Pregnancy disease risk prediction method and device based on biochemical indexes and program product

Abstract

The invention relates to the field of intelligent medical treatment, in particular to a pregnancy disease risk prediction method and device based on biochemical indexes and a program product. Comprising the following steps: S1, acquiring serum biochemical index data of a pregnant woman; s2, comparing the serum biochemical indexes with a preset threshold value; the serum biochemical indexes include aspartate aminotransferase, total protein, albumin, lactic dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood sugar, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chlorine, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol and homocysteine. When one or more of the myoglobin, the hypersensitive troponin I, the prealbumin, the cystatin C and the creatine kinase isoenzyme MB are abnormal, judging that the pregnancy eclampsia exists. The method is simple, convenient and rapid to operate and low in cost, can be clinically popularized to predict the health state of the pregnant woman on a large scale, and has good clinical value.

Description

Technical Field

[0001] This application relates to the field of intelligent healthcare, and specifically to a method, device, program product, and computer-readable storage medium for predicting the risk of pregnancy diseases based on biochemical indicators. Background Art

[0002] During pregnancy, a series of diseases such as pregnancy-induced hypertension, eclampsia, and threatened abortion may occur. Clinically, it is difficult to estimate the development stage in a timely manner and take symptomatic treatment. Existing technologies generally measure the blood pressure of pregnant women through a sphygmomanometer, but there is little intervention in the early stage of pregnancy-induced hypertension. Eclampsia is judged through a proteomics model and immunoassay, but this method takes a long time and has a high detection cost, so the penetration rate is low. When it develops to the clinical manifestations of threatened abortion, irreversible harm has been caused to the pregnant woman and the fetus. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method for predicting the risk of pregnancy diseases based on biochemical indicators, specifically including:

[0004] S1. Obtain the serum biochemical index data of a pregnant woman;

[0005] S2. Compare the serum biochemical indicators with a preset threshold. When one or more of aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chloride, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, hypersensitive cardiac troponin I, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indicators are abnormal, it is determined that eclampsia exists.

[0006] The abnormality is that the serum biochemical indicator is greater than or less than the preset threshold;

[0007] Optionally, S2 is replaced by: inputting the serum biochemical indicators into a first prediction model for prediction to obtain a prediction result of whether it is eclampsia;

[0008] Optionally, the training process of the first prediction model is:

[0009] Obtain a dataset and labels of serum biochemical indicators of pregnant women;

[0010] Input the dataset and labels into the first prediction model for training until the loss function remains unchanged to obtain the first prediction model;

[0011] Optionally, the labels include normal labels of each biochemical indicator and labels of each biochemical indicator of eclampsia.

[0012] S2 is replaced with: comparing the serum biochemical indexes with preset thresholds, and when one or more of alanine aminotransferase, gamma-glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, it is determined that pregnancy-induced hypertension exists.

[0013] S2 is replaced with: inputting the serum biochemical indexes into a second prediction model for prediction to obtain a prediction result of whether it is pregnancy-induced hypertension;

[0014] Optionally, the training process of the second prediction model is as follows:

[0015] Obtain a dataset and labels of pregnant women's serum biochemical indexes;

[0016] Input the dataset and labels into the second prediction model for training until the loss function remains unchanged to obtain the second prediction model;

[0017] Optionally, the labels include normal labels of each biochemical index and labels of each biochemical index of pregnancy-induced hypertension.

[0018] S2 is replaced with: comparing the serum biochemical indexes with preset thresholds, and when one or more of total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, and high-density lipoprotein cholesterol in the serum biochemical indexes are abnormal, it is determined that threatened abortion exists;

[0019] Optionally, S2 is replaced with: inputting the serum biochemical indexes into a third prediction model for prediction to obtain a prediction result of whether it is threatened abortion;

[0020] Optionally, the training process of the third prediction model is as follows:

[0021] Obtain a dataset and labels of pregnant women's serum biochemical indexes;

[0022] Input the dataset and labels into the third prediction model for training until the loss function remains unchanged to obtain the first prediction model;

[0023] Optionally, the labels include normal labels of each biochemical index and labels of each biochemical index of threatened abortion.

[0024] The S2 is replaced with: comparing the serum biochemical indexes with preset thresholds, and when aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chloride, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, predicting preeclampsia;

[0025] When alanine aminotransferase, gamma-glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, predicting gestational hypertension;

[0026] When total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, and high-density lipoprotein cholesterol in the serum biochemical indexes are abnormal, predicting threatened abortion.

[0027] The S2 is replaced with: inputting the serum biochemical indexes into a fourth prediction model for classification prediction to obtain a prediction result of whether there is a pregnancy disease; the pregnancy diseases include preeclampsia, gestational hypertension, and threatened abortion;

[0028] Optionally, the training process of the fourth prediction model is as follows:

[0029] Obtain a dataset of pregnant women's serum biochemical indexes and labels;

[0030] Input the dataset and labels into the fourth prediction model for training until the loss function remains unchanged to obtain the fourth prediction model;

[0031] Optionally, the labels include normal labels of each biochemical index and labels of each biochemical index of pregnancy diseases.

[0032] The object of the present invention is to provide a computer program product, which includes a computer program or instruction, and the computer program or instruction is executed by a processor to implement the above-mentioned pregnancy disease risk prediction method based on biochemical indexes.

[0033] The object of the present invention is to provide a computer device, which includes a memory, a processor, and a computer program or instruction stored on the memory, and the computer program or instruction is executed by the processor to implement the above-mentioned pregnancy disease risk prediction method based on biochemical indexes.

[0034] The objective of the present invention is to provide a computer-readable storage medium with a computer program or instructions stored thereon, and the computer program or instructions are executed by a processor to implement the above-mentioned pregnancy disease risk prediction method based on biochemical indicators.

[0035] Advantages of the present invention:

[0036] 1. Pregnancy-induced hypertension, pregnancy eclampsia, and threatened abortion are a series of diseases during the clinical pregnancy process. The states of these three diseases are combined or transformed into each other, making it difficult to estimate their development stages in a timely manner. Moreover, pregnancy diseases at different stages cause different harms to pregnant women and fetuses. Therefore, the present invention proposes a prediction scheme for pregnancy diseases at different stages. In the present invention, the disease prediction for pregnant women during pregnancy is carried out through biochemical index data, which is simple to operate and low in cost. In addition, only biochemical indicators are used in the pregnancy disease prediction method of the present invention, and biochemical indicators are examination items that can be carried out in any hospital. The pregnancy disease prediction method of the present invention has practical clinical application value and can be popularized on a large scale.

[0037] 2. The present invention separately proposes corresponding predictive biochemical indicators for different pregnancy diseases, and performs separate predictions for pregnancy-induced hypertension, pregnancy eclampsia, and threatened abortion or comprehensive predictions for pregnancy-induced hypertension, eclampsia, and threatened abortion through the corresponding biochemical indicators. The method of the present invention can quickly detect and obtain prediction results within several hours, which helps to detect pregnancy diseases early, enables doctors to diagnose the health risks of pregnant women, and reduces the risks of pregnant women and fetuses. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0039] Figure 1 It is a schematic flowchart of the pregnancy disease risk prediction method based on biochemical indicators provided by an embodiment of the present invention;

[0040] Figure 2 It is a schematic diagram of the pregnancy disease risk prediction system based on biochemical indicators provided by an embodiment of the present invention;

[0041] Figure 3 It is a schematic diagram of the pregnancy disease risk prediction device based on biochemical indicators provided by an embodiment of the present invention;

[0042] Figure 4 It is a box plot of aspartate aminotransferase and alanine aminotransferase in pregnancy diseases provided by an embodiment of the present invention, where ABCD represent normal, eclampsia, hypertension, and threatened abortion in sequence;

[0043] Figure 5 The box plot of albumin and total protein provided by the embodiments of the present invention in pregnancy diseases, where A, B, C, and D represent normal, eclampsia, hypertension, and threatened abortion in sequence;

[0044] Figure 6 The box plot of total bilirubin and bilirubin provided by the embodiments of the present invention in pregnancy diseases;

[0045] Figure 7 The box plot of lactate dehydrogenase and gamma-glutamyl transpeptidase provided by the embodiments of the present invention in pregnancy diseases;

[0046] Figure 8 The box plot of alkaline phosphatase and total bile acid provided by the embodiments of the present invention in pregnancy diseases;

[0047] Figure 9 The box plot of creatine kinase and blood glucose provided by the embodiments of the present invention in pregnancy diseases;

[0048] Figure 10 The box plot of urea nitrogen and uric acid provided by the embodiments of the present invention in pregnancy diseases;

[0049] Figure 11 The box plot of creatinine and glomerular filtration rate provided by the embodiments of the present invention in pregnancy diseases;

[0050] Figure 12 The box plot of potassium and sodium provided by the embodiments of the present invention in pregnancy diseases;

[0051] Figure 13 The box plot of chloride and total calcium provided by the embodiments of the present invention in pregnancy diseases;

[0052] Figure 14 The box plot of serum magnesium and inorganic phosphorus provided by the embodiments of the present invention in pregnancy diseases;

[0053] Figure 15 The box plot of serum iron and total cholesterol provided by the embodiments of the present invention in pregnancy diseases;

[0054] Figure 16 The box plot of triglyceride and high-density lipoprotein cholesterol provided by the embodiments of the present invention in pregnancy diseases;

[0055] Figure 17 The box plot of low-density lipoprotein cholesterol and homocysteine provided by the embodiments of the present invention in pregnancy diseases;

[0056] Figure 18 The box plot of myoglobin and creatine kinase isoenzyme MB provided by the embodiments of the present invention in pregnancy diseases;

[0057] Figure 19 The box plot of prealbumin and cystatin C in pregnancy diseases provided by the embodiments of the present invention. Specific embodiments

[0058] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0059] In some processes described in the specification and claims of the present invention and the above-mentioned drawings, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as S101, S102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent the sequence, nor do they limit that "first" and "second" are of different types.

[0060] Figure 1 The schematic diagram of the pregnancy disease risk prediction method based on biochemical indexes provided by the embodiments of the present invention specifically includes:

[0061] S1: Obtain the serum biochemical index data of the pregnant woman;

[0062] In one embodiment, the serum biochemical index data is the full item of biochemical indexes, including: alanine aminotransferase, aspartate aminotransferase, total protein, albumin, total bilirubin, direct bilirubin, lactate dehydrogenase, gamma-glutamyl transpeptidase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, sodium, chloride, total calcium, serum magnesium, inorganic phosphorus, serum iron, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, hypersensitive cardiac troponin I, prealbumin, cystatin C, creatine kinase isoenzyme MB.

[0063] S2: Compare the serum biochemical indexes with a preset threshold. When one or more of aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chloride, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, hypersensitive cardiac troponin I, prealbumin, cystatin C, creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, it is determined that pregnancy eclampsia exists.

[0064] In one embodiment, the abnormality is greater than a preset threshold or less than a preset threshold in serum biochemical indexes. The preset threshold is a numerical value or a numerical range in the normal state of the biochemical index. The serum biochemical indexes are compared with the preset thresholds of each biochemical index to obtain the abnormal biochemical index items.

[0065] In one embodiment, the serum biochemical indexes are compared with the preset thresholds. When aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chlorine, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, hypersensitive cardiac troponin I, prealbumin, cystatin C, creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, it is determined that pregnancy-induced eclampsia exists.

[0066] In one embodiment, S2 is replaced with: The serum biochemical indexes are input into a first prediction model for prediction to obtain a prediction result of whether it is pregnancy-induced eclampsia.

[0067] In one embodiment, the training process of the first prediction model is as follows:

[0068] Obtain a dataset and labels of pregnant women's serum biochemical indexes;

[0069] The dataset and labels are input into the first prediction model for training until the loss function remains unchanged to obtain the first prediction model;

[0070] Optionally, the labels include normal labels of each biochemical index and labels of each biochemical index of pregnancy-induced eclampsia.

[0071] In one embodiment, S2 is replaced with: The serum biochemical indexes are compared with the preset thresholds. When alanine aminotransferase, gamma-glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal in one or more of them, it is determined that pregnancy-induced hypertension exists.

[0072] In one embodiment, the serum biochemical indexes are compared with the preset thresholds. When alanine aminotransferase, gamma-glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, creatine kinase isoenzyme MB in the serum biochemical indexes, it is determined that pregnancy-induced hypertension exists.

[0073] In one embodiment, S2 is replaced with: inputting the serum biochemical indexes into a second prediction model for prediction to obtain a prediction result of whether it is pregnancy-induced hypertension.

[0074] In one embodiment, the training process of the second prediction model is as follows:

[0075] Obtain a dataset and labels of pregnant women's serum biochemical indexes;

[0076] Input the dataset and labels into the second prediction model for training until the loss function remains unchanged to obtain the second prediction model.

[0077] Optionally, the labels include normal labels of various biochemical indexes and labels of various biochemical indexes of pregnancy-induced hypertension.

[0078] In one embodiment, S2 is replaced with: comparing the serum biochemical indexes with a preset threshold, and when one or more of total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, and high-density lipoprotein cholesterol in the serum biochemical indexes are abnormal, it is determined that there is threatened abortion.

[0079] In one embodiment, the serum biochemical indexes are compared with a preset threshold, and when total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, and high-density lipoprotein cholesterol in the serum biochemical indexes are abnormal, it is determined that there is threatened abortion.

[0080] In one embodiment, S2 is replaced with: inputting the serum biochemical indexes into a third prediction model for prediction to obtain a prediction result of whether it is threatened abortion.

[0081] In one embodiment, the training process of the third prediction model is as follows:

[0082] Obtain a dataset and labels of pregnant women's serum biochemical indexes;

[0083] Input the dataset and labels into the third prediction model for training until the loss function remains unchanged to obtain the first prediction model;

[0084] Optionally, the labels include normal labels of various biochemical indexes and labels of various biochemical indexes of threatened abortion.

[0085] In one embodiment, S2 is replaced with: comparing the serum biochemical indexes with preset thresholds, and when aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chlorine, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, predicting preeclampsia;

[0086] When alanine aminotransferase, gamma-glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, predicting pregnancy-induced hypertension;

[0087] When total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, and high-density lipoprotein cholesterol in the serum biochemical indexes are abnormal, predicting threatened abortion.

[0088] In one embodiment, S2 is replaced with: inputting the serum biochemical indexes into a fourth prediction model for classification prediction to obtain a prediction result of whether there is a pregnancy disease and the type of pregnancy disease; the types of pregnancy diseases include preeclampsia, pregnancy-induced hypertension, and threatened abortion.

[0089] In one embodiment, the training process of the fourth prediction model is as follows:

[0090] Obtain a dataset and labels of pregnant women's serum biochemical indexes;

[0091] Input the dataset and labels into the fourth prediction model for training until the loss function remains unchanged to obtain the fourth prediction model;

[0092] Optionally, the labels include normal labels of each biochemical index and labels of each biochemical index of pregnancy diseases.

[0093] In one embodiment, input the biochemical index data of pregnant women into the fourth prediction model for prediction, or compare the biochemical indexes of pregnant women with the indexes of pregnancy diseases, and the obtained pregnancy disease results include preeclampsia, pregnancy-induced hypertension, threatened abortion, pregnancy-induced hypertension complicated with preeclampsia, pregnancy-induced hypertension complicated with threatened abortion, and preeclampsia complicated with threatened abortion, and assist in diagnosis or treatment through the pregnancy disease results.

[0094] In one embodiment, the fourth model concurrently performs predictions on whether the indicators of pregnancy-induced eclampsia, pregnancy-induced hypertension, and threatened abortion are normal or abnormal, and outputs multiple prediction results when multiple pregnancy diseases are satisfied.

[0095] In one embodiment, S2 is replaced with: inputting the serum biochemical indicators into a mathematical model for calculation to obtain a prediction result of the pregnancy health type. The pregnancy health types include normal, pregnancy-induced eclampsia, pregnancy-induced hypertension, and threatened abortion; the mathematical model includes the biochemical indicators of the pregnancy health type. When the biochemical indicators of the pregnant woman to be tested are input into the mathematical model, by comparing the values of the biochemical indicators of the pregnant woman to be tested with the biochemical indicators of the pregnancy health type in the mathematical model, when one or more of the pregnancy health types are satisfied, the result of the satisfied pregnancy health type is output. For example, when the full-term values of the biochemical indicators of the pregnant woman to be tested are input into the mathematical model, the full-term indicators are compared in parallel with the preset normal biochemical indicators, the preset pregnancy-induced hypertension biochemical indicators, the preset pregnancy-induced eclampsia biochemical indicators, and the preset threatened abortion biochemical indicators in the mathematical model. When the conditions are satisfied, the result is output. This solution of the present invention can quickly and simply obtain the health status of pregnant women, and at the same time, it can also be used as a means to exclude pregnancy diseases of pregnant women, and has good application value.

[0096] Among them, the preset pregnancy-induced hypertension biochemical indicators include alanine aminotransferase, glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB;

[0097] The preset pregnancy-induced eclampsia biochemical indicators include: aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chloride, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB;

[0098] The preset threatened abortion biochemical indicators include total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, and high-density lipoprotein cholesterol.

[0099] In a specific embodiment, the biochemical indicators of the pregnant woman's serum are detected by chemiluminescence method, the biochemical test results of pregnant women in different health states are analyzed, a model is established, and the biochemical test results of pregnant women are quickly classified to judge the health status of pregnant women. Data analysis is performed on the biochemical indicators of pregnant women, and the box plots of each indicator are as Figure 4-19As shown in the figure, the two lines parallel to the abscissa in the figure respectively represent the upper and lower marginal values of the normal values of biochemical indicators. For example, the upper marginal value of the normal value of alanine aminotransferase is 34, and the lower marginal value is 5. The biochemical test results of pregnant women in different health states are shown in Table 1.

[0100] Table 1

[0101]

[0102] Note: Label 1 represents a significant difference (P < 0.05).

[0103] In one embodiment, the normal values of biochemical indicators are obtained through statistical analysis of normal sample data. Under the change of material conditions for people in different eras, the hormone content indicators in the human body will shift, and the formulation of the normal value range will change. The normal values in the present invention include the normal values formulated for people in different eras.

[0104] The disclosed embodiment of the present invention also provides a computer program product or system, including a computer program, which when executed by a processor implements the steps of the above-mentioned pregnancy disease risk prediction method based on biochemical indicators.

[0105] Figure 2 The schematic diagram of the pregnancy disease risk prediction system based on biochemical indicators provided by the embodiment of the present invention specifically includes:

[0106] Acquisition unit: Acquire the serum biochemical indicator data of pregnant women;

[0107] Prediction unit: Compare the serum biochemical indicators with a preset threshold. When one or more of aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chloride, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, hypersensitive cardiac troponin I, prealbumin, cystatin C, creatine kinase isoenzyme MB in the serum biochemical indicators are abnormal, it is determined that pregnancy pre-eclampsia exists.

[0108] Figure 3 The schematic diagram of the pregnancy disease risk prediction device based on biochemical indicators provided by the embodiment of the present invention specifically includes:

[0109] A memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, any one of the above-mentioned pregnancy disease risk prediction methods based on biochemical indicators.

[0110] The disclosed embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned pregnancy disease risk prediction methods based on biochemical indicators.

[0111] The verification results of this verification embodiment show that assigning fixed weights to indications can improve the performance of this method compared to the default settings. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium can include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk, or optical disc, etc.

[0112] Those of ordinary skill in the art can understand that all or part of the steps in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be read-only memory, magnetic disk, or optical disc, etc.

[0113] The above has introduced in detail a computer device provided by the present invention. For those of ordinary skill in the art, according to the idea of the embodiments of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for predicting the risk of pregnancy diseases based on biochemical indicators, characterized in that, Including: S1. Obtain the serum biochemical index data of the pregnant woman; S2. Compare the serum biochemical indexes with preset thresholds. When one or more of aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chloride, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, hypersensitive cardiac troponin I, prealbumin, cystatin C, creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, it is determined that pregnancy-induced eclampsia exists.

2. The method for predicting the risk of pregnancy diseases based on biochemical indicators according to claim 1, wherein The abnormality is that the serum biochemical index is greater than or less than the preset threshold; Optionally, S2 is replaced with: Input the serum biochemical indexes into the first prediction model for prediction to obtain the prediction result of whether it is pregnancy-induced eclampsia; Optionally, the training process of the first prediction model is: Obtain the pregnant woman's serum biochemical index data set and labels; Input the data set and labels into the first prediction model for training until the loss function remains unchanged to obtain the first prediction model; Optionally, the labels include the normal labels of each biochemical index and the labels of each biochemical index of pregnancy-induced eclampsia.

3. The method for predicting the risk of pregnancy diseases based on biochemical indexes according to claim 1, wherein, S2 is replaced with: Compare the serum biochemical indexes with preset thresholds. When one or more of alanine aminotransferase, gamma-glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, it is determined that pregnancy-induced hypertension exists.

4. The method for predicting the risk of pregnancy diseases based on biochemical indicators according to claim 1, wherein, S2 is replaced with: Input the serum biochemical indexes into the second prediction model for prediction to obtain the prediction result of whether it is pregnancy-induced hypertension; Optionally, the training process of the second prediction model is: Obtain the pregnant woman's serum biochemical index data set and labels; Input the data set and labels into the second prediction model for training until the loss function remains unchanged to obtain the second prediction model; Optionally, the labels include the normal labels of each biochemical index and the labels of each biochemical index of pregnancy-induced hypertension.

5. The method for predicting the risk of pregnancy diseases based on biochemical indicators according to claim 1, wherein S2 is replaced with: Compare the serum biochemical indexes with preset thresholds. When one or more of total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, high-density lipoprotein cholesterol in the serum biochemical indexes are abnormal, it is determined that threatened abortion exists. Optionally, S2 is replaced with: Input the serum biochemical indexes into the third prediction model for prediction to obtain the prediction result of whether it is threatened abortion; Optionally, the training process of the third prediction model is: Obtain the pregnant woman's serum biochemical index data set and labels; Input the data set and labels into the third prediction model for training until the loss function remains unchanged to obtain the first prediction model; Optionally, the labels include the normal labels of each biochemical index and the labels of each biochemical index of threatened abortion.

6. The method for predicting the risk of pregnancy diseases based on biochemical indexes according to claim 1, wherein The S2 is replaced with: comparing the serum biochemical indexes with preset thresholds, and predicting as pregnancy eclampsia when aspartate aminotransferase, total protein, albumin, lactate dehydrogenase, alkaline phosphatase, total bile acid, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, potassium, chloride, total calcium, serum magnesium, inorganic phosphorus, total cholesterol, triglyceride, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal; When alanine aminotransferase, gamma-glutamyl transpeptidase, creatine kinase, blood glucose, urea nitrogen, uric acid, creatinine, glomerular filtration rate, sodium, inorganic phosphorus, serum iron, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, homocysteine, myoglobin, prealbumin, cystatin C, and creatine kinase isoenzyme MB in the serum biochemical indexes are abnormal, predicting as pregnancy-induced hypertension; When total bilirubin, lactate dehydrogenase, alkaline phosphatase, blood glucose, glomerular filtration rate, serum iron, and high-density lipoprotein cholesterol in the serum biochemical indexes are abnormal, predicting threatened abortion.

7. The method for predicting the risk of pregnancy diseases based on biochemical indicators according to claim 1, characterized in that The S2 is replaced with: inputting the serum biochemical indexes into a fourth prediction model for classification prediction to obtain a prediction result of whether there is a pregnancy disease; the pregnancy disease includes pregnancy eclampsia, pregnancy-induced hypertension, and threatened abortion; Optionally, the training process of the fourth prediction model is as follows: Obtaining a dataset of pregnant women's serum biochemical indexes and labels; Inputting the dataset and labels into the fourth prediction model for training until the loss function remains unchanged to obtain the fourth prediction model; Optionally, the labels include normal labels of each biochemical index and labels of each biochemical index of pregnancy diseases.

8. A computer program product, which includes a computer program or instructions thereon, characterized in that, The computer program or instruction is executed by a processor to implement the method for predicting the risk of pregnancy diseases based on biochemical indexes according to any one of the claims.

9. A computer device, comprising a memory, a processor, and a computer program or instruction stored on the memory, characterized in that, The computer program or instruction is executed by a processor to implement the method for predicting the risk of pregnancy diseases based on biochemical indexes according to any one of the claims.

10. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, The computer program or instruction is executed by a processor to implement the method for predicting the risk of pregnancy diseases based on biochemical indexes according to any one of the claims.

Images