Gynecological disease health management method based on big data

Abstract

The invention provides a gynecological disease health management method based on big data. The method comprises the following steps: collecting medical data of multiple batches of patients with polycystic ovarian syndrome by using a data acquisition module, and uploading the medical data to a cloud server; the system extracts health parameters, such as hormone variation and glucose infusion amount, of the same batch of patients from the cloud, and the health parameters are processed by the data analysis module to obtain theoretical indexes of various indexes; meanwhile, the real-time data acquisition module acquires real-time health data of the patient and transmits the real-time health data to the cloud, and a real-time index is calculated; the cloud server compares the real-time index with the theoretical index, calculates a deviation threshold range, analyzes the health deviation index, and measures the deviation between the current health condition of the patient and the expectation; and finally, the cloud server generates analysis information, and pushes the analysis information to a user side through a user interaction module, including treatment effect evaluation, potential problems and health management suggestions. According to the method, through accurate monitoring and analysis, a personalized health management scheme is provided for the patient, and the scientificity and effectiveness of management are improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to a gynecological disease health management method based on big data. Background Art

[0002] With the continuous advancement of global medical technology and the increasing awareness of health, the diagnosis and treatment of gynecological diseases are also evolving. Polycystic ovary syndrome, a common gynecological endocrine disease, affects the reproductive health of many women. Traditional treatment evaluation methods rely primarily on the physician's clinical experience and subjective patient feedback, lacking systematic, data-based, and personalized evaluation methods. This evaluation method is not only inefficient but also fails to accurately reflect treatment effectiveness and individual patient differences, resulting in untimely and inaccurate adjustments to treatment plans.

[0003] In recent years, the application of big data technology in the medical field has gradually attracted attention. Big data technology can process massive amounts of medical data and, through data mining and analysis, provide more accurate evidence for disease diagnosis, treatment, and health management. However, most current big data-based medical solutions focus primarily on the diagnosis stage and lack comprehensive management of the patient's treatment process and personalized health management. In the field of gynecological diseases, in particular, there is no mature system that comprehensively considers the patient's physiological, psychological, and lifestyle factors to conduct comprehensive treatment effectiveness evaluation and tailor personalized treatment plans.

[0004] Furthermore, data security and privacy protection are also significant issues in current big data medical applications. Traditional data storage and analysis methods carry the risk of data leakage and misuse, which not only undermines patient trust but also limits the widespread application of big data technology in the medical field. Therefore, developing a big data-based gynecological health management method requires not only in-depth analysis and intelligent assessment of multi-dimensional data, but also ensuring data security and privacy, thereby providing patients with more accurate, efficient, and personalized medical services.

[0005] The present invention aims to address the deficiencies in the prior art and proposes a gynecological disease health management method based on big data. This method collects medical data of multiple batches of patients through a data acquisition module and uploads it to a cloud server. It uses a data analysis module to perform in-depth processing on the data, calculates the theoretical index and real-time index of each indicator, and generates a health deviation index through comparative analysis. This index can accurately measure the degree of deviation between the patient's current health status and the expected health status. At the same time, the present invention also pushes the analysis results and health management suggestions to the user end through a user interaction module, providing real-time feedback and decision support for patients and doctors. In addition, the present invention adopts encryption technology in the data storage and analysis process to ensure the security and privacy of the data, and provide patients with more reliable medical services. Summary of the Invention

[0006] In light of this, embodiments of the present invention provide a big data-based gynecological health management method that uses a cloud server to store and analyze multiple batches of patient medical data. This method utilizes a data analysis module to process key health parameters, calculate theoretical and real-time indices per unit time, and generate a health deviation index through comparative analysis to accurately assess the patient's health status. Simultaneously, a user interaction module pushes the assessment results and health management recommendations to the user end, providing a scientific basis for patients and doctors, and offering efficient and accurate health management solutions for patients with gynecological diseases.

[0007] To achieve the above object, the present invention provides the following technical solutions: S1. The data acquisition module collects relevant medical data of multiple batches of PCOS patients and uploads this data to the cloud server and sets it as target data; S2. The data acquisition module collects relevant health parameters of the same batch of PCOS patients from the target data and transmits them to the data analysis module; S3. The data analysis module processes the health parameters related to PCOS patients to obtain theoretical indices of various indicators per unit time; S4. The real-time data acquisition module collects real-time health data of any patient in the same batch within a unit time and transmits the data to the cloud data analysis module; S5. The data analysis module processes real-time health data in real time to obtain real-time indexes of various indicators within a unit of time; S6. The cloud server compares the real-time index with the theoretical index and calculates the deviation threshold range of each indicator per unit time; S7. The cloud server analyzes the patient's health deviation index based on the multiple deviation threshold ranges, and uses the health deviation index to measure the degree of deviation between the patient's current health status and the expected health status; S8. The cloud server generates analysis information based on the health deviation index and pushes the analysis information to the user end through the user interaction module. The analysis information includes the patient's current treatment effect evaluation and health management recommendations.

[0008] Technical effects and advantages of the present invention: 1. The present invention uses big data technology to conduct in-depth analysis of the medical data of multiple batches of patients with gynecological diseases, accurately calculates the theoretical index and real-time index of various health indicators, and generates a health deviation index. This quantitative evaluation method can accurately measure the deviation between the patient's current health status and the expected state, providing doctors with a scientific and objective basis for decision-making; at the same time, the present invention generates personalized health management recommendations based on the health deviation index, covering treatment effect evaluation, potential problem warnings and subsequent treatment plan adjustments, to achieve personalized management of patients with gynecological diseases; compared with traditional evaluation methods that rely on doctor experience and patient subjective feedback, the precise evaluation and personalized management plan of the present invention significantly improves the treatment effect, reduces treatment errors caused by individual differences, speeds up patient recovery, and improves quality of life; 2. The present invention utilizes a real-time data acquisition module and a cloud server to collect patients' health data in real time and conduct dynamic analysis. The data analysis module quickly processes real-time data, generates a real-time index and compares it with the theoretical index, promptly discovers health anomalies, and pushes warning information and health management suggestions to patients and doctors through the user interaction module. This real-time monitoring and dynamic feedback mechanism enables doctors to adjust treatment plans in a timely manner to avoid worsening of the disease. Patients can also understand their own health status in real time and actively participate in health management. Compared with traditional regular examinations and periodic assessments, the present invention significantly improves the timeliness and effectiveness of gynecological disease management and reduces the risk of complications caused by delayed treatment. 3. The present invention uses an advanced data analysis module to efficiently process massive amounts of medical data, quickly extract key information, and generate analysis results. By deeply exploring the underlying patterns in the data, it provides doctors with comprehensive and accurate decision-making support, helping to quickly develop personalized treatment plans; the user interaction module presents complex analysis results in a concise and clear manner, improving the efficiency of information transmission. Compared with traditional manual processing methods, the present invention significantly reduces the workload of doctors, improves the scientific nature and accuracy of medical decision-making, and provides patients with more timely and accurate health management services. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0010] Figure 2 The figure is a flow chart of the method steps of the present invention. DETAILED DESCRIPTION

[0011] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0012] As attached Figure 1 A gynecological disease health management method based on big data is shown, comprising a cloud server, a real-time data acquisition module, a data collection module, a data analysis module, and a user interaction module; Cloud servers are used to store medical data, analyze health parameters, calculate deviation thresholds, and generate health management recommendations; Real-time data acquisition module: The real-time data acquisition module is used to collect the patient's current health data and transmit it to the cloud server for real-time analysis; Data collection module: The data collection module is responsible for collecting medical data of multiple batches of patients and uploading them to the cloud server; Data analysis module: The data analysis module is used to process health data, calculate theoretical indexes and real-time indexes, and analyze deviations; User interaction module: The user interaction module is used to push analysis results and health management suggestions to the user end.

[0013] As attached Figure 2 A gynecological disease health management method based on big data is shown, and the specific implementation method includes the following steps: S1. The data acquisition module collects relevant medical data of multiple batches of PCOS patients and uploads this data to the cloud server and sets it as target data; In this embodiment, it is important to explain that the data acquisition module periodically extracts data from various data sources according to a preset acquisition frequency. For laboratory test data, after the test is completed, the data acquisition module automatically obtains the test results and performs a preliminary format conversion on the data to conform to a unified data standard.

[0014] It's important to further explain that after initial processing, the collected data is uploaded to a cloud server via a secure network channel. During the upload process, data encryption technology is used to ensure data security during transmission and prevent data leakage. Once successfully uploaded to the cloud server, the data is stored in a dedicated database, categorized and stored according to specific rules, and marked as target data, preparing it for subsequent data analysis and processing.

[0015] S2. The data acquisition module collects relevant health parameters of the same batch of PCOS patients from the target data and transmits them to the data analysis module; In this embodiment, it is important to explain that the data acquisition module accurately filters the target data stored in the cloud server. The classification rules can be set based on dimensions such as the patient's diagnosis and treatment time, treatment plan, or enrollment time. Specifically, the data acquisition module uses structured query language to execute filtering instructions in the target data repository. Based on the batch unique identifier and disease diagnosis information, it locates and extracts data from PCOS patients belonging to the same batch.

[0016] It should be noted that the health parameters include the hormone change amount per unit time and the glucose infusion amount per unit time; the deviation threshold range includes the hormone deviation threshold range and the glucose infusion deviation threshold range.

[0017] It should be further explained that the extracted health parameter data must be strictly verified to ensure the accuracy and completeness of the data.

[0018] S3. The data analysis module processes the health parameters related to PCOS patients to obtain theoretical indices of various indicators per unit time; In this embodiment, it should be explained that the calculation process of the theoretical index is as follows: A1. Collect hormone changes and glucose infusion volumes per unit time from n patients with PCOS from the same batch; A2. Based on the amount of hormone change per unit time and the amount of glucose infusion per unit time, a theoretical index of hormone change per unit time and a theoretical index of glucose infusion per unit time are obtained.

[0019] It needs further explanation that the calculation process of the hormone change theoretical index is as follows: a1. Calculate the mean I of the hormone changes per unit time for this batch of PCOS patients: , a2. Calculate the standard value of hormone changes per unit time for this batch of PCOS patients Right now: , a3. Set weight coefficient , , then the theoretical index of hormone change E is: , It should be noted that n represents the number of PCOS patients in the same batch. For example, if there are 50 patients in this batch, then n=50; i is an index from 1 to n, which is used to refer to each patient in turn. Represents the hormone change of the i-th patient per unit time; It reflects the degree of dispersion of the hormone change data of this group of patients. The larger the value, the more dispersed the data is and the greater the fluctuation is. E is the theoretical index of hormone change, which is a quantitative indicator obtained through comprehensive calculation and is used to reflect the relevant situation of hormone changes. and The weight coefficient is used to reflect the relative importance of different parts in the formula. For example, when evaluating hormone changes, the overall level represented by the mean is more important. Assign a larger value; if the degree of dispersion reflected by the standard deviation is more critical, increase The value of and To satisfy ; It is the overall reference value of the mean hormone change, which is calculated based on a large amount of historical diagnosis and treatment data. It is the overall reference value for the standard value of hormone changes and is also calculated based on a large amount of historical diagnosis and treatment data.

[0020] The calculation process of the glucose infusion theoretical index is as follows: b1. Calculate the mean C of the glucose infusion volume per unit time for this batch of PCOS patients, i.e.: , b2. Calculate the standard value of glucose infusion per unit time for this batch of PCOS patients Right now: , b3. Set weight coefficient , then the theoretical index of glucose infusion P is: , It should be noted that represents the amount of glucose infusion per unit time for the i-th patient; It reflects the discrete degree of glucose infusion data of this group of patients. The larger the value, the more dispersed the data is and the greater the fluctuation; It is the set weight coefficient used to reflect the mean C and standard value The relative importance of calculating the theoretical index of glucose infusion and meeting .For example ,So . It is the overall reference value of the mean glucose infusion volume, referring to the clinical treatment guidelines set up, It is the overall reference value for the standard value of glucose infusion volume and is set in combination with clinical operation specifications.

[0021] S4. The real-time data acquisition module collects real-time health data of any patient in the same batch within a unit time and transmits the data to the cloud data analysis module; In this embodiment, it is necessary to explain that the real-time data acquisition module will collect health data from any polycystic ovary syndrome patient in the same batch according to a set time period. The scope of its collection covers multiple types of data, such as obtaining real-time fluctuation data on hormone levels in patients through implantable sensors, including key hormones such as testosterone and estradiol; using portable blood glucose monitoring equipment to collect glucose infusion volume and blood glucose level change data per unit time; and using smart wearable devices to collect patient exercise data, sleep duration and quality, and other lifestyle-related data. The acquisition module relies on advanced wireless communication technology to establish a stable connection with various acquisition devices to ensure smooth data acquisition.

[0022] It should be noted that the collected data undergoes rigorous data preprocessing before transmission. First, data cleaning is performed, using filtering algorithms to remove abnormal data points caused by device noise or external interference. For example, this can eliminate extreme outliers that appear momentarily in blood glucose monitoring data. Data normalization is then performed, unifying health parameters of different dimensions and magnitudes, such as hormone levels and glucose infusion, into the same data range using specific mathematical transformations to facilitate subsequent analysis.

[0023] It's important to note that the preprocessed data is carefully packaged into a specially formatted data package. In addition to the raw health data, the package also includes detailed metadata, such as the precise time of data collection, the device number, and the patient's unique identification number. The data package is then transmitted to the cloud-based data analysis module via a secure virtual private network (VPN).

[0024] S5. The data analysis module processes real-time health data in real time to obtain real-time indexes of various indicators within a unit of time; In this embodiment, it needs to be explained that after the data analysis module receives the real-time health data of any patient in the same batch transmitted by the real-time data acquisition module, it immediately starts real-time processing to obtain the real-time index of each indicator within a unit time.

[0025] It should be noted that when processing hormone-related data, the module will analyze the real-time hormone changes collected. It will refer to the patient's past hormone level data and the mean and fluctuation range of hormone changes for patients in the same batch. For the hormone indicator of testosterone, the real-time testosterone changes are first compared with the patient's recent baseline testosterone level to determine its trend of change. At the same time, combined with the mean of the testosterone changes for patients in the same batch, it is assessed whether the patient's current testosterone changes are within a reasonable range. If it is found that the real-time changes deviate significantly from the mean, the data analysis module will make corresponding adjustments to the real-time index of the hormone indicator based on medical knowledge and big data analysis experience.

[0026] It should be further explained that for glucose infusion-related data, the data analysis module will comprehensively consider the glucose infusion volume per unit time and the patient's real-time blood sugar level. It will evaluate whether the current glucose infusion volume is appropriate based on the patient's individual characteristics and medically recommended glucose infusion standards. For example, for patients with a large body weight and poor blood sugar control, if the real-time glucose infusion volume is significantly higher than the average level of similar patients and the blood sugar level continues to rise, the data analysis module will accordingly lower the real-time index of the glucose infusion indicator to reflect the problems with the current infusion situation. Through this comprehensive analysis and processing of various real-time health data, the data analysis module ultimately obtains real-time indexes of various key indicators such as hormone changes and glucose infusion per unit time, providing timely and accurate data support for subsequent health assessments and interventions.

[0027] S6. The cloud server compares the real-time index with the theoretical index and calculates the deviation threshold range of each indicator per unit time; In this embodiment, it is necessary to explain the calculation process of the hormone deviation threshold range, namely: c1. The lower limit of the hormone deviation threshold L1 is: , c2. The upper limit of the hormone deviation threshold U1 is: , c3. That is, the hormone deviation threshold range is .

[0028] It should be noted that L1 is the lower limit of the hormone deviation threshold, which defines the lowest limit of the hormone change-related indicators within a reasonable range; U1 is the upper limit of the hormone deviation threshold, which defines the highest limit of the hormone change-related indicators within a reasonable range; Represents the mean of the Hormone Change Theory Index. It is a value obtained by averaging a certain number of Hormone Change Theory Indexes, reflecting the overall average level. It is the standard deviation of the hormone change theory index. The standard deviation measures the degree of dispersion of these hormone change theory indices, that is, the fluctuation of the data relative to the mean.

[0029] The glucose infusion deviation threshold range calculation process is: d1. The lower limit of the glucose infusion deviation threshold L2 is: , d2. The upper limit of the glucose infusion deviation threshold U2 is: , d3. That is, the glucose infusion deviation threshold range is .

[0030] It should be noted that L2 is the lower limit of the glucose infusion deviation threshold, which determines the lowest limit of glucose infusion-related indicators within the normal fluctuation range; U2 is the upper limit of the glucose infusion deviation threshold, which defines the highest limit of glucose infusion-related indicators within the normal fluctuation range; 、 The meanings are consistent with those in the lower limit formula, which are the mean and standard deviation of the theoretical index of glucose infusion, respectively.

[0031] S7. The cloud server analyzes the patient's health deviation index based on the multiple deviation threshold ranges, and uses the health deviation index to measure the degree of deviation between the patient's current health status and the expected health status; In this embodiment, it is necessary to explain that the health deviation index calculation process is as follows: f1. Assign weights to each indicator. The weight of the hormone change theory index is recorded as , the weight of the glucose infusion theoretical index is recorded as ; f2 were calculated hormone changes in the theoretical index deviation value D1 and glucose infusion theoretical index deviation value D2; f3. Therefore, the health deviation index H is: , It should be noted that 、 are the weights assigned to the theoretical index of hormone changes and the theoretical index of glucose infusion. The weight allocation is based on medical expertise and practical application needs to determine the relative importance of these two indicators in the comprehensive assessment of health deviations. H is the health deviation index, which is a quantitative value that comprehensively reflects the degree to which the patient's health status deviates from normal.

[0032] It is necessary to further explain that the calculation method of the deviation value D1 of the hormone change theoretical index and the deviation value D2 of the glucose infusion theoretical index are as follows: g1. The deviation value D1 of the theoretical index of hormone changes is: , It should be noted that when E < L1, the formula used results in a relative deviation below the lower limit. For example, if L1 = 10 and E = 8, then D1 = 0.2, indicating that the theoretical hormone change index is below the lower limit of the normal range, and the degree of deviation is 0.2. When E > U1, the result is a relative deviation from the upper limit. For example, if U1 = 20 and E = 22, then D1 = 0.1, indicating that the theoretical hormone change index is above the upper limit of the normal range, with a degree of deviation of 0.1. When L1 ≤ E ≤ U1, it indicates that the theoretical hormone change index is within the normal deviation threshold range. At this time, D1 = 0, indicating that there is no deviation from the normal range.

[0033] g2. The deviation value D2 of the theoretical index of glucose infusion is: , It should be noted that when P < L1, the formula used results in a relative deviation below the lower limit. For example, if L2 = 5 and P = 4, then D2 = 0.2, meaning the theoretical glucose infusion index is below the lower limit of the normal range, and the deviation is 0.2. When P > U2, the result is a relative deviation above the upper limit. For example, if U2 = 15 and P = 18, then D2 = 0.2, indicating that the theoretical hormone change index is above the upper limit of the normal range, with a deviation of 0.2. When L2 ≤ P ≤ U2, this indicates that the theoretical glucose infusion index is within the normal deviation threshold. At this time, D2 = 0, meaning there is no deviation from the normal range.

[0034] S8. The cloud server generates analysis information based on the health deviation index and pushes the analysis information to the user end through the user interaction module. The analysis information includes the patient's current treatment effect evaluation and health management recommendations.

[0035] In this embodiment, it is necessary to explain that the cloud server generates multi-dimensional analysis information based on the health deviation index output by the data analysis module. This process takes the health deviation index as the core basis, comprehensively considers the patient's historical health data, current treatment plan and diagnosis and treatment experience of similar patient groups, and ensures the scientificity and pertinence of the analysis information.

[0036] It should be noted that when generating an evaluation of a patient's current treatment effect, the cloud server compares the health deviation index with the pre-treatment baseline data and the average level of the same batch of patients. If the health deviation index is significantly lower than before treatment and is within the normal fluctuation range of the same batch of patients, the system determines that the current treatment plan is effective; if the index rises instead of falling or continues to exceed the threshold range, it indicates that the treatment effect is poor. For example, if the deviation value of the theoretical hormone change index does not decrease significantly after treatment, it indicates that the hormone regulation effect has not met expectations and further adjustment of the treatment strategy is needed.

[0037] It's important to note that to analyze potential issues, the cloud server cross-checks various real-time indices with theoretical indices and deviation thresholds to pinpoint abnormal indicators. If the deviation from the theoretical glucose infusion index remains consistently high, and the real-time blood glucose index falls outside the normal range, the system will identify potential issues such as insulin resistance or an infusion regimen that is inappropriate. Furthermore, the system analyzes potential influencing factors based on the patient's recent lifestyle data.

[0038] To generate subsequent health management recommendations, the cloud server uses the problem analysis results to access standardized diagnosis and treatment guidelines and personalized intervention plans from the knowledge base. If the treatment plan is determined to require adjustment, the system will recommend that the doctor optimize the medication dosage or switch treatments. If health indicators are abnormal due to lifestyle factors, customized recommendations will be sent to the patient, such as increasing daily exercise or adjusting the carbohydrate ratio in the diet. Ultimately, all analyzed information is structured and pushed to the patient and medical management end in real time through the user interaction module, achieving efficient access to health management information and closed-loop feedback.

[0039] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict. Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A gynecological disease health management method based on big data, characterized in that: The method includes a cloud server, a real-time data acquisition module, a data acquisition module, a data analysis module, and a user interaction module. The specific steps of the method are as follows: S1. The data acquisition module collects relevant medical data of multiple batches of PCOS patients and uploads this data to the cloud server and sets it as target data; S2. The data acquisition module collects relevant health parameters of the same batch of PCOS patients from the target data and transmits them to the data analysis module; S3. The data analysis module processes the health parameters related to PCOS patients to obtain theoretical indices of various indicators per unit time; S4. The real-time data acquisition module collects real-time health data of any patient in the same batch within a unit time and transmits the data to the cloud data analysis module; S5. The data analysis module processes real-time health data in real time to obtain real-time indexes of various indicators within a unit of time; S6. The cloud server compares the real-time index with the theoretical index and calculates the deviation threshold range of each indicator per unit time; S7. The cloud server analyzes the patient's health deviation index based on the multiple deviation threshold ranges, and uses the health deviation index to measure the degree of deviation between the patient's current health status and the expected health status; S8. The cloud server generates analysis information based on the health deviation index and pushes the analysis information to the user end through the user interaction module. The analysis information includes the patient's current treatment effect evaluation and health management recommendations.

2. The method for gynecological disease health management based on big data according to claim 1, characterized in that: The health parameters include the amount of hormone change per unit time and the amount of glucose infusion per unit time; the deviation threshold range includes the hormone deviation threshold range and the glucose infusion deviation threshold range.

3. The gynecological disease health management method based on big data according to claim 1, characterized in that: The calculation process of the theoretical index is as follows: A1. Collect hormone changes and glucose infusion volumes per unit time from n patients with PCOS from the same batch; A2. Based on the amount of hormone change per unit time and the amount of glucose infusion per unit time, a theoretical index of hormone change per unit time and a theoretical index of glucose infusion per unit time are obtained.

4. The method for gynecological disease health management based on big data according to claim 3, characterized in that: The calculation process of the hormone change theoretical index is as follows: a1. Calculate the mean I of the hormone changes per unit time for this batch of PCOS patients: ， n represents the number of patients with polycystic ovary syndrome in the same batch, and i is an index from 1 to n, which is used to refer to each patient in turn. Represents the hormone change of the i-th patient per unit time; a2. Calculate the standard value of hormone changes per unit time for this batch of PCOS patients Right now: ； a3. Set weight coefficient , , then the theoretical index of hormone change E is: ， It is the overall reference value of the mean hormone change, which is calculated based on historical diagnosis and treatment data. It is the overall reference value for the standard value of hormone changes and is calculated based on historical diagnosis and treatment data.

5. The method for gynecological disease health management based on big data according to claim 3, characterized in that: The calculation process of the glucose infusion theoretical index is as follows: b1. Calculate the mean C of the glucose infusion volume per unit time for this batch of PCOS patients, i.e.: ， represents the amount of glucose infusion per unit time for the i-th patient; b2. Calculate the standard value of glucose infusion per unit time for this batch of PCOS patients Right now: ； b3. Set weight coefficient , then the theoretical index of glucose infusion P is: ， It is the overall reference value of the mean glucose infusion volume, referring to the clinical treatment guidelines set up, It is the overall reference value for the standard value of glucose infusion volume and is set in combination with clinical operation specifications.

6. The method for gynecological disease health management based on big data according to claim 2, characterized in that: The hormone deviation threshold range calculation process is: c1. The lower limit of the hormone deviation threshold L1 is: ， Represents the mean of the theoretical index of hormone changes, is the standard deviation of the theoretical index of hormone changes; c2. The upper limit of the hormone deviation threshold U1 is: ； c3. That is, the hormone deviation threshold range is .

7. The method for gynecological disease health management based on big data according to claim 2, characterized in that: The glucose infusion deviation threshold range calculation process is: d1. The lower limit of the glucose infusion deviation threshold L2 is: ， is the mean of the theoretical exponents of glucose infusion, is the standard deviation of the theoretical index of glucose infusion; d2. The upper limit of the glucose infusion deviation threshold U2 is: ， d3. That is, the glucose infusion deviation threshold range is .

8. The method for gynecological disease health management based on big data according to claim 1, characterized in that: The health deviation index calculation process is as follows: f1. Assign weights to each indicator. The weight of the hormone change theory index is recorded as , the weight of the glucose infusion theoretical index is recorded as ; f2 were calculated hormone changes in the theoretical index deviation value D1 and glucose infusion theoretical index deviation value D2; f3. Therefore, the health deviation index H is: 。 9. The method for gynecological disease health management based on big data according to claim 8, characterized in that: The calculation method of the deviation value D1 of the hormone change theoretical index and the deviation value D2 of the glucose infusion theoretical index is as follows: g1. The deviation value D1 of the theoretical index of hormone changes is: ， g2. The deviation value D2 of the theoretical index of glucose infusion is: 。

Images