A Pregnancy Outcome Prediction System Based on Electronic Medical Records

Abstract

This invention proposes a pregnancy outcome prediction system based on electronic medical records. The system includes a data acquisition terminal, a data transmission device, a cloud terminal, and a data prediction terminal. The data acquisition terminal is used to collect electronic medical record information of pregnant users from a database in real time and dynamically adjust the information update query frequency based on database data retrieval parameters. The data transmission device is used to establish data communication connections and adjust communication frequencies between the data acquisition terminal and the data prediction terminal, between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal. The data prediction terminal is used to obtain pregnancy prediction results based on preprocessed medical record data and to visualize the prediction results. The cloud terminal is used to store the data information sent by the data acquisition terminal and the data prediction terminal in the cloud.

Description

Technical Field

[0001] This invention proposes a pregnancy outcome prediction system based on electronic medical records, belonging to the field of risk assessment technology based on electronic medical records. Background Technology

[0002] With the rapid development of medical information technology, electronic medical record (EMR) systems have become an indispensable part of the modern healthcare system. EMRs not only record detailed information such as the patient's diagnosis and treatment process, examination results, and medication use, but also provide rich data resources for clinical decision support, disease prediction, and prevention. In obstetrics and gynecology, pregnancy outcome prediction is of great significance to pregnant women and their families, medical institutions, and society as a whole. However, traditional methods for predicting pregnancy outcomes often rely on doctors' experience or simple statistical analysis, resulting in high subjectivity and insufficient accuracy. In recent years, with the rise of big data and artificial intelligence technologies, research on pregnancy outcome prediction based on EMR data has gradually gained attention. By mining the rich information contained in EMRs and combining it with advanced algorithm models, accurate prediction of pregnancy outcomes can be achieved, providing strong support for clinical decision-making. However, currently, there is no complete and efficient pregnancy outcome prediction system based on EMRs on the market to meet the high requirements of medical institutions for pregnancy management.

[0003] While some studies have attempted to use electronic medical record data for disease prediction, most of these studies focus on single diseases or specific populations. Furthermore, the data processing is complex, and the prediction models are limited, making it difficult to adapt to the complex scenario of pregnancy outcome prediction. In addition, existing systems often lack real-time data acquisition and dynamic adjustment mechanisms, failing to reflect changes in the patient's condition in a timely manner, thus affecting the accuracy and timeliness of the prediction results.

[0004] Therefore, this invention proposes a pregnancy outcome prediction system based on electronic medical records. It aims to achieve real-time collection, efficient transmission, and intelligent analysis of electronic medical record information for pregnant women by integrating multiple stages such as data acquisition, transmission, processing, and prediction, thereby providing accurate and timely pregnancy outcome prediction services. This system not only solves the problems of insufficient prediction accuracy and low data processing efficiency in existing technologies, but also improves the intuitiveness and ease of use of prediction results through visualization, providing medical institutions and patients with more convenient and efficient pregnancy management services. Summary of the Invention

[0005] This invention provides a pregnancy outcome prediction system based on electronic medical records to solve the technical problems existing in the prior art. The technical solution adopted is as follows:

[0006] A pregnancy outcome prediction system based on electronic medical records includes a data acquisition terminal, a data transmission device, a cloud terminal, and a data prediction terminal. The data acquisition terminal is connected to the data prediction terminal via the data transmission device. The data acquisition terminal and the data prediction terminal are connected to the cloud terminal via the data transmission device.

[0007] The data acquisition terminal is used to collect electronic medical record information of pregnant users from the database in real time, and dynamically adjust the information update query frequency according to the data retrieval and operation parameters of the database.

[0008] The data transmission device is used to establish data communication connections and adjust communication frequencies between the data acquisition terminal and the data prediction terminal, between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal.

[0009] The data prediction terminal is used to obtain pregnancy prediction results based on preprocessed medical record data and to visualize the prediction results.

[0010] The cloud terminal is used for cloud storage of data information sent by the data acquisition terminal and the data prediction terminal.

[0011] Furthermore, the data acquisition terminal includes:

[0012] The data update monitoring module is used to monitor in real time whether the electronic medical record information corresponding to pregnant users in the database has been updated.

[0013] The update data retrieval module is used to retrieve the updated data information when the electronic medical record information corresponding to the pregnant user is updated.

[0014] The data preprocessing module is used to preprocess the updated data information to obtain preprocessed medical record data information; wherein, the preprocessing includes data noise reduction, data cleaning and data standardization.

[0015] The data update retrieval monitoring module is used to monitor the data retrieval operation parameters of the data update retrieval module in real time, and dynamically adjust the query frequency of the data update monitoring module for the database update information based on the data retrieval operation parameters.

[0016] Furthermore, the operation process of the data update retrieval monitoring module includes:

[0017] The data retrieval operation parameters of the updated data retrieval module are monitored in real time, including the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency.

[0018] The data retrieval quality operation index parameters are obtained by using the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency.

[0019] When the data retrieval quality operation index parameters are lower than the preset operation index parameter threshold, the frequency of the data update monitoring module querying the database update information is adjusted.

[0020] Furthermore, the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency are used to obtain data retrieval quality operation index parameters, including:

[0021] Compare the complete scale parameter of the entire data retrieved during the data retrieval process with the preset complete scale parameter threshold;

[0022] When the overall completeness ratio parameter of the data is lower than the preset completeness ratio parameter threshold, the data retrieval response time for incomplete data is reduced.

[0023] The quality operation index parameters are obtained by combining the data retrieval response time of the incomplete data with the frequency of data retrieval errors; wherein, the quality operation index parameters are obtained by the following formula:

[0024]

[0025] Where S represents the quality operation index parameter; n represents the number of times incomplete data was retrieved; m represents the number of times data retrieval errors occurred; T c This indicates the preset data retrieval time reference value; T i T represents the data retrieval time corresponding to the i-th incomplete data retrieval; j represents the data retrieval duration corresponding to the j-th data retrieval error; p represents the complete proportion parameter of the entire retrieved data; p0 represents the preset complete proportion parameter threshold.

[0026] Furthermore, when the data retrieval quality operation index parameters are lower than the preset operation index parameter threshold, the frequency of the data update monitoring module's query frequency for update information in the database is adjusted, including:

[0027] When the data retrieval quality operation index parameters are lower than the preset operation index parameter threshold, the current data update monitoring module retrieves the query frequency of update information in the database and the lowest value of the data update frequency of pregnant users in the database.

[0028] Retrieve the change rate of concurrent connections, lock wait time, and lock conflict count corresponding to the current database operation;

[0029] The database operating load characterization coefficient is obtained by utilizing the rate of change of concurrent connections, the rate of change of lock wait time, and the rate of change of lock conflict count corresponding to the current database operation; wherein, the database operating load characterization coefficient is obtained by the following formula:

[0030]

[0031] Where L represents the database operating load characterization coefficient; S represents the quality operation index parameter; S0 represents the preset operating index parameter threshold; k represents the number of unit time intervals experienced by the database operation, and the unit time interval is 1 second; N i W represents the rate of change of the number of concurrent connections in the i-th unit of time; i C represents the rate of change of lock wait time corresponding to the i-th unit of time; i This represents the rate of change of the number of lock conflicts in the i-th unit of time;

[0032] The adjusted update information query frequency is obtained by combining the database operation load characterization coefficient with the database update information query frequency and the lowest data update frequency of pregnant users in the database;

[0033] The adjusted update information query frequency is obtained using the following formula:

[0034]

[0035] Among them, F new Indicates the adjusted frequency of update information queries; F c The value represents the query frequency of the database update information before adjustment; L represents the database operating load characterization coefficient; F represents the database operating load characterization coefficient. min This represents the lowest data update frequency for pregnant users in the database.

[0036] Furthermore, the data transmission device includes a first data transmission device and a second data transmission device;

[0037] The first data transmission device is used to establish a data communication connection between the data acquisition terminal and the data prediction terminal, and to dynamically adjust the communication frequency between the data acquisition terminal and the data prediction terminal according to the change in the update information query frequency of the data acquisition terminal.

[0038] The second data transmission device is used to establish data communication connections between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal, and to dynamically adjust the communication frequency between the data acquisition terminal and the cloud terminal according to the changes in the update information query frequency of the data acquisition terminal.

[0039] Furthermore, the operation of the first data transmission device includes:

[0040] Establish a data communication connection between the data acquisition terminal and the data prediction terminal;

[0041] The update information query frequency of the data acquisition terminal is retrieved in real time, and it is determined whether the update information query frequency of the data acquisition terminal has changed.

[0042] When the update information query frequency of the data acquisition terminal changes, the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal is adjusted using the changed update information query frequency.

[0043] The adjusted communication frequency is obtained using the following formula:

[0044]

[0045] Among them, R new01 This indicates the adjusted communication frequency corresponding to the communication connection between the data acquisition terminal and the data prediction terminal; R c01 This indicates the communication frequency before adjustment corresponding to the communication connection between the data acquisition terminal and the data prediction terminal; F new Indicates the adjusted frequency of update information queries; F c L represents the database update query frequency before adjustment; L represents the database operating load characterization coefficient; L max λ represents the maximum value of the database operation load characterization coefficient; λ represents the preset attenuation coefficient, which is used to determine the sensitivity of the communication frequency adjustment to changes in the frequency of updating information query; e represents the base of the natural logarithm.

[0046] Furthermore, the operation of the second data transmission device includes:

[0047] Establish a data communication connection between the data acquisition terminal and the cloud terminal;

[0048] Establish a data communication connection between the data prediction terminal and the cloud terminal;

[0049] The update information query frequency of the data acquisition terminal is retrieved in real time, and it is determined whether the update information query frequency of the data acquisition terminal has changed.

[0050] When the update information query frequency of the data acquisition terminal changes, the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal will change.

[0051] The communication frequency between the data acquisition terminal and the cloud terminal is adjusted by combining the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal with the frequency of querying updated information after the change.

[0052] The adjusted communication frequency between the data acquisition terminal and the cloud terminal is obtained using the following formula:

[0053]

[0054] Among them, R new02 This indicates the adjusted communication frequency between the data acquisition terminal and the cloud terminal; R c02 This indicates the communication frequency between the data acquisition terminal and the cloud terminal before the adjustment; F new Indicates the adjusted frequency of update information queries; R new01 The adjusted communication frequency corresponds to the communication connection between the data acquisition terminal and the data prediction terminal; L represents the database operating load characterization coefficient; L max λ represents the maximum value of the database operation load characterization coefficient; λ represents the preset attenuation coefficient, which is used to determine the sensitivity of the communication frequency adjustment to changes in the frequency of updating information query; e represents the base of the natural logarithm.

[0055] Furthermore, the data prediction terminal includes:

[0056] The real-time receiving and monitoring module is used to monitor in real time whether preprocessed medical record data information has been received;

[0057] The data input module is used to input the preprocessed medical record data into the deep learning model that has been trained and optimized after testing when it receives the preprocessed medical record data.

[0058] The prediction and visualization module is used to obtain the prediction results of pregnancy by combining the preprocessed medical record data with the deep learning model that has been trained and tested and optimized, and to visualize the prediction results of pregnancy. The prediction results of pregnancy include the prediction of whether the pregnancy is likely to proceed smoothly to full term and the prediction of the delivery method.

[0059] Furthermore, the structure of the deep learning model is as follows:

[0060] The input layer is used to receive preprocessed medical record data in real time, including but not limited to the patient's basic information, biochemical indicators, medical history, and examination results.

[0061] Convolutional Neural Networks (CNNs) are used to process image data, such as ultrasound images, to extract spatial features.

[0062] Recurrent neural networks (RNNs) are used to process time-series data, such as tracking changes in follow-up data of pregnant women.

[0063] Fully connected (Dense Layers) are used to process structured data, using multilayer perceptrons to learn non-linear relationships between data.

[0064] The feature fusion layer is used to fuse the output data of convolutional neural networks, recurrent neural networks, and fully connected layers. The key to this layer is to integrate data features from different sources and in different forms, which can be achieved using simple concatenation or more complex fusion techniques such as feature weighting.

[0065] A classification layer, which includes binary classification output and multi-class classification output;

[0066] One output node corresponding to the binary classification output is used to predict whether the pregnancy can proceed smoothly to full term;

[0067] Another set of output nodes corresponding to the multi-class output is used to predict the mode of delivery, such as natural childbirth or cesarean section. The softmax function can be used to handle this multi-class output.

[0068] The output layer is used to output specific prediction results, including the probability of full-term pregnancy and the classification results of delivery mode;

[0069] The post-processing layer is used to interpret the raw predictions output by the model and transform them into data information that is easy for doctors and patients to understand.

[0070] Beneficial effects of this invention:

[0071] This invention proposes a pregnancy outcome prediction system based on electronic medical records. By integrating multiple stages such as data acquisition, transmission, processing, and prediction, it achieves comprehensive, real-time collection and intelligent analysis of pregnant users' electronic medical record information, improving the accuracy and reliability of pregnancy outcome prediction. Automated data acquisition and transmission processes reduce manual intervention and errors, improving the efficiency of data processing and prediction. Simultaneously, dynamically adjusted information query and communication frequencies further optimize system performance and reduce resource consumption. The visualization function makes the prediction results more intuitive and easy to understand, allowing users to quickly understand their pregnancy status and risk predictions without requiring specialized knowledge, enhancing user experience and satisfaction. Accurate pregnancy outcome prediction provides doctors with strong decision support, enabling the development of more personalized and scientific treatment plans, improving the quality of medical services and patient satisfaction. Attached Figure Description

[0072] Figure 1 This is a system block diagram of the pregnancy outcome prediction system based on electronic medical records according to the present invention. Detailed Implementation

[0073] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0074] This invention proposes a pregnancy outcome prediction system based on electronic medical records, such as... Figure 1 As shown, the pregnancy outcome prediction system based on electronic medical records includes a data acquisition terminal, a data transmission device, a cloud terminal, and a data prediction terminal; wherein, the data acquisition terminal is connected to the data prediction terminal via the data transmission device; and the data acquisition terminal and the data prediction terminal are connected to the cloud terminal via the data transmission device.

[0075] The data acquisition terminal is used to collect electronic medical record information of pregnant users from the database in real time, and dynamically adjust the information update query frequency according to the data retrieval and operation parameters of the database.

[0076] The data transmission device is used to establish data communication connections and adjust communication frequencies between the data acquisition terminal and the data prediction terminal, between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal.

[0077] The data prediction terminal is used to obtain pregnancy prediction results based on preprocessed medical record data and to visualize the prediction results.

[0078] The cloud terminal is used for cloud storage of data information sent by the data acquisition terminal and the data prediction terminal.

[0079] The working principle of the above technical solution is as follows: The terminal first establishes a connection with a medical institution or relevant database, and collects the electronic medical record information of pregnant users in real time through a preset interface or protocol. This information includes, but is not limited to, the pregnant woman's basic information (such as age, weight, parity, etc.), past medical history, current pregnancy status (such as gestational age, prenatal examination results, etc.), medication records, etc. The data collection terminal also has intelligent analysis capabilities, which can dynamically adjust its information query frequency according to the data retrieval and operation parameters of the database (such as data update frequency, query load, etc.) to ensure that the latest data can be obtained in a timely manner while avoiding excessive access pressure on the database.

[0080] Data transmission device: This device acts as a bridge for data transmission, responsible for establishing stable and efficient data communication connections between data acquisition terminals, data prediction terminals, and cloud terminals. It supports multiple communication protocols and encryption technologies to ensure the security, reliability, and real-time performance of data transmission. Simultaneously, the transmission device also features a communication frequency adjustment function, dynamically adjusting the data transmission rate and frequency according to actual data transmission needs and network conditions to optimize data transmission efficiency.

[0081] Cloud Terminal: As the central hub for data storage and processing, the cloud terminal receives data from data acquisition and prediction terminals. It possesses powerful data processing capabilities and ample storage space, enabling rapid retrieval, analysis, and mining of massive amounts of electronic medical record information. The cloud terminal also handles data backup and recovery, ensuring data security and availability.

[0082] Data Prediction Terminal: After receiving preprocessed medical record data, this terminal uses advanced algorithm models (such as machine learning and deep learning) to intelligently analyze the data and obtain pregnancy prediction results. These predictions may include the probability of pregnancy success, risk of complications, and recommendations for delivery methods. The data prediction terminal also features visualization capabilities, presenting complex prediction results intuitively to users in the form of charts and reports, facilitating user understanding and decision-making.

[0083] The above technical solution achieves the following effects: By integrating multiple stages such as data collection, transmission, processing, and prediction, it enables comprehensive, real-time collection and intelligent analysis of electronic medical record information for pregnant users, improving the accuracy and reliability of pregnancy outcome prediction. Automated data collection and transmission processes reduce human intervention and errors, improving the efficiency of data processing and prediction. Simultaneously, dynamically adjusted information query and communication frequencies further optimize system performance and reduce resource consumption. The visualization function makes the prediction results more intuitive and easy to understand, allowing users to quickly understand their pregnancy status and risk predictions without requiring specialized knowledge, enhancing user experience and satisfaction. Accurate pregnancy outcome prediction provides doctors with strong decision support, enabling the development of more personalized and scientific treatment plans, improving the quality of medical services and patient satisfaction.

[0084] In one embodiment of the present invention, the data acquisition terminal includes:

[0085] The data update monitoring module is used to monitor in real time whether the electronic medical record information corresponding to pregnant users in the database has been updated.

[0086] The update data retrieval module is used to retrieve the updated data information when the electronic medical record information corresponding to the pregnant user is updated.

[0087] The data preprocessing module is used to preprocess the updated data information to obtain preprocessed medical record data information; wherein, the preprocessing includes data noise reduction, data cleaning and data standardization.

[0088] The data update retrieval monitoring module is used to monitor the data retrieval operation parameters of the data update retrieval module in real time, and dynamically adjust the query frequency of the data update monitoring module for the database update information based on the data retrieval operation parameters.

[0089] The operation process of the data update retrieval monitoring module includes:

[0090] S1. Monitor the data retrieval operation parameters of the updated data retrieval module in real time, wherein the data retrieval operation parameters include the data retrieval completeness ratio, data retrieval response time, and data retrieval error occurrence frequency;

[0091] S2. Obtain data retrieval quality operation index parameters using the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency.

[0092] S3. When the data retrieval quality operation index parameter is lower than the preset operation index parameter threshold, the frequency of the data update monitoring module querying the database update information is adjusted.

[0093] The working principle of the above technical solution is as follows: This module continuously monitors whether the electronic medical record information corresponding to pregnant users in the database has been updated. When an update is detected, it triggers the subsequent data retrieval process.

[0094] Updated Data Retrieval Module: Once the data update monitoring module detects a data update, this module will immediately retrieve the updated data from the database. This data includes, but is not limited to, newly generated test results, medication records, or other pregnancy-related medical information.

[0095] Data Preprocessing Module: After the data is successfully retrieved, the data preprocessing module performs a series of preprocessing operations on the updated data to ensure data quality and consistency. These preprocessing steps include data denoising (removing noisy data), data cleaning (correcting or deleting erroneous, incomplete, or inconsistent data), and data standardization (converting the data into a uniform format for easier subsequent analysis).

[0096] Data Update Retrieval Monitoring Module: This module is responsible for monitoring the operational status of the data retrieval module, specifically including real-time monitoring of data retrieval parameters. These parameters include the data retrieval completeness ratio (measuring whether the data is complete), data retrieval response time (measuring data retrieval speed), and data retrieval error frequency (measuring the error rate during data retrieval). Using these parameters, the module can evaluate the quality of data retrieval and adjust the frequency of database update information queries by the data update monitoring module accordingly.

[0097] During monitoring, if the data retrieval quality performance indicators (calculated based on the three parameters mentioned above) fall below the preset threshold, it indicates a problem with data retrieval efficiency or quality, which may be due to excessive database load, network latency, or other factors. In this case, the data update retrieval monitoring module will trigger an adjustment mechanism to reduce the frequency of database queries by the data update monitoring module, thereby alleviating system burden and improving overall operating efficiency.

[0098] The effect of the above technical solution is that by monitoring data updates in real time and retrieving them immediately, the timeliness and accuracy of the data are ensured, providing the latest and most accurate data foundation for pregnancy outcome prediction.

[0099] Optimized data processing workflows: The data preprocessing module effectively improves data quality through noise reduction, cleaning, and standardization, providing a reliable data source for subsequent data analysis and prediction. The data update retrieval monitoring module monitors data retrieval parameters in real time and dynamically adjusts the query frequency based on actual conditions, effectively avoiding excessive system load caused by excessive queries and improving the overall system performance and stability. By optimizing the data processing and query workflows, user waiting time is reduced, system response speed is improved, and user experience is enhanced. High-quality data processing and analysis results provide doctors with more accurate and comprehensive information for predicting pregnancy outcomes, enabling them to develop more scientific and personalized treatment plans.

[0100] In one embodiment of the present invention, data retrieval quality operation index parameters are obtained using the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency, including:

[0101] S201. Compare the complete scale parameter of the entire data retrieved during the data retrieval process with the preset complete scale parameter threshold.

[0102] S202. When the overall completeness ratio parameter of the data is lower than the preset completeness ratio parameter threshold, the data retrieval response time for incomplete data is reduced.

[0103] S203. Obtain quality operation index parameters by combining the data retrieval response time of the incomplete data with the data retrieval error frequency; wherein, the quality operation index parameters are obtained by the following formula:

[0104]

[0105] Where S represents the quality operation index parameter; n represents the number of times incomplete data was retrieved; m represents the number of times data retrieval errors occurred; T c This indicates the preset data retrieval time reference value; T iT represents the data retrieval time corresponding to the i-th incomplete data retrieval; j represents the data retrieval duration corresponding to the j-th data retrieval error; p represents the complete proportion parameter of the entire retrieved data; p0 represents the preset complete proportion parameter threshold.

[0106] The working principle of the above technical solution is as follows: First, the system compares the actual data retrieval completeness ratio parameter (i.e., the proportion of complete data in the actual retrieved data) with a preset completeness ratio parameter threshold. The purpose of this step is to determine whether the completeness of the retrieved data meets the basic requirements. If the overall completeness ratio parameter is lower than the preset threshold, it indicates that there is incomplete data retrieval. At this time, the system will further retrieve the data retrieval response time of these incomplete data, that is, the time spent by the system from issuing a data retrieval request to successfully obtaining the data (regardless of whether the data is complete). Based on the data retrieval response time of incomplete data and the frequency of data retrieval errors, combined with the preset data retrieval time reference value (Tc), a quality operation index parameter (S) is calculated through a specific formula. This parameter comprehensively considers multiple aspects such as data completeness, retrieval efficiency, and error rate, and can comprehensively reflect the quality status of data retrieval.

[0107] The above technical solution achieves the following results: through specific formulas and parameters, it enables a quantitative assessment of data retrieval quality, making data quality monitoring more scientific and objective. By real-time monitoring and calculation of quality operation indicators, the system can promptly identify problems in the data retrieval process (such as incomplete data, low retrieval efficiency, and high error rates), and take corresponding measures to resolve them, ensuring data quality and availability.

[0108] Based on feedback from quality operation indicators, the system can dynamically adjust its data retrieval strategy (such as adjusting query frequency and optimizing query algorithms) to reduce system load, improve data retrieval efficiency, and thus optimize overall system performance. High-quality data retrieval services can reduce user waiting time and improve data accuracy, thereby enhancing user experience and satisfaction. Accurate and reliable data is the foundation of intelligent decision-making. Through the above technical solutions, medical institutions can obtain more comprehensive and accurate patient data, providing stronger support for clinical decision-making.

[0109] In one embodiment of the present invention, when the data retrieval quality operation index parameter is lower than a preset operation index parameter threshold, the frequency of the data update monitoring module querying the database update information is adjusted, including:

[0110] S301. When the data retrieval quality operation index parameter is lower than the preset operation index parameter threshold, retrieve the current data update monitoring module's query frequency of update information in the database and the lowest value of the data update frequency of pregnant users in the database.

[0111] S302. Retrieve the change rate of concurrent connections, lock wait time, and lock conflict count corresponding to the current database operation.

[0112] S303. Obtain the database operating load characterization coefficient using the rate of change of concurrent connections, the rate of change of lock wait time, and the rate of change of lock conflict count corresponding to the current database operation; wherein, the database operating load characterization coefficient is obtained by the following formula:

[0113]

[0114] Where L represents the database operating load characterization coefficient; S represents the quality operation index parameter; S0 represents the preset operating index parameter threshold; k represents the number of unit time intervals experienced by the database operation, and the unit time interval is 1 second; N i W represents the rate of change of the number of concurrent connections in the i-th unit of time; i C represents the rate of change of lock wait time corresponding to the i-th unit of time; i This represents the rate of change of the number of lock conflicts in the i-th unit of time;

[0115] S304. The adjusted update information query frequency is obtained by combining the database operation load characterization coefficient with the database update information query frequency and the lowest data update frequency of pregnant users in the database.

[0116] The adjusted update information query frequency is obtained using the following formula:

[0117]

[0118] Among them, F new Indicates the adjusted frequency of update information queries; F c The value represents the query frequency of the database update information before adjustment; L represents the database operating load characterization coefficient; F represents the database operating load characterization coefficient. min This represents the lowest data update frequency for pregnant users in the database.

[0119] The working principle of the above technical solution is as follows: when the data retrieval quality operation index parameter is lower than the preset operation index parameter threshold, the system considers that the current data retrieval quality does not meet the requirements and needs to adjust the query frequency of the data update monitoring module.

[0120] The system first retrieves the current query frequency of the data update monitoring module for database updates (i.e., the query frequency before adjustment) and the lowest update frequency for pregnant users in the database. This lowest value reflects the slowest update speed of pregnant user data in the database and is an important factor to consider when adjusting the query frequency.

[0121] The system assesses the database's operational load by retrieving key metrics such as the rate of change in concurrent connections, the rate of change in lock wait time, and the rate of change in lock conflict counts. These metrics reflect performance bottlenecks and potential problems in the database's query processing. Then, using these metrics, a database operational load characterization coefficient (L) is calculated using a specific formula. This coefficient quantifies the current operational load status of the database.

[0122] Finally, the system combines the database load characterization coefficient (L), the query frequency before adjustment (Fc), and the minimum data update frequency for pregnant users in the database (Fmin) to calculate the adjusted update information query frequency (Fnew) using a specific formula. This adjustment process aims to reduce the database load and improve the overall performance and stability of the system while ensuring data real-time performance.

[0123] The above technical solution achieves the following effects: By real-time monitoring of data to retrieve quality operation index parameters and database operating load, the query frequency of the data update monitoring module is dynamically adjusted. This ensures both the real-time nature and accuracy of the data while avoiding database performance degradation due to excessive queries. By rationally adjusting the query frequency, the database burden is reduced, lock wait time and the number of lock conflicts are decreased, improving the system's concurrent processing capacity and overall performance. Simultaneously, it reduces system instability caused by query conflicts and data inconsistencies. While ensuring data quality, optimizing the query frequency improves system response speed and user experience. Users can obtain the necessary pregnancy user data more quickly, providing more timely and accurate information support for clinical decision-making. Through this technical solution, medical institutions can obtain more accurate, timely, and comprehensive pregnancy user data, providing stronger support for clinical decision-making. Furthermore, the system can intelligently adjust and optimize based on the actual data situation and database operating status, further improving the level of intelligent decision-making.

[0124] In one embodiment of the present invention, the data transmission device includes a first data transmission device and a second data transmission device;

[0125] The first data transmission device is used to establish a data communication connection between the data acquisition terminal and the data prediction terminal, and to dynamically adjust the communication frequency between the data acquisition terminal and the data prediction terminal according to the change in the update information query frequency of the data acquisition terminal.

[0126] The second data transmission device is used to establish data communication connections between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal, and to dynamically adjust the communication frequency between the data acquisition terminal and the cloud terminal according to the changes in the update information query frequency of the data acquisition terminal.

[0127] Specifically, the operation of the first data transmission device includes:

[0128] Step a1: Establish a data communication connection between the data acquisition terminal and the data prediction terminal;

[0129] Step a2: Real-time retrieval of the update information query frequency of the data acquisition terminal, and determination of whether the update information query frequency of the data acquisition terminal has changed;

[0130] Step a3: When the update information query frequency of the data acquisition terminal changes, the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal is adjusted using the changed update information query frequency.

[0131] The adjusted communication frequency is obtained using the following formula:

[0132]

[0133] Among them, R new01 This indicates the adjusted communication frequency corresponding to the communication connection between the data acquisition terminal and the data prediction terminal; R c01 This indicates the communication frequency before adjustment corresponding to the communication connection between the data acquisition terminal and the data prediction terminal; F new Indicates the adjusted frequency of update information queries; F c L represents the database update query frequency before adjustment; L represents the database operating load characterization coefficient; L max λ represents the maximum value of the database operation load characterization coefficient; λ represents the preset attenuation coefficient, which is used to determine the sensitivity of the communication frequency adjustment to changes in the frequency of updating information query; e represents the base of the natural logarithm.

[0134] The working principle of the above technical solution is as follows: The first data transmission device first establishes a stable data communication connection between the data acquisition terminal and the data prediction terminal to ensure smooth data transmission between them. This device continuously retrieves the update information query frequency of the data acquisition terminal and determines whether this frequency has changed. This step is the basis for dynamically adjusting the communication frequency, as changes in the update information query frequency may reflect the data acquisition terminal's demand for real-time data. When a change in the update information query frequency of the data acquisition terminal is detected, the first data transmission device adjusts the communication frequency of the connection between the data acquisition terminal and the data prediction terminal using a specific formula, based on the changed query frequency. This adjustment process aims to match the communication frequency with data demand, ensuring real-time data transmission while avoiding unnecessary waste of communication resources.

[0135] The adjusted communication frequency is calculated using a formula that comprehensively considers the original communication frequency, the adjusted update information query frequency, the original database update information query frequency, the database operating load characterization coefficient and its maximum value, as well as a preset attenuation coefficient. This formula is designed to take multiple factors into account, ensuring that the adjusted communication frequency reflects changes in data demand while also considering the database's operating load and system stability.

[0136] The above technical solution achieves the following effect: When the data retrieval quality operation index parameters are lower than the preset operation index parameter threshold (step S301), the above technical solution can automatically trigger an adjustment mechanism to dynamically adjust the update information query frequency based on the current database operation status and data update frequency. This adaptive adjustment ensures that the database can respond and optimize quickly when facing performance bottlenecks or data quality degradation. Comprehensive consideration of database operating load: In steps S302 and S303, the above technical solution comprehensively evaluates the database operating load by monitoring the rate of change of concurrent connections, the rate of change of lock wait time, and the rate of change of lock conflict count. These indicators reflect the database's load and potential performance bottlenecks when processing requests. By calculating the database operating load characterization coefficient L, the above technical solution can quantify the current operating status of the database, providing a scientific basis for subsequent adjustments. Optimization of update information query frequency: In step S304, the above technical solution utilizes the database operating load characterization coefficient L, the database update information query frequency Fc, and the minimum data update frequency Fc for pregnant users in the database. min The adjusted update information query frequency F is calculated using the above formula. new This adjustment strategy aims to minimize database resource consumption and improve overall database efficiency while ensuring timely data updates. It also prioritizes specific user groups: by considering the minimum data update frequency F for pregnant users in the database.min The aforementioned technical solutions ensure that the data update needs of special user groups are met. This is particularly important for applications such as medical care and health management that require real-time monitoring and updating of pregnancy user data, thereby improving user satisfaction and trust. Enhancing system stability and reliability: By dynamically adjusting the frequency of update information queries, the above technical solutions can reduce the pressure on the database under high load, mitigating the risk of system crashes or performance degradation due to untimely data updates or excessively high query frequencies. This improves system stability and reliability, ensuring the continuity and availability of data services.

[0137] Furthermore, by dynamically adjusting the communication frequency, data transmission is matched to data demand in real time, avoiding wasted communication resources when data demand is low and improving the overall efficiency of data transmission. Adjusting the communication frequency based on changes in the frequency of updated information queries reduces unnecessary communication overhead, lowers system load, and optimizes the utilization of system resources. By considering the database operating load characterization coefficient and preset attenuation coefficient, the adjustment process is smoother and more stable, reducing system fluctuations and potential problems caused by frequent communication frequency adjustments. Real-time and accurate data transmission provides reliable data support for data prediction terminals, enabling medical institutions to make more scientific and rational clinical decisions. The optimized data transmission service reduces user waiting time, improves the timeliness and accuracy of data acquisition, and thus enhances the user experience.

[0138] In summary, the above technical solution optimizes and improves database performance by comprehensively considering data retrieval quality, database workload, and the needs of specific user groups, and dynamically adjusting the update information query frequency of the data update monitoring module. This ensures the accuracy and timeliness of data services, and improves the overall system performance and user experience.

[0139] In one embodiment of the present invention, the operation of the second data transmission device includes:

[0140] Step b1: Establish a data communication connection between the data acquisition terminal and the cloud terminal;

[0141] Step b2: Establish a data communication connection between the data prediction terminal and the cloud terminal;

[0142] Step b3: Real-time retrieval of the update information query frequency of the data acquisition terminal, and determination of whether the update information query frequency of the data acquisition terminal has changed;

[0143] Step b4: When the update information query frequency of the data acquisition terminal changes, the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal is adjusted.

[0144] Step b5: Adjust the communication frequency between the data acquisition terminal and the cloud terminal by combining the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal with the changed update information query frequency;

[0145] The adjusted communication frequency between the data acquisition terminal and the cloud terminal is obtained using the following formula:

[0146]

[0147] Among them, R new02 This indicates the adjusted communication frequency between the data acquisition terminal and the cloud terminal; R c02 This indicates the communication frequency between the data acquisition terminal and the cloud terminal before the adjustment; F new Indicates the adjusted frequency of update information queries; R new01 The adjusted communication frequency corresponds to the communication connection between the data acquisition terminal and the data prediction terminal; L represents the database operating load characterization coefficient; L max λ represents the maximum value of the database operation load characterization coefficient; λ represents the preset attenuation coefficient, which is used to determine the sensitivity of the communication frequency adjustment to changes in the frequency of updating information query; e represents the base of the natural logarithm.

[0148] The working principle of the above technical solution is as follows: The second data transmission device first establishes data communication connections between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal, respectively, to ensure smooth data transmission between these terminals. The device retrieves the update information query frequency of the data acquisition terminal in real time and determines whether this frequency has changed. This serves as the basis for subsequently adjusting the communication frequency between the data acquisition terminal and the cloud terminal.

[0149] When a change in the update information query frequency of the data acquisition terminal is detected, although the description of step b4 directly mentions adjusting the communication frequency between the data acquisition terminal and the data prediction terminal, based on the context, it is more likely that this is to explain that the change in the update information query frequency is the condition that triggers the adjustment of the communication frequency, while the actual adjustment operation will target the communication frequency between the data acquisition terminal and the cloud terminal. Based on the adjusted communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal, the change in the update information query frequency of the data acquisition terminal, and factors such as the database operating load characterization coefficient, the communication frequency between the data acquisition terminal and the cloud terminal is calculated and adjusted using a specific formula. This adjustment process aims to enable the cloud terminal to receive and process data from the data acquisition terminal more effectively, while taking into account the communication needs between the data prediction terminal and the cloud terminal and the operating load of the database.

[0150] The above technical solution achieves the following effects: By monitoring and adjusting the communication frequency in real time based on the frequency of updated information queries, data transmission becomes more flexible and can quickly adapt to changes in data demands. Dynamically adjusting the communication frequency according to data requirements avoids unnecessary waste of communication resources and optimizes the allocation and utilization of system resources. By considering the database operating load characterization coefficient and a preset attenuation coefficient, the adjustment process is smoother, reducing system fluctuations and potential problems caused by frequent communication frequency adjustments, thus enhancing system stability. The adjusted communication frequency better matches data demands, improving the efficiency and accuracy of data transmission. Optimizing the data transmission mechanism provides strong support for cloud terminals to process large amounts of data, enabling medical institutions to better utilize big data for clinical decision-making and research.

[0151] Meanwhile, the aforementioned technical solution can monitor the update information query frequency of the data acquisition terminal in real time and dynamically adjust the communication frequency between the data acquisition terminal and the cloud terminal according to its changes. This dynamic adaptability helps ensure the timeliness and efficiency of data transmission, especially when data updates are frequent or the data volume is large. By adjusting the communication frequency, the aforementioned technical solution can utilize network resources more effectively. When the update information query frequency increases, increasing the communication frequency can ensure timely data transmission; when the update information query frequency decreases, reducing the communication frequency can reduce unnecessary network occupation, thereby optimizing resource utilization. When adjusting the communication frequency, the aforementioned technical solution also considers the database operating load characterization coefficient L, which helps avoid performance degradation caused by increasing the communication frequency under high system load. By introducing L... max With a preset attenuation coefficient λ, the above technical solution can more precisely control the adjustment range of the communication frequency, ensuring stable system operation. By optimizing the communication frequency between the data acquisition terminal and the cloud terminal, the above technical solution can reduce data transmission latency and improve system response speed. This is particularly important for application scenarios requiring real-time data processing and decision support. Furthermore, the design of the above technical solution considers system scalability. As the number of data acquisition terminals increases or the data volume grows, the system can maintain efficient operation by dynamically adjusting the communication frequency without requiring large-scale hardware or software upgrades. By optimizing data transmission efficiency and system performance, the above technical solution can improve user experience. For example, in application scenarios requiring real-time data updates, users can obtain the information they need faster, thereby improving satisfaction and trust.

[0152] In summary, the above technical solution optimizes data transmission efficiency and system performance by dynamically adjusting the communication frequency between the data acquisition terminal, data prediction terminal, and cloud terminal. This adjustment, based on changes in real-time data update frequency and system load considerations, helps ensure the timeliness and accuracy of data transmission while optimizing resource utilization and system response speed.

[0153] In one embodiment of the present invention, the data prediction terminal includes:

[0154] The real-time receiving and monitoring module is used to monitor in real time whether preprocessed medical record data information has been received;

[0155] The data input module is used to input the preprocessed medical record data into the deep learning model that has been trained and optimized after testing when it receives the preprocessed medical record data.

[0156] The prediction and visualization module is used to obtain pregnancy prediction results by combining the trained and tested optimized deep learning model with preprocessed medical record data, and to visualize the pregnancy prediction results. The pregnancy prediction results include a prediction of whether the pregnancy is likely to proceed smoothly to full term and a prediction of the delivery method. Specific delivery methods include natural childbirth and cesarean section.

[0157] The structure of the deep learning model is as follows:

[0158] The input layer is used to receive preprocessed medical record data in real time, including but not limited to the patient's basic information, biochemical indicators, medical history, and examination results.

[0159] Convolutional Neural Networks (CNNs) are used to process image data, such as ultrasound images, to extract spatial features.

[0160] Recurrent neural networks (RNNs) are used to process time-series data, such as tracking changes in follow-up data of pregnant women.

[0161] Fully connected (Dense Layers) are used to process structured data, using multilayer perceptrons to learn non-linear relationships between data.

[0162] The feature fusion layer is used to fuse the output data of convolutional neural networks, recurrent neural networks, and fully connected layers. The key to this layer is to integrate data features from different sources and in different forms, which can be achieved using simple concatenation or more complex fusion techniques such as feature weighting.

[0163] The classification layer includes binary classification output and multi-class classification output; wherein,

[0164] One output node corresponding to the binary classification output is used to predict whether the pregnancy can proceed smoothly to full term;

[0165] Another set of output nodes corresponding to the multi-class output is used to predict the mode of delivery, such as natural childbirth or cesarean section. The softmax function can be used to handle this multi-class output.

[0166] The output layer is used to output specific prediction results, including the probability of full-term pregnancy and the classification results of delivery mode;

[0167] The post-processing layer is used to interpret the raw predictions output by the model and transform them into data information that is easy for doctors and patients to understand.

[0168] The working principle of the above technical solution is as follows: the real-time receiving and monitoring module continuously monitors whether pre-processed medical record data information has arrived. This data has undergone preliminary processing to facilitate subsequent model input and analysis.

[0169] Data Input: Once the preprocessed medical record data is received, the data input module immediately feeds this data into the deep learning model that has been trained and optimized through testing. This data includes, but is not limited to, the patient's basic information, biochemical indicators, medical history, examination results, and possible image data (such as ultrasound images) and time series data (such as follow-up data).

[0170] Model processing:

[0171] After the input layer receives the data, the data is distributed to different network layers for processing.

[0172] Convolutional Neural Networks (CNNs) are specifically designed to process image data, such as ultrasound images, and extract spatial features from them.

[0173] Recurrent neural networks (RNNs) process time-series data, capturing the time-varying characteristics in pregnant women's follow-up data.

[0174] Fully connected (Dense Layers) process structured data and learn non-linear relationships between data through multilayer perceptrons.

[0175] The feature fusion layer integrates the output data from different network layers to form a comprehensive representation of data features.

[0176] The classification layer includes binary and multi-class outputs. Binary outputs predict whether the pregnancy is likely to proceed to full term, while multi-class outputs predict the mode of delivery (such as vaginal delivery, cesarean section, etc.). The softmax function is used to process the multi-class outputs.

[0177] Prediction and Visualization: The prediction and visualization module receives the output from the classification layer, generates specific prediction results, and displays them to doctors and patients in a visual manner. This includes probability estimates of the likelihood of full-term pregnancy and classification results of delivery methods.

[0178] Post-processing: The post-processing layer further interprets and transforms the raw predictions output by the model, making them easier for doctors and patients to understand. This may include converting probabilities into more intuitive expressions or providing detailed explanations of the classification results.

[0179] The effects of the above technical solution are as follows: By integrating multiple deep learning techniques (CNN, RNN, Dense Layers) and feature fusion strategies, it can more comprehensively capture useful information from medical record data, thereby improving the accuracy of pregnancy prediction. Because the model can process multiple types of data (including images, time series, and structured data), it can better support personalized predictions, taking into account the unique circumstances of each pregnant woman. Real-time reception and rapid processing of medical record data enable doctors to quickly obtain pregnancy prediction results, thus allowing for faster development and adjustment of medical plans. Visualizing the prediction results allows doctors and patients to understand the prediction content more intuitively, enhancing communication and trust between doctors and patients. Accurate pregnancy prediction enables medical institutions to better plan and manage resources, ensuring sufficient resources to support the health of pregnant women and newborns during critical periods.

[0180] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A pregnancy outcome prediction system based on electronic medical records, characterized in that, The pregnancy outcome prediction system based on electronic medical records includes a data acquisition terminal, a data transmission device, a cloud terminal, and a data prediction terminal; wherein, the data acquisition terminal is connected to the data prediction terminal via the data transmission device; and the data acquisition terminal and the data prediction terminal are connected to the cloud terminal via the data transmission device. The data acquisition terminal is used to collect electronic medical record information of pregnant users from the database in real time, and dynamically adjust the information update query frequency according to the data retrieval and operation parameters of the database. Meanwhile, the data acquisition terminal includes a data update retrieval monitoring module. This module uses the data retrieval operation parameters of the update data retrieval module to obtain data retrieval quality operation index parameters. When these parameters are lower than their corresponding thresholds, the module uses the change rate of concurrent connections, the change rate of lock wait time, and the change rate of lock conflict count corresponding to the current database operation to obtain a database operation load characterization coefficient. Then, the database operation load characterization coefficient is combined with the database update information query frequency and the lowest data update frequency for pregnant users in the database to obtain an adjusted update information query frequency. The adjusted update information query frequency is obtained using the following formula: in, F new This indicates the frequency of querying the updated information after the adjustment. F c This indicates the frequency of querying update information in the database before the adjustment; L This represents a coefficient indicating the database's operational load. F min This represents the lowest data update frequency for pregnant users in the database; The database operating load characterization coefficient is obtained using the following formula: in, L This represents a coefficient indicating the database's operational load. S Indicates the parameters of quality operation indicators; S 0 indicates a preset threshold for the operating indicator parameter; k This represents the number of time units that the database has run through, where each time unit is 1 second. N i Indicates the first i Rate of change of concurrent connections per unit time; W i Indicates the first i Rate of change of lock waiting time per unit time; C i Indicates the first i Rate of change of lock conflict count per unit time; The data transmission device is used to establish data communication connections and adjust communication frequencies between the data acquisition terminal and the data prediction terminal, between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal. The data prediction terminal is used to obtain pregnancy prediction results based on preprocessed medical record data and to visualize the prediction results. The cloud terminal is used for cloud storage of data information sent by the data acquisition terminal and the data prediction terminal.

2. The pregnancy outcome prediction system based on electronic medical records according to claim 1, characterized in that, The data acquisition terminal includes: The data update monitoring module is used to monitor in real time whether the electronic medical record information corresponding to pregnant users in the database has been updated. The update data retrieval module is used to retrieve the updated data information when the electronic medical record information corresponding to the pregnant user is updated. The data preprocessing module is used to preprocess the updated data information to obtain preprocessed medical record data information; wherein, the preprocessing includes data noise reduction, data cleaning and data standardization. The data update retrieval monitoring module is used to monitor the data retrieval operation parameters of the data update retrieval module in real time, and dynamically adjust the query frequency of the data update monitoring module for the database update information based on the data retrieval operation parameters.

3. The pregnancy outcome prediction system based on electronic medical records according to claim 2, characterized in that, The operation process of the data update retrieval monitoring module includes: The data retrieval operation parameters of the updated data retrieval module are monitored in real time, including the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency. The data retrieval quality operation index parameters are obtained by using the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency. When the data retrieval quality operation index parameters are lower than the preset operation index parameter threshold, the frequency of the data update monitoring module querying the database update information is adjusted.

4. The pregnancy outcome prediction system based on electronic medical records according to claim 3, characterized in that, The data retrieval quality operation index parameters are obtained using the data retrieval completeness ratio, data retrieval response time, and data retrieval error frequency, including: Compare the complete scale parameter of the entire data retrieved during the data retrieval process with the preset complete scale parameter threshold; When the overall completeness ratio parameter of the data is lower than the preset completeness ratio parameter threshold, the data retrieval response time for incomplete data is reduced. The quality operation index parameters are obtained by combining the data retrieval response time of the incomplete data with the frequency of data retrieval errors; wherein, the quality operation index parameters are obtained by the following formula: in, S Indicates the parameters of quality operation indicators; n Indicates the number of times incomplete data was retrieved; m Indicates the number of data retrieval errors; T c This indicates the preset data retrieval time reference value; T i Indicates the first i Data retrieval time corresponding to each incomplete data retrieval; T j Indicates the first j The data retrieval time corresponding to the data retrieval error; p This represents the complete scale parameter for retrieving the entire dataset; p 0 indicates the preset threshold for the full scaling parameter.

5. The pregnancy outcome prediction system based on electronic medical records according to claim 3, characterized in that, When the data retrieval quality operation index parameters are lower than the preset operation index parameter threshold, the frequency of the data update monitoring module querying the database update information is adjusted, including: When the data retrieval quality operation index parameters are lower than the preset operation index parameter threshold, the current data update monitoring module retrieves the query frequency of update information in the database and the lowest value of the data update frequency of pregnant users in the database. Retrieve the change rate of concurrent connections, lock wait time, and lock conflict count corresponding to the current database operation; The database operating load characterization coefficients are obtained by utilizing the rate of change of concurrent connections, the rate of change of lock wait time, and the rate of change of lock conflict count corresponding to the current database operation. The adjusted update information query frequency is obtained by combining the database operation load characterization coefficient with the database update information query frequency and the lowest data update frequency of pregnant users in the database.

6. The pregnancy outcome prediction system based on electronic medical records according to claim 1, characterized in that, The data transmission device includes a first data transmission device and a second data transmission device; The first data transmission device is used to establish a data communication connection between the data acquisition terminal and the data prediction terminal, and to dynamically adjust the communication frequency between the data acquisition terminal and the data prediction terminal according to the change in the update information query frequency of the data acquisition terminal. The second data transmission device is used to establish data communication connections between the data acquisition terminal and the cloud terminal, and between the data prediction terminal and the cloud terminal, and to dynamically adjust the communication frequency between the data acquisition terminal and the cloud terminal according to the changes in the update information query frequency of the data acquisition terminal.

7. The pregnancy outcome prediction system based on electronic medical records according to claim 6, characterized in that, The operation of the first data transmission device includes: Establish a data communication connection between the data acquisition terminal and the data prediction terminal; The update information query frequency of the data acquisition terminal is retrieved in real time, and it is determined whether the update information query frequency of the data acquisition terminal has changed. When the update information query frequency of the data acquisition terminal changes, the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal is adjusted using the changed update information query frequency. The adjusted communication frequency is obtained using the following formula: in, R new01 This indicates the adjusted communication frequency corresponding to the communication connection between the data acquisition terminal and the data prediction terminal. R c01 This indicates the communication frequency before adjustment corresponding to the communication connection between the data acquisition terminal and the data prediction terminal. F new This indicates the frequency of querying the updated information after the adjustment. F c This indicates the frequency of querying update information in the database before the adjustment; L This represents a coefficient indicating the database's operational load. L max This indicates the maximum value of the database load characterization coefficient. λ This represents the preset attenuation coefficient, which determines the sensitivity of communication frequency adjustments to changes in the frequency of information update queries. e It represents the base of the natural logarithm.

8. The pregnancy outcome prediction system based on electronic medical records according to claim 6, characterized in that, The operation of the second data transmission device includes: Establish a data communication connection between the data acquisition terminal and the cloud terminal; Establish a data communication connection between the data prediction terminal and the cloud terminal; The update information query frequency of the data acquisition terminal is retrieved in real time, and it is determined whether the update information query frequency of the data acquisition terminal has changed. When the update information query frequency of the data acquisition terminal changes, the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal will change. The communication frequency between the data acquisition terminal and the cloud terminal is adjusted by combining the communication frequency of the communication connection between the data acquisition terminal and the data prediction terminal with the frequency of querying updated information after the change. The adjusted communication frequency between the data acquisition terminal and the cloud terminal is obtained using the following formula: in, R new02 This indicates the adjusted communication frequency between the data acquisition terminal and the cloud terminal. R c02 This indicates the communication frequency between the data acquisition terminal and the cloud terminal before the adjustment. F new This indicates the frequency of querying the updated information after the adjustment. R new01 This indicates the adjusted communication frequency corresponding to the communication connection between the data acquisition terminal and the data prediction terminal. L This represents a coefficient indicating the database's operational load. L max This indicates the maximum value of the database load characterization coefficient. λ This represents the preset attenuation coefficient, which determines the sensitivity of communication frequency adjustments to changes in the frequency of information update queries. e It represents the base of the natural logarithm.

9. The pregnancy outcome prediction system based on electronic medical records according to claim 1, characterized in that, The data prediction terminal includes: The real-time receiving and monitoring module is used to monitor in real time whether preprocessed medical record data information has been received; The data input module is used to input the preprocessed medical record data into the deep learning model that has been trained and optimized after testing when it receives the preprocessed medical record data. The prediction and visualization module is used to obtain the prediction results of pregnancy by combining the preprocessed medical record data with the deep learning model that has been trained and tested and optimized, and to visualize the prediction results of pregnancy. The prediction results of pregnancy include the prediction of whether the pregnancy is likely to proceed smoothly to full term and the prediction of the delivery method.

Images