computer readable media.

[0131] Computer readable media includes permanent and non-permanent, moveable and non- moveable media that can be implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disks (DVDs) or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that is accessible to a computing device. According to the definition in this disclosure, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0132] It is also to be noted that the terms "comprising", "including", and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0133] The application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer.

[0134] Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0135] The various embodiments described in this specification are presented by way of example, and are not intended to limit the scope of the application. The various embodiments can be implemented in any combination of hardware and / or software. The description of the embodiments is intended to cover any and all modifications within the scope of the present application, including various alternative embodiments as can be gleaned from a review of the disclosure. For the purposes of the present application, the terms "coupled" and "connected", along with their derivatives, can be used interchangeably, unless expressly stated to the contrary. The term "coupled" or "connected" means either a direct connection or an indirect connection or an indirect connection through one or more intervening devices or components.

[0136] The principles and implementation modes of the present application are described herein by applying specific examples, and the above description of the examples is only for the purpose of helping to understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will have changes. In view of the above, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A blastulation prediction method based on embryonic morphogenesis score, characterized by, The method comprises the following steps: Collecting embryo morphology information of a patient and constructing a training set and a validation set; Before collecting the embryo morphology information of the patient, further comprising: judging whether the patient is a patient meeting the inclusion criteria; the patient meeting the inclusion criteria is a patient who is excluded from any assisted reproductive technology contraindication and decides to perform blastocyst culture; the embryo morphology information comprises: whether early cleavage occurs on the first day after fertilization, the number of cells on the third day after fertilization, the grade of cell fragments on the third day after fertilization, and the symmetry of cells on the third day after fertilization; Based on the training set, a generalized estimating equation is used for modeling to obtain a blast formation prediction model; the expression of the blast formation prediction model is as follows: p = exp(y) / (1-exp(y)), y = β1X1+...+β n X n +intercept; wherein p represents a blast formation prediction value, y represents an intermediate quantity, X n represents the n th embryo morphology information of the current patient. Verifying and calibrating the blastocyst formation prediction model based on the validation set; specifically comprising: verifying the accuracy of the blastocyst formation prediction model in the validation set through a receiver operating characteristic curve; inputting the validation set into the blastocyst formation prediction model to obtain a predicted value; constructing a calibration curve with the predicted value as the abscissa and the observed value corresponding to the validation set as the ordinate; linearly and smoothly fitting the calibration curve to obtain a fitting curve; calibrating the blastocyst formation prediction model according to the slope and intercept of the fitting curve; Predicting whether a blastocyst is formed by the calibrated blastocyst formation prediction model.

2. The blastulation prediction method based on embryonic patterning score according to claim 1, wherein, After predicting whether a blastocyst is formed by the calibrated blastocyst formation prediction model, further comprising: Calculating the cumulative probability of no blastocyst formation for the current patient according to the predicted value of blastocyst formation output by the blastocyst formation prediction model.

3. A blastocyst formation prediction system based on embryonic morphometrics scoring, characterized by, The system is applied to the blastocyst formation prediction method based on embryo formation score according to any one of claims 1-2, and the system comprises: A training set and a validation set construction module for collecting embryo morphology information of a patient and constructing a training set and a validation set; A model establishment module for modeling based on the training set by using a generalized estimating equation to obtain a blastocyst formation prediction model; A model verification and calibration module for verifying and calibrating the blastocyst formation prediction model based on the validation set; A prediction module for predicting whether a blastocyst is formed by the calibrated blastocyst formation prediction model.

4. An electronic device, comprising: The electronic device comprises a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to make the electronic device execute the blastocyst formation prediction method based on embryo formation score according to any one of claims 1-2.

5. A computer readable storage medium, characterized in that, The computer program stored in the memory is executed by the processor to implement the blastocyst formation prediction method based on embryo formation score according to any one of claims 1-2.

Images