Gestational hypertension early warning system based on data analysis

Abstract

The invention relates to the technical field of data analysis, in particular to a gestational hypertension early warning system based on data analysis, and the system comprises an obtaining module which obtains monitoring parameters; the monitoring module draws an actual body weight monitoring curve and an actual blood pressure monitoring curve; the first threshold value setting module and the second threshold value setting module compare the basic information of the user with a preset blood pressure database to determine an initial hypertension threshold value, calibrate the initial hypertension threshold value to obtain a target hypertension threshold value, compare the basic information of the user with a preset weight database to determine an initial weight gain threshold value, and calibrate the target hypertension threshold value to obtain a target hypertension threshold value; calibrating the initial weight gain threshold value to obtain a target weight gain threshold value; the analysis module analyzes the actual body weight monitoring curve and the actual blood pressure monitoring curve, identifies a body weight growth abnormal time period and a blood pressure abnormal time period, and performs analysis to determine an early warning level; and the early warning module determines an early warning strategy according to the early warning level. The accuracy of the early warning result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a gestational hypertension early warning system based on data analysis. Background Art

[0002] Hypertension during pregnancy is one of the common complications for pregnant women, which seriously threatens the health of mothers and babies. Traditional monitoring methods rely on regular prenatal examinations, which have problems such as poor timeliness and delayed warning. With the development of big data and artificial intelligence technology, it has become possible to conduct health warnings through real-time monitoring and data analysis.

[0003] The patent document with Chinese patent application number CN113871016A discloses a method and device for predicting adverse outcomes of patients with hypertensive disorders complicating pregnancy. The method comprises: collecting and entering clinical data of HDP patients in multiple hospitals in different regions within a first preselected time period to generate a first HDP patient data set, collecting and entering clinical data of HDP patients in preselected hospitals within a second preselected time period to generate a second HDP patient data set; performing univariate analysis on multiple variables in the first HDP patient data set to screen out variables with statistically significant differences; incorporating variables with statistically significant differences and clinically significant variables in the first HDP patient data set into a lasso algorithm for variable screening to obtain initial predictive variables; incorporating the initial predictive variables into a multifactorial logistic regression analysis to obtain optimal predictive variables; incorporating the optimal predictive variables into a binary logistic regression analysis to obtain optimal predictive variables; ic regression analysis was performed to construct a prediction model for adverse outcomes of HDP patients; based on the first HDP patient data set, the HDP patient adverse outcome prediction model was evaluated and internally verified; after evaluation and internal verification, the second HDP patient data set was included in the HDP patient adverse outcome prediction model for external verification; after external verification, the HDP patient adverse outcome prediction model was displayed using prediction formulas, visual nomograms, and web calculators; the optimal predictive variables of the HDP patients to be tested were input into the HDP patient adverse outcome prediction model, and the probability of adverse outcomes in the HDP patients to be tested was output.

[0004] The existing technology does not comprehensively carry out early warning and continuous monitoring of gestational hypertension, resulting in the problem of low accuracy of gestational hypertension risk warning. Summary of the invention

[0005] To this end, the present invention provides a gestational hypertension early warning system based on data analysis, which can solve the problem of inaccurate early warning.

[0006] To achieve the above object, the present invention provides a gestational hypertension early warning system based on data analysis, the system comprising:

[0007] An acquisition module is used to acquire basic information of the user and acquire monitoring parameters of the user in real time during any monitoring period, wherein the monitoring parameters include real-time weight parameters and real-time blood pressure parameters;

[0008] A monitoring module, connected to the acquisition module, for drawing an actual weight monitoring curve based on the real-time weight parameters, and drawing an actual blood pressure monitoring curve based on the real-time blood pressure data;

[0009] A first threshold setting module, connected to the acquisition module, is used to compare the user's basic information with a preset blood pressure database to obtain a blood pressure comparison result, determine an initial hypertension threshold based on the blood pressure comparison result, and calibrate the initial hypertension threshold based on the user's historical blood pressure data to determine a target hypertension threshold;

[0010] A second threshold setting module, connected to the acquisition module, is used to compare the user's basic information with a preset weight database to obtain a weight comparison result, determine an initial weight gain threshold based on the weight comparison result, calibrate the initial weight gain threshold based on the user's historical weight data, and obtain a target weight gain threshold;

[0011] an analysis module connected to the monitoring module, the first threshold setting module and the second threshold setting module, for analyzing the actual weight monitoring curve and the actual blood pressure monitoring curve, identifying an abnormal weight gain period based on the target weight gain threshold, identifying an abnormal blood pressure period based on the target hypertension threshold, analyzing the abnormal weight period and the abnormal blood pressure period, and determining a warning level according to the analysis results;

[0012] The early warning module is connected to the analysis module and is used to formulate an early warning strategy according to the early warning level.

[0013] Furthermore, the first threshold setting module includes:

[0014] An information acquisition unit, used to acquire basic information of the user, wherein the basic information includes actual age information, actual gestational age information and actual weight information;

[0015] a first comparison unit, connected to the information acquisition unit, for comparing the actual age information, the actual gestational age information and the actual weight information with the preset age information, the preset gestational age information and the preset weight information in the preset blood pressure database to determine an initial hypertension threshold;

[0016] A first calibration unit is connected to the first comparison unit, and is used to draw a historical blood pressure monitoring curve according to the historical blood pressure data, analyze the historical blood pressure monitoring curve, calibrate the initial high pressure threshold value based on the analysis result, and obtain a target high blood pressure threshold value.

[0017] Furthermore, the first calibration unit includes:

[0018] A curve analysis subunit, configured to analyze the change trend of the historical blood pressure monitoring curve, identify an abnormal trend change region based on the change trend, mark the abnormal trend change region, and obtain a first abnormal blood pressure region;

[0019] a threshold analysis subunit, configured to analyze the historical blood pressure monitoring curve based on the initial hypertension threshold, and determine a second abnormal blood pressure area based on the analysis result;

[0020] The adjustment subunit is connected to the curve analysis subunit and the threshold analysis subunit, and is used to analyze the first abnormal blood pressure area and the second abnormal blood pressure area, calibrate the initial hypertension threshold based on the regional analysis results, and obtain the target hypertension threshold.

[0021] Furthermore, the adjustment subunit includes:

[0022] An analysis block, configured to determine a union region based on the first abnormal blood pressure region and the second abnormal blood pressure region;

[0023] A calibration block is used to identify a number of historical blood pressure data in the union area, calculate the average of the several historical blood pressure data, calculate the blood pressure deviation value between the average and the initial hypertension threshold, calculate the calibration coefficient based on the blood pressure deviation value, and calibrate the initial hypertension threshold according to the calibration coefficient to obtain the target hypertension threshold.

[0024] Furthermore, the second threshold setting module includes:

[0025] A second comparison unit is used to compare the actual age information, the actual gestational age information and the actual weight information with the preset age information, the preset gestational age information and the preset weight information in the preset weight database to determine an initial weight gain threshold;

[0026] A second calibration unit is connected to the second comparison unit, and is used to draw a historical weight monitoring curve according to the historical weight data, analyze the historical weight monitoring curve, calibrate the initial weight gain threshold based on the analysis result, and obtain a target weight gain threshold.

[0027] Furthermore, the analysis module includes:

[0028] an identification unit, configured to identify a period of abnormal weight gain based on the target weight gain threshold, and to identify a period of abnormal blood pressure based on the target hypertension threshold;

[0029] an analysis unit connected to the identification unit, for analyzing the correlation between the abnormal weight gain period and the abnormal blood pressure period;

[0030] The level determination unit is connected to the analysis unit and is used to calculate an abnormality score based on the correlation analysis result and determine the warning level based on the abnormality score.

[0031] Furthermore, the analysis unit comprises:

[0032] An alignment subunit, used for performing time alignment processing on the abnormal weight gain period and the abnormal blood pressure period;

[0033] The correlation calculation subunit is connected to the alignment subunit and is used to calculate the actual correlation coefficient between the abnormal weight gain period and the abnormal blood pressure period according to the processed alignment period.

[0034] Furthermore, the correlation calculation subunit includes:

[0035] A segmentation block, for dividing the alignment period into a number of sub-periods;

[0036] A calculation block, connected to the segmentation block, for calculating initial correlation coefficients in a number of the sub-periods to obtain a number of initial correlation coefficients;

[0037] The determination block is connected to the calculation block and is used to perform weighted average processing on a plurality of the initial correlation coefficients to obtain the actual correlation coefficient.

[0038] Furthermore, the level determination unit includes:

[0039] A score calculation subunit, used to calculate an abnormality score according to the actual correlation coefficient;

[0040] The threshold comparison subunit is connected to the score calculation subunit, and is used to compare the calculated abnormal score with a preset score threshold, and determine the warning level according to the comparison result.

[0041] Furthermore, the early warning module includes:

[0042] A comparison unit, used to compare the warning level with a preset level to obtain a comparison result;

[0043] The strategy determination unit is connected to the comparison unit and is used to issue an alarm when the warning level is greater than or equal to the preset level, and to continue monitoring when the warning level is less than the preset level.

[0044] Compared with the prior art, the beneficial effects of the present invention are that, by setting the acquisition module to collect the basic information and monitoring parameters of the user in real time and accurately, a basis is provided for subsequent data analysis and early warning, and the acquisition of real-time data ensures the timeliness and accuracy of the early warning. By setting the monitoring module to draw the monitoring curves of the actual weight and blood pressure, the weight and blood pressure change trends of the user are intuitively displayed, which is helpful to more accurately evaluate the health status of the user. By setting the first threshold setting module to compare the basic information of the user with the preset blood pressure database, combined with the historical blood pressure data of the user, the target hypertension threshold is dynamically calibrated and determined, the accuracy of the early warning is improved, and the early warning error caused by improper threshold setting is avoided. By setting the second threshold setting module to compare the basic information of the user with the preset weight database, and combined with the historical weight data of the user, the target weight growth threshold is determined, which is helpful to timely discover abnormal situations such as excessive weight growth, and improve the accuracy of subsequent early warnings. By setting the analysis module to comprehensively analyze the actual weight monitoring curve and the blood pressure monitoring curve, the time period of abnormal weight growth and abnormal blood pressure is identified, and the early warning level is determined accordingly, which comprehensively improves the accuracy of the early warning. By setting the early warning module to formulate a scientific early warning strategy according to the early warning level, the accuracy of the early warning result is improved.

[0045] In particular, by setting the information acquisition unit to obtain the user's actual age information, actual gestational age information and actual weight information, personalized basic data is provided for subsequent threshold setting, ensuring that the subsequent comparison and calibration process is based on accurate user information, thereby improving the accuracy and reliability of threshold setting. By setting the first comparison unit to compare the user's actual information with the information in the preset database, the preset threshold range can be quickly found as a reference for the initial hypertension threshold, laying the foundation for subsequent more detailed calibration work. By setting the first calibration unit to draw and analyze the historical blood pressure monitoring curve based on the user's historical blood pressure data, the user's blood pressure change trend and characteristics can be more accurately reflected. Calibration through analysis of historical data can achieve dynamic adjustment of the hypertension threshold and improve the sensitivity and accuracy of monitoring.

[0046] In particular, by setting the identification unit to set clear target weight gain thresholds and hypertension thresholds, the time periods of abnormal weight gain and abnormal blood pressure can be accurately identified, which helps to focus on the abnormal stages in subsequent analysis and provide an accurate basis for subsequent warnings. By setting the analysis unit to conduct an in-depth analysis of the correlation between the time periods of abnormal weight gain and the time periods of abnormal blood pressure, the potential relationship between the two can be revealed, which helps to provide a basis for accurate warnings. By setting the level determination unit to calculate the abnormality score based on the correlation analysis results and convert it into an intuitive warning level, the assessment of health risks can be more quantitative and standardized, which helps to ensure the accuracy of the warning results. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A structural block diagram of a pregnancy-related hypertension early warning system based on data analysis provided by an embodiment of the present invention;

[0048] Figure 2 A structural block diagram of a first threshold setting module of a pregnancy-related hypertension warning system based on data analysis provided by an embodiment of the present invention;

[0049] Figure 3 A block diagram of a second threshold setting module of a pregnancy hypertension early warning system based on data analysis provided by an embodiment of the present invention;

[0050] Figure 4 This is a structural block diagram of the warning module of the pregnancy-related hypertension warning system based on data analysis provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0053] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be understood as a limitation on the present invention.

[0054] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] See also Figure 1 As shown, an embodiment of the present invention provides a gestational hypertension early warning system based on data analysis, characterized in that it includes:

[0056] An acquisition module 10 is used to acquire basic information of the user and acquire monitoring parameters of the user in real time during any monitoring period, wherein the monitoring parameters include real-time weight parameters and real-time blood pressure parameters;

[0057] A monitoring module 20, connected to the acquisition module 10, for drawing an actual weight monitoring curve based on the real-time weight parameters, and drawing an actual blood pressure monitoring curve based on the real-time blood pressure data;

[0058] A first threshold setting module 30, connected to the acquisition module 10, is used to compare the user's basic information with a preset blood pressure database to obtain a blood pressure comparison result, determine an initial hypertension threshold based on the blood pressure comparison result, and calibrate the initial hypertension threshold based on the user's historical blood pressure data to determine a target hypertension threshold;

[0059] A second threshold setting module 40, connected to the acquisition module 10, is used to compare the user's basic information with a preset weight database to obtain a weight comparison result, determine an initial weight gain threshold based on the weight comparison result, calibrate the initial weight gain threshold based on the user's historical weight data, and obtain a target weight gain threshold;

[0060] an analysis module 50, connected to the monitoring module 20, the first threshold setting module 30 and the second threshold setting module 40, for analyzing the actual weight monitoring curve and the actual blood pressure monitoring curve, identifying the abnormal weight gain period based on the target weight gain threshold, identifying the abnormal blood pressure period based on the target hypertension threshold, analyzing the abnormal weight period and the abnormal blood pressure period, and determining the warning level according to the analysis results;

[0061] The early warning module 60 is connected to the analysis module 50 and is used to formulate an early warning strategy according to the early warning level.

[0062] Specifically, the embodiment of the present invention provides a basis for subsequent data analysis and early warning by setting the acquisition module to collect the user's basic information and monitoring parameters in real time and accurately. The acquisition of real-time data ensures the timeliness and accuracy of the early warning. By setting the monitoring module to draw the monitoring curves of the actual weight and blood pressure, the weight and blood pressure change trends of the user are intuitively displayed, which helps to more accurately evaluate the health status of the user. By setting the first threshold setting module to compare the user's basic information with the preset blood pressure database, combined with the user's historical blood pressure data, dynamically calibrate and determine the target hypertension threshold, improve the accuracy of the early warning, and avoid early warning errors caused by improper threshold setting. By setting the second threshold setting module to compare the user's basic information with the preset weight database, and combined with the user's historical weight data, the target weight growth threshold is determined, which helps to timely discover abnormal situations such as excessive weight growth, and improves the accuracy of subsequent early warnings. By setting the analysis module to comprehensively analyze the actual weight monitoring curve and the blood pressure monitoring curve, identify the time period of abnormal weight growth and abnormal blood pressure, and determine the early warning level accordingly, the accuracy of the early warning is comprehensively improved. By setting the early warning module to formulate a scientific early warning strategy according to the early warning level, the accuracy of the early warning result is improved.

[0063] See also Figure 2 As shown, the first threshold setting module 30 includes:

[0064] An information acquisition unit 31 is used to acquire basic information of the user, wherein the basic information includes actual age information, actual gestational age information and actual weight information;

[0065] A first comparison unit 32, connected to the information acquisition unit 31, is used to compare the actual age information, the actual gestational age information and the actual weight information with the preset age information, the preset gestational age information and the preset weight information in the preset blood pressure database to determine an initial hypertension threshold;

[0066] The first calibration unit 33 is connected to the first comparison unit 32, and is used to draw a historical blood pressure monitoring curve according to the historical blood pressure data, analyze the historical blood pressure monitoring curve, calibrate the initial high pressure threshold value based on the analysis result, and obtain a target high blood pressure threshold value.

[0067] Specifically, the preset blood pressure database described in the embodiment of the present invention includes standard blood pressure range data corresponding to people of different age groups, different gestational weeks, and different weights. The data is obtained through a large amount of clinical practice and scientific research, and aims to provide a scientific and reasonable reference standard.

[0068] Specifically, the initial hypertension threshold value described in the embodiment of the present invention is the maximum value of a preset standard blood pressure range in a preset blood pressure database obtained according to the comparison result.

[0069] Specifically, the embodiment of the present invention obtains the user's actual age information, actual gestational age information and actual weight information by setting the information acquisition unit, thereby providing personalized basic data for subsequent threshold setting, ensuring that subsequent comparison and calibration processes are based on accurate user information, thereby improving the accuracy and reliability of threshold setting, and by setting the first comparison unit to compare the user's actual information with the information in the preset database, it is possible to quickly find the preset threshold range as a reference for the initial hypertension threshold, laying the foundation for subsequent more detailed calibration work, and by setting the first calibration unit to draw and analyze the historical blood pressure monitoring curve based on the user's historical blood pressure data, it is possible to more accurately reflect the user's blood pressure change trend and characteristics, and by calibrating through analysis of historical data, it is possible to achieve dynamic adjustment of the hypertension threshold and improve the sensitivity and accuracy of monitoring.

[0070] Specifically, the first calibration unit includes:

[0071] A curve analysis subunit, configured to analyze the change trend of the historical blood pressure monitoring curve, identify an abnormal trend change region based on the change trend, mark the abnormal trend change region, and obtain a first abnormal blood pressure region;

[0072] a threshold analysis subunit, configured to analyze the historical blood pressure monitoring curve based on the initial hypertension threshold, and determine a second abnormal blood pressure area based on the analysis result;

[0073] The adjustment subunit is connected to the curve analysis subunit and the threshold analysis subunit, and is used to analyze the first abnormal blood pressure area and the second abnormal blood pressure area, calibrate the initial hypertension threshold based on the regional analysis results, and obtain the target hypertension threshold.

[0074] Specifically, the curve analysis subunit described in the embodiment of the present invention includes:

[0075] A trend identification block is used to calculate the slope value at each point on the historical blood pressure detection curve to obtain a plurality of slope values;

[0076] The abnormality identification block is connected to the trend identification block, and is used to mark a number of points whose slope values ​​are greater than a preset slope value, obtain abnormal points, and connect adjacent continuous abnormal points to obtain a first blood pressure abnormal area.

[0077] Specifically, the preset slope value in the embodiment of the present invention is 1 / 3.

[0078] Specifically, the embodiment of the present invention sets the curve analysis subunit to analyze the changing trend of the historical blood pressure monitoring curve, accurately identifies abnormal areas in the blood pressure changing trend, helps to timely discover the problem of blood pressure changes, and provides an accurate basis for subsequent early warnings. By setting the threshold analysis subunit to analyze the historical blood pressure monitoring curve based on the initial hypertension threshold, the misjudgment caused by improper threshold setting is reduced, and the accuracy and efficiency of blood pressure early warnings are improved. By setting the adjustment subunit to comprehensively analyze the information of the first blood pressure abnormal area and the second blood pressure abnormal area, the initial hypertension threshold is accurately calibrated to ensure the accuracy of the target hypertension threshold.

[0079] Specifically, the adjustment subunit includes:

[0080] An analysis block, configured to determine a union region based on the first abnormal blood pressure region and the second abnormal blood pressure region;

[0081] A calibration block is used to identify a number of historical blood pressure data in the union area, calculate the average of the several historical blood pressure data, calculate the blood pressure deviation value between the average and the initial hypertension threshold, calculate the calibration coefficient based on the blood pressure deviation value, and calibrate the initial hypertension threshold according to the calibration coefficient to obtain the target hypertension threshold.

[0082] Specifically, the union region described in the embodiment of the present invention includes all abnormal blood pressure data of both the first abnormal blood pressure region and the second abnormal blood pressure region.

[0083] Specifically, the calibration coefficient in the embodiment of the present invention is the blood pressure deviation divided by the mean.

[0084] See also Figure 3 As shown, the second threshold setting module 40 includes:

[0085] A second comparison unit 41 is used to compare the actual age information, the actual gestational age information and the actual weight information with the preset age information, the preset gestational age information and the preset weight information in the preset weight database to determine an initial weight gain threshold;

[0086] The second calibration unit 42 is connected to the second comparison unit 41, and is used to draw a historical weight monitoring curve according to the historical weight data, analyze the historical weight monitoring curve, calibrate the initial weight gain threshold based on the analysis result, and obtain the target weight gain threshold.

[0087] Specifically, the preset weight database described in the embodiment of the present invention includes standard weight gain ranges corresponding to pregnant women of different age groups, different gestational weeks, and different weights. These data are also based on extensive clinical observations and scientific research, and aim to provide a personalized and scientific weight management reference standard. In particular, the initial weight gain threshold in this embodiment is the maximum value of the standard weight gain range obtained based on the comparison results.

[0088] Specifically, the measures taken by the embodiment of the present invention to calibrate the initial weight gain threshold to obtain the target weight gain threshold are the same as the method for calibrating the blood pressure threshold, which will not be repeated here.

[0089] See also Figure 4 As shown, the analysis module 50 includes:

[0090] an identification unit 51, configured to identify a period of abnormal weight gain based on the target weight gain threshold, and to identify a period of abnormal blood pressure based on the target hypertension threshold;

[0091] An analysis unit 52, connected to the identification unit 51, for analyzing the correlation between the abnormal weight gain period and the abnormal blood pressure period;

[0092] The level determination unit 53 is connected to the analysis unit 52 and is used to calculate an abnormality score based on the correlation analysis result and determine the warning level based on the abnormality score.

[0093] Specifically, the present invention implements the method of setting a clear target weight gain threshold and a high blood pressure threshold by setting the recognition unit to accurately identify the time periods of abnormal weight gain and abnormal blood pressure, which helps to focus on the abnormal stage in subsequent analysis and provide an accurate basis for subsequent warnings. By setting the analysis unit to conduct an in-depth analysis of the correlation between the time periods of abnormal weight gain and the time periods of abnormal blood pressure, the potential relationship between the two can be revealed, which helps to provide a basis for accurate warnings. By setting the level determination unit to calculate the abnormality score based on the correlation analysis results and convert it into an intuitive warning level, the assessment of health risks can be more quantitative and standardized, which helps to ensure the accuracy of the warning results.

[0094] Specifically, the analysis unit includes:

[0095] An alignment subunit, used for performing time alignment processing on the abnormal weight gain period and the abnormal blood pressure period;

[0096] The correlation calculation subunit is connected to the alignment subunit and is used to calculate the actual correlation coefficient between the abnormal weight gain period and the abnormal blood pressure period according to the processed alignment period.

[0097] Specifically, the embodiment of the present invention can calculate the actual correlation coefficient through the Pearson correlation coefficient and the Spearman rank correlation coefficient. The closer the absolute value of the correlation coefficient is to 1, the stronger the correlation between the two time periods is; a positive value indicates a positive correlation, and a negative value indicates a negative correlation.

[0098] Specifically, the correlation calculation subunit includes:

[0099] A segmentation block, for dividing the alignment period into a number of sub-periods;

[0100] A calculation block, connected to the segmentation block, for calculating initial correlation coefficients in a number of the sub-periods to obtain a number of initial correlation coefficients;

[0101] The determination block is connected to the calculation block and is used to perform weighted average processing on a plurality of the initial correlation coefficients to obtain the actual correlation coefficient.

[0102] Specifically, the embodiment of the present invention subdivides the overall alignment period into several sub-periods by setting the segmented blocks, so that the correlation coefficient calculated in each sub-period can better reflect the local relationship between weight gain and blood pressure changes in the period, capture these subtle changes, and thus improve the accuracy of the correlation analysis. By setting the calculation block to calculate the initial correlation coefficient in multiple sub-periods respectively, and determining the block to perform weighted averaging processing to obtain the actual correlation coefficient, the final result is more accurate, the accuracy of the correlation analysis is improved, and detailed information on the changes in the relationship between weight gain and blood pressure changes in different time periods is provided.

[0103] Specifically, the level determination unit includes:

[0104] A score calculation subunit, used to calculate an abnormality score according to the actual correlation coefficient;

[0105] The threshold comparison subunit is connected to the score calculation subunit, and is used to compare the calculated abnormal score with a preset score threshold, and determine the warning level according to the comparison result.

[0106] Specifically, the anomaly score in the embodiment of the present invention is the absolute value of the actual correlation coefficient;

[0107] The scoring threshold was 1±0.3.

[0108] Specifically, the early warning module includes:

[0109] A comparison unit, used to compare the warning level with a preset level to obtain a comparison result;

[0110] The strategy determination unit is connected to the comparison unit and is used to issue an alarm when the warning level is greater than or equal to the preset level, and to continue monitoring when the warning level is less than the preset level.

[0111] Specifically, it also includes:

[0112] The update module is used to update the preset blood pressure database according to the user's target hypertension threshold, and to update the preset weight database according to the target weight gain threshold.

[0113] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A gestational hypertension early warning system based on data analysis, characterized in that: include: An acquisition module is used to acquire basic information of the user and acquire monitoring parameters of the user in real time during any monitoring period, wherein the monitoring parameters include real-time weight parameters and real-time blood pressure parameters; A monitoring module, connected to the acquisition module, for drawing an actual weight monitoring curve based on the real-time weight parameters, and drawing an actual blood pressure monitoring curve based on the real-time blood pressure data; A first threshold setting module, connected to the acquisition module, is used to compare the user's basic information with a preset blood pressure database to obtain a blood pressure comparison result, determine an initial hypertension threshold based on the blood pressure comparison result, and calibrate the initial hypertension threshold based on the user's historical blood pressure data to determine a target hypertension threshold; A second threshold setting module, connected to the acquisition module, is used to compare the user's basic information with a preset weight database to obtain a weight comparison result, determine an initial weight gain threshold based on the weight comparison result, calibrate the initial weight gain threshold based on the user's historical weight data, and obtain a target weight gain threshold; an analysis module connected to the monitoring module, the first threshold setting module and the second threshold setting module, for analyzing the actual weight monitoring curve and the actual blood pressure monitoring curve, identifying an abnormal weight gain period based on the target weight gain threshold, identifying an abnormal blood pressure period based on the target hypertension threshold, analyzing the abnormal weight period and the abnormal blood pressure period, and determining a warning level according to the analysis results; The early warning module is connected to the analysis module and is used to formulate an early warning strategy according to the early warning level.

2. The gestational hypertension early warning system based on data analysis according to claim 1, characterized in that: The first threshold setting module includes: An information acquisition unit, used to acquire basic information of the user, wherein the basic information includes actual age information, actual gestational age information and actual weight information; a first comparison unit, connected to the information acquisition unit, for comparing the actual age information, the actual gestational age information and the actual weight information with the preset age information, the preset gestational age information and the preset weight information in the preset blood pressure database to determine an initial hypertension threshold; A first calibration unit is connected to the first comparison unit, and is used to draw a historical blood pressure monitoring curve according to the historical blood pressure data, analyze the historical blood pressure monitoring curve, calibrate the initial high pressure threshold value based on the analysis result, and obtain a target high blood pressure threshold value.

3. The gestational hypertension early warning system based on data analysis according to claim 2, characterized in that: The first calibration unit comprises: A curve analysis subunit, configured to analyze the change trend of the historical blood pressure monitoring curve, identify an abnormal trend change region based on the change trend, mark the abnormal trend change region, and obtain a first abnormal blood pressure region; a threshold analysis subunit, configured to analyze the historical blood pressure monitoring curve based on the initial hypertension threshold, and determine a second abnormal blood pressure area based on the analysis result; The adjustment subunit is connected to the curve analysis subunit and the threshold analysis subunit, and is used to analyze the first abnormal blood pressure area and the second abnormal blood pressure area, calibrate the initial hypertension threshold based on the regional analysis results, and obtain the target hypertension threshold.

4. The gestational hypertension early warning system based on data analysis according to claim 3, characterized in that: The adjustment subunit comprises: An analysis block, configured to determine a union region based on the first abnormal blood pressure region and the second abnormal blood pressure region; A calibration block is used to identify a number of historical blood pressure data in the union area, calculate the average of the several historical blood pressure data, calculate the blood pressure deviation value between the average and the initial hypertension threshold, calculate the calibration coefficient based on the blood pressure deviation value, and calibrate the initial hypertension threshold according to the calibration coefficient to obtain the target hypertension threshold.

5. The gestational hypertension early warning system based on data analysis according to claim 4, characterized in that: The second threshold setting module includes: A second comparison unit is used to compare the actual age information, the actual gestational age information and the actual weight information with the preset age information, the preset gestational age information and the preset weight information in the preset weight database to determine an initial weight gain threshold; A second calibration unit is connected to the second comparison unit, and is used to draw a historical weight monitoring curve according to the historical weight data, analyze the historical weight monitoring curve, calibrate the initial weight gain threshold based on the analysis result, and obtain a target weight gain threshold.

6. The gestational hypertension early warning system based on data analysis according to claim 5, characterized in that: The analysis module comprises: an identification unit, configured to identify a period of abnormal weight gain based on the target weight gain threshold, and to identify a period of abnormal blood pressure based on the target hypertension threshold; an analysis unit connected to the identification unit, for analyzing the correlation between the abnormal weight gain period and the abnormal blood pressure period; The level determination unit is connected to the analysis unit and is used to calculate an abnormality score based on the correlation analysis result and determine the warning level based on the abnormality score.

7. The gestational hypertension early warning system based on data analysis according to claim 6, characterized in that: The analysis unit comprises: An alignment subunit, used for performing time alignment processing on the abnormal weight gain period and the abnormal blood pressure period; The correlation calculation subunit is connected to the alignment subunit and is used to calculate the actual correlation coefficient between the abnormal weight gain period and the abnormal blood pressure period according to the processed alignment period.

8. The gestational hypertension early warning system based on data analysis according to claim 7, characterized in that: The correlation calculation subunit comprises: A segmentation block, for dividing the alignment period into a number of sub-periods; A calculation block, connected to the segmentation block, for calculating initial correlation coefficients in a plurality of the sub-periods to obtain a plurality of initial correlation coefficients; The determination block is connected to the calculation block and is used to perform weighted average processing on a plurality of the initial correlation coefficients to obtain the actual correlation coefficient.

9. The gestational hypertension early warning system based on data analysis according to claim 8, characterized in that: The level determination unit comprises: A score calculation subunit, used to calculate an abnormality score according to the actual correlation coefficient; The threshold comparison subunit is connected to the score calculation subunit, and is used to compare the calculated abnormal score with a preset score threshold, and determine the warning level according to the comparison result.

10. The data analysis-based early warning system for hypertension during pregnancy according to claim 9, characterized in that: The early warning module comprises: A comparison unit, used to compare the warning level with a preset level to obtain a comparison result; The strategy determination unit is connected to the comparison unit and is used to issue an alarm when the warning level is greater than or equal to the preset level, and to continue monitoring when the warning level is less than the preset level.

Images