Maternal and fetal congenital abnormality case tracking system based on regional big data

Abstract

The invention belongs to the technical field of big data medical health, and particularly relates to a maternal and fetal congenital anomaly case tracking system based on regional big data, which comprises a data acquisition module, a data transmission and storage module, a big data analysis module, a case tracking and early warning module, a patient feedback and intervention module and a case database and cloud management module. The system can monitor the health conditions of pregnant women and fetuses in real time, generate abnormal early warning in time, effectively reduce the missed diagnosis rate and misdiagnosis rate of maternal and fetal congenital abnormalities, and perform intelligent analysis on large-scale maternal and fetal health data through the big data analysis module to find potential disease risks, thereby providing decision support for doctors, and improving the diagnosis efficiency of the maternal and fetal congenital abnormalities. Meanwhile, the system not only can monitor health data of individuals, but also can realize large-scale maternal and fetal congenital abnormality case tracking, promote reasonable configuration and allocation of regional health resources, improve the working efficiency of doctors, reduce errors of manual diagnosis and ensure early intervention of maternal and fetal health.

Description

Technical Field

[0001] This invention relates to the field of big data medical and health technology, specifically to a maternal-fetal congenital abnormality case tracking system based on regional big data. Background Technology

[0002] In the past half-century, with the rapid development of medical science, the continuous accumulation of medical knowledge, and the emergence of new diagnostic technologies, treatment methods and interventions, people's needs and expectations for maternal and infant health have reached an unprecedented level, giving rise to maternal-fetal medicine.

[0003] Maternal-fetal medicine is dedicated to maternal and infant health, reducing birth defects, and truly placing mothers and children on an equal footing from a medical perspective. In the past decade, maternal-fetal medicine has made significant progress in Europe and America, while its development in Asia is still in its early stages.

[0004] Maternal-fetal medicine encompasses basic obstetrics and gynecology knowledge, focusing on early pregnancy screening, prenatal and postnatal care, fetal medicine, obstetric ultrasound, molecular and cytogenetics, maternal medicine, perinatal medicine, and other related knowledge and technological advancements. With advancements in technology, maternal and fetal health has become a crucial issue in the medical field. Congenital abnormalities in pregnant women can affect fetal development and even endanger the lives of both mother and child.

[0005] The existing technology has the following defects or problems: Existing maternal-fetal health management systems mostly rely on traditional hospital checkups or single data collection systems, which cannot effectively integrate all case information within a geographical area. This results in problems such as information fragmentation, delayed data transmission, and uneven distribution of medical resources. Therefore, establishing a maternal-fetal congenital anomaly case tracking system based on big data technology is of significant practical importance. This system would enable comprehensive monitoring and analysis of the health data of all pregnant women and fetuses within a region, allowing for the timely detection of potential health risks and effective intervention.

[0006] It should be noted that the above content falls within the inventor's technical knowledge and does not necessarily constitute prior art. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides a case tracking system for maternal-fetal congenital abnormalities based on regional big data, which solves the current problems.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a maternal-fetal congenital abnormality case tracking system based on regional big data, comprising: The data acquisition module collects various physiological data of pregnant women and fetuses through networked medical devices, sensors, and mobile terminals; The physiological data includes changes in the pregnant woman's body temperature, blood pressure, heart rate, and weight, as well as the fetal movement frequency, fetal heart rate monitoring data, and ultrasound examination data. The data transmission and storage module transmits the collected data to the cloud platform via a wireless network. All health-related data is centrally stored on the cloud server. Encryption technology is used during the data transmission process to ensure data security and privacy. The big data analytics module uses machine learning and artificial intelligence algorithms to conduct in-depth analysis of a large amount of maternal and fetal health data, uncover potential disease patterns and trends, analyze the health status of pregnant women and fetuses in real time, generate health reports and compare them with historical cases, conduct real-time risk assessment and prediction, and identify potential risks of congenital abnormalities. The case tracking and early warning module generates real-time abnormal early warning information based on the results of big data analysis. In addition, it has a built-in early warning threshold. When the monitoring status of pregnant women and fetuses exceeds the normal range, the system will automatically send an early warning notification to relevant medical staff and provide timely intervention suggestions. The patient feedback and intervention module can provide real-time feedback of various maternal and fetal monitoring data to the patient's end. Medical staff can also view various health data and analysis results in real time through mobile and computer terminals. At the same time, the system provides intervention suggestions to help medical staff make decisions more quickly. The case database and cloud management module can establish a regional maternal-fetal health case database, which facilitates subsequent case queries, data analysis and research. By performing regional cluster analysis on the data, the characteristics and patterns of maternal-fetal health in different regions can be discovered.

[0009] In some embodiments, the data acquisition module collects health information through smart wearable devices, ultrasound devices, and mobile sensors. The smart wearable devices include medical facilities such as smartwatches, blood pressure monitors, fetal heart rate monitors, and blood glucose meters. The ultrasound devices can periodically check the growth and development of the fetus, monitor the fetal weight, bone development, and fetal position. The mobile sensors include accelerometers and GPS modules built into smartphones. The raw data collected by the data acquisition module needs to undergo noise reduction, deduplication, and standardization processing to ensure data accuracy.

[0010] In some embodiments, the data transmission and storage module uses an end-to-end encryption algorithm during transmission to ensure that even if the data is intercepted, an unauthorized party cannot read the data content. The data transmission steps are as follows: 1) Compress the data preprocessed by the data acquisition module to reduce the size of the data packets and improve transmission efficiency; 2) For large data packets, fragmentation technology is used to split them into multiple smaller packets for transmission. This can avoid packet loss and delay during the transmission of a single large data packet. Sequence numbers are used to mark each fragment during transmission to ensure that the receiving end can reassemble the data in the correct order. 3) If network instability occurs during data transmission, data can be saved through a local caching mechanism and resent after the network is restored to ensure that the data is not lost; The data transmission and storage module uses cloud storage, selecting one of Amazon S3, Azure Blob Storage, or Google Cloud Storage as the storage medium. At the same time, important case data is backed up regularly using automated tools to ensure rapid recovery in case of data loss.

[0011] In some embodiments, the big data analysis module trains a model using historical case data to identify risk patterns of congenital diseases, with the following identification features: The data acquisition module collects various test data, the pregnant woman's age, weight, BMI and history of gestational hyperglycemia and hypertension, fetal development indicators including weight, heart rate, head circumference and umbilical cord entanglement, and the pregnant woman's family genetic data, including gene mutation index and family history of genetic diseases. The potential disease risk assessment uses a logistic regression model, the specific model of which is as follows: in It is the probability of the fetus being sick. These are the features of the input. These are regression coefficients, which are optimized using maximum likelihood estimation. The aforementioned risk and assessment uses a trained model to predict new maternal and fetal health data, thereby identifying potential diseases, wherein: Regression-based risk assessment generates individual risk scores based on the probability values ​​output by the model. in, It is the predicted probability of each feature. It is the weight of that feature; The health assessment report assesses the health status of the pregnant woman and fetus based on the risk score output by the model, compares the current data with similar data in historical cases, and assesses whether the disease risk has changed.

[0012] In some embodiments, the specific steps of the case tracking and early warning module are as follows: 1) During real-time monitoring, the big data analytics module performs rule-based threshold judgments based on the data analysis results; 2) Develop anomaly warning rules based on various thresholds; 3) Assign different risk levels to different types of abnormalities to ensure that high-risk cases are treated first; 4) When the case tracking and early warning module detects abnormal data, it promptly activates the notification mechanism to send early warning information to relevant personnel. The notification mechanism is set to be dual-ended, including: Notification to medical staff: Warning information will be sent to medical staff in a timely manner through SMS, APP push and manual communication. The information includes abnormal data, risk level and suggestions for further examination. Patient notification: The pregnant woman will be notified of mild abnormalities via SMS, APP push, and telephone, and advised to seek medical attention promptly; 5) For high-risk warnings, the module will generate an emergency response notification, recommending immediate medical attention and contacting a doctor, and providing emergency contact information. At this time, the warning notification will not only be sent to medical staff, but also require the patient to take immediate medical intervention. 6) The intervention module will automatically generate corresponding interference suggestions based on abnormal data and warning levels; 7) Medical staff will receive detailed warning reports and further assess the health of the pregnant woman and fetus based on the data provided by the system, deciding whether to conduct more examinations and arrange hospitalization for observation. At this time, doctors can view the patient's historical health records through the system to conduct more comprehensive analysis and decision-making. 8) The system collects feedback from doctors and patients after each abnormal warning to optimize the machine learning model. At the same time, the system can make customized warning strategies according to different regions and medical conditions.

[0013] In some embodiments, the warning rules are as follows: Abnormal fetal heart rate: too fast (>180 bpm) and too slow (<110 bpm); Abnormal blood pressure in pregnant women: higher than 140 / 90 mmHg (hypertension), lower than 90 / 60 mmHg (hypotension); Fetal movement frequency is lower than the normal range: Too few fetal movements (<10 times / 24 hours). Abnormal fetal growth: Fetal weight gain below the normal percentile may lead to intrauterine growth retardation; The risk levels are as follows: Red high-risk warning: fetal heart rate too fast or too slow, severe blood sugar abnormalities and high blood pressure; Orange-level medium-risk warning: decreased fetal movement, mild blood pressure abnormalities, and mild body temperature fluctuations; Yellow low-risk warning: fluctuations in the pregnant woman's weight and slight irregular fetal movements.

[0014] In some embodiments, the interference suggestions are specifically as follows: Abnormal fetal heart rate: When the fetal heart rate is abnormal, the module will recommend an ultrasound examination, monitoring of fetal movement, and, depending on the situation, arrange medical actions such as an emergency cesarean section; Pregnant women with hypertension: It is recommended to monitor blood pressure regularly, avoid strenuous exercise, and use medication to control blood pressure if necessary. Hospitalization for observation is also recommended. Fetal growth restriction: It is recommended to conduct a detailed ultrasound examination and hemodynamic monitoring to observe the fetal growth curve and adjust the pregnant woman's diet and rest in a timely manner. In some embodiments, the case database and the maternal-fetal health case database in the cloud management module are built on a cloud server, and a distributed storage system is used to ensure high availability and scalability of the data. The database architecture includes the following key modules: Patient Information Form: Stores basic personal information, including the pregnant woman's age, address, health condition, and medical history; Health monitoring data sheet: Records the physiological data of pregnant women and fetuses, including heart rate, blood sugar, blood pressure and body temperature. Data timestamps ensure the timeliness of the records. Prenatal checkup record form: Records detailed information about each prenatal checkup, including ultrasound reports, laboratory results, and fetal health assessments; Medical intervention record form: includes all medical interventions, including medication prescriptions, emergency interventions, and hospitalization records; Health Risk Assessment Form: A health risk scoring form generated based on machine learning models, rule thresholds, and human assessment to help hospitals make decisions; The above data tables will be linked horizontally and vertically to ensure that a pregnant woman's health data can be tracked through a unique identifier, making it easy for doctors to view the patient's history.

[0015] Compared with existing technologies, this invention provides a case tracking system for maternal-fetal congenital abnormalities based on regional big data, which has the following beneficial effects: This regional big data-based system for tracking maternal and fetal congenital anomalies can monitor the health status of pregnant women and fetuses in real time and generate timely warnings of abnormalities, effectively reducing the rate of missed and misdiagnosed cases of maternal and fetal congenital anomalies. Simultaneously, through a big data analysis module, it can intelligently analyze large-scale maternal and fetal health data to identify potential disease risks, thereby providing decision support for doctors. Furthermore, the system not only monitors individual health data but also enables large-scale tracking of maternal and fetal congenital anomalies, promoting the rational allocation and distribution of regional health resources. By automating data processing and report generation, it improves doctors' work efficiency, reduces errors in manual diagnosis, and ensures early intervention for maternal and fetal health. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the maternal-fetal congenital abnormality case tracking system based on regional big data according to the present invention. Detailed Implementation

[0017] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments and accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0019] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0020] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0021] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0022] Please see Figure 1 In this implementation plan, a maternal-fetal congenital abnormality case tracking system based on regional big data includes: The data acquisition module collects various physiological data of pregnant women and fetuses through networked medical devices, sensors, and mobile terminals; Physiological data include changes in the pregnant woman's body temperature, blood pressure, heart rate, and weight, as well as the fetal movement frequency, fetal heart rate monitoring data, and ultrasound examination data. The data acquisition module collects health information through smart wearable devices, ultrasound equipment, and mobile sensors. Smart wearable devices include medical facilities such as smartwatches, blood pressure monitors, fetal heart rate monitors, and blood glucose meters. Ultrasound equipment can regularly check the growth and development of the fetus, monitor the fetal weight, bone development, and fetal position. Mobile sensors include the accelerometer and GPS module built into smartphones. The raw data collected by the data acquisition module needs to be denoised, deduplicated, and standardized to ensure data accuracy; The data transmission and storage module transmits the collected data to the cloud platform via a wireless network. All health-related data is centrally stored on the cloud server, and encryption technology is used during data transmission to ensure data security and privacy. The data transmission and storage module uses an end-to-end encryption algorithm during transmission to ensure that even if the data is intercepted, unauthorized parties cannot read the data content. The data transmission steps are as follows: 1) Compress the data preprocessed by the data acquisition module to reduce the size of the data packets and improve transmission efficiency; 2) For large data packets, fragmentation technology is used to split them into multiple smaller packets for transmission. This can avoid packet loss and delay during the transmission of a single large data packet. Sequence numbers are used to mark each fragment during transmission to ensure that the receiving end can reassemble the data in the correct order. 3) If network instability occurs during data transmission, data can be saved through a local caching mechanism and resent after the network is restored to ensure that the data is not lost; The data transmission and storage module uses cloud storage, choosing one of Amazon S3, Azure BlobStorage, or Google Cloud Storage as the storage medium. At the same time, important case data is backed up regularly using automated tools to ensure rapid recovery in case of data loss. The big data analytics module trains a model using historical case data to identify risk patterns for congenital diseases. The identification features are as follows: The data acquisition module collects various test data, the pregnant woman's age, weight, BMI and history of gestational hyperglycemia and hypertension, fetal development indicators including weight, heart rate, head circumference and umbilical cord entanglement, and the pregnant woman's family genetic data, including gene mutation index and family history of genetic diseases. The logistic regression model was used to assess potential disease risk, and the specific model is as follows: in It is the probability of the fetus being sick. These are the features of the input. These are regression coefficients, which are optimized using maximum likelihood estimation. Risk and assessment utilizes a trained model to predict new maternal and fetal health data, thereby identifying potential diseases, including: Regression-based risk assessment generates individual risk scores based on the probability values ​​output by the model. in, It is the predicted probability of each feature. It is the weight of that feature; The health assessment report assesses the health status of pregnant women and fetuses based on the risk score output by the model, compares current data with similar data in historical cases, and assesses whether the disease risk has changed. The big data analytics module uses machine learning and artificial intelligence algorithms to conduct in-depth analysis of a large amount of maternal and fetal health data, uncover potential disease patterns and trends, analyze the health status of pregnant women and fetuses in real time, generate health reports and compare them with historical cases, conduct real-time risk assessment and prediction, and identify potential risks of congenital abnormalities. The case tracking and early warning module generates real-time abnormal early warning information based on the results of big data analysis. In addition, it has a built-in early warning threshold. When the monitoring status of pregnant women and fetuses exceeds the normal range, the system will automatically send an early warning notification to relevant medical staff and provide timely intervention suggestions. The specific steps of the case tracking and early warning module are as follows: 1) During real-time monitoring, the big data analytics module performs rule-based threshold judgments based on the data analysis results; 2) Develop anomaly warning rules based on various thresholds; 3) Assign different risk levels to different types of abnormalities to ensure that high-risk cases are treated first; 4) When the case tracking and early warning module detects abnormal data, it promptly activates the notification mechanism to send early warning information to relevant personnel. The notification mechanism is set to be dual-ended, including: Notification to medical staff: Warning information will be sent to medical staff in a timely manner through SMS, APP push and manual communication. The information includes abnormal data, risk level and suggestions for further examination. Patient notification: The pregnant woman will be notified of mild abnormalities via SMS, APP push, and telephone, and advised to seek medical attention promptly; 5) For high-risk warnings, the module will generate an emergency response notification, recommending immediate medical attention and contacting a doctor, and providing emergency contact information. At this time, the warning notification will not only be sent to medical staff, but also require the patient to take immediate medical intervention. 6) The intervention module will automatically generate corresponding interference suggestions based on abnormal data and warning levels; The warning rules are as follows: Abnormal fetal heart rate: too fast (>180 bpm) and too slow (<110 bpm); Abnormal blood pressure in pregnant women: higher than 140 / 90 mmHg (hypertension), lower than 90 / 60 mmHg (hypotension); Fetal movement frequency is lower than the normal range: Too few fetal movements (<10 times / 24 hours). Abnormal fetal growth: Fetal weight gain below the normal percentile may lead to intrauterine growth retardation; The risk levels are as follows: Red high-risk warning: fetal heart rate too fast or too slow, severe blood sugar abnormalities and high blood pressure; Orange-level medium-risk warning: decreased fetal movement, mild blood pressure abnormalities, and mild body temperature fluctuations; Yellow low-risk warning: fluctuations in pregnant woman's weight and slight irregular fetal movements; The specific interference suggestions are as follows: Abnormal fetal heart rate: When the fetal heart rate is abnormal, the module will recommend an ultrasound examination, monitoring of fetal movement, and, depending on the situation, arrange medical actions such as an emergency cesarean section; Pregnant women with hypertension: It is recommended to monitor blood pressure regularly, avoid strenuous exercise, and use medication to control blood pressure if necessary. Hospitalization for observation is also recommended. Fetal growth restriction: It is recommended to conduct a detailed ultrasound examination and hemodynamic monitoring, observe the fetal growth curve, and adjust the pregnant woman's diet and rest in a timely manner. 7) Medical staff will receive detailed warning reports and further assess the health of the pregnant woman and fetus based on the data provided by the system, deciding whether to conduct more examinations and arrange hospitalization for observation. At this time, doctors can view the patient's historical health records through the system to conduct more comprehensive analysis and decision-making. 8) The system collects feedback from doctors and patients after each abnormal warning to optimize the machine learning model. At the same time, the system can make customized warning strategies according to different regions and medical conditions. The patient feedback and intervention module can provide real-time feedback of various maternal and fetal monitoring data to the patient's end. Medical staff can also view various health data and analysis results in real time through mobile and computer terminals. At the same time, the system provides intervention suggestions to help medical staff make decisions more quickly. The case database and cloud management module can establish a regional maternal-fetal health case database, which facilitates subsequent case queries, data analysis and research. By performing regional cluster analysis on the data, the characteristics and patterns of maternal-fetal health in different regions can be discovered. The maternal-fetal health case database in the case database and cloud management module is built on a cloud server and uses a distributed storage system to ensure high availability and scalability of the data. The database architecture includes the following key modules: Patient Information Form: Stores basic personal information, including the pregnant woman's age, address, health condition, and medical history; Health monitoring data sheet: Records the physiological data of pregnant women and fetuses, including heart rate, blood sugar, blood pressure and body temperature. Data timestamps ensure the timeliness of the records. Prenatal checkup record form: Records detailed information about each prenatal checkup, including ultrasound reports, laboratory results, and fetal health assessments; Medical intervention record form: includes all medical interventions, including medication prescriptions, emergency interventions, and hospitalization records; Health Risk Assessment Form: A health risk scoring form generated based on machine learning models, rule thresholds, and human assessment to help hospitals make decisions; The above data tables will be linked horizontally and vertically to ensure that a pregnant woman's health data can be tracked through a unique identifier, making it easy for doctors to view the patient's history.

[0023] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0024] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A case tracking system for maternal-fetal congenital abnormalities based on regional big data, characterized in that, include: The data acquisition module collects various physiological data of pregnant women and fetuses through networked medical devices, sensors, and mobile terminals; The physiological data includes changes in the pregnant woman's body temperature, blood pressure, heart rate, and weight, as well as the fetal movement frequency, fetal heart rate monitoring data, and ultrasound examination data. The data transmission and storage module transmits the collected data to the cloud platform via a wireless network. All health-related data is centrally stored on the cloud server. Encryption technology is used during the data transmission process to ensure data security and privacy. The big data analytics module uses machine learning and artificial intelligence algorithms to conduct in-depth analysis of a large amount of maternal and fetal health data, uncover potential disease patterns and trends, analyze the health status of pregnant women and fetuses in real time, generate health reports and compare them with historical cases, conduct real-time risk assessment and prediction, and identify potential risks of congenital abnormalities. The case tracking and early warning module generates real-time abnormal early warning information based on the results of big data analysis. In addition, it has a built-in early warning threshold. When the monitoring status of pregnant women and fetuses exceeds the normal range, the system will automatically send an early warning notification to relevant medical staff and provide timely intervention suggestions. The patient feedback and intervention module can provide real-time feedback of various maternal and fetal monitoring data to the patient's end. Medical staff can also view various health data and analysis results in real time through mobile and computer terminals. At the same time, the system provides intervention suggestions to help medical staff make decisions more quickly. The case database and cloud management module can establish a regional maternal-fetal health case database, which facilitates subsequent case queries, data analysis and research. By performing regional cluster analysis on the data, the characteristics and patterns of maternal-fetal health in different regions can be discovered.

2. The maternal-fetal congenital abnormality case tracking system based on regional big data according to claim 1, characterized in that, The data acquisition module collects health information through smart wearable devices, ultrasound devices, and mobile sensors. The smart wearable devices include medical facilities such as smartwatches, blood pressure monitors, fetal heart rate monitors, and blood glucose meters. The ultrasound devices can periodically check the growth and development of the fetus, monitor the fetal weight, bone development, and fetal position. The mobile sensors include the accelerometer and GPS module built into a smartphone. The raw data collected by the data acquisition module needs to undergo noise reduction, deduplication, and standardization processing to ensure data accuracy.

3. The maternal-fetal congenital abnormality case tracking system based on regional big data according to claim 1, characterized in that, The data transmission and storage module uses an end-to-end encryption algorithm during transmission to ensure that even if the data is intercepted, unauthorized parties cannot read the data content. The data transmission steps are as follows: 1) Compress the data preprocessed by the data acquisition module to reduce the size of the data packets and improve transmission efficiency; 2) For large data packets, fragmentation technology is used to split them into multiple smaller packets for transmission. This can avoid packet loss and delay during the transmission of a single large data packet. Sequence numbers are used to mark each fragment during transmission to ensure that the receiving end can reassemble the data in the correct order. 3) If network instability occurs during data transmission, data can be saved through a local caching mechanism and resent after the network is restored to ensure that the data is not lost; The data transmission and storage module uses cloud storage, selecting one of Amazon S3, Azure BlobStorage, or Google Cloud Storage as the storage medium. At the same time, important case data is backed up regularly using automated tools to ensure rapid recovery in case of data loss.

4. The maternal-fetal congenital abnormality case tracking system based on regional big data according to claim 1, characterized in that, The big data analysis module trains a model using historical case data to identify risk patterns for congenital diseases. Its identification features are as follows: The data acquisition module collects various test data, the pregnant woman's age, weight, BMI and history of gestational hyperglycemia and hypertension, fetal development indicators including weight, heart rate, head circumference and umbilical cord entanglement, and the pregnant woman's family genetic data, including gene mutation index and family history of genetic diseases. The potential disease risk assessment uses a logistic regression model, the specific model of which is as follows: in It is the probability of the fetus being sick. These are the features of the input. These are regression coefficients, which are optimized using maximum likelihood estimation. The aforementioned risk and assessment uses a trained model to predict new maternal and fetal health data, thereby identifying potential diseases, wherein: Regression-based risk assessment generates individual risk scores based on the probability values ​​output by the model. in, It is the predicted probability of each feature. It is the weight of that feature; The health assessment report assesses the health status of the pregnant woman and fetus based on the risk score output by the model, compares the current data with similar data in historical cases, and assesses whether the disease risk has changed.

5. The maternal-fetal congenital abnormality case tracking system based on regional big data according to claim 1, characterized in that, The specific steps of the case tracking and early warning module are as follows: 1) During real-time monitoring, the big data analytics module performs rule-based threshold judgments based on the data analysis results; 2) Formulate abnormal early warning rules based on various thresholds; 3) Assign different risk levels to different types of abnormalities to ensure that high-risk cases are treated first; 4) When the case tracking and early warning module detects abnormal data, it promptly activates the notification mechanism to send early warning information to relevant personnel. The notification mechanism is set to be dual-ended, including: Notification to medical staff: Warning information will be sent to medical staff in a timely manner through SMS, APP push and manual communication. The information includes abnormal data, risk level and suggestions for further examination. Patient notification: The pregnant woman will be notified of mild abnormalities via SMS, APP push, and telephone, and advised to seek medical attention promptly; 5) For high-risk warnings, the module will generate an emergency response notification, recommending immediate medical attention and contacting a doctor, and providing emergency contact information. At this time, the warning notification will not only be sent to medical staff, but also require the patient to take immediate medical intervention. 6) The intervention module will automatically generate corresponding interference suggestions based on abnormal data and warning levels; 7) Medical staff will receive detailed warning reports and further assess the health of the pregnant woman and fetus based on the data provided by the system, deciding whether to conduct more examinations and arrange hospitalization for observation. At this time, doctors can view the patient's historical health records through the system to conduct more comprehensive analysis and decision-making. 8) The system collects feedback from doctors and patients after each abnormal warning to optimize the machine learning model. At the same time, the system can make customized warning strategies according to different regions and medical conditions.

6. The maternal-fetal congenital abnormality case tracking system based on regional big data according to claim 5, characterized in that, The warning rules are as follows: Abnormal fetal heart rate: too fast (>180 bpm) and too slow (<110 bpm). Abnormal blood pressure in pregnant women: higher than 140 / 90 mmHg (hypertension), lower than 90 / 60 mmHg (hypotension); Fetal movement frequency is lower than the normal range: Too few fetal movements (<10 times / 24 hours). Abnormal fetal growth: Fetal weight gain below the normal percentile may lead to intrauterine growth retardation; The risk levels are as follows: Red high-risk warning: fetal heart rate too fast or too slow, severe blood sugar abnormalities and high blood pressure; Orange-level medium-risk warning: decreased fetal movement, mild blood pressure abnormalities, and mild body temperature fluctuations; Yellow low-risk warning: fluctuations in the pregnant woman's weight and slight irregular fetal movements.

7. The maternal-fetal congenital abnormality case tracking system based on regional big data according to claim 5, characterized in that, The specific interference suggestions are as follows: Abnormal fetal heart rate: When the fetal heart rate is abnormal, the module will recommend an ultrasound examination, monitoring of fetal movement, and, depending on the situation, arrange medical actions such as an emergency cesarean section; Pregnant women with hypertension: It is recommended to monitor blood pressure regularly, avoid strenuous exercise, and use medication to control blood pressure if necessary. Hospitalization for observation is also recommended. Fetal growth restriction: It is recommended to conduct a detailed ultrasound examination and hemodynamic monitoring, observe the fetal growth curve, and adjust the pregnant woman's diet and rest in a timely manner.

8. The maternal-fetal congenital abnormality case tracking system based on regional big data according to claim 1, characterized in that, The case database and the maternal-fetal health case database in the cloud management module are built on a cloud server, and a distributed storage system is used to ensure high availability and scalability of the data. The database architecture includes the following key modules: Patient Information Form: Stores basic personal information, including the pregnant woman's age, address, health condition, and medical history; Health monitoring data sheet: Records the physiological data of pregnant women and fetuses, including heart rate, blood sugar, blood pressure and body temperature. Data timestamps ensure the timeliness of the records. Prenatal checkup record form: Records detailed information about each prenatal checkup, including ultrasound reports, laboratory results, and fetal health assessments; Medical intervention record form: includes all medical interventions, including medication prescriptions, emergency interventions, and hospitalization records; Health Risk Assessment Form: A health risk scoring form generated based on machine learning models, rule thresholds, and human assessment to help hospitals make decisions; The above data tables will be linked horizontally and vertically to ensure that a pregnant woman's health data can be tracked through a unique identifier, making it easy for doctors to view the patient's history.

Images