CN114758780A

CN114758780A - Postpartum hemorrhage prediction method, device, terminal and storage medium

Info

Publication number: CN114758780A
Application number: CN202210495121.2A
Authority: CN
Inventors: 陈艳红; 陈敦金; 王志坚; 黄素然; 詹芷晴; 甘玉杰; 杜丽丽; 廖色坭; 陈子恩; 赵磊
Original assignee: Individual
Current assignee: Individual
Priority date: 2022-05-07
Filing date: 2022-05-07
Publication date: 2022-07-15

Abstract

The application is applicable to the technical field of clinical prediction, and provides a postpartum hemorrhage prediction method, device, terminal and storage medium, wherein the method comprises the following steps: acquiring clinical data of pregnant and lying-in women according to a preset standard; acquiring a prenatal variable, an intrapartum variable and a postpartum variable; constructing a first model by combining prenatal variables based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm; constructing a second model by combining a prenatal variable and an intrapartum variable based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm; constructing a third model by combining a prenatal variable and an intrapartum variable based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm; and constructing a fourth model by combining the antepartum variable, the intrapartum variable and the postpartum variable based on an artificial neural network and an extreme gradient propulsion algorithm. The method and the device can accurately and efficiently predict whether the postpartum hemorrhage can be caused or not and the severity of the postpartum hemorrhage.

Description

Postpartum hemorrhage prediction method, device, terminal and storage medium

Technical Field

The application belongs to the technical field of prediction, and particularly relates to a postpartum hemorrhage prediction method, device, terminal and storage medium.

Background

Postpartum Hemorrhage (PPH) can lead to a variety of complications, such as perinatal hysterectomy, multiple organ failure, disseminated intravascular coagulation disorders, schin's syndrome, and the like, with severe cases even death. Therefore, the reduction of the postpartum hemorrhage rate has important significance for reducing the death rate of pregnant and lying-in women and ensuring the health and safety of mothers and babies. Studies have shown that most of the deaths associated with postpartum hemorrhage can be avoided if appropriate early clinical interventions are taken in time, including: the preparation before full childbirth, accurate blood preparation, proper childbirth time and mode, timely treatment and the like.

Meanwhile, in the prior art, several clinical prediction models for postpartum hemorrhage are developed aiming at pregnant women of the general population who are delivered by vagina or cesarean section, or scar uterus, or pre-placenta, or preeclampsia. However, these models are considered to have a higher risk of bias due to poor data quality or lack of external validation, insufficient sample size, etc. In addition, these models can only identify women at high risk of postpartum hemorrhage, respectively, and cannot accurately predict the severity of postpartum hemorrhage, resulting in delayed diagnosis and treatment, and even severe perinatal risks.

Disclosure of Invention

In view of this, embodiments of the present application provide a method, an apparatus, a terminal and a storage medium for predicting postpartum hemorrhage, so as to solve the above technical problems.

A first aspect of an embodiment of the present application provides a method for predicting postpartum hemorrhage, including:

acquiring clinical data of pregnant and lying-in women according to a preset standard;

performing advanced screening on clinical data to obtain a plurality of candidate independent variables, and classifying the independent variables to obtain antenatal, intrapartum and postpartum variables;

constructing a first model based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm and combining with prenatal variables to predict whether postpartum hemorrhage occurs through the first model on the premise that a delivery mode is not considered before delivery, and:

based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm, a second model is constructed by combining a prenatal variable and an intrapartum variable, so that whether postpartum hemorrhage can occur or not is predicted through the second model when the parturition mode is cesarean section, and:

constructing a third model based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm by combining a prenatal variable and an intrapartum variable, predicting whether postpartum hemorrhage can occur or not through the third model when the delivery mode is vaginal delivery, and:

and constructing a fourth model by combining the prenatal variable, the intrapartum variable and the postpartum variable based on an artificial neural network and an extreme gradient propulsion algorithm, and predicting the postpartum hemorrhage severity through the fourth model when the delivery mode is caesarean delivery or vaginal delivery.

A second aspect of embodiments of the present application provides a postpartum hemorrhage prediction device, including:

the acquisition module is used for acquiring the clinical data of the pregnant and lying-in women according to a preset standard;

the screening module is used for carrying out advanced screening on the clinical data to obtain a plurality of candidate independent variables and classifying the independent variables to obtain antenatal, antenatal and postpartum variables;

a building module, configured to build a first model based on an artificial neural network, a support vector machine, and an extreme gradient push algorithm, in combination with prenatal variables, to predict whether postpartum hemorrhage will occur through the first model before parturition without considering a parturition manner, and:

A third aspect of embodiments of the present application provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect when executing the computer program.

A fourth aspect of embodiments of the present application provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, performs the steps of the method according to the first aspect.

A fifth aspect of the present application provides a computer program product, which, when run on a terminal, causes the terminal to perform the steps of the method of the first aspect described above.

Therefore, different models are built in stages on the premise of considering different delivery modes by combining actual retrospective multi-center case data based on three different machine learning methods, early diagnosis and intervention of postpartum hemorrhage are facilitated, and the accuracy of clinical treatment, the efficiency of medical resource allocation and the prognosis of patients are finally improved.

The method for constructing the clinical prediction model through the machine learning algorithm has accuracy and high efficiency, and can be widely applied to the technical field of clinical prediction.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a flowchart of a method for predicting postpartum hemorrhage according to an embodiment of the present application;

FIG. 2 is a schematic diagram of the application state of FIG. 1;

fig. 3 is a block diagram of a postpartum hemorrhage prediction device provided in an embodiment of the present application;

fig. 4 is a structural diagram of a terminal according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".

In particular implementations, the terminals described in embodiments of the present application include, but are not limited to, other portable devices such as mobile phones, laptop computers, or tablet computers having touch sensitive surfaces (e.g., touch screen displays and/or touch pads). It should also be understood that in some embodiments, the device is not a portable communication device, but is a desktop computer having a touch-sensitive surface (e.g., a touch screen display and/or touchpad).

In the discussion that follows, a terminal that includes a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse, and/or joystick.

The terminal supports various applications, such as one or more of the following: a drawing application, a presentation application, a word processing application, a website creation application, a disc burning application, a spreadsheet application, a gaming application, a telephone application, a video conferencing application, an email application, an instant messaging application, an exercise support application, a photo management application, a digital camera application, a web browsing application, a digital music player application, and/or a digital video player application.

Various applications that may be executed on the terminal may use at least one common physical user interface device, such as a touch-sensitive surface. One or more functions of the touch-sensitive surface and corresponding information displayed on the terminal can be adjusted and/or changed between applications and/or within respective applications. In this way, a common physical architecture (e.g., touch-sensitive surface) of the terminal can support various applications with user interfaces that are intuitive and transparent to the user.

It should be understood that, the sequence numbers of the steps in this embodiment do not mean the execution sequence, and the execution sequence of each process should be determined by the function and the inherent logic of the process, and should not constitute any limitation to the implementation process of the embodiment of the present application.

In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.

As shown in fig. 1-2, a method for predicting postpartum hemorrhage, the method comprising the steps of:

step 101, acquiring clinical data of pregnant and lying-in women according to a preset standard;

wherein the predetermined criteria may be: 1) women who receive routine prenatal examinations in hospitals; 2) the gestational week is more than or equal to 28 weeks during delivery; 3) the medical record of the pregnant and lying-in women is complete and available at any time.

The collection range can be the clinical data of pregnant and lying-in women in three hospitals of China, and the three hospitals can be the third subsidiary hospital of Guangzhou medical university, southern hospital of southern medical university, people's hospital of Dongguan city, and the like.

Clinical data includes demographic data, prenatal complications, labor and postpartum information, and maternal and neonatal outcomes.

Further, the acquired maternal clinical data may also be subjected to a preliminary screening, e.g. excluding data with missing observations above a preset threshold (e.g. 20%).

In an optional embodiment, when the clinical data of the pregnant and lying-in women is acquired, the clinical data may be further subjected to advanced screening to acquire several candidate independent variables, in this embodiment, 50 candidate independent variables are acquired, including: the method comprises the following steps of age, body mass index, abortion history, uterine fibroid rejection history, vaginal bleeding during pregnancy, hypertensive disease during pregnancy, diabetes mellitus complicated by pregnancy, blood system diseases, autoimmune diseases, uterine fibroids, prenatal hemoglobin, uterine contraction inhibitors, pre-placentas, induced labor, soft birth canal injury, placenta implantation, placenta detention, placental premature peeling, fever during labor, 24h postpartum vaginal bleeding, blood oxygen saturation, heart rate, prothrombin time, activated partial thromboplastin time, fibrinogen, hemoglobin, hematocrit and the like, but the specific implementation is not limited to the above, the number and the variable can be set according to actual needs, and meanwhile, independent variables are classified, and in the embodiment, the method is divided into three types, specifically:

1) prenatal variables, which are the latest prenatal findings within one week before delivery, e.g., prenatal hemoglobin, fetal position abnormalities, pregnancy complications, etc.;

2) intrapartum variables, such as mode of delivery, placental retention, placental prematurity, fever during intrapartum, whether labor is induced, etc.;

3) postpartum variables including mean values of vital signs within 2 hours post partum, laboratory indices are mean values within 24 hours post partum, e.g., fibrinogen, hematocrit, platelet count, blood oxygen saturation, etc.;

wherein the advanced screening mode can be that a multidisciplinary expert team consisting of obstetricians, statisticians and clinical researchers carries out comprehensive evaluation screening according to expert opinions, consensus statements and literature reviews.

Further, univariate regression analysis was performed on the selected candidate independent variables to evaluate the efficacy of the candidate predictors, when variables correlated with postpartum hemorrhage (coefficient P <0.01) were included in the prediction model.

In this embodiment, the prenatal variables included in the prediction model include: age, body mass index, parity of labor, history of abortion, history of cesarean section, history of uterine fibroid removal, history of postpartum hemorrhage, vaginal bleeding during pregnancy, hypertensive disease during pregnancy, pregnancy complicated with diabetes, hematologic diseases, autoimmune diseases, uterine fibroids, prenatal hemoglobin, uterine contraction inhibitor, conception mode, premature rupture of fetal membranes in the short term, premature rupture of fetal membranes, abnormal birth, fetal quantity, and placenta prearranged;

a time-of-flight variable incorporated into the predictive model, comprising: delivery manner, vaginal midwifery, induced labor, soft birth canal injury, placenta implantation, placenta retention, placenta residue, placenta premature peeling, puerperal fever, newborn birth weight, first birth process extension, second birth process extension, third birth process extension, etc.;

postpartum variables incorporated into the predictive model, including: respiratory rate, blood oxygen saturation, heart rate, systolic pressure, diastolic pressure, body temperature, prothrombin time, prothrombin activity, activated partial thromboplastin time, fibrinogen, hemoglobin, hematocrit, platelet count, etc. 2h after delivery.

Step 102, constructing a first model based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm in combination with prenatal variables, so as to predict whether postpartum hemorrhage occurs through the first model without considering a delivery mode before delivery, and:

based on an artificial neural network, a support vector machine and an extreme gradient propulsion algorithm, a second model is constructed by combining a prenatal variable and an intrapartum variable, so that whether postpartum hemorrhage occurs or not is predicted through the second model when the parturition mode is cesarean section, and:

and constructing a fourth model by combining the prenatal variable, the intrapartum variable and the postpartum variable based on an artificial neural network and an extreme gradient advancing algorithm so as to predict the severity of postpartum hemorrhage through the fourth model when the delivery mode is cesarean delivery or vaginal delivery, wherein the severity of PPH can be divided into five grades according to the postpartum hemorrhage amount of the cesarean delivery and the vaginal delivery, and the severity is shown in the following table:

in this embodiment, specific variables included in the first model, the second model, the third model, and the fourth model are shown in the following tables:

it should be noted that, since the first model, the second model and the third model are two-class prediction models, model development is performed by using an artificial neural network, a support vector machine and an extreme gradient push algorithm, and the fourth model predicts the severity of postpartum hemorrhage in caesarean section or vaginal delivery and is a multi-class prediction model, but the support vector machine is a binary classification algorithm and cannot be used for constructing the multi-class prediction model, and therefore, the fourth model is developed only by using the artificial neural network and the extreme gradient push algorithm.

Obviously, different models are constructed in stages on the premise of considering different delivery modes by combining actual retrospective multi-center case data based on three different machine learning methods, so that the early diagnosis and intervention of postpartum hemorrhage are facilitated, and the accuracy of clinical treatment, the efficiency of medical resource allocation and the prognosis of patients are finally improved.

Further, according to a preset rule, dividing the clinical data of the pregnant and lying-in women into a training data set, an internal verification data set and an external test data set according to a preset proportion, and respectively verifying the first model, the second model, the third model and the fourth model to ensure the stability and the extrapolation capability of the machine learning model;

in this embodiment, the data set collected at the third affiliated hospital of Guangzhou medical university is randomly divided into a training data set and an internal verification data set at a ratio of 7:3, and the data sets collected at the southern hospital of southern medical university and the people's hospital of Dongguan are used as external test data sets, but the method is not limited thereto and may be set according to specific situations.

Still further, since the first model, the second model, and the third model are two-class models aimed at distinguishing postpartum hemorrhage from non-postpartum hemorrhage results, they can be evaluated with the area under the subject's working characteristic curve (AUC), accuracy, confusion matrix, and calibration curve, while the fourth model can be evaluated with the accuracy, recall, comprehensive assessment index (F1-Measure), and calibration curve.

In addition, the contribution degrees of the predictive variables may be ranked, specifically:

the variable importance is scalar measurement, the maximum value is 100 minutes, and the top ten variables with the highest score are screened out from candidate variables related to postpartum hemorrhage by using a gradient tree lifting method in XGboost, namely, the contribution degrees of postpartum hemorrhage prediction can be ranked.

Step 103, outputting a preset treatment suggestion according to the prediction result, for example, when the prediction result is no bleeding risk, outputting a similar instruction according to normal perinatal operation and the like, and when the prediction result is 5-level postpartum hemorrhage severity, starting a preset operation flow in advance, for example, preparing sufficient blood, notifying family members in advance and the like.

The method is used for constructing the postpartum hemorrhage clinical prediction model based on the machine learning algorithm, has strong intelligence, can simulate the reasoning process of medical experts for diagnosing diseases by using medical knowledge and provide a reasonable disease treatment scheme, can not only realize the staged prediction of obstetrical disease risks of pregnant and lying-in women and screen factors possibly causing postpartum hemorrhage of the lying-in women, but also can provide corresponding diagnosis and treatment guides in time to guide standardized operation after postpartum hemorrhage, and plays a role in assisting clinicians in making accurate diagnosis and treatment decisions in time and solving complex medical problems, namely, the AI assists in diagnosis and treatment, and is favorable for reducing misdiagnosis rate and missed diagnosis rate;

meanwhile, the postpartum hemorrhage clinical prediction model is constructed based on a machine learning algorithm, and long-term practice, accumulated and searched experience knowledge, scientific research achievements of obstetrical experts can be combined with computer technology to establish a complete set of complete networked disease diagnosis system integrating disease diagnosis, expert online diagnosis and wide information consultation services, so that the knowledge, experience and problem analysis and solving methods of the obstetrical experts can be shared on different levels of treatment platforms, the medical treatment level and technical resources of primary hospitals and the comprehensive capacity of medical staff are improved, and the service efficiency and service quality of medical treatment processes are further improved.

In addition, the perfect medical knowledge base of the application integrates medical knowledge of various departments in the medical field, the diagnosis level of the diagnosis system using the knowledge base can even exceed one single medical expert, and the system can not influence the judgment of diseases due to fatigue or stress and other subjective factors like human experts, thereby greatly improving the diagnosis and treatment efficiency of the diseases.

Referring to fig. 3, fig. 3 is a structural diagram of a postpartum hemorrhage prediction device provided in an embodiment of the present application, and for convenience of explanation, only the parts related to the embodiment of the present application are shown.

The postpartum hemorrhage prediction device comprises:

the acquisition module 301 is used for acquiring clinical data of pregnant and lying-in women according to a preset standard;

a screening module 302 for performing advanced screening on the clinical data to obtain a plurality of candidate independent variables, and classifying the independent variables to obtain prenatal, intrapartum and postpartum variables;

a building module 303, configured to build a first model based on an artificial neural network, a support vector machine, and an extreme gradient prediction algorithm, in combination with prenatal variables, to predict whether postpartum hemorrhage will occur through the first model without considering a delivery manner before delivery, and:

Fig. 4 is a structural diagram of a terminal according to an embodiment of the present application. As shown in the figure, the terminal 4 of this embodiment includes: at least one processor 40 (only one shown in fig. 4), a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, the steps of any of the various method embodiments described above being implemented when the computer program 42 is executed by the processor 40.

The terminal 4 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal 4 may include, but is not limited to, a processor 40, a memory 41. Those skilled in the art will appreciate that fig. 4 is only an example of a terminal 4 and does not constitute a limitation of terminal 4 and may include more or less components than those shown, or some components in combination, or different components, for example, the terminal may also include input output devices, network access devices, buses, etc.

The Processor 40 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or a memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) and the like provided on the terminal 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used for storing the computer program and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the present application. For the specific working processes of the units and modules in the system, reference may be made to the corresponding processes in the foregoing method embodiments, which are not described herein again.

In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal and method may be implemented in other ways. For example, the above-described apparatus/terminal embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated module/unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The present application realizes all or part of the processes in the method of the above embodiments, and may also be implemented by a computer program product, when the computer program product runs on a terminal, the steps in the above method embodiments may be implemented when the terminal executes the computer program product.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A method for predicting postpartum hemorrhage, comprising:

2. The method of claim 1, further comprising: the acquired clinical data of the pregnant and lying-in women are preliminarily screened to exclude data with missing observations exceeding a preset threshold.

3. The method of claim 1, further comprising: and carrying out univariate regression analysis on the screened candidate independent variables to evaluate the effectiveness of the candidate prediction factors, and bringing the variables of which the correlation coefficients with postpartum hemorrhage are smaller than a preset value into a prediction model.

4. The method of claim 1, further comprising: the degree of the postpartum hemorrhage is divided into five grades according to the severity of the postpartum hemorrhage during cesarean delivery and vaginal delivery.

5. The method of claim 1, further comprising: according to a preset rule, the clinical data of the pregnant and lying-in women are divided into a training data set, an internal verification data set and an external test data set according to a preset proportion so as to verify the first model, the second model, the third model and the fourth model respectively.

6. The method of claim 5, further comprising: evaluating the first model, the second model and the third model through the area under the working characteristic curve, the accuracy, the confusion matrix and the calibration curve;

the fourth model is evaluated by accuracy, recall, comprehensive evaluation index and calibration curve.

7. The method of claim 1, wherein a predetermined processing recommendation is output based on the prediction result.

8. A postpartum hemorrhage prediction device, comprising:

the acquisition module is used for acquiring clinical data of pregnant and lying-in women according to a preset standard;

and constructing a fourth model by combining the prenatal variable, the intrapartum variable and the postpartum variable based on an artificial neural network and an extreme gradient propulsion algorithm so as to predict the postpartum hemorrhage severity degree when the parturition mode is caesarean section or vaginal delivery.

9. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.