Gynaecology and obstetrics data analysis method based on knowledge graph

Through the obstetrics and gynecology data analysis method based on knowledge graph, the risk index and health assessment index of maternals are calculated, and the subjectivity of existing assessment methods and the lack of quantitative indicators are solved, and the effect of personalized care and timely discovering potential risks is achieved.

CN120183695AInactive Publication Date: 2025-06-20SHANDONG JIAHAO MEDICAL TECHNOLOGY CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202510260720.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-06
Publication Date
2025-06-20
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing obstetrics and gynecology evaluation methods are subjective and lack quantitative indicators, making it difficult to conduct a comprehensive and objective maternal health assessment, and making personalized prenatal care plans, resulting in different nursing effects and difficulty in time to detect potential health risks.

Method used

Using the obstetrics and gynecology data analysis method based on knowledge graphs, we collect basic information of the mother and reference information of other mothers during the same pregnancy in real time, and use the analysis and diagnosis module to calculate the maternal risk index, complication prediction value and health assessment index, and then formulate a personalized prenatal care plan.

Benefits of technology

It improves the accuracy of maternal health assessment, realizes personalized prenatal care, timely discovers potential health risks, and dynamically adjusts nursing plans through circular impact and optimization mechanisms, improving nursing effects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120183695A_ABST
    Figure CN120183695A_ABST
Patent Text Reader

Abstract

A data analysis method for gynaecology and obstetrics based on a knowledge graph particularly relates to the technical field of data analysis for gynaecology and obstetrics, and comprises the following steps: acquiring basic information of a current puerpera in real time by using a data acquisition module, and acquiring reference information of other puerpera in the same pregnancy period as the current puerpera and reference graph information from a knowledge graph database; based on basic information, reference information and atlas information, an analysis and diagnosis module is utilized to sequentially calculate and output a puerpera risk index FF, a complication prediction value YB and a health assessment index FJ, and based on result comparison of the health assessment index FJ and a health assessment average index FJavg, the analysis and diagnosis module is utilized to analyze and judge data. The method has the remarkable advantages of improving evaluation accuracy, achieving personalized nursing, timely finding potential risks, promoting circulation influence and optimization and the like, accurate evaluation and targeted adjustment of the health condition of the puerpera are achieved, and powerful support is provided for clinical decision making.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of obstetrics and gynecology data analysis, specifically a method for obstetrics and gynecology data analysis based on a knowledge graph. Background Art

[0002] In the field of obstetrics and gynecology, accurately assessing the health status of parturients is the key to ensuring the safety of mother and child. However, the existing assessment methods mainly rely on doctors' clinical experience and parturients' subjective descriptions. This method has problems such as strong subjectivity, lack of quantitative indicators, and it is difficult to comprehensively and objectively evaluate the health status of parturients.

[0003] Specifically, the existing assessment methods mainly rely on doctors' clinical experience and parturients' subjective descriptions, lack quantitative indicators, and it is difficult to comprehensively and objectively evaluate the health status of parturients. Moreover, due to the subjectivity and uncertainty of the assessment method, it is difficult to formulate personalized prenatal care plans for each parturient, resulting in uneven nursing effects. In addition, the existing methods are difficult to detect potential health risks of parturients in a timely manner, and often measures can only be taken after problems occur, thus missing the best intervention opportunity. In addition, the existing assessment methods are often one-time, lacking a cyclic influence and optimization mechanism, and unable to adjust the nursing plan in a timely manner according to the changes in the health status of parturients.

[0004] Therefore, those skilled in the art have provided a method for obstetrics and gynecology data analysis based on a knowledge graph to solve the problems raised in the above background art. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method for obstetrics and gynecology data analysis based on a knowledge graph to achieve the effects of improving assessment accuracy, realizing personalized care, timely discovering potential risks, and promoting cyclic influence and optimization.

[0006] To solve the above problems, the present invention provides the following technical solutions:

[0007] A method for obstetrics and gynecology data analysis based on a knowledge graph, and the specific data analysis method steps are as follows:

[0008] Step 1: Based on basic information, reference information, and graph information, and using a data acquisition module, real-time collect the basic information of the current parturient, and collect reference information of other parturients in the same pregnancy period as the current parturient and reference graph information from the knowledge graph database;

[0009] Step 2: Use an analysis and diagnosis module to calculate and output the parturient risk index FF, the complication prediction value YB, and the health assessment index FJ in sequence;

[0010] Among them, the analysis and diagnosis module includes a parturient risk analysis unit, a unit for predicting the probability of occurrence of delivery complications, and a unit for comprehensively evaluating the overall health of parturients;

[0011] The basic information includes the blood pressure, age, weight, height, and hemoglobin concentration of the current pregnant woman. The reference information includes the prenatal reference weight QT ref , the average health assessment index FJ avg , and the atlas information includes the blood pressure, hemoglobin concentration, and weight gain range of the pregnant woman in different pregnancy trimesters;

[0012] Step 3: Compare the results of the health assessment index FJ with the average health assessment index FJ avg , and use the analysis and diagnosis module to analyze and judge the data.

[0013] Furthermore: The devices used by the data collection module include a sphygmomanometer, a hemoglobin concentration measuring instrument, a weighing scale, and a knowledge graph database;

[0014] The devices used by the analysis and diagnosis module include computer equipment.

[0015] Furthermore: The calculation formula of the maternal risk analysis unit is as follows:

[0016]

[0017] BMI = QT / G;

[0018] Where:

[0019] FF is the maternal risk index, and FF is used to evaluate the degree of risk faced by the pregnant woman during childbirth;

[0020] XY is the blood pressure of the pregnant woman;

[0021] N is the age of the pregnant woman;

[0022] BMI is the body mass index;

[0023] QT is the prenatal weight, and G is the height of the pregnant woman;

[0024] DW is the hemoglobin concentration;

[0025] It is used to eliminate the risk index fluctuations caused by individual differences among different pregnant women;

[0026] G - QT reflects the balance ratio relationship between height and weight, and the degree to which this balance ratio relationship affects the delivery risk of the pregnant woman;

[0027] A large FF value indicates a large production risk;

[0028] A small FF value indicates a small production risk.

[0029] Furthermore, the calculation formula of the unit for predicting the probability of occurrence of childbirth complications is as follows:

[0030]

[0031] Where:

[0032] YB is the complication prediction value;

[0033] QT ref is the pre-pregnancy reference weight;

[0034] QT - QT ref reflects the growth difference of the parturient's weight. Divide this difference by to consider the adjustment effect of the parturient risk index FF and the parturient blood pressure XY on the weight gain;

[0035] reflects the relative relationship between the age and weight of the parturient, and is used to adjust YB;

[0036] A large YB value indicates a high probability of occurrence of complications;

[0037] A small YB value indicates a low probability of occurrence of complications.

[0038] Furthermore, the pre-pregnancy reference weight QT ref has the following calculation formula:

[0039] QT ref = (QT1 + QT2 + QT3 +...... + QT n ) / n;

[0040] n is the number of parturients, and n reflects the total number of parturients with a small YB value during the same pregnancy period;

[0041] QT1 is the pre-pregnancy weight of the first parturient, QT2 is the pre-pregnancy weight of the second parturient, QT3 is the pre-pregnancy weight of the third parturient, and QT n is the pre-pregnancy weight of the nth parturient.

[0042] Furthermore, the calculation formula of the unit for comprehensively evaluating the overall health of the parturient is as follows:

[0043]

[0044] Where:

[0045] FJ is the health assessment index;

[0046] QT pre is the pre-pregnancy weight;

[0047] Reflect the combined influence of the complication prediction value YB on the height and age of the parturient. Divide this result by the result of YB + BMI×(QT - QT pre ), in order to comprehensively evaluate the complication prediction value YB and the overall health status of the parturient;

[0048] Reflect the relative relationship between the parturient risk index FF, the height G of the parturient and the body mass index BMI. And this calculation result is used as part of the subtrahend to adjust the evaluation result of the overall health status of the parturient.

[0049] Furthermore: The data analysis based on the health assessment index FJ is as follows:

[0050] If the health assessment index FJ is higher than the average health assessment index FJ avg , it indicates that there are risks and potential problems in the current parturient's health status compared with other parturients in the same pregnancy period. When analyzing the parturient's blood pressure XY, hemoglobin concentration DW and QT - QT ref one by one, the specific analysis is as follows:

[0051] By comparing the current parturient's blood pressure XY with the safe range of blood pressure in the corresponding pregnancy period provided in the knowledge graph, judge and analyze the parturient's hypertension risk;

[0052] By comparing the current parturient's hemoglobin concentration DW with the safe range in the knowledge graph, judge and analyze the parturient's anemia problem;

[0053] By comparing the difference value of the current parturient's QT - QT ref and the safe range of weight gain of parturients in different pregnancy periods provided by the knowledge graph, judge the reasonable degree of the parturient's weight gain;

[0054] If the health assessment index FJ is lower than the average health assessment index FJ avg , it indicates that the current parturient's health status is relatively good and in a relatively safe state, and the current data should be maintained.

[0055] Furthermore: The calculation formula of the average health assessment index FJ avg is as follows:

[0056] FJ ref = (FJ1 + FJ2 + FJ3 +...... + FJ n ) / n;

[0057] n reflects the total number of parturients with relatively good health status and in a relatively safe state in the same pregnancy period;

[0058] FJ1 is the first maternal health assessment index, FJ2 is the second maternal health assessment index, FJ3 is the third maternal health assessment index, and FJ n is the nth maternal health assessment index.

[0059] The effects of the above solutions are as follows:

[0060] 1. The present invention evaluates the health status of parturients through quantitative indicators, avoiding the subjectivity and uncertainty of existing methods, and thus improving the accuracy of the evaluation.

[0061] 2. The present invention compares the health assessment index FJ with the average health assessment index FJ of parturients in the same pregnancy period and within the safe value range avg to formulate a personalized prenatal care plan for each parturient, thereby improving the nursing effect.

[0062] 3. In the present invention, if the health assessment index FJ is lower than the average value, it indicates that the parturient has potential health risks. Furthermore, through the safe ranges of blood pressure, hemoglobin concentration, and weight gain in different pregnancy cycles of parturients provided by the knowledge graph, it is possible to quickly analyze and judge which parameter values have problems, and thus timely take intervention measures.

[0063] In addition, the health assessment index FJ not only reflects the current health status of the parturient, but also can affect the parameters in the formula through the feedback mechanism, thereby realizing cyclic influence and optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is a schematic flowchart of the method for analyzing and processing obstetrics and gynecology data based on a knowledge graph;

[0065] Figure 2 is a schematic structural diagram of the analysis and diagnosis module in the present invention;

[0066] Figure 3 is a schematic diagram for analyzing and judging the health assessment index FJ in the present invention;

[0067] Figure 4 is a schematic diagram for analyzing attention after judgment in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0068] The following will clearly and completely introduce the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention.

[0069] Example 1. Please refer to Figures 1-4 , the method for analyzing and processing obstetrics and gynecology data based on a knowledge graph, and the specific method steps for data analysis are as follows:

[0070] Step 1: Use the data collection module to collect the basic information of the current parturient in real time, and collect the reference information of other parturients in the same pregnancy period as the current parturient and the reference atlas information from the knowledge graph database;

[0071] Step 2: Based on the basic information, reference information, and atlas information, and using the analysis and diagnosis module, calculate and output the parturient risk index FF, complication prediction value YB, and health assessment index FJ in sequence;

[0072] Among them, the analysis and diagnosis module includes a parturient risk analysis unit, a unit for predicting the probability of occurrence of delivery complications, and a unit for comprehensively evaluating the overall health of the parturient;

[0073] The basic information includes the blood pressure, age, weight, height, and hemoglobin concentration of the current parturient, and the reference information includes the prenatal reference weight QT ref and the average health assessment index FJ avg , and the atlas information includes the blood pressure, hemoglobin concentration, and weight gain range of the parturient in different pregnancy periods;

[0074] Step 3: Based on the comparison of the results of the health assessment index FJ and the average health assessment index FJ avg , and use the analysis and diagnosis module to analyze and judge the data;

[0075] The devices used by the data collection module include a sphygmomanometer, a hemoglobin concentration measuring instrument, a weighing scale, and a knowledge graph database;

[0076] The devices used by the analysis and diagnosis module include computer devices.

[0077] In this embodiment, the method for analyzing and processing obstetrics and gynecology data based on the knowledge graph realizes the accurate assessment and targeted adjustment of the parturient's health status through a series of steps, modules, and units, and combines advanced data collection and processing devices, providing strong support for clinical decision-making. These formulas can comprehensively reflect the parturient's health status by considering multiple factors such as the parturient's physiological function, weight gain, basic physiological characteristics, and risk index, and thus provide more accurate and reliable assessment results.

[0078] Please refer to Figures 1-4 , the calculation formula of the parturient risk analysis unit is as follows:

[0079]

[0080] BMI = QT / G;

[0081] Among them:

[0082] FF is the parturient risk index, and FF is used to evaluate the degree of risk faced by the parturient during the production process;

[0083] XY is the blood pressure of the parturient;

[0084] N is the age of the parturient;

[0085] BMI is the body mass index;

[0086] QT is the pre-pregnancy weight and G is the height of the parturient;

[0087] DW is the hemoglobin concentration;

[0088] It is used to eliminate the risk index fluctuations caused by individual differences among different parturients;

[0089] G - QT reflects the balance ratio relationship between height and weight, and the degree to which this balance ratio relationship affects the parturient's delivery risk;

[0090] If the FF value is large, it reflects a high production risk;

[0091] If the FF value is small, it reflects a low production risk.

[0092] In this embodiment, first The calculation part aims to preliminarily evaluate the risk level of the parturient by comprehensively considering the parturient's blood pressure XY, the parturient's age N, the body mass index BMI, and the hemoglobin concentration DW. The parturient's blood pressure XY and the parturient's age N are important indicators reflecting the parturient's physiological functions, while the body mass index BMI and the hemoglobin concentration DW are closely related to the parturient's nutritional status and health status. The calculation part uses square root operations and division operations to standardize parameters with different dimensions, making the results more comparable. At the same time, through addition and subtraction operations, the positively correlated parameters, the parturient's blood pressure XY and the parturient's age N, are combined with the negatively correlated parameters, the body mass index BMI and the hemoglobin concentration DW, to reflect the comprehensive effect of the parturient's risk. As the core calculation unit in the calculation formula of the parturient risk analysis unit, the result of this calculation part provides basic data for subsequent multiplication operations;

[0093] In addition, the body mass index BMI reflects the ratio of the parturient's weight to height and is an important indicator for evaluating obesity, while the hemoglobin concentration DW reflects the parturient's anemia status. Subtracting the hemoglobin concentration DW from the body mass index BM is to consider the combined effect of weight and anemia status on the parturient's risk. If the body mass index BM is too high / the hemoglobin concentration DW is too low, both will increase the parturient's risk. Therefore, through this calculation method, the effects of these two factors can be comprehensively reflected;

[0094] In this algorithm unit, age and height, as basic physiological characteristics, have a certain impact on the delivery risk of parturients. Young parturients usually have a lower delivery risk. For parturients with a higher height, the pelvic space is relatively larger during childbirth, which is conducive to the delivery of the fetus. Regarding other parameters:

[0095] Both being overweight or underweight will increase the delivery risk;

[0096] Both having too high or too low blood pressure will lead to delivery complications;

[0097] The hemoglobin concentration DW reflects the anemia status of parturients. Anemic parturients will face a higher bleeding risk during childbirth. By comprehensively considering these parameters, the parturient risk index FF can accurately predict potential production risks;

[0098] During the calculation of the parturient risk index FF, individual differences of parturients are considered, including parturients of different ages, heights, and weights. Their delivery risks may vary. Therefore, the parturient risk index FF can provide personalized risk assessments for each parturient, which helps to formulate a more scientific and reasonable prenatal care plan;

[0099] As an important reference basis for clinical decisions, the value of the parturient risk index FF has a high degree of reliability and can be used to determine whether a parturient needs further examinations and treatments based on the level of the parturient risk index FF value. Specifically, for parturients with a higher parturient risk index FF value, it is necessary to increase the frequency of prenatal examinations and take other preventive measures to reduce the delivery risk.

[0100] Please refer to Figures 1-4 , the calculation formula of the unit for predicting the probability of occurrence of delivery complications is as follows:

[0101]

[0102] Where:

[0103] YB is the complication prediction value;

[0104] QT ref is the reference weight before delivery;

[0105] QT - QT ref reflects the growth difference of the parturient's weight. Dividing this difference by is to consider the adjustment effect of the parturient risk index FF and the parturient blood pressure XY on the impact of weight growth;

[0106] reflects the relative relationship between the parturient's age and weight and is used to adjust YB;

[0107] A larger YB value indicates a higher probability of occurrence of complications;

[0108] A smaller YB value indicates a lower probability of complications

[0109] Prenatal reference weight QT ref is calculated as follows:

[0110] QT ref =(QT1 + QT2 + QT3 +......+ QT n ) / n;

[0111] n is the number of parturients, and n reflects the total number of parturients with a small YB value during the same pregnancy

[0112] QT1 is the prenatal weight of the first parturient, QT2 is the prenatal weight of the second parturient, QT3 is the prenatal weight of the third parturient, and QT n is the prenatal weight of the nth parturient

[0113] In this embodiment, first The difference between QT - QT in the calculation part reflects the weight gain of the parturient. Dividing this difference by the sum of the parturient risk index FF and the square root of the parturient blood pressure XY is to consider the regulatory effect of the parturient risk index and blood pressure on the degree of weight gain. In this way, the impact of weight gain on the risk of delivery complications can be more accurately evaluated ref The calculation result of adding the parturient risk index FF and the square root of the parturient blood pressure XY reflects the combined effect of the parturient risk index and blood pressure. This calculation result is used as part of the denominator in the unit for predicting the probability of delivery complications to adjust the impact of weight gain on the risk of delivery complications. In this way, the predicted value of delivery complications can more sensitively reflect the physiological condition of the parturient

[0114] The calculation result of adding the parturient risk index FF and the square root of the parturient blood pressure XY reflects the combined effect of the parturient risk index and blood pressure. This calculation result is used as part of the denominator in the unit for predicting the probability of delivery complications to adjust the impact of weight gain on the risk of delivery complications. In this way, the predicted value of delivery complications can more sensitively reflect the physiological condition of the parturient

[0115] The calculation result reflects the relative relationship between the parturient's age and weight. In the unit for predicting the probability of delivery complications, this calculation result is used as part of the subtrahend to adjust the predicted value of delivery complications YB. In this way, the combined impact of age and weight on the risk of delivery complications can be considered, making the prediction result more accurate

[0116] The prenatal reference weight QT in this algorithm unit ref is an important predictive factor, which reflects the weight gain of the parturient during pregnancy. Excessive or too slow weight gain during pregnancy will increase the risk of delivery complications. The predicted value of complications YB can more accurately predict the probability of delivery complications by comprehensively considering multiple physiological indicators and historical data

[0117] According to the level of the complication prediction value YB, the prenatal care plan can be adjusted to reduce the occurrence of delivery complications. Specifically, for pregnant women with a relatively high complication prediction value YB, the frequency of prenatal examinations can be increased, the diet plan can be adjusted, and exercise can be strengthened to reduce the delivery risk. This targeted prenatal care plan helps improve the safety of delivery.

[0118] Taking the complication prediction value YB as an important tool for communication with pregnant women helps them better understand their delivery risks. Through transparent communication, pregnant women can actively participate in the formulation and implementation of the prenatal care plan, thereby improving their cooperation and satisfaction during delivery.

[0119] Please refer to Figures 1-4 , and the calculation formula for comprehensively evaluating the overall health unit of pregnant women is as follows:

[0120]

[0121] Where:

[0122] FJ is the health assessment index;

[0123] QT pre is the pre-pregnancy weight;

[0124] reflects the combined influence of the complication prediction value YB on the height and age of the pregnant woman. Dividing this result by the result of YB + BMI × (QT - QT pre ) is to comprehensively evaluate the complication prediction value YB and the overall health status of the pregnant woman;

[0125] reflects the relative relationship between the maternal risk index FF, the maternal height G, and the body mass index BMI, and this calculation result is used as part of the subtrahend to adjust the evaluation result of the overall health status of the pregnant woman.

[0126] In this embodiment, first In the calculation part, the calculation result reflects the combined influence of the delivery complication prediction value YB on the maternal height G and the maternal age N. Dividing this result by YB + BMI × (QT - QT pre) The result is to comprehensively evaluate the prediction value YB of childbirth complications and the overall health status of the parturient. In this way, it can more comprehensively reflect the health status of the parturient and provide strong support for clinical decision-making. Among them, the height G of the parturient and the age N of the parturient are both important indicators reflecting the basic physiological characteristics of the parturient. Adding the height G of the parturient and the square root of the age N of the parturient is to comprehensively consider the influence of these two factors on the health of the parturient. Multiplying this result by the complication prediction value YB is to emphasize the correlation between the childbirth complication prediction value YB and the basic physiological characteristics of the parturient, making the calculation result of the health assessment index FJ more sensitively reflect the physiological status of the parturient, BMI×(QT - QT pre ) The calculation result reflects the comprehensive influence of the weight gain of the parturient and the body mass index BMI. This calculation result is used as part of an addend in the comprehensive evaluation of the overall health unit of the parturient to adjust the influence degree of the childbirth complication prediction value YB on the overall health status of the parturient. In this way, the combined influence of weight gain and body mass index BMI on the health of the parturient can be considered. And in the comprehensive evaluation of the overall health unit of the parturient, the complication prediction value YB is used as part of an addend to emphasize the importance of the childbirth complication prediction value in the assessment of the overall health status of the parturient. By combining the complication prediction value YB with other factors, the health status of the parturient can be more comprehensively reflected;

[0127] The calculation result of the calculation part reflects the relative relationship between the parturient risk index FF, the height G of the parturient, and the body mass index BMI. In the comprehensive evaluation of the overall health unit of the parturient, this calculation result is used as part of a subtractor to adjust the evaluation result of the overall health status of the parturient. In this way, the combined influence of the parturient risk index FF, the height G of the parturient, and the body mass index BMI on the health of the parturient can be considered, making the calculation result of the health assessment index FJ more accurate;

[0128] In this algorithm unit, the health assessment index FJ can comprehensively consider multiple physiological indicators and historical data of the parturient, including the pre-pregnancy weight QT pre , the weight gain during pregnancy, blood pressure changes, and hemoglobin concentration DW, and then provide a comprehensive assessment of the health status of the parturient. This comprehensive assessment helps doctors more accurately understand the health status and needs of the parturient;

[0129] According to the level of the health assessment index FJ, the antenatal care plan can be adjusted in a timely manner to improve the health status of the parturient. For parturients with a lower health assessment index FJ, the nutritional intake can be increased, the diet structure can be adjusted, and exercise can be strengthened to improve physical fitness and childbirth safety. This timely adjustment of antenatal care helps reduce the childbirth risk and improve the childbirth success rate;

[0130] The health assessment index FJ not only reflects the current health status of the parturient, but also can affect the parameters in the parturient risk analysis unit through the feedback mechanism. This cyclic influence mechanism helps to dynamically adjust the prenatal care plan according to the changes in the parturient's health status, so as to achieve more accurate and personalized care. This dynamic care adjustment helps to improve the overall care effect and enhance the parturient's childbirth experience.

[0131] Example 2, please refer to Figures 1-4 , and the data analysis based on the health assessment index FJ is as follows:

[0132] If the health assessment index FJ is higher than the average health assessment index FJ avg , it reflects that there are risks and potential problems in the current health status of the parturient compared with other parturients in the same pregnancy period. When analyzing the parturient's blood pressure XY, hemoglobin concentration DW, and QT-QT ref one by one, the specific analysis is as follows:

[0133] By comparing the current parturient's blood pressure XY with the safe range of blood pressure in the corresponding pregnancy period provided in the knowledge graph, judge and analyze the parturient's hypertension risk;

[0134] By comparing the current parturient's hemoglobin concentration DW with the safe range in the knowledge graph, judge and analyze the parturient's anemia problem;

[0135] By comparing the difference value of the current parturient's QT-QT ref and the safe range of weight gain of parturients in different pregnancy periods provided by the knowledge graph, judge the reasonable degree of the parturient's weight gain;

[0136] If the health assessment index FJ is lower than the average health assessment index FJ avg , it reflects that the current health status of the parturient is relatively good and in a relatively safe state, and the current data should be maintained;

[0137] The calculation formula of the average health assessment index FJ avg is as follows:

[0138] FJ ref = (FJ1 + FJ2 + FJ3 +...... + FJ n ) / n;

[0139] n reflects the total number of parturients with relatively good health status and in a relatively safe state in the same pregnancy period;

[0140] FJ1 is the health assessment index of the first parturient, FJ2 is the health assessment index of the second parturient, FJ3 is the health assessment index of the third parturient, and FJ n is the health assessment index of the nth parturient.

[0141] Through the feedback mechanism of the health assessment index FJ, the parameters in the maternal risk analysis unit can be dynamically adjusted, thereby affecting the calculation result of the maternal risk index FF. This dynamic adjustment helps to more accurately assess the production risk of the parturient and take corresponding preventive measures;

[0142] According to the feedback results of the health assessment index FJ, the antenatal care plan can be continuously optimized to meet the health needs of the parturient in different pregnancy cycles. This optimization helps to improve the pertinence and effectiveness of antenatal care and reduce the incidence of delivery complications;

[0143] By comprehensively evaluating the cyclic influence mechanism of the maternal overall health unit on the maternal risk analysis unit, the health status and needs of the parturient can be more comprehensively understood, so as to formulate a more scientific and reasonable antenatal care plan, which helps to improve the overall nursing quality and ensure the safety of the mother and baby;

[0144] The maternal risk index FF is calculated through the maternal risk analysis unit. This index synthesizes multiple physiological parameters such as blood pressure, age, body mass index BMI, hemoglobin concentration DW, height and prenatal weight, providing a comprehensive assessment of the maternal health status for medical staff. The unit for predicting the probability of delivery complications further calculates the predicted value of delivery complications (complication prediction value YB) using parameters such as the maternal risk index FF and prenatal weight, further refining the assessment of the potential risks of the parturient. And the comprehensive evaluation of the maternal overall health unit calculates the adjusted health assessment index FJ by integrating the complication prediction value YB, height, age, body mass index and pre-pregnancy weight QT pre information, and then provides a more accurate indicator of the maternal health status;

[0145] Comparing the calculated health assessment index FJ with the average health assessment index FJ avg calculated and output for parturients in the same pregnancy period and within the safe value range before can quickly detect whether there is an abnormality in the maternal health status. When the health assessment index FJ is higher than the average health assessment index FJ avg it means that the parturient may face problems such as hypertension, anemia, too rapid or too slow weight gain. At this time, relying on the safe range of physiological parameters for different pregnancy cycles of parturients provided in the knowledge graph, each physiological parameter of the parturient will be checked one by one to find out the specific indicators that exceed the safe range, so as to discover and solve the problem in time;

[0146] After determining the problem parameters, according to the specific situation of the parturient, combining the calculation results of the maternal risk analysis unit, the unit for predicting the probability of delivery complications and the comprehensive evaluation of the maternal overall health unit and the information provided by the knowledge graph, a personalized antenatal care plan can be formulated. Specifically:

[0147] For parturients with slightly high blood pressure, it is possible to adjust the diet, reduce salt intake, and increase foods rich in potassium;

[0148] For anemic parturients, it is possible to increase foods rich in iron and, if necessary, carry out drug treatment;

[0149] For parturients with excessive weight gain, it is possible to increase physical activity and adjust the diet plan;

[0150] The above-mentioned personalized care plan can more effectively improve the health of parturients and reduce the risk of delivery complications;

[0151] During the prenatal care process, the changes in various physiological parameters of parturients should be continuously monitored, and the care plan should be dynamically adjusted according to the actual situation. By regularly calculating the health assessment index FJ and comparing it with the average health assessment index FJ avg new changes in the health status of parturients can be detected in a timely manner, and corresponding measures can be taken for adjustment. This process of continuous monitoring and dynamic adjustment helps to ensure that parturients can maintain a stable health status throughout the pregnancy;

[0152] Using the parturient risk analysis unit, the unit for predicting the probability of delivery complications, and the unit for comprehensively evaluating the overall health of parturients to conduct data analysis and feedback in obstetrics and gynecology not only improves the accuracy of the assessment of parturient health status, but also provides a scientific basis for formulating personalized prenatal care plans. This data-driven care model helps to improve the quality and efficiency of medical care, reduce medical costs, and at the same time improve the health levels of parturients and newborns;

[0153] In summary, combining the parturient risk analysis unit, the unit for predicting the probability of delivery complications, and the unit for comprehensively evaluating the overall health of parturients to conduct data analysis and feedback in obstetrics and gynecology has many beneficial effects, including accurately assessing the health status of parturients, timely discovering and solving problems, formulating personalized prenatal care plans, continuous monitoring and dynamic adjustment, and improving the quality and efficiency of medical care. These effects work together in the health management process of parturients and help to ensure the health and safety of mothers and infants.

[0154] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention should be subject to the scope defined by the claims.

Claims

1. The obstetrics and gynecology data analysis method based on knowledge graph is characterized by: The specific steps of data analysis are as follows: Step 1: Use the data collection module to collect the basic information of the current parturient in real time, and collect reference information of other parturients in the same pregnancy period as the current parturient and reference graph information from the knowledge graph database; Step 2: Based on the basic information, reference information, and atlas information, and using the analysis and diagnosis module, the maternal risk index FF, the complication prediction value YB, and the health assessment index FJ are calculated and output in sequence; The analysis and diagnosis module includes a maternal risk analysis unit, a unit for predicting the probability of delivery complications, and a unit for comprehensively evaluating the overall health of the maternal; Basic information includes the current maternal blood pressure, age, weight, height, and hemoglobin concentration. Reference information includes prenatal reference weight, QT ref , health assessment average index FJ avg The atlas information includes the blood pressure, hemoglobin concentration and weight gain range of the parturient at different stages of pregnancy; Step 3: Based on the health assessment index FJ and the health assessment average index FJ avg The results are compared and the analysis and diagnosis module is used to analyze and judge the data.

2. The obstetrics and gynecology data analysis method based on knowledge graph according to claim 1, characterized in that: The equipment used in the data acquisition module includes a sphygmomanometer, a hemoglobin concentration measuring instrument, a weight scale, and a knowledge graph database; The equipment used by the analysis and diagnosis module includes computer equipment.

3. The obstetrics and gynecology data analysis method based on knowledge graph according to claim 2 is characterized in that: The calculation formula of the maternal risk analysis unit is as follows: BMI = QT / G; in: FF is the maternal risk index, which is used to assess the degree of risk faced by mothers during childbirth; XY is maternal blood pressure; N is maternal age; BMI is body mass index; QT is prenatal weight, G is maternal height; DW is the hemoglobin concentration; Used to eliminate the fluctuation of risk index caused by individual differences among different parturients; G-QT reflects the balanced relationship between height and weight, and the extent to which this balanced relationship affects the risk of maternal delivery; A large FF value reflects a high production risk; A small FF value reflects a small production risk.

4. The obstetrics and gynecology data analysis method based on knowledge graph according to claim 3 is characterized by: The calculation formula of the unit for predicting the probability of delivery complications is as follows: in: YB is the predicted value of complications; QT ref It is the reference weight before delivery; QT-QT ref Reflecting the difference in maternal weight gain, this difference is divided by This is to consider the regulatory effect of maternal risk index FF and maternal blood pressure XY on weight gain; Reflects the relative relationship between maternal age and weight and is used to adjust YB; A large YB value reflects a high probability of complications; A smaller YB value reflects a lower probability of complications.

5. The obstetrics and gynecology data analysis method based on knowledge graph according to claim 4 is characterized in that: The antenatal reference weight QT ref The calculation formula is as follows: QT ref =(QT1+QT2+QT3+......+QT n ) / n; n is the number of parturients, and n reflects the total number of parturients with small YB values ​​in the same gestational period; QT1 is the prenatal weight of the first parturient, QT2 is the prenatal weight of the second parturient, QT3 is the prenatal weight of the third parturient, and QT n is the prenatal weight of the nth mother.

6. The obstetrics and gynecology data analysis method based on knowledge graph according to claim 5 is characterized by: The calculation formula for the comprehensive assessment of maternal overall health unit is as follows: in: FJ is the health assessment index; QT pre is the pre-pregnancy weight; The combined effect of YB, the height and age of the parturient, and YB+BMI×(QT-QT pre ) is to comprehensively evaluate the complication prediction value YB and the overall health status of the parturient; It reflects the relative relationship between the maternal risk index FF and the maternal height G and body mass index BMI, and this calculation result is used as part of the subtraction to adjust the assessment results of the overall health status of the mother.

7. The obstetrics and gynecology data analysis method based on knowledge graph according to claim 6 is characterized in that: The data analysis based on the health assessment index FJ is as follows: If the health assessment index FJ is higher than the average health assessment index FJ avg , it reflects that the current health status of the parturient is at risk and has potential problems compared with other parturients in the same pregnancy period. ref Analyze them one by one, the specific analysis is as follows: By comparing the current maternal blood pressure XY with the safety range of blood pressure during the corresponding pregnancy period provided in the knowledge graph, the risk of hypertension in the maternal body can be determined and analyzed; By comparing the current maternal hemoglobin concentration DW with the safety interval in the knowledge graph, the anemia problem of the maternal can be judged and analyzed; By comparing the current maternal QT-QT ref The difference between the two values ​​and the safe range of maternal weight gain in different gestational periods provided by the knowledge graph can be used to determine the reasonableness of maternal weight gain; If the health assessment index FJ is lower than the average health assessment index FJ avg , it reflects that the current health status of the mother is relatively good and in a relatively safe state, so the current data should be maintained.

8. The obstetrics and gynecology data analysis method based on knowledge graph according to claim 7 is characterized in that: The health assessment average index FJ avg The calculation formula is as follows: FJ ref =(FJ1+FJ2+FJ3+......+FJ n ) / n; n reflects the total number of pregnant women who are in relatively good health and safe condition during the same period of pregnancy; FJ1 is the first maternal health assessment index, FJ2 is the second maternal health assessment index, FJ3 is the third maternal health assessment index, and FJ n is the nth maternal health assessment index.

Citation Information

Cited By

  • Pregnant woman health management method and system based on digital human

    CN120783932A