An auxiliary prediction system for premature birth risk during pregnancy

Abstract

The present invention relates to the field of biomedical technology, and more specifically to a method and system for assisting in predicting the risk of premature birth during pregnancy. The method comprises obtaining the physical data and delivery cycles of historical pregnant women, determining the degree of premature birth of the historical pregnant women based on the delivery cycles, and determining the degree of premature birth correlation of different types of physical data of the historical pregnant women based on the differences in the degree of premature birth between different historical pregnant women and the differences in the deviation changes of the same type of physical data during each physical examination. The historical pregnant women are clustered based on the deviation time differences of the same type of physical data between different historical pregnant women, and the overall correlation of each type of physical data is determined based on the number of pregnant women in the cluster and the degree of premature birth correlation of the corresponding type of physical data, thereby screening out the physical data of the target type. A premature birth prediction model is constructed based on the physical data of the target type during different physical examinations of the historical pregnant women to perform premature birth prediction. The present invention effectively improves the accuracy of premature birth prediction.

Description

Technical Field

[0001] The present invention relates to the field of biomedical technology, and in particular to a method and system for auxiliary prediction of premature birth risk during pregnancy. Background Art

[0002] Preterm birth refers to delivery before 37 weeks of gestation. The risk of premature birth is influenced by a variety of physiological, pathological, and environmental factors, including maternal health, fetal development, lifestyle, and external environment. Common risk factors include shortened cervix, pregnancy-induced hypertension or diabetes, placental abnormalities, infection (such as intrauterine infection or urinary tract infection), multiple pregnancies, a history of premature birth, and chronic psychological stress or unhealthy lifestyle habits.

[0003] Premature birth can not only lead to health problems for the fetus after birth, such as low birth weight, respiratory distress, and brain damage, but also increase the risk of childbirth for the pregnant woman. Therefore, monitoring, predicting, and intervening in the risk of premature birth are crucial for the health of both mother and child. Regular prenatal checkups, dynamic monitoring of key physiological indicators, timely identification of signs of premature birth, and necessary medical intervention can effectively reduce the incidence of premature birth and its adverse consequences.

[0004] Prior art uses a random forest method to construct a decision tree using various data from prenatal checkups, and this decision tree can be used to predict preterm birth. However, due to the presence of redundant or irrelevant features in prenatal checkup data, improper feature selection can affect model performance and lead to inaccurate predictions of preterm birth. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for auxiliary prediction of the risk of premature birth during pregnancy, which is used to solve the problem of inaccurate prediction of premature birth during pregnancy due to improper selection of prenatal examination data.

[0006] To solve the above technical problems, in a first aspect, the present invention provides a method for auxiliary prediction of premature birth risk during pregnancy, comprising the following steps:

[0007] Obtaining physical data and delivery cycles of pregnant women with different histories, wherein the physical data includes different types of physical data during each physical examination, and the gestational time of different pregnant women with different histories during the same physical examination is the same;

[0008] determining the degree of premature birth of different historical pregnant women according to the delivery cycle, and determining the deviation of different types of physical data during different physical examinations for each historical pregnant woman according to the degree of premature birth and the difference in the same type of physical data during the same physical examination between different historical pregnant women;

[0009] determining the degree of relevance of different types of physical data of each historical pregnant woman to premature birth based on the differences in the degree of premature birth between different historical pregnant women and the differences in the changes in the deviations of the same type of physical data during different physical examinations;

[0010] According to the change in the degree of deviation of the same type of physical data during different physical examinations of each historical pregnant woman, the deviation time of different types of physical data of each historical pregnant woman is determined, and according to the difference in the deviation time of the same type of physical data between different historical pregnant women, different historical pregnant women are clustered to obtain several clusters;

[0011] determining an overall correlation between different types of physical data based on the degree of relevance to premature birth of the corresponding types of physical data of all historical pregnant women in the cluster and the number of all historical pregnant women, and screening out target types of physical data from the different types of physical data based on the overall correlation;

[0012] Based on the target type of physical data of different historical pregnant women at different physical examinations, a premature birth prediction model is constructed to predict premature birth.

[0013] In conjunction with the first aspect above, in some possible implementations, determining the deviation of different types of physical data during different physical examinations of each historical pregnant woman includes:

[0014] determining a difference value of the same type of physical data during the same physical examination based on the difference of the same type of physical data during the same physical examination between each historical pregnant woman and each other historical pregnant woman;

[0015] determining the confidence level of normal delivery for each other historical pregnant woman according to the degree of premature delivery, wherein the greater the degree of premature delivery, the smaller the confidence level of normal delivery;

[0016] The cumulative value of the product of the normal delivery confidence and the physical data difference value between each historical pregnant woman and each other historical pregnant woman is determined, thereby obtaining the deviation of different types of physical data of each historical pregnant woman during different physical examinations.

[0017] In conjunction with the first aspect above, in some possible implementations, determining the relevance of different types of physical data of each historical pregnant woman to premature birth includes:

[0018] Determining the persistence of deviations of different types of physical data during different physical examinations for each historical pregnant woman based on changes in deviations of the same type of physical data during different physical examinations for each historical pregnant woman;

[0019] determining abnormality indexes of different types of physical data of each historical pregnant woman according to the degree of deviation and the degree of persistence of the deviation;

[0020] determining a preterm birth correlation index of the same type of physical data between any two historical pregnant women based on the correlation between the difference in abnormality index of the same type of physical data and the difference in degree of preterm birth between different historical pregnant women;

[0021] The preterm birth correlation index of the same type of physical data of each historical pregnant woman is integrated with that of each other historical pregnant woman to determine the preterm birth correlation degree of different types of physical data of each historical pregnant woman.

[0022] In conjunction with the first aspect above, in some possible implementations, determining the degree of persistence of deviation of different types of physical data during different physical examinations of each historical pregnant woman includes:

[0023] determining an increase in the degree of deviation of different types of physical data during each physical examination of each historical pregnant woman according to the difference in the degree of deviation of the same type of physical data between each physical examination of each historical pregnant woman and her previous physical examination;

[0024] Determine the minimum value of the deviation growth of the same type of physical data during each physical examination of each historical pregnant woman and all subsequent physical examinations, and obtain the minimum deviation growth of different types of physical data during each physical examination of each historical pregnant woman;

[0025] Determine whether the minimum deviation growth rate is greater than 0, and determine the deviation persistence of different types of physical data during different physical examinations of each historical pregnant woman based on the judgment result, wherein the deviation persistence is determined by the maximum value between the minimum deviation growth rate and 0.

[0026] In conjunction with the first aspect above, in some possible implementations, determining abnormality indexes of different types of physical data for each historical pregnant woman includes:

[0027] The cumulative value of the product value of the deviation degree and the deviation persistence degree of the same type of physical data during different physical examinations of each historical pregnant woman is determined, thereby obtaining the abnormality index of different types of physical data of each historical pregnant woman.

[0028] In conjunction with the first aspect above, in some possible implementations, determining the preterm birth-related index based on the same type of physical data between any two historical pregnant women includes:

[0029] Determine the difference in the degree of preterm birth of any two historical pregnant women with the same type of physical data to obtain a first difference value;

[0030] determining a difference in abnormality index of the same type of physical data between any two historical pregnant women to obtain a second difference value;

[0031] If the first difference value and the second difference value have different signs, the premature birth correlation index of the same type of physical data between any two historical pregnant women is set to 0; otherwise, the premature birth correlation index of the same type of physical data between any two historical pregnant women is set to 1.

[0032] In conjunction with the first aspect above, in some possible implementations, determining the deviation time of different types of physical data of each historical pregnant woman includes:

[0033] Determine the difference in the degree of deviation of the same type of physical data between each physical examination of each historical pregnant woman and her previous physical examination to obtain the degree of mutation;

[0034] Determine the maximum value of the mutation levels corresponding to the same type of physical data during each physical examination of each historical pregnant woman to obtain the maximum mutation level;

[0035] The number of physical examinations corresponding to the maximum mutation degree is determined as the deviation time of different types of physical data of each historical pregnant woman.

[0036] In conjunction with the first aspect above, in some possible implementations, determining the overall relevance of different types of body data includes:

[0037] determining an average value of the degree of relevance to premature birth of the corresponding type of physical data of all historical pregnant women in each cluster, to obtain a mean value of the degree of relevance to premature birth corresponding to each cluster;

[0038] Determining the fractional correlation corresponding to each cluster according to the number of all historical pregnant women and the mean value of the correlation degree of premature birth in each cluster, wherein both the number of all historical pregnant women and the mean value of the correlation degree of premature birth are positively correlated with the fractional correlation;

[0039] The cumulative values ​​of the sub-correlations corresponding to all the clusters of different types of body data are determined, thereby obtaining the overall correlations of different types of body data.

[0040] In conjunction with the first aspect above, in some possible implementations, constructing a premature birth prediction model to perform premature birth prediction includes:

[0041] Based on the physical data of all target types during the same physical examination of different historical pregnant women, a decision tree was constructed using the random forest method, and the constructed decision tree was used as the premature birth prediction model during the corresponding physical examination to predict premature birth.

[0042] To address the above technical issues, in a second aspect, the present invention further provides a system for assisting in predicting the risk of premature birth during pregnancy, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, causing the device to perform the method of the above-described first aspect or any possible implementation of the first aspect.

[0043] In order to solve the above technical problems, in a third aspect, the present invention also provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, enables the computer to execute the method in the above first aspect or any possible implementation of the first aspect.

[0044] In order to solve the above technical problems, in the fourth aspect, the present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code is run on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0045] The present invention has the following beneficial effects: by obtaining the physical data and delivery cycles of different historical pregnant women, the degree of premature birth of different historical pregnant women is determined according to the delivery cycle, and then the deviation of different types of physical data of each historical pregnant woman at different physical examinations is determined according to the degree of premature birth and the difference in the same type of physical data of different historical pregnant women at the same physical examination, and the deviation reflects the difference in the physical data of the premature pregnant women compared with the pregnant women with normal delivery at the same gestational time; according to the difference in the degree of premature birth between different historical pregnant women and the difference in the change in the deviation of the same type of physical data at different physical examinations, the premature birth correlation degree of different types of physical data of each historical pregnant woman is determined, and the premature birth correlation degree reflects the correlation degree between different types of physical data of pregnant women and the induction of premature birth; considering the induction of premature birth of different pregnant women Because of the difference, according to the change of the deviation degree of the same type of physical data during different physical examinations of each historical pregnant woman, the deviation time of different types of physical data of each historical pregnant woman is determined, and according to the difference in the deviation time of the same type of physical data between different historical pregnant women, different historical pregnant women are clustered to obtain several clusters; since the more pregnant women in the same cluster, the more likely the premature pregnant women in the cluster are to be caused by the same inducement, the more representative the physical data of this type is, and the degree of correlation between premature birth of all pregnant women in the cluster is large, which indicates that the overall correlation between the corresponding type of physical data and premature birth is higher, thereby screening out the target type of physical data that is overall related to premature birth among different types of physical data; finally, based on the target type of physical data during different physical examinations of different historical pregnant women, a premature birth prediction model is constructed to achieve accurate premature birth prediction. The present invention screens the physical data of different historical pregnant women to determine the target type of physical data with a higher overall correlation with premature birth, so as to construct a more accurate premature birth prediction model, effectively improving the accuracy of premature birth prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 any creative work.

[0047] Figure 1 This is a flowchart of the steps of a method for auxiliary prediction of premature birth risk during pregnancy according to an embodiment of the present invention;

[0048] Figure 2 This is a structural diagram of a system for auxiliary prediction of premature birth risk during pregnancy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to clearly illustrate the technical features of this solution, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0050] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0051] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0052] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0053] It should be noted that the concepts of "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0054] Although operations or steps are described in a particular order in the drawings in the embodiments of the present invention, this should not be understood as requiring that these operations or steps be performed in the particular order shown or in a serial order, or that all of the operations or steps shown be performed to obtain a desired result. In the embodiments of the present invention, these operations or steps may be performed serially; they may also be performed in parallel; or a portion of these operations or steps may be performed.

[0055] At the same time, it is understood that the data involved in the technical solutions of the present invention (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions. Unless otherwise defined, all technical and scientific terms used in this invention have the same meanings as those commonly understood by those skilled in the art to which this invention belongs, and all parameters or indicators in the formulas involved in this invention are normalized values ​​to eliminate dimension effects.

[0056] In order to solve the problem of poor accuracy in predicting premature birth during pregnancy due to improper selection of prenatal examination data, an embodiment of the present invention provides a method and system for auxiliary prediction of premature birth risk during pregnancy. By obtaining the physical data and delivery cycles of different historical pregnant women, the physical data of different historical pregnant women are screened to determine the target type of physical data with a higher overall correlation with premature birth, so as to construct a more accurate premature birth prediction model, thereby effectively improving the accuracy of premature birth risk prediction.

[0057] The following will describe in detail a method and system for auxiliary prediction of premature birth risk during pregnancy provided by an embodiment of the present invention in conjunction with the accompanying drawings.

[0058] Figure 1 FIG. 1 shows a basic flow chart of a method for auxiliary prediction of premature birth risk during pregnancy provided by an embodiment of the present invention. Figure 1 As shown, the method specifically includes the following steps:

[0059] Step S100: obtaining physical data and delivery cycles of different historical pregnant women, wherein the physical data includes different types of physical data during each physical examination, and the gestational time of different historical pregnant women during the same physical examination is the same.

[0060] Specifically, to facilitate subsequent risk prediction of premature birth for pregnant women, it is first necessary to obtain relevant data for constructing a premature birth prediction model. Therefore, for several historical pregnant women who have already given birth, physical examinations are performed at fixed intervals starting from 12 weeks of gestation, such as monthly or biweekly physical examinations. Different types of physical data are recorded for each historical pregnant woman during each physical examination. These physical data refer to examination data that may cause premature birth or reflect premature birth phenomena. Among them, physical data include but are not limited to blood pressure, blood sugar, weight, body fat percentage, heart rate, cervical length, frequency and intensity of uterine contractions, uterine tone, hemoglobin concentration, white blood cell count, platelet count, C-reactive protein, urine protein level, fetal weight, biparietal diameter, femur length, abdominal circumference, head circumference, fetal heart rate, and amniotic fluid index. It should be understood that since the physical examinations for different historical pregnant women are performed at the same interval starting from 12 weeks of gestation, the gestational age of different historical pregnant women at the same physical examination is the same. At the same time, the conception time and delivery time of each historical pregnant woman are recorded, and the number of weeks included in the time period from the conception time to the delivery time is determined, and the number of weeks included in the time period is used as the delivery cycle, thereby obtaining the delivery cycle of each historical pregnant woman.

[0061] It should be understood that since the risk of premature birth during pregnancy is predicted for pregnant women, in order to reduce the amount of data analysis, late-term pregnant women whose conception to delivery cycle exceeds 42 weeks can be excluded. By selecting the physical data and delivery cycles of different historical pregnant women whose delivery cycles do not exceed 42 weeks as analysis data, a premature birth prediction model can be finally constructed.

[0062] Step S200: Determine the degree of premature birth of different historical pregnant women based on the delivery cycle, and determine the deviation of different types of physical data during different physical examinations for each historical pregnant woman based on the degree of premature birth and the differences in the same type of physical data during the same physical examination between different historical pregnant women.

[0063] Specifically, when analyzing the physical data of different historical pregnant women, it is necessary to first determine the degree of preterm birth for each pregnant woman. This allows the physical data of pregnant women with low preterm births to be used as control data for the physical data of pregnant women with high preterm births. Preterm birth is generally defined as delivery before 37 weeks of gestation, so the earlier the delivery, the higher the degree of preterm birth. Therefore, the degree of preterm birth in different historical pregnant women can be determined based on the delivery cycle of different pregnant women.

[0064] Furthermore, in an embodiment of the present invention, the above-mentioned calculation formula for determining the degree of premature birth of pregnant women with different histories according to the delivery cycle is:

[0065] ;

[0066] in, Indicates the the degree of preterm birth in the historical pregnant women; Indicates the The delivery cycle of each historical pregnant woman, that is, the number of weeks from the time of conception to the time of delivery; Indicates the preset threshold for premature birth weeks. ; represents the normalization function; Represents the maximum value function.

[0067] In the above calculation formula, by The delivery cycle of the first pregnant woman was compared with the preset threshold of premature delivery weeks to determine the first The degree of premature birth of a historical pregnant woman is determined by the following equation: when the delivery cycle is less than the preset premature birth week threshold, and the greater the difference between the two, the greater the corresponding premature birth degree value.

[0068] Before premature birth occurs, some of a woman's relevant physical data will exhibit corresponding and persistent deviations compared to normal pregnant women. This deviation often reflects potential physiological or pathological issues during pregnancy and is an important signal of premature birth risk. Specifically, the degree of deviation in a woman's physical data is primarily reflected in the difference in physical examination data between a premature woman and a woman who delivered a normal pregnancy at the same time during pregnancy. The greater the difference, the greater the deviation in that type of physical data during that physical examination.

[0069] Furthermore, the above-mentioned steps of determining the deviation of different types of physical data during different physical examinations of each pregnant woman include:

[0070] Step S201: determining a difference value of the same type of physical data during physical examinations in the same gestational cycle based on the difference of the same type of physical data between each historical pregnant woman and each other historical pregnant woman during physical examinations in the same gestational cycle;

[0071] Step S202: determining the normal delivery confidence of each other historical pregnant woman according to the degree of premature delivery, wherein the greater the degree of premature delivery, the smaller the normal delivery confidence;

[0072] Step S203: Determine the cumulative value of the product of the normal delivery confidence and the physical data difference value between each historical pregnant woman and each other historical pregnant woman, so as to obtain the deviation of different types of physical data during physical examinations of different pregnancy cycles for each historical pregnant woman.

[0073] With respect to the above steps, in an embodiment of the present invention, the deviation of different types of physical data during different physical examinations of each historical pregnant woman is determined, and the corresponding calculation formula is:

[0074] ;

[0075] in, Indicates the The first pregnant woman in history The first physical examination Deviation of different types of body data; represents the total number of historical pregnant women; Indicates the the degree of preterm birth in the historical pregnant women; Indicates the The first pregnant woman in history The first physical examination Data values ​​for types of body data; Indicates the The first pregnant woman in history The first physical examination Data values ​​for types of body data; Represents the normalization function.

[0076] In the above calculation formula, according to The degree of preterm birth in pregnant women , determine the Confidence of normal delivery of historical pregnant women , thereby setting a greater confidence level for normal delivery pregnant women with less preterm birth, The first pregnant woman in history The first physical examination This type of body data is compared with other historical pregnant women with greater confidence. The first physical examination The greater the difference between the two types of body data, the The first pregnant woman in history The first physical examination The higher the deviation corresponding to the type of body data.

[0077] Step S300: Determine the degree of relevance of different types of physical data for each historical pregnant woman based on the differences in the degree of premature birth between different historical pregnant women and the differences in the changes in the deviations of the same type of physical data during different physical examinations.

[0078] Specifically, persistent deviations in a woman's physical data during pregnancy often reflect the cumulative effects of underlying issues during the pregnancy. These deviations aren't short-lived fluctuations, but rather result from a gradual imbalance of physiological or pathological factors, such as a gradual shortening of the cervix, a gradual decline in placental function, or persistent chronic inflammation or infection. Because these issues often worsen in a certain trend before premature birth, physical data can exhibit stable and persistent deviations. This deviation is manifested as increasing deviations in physical data as the number of physical examinations increases and the closer to delivery approaches. Because persistent deviations in a particular physical data point to a high likelihood of an abnormality in that data, a significant correlation between the difference in abnormal data between a particular woman and other women and the severity of preterm birth indicates a higher likelihood of that data being associated with premature birth. This allows us to determine the degree of preterm birth relevance for that particular data.

[0079] Furthermore, the above steps of determining the relevance of different types of physical data of each historical pregnant woman to premature birth include:

[0080] Step S301: determining the degree of persistence of deviation of different types of physical data during different physical examinations for each pregnant woman based on the change in the degree of deviation of the same type of physical data during different physical examinations for each pregnant woman;

[0081] Step S302: determining abnormality indexes of different types of body data of each historical pregnant woman based on the degree of deviation and the degree of persistence of the deviation;

[0082] Step S303: determining a premature birth correlation index for the same type of physical data between any two historical pregnant women based on the correlation between the differences in abnormality indexes of the same type of physical data between different historical pregnant women and the differences in the degree of premature birth;

[0083] Step S304: The premature birth correlation index of the same type of body data of each historical pregnant woman is integrated with that of each other historical pregnant woman to determine the premature birth correlation degree of different types of body data of each historical pregnant woman.

[0084] Regarding the above step S301, when the deviation of the same type of physical data during different physical examinations of each historical pregnant woman continues to increase, and the minimum degree of continuous increase of the physical data after a certain physical examination is higher, it means that the degree of continuous deviation of the physical data after the physical examination is higher.

[0085] Furthermore, in this embodiment of the present invention, determining the degree of persistence of deviation of different types of physical data during different physical examinations of each pregnant woman in the above step S301 includes:

[0086] First, based on the difference in deviation of the same type of physical data between each physical examination of each historical pregnant woman and her previous physical examination, the degree of growth of the deviation of different types of physical data at each physical examination of each historical pregnant woman is determined, that is, the difference in the deviation of the same type of physical data between each physical examination of each historical pregnant woman and her previous physical examination is determined, and the difference is used as the degree of growth of the deviation of the corresponding type of physical data at each physical examination of each historical pregnant woman.

[0087] Secondly, the minimum value of the deviation growth of the same type of physical data in each physical examination of each historical pregnant woman and all subsequent physical examinations is determined to obtain the minimum deviation growth of different types of physical data in each physical examination of each historical pregnant woman. The first pregnant woman in history The first physical examination Type of physical data, determine the The first pregnant woman in history From the first physical examination to the last physical examination The minimum value of all deviation growth degrees of the body data of this type is used as the first The first pregnant woman in history The first physical examination The minimum deviation growth rate of different types of body data.

[0088] Finally, determine whether the minimum deviation growth rate of different types of physical data during each physical examination of each historical pregnant woman is greater than 0, and determine the deviation persistence rate of different types of physical data during different physical examinations of each historical pregnant woman based on the judgment result. The deviation persistence rate is determined by the maximum value between the corresponding minimum deviation growth rate and 0.

[0089] In this embodiment of the present invention, the calculation formula for determining the degree of persistence of deviation of different types of physical data during different physical examinations of each historical pregnant woman is:

[0090] ;

[0091] in, Indicates the The first pregnant woman in history The first physical examination The degree of persistence of deviation of various types of physical data; Indicates the The first pregnant woman in history The first physical examination The minimum deviation growth degree of the first type of body data, that is, The first pregnant woman in history From the first physical examination to the last physical examination The minimum value of all deviation growth degrees of the body data of the type; Represents the maximum value function.

[0092] Regarding the above step S302, when a certain type of body data of a pregnant woman with a higher degree of deviation continues to deviate more, the more abnormal the body data of this type is, the larger the corresponding abnormality index is, and the greater the degree of premature birth is.

[0093] Furthermore, the above step S302 determines the abnormality index of different types of physical data for each historical pregnant woman, including: determining the cumulative value of the product value of the deviation and the deviation persistence of the same type of physical data during different physical examinations of each historical pregnant woman, thereby obtaining the abnormality index of different types of physical data for each historical pregnant woman. The corresponding calculation formula is:

[0094] ;

[0095] in, Indicates the The first pregnant woman in history Abnormal index of various types of physical data; Indicates the Number of examinations per pregnant woman; Indicates the The first pregnant woman in history The first physical examination The degree of persistence of deviation of various types of physical data; Indicates the The first pregnant woman in history The first physical examination The deviation of different types of body data.

[0096] In the above calculation formula, Pregnant women with a history of The greater the deviation of the physical data type and the greater the deviation, the The first pregnant woman in history The more likely a type of physical data is abnormal, the greater its corresponding abnormality index.

[0097] Regarding step S303 above, the greater the deviation of a certain type of physical data related to premature birth from normal levels, and the longer the deviation lasts, the earlier the onset of premature birth will generally be. This is because severe and long-term deviations generally reflect more serious physiological or pathological problems. For example, a significant shortening of the cervical length may indicate cervical insufficiency, and a persistent decline in placental function may lead to insufficient fetal oxygen supply or intrauterine growth restriction. When these problems accumulate to a certain extent, they can trigger uterine contractions, premature rupture of membranes, or other preterm birth triggers, forcing delivery to be earlier. Therefore, the magnitude and duration of the deviation of a pregnant woman's physical data are directly related to the increased risk of premature birth and the time of its occurrence. That is, for all pregnant women, the greater the correlation between a certain abnormal index of physical data and the degree of premature birth of the pregnant woman, the greater the degree of relevance of that physical data to premature birth.

[0098] Furthermore, the above-mentioned step S303 determines the premature birth correlation index of the same type of physical data between any two historical pregnant women, including: determining the difference in the degree of premature birth of the same type of physical data between any two historical pregnant women to obtain a first difference value; determining the difference in the abnormality index of the same type of physical data between any two historical pregnant women to obtain a second difference value; if the first difference value and the second difference value have different signs, the premature birth correlation index of the same type of physical data between any two historical pregnant women is set to 0, otherwise the premature birth correlation index of the same type of physical data between any two historical pregnant women is set to 1.

[0099] In the embodiment of the present invention, the above step S303 determines the premature birth correlation index of the same type of physical data between any two historical pregnant women, and the corresponding calculation formula is:

[0100] ;in, Indicates the The first pregnant woman in history The first pregnant woman in history Prematurity-related indices based on various types of physical data; Indicates the The first pregnant woman in history Abnormal index of various types of physical data; Indicates the The first pregnant woman in history Abnormal index of various types of physical data; Indicates the the degree of preterm birth in the historical pregnant women; Indicates the The degree of preterm birth in pregnant women with a history of premature delivery.

[0101] In the above calculation formula, if The first pregnant woman in history The first pregnant woman in history If the premature birth related index of the physical data of the first type is 1, it means that The first pregnant woman in history The first among pregnant women in history The following types of physical data are correlated with the degree of premature birth; The first pregnant woman in history The first pregnant woman in history If the premature birth related index of the physical data of the first type is 0, it means that The first pregnant woman in history The first among pregnant women in history These types of physical data were not correlated with the degree of preterm birth.

[0102] Regarding step S304 above, when a certain type of physical data shows correlation between a particular pregnant woman and other pregnant women, it indicates that the correlation level for premature birth in that type of physical data is greater for that particular pregnant woman. Therefore, by integrating the premature birth correlation index for the same type of physical data between each pregnant woman and all other pregnant women, the correlation level for each type of physical data can be determined for each pregnant woman.

[0103] Furthermore, in this embodiment of the present invention, the above step S304 determines the degree of relevance of premature birth for different types of physical data of each historical pregnant woman, and the corresponding calculation formula is:

[0104] ;

[0105] in, Indicates the The first pregnant woman in history the degree to which various types of physical data are associated with premature birth; represents the total number of historical pregnant women; Indicates the The first pregnant woman in history The first pregnant woman in history Prematurity-related indices based on three types of physical data.

[0106] Step S400: Determine the deviation time of different types of physical data of each historical pregnant woman based on the change in the deviation degree of the same type of physical data of different physical examinations of each historical pregnant woman, and cluster the different historical pregnant women based on the difference in the deviation time of the same type of physical data between different historical pregnant women to obtain several clusters.

[0107] Specifically, because different pregnant women have different triggers for premature birth, physical data that show the same degree of relevance to premature birth may also vary. For example, a higher degree of relevance to premature birth in type C physical data may only be observed in certain patients whose premature births are caused by the same trigger. However, when a specific trigger causes premature birth, pregnant women with premature births related to this trigger typically experience abnormalities in certain relevant physical data at similar stages. This is because the same trigger often follows similar pathological mechanisms. For example, pregnant women with cervical insufficiency may experience a significant shortening of the cervix in the second trimester, while pregnant women with placental dysfunction may experience fetal growth restriction or abnormal amniotic fluid volume in the third trimester. This staged consistency in the pathological mechanism makes the time periods when abnormalities in relevant physical data occur highly similar.

[0108] Based on the above analysis, according to the change in the degree of deviation of the same type of physical data in different physical examinations of each historical pregnant woman, the degree of persistence of the deviation of different types of physical data in different physical examinations of each historical pregnant woman can be determined. The process of obtaining the degree of persistence of the deviation has been described in detail in the above step S301 and will not be repeated here. When a certain type of physical data of a pregnant woman deviates continuously, it indicates that an abnormality has occurred in the physical data of that type of pregnant woman. When the degree of persistence of the deviation of a certain type of physical data suddenly increases during a physical examination of a pregnant woman, it indicates that the physical examination reflects an abnormality in the physical data of that type. Therefore, the deviation time of the physical data of that type of pregnant woman can be determined. The more similar the deviation time of a certain type of physical data of a pregnant woman is, the more likely it is that the cause of her premature birth is similar. If the degree of correlation between her premature birth is relatively high, it indicates that the overall correlation between this type of physical data and premature birth is higher.

[0109] Furthermore, the above steps of determining the deviation time of different types of physical data of each historical pregnant woman include:

[0110] Step S401: determining the difference in the degree of deviation of the same type of physical data between each physical examination of each historical pregnant woman and her previous physical examination, and obtaining the degree of mutation;

[0111] Step S402: determining the maximum value of the mutation degree corresponding to the same type of physical data during each physical examination of each historical pregnant woman, and obtaining the maximum mutation degree;

[0112] Step S403: determining the number of physical examinations corresponding to the maximum mutation degree as the deviation time of different types of physical data of each historical pregnant woman.

[0113] For the above steps, any pregnant woman in any physical examination The degree of persistence of the deviation of the physical data of this type is the same as that of the last physical examination. The difference in the degree of deviation of the physical data of the two types is recorded as the value of the first physical examination at any one time. The degree of mutation of the physical data of this type is determined by the The maximum mutation degree of the physical data of the type is obtained, and the number of physical examinations corresponding to the maximum mutation degree is recorded as the number of physical examinations of any historical pregnant woman in the first The deviation time of different types of physical data.

[0114] Based on the differences in the time of deviation of the same type of physical data among different historical pregnant women, different historical pregnant women were clustered to obtain several clusters. The more historical pregnant women in a cluster, the more likely the premature births in that cluster were caused by the same cause. The fewer historical pregnant women in a cluster, the more random the deviations in the corresponding type of physical data in that cluster were, and the less representative they were.

[0115] Furthermore, in this embodiment of the present invention, the absolute value of the difference in the time of deviation of the same type of physical data between any two different pregnant women is determined and used as a distance metric between the different pregnant women. Based on this distance metric, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm is used to cluster all the historical pregnant women, resulting in a number of clusters.

[0116] Step S500: Determine the overall correlation of different types of physical data based on the degree of correlation with premature birth of the corresponding types of physical data of all historical pregnant women in the cluster and the number of all historical pregnant women, and screen out target types of physical data from the different types of physical data based on the overall correlation.

[0117] Specifically, for several clusters corresponding to any type of physical data, the more pregnant women there are in the same cluster, the more likely the premature pregnant women in the cluster are to be caused by the same cause. This type of physical data is more representative, and the degree of correlation between premature birth and all pregnant women in the cluster is greater. This indicates that the overall correlation between the corresponding type of physical data and premature birth is higher, and this type of physical data is more able to provide a basis for predicting premature birth.

[0118] Furthermore, the above steps of determining the overall correlation of different types of body data include:

[0119] Step S501: determining the average value of the degree of relevance of premature birth of the corresponding type of physical data of all historical pregnant women in each cluster, to obtain the mean value of the degree of relevance of premature birth corresponding to each cluster;

[0120] Step S502: determining the fractional correlation corresponding to each cluster based on the number of all historical pregnant women and the mean value of the correlation degree of premature birth in each cluster, wherein both the number of all historical pregnant women and the mean value of the correlation degree of premature birth are positively correlated with the fractional correlation;

[0121] Step S503: Determine the cumulative value of the sub-correlations corresponding to all the clusters of different types of body data, so as to obtain the overall correlation of different types of body data.

[0122] With respect to the above steps, in an embodiment of the present invention, the overall correlation of different types of body data is determined, and the corresponding calculation formula is:

[0123] ;

[0124] in, Indicates the The overall correlation of various types of physical data; Indicates the The total number of clusters of each type of body data; Indicates the Type of physical data The number of historical pregnancies in each cluster; Indicates the Type of physical data All historical pregnant women in the cluster Mean correlation between preterm birth and various types of physical data; Represents the normalization function.

[0125] In the above calculation formula, by The number of historical pregnant women in each cluster of the body data of each type is normalized as the first number of all historical pregnant women in each cluster. The weights of the mean values ​​of premature birth correlation of the various types of body data are calculated, and the weighted correlations of the mean values ​​of premature birth correlation of each cluster are accumulated to obtain the first The overall correlation of the body data of the first type is greater. The more likely a type of physical data is related to premature birth, the more it should be used as a reference data for predicting premature birth.

[0126] A correlation threshold is pre-set. The specific value of the correlation threshold can be selected as needed. In the embodiment of the present invention, the correlation threshold is set to 0.7. The overall correlation of different types of body data is compared with the correlation threshold. If the overall correlation is greater than the correlation threshold, the corresponding type of body data is selected as the target type of body data. In this way, all target type of body data can be screened from different types of body data based on the overall correlation.

[0127] Step S600: constructing a premature birth prediction model based on the target type of physical data of different historical pregnant women during different physical examinations to perform premature birth prediction.

[0128] Specifically, based on all the target physical data from the same physical examinations for all pregnant women, combined with the birth cycles of all the pregnant women, a random forest was used to construct a decision tree for each physical examination. This constructed decision tree serves as a model for predicting premature birth for each physical examination. Because the specific implementation process of constructing the decision tree is well-known, it will not be detailed here.

[0129] When a premature birth prediction is required for a pregnant woman, all target types of physical data of the pregnant woman are obtained and input into a premature birth prediction model corresponding to the number of physical examinations, i.e., a decision tree. The decision tree is used to predict premature birth and ultimately obtain the corresponding premature birth prediction result. Since the specific implementation process of using a decision tree for prediction and obtaining the prediction result also belongs to the prior art, it will not be described in detail here. It should be understood that since the gestational age of the pregnant woman can be determined, and each physical examination corresponds to a gestational age, a premature birth prediction model corresponding to the number of physical examinations of the pregnant woman can be determined.

[0130] Based on the same inventive concept, the embodiment of the present invention also provides an auxiliary prediction system for the risk of premature birth during pregnancy, such as Figure 2 As shown, the prediction system includes: a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and running on the processor 202, wherein when the processor 202 executes the computer program 203, the system can execute any of the aforementioned auxiliary prediction methods for the risk of premature birth during pregnancy.

[0131] In embodiments of the present invention, the system can be divided into functional modules based on the above-described method examples. For example, these modules can correspond to individual functional modules, or two or more functions can be integrated into a single processing module. The integrated modules can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0132] Based on the same inventive concept, an embodiment of the present invention also provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute any one of the aforementioned auxiliary prediction methods for the risk of premature birth during pregnancy.

[0133] Based on the same inventive concept, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the aforementioned auxiliary prediction methods for the risk of premature birth during pregnancy.

[0134] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A system for assisting in predicting the risk of premature birth during pregnancy, characterized in that: The system comprises a memory, a processor, and an executable computer program stored in the memory and runnable on the processor, wherein when the processor executes the computer program, the following steps are performed: Obtaining physical data and delivery cycles of pregnant women with different histories, wherein the physical data includes different types of physical data during each physical examination, and the gestational time of different pregnant women with different histories during the same physical examination is the same; determining the degree of premature birth of different historical pregnant women according to the delivery cycle, and determining the deviation of different types of physical data during different physical examinations for each historical pregnant woman according to the degree of premature birth and the difference in the same type of physical data during the same physical examination between different historical pregnant women; Determining the degree of relevance of different types of physical data of each historical pregnant woman based on the differences in the degree of premature birth between different historical pregnant women and the differences in the changes in the deviations of the same type of physical data at different physical examinations, including: determining the degree of persistence of deviation of different types of physical data of each historical pregnant woman at different physical examinations based on the changes in the deviations of the same type of physical data at different physical examinations; determining the abnormality index of different types of physical data of each historical pregnant woman based on the deviations and the persistence of the deviations; determining the premature birth relevance index of the same type of physical data between any two historical pregnant women based on the correlation between the differences in the abnormality indexes of the same type of physical data and the differences in the degree of premature birth between different historical pregnant women; and determining the degree of relevance of different types of physical data of each historical pregnant woman by fusing the premature birth relevance index of the same type of physical data between each historical pregnant woman and each other historical pregnant woman. Determine the deviation time of different types of physical data of each historical pregnant woman based on the change in the degree of deviation of the same type of physical data during different physical examinations of each historical pregnant woman, and cluster the different historical pregnant women based on the difference in the deviation time of the same type of physical data between different historical pregnant women to obtain a plurality of clusters; wherein, determining the deviation time of different types of physical data of each historical pregnant woman includes: determining the difference in the degree of deviation of the same type of physical data between each physical examination of each historical pregnant woman and her previous physical examination to obtain the mutation degree; determining the maximum value of the mutation degrees corresponding to the same type of physical data during each physical examination of each historical pregnant woman to obtain the maximum mutation degree; and determining the number of physical examinations corresponding to the maximum mutation degree as the deviation time of different types of physical data of each historical pregnant woman; determining an overall correlation between different types of physical data based on the degree of relevance to premature birth of the corresponding types of physical data of all historical pregnant women in the cluster and the number of all historical pregnant women, and screening out target types of physical data from the different types of physical data based on the overall correlation; Based on the target type of physical data from different physical examinations of different historical pregnant women, a premature birth prediction model is constructed to predict premature birth; The corresponding calculation formula for determining the deviation of different types of physical data during different physical examinations of each historical pregnant woman is: ； in, Indicates the The first pregnant woman in history The first physical examination Deviation of different types of body data; represents the total number of historical pregnant women; Indicates the the degree of preterm birth in the historical pregnant women; Indicates the The first pregnant woman in history The first physical examination Data values ​​for types of body data; Indicates the The first pregnant woman in history The first physical examination Data values ​​for types of body data; represents the normalization function; Determine the degree of persistence of deviation of different types of physical data during different physical examinations of each historical pregnant woman. The corresponding calculation formula is: ； in, Indicates the The first pregnant woman in history The first physical examination The degree of persistence of deviation of various types of physical data; Indicates the The first pregnant woman in history The first physical examination The minimum deviation growth degree of the first type of body data, that is, The first pregnant woman in history From the first physical examination to the last physical examination The minimum value of all deviation growth degrees of the body data of the type; Represents the maximum value function.

2. The system for auxiliary prediction of premature birth risk during pregnancy according to claim 1, characterized in that: Determine the deviation of different types of physical data at different physical examinations for each historical pregnant woman, including: determining a difference value of the same type of physical data during the same physical examination based on the difference of the same type of physical data during the same physical examination between each historical pregnant woman and each other historical pregnant woman; determining the confidence level of normal delivery for each other historical pregnant woman according to the degree of premature delivery, wherein the greater the degree of premature delivery, the smaller the confidence level of normal delivery; The cumulative value of the product of the normal delivery confidence and the physical data difference value between each historical pregnant woman and each other historical pregnant woman is determined, thereby obtaining the deviation of different types of physical data of each historical pregnant woman during different physical examinations.

3. The system for auxiliary prediction of premature birth risk during pregnancy according to claim 1, characterized in that: Determine the degree of persistence of deviations in different types of physical data at different physical examinations for each historical pregnant woman, including: determining an increase in the degree of deviation of different types of physical data during each physical examination of each historical pregnant woman according to the difference in the degree of deviation of the same type of physical data between each physical examination of each historical pregnant woman and her previous physical examination; Determine the minimum value of the deviation growth of the same type of physical data during each physical examination of each historical pregnant woman and all subsequent physical examinations, and obtain the minimum deviation growth of different types of physical data during each physical examination of each historical pregnant woman; Determine whether the minimum deviation growth rate is greater than 0, and determine the deviation persistence of different types of physical data during different physical examinations of each historical pregnant woman based on the judgment result, wherein the deviation persistence is determined by the maximum value between the minimum deviation growth rate and 0.

4. The system for auxiliary prediction of premature birth risk during pregnancy according to claim 1, characterized in that: Determine the abnormality index of different types of physical data for each historical pregnant woman, including: The cumulative value of the product value of the deviation degree and the deviation persistence degree of the same type of physical data during different physical examinations of each historical pregnant woman is determined, thereby obtaining the abnormality index of different types of physical data of each historical pregnant woman.

5. The system for auxiliary prediction of premature birth risk during pregnancy according to claim 1, characterized in that: Determine the preterm birth-related index between any two historical pregnancies with the same type of physical data, including: Determine the difference in the degree of preterm birth of any two historical pregnant women with the same type of physical data to obtain a first difference value; determining a difference in abnormality index of the same type of physical data between any two historical pregnant women to obtain a second difference value; If the first difference value and the second difference value have different signs, the premature birth correlation index of the same type of physical data between any two historical pregnant women is set to 0; otherwise, the premature birth correlation index of the same type of physical data between any two historical pregnant women is set to 1.

6. The system for auxiliary prediction of premature birth risk during pregnancy according to claim 1, characterized in that: Determine the overall relevance of different types of body data, including: determining an average value of the degree of relevance to premature birth of the corresponding type of physical data of all historical pregnant women in each cluster, to obtain a mean value of the degree of relevance to premature birth corresponding to each cluster; Determining the fractional correlation corresponding to each cluster according to the number of all historical pregnant women and the mean value of the correlation degree of premature birth in each cluster, wherein both the number of all historical pregnant women and the mean value of the correlation degree of premature birth are positively correlated with the fractional correlation; The accumulated values ​​of the sub-correlations corresponding to all the clusters of different types of body data are determined, thereby obtaining the overall correlations of different types of body data.

7. The system for auxiliary prediction of premature birth risk during pregnancy according to claim 1, characterized in that: Constructing a premature birth prediction model to predict premature birth, including: Based on the physical data of all target types during the same physical examination of different historical pregnant women, a decision tree was constructed using the random forest method, and the constructed decision tree was used as the premature birth prediction model during the corresponding physical examination to predict premature birth.

Images