A pregnancy complication risk assessment system for high-risk pregnant women

Abstract

The present invention relates to the technical field of pregnancy complication risk assessment, and specifically to a pregnancy complication risk assessment system for high-risk pregnant women. The system can implement the following steps through the mutual cooperation between multiple modules: obtaining the current dimensional data of the pregnant woman to be detected under all preset dimensions during the current pregnancy examination process; screening out matching pregnant woman categories; screening out matching prone stages; screening out the preset dimensions that have the greatest impact on the proneness of complications in the matching prone stages; constructing reference clusters and comparison clusters; and determining the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be detected according to the degree of belonging of the current dimensional data under distinguishing characteristic dimensions to the reference cluster and the comparison cluster. The present invention quantifies the current pregnancy complication risk assessment factor, thereby assisting doctors in conducting pregnancy complication risk assessment on high-risk pregnant women, and improving the rationality of conducting pregnancy complication risk assessment on high-risk pregnant women.

Description

Technical Field

[0001] The present invention relates to the technical field of pregnancy complication risk assessment, and in particular to a pregnancy complication risk assessment system for high-risk pregnant women. Background Art

[0002] Pregnancy complications are a series of health problems that may occur during pregnancy, including pregnancy-induced hypertension syndrome, bleeding during pregnancy, placental abnormalities, amniotic fluid abnormalities, and fetal distress. These complications may increase the risk of miscarriage, uterine rupture, and placental retention. In severe cases, they may lead to maternal multi-organ dysfunction and even threaten the lives of mothers and babies. For example, gestational diabetes not only increases the risk of macrosomia, premature birth, and fetal developmental abnormalities, but may also increase the risk of pregnant women developing diabetes in the future. In addition, hypertensive disorders complicating pregnancy may lead to serious consequences such as placental insufficiency, fetal growth restriction, and premature birth. In general, high-risk pregnant women have a relatively high risk of pregnancy complications. Therefore, it is crucial to conduct a risk assessment of pregnancy complications for high-risk pregnant women. At present, the method commonly used for disease risk assessment is to conduct disease risk assessment based on the doctor's subjective experience.

[0003] However, when the risk of pregnancy complications is assessed for high-risk pregnant women based on the doctor's subjective experience, the following technical problems often occur:

[0004] As different pregnancy stages proceed, different high-risk pregnant women often have different pregnancy reactions, and their risk levels of pregnancy complications often vary. In addition, different doctors often have different levels of experience in different pregnancy situations. Therefore, if the pregnancy complication risk assessment is conducted directly based on the doctor's subjective experience, the pregnancy complication risk assessment results for high-risk pregnant women may be greatly influenced by the doctor's subjective factors, resulting in poor rationality in the pregnancy complication risk assessment for high-risk pregnant women. Summary of the invention

[0005] In order to solve the technical problem of poor rationality in risk assessment of pregnancy complications for high-risk pregnant women, the present invention proposes a risk assessment system for pregnancy complications for high-risk pregnant women.

[0006] In a first aspect, the present invention provides a pregnancy complication risk assessment system for high-risk pregnant women, the system comprising:

[0007] A data acquisition module is used to obtain the current dimension data of the pregnant woman to be tested under all preset dimensions during the current pregnancy examination process;

[0008] Category screening module, used to screen out matching pregnant women categories from all historical pregnant women categories based on all current dimension data;

[0009] A stage screening module is used to screen out the complication-prone stage closest to the pregnancy stage corresponding to the current pregnancy examination process from the pregnancy stages of all historical pregnant women in the matching pregnant woman category as the matching complication-prone stage;

[0010] A division and screening module is used to select the historical pregnant women who have newly developed complications in the matching prone stage and the historical pregnant women who have not developed complications in the matching pregnant women category as reference pregnant women and comparison pregnant women, respectively, and screen out the preset dimensions that have the greatest impact on the susceptibility of complications in the matching prone stage as distinguishing feature dimensions;

[0011] A cluster building module is used to form a reference cluster by combining the historical dimension data of all reference pregnant women under the distinguishing characteristic dimension in the matching prone stage, and to form a comparison cluster by combining the historical dimension data of all comparison pregnant women under the distinguishing characteristic dimension in the matching prone stage;

[0012] The risk assessment factor determination module is used to determine the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be tested according to the degree of belonging of the current dimensional data under the distinguishing feature dimension to the reference cluster cluster and the comparison cluster cluster respectively.

[0013] In combination with the first aspect above, in a possible implementation, a method for obtaining historical pregnant women categories includes:

[0014] Obtain historical dimension data of all preset dimensions obtained by pregnancy examination of each historical pregnant woman in each pregnancy stage, and form a historical data vector of each historical pregnant woman in each pregnancy stage;

[0015] Initial pregnancy stage was screened out from all pregnancy stages;

[0016] According to the historical data vectors of all historical pregnant women in the initial pregnancy stage, all historical pregnant women are clustered to obtain historical pregnant woman categories.

[0017] In combination with the first aspect above, in a possible implementation, the step of filtering out matching pregnant woman categories from all historical pregnant woman categories based on all current dimension data includes:

[0018] All current dimensional data are used to form a current data vector, and the pregnancy stage corresponding to the current pregnancy examination process is determined as the target pregnancy stage;

[0019] Determine the mean of the historical data vectors of all historical pregnant women in each historical pregnant woman category at the target pregnancy stage as the representative vector to be matched corresponding to each historical pregnant woman category;

[0020] Determine the distance between the to-be-matched representative vector corresponding to each historical pregnant woman category and the current data vector as the target distance corresponding to each historical pregnant woman category;

[0021] The historical pregnant woman category with the smallest target distance is selected from all historical pregnant woman categories as the matching pregnant woman category.

[0022] In combination with the first aspect above, in a possible implementation, a method for obtaining the complication-prone stage includes:

[0023] The pregnancy stages of historical pregnant women with new complications and historical pregnant women without complications are screened out from all pregnancy stages of all historical pregnant women in the matching pregnant woman category as candidate pregnancy stages;

[0024] If the number of historical pregnant women who have new complications in the candidate pregnancy stage in the matching pregnant woman category is greater than the preset number, the candidate pregnancy stage is determined as a temporary pregnancy stage;

[0025] According to the time interval between each two temporary pregnancy stages, a target combined factor between each two temporary pregnancy stages is determined;

[0026] The interim pregnancy stages with mutual target merging factors greater than the preset merging threshold constitute the complication-prone stages.

[0027] In combination with the first aspect above, in a possible implementation, the formula corresponding to the target merging factor between two temporary pregnancy stages is:

[0028] ;

[0029] ;in, is the target merging factor between the i-th temporary pregnancy stage and the j-th temporary pregnancy stage; i and j are the serial numbers of different temporary pregnancy stages; is a natural exponential function; is the time interval between the i-th temporary pregnancy stage and the j-th temporary pregnancy stage; T represents the approximate average time interval between temporary pregnancy stages; M is the length of time corresponding to the standard complete pregnancy period; N is the number of temporary pregnancy stages.

[0030] In combination with the first aspect above, in a possible implementation, a method for obtaining the influence degree of each preset dimension on the complication susceptibility of matching the susceptibility stage includes:

[0031] Based on the historical dimension data of all reference pregnant women and all comparison pregnant women under each preset dimension in the matching prone stage, the influence of each preset dimension on the complication susceptibility in the matching prone stage was determined.

[0032] In combination with the first aspect above, in a possible implementation, determining the influence of each preset dimension on the susceptibility of complications in the matching prone stage according to the historical dimension data of all reference pregnant women and all comparison pregnant women in each preset dimension in the matching prone stage includes:

[0033] Any preset dimension is determined as a marked dimension, and according to the historical dimension data of all reference pregnant women and all comparison pregnant women under the marked dimension in the matching prone stage, the set consisting of all reference pregnant women and all comparison pregnant women is sorted in descending order to obtain a target pregnant woman sequence;

[0034] The influence degree of the marking dimension on the susceptibility of complications in the matching prone stage is determined according to the continuous occurrence of the comparison pregnant women in the target pregnant woman sequence.

[0035] In combination with the first aspect above, in a possible implementation, determining the influence of the marking dimension on the susceptibility of complications in the matching prone stage according to the continuous appearance of the comparison pregnant women in the target pregnant woman sequence includes:

[0036] Each consecutive comparison pregnant woman in the target pregnant woman sequence is used to form a comparison pregnant woman group, thereby obtaining a comparison pregnant woman group set;

[0037] The number of comparison pregnant women groups in the comparison pregnant women group set is determined as the target continuous appearance number;

[0038] The number of comparison pregnant women in each comparison pregnant woman group was determined as the comparison number;

[0039] According to the size of the comparison quantity, all the comparison quantities are divided into two categories, namely the first quantity category and the second quantity category;

[0040] The mean of all comparison quantities in the first quantity category is determined as the first representative quantity;

[0041] The mean of all comparison quantities in the second quantity class is determined as the second representative quantity;

[0042] determining an absolute value of a difference between the first representative quantity and the second representative quantity as a quantity change difference;

[0043] According to the number of consecutive occurrences of the target and the difference in quantity changes, the degree of influence of the marking dimension on the susceptibility of complications in the matching prone stage is determined, wherein the number of consecutive occurrences of the target is positively correlated with the degree of influence on the susceptibility of complications, and the difference in quantity changes is negatively correlated with the degree of influence on the susceptibility of complications.

[0044] In combination with the first aspect above, in a possible implementation, the formula corresponding to the influence degree of the marking dimension on the complication susceptibility of the matching prone stage is:

[0045] ; Where, f is the influence of the marking dimension on the complication susceptibility of the matching prone stage; y is the number of consecutive appearances of the target; is the natural exponential function; c is the difference in quantity change.

[0046] In combination with the first aspect above, in a possible implementation, the formula corresponding to the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be detected is:

[0047] ;Wherein, w is the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be tested; It is to distinguish the degree of belonging of the current dimension data under the feature dimension to the reference clustering cluster; It is to distinguish the degree of belonging of the current dimension data under the feature dimension to the contrast clustering cluster.

[0048] In a second aspect, the present invention provides a method for assessing the risk of pregnancy complications in high-risk pregnant women implemented by a pregnancy complication risk assessment system for high-risk pregnant women, the method comprising:

[0049] Obtain the current dimension data of all preset dimensions of the pregnant woman to be tested during the current pregnancy test;

[0050] Based on all current dimension data, matching pregnant women categories are selected from all historical pregnant women categories;

[0051] The complication-prone stage closest to the gestational stage corresponding to the current pregnancy examination process is selected from the gestational stages of all historical pregnant women in the matching pregnant woman category as the matching complication-prone stage;

[0052] The pregnant women with new complications and the pregnant women without complications in the matched pregnant women category are used as reference pregnant women and comparison pregnant women respectively, and the preset dimensions with the greatest impact on the susceptibility of complications in the matched prone stage are selected as distinguishing characteristic dimensions;

[0053] The historical dimension data of all reference pregnant women under the distinguishing characteristic dimension in the matching prone stage are used to form a reference cluster, and the historical dimension data of all comparison pregnant women under the distinguishing characteristic dimension in the matching prone stage are used to form a comparison cluster;

[0054] According to the degree of belonging of the current dimension data under the distinguishing feature dimension to the reference cluster and the comparison cluster, the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be tested is determined.

[0055] In a third aspect, a server is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the above-mentioned method for assessing the risk of pregnancy complications in high-risk pregnant women.

[0056] In a fourth aspect, a computer program product is provided, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the above-mentioned method for assessing the risk of pregnancy complications for high-risk pregnant women.

[0057] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned method for assessing the risk of pregnancy complications in high-risk pregnant women.

[0058] The present invention has the following beneficial effects:

[0059] The present invention provides a pregnancy complication risk assessment system for high-risk pregnant women, which quantifies the current pregnancy complication risk assessment factor, thereby assisting doctors in performing pregnancy complication risk assessment on high-risk pregnant women, solving the technical problem of poor rationality of pregnancy complication risk assessment on high-risk pregnant women, and improving the rationality of pregnancy complication risk assessment on high-risk pregnant women. Compared with the pregnancy complication risk assessment on high-risk pregnant women based on the subjective experience of doctors, the present invention considers the historical pregnant women in the matching pregnant women category similar to the pregnant women to be tested when performing pregnancy complication risk assessment on high-risk pregnant women, and screens the complication prone stage closest to the pregnancy stage of the pregnant women to be tested, so as to facilitate the subsequent analysis of the complication prone situation in the pregnancy stage of the pregnant women to be tested, and screen out the preset dimension with the greatest influence on the complication proneness of the matching prone stage, which can facilitate the subsequent classification of the current dimensional data under the distinguishing feature dimension respectively for the reference clustering cluster and the comparison clustering cluster, and quantify the current pregnancy complication risk assessment factor corresponding to the pregnant women to be tested, thereby assisting doctors in performing pregnancy complication risk assessment on high-risk pregnant women, thereby improving the rationality of pregnancy complication risk assessment on high-risk pregnant women. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0061] Figure 1It is a structural schematic diagram of a pregnancy complication risk assessment system for high-risk pregnant women of the present invention;

[0062] Figure 2 A schematic diagram of a process for assessing the risk of pregnancy complications in high-risk pregnant women according to the present invention;

[0063] Figure 3 The figure is a schematic diagram of the structure of a computer device of the present invention. DETAILED DESCRIPTION

[0064] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0065] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0066] refer to Figure 1 , shows a schematic diagram of the structure of a pregnancy complication risk assessment system for high-risk pregnant women according to the present invention. The pregnancy complication risk assessment system for high-risk pregnant women includes:

[0067] The data acquisition module 101 is used to acquire the current dimension data of the pregnant woman to be detected in all preset dimensions during the current pregnancy examination process.

[0068] Among them, the pregnant woman to be tested may be a high-risk pregnant woman who has not yet developed pregnancy complications and is to undergo a risk assessment for pregnancy complications. A high-risk pregnant woman refers to a pregnant woman with high-risk pregnancy factors, such as advanced age, age under 18 years old, postpartum hemorrhage, or underlying diseases. The current pregnancy check process may be the most recent pregnancy check process of the pregnant woman to be tested, and its end time may be the current time. The preset dimension may be a pre-set dimension related to pregnancy complications. For example, the preset dimension may be, but is not limited to: weight dimension, blood pressure dimension, hemoglobin concentration dimension, white blood cell concentration dimension, and platelet concentration dimension. The number of preset dimensions may be a preset number, which may be equal to 5. The current dimensional data may be the dimensional data of the pregnant woman to be tested detected during the current pregnancy check process. The dimensional data may be data detected under the preset dimensions.

[0069] For example, if a preset dimension is a weight dimension, the weight of the pregnant woman to be tested can be collected through a weight sensor during the current pregnancy test. The weight collected at this time is the data detected under the weight dimension, which can be used as the current dimension data under the weight dimension. Similarly, the current dimension data under other preset dimensions can be collected during the current pregnancy test.

[0070] It should be noted that ultrasound diagnosis can also be performed on pregnant women to obtain data in different dimensions. For example, a three-dimensional color Doppler ultrasound diagnostic instrument can be used for diagnosis, and the instrument mode can be adjusted to the gynecological examination mode. First, an abdominal ultrasound examination is performed on the pregnant woman, and the probe frequency is set to 2.0~6.0MHz; a vaginal ultrasound examination is performed, and the probe frequency is set to 5.0~8.00MHz. The uterine condition of the pregnant woman is observed in detail, including local blood flow, the anatomical relationship between the gestational sac and the uterine scar, the size and shape of the uterus, whether the lower segment of the anterior wall is in a continuous and complete state, and the bilateral attachments. Through the historical data of the hospital, a large number of examination parameters of pregnant women can be obtained. These examination parameter values ​​form a sequence, which can be recorded as data of each pregnant woman in different dimensions.

[0071] The category screening module 102 is used to screen out matching pregnant woman categories from all historical pregnant woman categories based on all current dimension data.

[0072] As an example, the category screening module 102 may be used to implement the following steps:

[0073] The first step is to obtain the historical dimensional data of all preset dimensions obtained by pregnancy examinations of each historical pregnant woman in each pregnancy stage, and form a historical data vector of each historical pregnant woman in each pregnancy stage.

[0074] Among them, the historical pregnant woman may be a high-risk pregnant woman who has completed pregnancy in a historical time period. The pregnancy stage may be a stage pre-divided during the entire pregnancy process. The required dimensional data may be collected once at each pregnancy stage. The historical dimensional data may be dimensional data of historical pregnant women detected during historical pregnancy stages, and the acquisition method thereof may be the same as the acquisition method of the current dimensional data, which will not be repeated here.

[0075] For example, every 10 days in the complete pregnancy process can be regarded as a pregnancy stage. The complete pregnancy process can be the process of growth and development of the embryo and fetus in the mother's body, which takes about 40 weeks. Taking 40 weeks as an example, the embodiment of the present invention can be divided into 28 pregnancy stages, and if the current pregnancy stage of the pregnant woman to be tested is within 40 weeks, the risk assessment of pregnancy complications can be performed through the embodiment of the present invention; if the current pregnancy stage of the pregnant woman to be tested is greater than 40 weeks, the pregnant woman to be tested can be reminded to wait for delivery in the hospital, and the risk assessment of pregnancy complications can be performed by the doctor at this time.

[0076] In the second step, the initial pregnancy stage was screened out from all pregnancy stages.

[0077] Among them, the initial pregnancy stage may be the earliest pregnancy stage.

[0078] For example, if the duration of a pregnancy stage is 10 days, the initial pregnancy stage may be the first 10 days of a pregnant woman's pregnancy.

[0079] The third step is to cluster all historical pregnant women according to their historical data vectors at the above initial pregnancy stage to obtain historical pregnant woman categories.

[0080] For example, according to the historical data vectors of all historical pregnant women in the above-mentioned initial pregnancy stage, all historical pregnant women are clustered by using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, and each category obtained by clustering at this time is used as a historical pregnant woman category.

[0081] It should be noted that the historical pregnant women in the historical pregnant women category may be pregnant women with similar initial pregnancies.

[0082] The fourth step is to combine all current dimensional data into a current data vector, and determine the pregnancy stage corresponding to the current pregnancy examination process as the target pregnancy stage.

[0083] For example, if the current pregnancy checkup process is conducted within the third 10 days of the pregnancy of the pregnant woman to be tested, the pregnancy stage corresponding to the current pregnancy checkup process may be the third 10 days of the pregnancy.

[0084] It should be noted that the possible situations in which complications may occur in pregnant women at different stages of pregnancy are often different. Therefore, obtaining the pregnancy stage corresponding to the current pregnancy examination process can facilitate the subsequent analysis of the actual situation of complications in historical pregnant women at the same pregnancy stage as the pregnant woman to be tested, thereby facilitating the subsequent evaluation of whether the pregnancy stage of the pregnant woman to be tested is prone to complications.

[0085] In the fifth step, the mean of the historical data vectors of all historical pregnant women in each historical pregnant woman category at the above target pregnancy stage is determined as the representative vector to be matched corresponding to each historical pregnant woman category.

[0086] The mean of the multiple vectors may be a vector formed by the average values ​​of the corresponding elements of the multiple vectors.

[0087] It should be noted that the representative vector to be matched corresponding to the historical pregnant woman category can represent the overall pregnancy situation of the historical pregnant women in the historical pregnant woman category who are at the same pregnancy stage as the pregnant woman to be detected.

[0088] In the sixth step, the distance between the to-be-matched representative vector corresponding to each historical pregnant woman category and the above current data vector is determined as the target distance corresponding to each historical pregnant woman category.

[0089] Step 7: Filter out the historical pregnant woman category with the smallest target distance from all historical pregnant woman categories as the matching pregnant woman category.

[0090] It should be noted that different pregnant women often have different probabilities of developing complications during the same stage of pregnancy. For example, obese pregnant women and pregnant women with high blood sugar often face different risks of complications during the same stage of pregnancy. Therefore, obtaining a matching pregnant woman category with a similar pregnancy condition to the pregnant woman to be tested can facilitate subsequent risk assessment of pregnancy complications for the pregnant woman to be tested.

[0091] The stage screening module 103 is used to screen out the complication-prone stage closest to the pregnancy stage corresponding to the current pregnancy examination process from the pregnancy stages of all historical pregnant women in the matching pregnant woman category as the matching complication-prone stage.

[0092] As an example, the stage screening module 103 may be used to implement the following steps:

[0093] In the first step, the pregnancy stages of historical pregnant women with new complications and historical pregnant women without complications are screened out from all pregnancy stages of all historical pregnant women in the matching pregnant woman category as candidate pregnancy stages.

[0094] If there are pregnant women with a history of new complications during a certain stage of pregnancy, it often means that there are pregnant women who did not have complications during this stage of pregnancy. Pregnant women with a history of no complications during a certain stage of pregnancy may be pregnant women who have not had complications until the end of this stage of pregnancy.

[0095] In the second step, if the number of historical pregnant women who have newly developed complications in the candidate pregnancy stage in the matching pregnant woman category is greater than a preset number, the candidate pregnancy stage is determined as a temporary pregnancy stage.

[0096] For example, the preset number may be a pre-set number that may be equal to 50% of the number of historical pregnancies in the matching pregnant woman category that did not develop complications during the candidate pregnancy stage.

[0097] It should be noted that different pregnant women often have different probabilities of developing complications at different stages of pregnancy. Similar pregnant women may be prone to complications at certain stages of pregnancy, but not at other stages of pregnancy. The temporary pregnancy stage can characterize the stage of pregnancy at which historical pregnant women similar to the pregnant woman to be tested are relatively prone to complications.

[0098] The third step is to determine the target merging factor between each two temporary pregnancy stages according to the time interval between each two temporary pregnancy stages.

[0099] For example, the formula for determining the target merging factor between two interim pregnancy stages may be:

[0100] ;

[0101] ;in, is the target merging factor between the i-th temporary pregnancy stage and the j-th temporary pregnancy stage. i and j are the serial numbers of different temporary pregnancy stages. is a natural exponential function. is the time interval between the i-th temporary pregnancy stage and the j-th temporary pregnancy stage. T represents the approximate average time interval between temporary pregnancy stages. M is the length of the standard complete pregnancy period. The standard complete pregnancy period can represent a complete normal pregnancy period, and its corresponding length can be 40 weeks. N is the number of temporary pregnancy stages.

[0102] It should be noted that when The smaller it is, the smaller the time interval between the i-th temporary pregnancy stage and the j-th temporary pregnancy stage is, which often means that the i-th temporary pregnancy stage and the j-th temporary pregnancy stage can be combined for analysis. The larger it is, the more likely it is that the i-th temporary pregnancy stage and the j-th temporary pregnancy stage can be combined for analysis.

[0103] In the fourth step, temporary pregnancy stages with mutual target merging factors greater than the preset merging threshold are considered to constitute complication-prone stages.

[0104] The preset merging threshold may be a pre-set threshold, which may be 0.6.

[0105] For example, if the target merging factor between the first temporary pregnancy stage and the second temporary pregnancy stage is greater than the preset merging threshold, and the target merging factor between the second temporary pregnancy stage and the third temporary pregnancy stage is greater than the preset merging threshold, then the union of the first temporary pregnancy stage, the second temporary pregnancy stage and the third temporary pregnancy stage can be taken as a complication-prone stage.

[0106] It should be noted that the complication-prone stage can represent the period of pregnancy during which pregnant women with a history similar to that of the pregnant woman to be tested are relatively prone to complications.

[0107] The fifth step is to select the complication-prone stage closest to the complication-prone stage corresponding to the current pregnancy examination process from the gestational stages of all historical pregnant women in the matching pregnant woman category. The matching complication-prone stage may include the following sub-steps:

[0108] In the first sub-step, if the pregnancy stage corresponding to the current pregnancy examination process is at a stage prone to complications, the stage prone to complications may be used as a matching stage prone to complications.

[0109] In the second sub-step, if the pregnancy stage corresponding to the current pregnancy checkup process does not belong to any complication-prone stage, the complication-prone stage that is after the pregnancy stage corresponding to the current pregnancy checkup process and has the shortest time interval with the pregnancy stage corresponding to the current pregnancy checkup process can be used as the matching complication-prone stage.

[0110] It should be noted that matching the prone stage can represent the stage of complications that the pregnant woman to be tested is currently most likely to be in.

[0111] The division and screening module 104 is used to select historical pregnant women who have newly developed complications in the matching prone stage and historical pregnant women who have not developed complications in the matching pregnant women category as reference pregnant women and comparison pregnant women, respectively, and screen out the preset dimensions that have the greatest impact on the susceptibility of complications in the matching prone stage as distinguishing feature dimensions.

[0112] The reference pregnant women may be pregnant women with new complications in the matching prone stage in the matching pregnant women category, and the comparison pregnant women may be pregnant women with no complications in the matching prone stage in the matching pregnant women category.

[0113] As an example, a method for obtaining the influence degree of each preset dimension on the complication susceptibility of the matching prone stage may include determining the influence degree of each preset dimension on the complication susceptibility of the matching prone stage according to the historical dimension data of all reference pregnant women and all comparison pregnant women under each preset dimension in the matching prone stage, which may specifically include the following steps:

[0114] In the first step, any preset dimension is determined as a marking dimension, and according to the historical dimension data of all reference pregnant women and all comparison pregnant women under the above marking dimension during the matching prone stage, the set consisting of all reference pregnant women and all comparison pregnant women is sorted in descending order to obtain the target pregnant woman sequence.

[0115] Among them, the reference pregnant women or comparison pregnant women who are closer to the front in the target pregnant women sequence tend to have larger historical dimension data under the label dimension within the matching prone stage.

[0116] The second step is to determine the influence of the above-mentioned marking dimension on the susceptibility of complications in the matching prone stage according to the continuous appearance of the comparison pregnant women in the above-mentioned target pregnant women sequence, which may include the following sub-steps:

[0117] In the first sub-step, each consecutive comparison pregnant woman in the target pregnant woman sequence is used to form a comparison pregnant woman group, thereby obtaining a comparison pregnant woman group set.

[0118] For example, if the target pregnant woman sequence is {first comparison pregnant woman, second comparison pregnant woman, third comparison pregnant woman, first reference pregnant woman, second reference pregnant woman, fourth comparison pregnant woman, fifth comparison pregnant woman, third reference pregnant woman, fourth reference pregnant woman, fifth reference pregnant woman, sixth comparison pregnant woman, sixth reference pregnant woman}, then three comparison pregnant woman groups can be obtained, that is, the comparison pregnant woman group set can include: {first comparison pregnant woman, second comparison pregnant woman, third comparison pregnant woman}, {fourth comparison pregnant woman, fifth comparison pregnant woman} and {sixth comparison pregnant woman}.

[0119] In the second sub-step, the number of comparison pregnant women groups in the above comparison pregnant women group set is determined as the target continuous appearance number.

[0120] In the third sub-step, the number of comparison pregnant women in each comparison pregnant woman group is determined as the comparison number.

[0121] In the fourth sub-step, all the comparison quantities are divided into two categories according to the size of the comparison quantities, namely the first quantity category and the second quantity category.

[0122] For example, the OTSU algorithm can be used to divide all comparison quantities into two categories, namely the first quantity category and the second quantity category.

[0123] Optionally, the method for obtaining the first quantity class and the second quantity class can also be: determine the mean of all comparison quantities as the quantity threshold, constitute the first quantity class with the comparison quantities less than or equal to the quantity threshold, and constitute the second quantity class with the comparison quantities greater than the quantity threshold.

[0124] The fifth sub-step is to determine the mean of all comparison quantities in the first quantity category as the first representative quantity.

[0125] The sixth sub-step is to determine the mean of all comparison quantities in the second quantity class as the second representative quantity.

[0126] In a seventh sub-step, the absolute value of the difference between the first representative quantity and the second representative quantity is determined as the quantity change difference.

[0127] The eighth sub-step is to determine the degree of influence of the above-mentioned marking dimension on the susceptibility of complications in the matching prone stage according to the number of consecutive occurrences of the above-mentioned target and the difference in the above-mentioned quantity changes.

[0128] Among them, the number of consecutive occurrences of the target can be negatively correlated with the degree of complication susceptibility, and the difference in quantity changes can be positively correlated with the degree of complication susceptibility.

[0129] For example, the formula for determining the influence of the marking dimension on the complication susceptibility of the matching prone stage can be:

[0130] ; where f is the influence of the marking dimension on the complication susceptibility of the matching prone stage. c is the number of consecutive appearances of the target. is a natural exponential function. y is the difference in quantity change.

[0131] It should be noted that in actual situations, if a preset dimension has no effect on whether a pregnant woman has complications, the difference between the dimensional data of pregnant women with complications and those without complications under the preset dimension is often not large. The distribution of pregnant women with complications and those without complications in the obtained sequence of pregnant women is often relatively uniform, and the number of consecutive appearances of historical pregnant women with or without complications is often large. Therefore, when c is larger, it often means that the number of consecutive appearances of pregnant women without complications in the target sequence of pregnant women is more, which often means that the influence of the marked dimension on whether complications occur in the matching prone stage is smaller. In actual situations, if a preset dimension has no effect on whether a pregnant woman has complications, the dimensional data of pregnant women without complications under the preset dimension is more likely to be evenly distributed, and the change is often small. When y is smaller, it often means that the dimensional data of the comparison pregnant women under the marked dimension is more likely to be evenly distributed, and the data difference between different categories is not large, which often means that the marked dimension has less influence on whether complications occur in the matching prone stage. Therefore, when f is larger, it often means that the label dimension has a greater impact on whether complications occur in the prone stage, and it often means that the label dimension can be used as a key dimension to assist in judging whether the pregnant woman to be tested is currently prone to complications.

[0132] The cluster construction module 105 is used to form a reference cluster by combining the historical dimension data of all reference pregnant women under the distinguishing feature dimension in the matching prone stage, and to form a comparison cluster by combining the historical dimension data of all comparison pregnant women under the distinguishing feature dimension in the matching prone stage.

[0133] As an example, first, the clustering cluster formed by the historical dimension data of all reference pregnant women under the distinguishable characteristic dimension in the matching prone stage can be used as the reference clustering cluster, and then, the clustering cluster formed by the historical dimension data of all comparison pregnant women under the distinguishable characteristic dimension in the matching prone stage can be used as the comparison clustering cluster.

[0134] The risk assessment factor determination module 106 is used to determine the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be detected according to the degree of belonging of the current dimension data under the distinguishing feature dimension to the reference cluster and the comparison cluster respectively.

[0135] Among them, the degree of belonging, also known as the degree of membership, indicates the degree to which the data can be divided into clusters. The larger the value, the more the data should be divided into the corresponding cluster.

[0136] It should be noted that the current pregnancy complication risk assessment factors can assist doctors in conducting pregnancy complication risk assessment for pregnant women to be tested.

[0137] As an example, the formula for determining the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be tested may be:

[0138] ; Among them, w is the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be tested. It is to distinguish the degree of belonging of the current dimension data under the feature dimension to the reference clustering cluster. It is to distinguish the degree of belonging of the current dimension data under the feature dimension to the contrast clustering cluster.

[0139] It should be noted that when When it is larger, it often means that the pregnant woman to be tested has a higher degree of belonging to the pregnant woman with complications, which often means that the risk of complications for the pregnant woman to be tested is greater. Therefore, w can represent the risk of pregnancy complications for the pregnant woman to be tested.

[0140] refer to Figure 2 Based on the same inventive concept as the above method embodiment, the present invention provides a method for assessing the risk of pregnancy complications in high-risk pregnant women, comprising the following steps:

[0141] Step 201, obtaining current dimension data of the pregnant woman to be tested under all preset dimensions during the current pregnancy test;

[0142] Step 202, based on all current dimension data, filter out matching pregnant woman categories from all historical pregnant woman categories;

[0143] Step 203, selecting the complication-prone stage closest to the pregnancy stage corresponding to the current pregnancy examination process from the pregnancy stages of all historical pregnant women in the matching pregnant woman category as the matching complication-prone stage;

[0144] Step 204, taking the historical pregnant women who newly developed complications in the matching prone stage and the historical pregnant women who did not develop complications in the matching prone stage as reference pregnant women and comparison pregnant women, respectively, and selecting the preset dimensions that have the greatest impact on the proneness of complications in the matching prone stage as distinguishing feature dimensions;

[0145] Step 205, the historical dimension data of all reference pregnant women under the distinguishing characteristic dimension in the matching prone stage are used to form a reference cluster, and the historical dimension data of all comparison pregnant women under the distinguishing characteristic dimension in the matching prone stage are used to form a comparison cluster;

[0146] Step 206 , determining the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be detected according to the degree of belonging of the current dimension data under the distinguishing feature dimension to the reference cluster and the comparison cluster respectively.

[0147] Figure 3 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute the aforementioned method for assessing the risk of pregnancy complications for high-risk pregnant women.

[0148] Based on the same inventive concept as the above method embodiment, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the above method for assessing the risk of pregnancy complications in high-risk pregnant women.

[0149] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, the computer executes the above-mentioned method for assessing the risk of pregnancy complications in high-risk pregnant women.

[0150] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned method for assessing the risk of pregnancy complications in high-risk pregnant women.

[0151] In summary, compared with the pregnancy complication risk assessment for high-risk pregnant women based on the subjective experience of doctors, the present invention takes into account the historical pregnant women in the matching pregnant women category similar to the pregnant women to be tested when conducting pregnancy complication risk assessment for high-risk pregnant women, and screens the complication-prone stage closest to the pregnancy stage of the pregnant women to be tested, so as to facilitate the subsequent analysis of the complication susceptibility within the pregnancy stage of the pregnant women to be tested, and screen out the preset dimensions that have the greatest impact on the complication susceptibility of the matching prone stage, so as to facilitate the subsequent quantification of the current pregnancy complication risk assessment factor corresponding to the pregnant women to be tested based on the degree of attribution of the current dimensional data under the distinguishing feature dimension to the reference clustering cluster and the comparison clustering cluster, thereby assisting doctors in conducting pregnancy complication risk assessment for high-risk pregnant women, thereby improving the rationality of pregnancy complication risk assessment for high-risk pregnant women.

[0152] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A pregnancy complication risk assessment system for high-risk pregnant women, characterized in that: The system comprises: A data acquisition module is used to obtain the current dimension data of the pregnant woman to be tested under all preset dimensions during the current pregnancy examination process; Category screening module, used to screen out matching pregnant women categories from all historical pregnant women categories based on all current dimension data; A stage screening module is used to screen out the complication-prone stage closest to the gestational stage corresponding to the current pregnancy examination process from the gestational stages of all historical pregnant women in the matching pregnant woman category as the matching complication-prone stage; A division and screening module is used to select the historical pregnant women who have newly developed complications in the matching prone stage and the historical pregnant women who have not developed complications in the matching pregnant women category as reference pregnant women and comparison pregnant women, respectively, and screen out the preset dimensions that have the greatest impact on the susceptibility of complications in the matching prone stage as distinguishing feature dimensions; A cluster building module is used to form a reference cluster by combining the historical dimension data of all reference pregnant women under the distinguishing feature dimension in the matching prone stage, and to form a comparison cluster by combining the historical dimension data of all comparison pregnant women under the distinguishing feature dimension in the matching prone stage; A risk assessment factor determination module is used to determine the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be tested according to the degree of belonging of the current dimension data under the distinguishing feature dimension to the reference cluster and the comparison cluster respectively; Methods of obtaining information during the complication-prone phase include: The pregnancy stages of historical pregnant women with new complications and historical pregnant women without complications are screened out from all pregnancy stages of all historical pregnant women in the matching pregnant woman category as candidate pregnancy stages; If the number of historical pregnant women who have new complications in the candidate pregnancy stage in the matching pregnant women category is greater than the preset number, the candidate pregnancy stage is determined as a temporary pregnancy stage; According to the time interval between each two temporary pregnancy stages, a target combined factor between each two temporary pregnancy stages is determined; The interim pregnancy stages whose mutual target merging factors are greater than the preset merging threshold are regarded as complication-prone stages; The formula for the target merging factor between two interim pregnancy stages is: ； ;in, is the target merging factor between the i-th temporary pregnancy stage and the j-th temporary pregnancy stage; i and j are the serial numbers of different temporary pregnancy stages; is a natural exponential function; is the time interval between the i-th temporary pregnancy stage and the j-th temporary pregnancy stage; T represents the approximate average time interval between temporary pregnancy stages; M is the length of time corresponding to the standard complete pregnancy period; N is the number of temporary pregnancy stages.

2. A pregnancy complication risk assessment system for high-risk pregnant women according to claim 1, characterized in that: Methods for obtaining historical maternity categories include: Obtain historical dimension data of all preset dimensions obtained by pregnancy examination of each historical pregnant woman in each pregnancy stage, and form a historical data vector of each historical pregnant woman in each pregnancy stage; Initial pregnancy stage was screened out from all pregnancy stages; According to the historical data vectors of all historical pregnant women in the initial pregnancy stage, all historical pregnant women are clustered to obtain historical pregnant woman categories.

3. A pregnancy complication risk assessment system for high-risk pregnant women according to claim 1, characterized in that: Based on all current dimension data, matching pregnant women categories are screened out from all historical pregnant women categories, including: All current dimensional data are used to form a current data vector, and the pregnancy stage corresponding to the current pregnancy examination process is determined as the target pregnancy stage; Determine the mean of the historical data vectors of all historical pregnant women in each historical pregnant woman category at the target pregnancy stage as the representative vector to be matched corresponding to each historical pregnant woman category; Determine the distance between the to-be-matched representative vector corresponding to each historical pregnant woman category and the current data vector as the target distance corresponding to each historical pregnant woman category; The historical pregnant woman category with the smallest target distance is selected from all historical pregnant woman categories as the matching pregnant woman category.

4. The pregnancy complication risk assessment system for high-risk pregnant women according to claim 1, characterized in that: The method for obtaining the influence of each preset dimension on the susceptibility of complications in the matching prone stage includes: Based on the historical dimension data of all reference pregnant women and all comparison pregnant women under each preset dimension in the matching prone stage, the influence of each preset dimension on the complication susceptibility in the matching prone stage was determined.

5. A pregnancy complication risk assessment system for high-risk pregnant women according to claim 4, characterized in that: Determining the influence of each preset dimension on the susceptibility of complications in the matching prone stage according to the historical dimension data of all reference pregnant women and all comparison pregnant women in each preset dimension in the matching prone stage includes: Any preset dimension is determined as a marked dimension, and according to the historical dimension data of all reference pregnant women and all comparison pregnant women under the marked dimension in the matching prone stage, the set consisting of all reference pregnant women and all comparison pregnant women is sorted in descending order to obtain a target pregnant woman sequence; The influence degree of the marking dimension on the susceptibility of complications in the matching prone stage is determined according to the continuous occurrence of the comparison pregnant women in the target pregnant woman sequence.

6. A pregnancy complication risk assessment system for high-risk pregnant women according to claim 5, characterized in that: Determining the influence of the marking dimension on the susceptibility of complications in the matching prone stage according to the continuous occurrence of the comparison pregnant women in the target pregnant woman sequence includes: Each consecutive comparison pregnant woman in the target pregnant woman sequence is used to form a comparison pregnant woman group, thereby obtaining a comparison pregnant woman group set; The number of comparison pregnant women groups in the comparison pregnant women group set is determined as the target continuous appearance number; The number of comparison pregnant women in each comparison pregnant woman group was determined as the comparison number; According to the size of the comparison quantity, all the comparison quantities are divided into two categories, namely the first quantity category and the second quantity category; The mean of all comparison quantities in the first quantity category is determined as the first representative quantity; The mean of all comparison quantities in the second quantity class is determined as the second representative quantity; determining an absolute value of a difference between the first representative quantity and the second representative quantity as a quantity change difference; According to the number of consecutive occurrences of the target and the difference in quantity changes, the degree of influence of the marking dimension on the susceptibility of complications in the matching prone stage is determined, wherein the number of consecutive occurrences of the target is negatively correlated with the degree of influence on the susceptibility of complications, and the difference in quantity changes is positively correlated with the degree of influence on the susceptibility of complications.

7. A pregnancy complication risk assessment system for high-risk pregnant women according to claim 6, characterized in that: The corresponding formula for the influence of the marking dimension on the complication susceptibility of matching prone stages is: ; Where, f is the influence of the marking dimension on the complication susceptibility of the matching prone stage; c is the number of consecutive appearances of the target; is a natural exponential function; y is the difference in quantity change.

8. The pregnancy complication risk assessment system for high-risk pregnant women according to claim 1, characterized in that: The formula corresponding to the current pregnancy complication risk assessment factor for the pregnant woman to be tested is: ;Wherein, w is the current pregnancy complication risk assessment factor corresponding to the pregnant woman to be tested; It is to distinguish the degree of belonging of the current dimension data under the feature dimension to the reference clustering cluster; It is to distinguish the degree of belonging of the current dimension data under the feature dimension to the contrast clustering cluster.

Images