Obstetrics and Gynecology Pregnant Woman Assessment and Analysis Method and System Based on Community Antenatal Care Data Stream

Abstract

The present invention provides an obstetrics and gynecology pregnant woman assessment and analysis method and system based on community antenatal examination data streams, which relates to the technical field of medical health analysis. The obstetrics and gynecology pregnant woman assessment and analysis method based on community antenatal examination data streams includes the following steps: constructing a community antenatal examination data stream storage platform to obtain and store antenatal examination data in real time; based on the obtained antenatal examination data, constructing a coupling matrix through antenatal examination cycle decomposition and risk factor decomposition; based on the constructed coupling matrix, establishing an antenatal examination risk tree risk model by using the antenatal examination risk tree analysis method, and performing risk assessment on the antenatal examination results through the antenatal examination risk tree risk model; and displaying the risk assessment results through data visualization technology. The present invention performs risk assessment on the antenatal examination results through the antenatal examination risk tree risk model, and can provide more accurate and personalized assessment results.

Description

Technical Field

[0001] The present invention relates to the technical field of medical and health analysis. Specifically, it particularly relates to a method and system for evaluating and analyzing pregnant women in obstetrics and gynecology based on community antenatal examination data streams. Background Art

[0002] Antenatal examination is an important means of obtaining the health status of pregnant women and their fetuses. Reasonable antenatal examinations can not only help pregnant women understand their own and their fetuses' health status, but also adjust the pregnant women's living habits, diet, and exercise plans in a timely manner based on the antenatal examination information. Usually, when a pregnant woman learns of her pregnancy, she will register at a community hospital and receive regular antenatal examinations. These regular examinations help to identify and address potential health problems at an early stage. In a community medical environment, such regular antenatal examination activities generate a large amount of data, including the basic health indicators of pregnant women, fetal development, genetic disease screening results, etc., forming a multi-dimensional community antenatal examination data stream. By deeply analyzing and evaluating this data, medical experts can conduct high-risk pregnancy assessments on pregnant women, predict possible health problems, and provide personalized medical advice and intervention measures accordingly.

[0003] Currently, in traditional antenatal examination data management, the phenomena of data fragmentation and information silos are widespread. It is difficult to integrate data between different medical institutions, which limits the comprehensiveness and accuracy of medical decision-making. The incoherence of data results in medical providers being unable to obtain the complete health records of pregnant women, affecting the efficiency and effectiveness of medical services. Moreover, when processing antenatal examination data, the comprehensive analysis of periodicity and risk factors is often ignored, which limits the medical service providers' comprehensive understanding of the dynamic changes in the health status of pregnant women. In addition, there is a lack of refined data analysis tools, making it difficult to extract information that is instructive for clinical practice from a large amount of data.

[0004] Regarding the problems in the related art, no effective solutions have been proposed yet. Summary of the Invention

[0005] In view of this, the present invention provides a method and system for evaluating and analyzing pregnant women in obstetrics and gynecology based on community antenatal examination data streams to solve the above-mentioned problems.

[0006] To solve the above problems, the specific technical solutions adopted by the present invention are as follows:

[0007] According to one aspect of the present invention, there is provided a method for evaluating and analyzing pregnant women in obstetrics and gynecology based on community antenatal examination data streams. The method for evaluating and analyzing pregnant women in obstetrics and gynecology based on community antenatal examination data streams includes the following steps:

[0008] S1. Construct a storage platform for community antenatal examination data streams, and obtain and store antenatal examination data in real time;

[0009] S2. Based on the obtained prenatal examination data, construct a coupling matrix through the decomposition of the prenatal examination cycle and the decomposition of risk factors;

[0010] S3. Based on the constructed coupling matrix, establish a prenatal examination risk tree risk model using the prenatal examination risk tree analysis method, and conduct a risk assessment of the prenatal examination results through the prenatal examination risk tree risk model;

[0011] S4. Display the risk assessment results through data visualization technology;

[0012] Preferably, based on the obtained prenatal examination data, constructing a coupling matrix through the decomposition of the prenatal examination cycle and the decomposition of risk factors includes the following steps:

[0013] S21. Preprocess the obtained prenatal examination data, and the preprocessing includes data cleaning and standardization processing;

[0014] S22. Construct a prenatal examination data classification model, and classify the preprocessed prenatal examination data through the prenatal examination data classification model;

[0015] S23. Conduct time series analysis on each type of data in the prenatal examination data, and according to the analysis results, decompose the prenatal examination data through a preset cycle standard;

[0016] S24. Construct a cycle decomposition structure according to the cycle decomposition result and classification result of the prenatal examination data;

[0017] S25. Identify the risk factors of each type of data according to the inherent attributes of each type of data in the prenatal examination data, and construct a risk factor decomposition structure through hierarchical decomposition and analysis;

[0018] S26. Establish a coupling matrix according to the cycle decomposition structure and the risk factor decomposition structure.

[0019] Preferably, constructing a prenatal examination data classification model and classifying the preprocessed prenatal examination data through the prenatal examination data classification model includes the following steps:

[0020] S221. Collect historical prenatal examination sample data, and establish a training data set through feature selection processing;

[0021] S222. According to the obtained training data set, construct and train a prenatal examination data classification model through the support vector machine algorithm;

[0022] S223. Use the preprocessed prenatal examination data as input and input it into the trained prenatal examination data classification model to realize the classification of the preprocessed prenatal examination data.

[0023] Preferably, collecting historical prenatal examination sample data and establishing a training data set through feature selection processing includes the following steps:

[0024] S2211. Perform dimensionality reduction on the historical antenatal examination sample data through dimensionality reduction technology;

[0025] S2212. Conduct correlation feature selection on the dimensionality-reduced historical antenatal examination sample data to establish a feature data set;

[0026] S2213. Use the spectral clustering algorithm to optimize the feature data set to obtain a new feature data set, and use the new feature data set as the training data set.

[0027] Preferably, using the spectral clustering algorithm to process the feature data set to obtain a new feature data set includes the following steps:

[0028] S22131. For each feature data point in the feature data set, calculate the similarity between each pair of feature data points;

[0029] S22132. Construct an undirected graph with each feature data point in the feature data set as a node, and use the similarity between feature data points as the weight of the edge between nodes in the undirected graph;

[0030] S22133. Construct a weighted adjacency matrix and a degree matrix respectively according to the similarity between nodes and the sum of the weights of all edges connected to each node;

[0031] S22134. Calculate the normalized Laplacian matrix according to the constructed weighted adjacency matrix and degree matrix;

[0032] S22135. Perform eigenvalue decomposition on the calculated normalized Laplacian matrix, and extract the eigenvectors corresponding to several smallest non-zero eigenvalues;

[0033] S22136. Divide the data points into several clusters according to the eigenvectors, and select the cluster center from each cluster as the representative point to form a new feature data set.

[0034] Preferably, the formula for calculating the normalized Laplacian matrix according to the constructed weighted adjacency matrix and degree matrix is:

[0035] R = F -1 / 2 W F -1 / 2 ;

[0036] In the formula, R represents the normalized Laplacian matrix;

[0037] F represents the degree matrix;

[0038] F -1 / 2 represents the diagonal matrix formed by taking the reciprocal square root of each diagonal element of the degree matrix F;

[0039] W Represents a weighted connection matrix.

[0040] Preferably, time series analysis is performed on each type of prenatal examination data, and according to the analysis results, cycle decomposition of the prenatal examination data is carried out through a preset cycle standard, including the following steps:

[0041] S231. Obtain the real-time acquisition time of the prenatal examination data, arrange each type of data in the prenatal examination data in the order of the real-time acquisition time to form a time series;

[0042] S232. Divide each type of data in the prenatal examination data according to the preset cycle standard;

[0043] S233. Group and organize the prenatal examination data after cycle division according to the cycle.

[0044] Preferably, based on the constructed coupling matrix, a prenatal examination risk tree risk model is established using the prenatal examination risk tree analysis method, and risk assessment of the prenatal examination results is carried out through the prenatal examination risk tree risk model, including the following steps:

[0045] S31. Determine the top event of the prenatal examination risk tree, perform prenatal examination risk tree analysis on the top event using the coupling matrix, identify the basic events, and construct a prenatal examination risk tree risk model;

[0046] S32. According to the prenatal examination risk tree risk model, calculate the probability of the top event occurring through the probability calculation method;

[0047] S33. According to the probability of the top event occurring, calculate the sensitivity coefficient of each basic event through sensitivity analysis;

[0048] S34. According to the sensitivity analysis results, conduct risk assessment on the prenatal examination results.

[0049] Preferably, calculating the probability of the top event occurring through the probability calculation method according to the prenatal examination risk tree risk model includes the following steps:

[0050] S321. Assign basic probability values to each basic event in the prenatal examination risk tree risk model;

[0051] S322. Determine the logical relationship between events according to the logic gates in the prenatal examination risk tree risk model;

[0052] S323. Starting from the basic events at the bottom of the prenatal examination risk tree risk model, calculate step by step upward according to the logical relationship to obtain the probability of the top event occurring.

[0053] Preferably, the calculation formula for calculating the sensitivity coefficient of each basic event through sensitivity analysis according to the probability of the top event occurring is:

[0054] ;

[0055] Wherein, H i represents the sensitivity coefficient of the basic event i ;

[0056] represents the partial derivative value of the probability value of the top event T occurring;

[0057] D ( T ) represents the probability value of the top event T occurring;

[0058] represents the partial derivative value of the basic probability value of the basic event i ;

[0059] k i represents the basic probability value of the basic event i ;

[0060] According to another aspect of the present invention, there is provided an obstetrics and gynecology pregnant woman assessment and analysis system based on community antenatal examination data stream. The obstetrics and gynecology pregnant woman assessment and analysis system based on community antenatal examination data stream includes: a data storage module, a matrix construction module, a risk assessment module, and a result display module. Among them, the data storage module, the matrix construction module, the risk assessment module, and the result display module are connected in sequence;

[0061] The data storage module is used to construct a community antenatal examination data stream storage platform and obtain and store antenatal examination data in real time;

[0062] The matrix construction module is used to construct a coupling matrix based on the obtained antenatal examination data through antenatal examination cycle decomposition and risk factor decomposition;

[0063] The risk assessment module is used to establish a risk model of the antenatal examination risk tree based on the constructed coupling matrix by using the antenatal examination risk tree analysis method, and perform risk assessment on the antenatal examination results through the risk model of the antenatal examination risk tree;

[0064] The result display module is used to display the risk assessment results through data visualization technology.

[0065] The beneficial effects of the present invention are:

[0066] 1. By constructing a community antenatal care data stream storage platform, the present invention can obtain and store antenatal care data in real time, ensuring the timeliness and accuracy of the data. Based on the obtained antenatal care data, a coupling matrix is constructed through antenatal care cycle decomposition and risk factor decomposition, which helps to systematically identify and analyze key information and risk factors in antenatal care data. The coupling matrix can clearly show the associations and interactions between different antenatal care cycles and risk factors, providing strong support for subsequent risk assessment. By using the antenatal care risk tree analysis method to establish an antenatal care risk tree risk model, various risks and abnormal situations that may exist during the antenatal care process can be intuitively displayed. By performing risk assessment on the antenatal care results through the antenatal care risk tree risk model, more accurate and personalized assessment results can be provided.

[0067] 2. By collecting historical antenatal care sample data and using feature selection processing and dimensionality reduction techniques, the present invention can construct an efficient and accurate antenatal care data classification model. By using the spectral clustering algorithm to optimize the feature data set, a more compact and representative feature set can be obtained, improving the efficiency and accuracy of the classification model. The calculation of the standardized Laplacian matrix and eigenvalue decomposition can ensure the reasonable clustering of data points, thereby extracting the most discriminative features. The constructed coupling matrix can clearly show the cycle decomposition structure and risk factor decomposition structure of antenatal care data, facilitating the rapid identification and understanding of key information.

[0068] 3. By using the antenatal care risk tree analysis method, the present invention can systematically evaluate the risks that pregnant women may face during the entire antenatal care process, helping doctors comprehensively understand the health status and potential problems of pregnant women, and thus formulating more accurate and effective treatment and management plans. The antenatal care risk tree risk model intuitively shows various risk factors and their relationships in a tree structure, enabling a clear view of which factors may have the greatest impact on the health of pregnant women and fetuses. By calculating the probability of the top event (i.e., adverse pregnancy outcome) using the probability calculation method, a quantitative risk assessment result is provided for doctors, enabling them to judge the severity of the risk based on specific values and thus making more scientific decisions, which helps to improve the health level of mothers and infants. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0070] Figure 1 is a flowchart of an obstetrics and gynecology pregnant woman assessment and analysis method based on community antenatal care data stream according to an embodiment of the present invention;

[0071] Figure 2 It is a principle block diagram of an obstetrics and gynecology pregnant woman assessment and analysis system based on community antenatal examination data stream according to an embodiment of the present invention.

[0072] In the figure:

[0073] 1. Data storage module; 2. Matrix construction module; 3. Risk assessment module; 4. Result display module. Specific implementation manners

[0074] In order to enable those skilled in the art of this technology to better understand the technical solutions in this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without making creative efforts shall fall within the protection scope of this application.

[0075] According to an embodiment of the present invention, an obstetrics and gynecology pregnant woman assessment and analysis method and system based on community antenatal examination data stream are provided.

[0076] Now, the present invention will be further described in conjunction with the accompanying drawings and specific implementation manners. As Figure 1 shown, according to an embodiment of an embodiment of the present invention, an obstetrics and gynecology pregnant woman assessment and analysis method based on community antenatal examination data stream is provided. The obstetrics and gynecology pregnant woman assessment and analysis method based on community antenatal examination data stream includes the following steps:

[0077] S1. Build a community antenatal examination data stream storage platform to obtain and store antenatal examination data in real time;

[0078] Specifically, the community antenatal examination data stream storage platform should be divided into a front-end display layer, a back-end service layer, and a data storage layer. The front-end display layer is responsible for the display and interaction of the user interface. The back-end service layer processes business logic and data processing. The data storage layer is responsible for storing user data and platform information. Antenatal examination data can be collected through various channels such as hospital systems, medical devices, and personal input of pregnant women.

[0079] The antenatal examination data includes basic personal information, medical history, physical examination data and test results at each stage of pregnancy, etc.

[0080] S2. Based on the obtained antenatal examination data, construct a coupling matrix through antenatal examination cycle decomposition and risk factor decomposition;

[0081] As a preferred implementation manner, constructing a coupling matrix based on the obtained antenatal examination data through antenatal examination cycle decomposition and risk factor decomposition includes the following steps:

[0082] S21. Preprocess the obtained prenatal examination data, where the preprocessing includes data cleaning and standardization.

[0083] It should be noted that data cleaning mainly addresses errors and inconsistencies in the data, including removing duplicate records, handling missing values, and correcting errors and outliers. Standardization is to adjust the data to a unified format and range for easy analysis and processing.

[0084] S22. Construct a classification model for prenatal examination data, and classify the preprocessed prenatal examination data through the classification model for prenatal examination data.

[0085] As a preferred implementation, constructing a classification model for prenatal examination data and classifying the preprocessed prenatal examination data through the classification model for prenatal examination data includes the following steps:

[0086] S221. Collect historical prenatal examination sample data, and establish a training data set through feature selection processing.

[0087] As a preferred implementation, collecting historical prenatal examination sample data and establishing a training data set through feature selection processing includes the following steps:

[0088] S2211. Perform dimensionality reduction processing on the historical prenatal examination sample data through dimensionality reduction techniques.

[0089] Specifically, dimensionality reduction techniques include principal component analysis (PCA), linear discriminant analysis, t-distributed stochastic neighbor embedding, and so on.

[0090] For example, use principal component analysis (PCA) as an example:

[0091] Standardize the data: Before applying PCA, it is usually necessary to standardize the data to eliminate the dimensionality differences between different features.

[0092] Calculate the covariance matrix: Calculate the covariance matrix or correlation coefficient matrix of the standardized data.

[0093] Calculate the eigenvalues and eigenvectors of the covariance matrix: These eigenvalues and eigenvectors describe the main directions of data variation.

[0094] Select the principal components: Select the first n principal components according to the magnitudes of the eigenvalues. These principal components will serve as the new feature space. Usually, the first n principal components with the cumulative eigenvalue ratio reaching a certain threshold (such as 90%) can be selected.

[0095] Transform the data: Transform the data from the original feature space to the new principal component space. Usually, perform matrix multiplication operations on the original data and the eigenvectors of the selected principal components.

[0096] S2212. Perform correlation feature selection on the dimension-reduced historical prenatal examination sample data to establish a feature dataset;

[0097] It should be noted that performing correlation feature selection on the dimension-reduced historical prenatal examination sample data aims to identify and retain the features most relevant to the target variable. The Pearson correlation coefficient method is used to calculate the correlation between the dimension-reduced features and the target variable. According to the results of the correlation analysis, a correlation threshold is set. For example, features with a correlation higher than a certain threshold with the target variable can be selected. The selected features and the target variable are combined into a feature dataset.

[0098] S2213. Use the spectral clustering algorithm to optimize the feature dataset to obtain a new feature dataset, and use the new feature dataset as the training dataset.

[0099] As a preferred implementation, using the spectral clustering algorithm to process the feature dataset to obtain a new feature dataset includes the following steps:

[0100] S22131. For each feature data point in the feature dataset, calculate the similarity between each pair of feature data points;

[0101] It should be noted that when calculating the similarity between each pair of feature data points in the feature dataset, the Euclidean distance is used for similarity measurement.

[0102] S22132. Use each feature data point in the feature dataset as a node to construct an undirected graph, and use the similarity between the feature data points as the weight of the edge between the nodes in the undirected graph;

[0103] Specifically, using each feature data point in the feature dataset as a node to construct an undirected graph and using the similarity between the feature data points as the weight of the edge between the nodes in the undirected graph includes the following steps:

[0104] Create an empty undirected graph whose node set is all the data points in the feature dataset;

[0105] The similarity between each pair of data points in the feature dataset is stored in a similarity matrix;

[0106] Traverse the similarity matrix. For each non-zero element in the matrix, add an edge from the node to the node in the undirected graph, and set the weight of this edge to the similarity value.

[0107] S22133. Construct a weighted connection matrix and a degree matrix respectively according to the similarity between the nodes and the sum of the weights of all the edges connected to each node;

[0108] It should be noted that the degree matrix is a diagonal matrix, where each diagonal element represents the degree of the data point, that is, the sum of the similarities between the data point and all other data points.

[0109] S22134. Calculate the normalized Laplacian matrix according to the constructed weighted connection matrix and degree matrix;

[0110] Specifically, the calculation formula for calculating the normalized Laplacian matrix according to the constructed weighted connection matrix and degree matrix is:

[0111] R = F -1 / 2 W F -1 / 2 ;

[0112] In the formula, R represents the normalized Laplacian matrix;

[0113] F represents the degree matrix;

[0114] F -1 / 2 represents the diagonal matrix formed by taking the square root of the reciprocal of each diagonal element of the degree matrix F;

[0115] W represents the weighted connection matrix.

[0116] S22135. Perform eigenvalue decomposition on the calculated normalized Laplacian matrix, and extract the eigenvectors corresponding to several of the smallest non-zero eigenvalues;

[0117] Specifically, eigenvalue decomposition is a mathematical process that decomposes a matrix into its eigenvalues and eigenvectors. When performing eigenvalue decomposition, a series of eigenvalues and corresponding eigenvectors will be obtained. Since the normalized Laplacian matrix is positive semi-definite, its eigenvalues are all non-negative. The specific steps for extracting the eigenvectors corresponding to several of the smallest non-zero eigenvalues are as follows:

[0118] Perform eigenvalue decomposition on the normalized Laplacian matrix to obtain a set of eigenvalues and corresponding eigenvectors;

[0119] Sort the eigenvalues in ascending order and correspondingly adjust the order of the eigenvectors;

[0120] Skip the zero eigenvalues (if any) because they do not contain any information about data clustering;

[0121] Select several of the smallest non-zero eigenvalues (usually the number selected is close to the expected number of clusters), and extract their corresponding eigenvectors.

[0122] For example, assume there is a dataset containing 100 data points, and a normalized Laplacian matrix has been constructed based on the similarity between these data points, and we hope to cluster these data points into 5 categories;

[0123] Use the eigenvalue decomposition algorithm to decompose the normalized Laplacian matrix L; two arrays will be returned: one is an array of eigenvalues sorted in ascending order, and the other is an array of eigenvectors corresponding to these eigenvalues. Assume the array of eigenvalues obtained after eigenvalue decomposition is: [0, 0.05, 0.1, 0.15, 0.2, 0.25, 0.3,...];

[0124] Skip the zero eigenvalue (if it exists) because the zero eigenvalue does not provide useful information about data clustering. Extract the eigenvectors corresponding to the 5 smallest non-zero eigenvalues from the eigenvalue array (in this example, from 0.05 to 0.25). These eigenvectors will form a new matrix V, where each row represents the representation of a data point in the new feature space;

[0125] Cluster the rows of matrix V. Since 5 eigenvectors are selected, the clustering algorithm will attempt to divide the data points into 5 categories.

[0126] S22136. Divide the data points into several clusters according to the eigenvectors, and select the cluster center as the representative point from each cluster to form a new feature dataset.

[0127] It should be noted that using the selected eigenvectors as new features, map the data points into this low-dimensional feature space. The coordinates of each data point in the new feature space are composed of its corresponding eigenvector values. Use clustering algorithms such as K-means in the new feature space to divide the data points into k clusters, and for each cluster, select its cluster center as the representative point. The cluster center is usually the mean of all data points in that cluster.

[0128] S222. According to the obtained training dataset, construct and train an antenatal care data classification model through the support vector machine algorithm;

[0129] Specifically, constructing and training an antenatal care data classification model through the support vector machine algorithm according to the obtained training dataset includes the following steps:

[0130] Use the support vector machine algorithm to construct a classification model and select an appropriate kernel function (such as linear, polynomial, radial basis function, etc.);

[0131] Adjust the hyperparameters of the model, such as the penalty coefficient C (controlling the penalty degree of misclassification) and the coefficient of the kernel function (such as the gamma parameter of the RBF kernel);

[0132] Use the training dataset to train the classification model, and evaluate the performance of the model by obtaining the test dataset, etc., to obtain the antenatal examination data classification model.

[0133] S223. Use the preprocessed antenatal examination data as input and input it into the trained antenatal examination data classification model to achieve the classification of the preprocessed antenatal examination data.

[0134] S23. Perform time series analysis on each type of data in the antenatal examination data, and according to the analysis results, decompose the antenatal examination data by a preset cycle standard;

[0135] As a preferred implementation, performing time series analysis on each type of data in the antenatal examination data and decomposing the antenatal examination data by a preset cycle standard includes the following steps:

[0136] S231. Obtain the real-time acquisition time of the antenatal examination data, arrange each type of data in the antenatal examination data in the order of the real-time acquisition time to form a time series;

[0137] It should be noted that the real-time acquisition time (usually the date or timestamp) of each piece of data is extracted from the antenatal examination dataset. According to these timestamps, each type of data (such as blood pressure, blood sugar, weight, etc.) in the antenatal examination data is sorted in chronological order. The sorted data forms a time series, which shows the changes in each type of antenatal examination data over time.

[0138] S232. Divide each type of data in the antenatal examination data according to the preset cycle standard;

[0139] It should be noted that each type of data in the antenatal examination data is divided according to the pregnancy cycle standard. The pregnancy cycle standard groups the data according to the pregnant woman's pregnancy stage (such as the first trimester, second trimester, third trimester) or the specific number of pregnancy weeks. The number of pregnancy weeks (such as every 4 weeks as a cycle), and according to the number of pregnancy weeks, the antenatal examination data can be divided into the corresponding cycles.

[0140] S233. Organize the antenatal examination data after cycle division into groups according to the cycles.

[0141] S24. Construct a cycle decomposition structure according to the cycle decomposition result and classification result of the antenatal examination data;

[0142] S25. Identify the risk factors of each type of data according to the inherent attributes of each type of data in the antenatal examination data, and construct a risk factor decomposition structure through hierarchical decomposition and analysis;

[0143] S26. Establish a coupling matrix according to the cycle decomposition structure and the risk factor decomposition structure.

[0144] It should be noted that the cycle decomposition of antenatal examination data and the decomposition of risk factors adopt the principle of the WBS-RBS (Work Breakdown Structure - Risk Breakdown Structure) decomposition structure. Using the WBS-RBS decomposition structure principle to handle the cycle decomposition of antenatal examination data and the decomposition of risk factors is a structured and systematic method. This method can more clearly understand each stage and potential risk factors in the antenatal examination cycle.

[0145] WBS is a method of breaking down complex projects into smaller and more manageable parts. In the context of antenatal examination data, WBS can divide the entire pregnancy into different examination stages, each stage including different examination items and objectives; RBS is a method of identifying and classifying project risks. It can classify risks into different categories and further refine them to specific risk sources. In antenatal examination, potential health risks related to pregnancy can be identified and managed.

[0146] S3. Based on the constructed coupling matrix, use the antenatal examination risk tree analysis method to establish an antenatal examination risk tree risk model, and conduct a risk assessment of the antenatal examination results through the antenatal examination risk tree risk model;

[0147] It should be noted that the main idea of the antenatal examination risk tree analysis method is the fault tree analysis principle. It aims to depict a directed logic tree of accident occurrence through logical deduction, so as to deeply analyze the phenomena, causes and results of the accident, and then provide effective measures for accident prevention. The antenatal examination risk tree analysis method is based on the fault tree principle. By constructing a logically clear fault tree, it deeply analyzes the risk factors and their interrelationships in the antenatal examination process, providing effective measures and basis for preventing adverse pregnancy outcomes.

[0148] As a preferred implementation method, based on the constructed coupling matrix, using the antenatal examination risk tree analysis method to establish an antenatal examination risk tree risk model, and conducting a risk assessment of the antenatal examination results through the antenatal examination risk tree risk model includes the following steps:

[0149] S31. Determine the top event of the antenatal examination risk tree, use the coupling matrix to conduct antenatal examination risk tree analysis on the top event, identify the basic events and construct an antenatal examination risk tree risk model;

[0150] It should be noted that the top event is the most critical component in the antenatal examination risk tree analysis. It represents the focus of the analysis and is usually a major adverse outcome that is not desired. In the context of antenatal examination, a typical top event may be "serious complications occur during antenatal examination".

[0151] The coupling matrix connects the cycle decomposition structure and the risk factor decomposition structure, providing the necessary input for the antenatal examination risk tree analysis. This step involves the following operations:

[0152] Analyze the coupling matrix: Check the coupling degree of each risk factor related to the top event to determine the key factors affecting the top event.

[0153] Select basic events: Based on the analysis of the coupling matrix, select those risk factors that have the greatest impact on the top event as the basic events of the antenatal examination risk tree. For example, if "hypertension" and "diabetes" are highly correlated with the top event in the coupling matrix, these factors will be selected as basic events.

[0154] Among them, after determining the top event and related basic events, constructing the antenatal examination risk tree model involves the following steps:

[0155] Determine the structure of the antenatal examination risk tree: Starting from the top event, expand downward to include all identified basic events. Use "AND gates" and "OR gates" to represent the logical relationships between events:

[0156] AND gate: All input events must occur simultaneously to cause the output event to occur.

[0157] OR gate: The occurrence of any one input event can cause the output event to occur.

[0158] Connect logical gates: According to the dependencies and interactions between events, select appropriate logical gates to connect the top event and basic events. For example, if the top event "severe complications during antenatal examination" is caused by both "hypertension" and "diabetes", then these two basic events are connected to the top event through an "AND gate".

[0159] S32. According to the antenatal examination risk tree risk model, calculate the probability of the top event occurring through the probability calculation method;

[0160] As a preferred implementation, calculating the probability of the top event occurring through the probability calculation method according to the antenatal examination risk tree risk model includes the following steps:

[0161] S321. Assign basic probability values to each basic event in the antenatal examination risk tree risk model;

[0162] It should be noted that the assignment of basic probability values is usually based on historical data, expert opinions, or relevant research. For example, according to historical data, by checking past medical records and counting the occurrence frequencies of relevant complications, a basic probability value assigns a probability value to each basic event, usually between 0 (not occurring) and 1 (certain to occur).

[0163] Suppose the antenatal examination risk tree includes the following basic events:

[0164] Hypertension: Historical data shows that the incidence rate among pregnant women is about 10%, so a probability value of 0.1 is assigned.

[0165] Diabetes: According to research, the incidence of gestational diabetes is approximately 7%, so a probability value of 0.07 is assigned.

[0166] Lifestyle risks (such as smoking, poor diet): Experts estimate that the probability of the impact of such risks is about 5%, and a probability value of 0.05 is assigned.

[0167] Environmental risks (such as exposure to harmful substances): It is difficult to accurately quantify, and the estimated probability is 3%, so a probability value of 0.03 is assigned.

[0168] S322. Determine the logical relationship between events according to the logic gates in the antenatal examination risk tree risk model;

[0169] It should be noted that in the Fault Tree Analysis (FTA) of antenatal examination risk, determining the logical relationship between events is achieved by using logic gates, mainly including "AND gate" and "OR gate", and these logic gates define how different events interact to cause the occurrence of the top event.

[0170] In the antenatal examination risk tree, if the top event "serious complications occur during antenatal examination" requires multiple conditions to be met simultaneously (for example, hypertension and diabetes coexist), then these conditions are connected by an AND gate; if the top event can be caused by multiple different single conditions, such as "serious complications occur during antenatal examination" can be independently caused by any one of "hypertension" or "lifestyle risk", then these events are connected by an OR gate.

[0171] S323. Starting from the basic events at the bottom of the antenatal examination risk tree risk model, calculate step by step upward according to the logical relationship to obtain the probability of the occurrence of the top event.

[0172] It should be noted that each basic event has a pre-assigned probability value, reflecting the possibility of its independent occurrence. For example, the probability of hypertension is 0.110%, the probability of diabetes is 0.07 (7%), the probability of lifestyle risk is 0.05 (5%), and the probability of environmental risk is 0.03 (3%);

[0173] Use the AND gate to calculate the probability of two events occurring simultaneously. For example, the probability of hypertension and diabetes occurring simultaneously is 0.007 (0.7%), which is obtained by multiplying the probabilities of the two events.

[0174] Use the OR gate to calculate the total probability of any event occurring. This includes the probability of individual events plus the probability of any combination, minus the probability of their simultaneous occurrence.

[0175] Combining the results of the AND gate and the OR gate, calculate the total probability of the top event "serious complications occur during antenatal examination". The specific calculation is as follows:

[0176] First, add up the probabilities of all basic events.

[0177] Then, subtract the overlapping probability parts when these events are combined pairwise.

[0178] Finally, if there are cases where three or more events occur simultaneously, add the probability of this part.

[0179] The calculation results show that the occurrence probability of the top event is approximately 0.085 or 8.5%, which means that under all considered risk factors, there is an 8.5% probability of severe complications occurring.

[0180] S33. According to the probability of the top event occurring, calculate the sensitivity coefficient of each basic event through sensitivity analysis;

[0181] As a preferred implementation, the calculation formula for calculating the sensitivity coefficient of each basic event through sensitivity analysis according to the probability of the top event occurring is:

[0182] ;

[0183] In the formula, H i represents the sensitivity coefficient of the basic event i ;

[0184] represents the partial derivative value of the probability value of the top event T occurring;

[0185] D ( T ) represents the probability value of the top event T occurring;

[0186] represents the partial derivative value of the basic probability value of the basic event i ;

[0187] k i represents the basic probability value of the basic event i ;

[0188] S34. According to the sensitivity analysis results, conduct a risk assessment on the antenatal examination results.

[0189] Specifically, according to the sensitivity analysis results, conducting a risk assessment on the antenatal examination results includes the following steps:

[0190] Identify key risk factors: Basic events with high sensitivity coefficients mean that they have a greater impact on the probability of the top event occurring. These factors should be the focus of risk management.

[0191] Develop a risk mitigation strategy: Based on the results of sensitivity analysis, formulate targeted risk mitigation measures, especially for those basic events with high sensitivity coefficients.

[0192] Optimize the allocation of resources: Allocate resources according to the sensitivity coefficients, and give priority to the basic events that have the greatest impact on the probability of the top event.

[0193] S4. Display the risk assessment results through data visualization techniques;

[0194] Specifically, the risk assessment results can be displayed through data visualization techniques using bar charts. Using bar charts can effectively display the sensitivity coefficients of each basic event. The length of each bar represents the sensitivity of the corresponding event, making it clear at a glance which factors have the greatest impact on the probability of the top event.

[0195] As Figure 2 shown, according to another embodiment of the present invention, there is provided an obstetrics and gynecology pregnant woman assessment and analysis system based on community antenatal examination data streams. The obstetrics and gynecology pregnant woman assessment and analysis system based on community antenatal examination data streams includes: a data storage module 1, a matrix construction module 2, a risk assessment module 3, and a result display module 4. Among them, the data storage module 1, the matrix construction module 2, the risk assessment module 3, and the result display module 4 are connected in sequence;

[0196] The data storage module 1 is used to build a community antenatal examination data stream storage platform to obtain and store antenatal examination data in real time;

[0197] The matrix construction module 2 is used to build a coupling matrix based on the obtained antenatal examination data through antenatal examination cycle decomposition and risk factor decomposition;

[0198] The risk assessment module 3 is used to establish a risk model of the antenatal examination risk tree based on the constructed coupling matrix by using the antenatal examination risk tree analysis method, and conduct a risk assessment on the antenatal examination results through the antenatal examination risk tree risk model;

[0199] The result display module 4 is used to display the risk assessment results through data visualization techniques.

[0200] In summary, by means of the above technical solutions of the present invention, the present invention can obtain and store antenatal examination data in real time by constructing a community antenatal examination data stream storage platform, ensuring the timeliness and accuracy of the data. Based on the obtained antenatal examination data, a coupling matrix is constructed through antenatal examination cycle decomposition and risk factor decomposition, which helps to systematically identify and analyze key information and risk factors in antenatal examination data. The coupling matrix can clearly show the association and interaction between different antenatal examination cycles and risk factors, providing strong support for subsequent risk assessment. Using the antenatal examination risk tree analysis method to establish an antenatal examination risk tree risk model can visually display various risks and abnormal situations that may exist during the antenatal examination process. By performing risk assessment on the antenatal examination results through the antenatal examination risk tree risk model, a more accurate and personalized assessment result can be provided. The present invention can construct an efficient and accurate antenatal examination data classification model by collecting historical antenatal examination sample data and using feature selection processing and dimensionality reduction techniques. By using the spectral clustering algorithm to optimize the feature data set, a more compact and representative feature set can be obtained, improving the efficiency and accuracy of the classification model. The calculation of the standardized Laplacian matrix and eigenvalue decomposition can ensure the reasonable clustering of data points, thereby extracting the most discriminative features. The constructed coupling matrix can clearly show the cycle decomposition structure and risk factor decomposition structure of antenatal examination data, facilitating the rapid identification and understanding of key information. Through the antenatal examination risk tree analysis method, the present invention can systematically evaluate the risks that pregnant women may face during the entire antenatal examination process, helping doctors comprehensively understand the health status and potential problems of pregnant women, and thus formulating more accurate and effective treatment and management plans. The antenatal examination risk tree risk model visually displays various risk factors and their relationships in a tree structure, enabling a clear view of which factors may have the greatest impact on the health of pregnant women and fetuses. By calculating the probability of the top event (i.e., adverse pregnancy outcome) occurring using the probability calculation method, a quantitative risk assessment result is provided for doctors, enabling them to judge the severity of the risk based on specific values and thus make more scientific decisions, which helps to improve the health level of mothers and infants.

[0201] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention 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, optical storage, etc.) that contain computer-usable program code.

[0202] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for evaluating and analyzing pregnant women in obstetrics and gynecology based on community prenatal examination data stream, characterized in that: The obstetrics and gynecology pregnant woman assessment and analysis method based on community prenatal examination data stream includes the following steps: S1. Build a community prenatal examination data stream storage platform to obtain and store prenatal examination data in real time; S2. Based on the acquired prenatal examination data, a coupling matrix is ​​constructed by decomposing the prenatal examination cycle and risk factors; S3. Based on the constructed coupling matrix, a prenatal examination risk tree risk model is established using the prenatal examination risk tree analysis method, and the prenatal examination risk tree risk model is used to conduct risk assessment on the prenatal examination results; S4. Display risk assessment results through data visualization technology; The step of constructing a coupling matrix based on the acquired prenatal examination data by decomposing the prenatal examination cycle and the risk factors includes the following steps: S21, preprocessing the acquired prenatal examination data, wherein the preprocessing includes data cleaning and standardization; S22, constructing a prenatal examination data classification model, and classifying the prenatal examination data after prenatal examination through the prenatal examination data classification model; S23, performing time series analysis on each type of data in the prenatal examination data, and according to the analysis results, performing period decomposition on the prenatal examination data using a preset period standard; S24. Construct a cycle decomposition structure according to the cycle decomposition results and classification results of the prenatal examination data; S25. According to the inherent attributes of each type of data in the prenatal examination data, identify the risk factors of each type of data, and construct a risk factor decomposition structure through step-by-step decomposition and analysis; S26. Establish a coupling matrix based on the cycle decomposition structure and risk factor decomposition structure.

2. The method for evaluating and analyzing obstetrics and gynecology pregnant women based on community prenatal examination data stream according to claim 1 is characterized in that: The method of constructing a prenatal examination data classification model and classifying the prenatal examination data after prenatal examination by using the prenatal examination data classification model comprises the following steps: S221, collect historical prenatal examination sample data, and establish a training data set through feature selection processing; S222. Construct and train a prenatal examination data classification model using a support vector machine algorithm based on the obtained training data set; S223. The preprocessed antenatal examination data is used as input and input into the trained antenatal examination data classification model to classify the preprocessed antenatal examination data.

3. The method for evaluating and analyzing obstetrics and gynecology pregnant women based on community prenatal examination data stream according to claim 2 is characterized in that: Collecting historical prenatal examination sample data and establishing a training data set through feature selection processing includes the following steps: S2211. Perform dimensionality reduction processing on historical prenatal examination sample data by using dimensionality reduction technology; S2212, performing correlation feature selection on the historical prenatal examination sample data after dimension reduction to establish a feature data set; S2213. Optimize the feature data set using a spectral clustering algorithm to obtain a new feature data set, and use the new feature data set as a training data set.

4. The method for evaluating and analyzing obstetrics and gynecology pregnant women based on community prenatal examination data stream according to claim 3 is characterized in that: The method of processing the feature data set by using the spectral clustering algorithm to obtain a new feature data set includes the following steps: S22131. For each feature data point in the feature data set, calculate the similarity between each pair of feature data points; S22132, constructing an undirected graph using each feature data point in the feature data set as a node, and using the similarity between the feature data points as the weight of the edge between the nodes in the undirected graph; S22133, constructing a weighted connection matrix and a degree matrix according to the similarity between nodes and the sum of the weights of all edges connected to each node; S22134. Calculate a normalized Laplace matrix based on the constructed weighted connection matrix and degree matrix; S22135, performing eigenvalue decomposition on the calculated normalized Laplace matrix, and extracting eigenvectors corresponding to several minimum non-zero eigenvalues ​​therein; S22136. Divide the data points into several clusters according to the feature vectors, and select the cluster center from each cluster as a representative point to form a new feature data set.

5. The method for evaluating and analyzing obstetrics and gynecology pregnant women based on community prenatal examination data stream according to claim 4 is characterized in that: The calculation formula for calculating the standardized Laplace matrix based on the constructed weighted connection matrix and degree matrix is: R=F -1 / 2 W F -1 / 2 ; Where R represents the normalized Laplace matrix; F represents the degree matrix; F -1 / 2 represents the diagonal matrix formed by taking the square root of the reciprocal of each diagonal element of the degree matrix F; W represents the weighted connection matrix.

6. The method for evaluating and analyzing obstetrics and gynecology pregnant women based on community prenatal examination data stream according to claim 1, characterized in that: The step of performing time series analysis on each type of data in the prenatal examination data and periodically decomposing the prenatal examination data according to the analysis results by using a preset period standard comprises the following steps: S231, obtaining the real-time acquisition time of the prenatal examination data, and arranging each type of data in the prenatal examination data in the order of the real-time acquisition time to form a time series; S232, dividing each type of data in the prenatal examination data into periods according to a preset period standard; S233, grouping and arranging the prenatal examination data after the cycle division according to the cycle.

7. The obstetrics and gynecology pregnant woman assessment and analysis method based on community prenatal examination data stream according to claim 1 is characterized in that: The method of establishing a prenatal examination risk tree risk model based on the constructed coupling matrix and using the prenatal examination risk tree analysis method, and conducting risk assessment on the prenatal examination results through the prenatal examination risk tree risk model includes the following steps: S31, determine the top event of the prenatal examination risk tree, use the coupling matrix to analyze the top event of the prenatal examination risk tree, identify the basic events and build a prenatal examination risk tree risk model; S32. Calculate the probability of occurrence of the top event by probability calculation method according to the antenatal examination risk tree risk model; S33. Calculate the sensitivity coefficient of each basic event through sensitivity analysis according to the probability of occurrence of the top event; S34. Conduct risk assessment on prenatal examination results based on sensitivity analysis results.

8. The method for evaluating and analyzing obstetrics and gynecology pregnant women based on community prenatal examination data stream according to claim 7, characterized in that: The method of calculating the probability of occurrence of the top event by a probability calculation method according to the prenatal examination risk tree risk model includes the following steps: S321, assigning a basic probability value to each basic event in the antenatal examination risk tree risk model; S322, determining the logical relationship between events according to the logic gates in the antenatal examination risk tree risk model; S323. Starting from the basic event at the bottom of the antenatal examination risk tree risk model, calculate upward step by step according to the logical relationship to obtain the probability of the top event occurring.

9. The method for evaluating and analyzing obstetrics and gynecology pregnant women based on community prenatal examination data stream according to claim 8, characterized in that: The calculation formula for calculating the sensitivity coefficient of each basic event through sensitivity analysis based on the probability of occurrence of the top event is: ； In the formula, H i Represents basic events i The sensitivity coefficient of Indicates top events T The partial derivative value of the probability value of occurrence; D ( T ) indicates the top event T Probability value of occurrence; Represents basic events i The partial derivative value of the basic probability value of ; k i Represents basic events i The basic probability value of .

10. A system for evaluating and analyzing obstetric and gynecological pregnant women based on community prenatal examination data stream, used to implement the method for evaluating and analyzing obstetric and gynecological pregnant women based on community prenatal examination data stream according to any one of claims 1 to 9, characterized in that: The obstetrics and gynecology pregnant woman assessment and analysis system based on community prenatal examination data stream includes: a data existence module, a matrix construction module, a risk assessment module and a result display module, wherein the data existence module, the matrix construction module, the risk assessment module and the result display module are connected in sequence; The data storage module is used to build a community prenatal examination data stream storage platform to obtain and store prenatal examination data in real time; The matrix construction module is used to construct a coupling matrix through prenatal examination cycle decomposition and risk factor decomposition based on the acquired prenatal examination data; The risk assessment module is used to establish a prenatal examination risk tree risk model based on the constructed coupling matrix using the prenatal examination risk tree analysis method, and to perform risk assessment on the prenatal examination results through the prenatal examination risk tree risk model; The result display module is used to display the risk assessment results through data visualization technology.

Images