AI-based intelligent early warning system for males with hyperuricemia in reproductive metabolism

Abstract

The invention relates to the technical field of medical informatics, in particular to an AI-based intelligent early warning system for hyperuricemia male reproductive metabolism abnormality. The system comprises a memory and a processor, and the processor executes a computer program stored in the memory to realize the following steps: acquiring uric acid data, waistline data, glycosylated hemoglobin data and reproductive index data of a target male; combining the uric acid fluctuation abnormality degree, the multi-dimensional blood glucose abnormality expression degree and the movement rule expression degree of each stage to obtain the reproduction metabolism abnormality degree; according to the relative relationship between the reproductive index data and the corresponding standard range, obtaining the abnormal performance degree of the reproductive index; integrating the reproductive metabolism abnormality degree and the reproductive index abnormality expression degree to obtain a multi-dimensional feature linkage reproductive metabolism expression comprehensive evaluation degree of the target male; and according to the comprehensive evaluation degree of the multi-dimensional feature linkage reproductive metabolism performance, whether early warning is carried out is judged. According to the invention, the accuracy and credibility of intelligent early warning of the risk of abnormal male reproductive metabolism of hyperuricemia are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical informatics, in particular to an AI-based intelligent early warning system for hyperuricemia male reproductive metabolic abnormalities. BACKGROUND

[0002] Hyperuricemia is closely related to gout, kidney disease and metabolic syndrome, and is considered a potential risk factor for reproductive metabolic abnormalities, especially in men. Hyperuricemia not only can lead to decreased sperm quality, but also is closely linked to sexual dysfunction. Through oxidative stress, it damages sperm DNA, and further causes problems such as decreased sperm motility and abnormal morphology. In addition, hyperuricemia can further affect male sexual function by damaging vascular endothelial function and changing hemodynamics. With the changes in modern lifestyle, especially under the influence of factors such as lack of exercise and unhealthy diet, the impact of hyperuricemia on male reproductive metabolic abnormalities is increasingly significant, threatening the overall health of men.

[0003] For the early warning of hyperuricemia on male reproductive metabolic abnormalities, the traditional method has significant limitations, i.e. relying on single and fragmented index detection after the patient presents obvious symptoms, and the doctor conducts static risk assessment based on personal experience. This traditional early warning method is essentially a passive, lagging and isolated mode. Due to the inability to integrate the patient's time-series clinical data and lifestyle and other multi-dimensional information, it is difficult to capture the complex nonlinear interaction and dynamic evolution law between hyperuricemia and reproductive endocrine disorders and decreased sperm quality in the early stage, resulting in low accuracy and reliability of early warning. SUMMARY

[0004] In order to solve the problem of low accuracy and reliability of early warning in the prior art for hyperuricemia male reproductive metabolic abnormalities, the purpose of the present application is to provide an AI-based intelligent early warning system for hyperuricemia male reproductive metabolic abnormalities, and the technical solution adopted is as follows: The present application provides an AI-based intelligent early warning system for hyperuricemia male reproductive metabolic abnormalities, which comprises a memory and a processor. The processor executes the computer program stored in the memory to realize the following steps: Obtaining the uric acid data, waist circumference data, glycosylated hemoglobin data, sitting time, low-intensity exercise time and reproductive index data of the target male; determine the uric acid fluctuation abnormality degree of each stage in combination with the change range of the uric acid data of each stage and the distribution of the uric acid data relative to the standard range, determine the multi-dimensional blood glucose abnormality performance degree of each stage in combination with the waist circumference data fluctuation characteristics within each stage and the distribution of the glycosylated hemoglobin data relative to the standard range, and determine the exercise regularity performance degree of each stage according to the distribution of the sedentary time and the low-to-moderate intensity exercise time of each day; obtain the reproductive index abnormality performance degree according to the relative relationship between the reproductive index data and the corresponding standard range; obtain the multi-dimensional feature linkage reproductive metabolism performance comprehensive evaluation degree of the target male by comprehensively combining the reproductive metabolism abnormality degree and the reproductive index abnormality performance degree, and determine whether to issue a warning according to the multi-dimensional feature linkage reproductive metabolism performance comprehensive evaluation degree.

[0005] Preferably, the determination of the uric acid fluctuation abnormality degree of each stage in combination with the change range of the uric acid data of each stage and the distribution of the uric acid data relative to the standard range comprises: For any stage: if all the uric acid data of all the detections of the any stage is within the standard range, the uric acid abnormal value of the any stage is a preset first value; if there is uric acid data within the standard range and there is uric acid data not within the standard range in all the detections of the any stage, the uric acid abnormal value of the any stage is a preset second value; if all the uric acid data of all the detections of the any stage is not within the standard range, the uric acid abnormal value of the any stage is a preset third value; the preset first value is less than the preset second value, and the preset second value is less than the preset third value; calculate the range of the uric acid data of all the detections of the any stage, and take the normalized result of the ratio between the range and the uric acid data of the last detection within the any stage as the uric acid change range of the any stage; obtain the uric acid fluctuation abnormality degree of the any stage according to the uric acid change range and the uric acid abnormal value, and the uric acid change range and the uric acid abnormal value are positively correlated with the uric acid fluctuation abnormality degree.

[0006] Preferably, the determination of the multi-dimensional blood glucose abnormality performance degree of each stage in combination with the waist circumference data fluctuation characteristics within each stage and the distribution of the glycosylated hemoglobin data relative to the standard range comprises: For any stage: divide the any stage into multiple time periods with the maximum point of the waist circumference data within the any stage as the division point; Based on the waist circumference data at the last moment of each time period in any given stage, the waist circumference data at the first moment, and the duration of each time period, the degree of abnormal change in waist circumference trend in any given stage is obtained. The ratio between the average of all glycated hemoglobin data from any given stage and the upper limit of the glycated hemoglobin standard range is used as the blood glucose abnormality coefficient for any given stage. By combining the abnormal trend change in waist circumference and the abnormal blood glucose coefficient, the multidimensional abnormal blood glucose performance of any stage is obtained. Both the abnormal trend change in waist circumference and the abnormal blood glucose coefficient are positively correlated with the multidimensional abnormal blood glucose performance.

[0007] Preferably, the step of obtaining the degree of abnormal change in waist circumference trend in any stage based on the waist circumference data at the last moment of each time period within any stage, the waist circumference data at the first moment, and the duration of each time period includes: Calculate the first difference between the waist circumference data at the last moment and the waist circumference data at the first moment in each time period; use the normalized result of the ratio between the first difference and the duration of the time period as the waist circumference change characteristic value for each time period. The ratio between the waist circumference data at the last moment of each time period and the waist circumference data at the first moment is taken as the waist circumference change ratio for each time period. By combining the characteristic values ​​and ratios of waist circumference changes across all time periods in any given stage, the degree of abnormal trend change in waist circumference in any given stage can be obtained.

[0008] Preferably, determining the degree of performance of exercise patterns in each stage based on the distribution of daily sedentary time and low-to-medium intensity exercise time within each stage includes: For any stage: The relative exercise performance level for any given stage is obtained based on the average daily sedentary time and the average daily low-to-medium intensity exercise time for any given stage. Obtain the intersection and union of the total time intervals of low-to-medium intensity exercise for each day of any given stage, and use the ratio between the duration of the intersection and the duration of the union as the exercise pattern factor for any given stage. Based on the relative motion performance degree and the motion law factor, the motion law performance degree of any stage is obtained, and both the relative motion performance degree and the motion law factor are positively correlated with the motion law performance degree.

[0009] Preferably, obtaining the relative exercise performance level for any given stage based on the average daily sedentary time and average daily low-to-moderate intensity exercise time includes: The average daily sitting time in any of the above stages is used as the sitting time performance index of the above stages; the average daily low-to-moderate intensity exercise time in any of the above stages is used as the exercise time performance index of the above stages. Based on the performance of exercise duration and the performance of sitting time in any given stage, the relative performance of exercise duration in any given stage is obtained. The performance of exercise duration is positively correlated with the relative performance of exercise duration, and the performance of sitting time is negatively correlated with the relative performance of exercise duration.

[0010] Preferably, the reproductive metabolic abnormality score is obtained by comprehensively considering all abnormalities in uric acid fluctuations, multidimensional abnormalities in blood glucose, and abnormalities in exercise patterns, including: The product of the abnormality of uric acid fluctuation and the abnormality of multidimensional blood glucose in each stage is calculated and recorded as the first characteristic value of each stage; the first difference between constant 1 and the abnormality of uric acid fluctuation in each stage is calculated; the product of the first difference and the corresponding stage's movement pattern performance is recorded as the second characteristic value of each stage. The degree of reproductive metabolic abnormality is obtained by combining the first and second feature values ​​from all stages.

[0011] Preferably, the step of obtaining the degree of reproductive metabolic abnormality by combining the first feature value and the second feature value from all stages includes: Calculate the second difference between the first eigenvalue and the second eigenvalue; The sum of the second differences across all stages is determined as the degree of reproductive metabolic abnormality.

[0012] Preferably, obtaining the degree of abnormality in reproductive indicators based on the relative relationship between reproductive indicator data and corresponding standard ranges includes: Each data point in the reproductive indicator data is determined to be within its corresponding standard range. If it is, the first parameter of the corresponding data point in the reproductive indicator data is set to a preset fourth value; otherwise, the first parameter of the corresponding data point in the reproductive indicator data is set to a fifth value. The fourth value is greater than the fifth value. The normalized result of the cumulative sum of the first parameter of all data in the reproductive index is determined as the degree of abnormality in the reproductive index.

[0013] Preferably, the comprehensive reproductive metabolic abnormality degree and reproductive indicator abnormality degree are used to obtain a comprehensive assessment degree of the target male's multidimensional characteristics linked to reproductive metabolic performance, including: By using the abnormality of the reproductive indicators as a weight, the abnormality of reproductive metabolism is weighted to obtain a comprehensive evaluation of the multidimensional characteristics of the target male's reproductive metabolic performance.

[0014] The present invention has at least the following beneficial effects: The AI-based intelligent early warning system for male reproductive metabolic abnormalities in hyperuricemia provided by this invention first constructs a comprehensive analytical framework covering the phased trends of uric acid, abnormal blood glucose manifestations, daily exercise regularity, and reproductive health indicators. Abnormal blood glucose manifestations are centered on dynamic changes in chemohetylhemoglobin and waist circumference. The abnormality of uric acid fluctuations, the multidimensional abnormality of blood glucose manifestations, and the manifestation of exercise regularity are coupled to constitute a multidimensional metabolic abnormality score. This is further linked with abnormal reproductive indicators to form a comprehensive assessment score of reproductive metabolic manifestations linked by multidimensional features. In this way, metabolic indicators, lifestyle, and reproductive indicators are effectively integrated, breaking through the limitations of traditional single, static assessments. Finally, the system determines whether to issue an intelligent early warning based on the comprehensive assessment score of reproductive metabolic manifestations linked by multidimensional features, improving the accuracy, systematicness, and personalization of the early warning system, and providing a reliable basis for early clinical intervention. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 The flowchart illustrates the method executed by an AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia, as provided in an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose, the following detailed description of the AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia, proposed according to the present invention, is provided in conjunction with the accompanying drawings and preferred embodiments.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of the AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia provided by this invention.

[0020] Example of an AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia: This embodiment proposes an AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia. The system includes a memory and a processor. The processor executes a computer program stored in the memory, such as... Figure 1As shown, the method executed by the AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia in this embodiment includes the following steps: Step S1: Obtain the target male's uric acid data, waist circumference data, glycated hemoglobin data, sedentary time, moderate-to-low intensity exercise time, and reproductive index data.

[0021] When evaluating male reproductive metabolic disorders caused by hyperuricemia, to improve the accuracy of the evaluation results, it is necessary to construct a comprehensive data system that reflects the patient's long-term metabolic status, physiological trends, and lifestyle, rather than considering only uric acid as a single data point. Patients with hyperuricemia typically undergo regular uric acid level testing. Although this method cannot achieve continuous monitoring of uric acid data, the data from regular checks can help analyze the phased trends in the patient's uric acid levels.

[0022] For the target males to be evaluated, multiple test data from their medical records are obtained, including uric acid and glycated hemoglobin data, reproductive index data, and anthropometric data. In this embodiment, the reproductive index data collected includes: total testosterone (TT), free testosterone (FT), luteinizing hormone (LH), follicle-stimulating hormone (FSH), estradiol (E2), sperm concentration, sperm motility (i.e., percentage of progressively motile sperm), sperm morphology (i.e., percentage of normal morphology), sperm DNA integrity, and sperm mitochondrial function. These are typically tested using appropriate methods during physician examination, and the results are recorded. Total testosterone and free testosterone reflect androgen levels; luteinizing hormone and follicle-stimulating hormone reflect the functional state of the hypothalamus-pituitary-gonadal axis; and anthropometric data includes waist circumference data.

[0023] At the same time, the target males are fitted with monitoring wristbands to monitor their sedentary time and low-to-moderate intensity exercise time.

[0024] Using the above method, uric acid data, waist circumference data, glycated hemoglobin data, reproductive index data, and daily sedentary time and moderate-to-low intensity exercise time were obtained from multiple tests conducted on the target male within a preset time period. In this embodiment, the preset time period is the set of all historical moments with a time interval less than or equal to the current moment, plus the current moment. In this embodiment, the preset time period is 6 months. In specific applications, the implementer can set it according to specific circumstances. It should be noted that all data in this embodiment were obtained with full authorization.

[0025] Step S2: Combine the variation range of uric acid data in each stage and the distribution of uric acid data relative to the standard range to determine the degree of uric acid fluctuation abnormality in each stage; combine the fluctuation characteristics of waist circumference data in each stage and the distribution of glycated hemoglobin data relative to the standard range to determine the degree of multidimensional blood glucose abnormality in each stage; and determine the degree of exercise regularity in each stage based on the distribution of daily sedentary time and moderate-to-low intensity exercise time in each stage.

[0026] The preset time period is divided into multiple stages with a fixed duration as the duration of each stage. In this embodiment, the fixed duration is 20 days. In specific applications, the implementer can set it according to the specific situation.

[0027] For each stage, it is necessary to fully consider whether the target male's urea data has been continuously abnormal during this period and whether the uric acid data has shown significant changes. These may indicate that the patient has potential health abnormalities or a risk of disease deterioration during this period, so that special attention can be paid to this stage.

[0028] The following embodiment will use one stage as an example for explanation. The methods provided in this embodiment can be used to process other stages.

[0029] Specifically, for any given stage: First, if all uric acid data from all tests in this phase are within the standard range, the abnormal uric acid value for this phase is set to a preset first value. If some uric acid data in this phase are within the standard range and some are outside the standard range, the abnormal uric acid value for this phase is set to a preset second value. If none of the uric acid data in this phase are within the standard range, the abnormal uric acid value for this phase is set to a preset third value. The preset first value is less than the preset second value, and the preset second value is less than the preset third value. In this embodiment, the preset first value is 0, the preset second value is 0.5, and the preset third value is 1. In specific applications, the implementer can set these values ​​according to the specific circumstances. It should be noted that the standard range for uric acid data is set by the doctor according to the specific circumstances, and this embodiment will not elaborate further.

[0030] Then, the range of uric acid data from all tests in that phase is calculated; the normalized result of the ratio between this range and the uric acid data from the last test in that phase is taken as the uric acid variation range in that phase. In this embodiment, the maximum-minimum normalization method is used to normalize the ratio between uric acid data. In other implementations, other existing data normalization methods can also be used.

[0031] Furthermore, based on the uric acid change range and the uric acid abnormality value during this period, the uric acid fluctuation abnormality degree during this period is obtained, and both the uric acid change range and the uric acid abnormality value are positively correlated with the uric acid fluctuation abnormality degree.

[0032] Among them, a positive correlation means that the dependent variable increases as the independent variable increases, and the dependent variable decreases as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by the actual application.

[0033] As a specific example, the sum of constant 1 and the abnormal uric acid value in this stage is calculated and recorded as the first sum. The product of the uric acid fluctuation range in this stage and the first sum is taken as the degree of uric acid fluctuation abnormality in this stage. The larger the abnormal uric acid value and the larger the uric acid fluctuation range in this stage, the more severe the high fluctuation of uric acid in this stage, that is, the higher the degree of uric acid fluctuation abnormality.

[0034] When analyzing male reproductive metabolic abnormalities in patients with hyperuricemia, it is necessary to fully consider the factor of abnormal blood glucose levels, because hyperuricemia is closely related to insulin resistance, and the two share an important pathological mechanism. Insulin resistance not only promotes increased renal reabsorption of uric acid, thereby raising blood uric acid levels, but may also further affect insulin sensitivity by inducing chronic low-grade inflammation and oxidative stress, forming a vicious cycle.

[0035] Chronic low-grade inflammation is a common manifestation of hyperuricemia. This inflammation not only exacerbates insulin resistance but may also lead to elevated blood glucose levels. The interaction between hyperglycemia and hyperuricemia can significantly aggravate reproductive metabolic abnormalities in male patients, potentially leading to sexual dysfunction, decreased sperm quality, and even infertility. Therefore, abnormal blood glucose should be considered an important co-factor in the analysis of reproductive metabolic abnormalities in male patients with hyperuricemia, helping to comprehensively assess and intervene in the patient's health status.

[0036] Abnormal blood glucose levels can be reflected in a patient's obesity, and central obesity is a more important risk predictor than body mass index. Visceral fat secretes a large number of inflammatory factors, directly driving insulin resistance and metabolic disorders. Therefore, an increase in waist circumference is a very direct early signal of worsening risk. Based on this, this embodiment will use glycated hemoglobin data as a reference for the overall assessment of abnormal blood glucose levels in patients, and will conduct continuous dynamic monitoring and analysis of abnormalities based on continuously collected waist circumference data.

[0037] First, curve fitting is performed on the waist circumference data of the target personnel within this stage to obtain the corresponding fitted curve. The horizontal axis of the fitted curve represents time, and the vertical axis represents the waist circumference data. The maximum value point of the fitted curve is then obtained. Curve fitting and the acquisition of the maximum value point are both well-known techniques, and will not be elaborated further in this embodiment. Using the maximum value point of the waist circumference data within this stage as the dividing point, the stage is divided into multiple time periods.

[0038] The difference between the waist circumference data at the last moment and the waist circumference data at the first moment within each time period is calculated. This difference is obtained by subtracting the waist circumference data at the first moment from the last moment's data, and this difference is recorded as the first difference. The normalized result of the ratio between the first difference and the duration of the corresponding time period is used as the waist circumference change characteristic value for each time period. Using this method, the waist circumference change characteristic value for each time period within that stage can be obtained, and this waist circumference change characteristic value reflects the rate of waist circumference change.

[0039] The faster the change in a patient's waist circumference during a given period, the more abnormal the metabolic activity may be. Therefore, this can be used as the weight of the corresponding waist circumference development stage, and the degree of abnormal waist circumference trend in a single stage can be determined by the number of time periods contained in that single stage.

[0040] The ratio of waist circumference data at the last moment of each time period to waist circumference data at the first moment is taken as the waist circumference change ratio for each time period. Using the above method, the characteristic value of waist circumference change and the waist circumference change ratio for each time period in this stage can be obtained. Each time period in this stage has one characteristic value of waist circumference change and one waist circumference change ratio.

[0041] Next, the characteristic values ​​and ratios of waist circumference changes across all time periods in this stage are combined to obtain the degree of abnormal waist circumference trend in this stage. Specifically, the characteristic value of waist circumference change for each time period in this stage is multiplied by its ratio, and the products for all time periods in this stage are summed. The sum is taken as the degree of abnormal waist circumference trend in this stage.

[0042] Furthermore, the average value of glycated hemoglobin (HbA1c) data from all tests in this phase is calculated. The ratio between this average value and the upper limit of the HbA1c standard range is used as the glycated blood glucose abnormality coefficient for this phase. The HbA1c standard range is set according to specific circumstances, and will not be elaborated upon in this embodiment. Combining the waist circumference trend abnormality and the glycated blood glucose abnormality coefficient for this phase, a multidimensional glycated blood glucose abnormality manifestation score is obtained. Both the waist circumference trend abnormality and the glycated blood glucose abnormality coefficient are positively correlated with the multidimensional glycated blood glucose abnormality manifestation score.

[0043] As a specific example, the product of the abnormal waist circumference trend and the abnormal blood glucose coefficient of the period is calculated, and this product is used as the multidimensional abnormal blood glucose performance of the period.

[0044] A patient's metabolic status directly affects multiple aspects of health, including blood sugar, uric acid, and reproductive health. Abnormal blood sugar is a common metabolic disorder in patients with hyperuricemia. Hyperuricemia is closely related to insulin resistance, and the two work together to negatively impact reproductive health, particularly hormonal balance and sperm quality in the male reproductive system. Therefore, regular daily exercise is crucial. Exercise not only regulates blood sugar levels and improves insulin sensitivity but also helps control hyperuricemia by promoting metabolism, lowering blood sugar and lipid levels. Furthermore, exercise improves blood circulation and reduces body fat, especially visceral fat. Excessive visceral fat exacerbates insulin resistance, leading to a worsening of hyperglycemia and hyperuricemia. By reducing visceral fat, exercise not only helps alleviate these metabolic abnormalities but also improves male reproductive health. Regular exercise can restore normal physiological function by reducing chronic low-grade inflammation and oxidative stress, thereby improving overall metabolic performance and reducing the risks associated with hyperuricemia and abnormal blood sugar.

[0045] Based on the above characteristics, this embodiment also analyzes the patient's long-term sedentary behavior and low-to-moderate intensity exercise behavior in a single phase.

[0046] Specifically, the average daily sitting time during this phase is used as the sitting time performance index for this phase; the average daily low-to-moderate intensity exercise time during this phase is used as the exercise time performance index for this phase. The average daily sitting time during this phase is obtained by taking the daily sitting time during this phase and averaging the sitting time across all days of this phase. Similarly, the average daily low-to-moderate intensity exercise time during this phase is obtained by taking the daily low-to-moderate intensity exercise time during this phase and averaging the low-to-moderate intensity exercise time across all days of this phase.

[0047] Prolonged sitting can lead to metabolic disorders, weight gain, abnormal blood sugar and lipids, and reproductive health problems. However, it is unavoidable to sit for long periods of time in life due to work or other reasons. In such cases, it is advisable to consider exercising after get off work to buffer the effects. This can be achieved by measuring the proportion of exercise time to sitting time, which reflects the patient's relative exercise performance.

[0048] Specifically, in this embodiment, the relative performance of a stage is obtained based on the performance of the duration of movement and the performance of the duration of sitting. The performance of the duration of movement is positively correlated with the performance of the relative performance, and the performance of the duration of sitting is negatively correlated with the performance of the relative performance.

[0049] Among them, a positive correlation means that the dependent variable increases as the independent variable increases, and the dependent variable decreases as the independent variable decreases. It can be an additive relationship, a multiplicative relationship, etc., which is determined by practical application. A negative correlation means that the dependent variable decreases as the independent variable increases, and the dependent variable increases as the independent variable decreases. It can be a subtractive relationship, a division relationship, etc., which is determined by practical application.

[0050] As a specific example, the ratio between the performance score of exercise duration in that phase and the performance score of sedentary time in that phase is used as the relative performance score of exercise in that phase. It should be noted that: in this embodiment, the target personnel engage in both low-to-moderate intensity exercise and sedentary time every day within the preset time period, therefore the performance score of sedentary time in that phase will not be 0.

[0051] Furthermore, the intersection and union of the daily low-to-medium intensity exercise time intervals for this stage are obtained respectively. The ratio between the duration of the intersection and the duration of the union is used as the exercise pattern factor for this stage. Based on the relative exercise performance and the exercise pattern factor for this stage, the exercise pattern performance degree for this stage is obtained. Both the relative exercise performance degree and the exercise pattern factor are positively correlated with the exercise pattern performance degree.

[0052] As a specific example, the product of the relative motion performance of that stage and the motion law factor of that stage is taken as the motion law performance of that stage.

[0053] Thus, by using the above method, it is possible to obtain the degree of uric acid fluctuation abnormality, multidimensional blood glucose abnormality, and exercise regularity at each stage.

[0054] Step S3: Combine all abnormalities in uric acid fluctuations, abnormalities in multidimensional blood glucose, and abnormalities in exercise patterns to obtain the degree of reproductive metabolic abnormality; and obtain the degree of abnormality in reproductive indicators based on the relative relationship between reproductive indicator data and corresponding standard ranges.

[0055] The higher the degree of abnormal fluctuation in uric acid levels in each stage, the more likely there is a metabolic abnormality in that process, and the more attention should be paid to the degree of abnormality in multidimensional blood glucose at each stage; conversely, it indicates that the abnormal uric acid levels in that stage are improving or declining, and attention should be paid to the degree of normality in exercise patterns. This embodiment will next evaluate the degree of reproductive metabolic abnormality by combining the degree of abnormal fluctuation in uric acid levels, the degree of abnormality in multidimensional blood glucose levels, and the degree of normality in exercise patterns across all stages.

[0056] Specifically, the product of the abnormality of uric acid fluctuation and the abnormality of multidimensional blood glucose in each stage is calculated and recorded as the first characteristic value of each stage; the first difference between constant 1 and the abnormality of uric acid fluctuation in each stage is calculated; the product of the first difference and the corresponding stage's exercise pattern performance is recorded as the second characteristic value of each stage; the difference between the first characteristic value and the second characteristic value is calculated and recorded as the second difference; the sum of the second differences of all stages is determined as the degree of reproductive metabolic abnormality.

[0057] In this embodiment, a specific formula for calculating the degree of reproductive metabolic abnormality is given, which can be expressed as: ; in, Indicates the degree of reproductive metabolic abnormalities. Indicates the number of stages. This indicates the degree of abnormality in uric acid fluctuations at the m-th stage. This represents the degree of multidimensional glycemic abnormality in the m-th stage. This represents the degree of motion pattern representation in the m-th stage.

[0058] The first feature value of the m-th stage. This is the first difference in the m-th stage. The second characteristic value of the m-th stage. This is the second difference in the m-th stage.

[0059] The higher the abnormality of high uric acid fluctuation in stage m, the more likely there is a metabolic abnormality in that stage, and more attention should be paid to the multidimensional blood glucose abnormality in each stage; the lower the abnormality of high uric acid fluctuation in stage m, the more likely there is a relief or decline in the patient's abnormal uric acid in stage m, and more attention should be paid to the exercise pattern in stage m.

[0060] The above process analyzes the indirect factors that affect male reproductive metabolic abnormalities. The essence of male reproductive metabolic abnormalities is the abnormality shown in their reproductive indicator data. However, reproductive indicator data is not checked frequently. Therefore, the most recent reproductive indicator data of the target male is used for analysis.

[0061] Testosterone levels are a core indicator of male reproductive metabolic health, especially important for men with hyperuricemia and abnormal glucose metabolism, where screening for low testosterone levels is crucial. Furthermore, sperm quality is a vital indicator of male fertility. Factors such as sperm motility, sperm DNA integrity, and sperm mitochondrial function are all directly related to male reproductive health. Insufficient sperm motility may lead to reduced fertilization capacity, sperm DNA damage may increase the risk of fetal developmental abnormalities, and sperm mitochondrial dysfunction directly affects sperm energy supply, thereby reducing fertility. Therefore, maintaining good testosterone levels and sperm quality is essential for male reproductive health.

[0062] In this embodiment, sperm motility, sperm DNA integrity, and sperm mitochondrial function are also considered as reproductive indicator data for subsequent analysis. Specifically, it is determined whether each data point in the reproductive indicator data falls within its corresponding standard range. If it does, the first parameter of the corresponding data point is set to a preset fourth value; if it does not fall within the standard range, the first parameter of the corresponding data point is set to a fifth value. The fourth value is greater than the fifth value. In this embodiment, the fourth value is 1 and the fifth value is 0. In specific applications, the implementer can set these values ​​according to the specific circumstances. It should be noted that each data point in the reproductive indicator data has its corresponding standard range, and the specific value of the standard range is set according to the specific circumstances, which will not be elaborated further here.

[0063] The normalized result of the sum of the first parameter of all data items in the reproductive index data is determined as the degree of abnormality in the reproductive index. In this embodiment, the normalization of the sum of the first parameter is performed using the hyperbolic tangent function. That is, the sum of the first parameter is directly substituted into the hyperbolic tangent function as the independent variable, and the function value of the hyperbolic tangent function is used as the normalized result of the sum of the first parameter. In other implementation methods, other existing data normalization methods can also be used.

[0064] This embodiment obtains the degree of reproductive metabolic abnormality and the degree of abnormality in reproductive indicators through the above steps.

[0065] Step S4: Combine the degree of reproductive metabolic abnormality and the degree of abnormality in reproductive indicators to obtain the comprehensive assessment degree of multidimensional characteristics linked to reproductive metabolic performance of the target male; determine whether to issue an early warning based on the comprehensive assessment degree of multidimensional characteristics linked to reproductive metabolic performance.

[0066] This step will comprehensively assess the reproductive metabolic abnormalities and abnormalities in reproductive indicators of the target male, and make a decision on whether to issue a warning based on the assessment results.

[0067] Since the greater the degree of abnormality in reproductive indicators, the more attention should be given to the target male, the degree of abnormality in reproductive indicators is used as a weight to weight the degree of abnormality in reproductive metabolism, so as to obtain the comprehensive evaluation degree of the target male's multidimensional characteristics linked to reproductive metabolic performance. In other words, the product of the degree of abnormality in reproductive indicators and the degree of abnormality in reproductive metabolism is used as the comprehensive evaluation degree of the target male's multidimensional characteristics linked to reproductive metabolic performance.

[0068] After obtaining the comprehensive assessment of multidimensional features linked to reproductive metabolic performance, a neural network can be used to determine the early warning of reproductive metabolic abnormalities in men with hyperuricemia. The comprehensive assessment of multidimensional features linked to reproductive metabolic performance in the target male, along with corresponding reproductive indicator data, uric acid data, and glycated hemoglobin data, are used as inputs to the neural network. The output of the neural network indicates whether an alert is issued. When an alert is issued, it indicates that the target male's condition needs closer attention, and therefore medical staff should increase their attention and take appropriate measures. The training process of the neural network is existing technology and will not be described in detail in this embodiment.

[0069] The AI-based intelligent early warning system for male reproductive metabolic abnormalities in hyperuricemia provided in this embodiment first constructs a comprehensive analytical framework covering the phased trends of uric acid, abnormal blood glucose manifestations, daily exercise regularity, and reproductive health indicators. Abnormal blood glucose manifestations are centered on dynamic changes in chemohetylhemoglobin and waist circumference. The abnormality of uric acid fluctuations, the multidimensional abnormality of blood glucose manifestations, and the manifestation of exercise regularity are coupled to form a multidimensional metabolic abnormality score. This is further linked with abnormal reproductive indicators to form a multidimensional feature-linked comprehensive assessment of reproductive metabolic manifestations. In this way, metabolic indicators, lifestyle, and reproductive indicators are effectively integrated, breaking through the limitations of traditional single, static assessments. Finally, the system determines whether to issue an intelligent early warning based on the multidimensional feature-linked comprehensive assessment of reproductive metabolic manifestations, improving the accuracy, systematicness, and personalization of the early warning system, and providing a reliable basis for early clinical intervention.

[0070] It should be noted that 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 principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia, characterized in that, The system includes a memory and a processor, the processor executing a computer program stored in the memory to perform the following steps: Obtain data on uric acid, waist circumference, glycated hemoglobin, sedentary time, moderate to low intensity exercise time, and reproductive indicators for the target male. By combining the variation range of uric acid data in each stage and the distribution of uric acid data relative to the standard range, the degree of uric acid fluctuation abnormality in each stage is determined; by combining the fluctuation characteristics of waist circumference data in each stage and the distribution of glycated hemoglobin data relative to the standard range, the degree of multidimensional blood glucose abnormality in each stage is determined. Based on the distribution of daily sitting time and low-to-medium intensity exercise time within each stage, the degree of exercise pattern performance in each stage is determined. The degree of reproductive metabolic abnormality is obtained by combining all abnormalities in uric acid fluctuations, abnormalities in multidimensional blood glucose, and abnormalities in exercise patterns; the degree of abnormality in reproductive indicators is obtained by considering the relative relationship between reproductive indicator data and corresponding standard ranges. By combining the degree of abnormality in reproductive metabolism and the degree of abnormality in reproductive indicators, a comprehensive assessment of the multidimensional characteristics linked to the reproductive metabolic performance of the target male is obtained; and a warning is issued based on the comprehensive assessment of the multidimensional characteristics linked to the reproductive metabolic performance.

2. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 1, characterized in that, The degree of abnormality in uric acid fluctuation at each stage is determined by combining the magnitude of changes in uric acid data at each stage and the distribution of uric acid data relative to the standard range, including: For any stage: If the uric acid data of all tests in any stage are within the standard range, then the abnormal value of uric acid in any stage is set as a preset first value. If, in any stage, there are uric acid data within the standard range and uric acid data outside the standard range in all tests, then the abnormal uric acid value for any stage is set to a preset second value. If the uric acid data of all tests in any stage are not within the standard range, then the abnormal value of uric acid in any stage is set to a preset third value. The preset first value is less than the preset second value, and the preset second value is less than the preset third value; Calculate the range of uric acid data from all tests in any given period; use the normalized result of the ratio between the range and the uric acid data from the last test in any given period as the uric acid change range in any given period. Based on the magnitude of uric acid changes and abnormal uric acid values, the degree of uric acid fluctuation abnormality in any given stage is obtained, and both the magnitude of uric acid changes and the abnormal uric acid values ​​are positively correlated with the degree of uric acid fluctuation abnormality.

3. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 1, characterized in that, The multidimensional glycemic abnormality manifestation in each stage is determined by combining the fluctuation characteristics of waist circumference data in each stage and the distribution of glycated hemoglobin data relative to the standard range, including: For any stage: Using the maximum value of waist circumference data within any given stage as the dividing point, any given stage is divided into multiple time periods; Based on the waist circumference data at the last moment of each time period in any given stage, the waist circumference data at the first moment, and the duration of each time period, the degree of abnormal change in waist circumference trend in any given stage is obtained. The ratio between the average of all glycated hemoglobin data from any given stage and the upper limit of the glycated hemoglobin standard range is used as the blood glucose abnormality coefficient for any given stage. By combining the abnormal trend change in waist circumference and the abnormal blood glucose coefficient, the multidimensional abnormal blood glucose performance of any stage is obtained. Both the abnormal trend change in waist circumference and the abnormal blood glucose coefficient are positively correlated with the multidimensional abnormal blood glucose performance.

4. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 3, characterized in that, The step of obtaining the degree of abnormal change in waist circumference trend in any stage based on the waist circumference data at the last moment of each time period, the waist circumference data at the first moment, and the duration of each time period includes: Calculate the first difference between the waist circumference data at the last moment and the waist circumference data at the first moment in each time period; use the normalized result of the ratio between the first difference and the duration of the time period as the waist circumference change characteristic value for each time period. The ratio between the waist circumference data at the last moment of each time period and the waist circumference data at the first moment is taken as the waist circumference change ratio for each time period. By combining the characteristic values ​​and ratios of waist circumference changes across all time periods in any given stage, the degree of abnormal trend change in waist circumference in any given stage can be obtained.

5. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 1, characterized in that, The determination of the exercise pattern performance in each stage is based on the distribution of daily sedentary time and low-to-moderate intensity exercise time within each stage, including: For any stage: The relative exercise performance level for any given stage is obtained based on the average daily sedentary time and the average daily low-to-medium intensity exercise time for any given stage. Obtain the intersection and union of the total time intervals of low-to-medium intensity exercise for each day of any given stage, and use the ratio between the duration of the intersection and the duration of the union as the exercise pattern factor for any given stage. Based on the relative motion performance degree and the motion law factor, the motion law performance degree of any stage is obtained, and both the relative motion performance degree and the motion law factor are positively correlated with the motion law performance degree.

6. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 5, characterized in that, The method of obtaining the relative exercise performance level for any given stage based on the average daily sedentary time and average daily low-to-moderate intensity exercise time includes: The average daily sitting time in any of the above stages is used as the sitting time performance index of the above stages; the average daily low-to-moderate intensity exercise time in any of the above stages is used as the exercise time performance index of the above stages. Based on the performance of exercise duration and the performance of sitting time in any given stage, the relative performance of exercise duration in any given stage is obtained. The performance of exercise duration is positively correlated with the relative performance of exercise duration, and the performance of sitting time is negatively correlated with the relative performance of exercise duration.

7. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 1, characterized in that, The reproductive metabolic abnormality score is obtained by comprehensively considering all abnormalities in uric acid fluctuations, multidimensional abnormalities in blood glucose, and abnormalities in exercise patterns. This includes: The product of the abnormality of uric acid fluctuation and the abnormality of multidimensional blood glucose in each stage is calculated and recorded as the first characteristic value of each stage; the first difference between constant 1 and the abnormality of uric acid fluctuation in each stage is calculated; the product of the first difference and the corresponding stage's movement pattern performance is recorded as the second characteristic value of each stage. The degree of reproductive metabolic abnormality is obtained by combining the first and second feature values ​​from all stages.

8. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 7, characterized in that, The degree of reproductive metabolic abnormality is obtained by combining the first and second feature values ​​from all stages, including: Calculate the second difference between the first eigenvalue and the second eigenvalue; The sum of the second differences across all stages is determined as the degree of reproductive metabolic abnormality.

9. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 1, characterized in that, The process of obtaining the degree of abnormality in reproductive indicators based on the relative relationship between reproductive indicator data and corresponding standard ranges includes: Each data point in the reproductive indicator data is determined to be within its corresponding standard range. If it is, the first parameter of the corresponding data point in the reproductive indicator data is set to a preset fourth value; otherwise, the first parameter of the corresponding data point in the reproductive indicator data is set to a fifth value. The fourth value is greater than the fifth value. The normalized result of the cumulative sum of the first parameter of all data in the reproductive index is determined as the degree of abnormality in the reproductive index.

10. The AI-based intelligent early warning system for male reproductive metabolic abnormalities with hyperuricemia according to claim 1, characterized in that, The combined degree of reproductive metabolic abnormality and the degree of abnormality in reproductive indicators yield a comprehensive assessment of the target male's multidimensional characteristics linked to his reproductive metabolic performance, including: By using the abnormality of the reproductive indicators as a weight, the abnormality of reproductive metabolism is weighted to obtain a comprehensive evaluation of the multidimensional characteristics of the target male's reproductive metabolic performance.

Images