Method for constructing antenatal image data of malformation of umbilical-portal-body vein system

Abstract

The invention discloses a construction method for antenatal image data of malformation of an umbilical-portal-body vein system, and the method comprises the following steps: obtaining a screening report in historical data, and recognizing and determining the type of a screening result through a natural language processing technology. The risk hierarchical management mode and the corresponding screening index value grading range are established, an individualized risk hierarchical management strategy is clinically formulated for the pregnant fetus suffering from the umbilical-portal-body vein system malformation, important guidance information is provided, an important scientific basis is provided for making an optimal decision for a child patient family, and the risk hierarchical management strategy is provided for the pregnant fetus suffering from the umbilical-portal-body vein system malformation. The heart malformation degree of a child patient is accurately and comprehensively diagnosed as soon as possible before antenatal, the severity of each child patient is refined, fetal umbilical-portal-body vein system malformation is found, diagnosed, prepared and treated early, the birth rate of the child patient with the malformation is reduced, prognosis is improved, and the birth population quality is improved. The method has important social value and economic value.

Description

Technical Field

[0001] The present invention relates to the technical field of gynecological and obstetric prenatal screening, and in particular to a method for constructing prenatal imaging data of umbilical-portal-system venous system malformations. Background Art

[0002] Umbilical-portal-systemic veins abnormalities (UPSVA) are a type of malformation in which the fetal umbilical vein, portal vein system and inferior vena cava junction (intrahepatic and extrahepatic) are abnormally developed. In addition to various variations, common malformations include: umbilical-systemic venous shunts, portal vein branch dysplasia, portal vein stenosis or cystic dilatation, portal-systemic venous shunts (extrahepatic and intrahepatic types), hepatic artery-portal vein fistulas, hepatic artery-hepatic vein fistulas, portal vein cavernous changes, ductus venosus anomalous connections, etc. These malformations seriously affect the survival and quality of life of children, bringing huge potential life loss and socioeconomic burdens.

[0003] However, there are only sporadic case reports of such malformations in the fetal period, and many cases of misdiagnosis are missed during prenatal examinations. This is a difficult and complex issue in prenatal examinations for the following reasons: 1) The source of the embryo is complex, and variations and malformations are difficult to distinguish; 2) The fetal umbilical-portal-systemic venous system has dense blood vessels, many variations, thin diameters, and low flow rates, making it difficult for ordinary ultrasound instruments to display them clearly; 3) Blood flow in the fetal umbilical-portal-systemic venous system is redistributed during the perinatal period, and there is a large difference in antenatal and postnatal hemodynamics; 4) Prenatal doctors lack knowledge and experience with such malformations. Summary of the invention

[0004] The object of the present invention is to provide a method for constructing prenatal imaging data of umbilical-portal-body venous system malformations to solve at least one of the above-mentioned problems of the prior art.

[0005] A method for constructing prenatal imaging data of umbilical-portal-body venous system malformation comprises the following steps:

[0006] Obtain screening reports from historical data and use natural language processing technology to identify and determine the type of screening results;

[0007] Among them, the types of screening results include: normal type, abnormal type;

[0008] Based on the type of screening results, conduct prenatal assessment and develop prenatal coping strategies;

[0009] Based on normal genetic test results, combined with the screening reports in historical data and the corresponding production assessment recommendations, we will analyze and determine the key screening indicators corresponding to the risk stratification level in the risk stratification management model;

[0010] Among them, the risk stratification management model includes level one risk, level two risk, level three risk, level four risk, and level five risk;

[0011] Based on the key screening indicators of each risk stratification level, the corresponding screening indicator values ​​are analyzed and the grading range of the screening indicator values ​​is output;

[0012] Based on a combined analysis of key screening indicators and the grading range of screening indicator values, the risk level of pregnant fetuses with umbilical-portal-systemic venous system malformations is assessed and prenatal guidance is provided.

[0013] Beneficial effects of the present invention:

[0014] The present invention establishes a risk stratification management model and a corresponding grading range of screening index values ​​to clinically formulate an individualized risk stratification management strategy for pregnant fetuses with umbilical-portal-system venous system malformations, and provides important guidance information, providing an important scientific basis for the families of children with the disease to make the best decision, and accurately and comprehensively diagnoses the degree of heart malformations in children as early as possible before birth, refines the severity of each child, and achieves early detection, early diagnosis, early preparation, and early treatment of fetal umbilical-portal-system venous system malformations, thereby reducing the birth rate of children with such malformations, improving prognosis, and improving the quality of the newborn population, which has important social and economic value. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 It is a flow chart of a method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to the present invention;

[0017] Figure 2 It is a schematic diagram of the structure of a device for constructing prenatal imaging data of umbilical-portal-body venous system malformations according to the present invention.

[0018] In the figure: 3, computer device; 301, processor; 302, memory; 303, computer program; DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0020] Embodiment 1

[0021] Figure 1 A flowchart of a method for constructing prenatal imaging data of an umbilical-portal-body venous system malformation provided in the first embodiment of the present invention. The embodiment of the present invention can be applied to the case of prenatal screening of fetal umbilical-portal-body venous system malformations. The method for constructing prenatal imaging data of an umbilical-portal-body venous system malformation can be executed by a system for constructing prenatal imaging data of an umbilical-portal-body venous system malformation. The system for constructing prenatal imaging data of an umbilical-portal-body venous system malformation can be implemented by software and / or hardware. The system for constructing prenatal imaging data of an umbilical-portal-body venous system malformation can be configured in a device for constructing prenatal imaging data of an umbilical-portal-body venous system malformation. Optionally, a device for constructing prenatal imaging data of an umbilical-portal-body venous system malformation can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0022] Our hospital has accumulated ultrasound medical technology and ultrasound doctors' experience, and has a clear understanding of this type of malformation. Based on the long-term summary of literature and domestic and foreign case reports, we have explored a prenatal screening model for this type of malformation. This invention is mainly based on the prenatal screening model for this type of malformation.

[0023] The prenatal screening mode mainly involves first performing routine prenatal examinations in accordance with the prenatal screening guidelines of the International Society of Ultrasound in Obstetrics & Gynecology (ISUOG), and then screening the fetal umbilical-portal-systemic venous system according to the "three-plane" continuous scanning method, storing and backing up the original images, and measuring parameters including: number of fetuses, biparietal diameter, middle cerebral artery flow velocity and resistance index, number and velocity of umbilical arteries, femoral length, umbilical-portal-systemic venous system vascular diameter, flow velocity and spectral morphology (superior mesenteric vein, splenic vein, portal vein trunk, left sagittal branch, left external inferior branch, left external superior branch, left internal branch, right anterior branch, right posterior branch and umbilical vein);

[0024] like Figure 1As shown, a method for constructing prenatal imaging data of umbilical-portal-body venous system malformation provided by an embodiment of the present invention specifically includes the following steps:

[0025] Step 1: Obtain screening reports from historical data and use natural language processing technology to identify and determine the type of screening results;

[0026] Among them, the types of screening results include: normal type, abnormal type;

[0027] It should be explained that the normal type means that the screening results show that the fetal heart structure is normal without any abnormalities or malformations, and the abnormal type means that the screening results show that the fetal heart structure is abnormal or malformed;

[0028] In some embodiments, a prenatal examination screening report is obtained from existing historical data, wherein the screening report is derived from an obstetric medicine database, and the screening report includes but is not limited to: screening index values ​​and screening results, and the screening report is stored in a text form;

[0029] Natural language processing (NLP) technology is used to identify and determine the type of screening results. The specific process is as follows:

[0030] Clean the acquired screening data and remove irrelevant information, including but not limited to: patient personal information and hospital information;

[0031] The screening data is segmented and the part of speech of each word is marked. Based on the segmentation and part of speech tagging, the named entity recognition technology is used to identify the key information in the text, such as "heart" and "deformity";

[0032] Establish a keyword library, including but not limited to "normal" and "abnormal", and preliminarily determine the type of screening results by matching keywords in the screening data;

[0033] For screening data containing complex descriptions, semantic understanding technology is used to deeply analyze the text content and accurately determine the type of screening results. For example, if the report contains "no abnormality in the heart structure", it can be judged as a "normal" type; if it contains "XX malformation in the heart", it can be judged as an "abnormal" type;

[0034] According to the results of information extraction, the screening results are divided into normal type and abnormal type;

[0035] Select a portion of the screening data as a labeled dataset, manually label the screening result types, and use them to train the NLP model. Use the labeled dataset to train the NLP model so that it can automatically identify key information in the doctor's report and determine the type of screening results.

[0036] Use the validation data set to evaluate the performance of the model, such as accuracy, recall, and other indicators, and tune the model based on the evaluation results to improve its performance;

[0037] Apply the trained NLP model to the screening data to automatically extract key information and determine the type of screening results;

[0038] Step 2: Conduct prenatal assessment and develop prenatal coping strategies based on the type of screening results;

[0039] In some embodiments, based on the fetus with a normal screening result, routine follow-up observation is performed, especially follow-up of the ductus venosus. If the ductus venosus is patent, the factors causing the patent ductus venosus are analyzed;

[0040] In this embodiment, the analysis of the factors related to the closure of the intravenous catheter was completed using the statistical software SPSS19.0, and Pearson correlation analysis was applied, with the test level set at α=0.05;

[0041] Among them, the Pearson correlation coefficient is between -1 and 1, and is used to quantify the degree of linear correlation between two variables. The closer the absolute value of the Pearson correlation coefficient is to 1, the stronger the linear relationship between the two variables is, and the closer the Pearson correlation coefficient is to 0, the weaker the linear relationship between the two variables is. The test level (α) refers to the preset standard used to determine whether the statistical test results are significant. Specifically, α = 0.05 means that if the P value obtained by the statistical test is less than or equal to 0.05, the difference is statistically significant, and if the P value is greater than 0.05, the difference is not statistically significant.

[0042] Obtain corresponding genetic test results based on the fetus with abnormal screening results;

[0043] Among them, genetic test results include normal genetic test results and abnormal genetic test results;

[0044] If the genetic test results are abnormal, medical induction of labor is performed, and with the informed consent of the pregnant woman, histological specimens of the umbilical cord and portal vein local tissues of the fetus that was induced or stillborn are collected and stored in liquid nitrogen for later RNA extraction. After the gross specimens are fixed in formalin containers for 24 hours, pathological dissection is performed to establish a biological sample library;

[0045] The technical solution of this embodiment is: by using natural language processing technology to identify and determine the type of screening results (normal or abnormal) from historical screening reports, and then conduct prenatal assessment based on the screening results, and formulate corresponding response strategies, conduct routine follow-up for normal fetuses, especially observation of venous catheters, and for abnormal fetuses, further obtain genetic test results, and decide whether to perform medical induction based on the results, and collect relevant histological specimens to establish a biological sample library.

[0046] Embodiment 2

[0047] Based on the above embodiments, Figure 1 As shown, a method for constructing prenatal imaging data of umbilical-portal-body venous system malformation provided by an embodiment of the present invention specifically includes the following steps:

[0048] Step 3: Based on the normal results of genetic testing, combined with the screening reports in the historical data and the corresponding production assessment recommendations, analyze and determine the key screening indicators corresponding to the risk stratification level in the risk stratification management model;

[0049] Among them, the risk stratification management model includes level one risk, level two risk, level three risk, level four risk, and level five risk;

[0050] It should be noted that different production recommendations are set for different levels of risk stratification: Level 1 risk is set as normal variation, Level 2 risk is set as elective delivery, Level 3 risk is set as elective surgery, Level 4 risk is set as early surgery, and Level 5 risk is set as medical induction of labor or liver transplantation;

[0051] If a fetus with a grade 5 risk is medically induced, with the informed consent of the pregnant woman, histological specimens of the umbilical cord and portal vein local tissues of the induced or intrauterine fetus will be collected and stored in liquid nitrogen for later RNA extraction. After the gross specimens are fixed in a formalin container for 24 hours, pathological dissection will be performed to establish a biological sample library;

[0052] In some embodiments, a screening report corresponding to a fetus with normal genetic test results is obtained, and a production assessment recommendation corresponding to the fetus is obtained;

[0053] Among them, production assessment recommendations correspond to different levels in the risk stratification management model;

[0054] For each risk stratification level, obtain the number of screening reports corresponding to each risk stratification level;

[0055] Extract abnormal screening indicators in each screening report and obtain the type of abnormal screening indicators;

[0056] Count the number of each abnormal screening indicator, and perform ratio processing on the number of abnormal screening indicators and the number of screening reports of the corresponding risk stratification level to obtain the ratio of a single abnormal screening indicator;

[0057] Set a threshold for the proportion of a single abnormal screening indicator, sort the values ​​of the proportion of a single abnormal screening indicator from large to small, retain the abnormal screening indicators that are greater than the threshold for the proportion of a single abnormal screening indicator, integrate the single abnormal screening indicators corresponding to each risk stratification level, and obtain the key screening indicators corresponding to each risk stratification level;

[0058] Among them, the threshold of the proportion of a single abnormal screening indicator is set by technicians in this field based on experimental data and experience;

[0059] Step 4: Based on the key screening indicators of each risk stratification level, analyze the corresponding screening indicator values ​​and output the grading range of the screening indicator values;

[0060] In some embodiments, the grading range value of the key screening indicator is obtained based on the key screening indicator, and the specific process is as follows:

[0061] For each risk stratification level, obtain the corresponding screening report and the screening indicator values ​​of the key screening indicators, integrate the screening indicator values ​​corresponding to each key screening indicator, obtain a screening indicator value array, and count the number of each screening indicator value array;

[0062] For each screening index array, a corresponding interval step length is set, wherein the interval step length is summarized and set by a person skilled in the art based on experience and data characteristics of the screening index array;

[0063] Extract the maximum and minimum values ​​in the screening indicator array, and obtain N screening indicator value intervals according to the maximum and minimum values ​​and the interval step length;

[0064] Count the number of screening indicator values ​​falling within each screening indicator value interval, and perform ratio processing on the number of screening indicator values ​​in each screening indicator value interval and the number of corresponding screening indicator value arrays to obtain the quantity weight SQ of each screening indicator value interval;

[0065] Calculate the standard deviation of the screening index value within each screening index value interval, standardize the standard deviation and calculate the original weight of the standard deviation of each screening index value interval. The specific formula is: Among them, BQ represents the original weight of the i-th screening index value interval, BZ max , BZ min It represents the maximum and minimum standard deviation of the screening index values ​​within the range of all screening index values, BZ i It represents the standard deviation of the i-th screening index value interval;

[0066] It should be noted that when the standard deviation is standardized, the screening index value interval corresponding to the maximum value of the standard deviation does not need to be calculated, and the screening index value interval is removed;

[0067] The original weights of all the standard deviations of the screening index value intervals are summed to obtain the total original weight value, and the original weight of each screening index value interval standard deviation is respectively ratioed to the total original weight value to obtain the final weight ZQ of each screening index value interval standard deviation;

[0068] For each screening index value interval, the quantity weight SQ and the final weight ZQ of the standard deviation are substituted into the formula SQ = 0.5*(SQ + ZQ) to calculate the grading weight SQ of the screening index value interval;

[0069] Set a grading weight threshold, sort the grading weights of each screening index value interval in descending order, retain the screening index value intervals corresponding to the grading weights greater than the grading weight threshold, and mark the ranking of the retained grading weights as a grading weight ranking table;

[0070] Among them, the classification weight threshold is summarized and set by those skilled in the art based on experimental data and experience;

[0071] Extract the screening index value interval corresponding to the first grading weight in the grading weight ranking table, mark it as the priority screening index grading range of the corresponding risk stratification level, extract the screening index value interval corresponding to the remaining grading weights in the grading weight ranking table, mark it as the auxiliary screening index grading range;

[0072] It should be noted that the ranking of the considerations for the grading range of auxiliary screening indicators is consistent with the grading weight ranking table;

[0073] The technical solution of this embodiment is: by combining the results of genetic testing, historical screening reports and production assessment recommendations, key screening indicators for different risk stratification levels are determined. Furthermore, based on these key screening indicators and their screening indicator values, through statistical analysis and weight calculation, a grading range of screening indicator values ​​is output, including a grading range of priority screening indicators and a grading range of auxiliary screening indicators. By determining the key screening indicators for different risk stratification levels, screening is made more targeted and accurate, which helps to detect and diagnose umbilical-portal-body venous system malformations at an early stage. According to the grading range of screening indicator values, doctors can formulate prenatal assessments and production recommendations more scientifically, and provide more personalized medical services for pregnant women and fetuses.

[0074] Embodiment 3

[0075] Based on the above embodiments, Figure 1As shown, a method for constructing prenatal imaging data of umbilical-portal-body venous system malformation provided by an embodiment of the present invention specifically includes the following steps:

[0076] Step 5: Based on the combined analysis of key screening indicators and the grading range of screening indicator values, the risk level of the fetus with umbilical-portal-system venous system malformation is assessed and prenatal guidance is provided;

[0077] In some embodiments, a screening report of the current parturient is obtained, abnormal screening indicators in the screening report are extracted, the abnormal screening indicators are compared with the key screening indicators corresponding to each risk stratification level, the overlapping screening indicators corresponding to each risk stratification level are extracted, and the number of overlapping screening indicators is counted;

[0078] For each risk stratification level, the number of overlapping screening indicators corresponding to each risk stratification level is ratioed with the number of key screening indicators of the corresponding stratification level to obtain the percentage of overlapping screening indicators;

[0079] Compare the overlapping screening index values ​​with the priority screening index grading range and auxiliary screening index grading range corresponding to the screening index in each risk stratification level;

[0080] Count the number of screening indicators that fall within the priority screening indicator classification range, and calculate the ratio with the number of overlapping screening indicators to obtain the ratio of priority range screening indicators;

[0081] The number of screening indicators that fall into the auxiliary screening indicator classification range is calculated by ratio with the number of overlapping screening indicators to obtain the ratio of auxiliary range screening indicators;

[0082] The weighted sum of the proportion of overlapping screening indicators, the proportion of priority range screening indicators and the proportion of auxiliary range screening indicators is calculated to obtain the graded assessment value, among which the weight of the proportion of overlapping screening indicators is 0.364, the weight of the proportion of priority range screening indicators is 0.334, and the weight of the proportion of auxiliary range screening indicators is 0.302;

[0083] The grading assessment values ​​of each risk stratification level are compared, and the risk stratification level corresponding to the maximum grading assessment value is extracted as the risk stratification level of the current parturient;

[0084] It should be noted that if there is a tie between the maximum values ​​of the graded assessment values, doctors in this field will determine the risk stratification level based on their experience, the physical condition of the mother, the growth of the fetus, etc.

[0085] The technical solution of this embodiment is: by combining the key screening indicators with the grading range of the screening indicator values, the risk level of the pregnant fetus with umbilical-portal-system venous system malformations is assessed, and prenatal guidance is provided accordingly. Specifically, the abnormal screening indicators in the screening report of the current parturient are first extracted, and compared with the key screening indicators of each risk stratification level, and the proportion of overlapping screening indicators is calculated. Then, the overlapping screening indicator values ​​are compared with the priority screening indicator grading range and the auxiliary screening indicator grading range, and the priority range screening indicator proportion and the auxiliary range screening indicator proportion are calculated. Finally, the graded evaluation value is obtained by weighted summation calculation, and the risk stratification level of the current parturient is determined to provide a basis for prenatal guidance. Therefore, by accurately assessing the risk level, medical resources can be reasonably allocated and the utilization efficiency of medical resources can be improved.

[0086] Embodiment 4

[0087] Based on the above embodiments, an embodiment of the present invention provides a system for constructing prenatal imaging data of umbilical-portal-body venous system malformations, specifically comprising:

[0088] Screening result classification module: obtains screening reports from historical data and uses natural language processing technology to identify and determine the type of screening results;

[0089] Among them, the types of screening results include: normal type, abnormal type;

[0090] Prenatal assessment module: Based on the type of screening results, conduct prenatal assessment and develop prenatal coping strategies;

[0091] Grading index acquisition module: Based on the normal results of genetic testing, combined with the screening reports in the historical data and the corresponding production assessment suggestions, the key screening indicators corresponding to the risk stratification level in the risk stratification management model are determined;

[0092] Among them, the risk stratification management model includes level one risk, level two risk, level three risk, level four risk, and level five risk;

[0093] Grading range acquisition module: Based on the key screening indicators of each risk stratification level, combined with the corresponding screening indicator values, analysis is performed to output the grading range of the screening indicator values;

[0094] Grade assessment module: Based on the combined analysis of key screening indicators and the grading range of screening indicator values, the risk level of pregnant fetuses with umbilical-portal-systemic venous system malformations is assessed and prenatal guidance is provided.

[0095] Embodiment 5

[0096] like Figure 2As shown, an embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, a method for constructing prenatal imaging data of umbilical-portal-body venous system malformation as described in any one of the above methods is implemented.

[0097] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that

[0098] Figure 2 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0099] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0100] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0101] Embodiment 6

[0102] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for constructing prenatal imaging data of an umbilical-portal-body venous system malformation as described in any one of the above methods is implemented.

[0103] In this embodiment, if the integrated unit is implemented in the form of 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 present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0104] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0105] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0106] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0109] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for constructing prenatal imaging data of umbilical-portal-body venous system malformation, characterized in that: The following steps are involved: Obtain screening reports from historical data and use natural language processing technology to identify and determine the type of screening results; Among them, the types of screening results include: normal type, abnormal type; Based on the type of screening results, conduct prenatal assessment and develop prenatal coping strategies; Based on normal genetic test results, combined with the screening reports in historical data and the corresponding production assessment recommendations, we will analyze and determine the key screening indicators corresponding to the risk stratification level in the risk stratification management model; Among them, the risk stratification management model includes level one risk, level two risk, level three risk, level four risk, and level five risk; Based on the key screening indicators of each risk stratification level, the corresponding screening indicator values ​​are analyzed and the grading range of the screening indicator values ​​is output; Based on a combined analysis of key screening indicators and the grading range of screening indicator values, the risk level of pregnant fetuses with umbilical-portal-systemic venous system malformations is assessed and prenatal guidance is provided.

2. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 1, characterized in that: The process of determining the type of screening result is: Obtaining a prenatal examination screening report from existing historical data, wherein the screening report is derived from an obstetric medicine database, and the screening report includes: screening index values ​​and screening results, and the screening report is stored in the form of text; Natural language processing (NLP) technology is used to identify and determine the type of screening results. The specific process is as follows: Clean the obtained screening data and remove irrelevant information; The screening data is segmented and the part of speech of each word is marked. Based on the segmentation and part of speech tagging, the named entity recognition technology is used to identify the key information in the text; Establish a keyword library and preliminarily determine the type of screening results by matching keywords in the screening data; For screening data containing complex descriptions, semantic understanding technology is used to deeply analyze the text content and accurately determine the type of screening results; According to the results of information extraction, the screening results are divided into normal type and abnormal type; Select a portion of the screening data as a labeled data set, manually label the screening result types for training the NLP model, and use the labeled data set to train the NLP model; Evaluate the performance of the model using the validation dataset; Apply the trained NLP model to the screening data to automatically extract key information and determine the type of screening results.

3. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 1, characterized in that: The process of conducting prenatal assessment and formulating prenatal response strategies based on the type of screening results is as follows: For fetuses with normal screening results, follow-up of the ductus venosus is performed. If patent ductus venosus is found, the factors causing patent ductus venosus are analyzed. Obtain corresponding genetic test results based on the fetus with abnormal screening results; Among them, genetic test results include normal genetic test results and abnormal genetic test results; Medical induction of labor is performed based on abnormal genetic test results.

4. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 1, characterized in that: The process of determining the key screening indicators corresponding to the risk stratification level in the risk stratification management model is as follows: Obtain screening reports for fetuses with normal genetic test results, and obtain production assessment recommendations for the fetuses, where the production assessment recommendations correspond to different levels in the risk stratification management model; For each risk stratification level, obtain the number of screening reports corresponding to each risk stratification level; Extract abnormal screening indicators in each screening report and obtain the type of abnormal screening indicators; Count the number of each abnormal screening indicator, and perform ratio processing on the number of abnormal screening indicators and the number of screening reports of the corresponding risk stratification level to obtain the ratio of a single abnormal screening indicator; Set a threshold for the proportion of single abnormal screening indicators, sort the values ​​of the proportion of single abnormal screening indicators from large to small, retain the abnormal screening indicators that are greater than the threshold for the proportion of single abnormal screening indicators, integrate the single abnormal screening indicators corresponding to each risk stratification level, and obtain the key screening indicators corresponding to each risk stratification level.

5. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 1, characterized in that: The process of outputting the classification range of screening index values ​​is as follows: Analyze the screening indicator values ​​corresponding to the key screening indicators to obtain a screening indicator value array, and analyze the screening indicator array to obtain a screening indicator value interval; The screening index value interval is analyzed to obtain the final weight of quantity weight SQ and standard deviation ZQ; For each screening index value interval, the quantity weight SQ and the final weight ZQ of the standard deviation are substituted into the formula SQ = 0.5*(SQ + ZQ) to calculate the grading weight SQ of the screening index value interval; Set a grading weight threshold, sort the grading weights of each screening index value interval in descending order, retain the screening index value intervals corresponding to the grading weights greater than the grading weight threshold, and mark the ranking of the retained grading weights as a grading weight ranking table; The screening index value interval corresponding to the first grading weight in the grading weight sorting table is extracted and marked as the priority screening index grading range of the corresponding risk stratification level; the screening index value intervals corresponding to the remaining grading weights in the grading weight sorting table are extracted and marked as the auxiliary screening index grading range.

6. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 5, characterized in that: The process of obtaining the quantity weight is as follows: For each risk stratification level, obtain the corresponding screening report and the screening indicator values ​​of the key screening indicators, integrate the screening indicator values ​​corresponding to each key screening indicator, obtain a screening indicator value array, and count the number of each screening indicator value array; For each screening indicator array, set the corresponding interval step size; Extract the maximum and minimum values ​​in the screening indicator array, and obtain N screening indicator value intervals according to the maximum and minimum values ​​and the interval step length; The number of screening indicator values ​​falling within each screening indicator value interval is counted, and the number of screening indicator values ​​in each screening indicator value interval is respectively ratioed with the number of corresponding screening indicator value arrays to obtain the quantity weight SQ of each screening indicator value interval.

7. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 5, characterized in that: The process of obtaining the final weight of the standard deviation is: Calculate the standard deviation of the screening index value within each screening index value interval, standardize the standard deviation and calculate the original weight of the standard deviation of each screening index value interval. The specific formula is: Among them, BQ represents the original weight of the i-th screening index value interval, BZ max , BZ min It represents the maximum and minimum standard deviation of the screening index values ​​within the range of all screening index values, BZ i It represents the standard deviation of the i-th screening index value interval; The original weights of all the standard deviations of the screening index value intervals are summed to obtain the total original weight value, and the original weight of each screening index value interval standard deviation is ratioed with the total original weight value to obtain the final weight ZQ of each screening index value interval standard deviation.

8. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 1, characterized in that: The process for assessing the risk level of a fetus with an umbilical-portal-systemic venous malformation during pregnancy is as follows: Obtain the percentage values ​​of overlapping screening indicators, the percentage values ​​of priority range screening indicators and the percentage values ​​of auxiliary range screening indicators; The weighted sum of the overlapping screening index proportions, the priority range screening index proportions and the auxiliary range screening index proportions is calculated to obtain the graded assessment value; The grading assessment values ​​of each risk stratification level are compared, and the risk stratification level corresponding to the maximum grading assessment value is extracted as the risk stratification level of the current parturient.

9. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 8, characterized in that: The process of obtaining the overlap screening index ratio is as follows: Obtain the current maternal screening report, extract abnormal screening indicators in the screening report, compare the abnormal screening indicators with the key screening indicators corresponding to each risk stratification level, extract the overlapping screening indicators corresponding to each risk stratification level, and count the number of overlapping screening indicators; For each risk stratification level, the ratio of the number of overlapping screening indicators corresponding to each risk stratification level to the number of key screening indicators of the corresponding stratification level was processed to obtain the proportion of overlapping screening indicators.

10. The method for constructing prenatal imaging data of umbilical-portal-body venous system malformation according to claim 9, characterized in that: The process of obtaining the priority range screening index ratio and the auxiliary range screening index ratio is as follows: Compare the overlapping screening index values ​​with the priority screening index grading range and auxiliary screening index grading range corresponding to the screening index in each risk stratification level; Count the number of screening indicators that fall within the priority screening indicator classification range, and calculate the ratio with the number of overlapping screening indicators to obtain the ratio of priority range screening indicators; The number of screening indicators that fall into the auxiliary screening indicator classification range is calculated by ratio with the number of overlapping screening indicators to obtain the proportion of auxiliary range screening indicators.

Images