Diabetes symptom automatic detection system

Abstract

The invention relates to the technical field of physiological measurement, in particular to a diabetes symptom automatic detection system which comprises a blood glucose fluctuation analysis module, a polydipsia and polyuria symptom detection module, a decline level evaluation module and a progress stage recognition module. According to the invention, through the correlation analysis of real-time blood glucose monitoring and the diet state of the patient, the change of the blood glucose level is accurately captured, the development trend of the illness state is predicted, the real-time performance of illness state monitoring is enhanced, the medical intervention is more timely and effective, and through the continuous monitoring of the water intake and the urine volume of the patient, the polydipsia and diuresis symptoms of the diabetic patient are timely found, and the patient experience is improved. The correlation between a target symptom and the development of diabetes is determined through data analysis, the recognition capability of early-stage diabetic complications is enhanced, the organ function level is evaluated, the signs of organ damage are recognized, the treatment strategy is helped to be adjusted, the development of complications is prevented, the real-time performance and accuracy of disease monitoring are improved, and the disease diagnosis and treatment efficiency is improved. And the complexity and the cost of long-term treatment are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of physiological measurement, and in particular to an automatic detection system for diabetes symptoms. Background Art

[0002] The field of physiological measurement technology focuses on detecting, recording and interpreting various physiological signals of the human body. It is used to monitor heart activity, blood pressure, blood sugar, blood oxygen saturation, body temperature and many other important physiological parameters. By using sensors, wearable devices and non-invasive monitoring systems, it helps medical professionals obtain patients' health status in real time, and assists in diagnosis, monitors disease progression, monitors treatment effects and prevents the development of chronic diseases. Combined with data processing and analysis technology, it extracts a variety of useful information from complex data to achieve long-term health management and acute disease monitoring.

[0003] Among them, an automatic detection system for diabetes symptoms focuses on automatically monitoring and identifying various related symptoms of diabetes, including real-time tracking of patients' blood sugar levels, physical reactions and various physiological indicators indicating changes in the disease, helping to understand the patient's blood sugar status in real time. By integrating sensing technology and intelligent algorithms, it realizes automated data collection and analysis, provides key information to doctors and patients in a timely manner and assists in medical decision-making, helps manage diabetes and prevent the occurrence of complications, achieves early intervention and reduces health risks, and improves patients' treatment effects and quality of life.

[0004] Traditional automatic diabetes symptom detection systems have steps in the management and prevention of diabetes. They focus on monitoring a single indicator or providing data at a specific point in time. They lack the ability to conduct in-depth analysis of the correlation between data and predict long-term trends. They are unable to analyze the trend of blood sugar changes and the interaction with multiple physiological parameters, including changes in diet and urine volume. As a result, medical professionals are unable to make the best medical decisions when they cannot obtain comprehensive information in real time. They rely on regular medical examinations to monitor organ decline, which delays the diagnosis of early organ damage, misses the best time for treatment, and has insufficient preventive measures for disease progression. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an automatic detection system for diabetes symptoms.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a diabetes symptom automatic detection system comprises:

[0007] The blood sugar fluctuation analysis module analyzes the patient's blood sugar fluctuation pattern based on real-time blood sugar monitoring data. Combined with the patient's dietary status, it analyzes the impact of nutritional intake on blood sugar fluctuations, predicts the patient's blood sugar level development trend, and generates a blood sugar feature data set.

[0008] The polyuria and polyuria symptom detection module is based on the blood sugar characteristic data set, collects the patient's water intake and urine volume data, evaluates the patient's polyuria symptom level, and calculates the correlation between the polyuria symptom characteristics and the diabetes progression stage according to the relationship between the urine volume level and the blood sugar characteristics, and outputs the polyuria symptom analysis results;

[0009] The decline level assessment module uses the polyuria symptom analysis results to collect multiple physiological characteristic data of the target patient, compares them with known organ decline pattern characteristic data, calculates the matching degree of the multiple physiological characteristic data, assesses the patient's organ decline level, and generates organ decline monitoring information;

[0010] The progression stage identification module identifies the development stage of the patient's condition based on the organ decline monitoring information and the patient's blood sugar level, urine volume level and organ function level data, and generates a diabetes stage classification result.

[0011] As a further solution of the present invention, the step of obtaining the blood sugar fluctuation pattern is specifically as follows:

[0012] Based on real-time blood glucose monitoring data, use the formula:

[0013]

[0014] Calculate the blood sugar fluctuation score;

[0015] Among them, x i is the blood glucose value measured at the ith time, i represents the measurement index, N is the number of blood glucose measurements in a day, k is the adjustment coefficient for adjusting the sensitivity of the fluctuation score, and σ represents the daily blood glucose fluctuation score;

[0016] Based on the blood sugar fluctuation degree score, the target patient's daily blood sugar fluctuation degree is analyzed, and the blood sugar fluctuation pattern is identified in combination with the fluctuation cycle of the patient's blood sugar data.

[0017] As a further solution of the present invention, the step of acquiring the blood glucose characteristic data set is specifically:

[0018] Based on the blood sugar fluctuation pattern, the target patient's dietary record information is collected, and the blood sugar measurement values ​​and corresponding nutrient intake corresponding to multiple dietary events are extracted. The formula is:

[0019]

[0020] Calculate the coefficient of the effect of nutrient intake on blood sugar,

[0021] Where ΔX j is the difference between the blood sugar level after eating and the previous measurement, C j is the corresponding nutritional intake, α represents the influence of nutritional intake level on blood sugar changes, Xj represents the blood glucose value measured after eating, and j is the index used to mark the eating event;

[0022] Based on the coefficient of the effect of the nutrient intake on blood sugar, analyze the blood sugar response under various nutrient intake levels, evaluate the expected blood sugar fluctuations under various dietary conditions, and generate sensitivity analysis results;

[0023] According to the sensitivity analysis results, the patient's blood sugar level development trend is predicted based on the patient's eating habits and nutritional intake level, and a blood sugar characteristic data set is generated.

[0024] As a further embodiment of the present invention, the step of obtaining the polyuria symptom level is specifically as follows:

[0025] Based on the blood sugar characteristic data set, collecting the patient's drinking and urination data, recording the patient's urination frequency and urine volume, and generating the patient's urine volume data;

[0026] Based on the patient's urine volume data, the formula:

[0027]

[0028] The severity score of polyuria symptoms was calculated;

[0029] Among them, U o is the urine volume per urination, Ul is the ratio of actual urine volume to ideal urine volume, which is used to quantify the severity of polyuria symptoms, Ub is the basal urine volume, and k a is the adjustment coefficient for age, k w is the adjustment factor for body weight, k s is the adjustment coefficient for sex, a is the actual age of the patient, w is the weight of the patient, s is the sex of the patient, and o is the index of urination events;

[0030] According to the severity score of the polyuria symptom, the polyuria symptom level of the target patient is classified to generate a polyuria symptom level.

[0031] As a further embodiment of the present invention, the steps for obtaining the polyuria symptom analysis results are specifically as follows:

[0032] Based on the polyuria symptom level, by extracting the daily urine volume data and blood glucose data of the target patient, the formula is:

[0033]

[0034] Calculate the correlation between daily urine volume and patient blood glucose data to obtain the correlation coefficient;

[0035] Among them, Y l represents a single measurement of daily urine volume, represents the average value of daily urine volume data, S l Indicates the blood sugar value of a single measurement. represents the average value of blood glucose data, r represents the correlation coefficient, and l represents the index of the data point;

[0036] Based on the correlation coefficient, the correlation between the polydipsia and polyuria symptom level and the stage of diabetes progression is evaluated, and the polyuria symptom analysis result is output in combination with the severity of the polydipsia and polyuria symptoms of the patient.

[0037] As a further solution of the present invention, the steps for obtaining the matching degree of the plurality of physiological characteristic data are specifically as follows:

[0038] Based on the polyuria symptom analysis results, multiple physiological parameter data of the target patient are collected, including blood pressure, electrocardiogram, and renal function index, and the change trends and fluctuation patterns of the multiple parameters, including the average change rate and fluctuation index, are calculated to generate data change characteristic values;

[0039] Based on the data change characteristic value, through the formula:

[0040]

[0041] Calculate the similarity between the measured physiological data and the known organ decline pattern characteristic data to obtain the physiological characteristic similarity value;

[0042] Among them, S pq is the similarity index between the measured data and the standard pattern, V p is the average rate of change of the measured data, F p is the volatility index of the measured data, V q is the average rate of change of known standard data, F q is the fluctuation index of known standard data, p represents the index of measured data characteristics, and q represents the index of known organ decline pattern characteristic data;

[0043] Based on the physiological characteristic similarity value, the similarity calculation results of multiple physiological parameter characteristic values ​​are summarized to generate the matching degree of multiple physiological characteristic data.

[0044] As a further solution of the present invention, the step of acquiring the organ decline monitoring information is specifically as follows:

[0045] Based on the matching degree of the multiple physiological characteristic data, influence weights are assigned to the multiple physiological parameters to reflect the actual influence of the multiple physiological parameters on the patient's health status, and characteristic weight matching degree data is generated;

[0046] Based on the feature weight matching data, the formula is:

[0047]

[0048] Calculate the degree of organ decline of the patient and obtain the predicted data of organ decline;

[0049] Among them, R represents the predicted organ decline, β0 is the intercept of the regression model, and β z is the regression coefficient of the zth physiological characteristic, Q z is the matching value of the zth physiological feature, z represents the index of a specific physiological feature, and Z represents the total number of physiological features;

[0050] Based on the organ decline prediction data, the organ decline level of the target diabetic patient is evaluated in real time to generate organ decline monitoring information.

[0051] As a further solution of the present invention, the steps for obtaining the diabetes stage classification result are specifically as follows:

[0052] Based on the organ decline monitoring information, extracting the patient's blood sugar level, urine volume level and organ function level data to generate diabetes progression characteristic data;

[0053] Based on the diabetes progression characteristic data, the formula:

[0054] P′=a′1·D1+a′2·D2+a′3·D3;

[0055] Calculate the condition score of the target patient;

[0056] P′ represents the comprehensive score of the disease condition, D1 represents the standardized score of blood glucose value, D2 represents the standardized score of urine volume, D3 represents the standardized score of organ function, a′1 is the weight coefficient of blood glucose value, a′2 is the weight coefficient of urine volume, and a′3 is the weight coefficient of organ function;

[0057] Based on the target patient's disease condition score and combined with the physician's opinion, the target diabetic patient's disease condition development stage is evaluated in real time to generate a diabetes stage classification result.

[0058] Compared with the prior art, the advantages and positive effects of the present invention are:

[0059] In the present invention, through the correlation analysis of real-time blood sugar monitoring and the patient's dietary status, the changes in blood sugar levels can be accurately captured, the development trend of the disease can be predicted, the real-time nature of disease monitoring can be enhanced, and medical intervention can be more timely and effective. Through the continuous monitoring of the patient's water intake and urine volume, the symptoms of polydipsia and polyuria in diabetic patients can be discovered in time, and the correlation between the target symptoms and the progression of diabetes can be determined through data analysis, thereby enhancing the ability to identify early diabetic complications. Combined with the assessment of organ function levels, signs of organ damage can be identified, helping to adjust treatment strategies and prevent the development of complications, thereby improving the real-time nature and accuracy of disease monitoring and reducing the complexity and cost of long-term treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a system flow chart of the present invention;

[0061] Figure 2 This is a flow chart of analyzing blood sugar fluctuation patterns of the present invention;

[0062] Figure 3 This is a flow chart of obtaining a blood glucose characteristic data set of the present invention;

[0063] Figure 4 A flow chart for calculating the polyuria symptom level of the present invention;

[0064] Figure 5 A flow chart of generating polyuria symptom analysis results of the present invention;

[0065] Figure 6 A flow chart of calculating the matching degree of multiple physiological characteristic data of the present invention;

[0066] Figure 7 A flow chart of obtaining organ decline monitoring information of the present invention;

[0067] Figure 8 The present invention is a flow chart for obtaining diabetes stage classification results. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0069] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0070] See also Figure 1 , a diabetes symptom automatic detection system comprising:

[0071] The blood sugar fluctuation analysis module analyzes the patient's blood sugar fluctuation pattern based on real-time blood sugar monitoring data. Combined with the patient's dietary status, it analyzes the impact of nutritional intake on blood sugar fluctuations, predicts the patient's blood sugar level development trend, and generates a blood sugar feature data set.

[0072] The polyuria and polyuria symptom detection module is based on the blood glucose characteristic data set. It collects the patient's water intake and urine volume data to evaluate the patient's polyuria symptom level, and calculates the correlation between the polyuria symptom characteristics and the stage of diabetes progression based on the relationship between the urine volume level and blood glucose characteristics, and outputs the polyuria symptom analysis results;

[0073] The decline level assessment module uses the polyuria symptom analysis results to collect multiple physiological characteristic data of the target patient, and by comparing with the known organ decline pattern characteristic data, calculates the matching degree of multiple physiological characteristic data, assesses the patient's organ decline level, and generates organ decline monitoring information;

[0074] The progression stage recognition module is based on the organ decline monitoring information and the patient's blood sugar level, urine volume level and organ function level data to identify the patient's disease development stage and generate a diabetes stage classification result.

[0075] The blood glucose feature data set specifically includes blood glucose peak and trough values, blood glucose fluctuation cycle, and nutritional intake impact analysis results. The polyuria symptom analysis results specifically include polyuria symptom level, diabetes progression stage correlation index, patient water intake and urine volume data. The organ decline monitoring information specifically includes organ decline level calculation results, data feature matching degree, and patient physiological feature data set. The diabetes stage classification results specifically include disease progression classification, patient disease risk score, and patient disease development trend information.

[0076] See also Figure 2 , the specific steps for obtaining the blood sugar fluctuation pattern are:

[0077] Based on real-time blood glucose monitoring data, use the formula:

[0078]

[0079] Calculate the blood sugar fluctuation score;

[0080] Among them, x i is the blood glucose value measured at the ith time, i represents the measurement index, N is the number of blood glucose measurements in a day, k is the adjustment coefficient for adjusting the sensitivity of the fluctuation score, and σ represents the daily blood glucose fluctuation score;

[0081] formula:

[0082]

[0083] Parameter meaning and acquisition method:

[0084] x i : The blood glucose value measured for the i-th time, obtained in real time through the blood glucose monitoring device;

[0085] N: the number of blood glucose measurements in a day, obtained through the daily record setting of the blood glucose monitoring device;

[0086] k: adjustment factor, used to adjust the sensitivity of the volatility score;

[0087] σ: represents the daily blood sugar fluctuation score;

[0088] Calculation example:

[0089] Suppose there are 5 blood sugar measurements, that is, N = 5, and the measured value x i They are 100, 105, 98, 103, and 110 respectively, and the adjustment coefficient k is 1.5. The degree of blood sugar fluctuation is calculated as follows:

[0090]

[0091]

[0092]

[0093] σ=1.5×4.66;

[0094] σ=6.99;

[0095] The calculation result σ=6.99 indicates that the patient's blood glucose fluctuation score for that day is 6.99. The numerical value provides an assessment of the enhanced sensitivity to blood glucose fluctuations and is used to understand the fluctuation of the patient's blood glucose control.

[0096] Based on the blood sugar fluctuation score, analyze the target patient's daily blood sugar fluctuation, and identify the blood sugar fluctuation pattern based on the fluctuation cycle of the patient's blood sugar data;

[0097] By collecting blood glucose monitoring data of target patients within a certain period, using time series analysis methods to analyze the data, determining the frequency and amplitude of blood glucose fluctuations, and identifying the main patterns of blood glucose fluctuations, such as periodic peaks and troughs, mathematical modeling technology and Fourier transform analysis methods are used to convert time series data into the frequency domain and extract the periodic characteristics of blood glucose data. The analysis helps medical providers to deeply understand the fluctuation patterns of the disease and provide a basis for adjusting treatment plans. The detailed blood glucose fluctuation reports generated are used to optimize disease management strategies and improve patient treatment responses.

[0098] See also Figure 3 ,The specific steps for obtaining the blood glucose feature dataset are:

[0099] Based on the blood sugar fluctuation pattern, the target patient's dietary record information is collected, and the blood sugar measurement values ​​and corresponding nutrient intake corresponding to multiple dietary events are extracted. The formula is:

[0100]

[0101] Calculate the coefficient of the effect of nutrient intake on blood sugar,

[0102] Where ΔX j is the difference between the blood sugar level after eating and the previous measurement, C j is the corresponding nutritional intake, α represents the influence of nutritional intake level on blood sugar changes, X j represents the blood glucose value measured after eating, and j is the index used to mark the eating event;

[0103] formula:

[0104]

[0105] Parameter meaning and acquisition method:

[0106] C j : is the carbohydrate intake of the jth dietary event, obtained through the food intake and nutrition database recorded in the dietary diary;

[0107] X j : is the blood glucose value measured after the jth dietary event, obtained by a blood glucose monitoring device;

[0108] ΔX j : is the change in blood sugar between the jth diet and the previous measurement;

[0109] α: The coefficient of the effect of nutrient intake on blood sugar, used to evaluate the average effect of diet on blood sugar changes;

[0110] Calculation example:

[0111] Setting C jis 50, 60, 40, ΔX j For 20, 15, and 10, calculate the influence coefficient:

[0112] Calculate ∑(C j ×ΔX j ):

[0113] ∑(C j ×ΔX j )=50×20+60×15+40×10=1000+900+400=2300; Calculate

[0114]

[0115] Calculate α:

[0116]

[0117] α=0.2987 indicates that the average change in blood sugar caused by each unit of carbohydrate is 0.2987. The value reflects the average intensity of the impact of food on blood sugar. The coefficient is used to evaluate the effect of dietary adjustment on blood sugar control.

[0118] Based on the coefficient of the effect of nutrient intake on blood sugar, analyze the blood sugar response under various nutrient intake levels, evaluate the expected blood sugar fluctuations under various dietary conditions, and generate sensitivity analysis results;

[0119] By analyzing the patient's past dietary records and corresponding blood sugar response data, the relationship between food intake and blood sugar response is quantitatively evaluated using regression analysis technology. During the analysis, the blood sugar impact coefficient of each type of food is determined, and the correlation coefficient between nutrients and blood sugar changes is calculated. The sensitivity analysis results show the impact of food ingredients on blood sugar control. By dynamically simulating blood sugar responses under different dietary scenarios, a food blood sugar response model is constructed to provide patients with personalized dietary advice, guide patients to adjust their daily diet, and optimize blood sugar control strategies.

[0120] According to the sensitivity analysis results, the patient's blood sugar level development trend is predicted based on the patient's eating habits and nutritional intake level, and a blood sugar feature data set is generated;

[0121] The linear regression model in machine learning technology is used to predict the patient's future blood sugar level trend. The patient's historical diet and blood sugar data are collected and organized, and the prediction model is trained with the data to ensure that the model can accurately reflect the patient's blood sugar change pattern. Through algorithm adjustment and optimization, the generated blood sugar feature data set provides a scientific basis for medical decision-making, improves the accuracy of diabetes management and the patient's quality of life.

[0122] See also Figure 4, the specific steps for obtaining the polyuria symptom level are:

[0123] Based on the blood glucose characteristic data set, the patient's drinking and urination data are collected, the patient's urination frequency and urine volume are recorded, and the patient's urine volume data is generated;

[0124] An automatic data collection system is set up to record the patient's water intake and subsequent urine output once an hour. Sensors and mobile applications are used to record detailed water intake and urine output data. The collected data is quality checked to exclude any abnormal values, such as abnormally high urine volume or unrecorded drinking events. The total daily urine volume and urine volume fluctuations are calculated through statistical software, and the intra-day and inter-day changes in urine volume are evaluated to generate detailed urine volume data for the patient. After the data is processed by an algorithm, it is converted into easy-to-interpret trend charts and cycle charts to assist medical professionals in monitoring and evaluating patients' water metabolism health and changes in diabetic conditions.

[0125] Based on the patient's urine volume data, the formula:

[0126]

[0127] The severity score of polyuria symptoms was calculated;

[0128] Among them, U o is the urine volume per urination, Ul is the ratio of actual urine volume to ideal urine volume, which is used to quantify the severity of polyuria symptoms, Ub is the basal urine volume, and k a is the adjustment coefficient for age, k w is the adjustment factor for body weight, k s is the adjustment coefficient for sex, a is the actual age of the patient, w is the weight of the patient, s is the sex of the patient, and o is the index of urination events;

[0129] formula:

[0130]

[0131] Parameter meaning and acquisition method

[0132] U o :The amount of urine the patient urinates each time is obtained through the urine volume measurement equipment in the hospital;

[0133] Ub: basal urine volume, representing the average urine volume standard for healthy adults, determined based on medical research;

[0134] k a : Age adjustment factor, determined based on clinical studies, used to adjust urine volume according to the patient's age;

[0135] k w : Weight adjustment factor, determined based on clinical studies, used to adjust urine volume according to the patient's weight;

[0136] k s : Gender adjustment coefficient, obtained based on research on gender differences;

[0137] a: The actual age of the patient, obtained from the patient's medical record;

[0138] w: actual weight of the patient, obtained from the patient's medical record;

[0139] s: patient's sex, obtained from the patient's medical record;

[0140] Calculation Example

[0141] Set the target patient's actual urine volume per time U o The data is [500, 550, 520, 540] mL, Ub = 1500 mL / day, k a =0.5mL / day / year, k w =1mL / day / kg, k s =100mL / day, a=55years, w=70kg, s=1, calculate the severity of symptoms:

[0142]

[0143] The result Ul=1.243 means that the actual urine volume is 124.3% of the ideal urine volume, indicating that the patient has significant polyuria symptoms. The value is used to help doctors evaluate the condition and adjust treatment strategies.

[0144] The polyuria symptom level of the target patient was classified according to the severity score of polyuria symptoms to generate a polyuria symptom level;

[0145] The patient's urine volume data is compared with the clinical symptom records, and a standardized scoring table is used to quantify the severity of each symptom. Statistical analysis tools, such as factor analysis, are used to determine the contribution of each symptom to the total score. The patient's polyuria symptoms are objectively classified. Based on the scoring results and relevant medical guidelines, a polyuria symptom level report is generated for each patient. This report lists the specific manifestations of the patient's polyuria symptoms and recommended medical responses, providing a basis for formulating targeted treatment plans.

[0146] See also Figure 5 , the specific steps for obtaining the results of polyuria symptom analysis are:

[0147] Based on the polyuria symptom level, by extracting the daily urine volume data and blood glucose data of the target patient, the formula is:

[0148]

[0149] Calculate the correlation between daily urine volume and patient blood glucose data to obtain the correlation coefficient;

[0150] Among them, Y l represents a single measurement of daily urine volume, represents the average value of daily urine volume data, S l Indicates the blood sugar value of a single measurement. represents the average value of blood glucose data, r represents the correlation coefficient, which is used to measure the strength of the linear correlation between daily urine volume Y and blood glucose S, and l represents the index of the data point;

[0151] formula:

[0152]

[0153] Parameter meaning and acquisition method:

[0154] Y l : Specific measurement of daily urine output;

[0155] Average daily urine output;

[0156] S l : Specific measurement value of blood sugar;

[0157] Average value of blood sugar data;

[0158] r: correlation coefficient, used to measure the strength of the linear correlation between daily urine volume Y and blood glucose S;

[0159] Calculation Example

[0160] The daily urine volume data of the target patients is set to [500, 600, 550, 580, 610], The blood sugar data is [5.0, 5.5, 5.3, 5.2, 5.6], Calculate the correlation coefficient:

[0161]

[0162]

[0163]

[0164]

[0165] r≈0.901;

[0166] The calculation result r=0.901 indicates that there is a positive correlation between urine volume and blood sugar, which means that as blood sugar increases, urine volume increases. The value reflects the close correlation between polyuria symptoms and the progression stage of diabetes.

[0167] Based on the correlation coefficient, the correlation between the polydipsia and polyuria symptom level and the stage of diabetes progression was evaluated, and the polyuria symptom analysis results were output in combination with the severity of the polydipsia and polyuria symptoms of the patient;

[0168] Multivariate regression analysis was used to evaluate the correlation between the level of polydipsia and polyuria symptoms and the stage of diabetes progression. The patient's urine volume data and blood glucose monitoring results were integrated, and statistical models were applied to analyze the target data to identify potential related patterns. By judging the interaction between changes in urine volume and abnormal blood glucose, detailed polyuria symptom analysis results were output. The results provided important insights into the progression of the patient's disease, supported clinical decision-making, and helped doctors adjust treatment plans for patients, including in diabetes management and complication prevention.

[0169] See also Figure 6 , the steps for obtaining the matching degree of multiple physiological characteristic data are as follows:

[0170] Based on the results of polyuria symptom analysis, multiple physiological parameter data of target patients are collected, including blood pressure, electrocardiogram, and renal function index, and the change trends and fluctuation patterns of multiple parameters, including average change rate and fluctuation index, are calculated to generate data change characteristic values;

[0171] Comprehensive collection of multiple physiological parameters of target patients is carried out, including data collected by sphygmomanometers, electrocardiographs and renal function testing equipment. Each device is calibrated to ensure data accuracy, and patients' daily blood pressure, electrocardiogram and renal function indicators are systematically recorded. Through data analysis software, the sliding window average method and standard deviation calculation method are used to evaluate the changing trend and volatility of each physiological parameter, identify key health change signals, and calculate data change characteristic values ​​including average change rate and fluctuation index. The characteristic values ​​serve as an important basis for evaluating patients' health status and changes in their condition.

[0172] Based on the data change characteristic value, through the formula:

[0173]

[0174] Calculate the similarity between the measured physiological data and the known organ decline pattern characteristic data to obtain the physiological characteristic similarity value;

[0175] Among them, S pq is the similarity index between the measured data and the standard pattern, V p is the average rate of change of the measured data, F p is the volatility index of the measured data, Vq is the average rate of change of known standard data, F q is the fluctuation index of known standard data, p represents the index of measured data characteristics, including blood pressure, electrocardiogram, and renal function level, and q represents the index of known organ decline pattern characteristic data;

[0176] formula:

[0177]

[0178] Parameter meaning and acquisition method:

[0179] V p : Average rate of change of measured physiological data;

[0180] F p : Fluctuation index of measured physiological data;

[0181] V q : The average rate of change of known organ decline pattern data;

[0182] F q : Fluctuation index of known organ decline pattern data:

[0183] Calculation example:

[0184] Assume that the measured physiological data points are [100, 105, 95, 110, 90], and the known organ decline pattern data points are [95, 100, 105, 95, 100]. p =-2.5, V q =1.25, F p =7.35, F q =3.74, calculate the similarity:

[0185]

[0186]

[0187] The calculation results show that the similarity between the measured values ​​and the known organ decline pattern characteristic data is 0.795. The value reflects the high similarity between the measured data and the known decline pattern. The calculation process is used to evaluate the matching degree of various physiological characteristics and pathological models.

[0188] Based on the physiological characteristic similarity value, the matching degree of multiple physiological characteristic data is generated by summarizing the similarity calculation results of multiple physiological parameter characteristic values;

[0189] Multivariate data analysis techniques, such as principal component analysis and cluster analysis, are used to calculate the similarity of the characteristic values ​​of each physiological parameter, standardize each physiological parameter to eliminate the impact of dimension, apply PCA to extract the main change trends and patterns, and further determine the similarity between parameters through cluster analysis. The calculation process reveals the correlation between different physiological parameters, providing a scientific basis for comprehensive judgment of the patient's health status, summarizing the similarity calculation results, and generating a comprehensive matching degree of multiple physiological characteristic data, providing medical professionals with accurate health assessment and disease monitoring tools.

[0190] See also Figure 7 ,The specific steps for obtaining organ decline monitoring information are:

[0191] Based on the matching degree of multiple physiological characteristic data, influence weights are assigned to multiple physiological parameters to reflect the actual impact of multiple physiological parameters on the patient's health status and generate feature weight matching degree data;

[0192] A weight allocation model, such as weighted linear regression analysis, is used to assign corresponding influence weights to different physiological parameters such as blood pressure, electrocardiogram and renal function indicators. A baseline impact model of each parameter on the patient's health status is established through historical data. The weight of each parameter is adjusted according to the current matching data to reflect its actual influence in the current health status assessment. The characteristic weight of each physiological parameter is calculated, and the weights are summarized to generate comprehensive characteristic weight matching data. The data helps medical professionals understand the importance of each physiological indicator on the disease and optimize treatment and monitoring strategies.

[0193] Based on the feature weight matching data, through the formula:

[0194]

[0195] Calculate the degree of organ decline of the patient and obtain the predicted data of organ decline;

[0196] Among them, R represents the predicted organ decline, β0 is the intercept of the regression model, and β z is the regression coefficient of the zth physiological characteristic, Q z is the matching value of the zth physiological feature, z represents the index of a specific physiological feature, and Z represents the total number of physiological features;

[0197] formula:

[0198]

[0199] Parameter meaning and acquisition method:

[0200] R: predicted organ decline;

[0201] β0: The intercept of the regression model, obtained by analyzing historical health data, represents the basic decline level when there is no influence of any physiological parameters;

[0202] β z : The regression coefficient of the zth physiological parameter, reflecting the weight of the physiological parameter on the degree of decline;

[0203] Q z : The matching value of the zth physiological parameter, obtained from the physiological feature matching data, is used as the input for linear regression analysis;

[0204] z: physiological parameter index;

[0205] Z: total number of physiological parameters;

[0206] Calculation example:

[0207] Set Q1 = 0.8, Q2 = 0.6, Q3 = 0.9, β0 = 0.5, β1 = 0.3, β2 = 0.2, β3 = 0.4, Z = 3, calculate the organ decline:

[0208] R=0.5+(0.3·0.8+0.2·0.6+0.4·0.9);

[0209] R = 0.5 + (0.24 + 0.12 + 0.36);

[0210] R = 0.5 + 0.72;

[0211] R = 1.22;

[0212] The calculation results show that the predicted organ decline degree is 1.22. The value reflects the comprehensive decline state based on the matching degree of given physiological parameters. The formula is used to evaluate the patient's organ decline level and help doctors make diagnosis and treatment decisions.

[0213] Based on the organ decline prediction data, the organ decline level of the target diabetic patient is evaluated in real time, and organ decline monitoring information is generated;

[0214] Use dynamic models, such as dynamic system models, combined with the patient's latest physiological parameter data and historical decline trends, to conduct real-time data analysis and prediction. Through the model, the decline rate and degree of organ function are calculated and updated in real time, generating detailed organ decline monitoring information. This information provides doctors with instant clinical data to support more accurate treatment decisions, while providing patients with important information about the progression of their disease, helping to adjust personal health management plans and prevent potential complications.

[0215] See also Figure 8 , the specific steps for obtaining the diabetes stage classification results are:

[0216] Based on the organ decline monitoring information, the patient's blood sugar level, urine volume level and organ function level data are extracted to generate diabetes progression characteristic data;

[0217] Data extraction technology is used to extract key physiological indicators, including patients' blood sugar levels, urine volume levels and organ function level data. The collected blood sugar and urine volume monitoring results are integrated through an automated data processing system, and the patient's latest organ function test report is synchronized. Through data integration and analysis, the changing trends of multiple indicators in time series are evaluated. Time series analysis techniques, such as moving average or exponential smoothing technology, are used to determine the fluctuation patterns of blood sugar and urine volume and their correlation with organ function decline. The process generates characteristic data on diabetes progression, which provides accurate basic information for subsequent disease analysis and stage classification.

[0218] Based on the diabetes progression characteristic data, the formula:

[0219] P′=a′1·D1+a′2·D2+a′3·D3;

[0220] Calculate the condition score of the target patient;

[0221] P′ represents the comprehensive score of the disease condition, D1 represents the standardized score of blood glucose value, D2 represents the standardized score of urine volume, D3 represents the standardized score of organ function, a′1 is the weight coefficient of blood glucose value, a′2 is the weight coefficient of urine volume, and a′3 is the weight coefficient of organ function;

[0222] formula:

[0223] P′=a′1·D1+a′2·D2+a′3·D3;

[0224] Parameter meaning and acquisition method:

[0225] P′ represents the comprehensive score of the disease condition;

[0226] D1 represents the standardized score of blood glucose value, which is obtained by standardizing the blood glucose data obtained by actual medical testing;

[0227] D2 represents the standardized fraction of urine volume, which is obtained by standardizing the urine volume data obtained from actual medical tests;

[0228] D3 represents the standardized score of organ function, which is obtained by standardizing the organ function test data obtained through actual medical examinations;

[0229] a′1 is the weight coefficient of blood glucose value, which is obtained by analyzing historical health data and reflects the influence of blood glucose value in disease assessment;

[0230] a′2 is the weight coefficient of urine volume, which is obtained by analyzing historical health data and reflects the influence of urine volume in disease assessment;

[0231] a′3 is the weight coefficient of organ function, which is obtained by analyzing historical health data and reflects the influence of organ function in disease assessment;

[0232] Calculation example:

[0233] Set D1 = 0.85, D2 = 0.75, D3 = 0.65, a′1 = 0.4, a′2 = 0.3, a′3 = 0.3, and calculate the comprehensive disease score:

[0234] P′=0.4·0.85+0.3·0.75+0.3·0.65;

[0235] P′=0.34+0.225+0.195;

[0236] P′=0.76;

[0237] The calculation results show that the target patient's comprehensive disease score is 0.76. The value reflects the disease development stage assessment score obtained by integrating blood sugar levels, urine volume and organ function. The value is used to help doctors determine the disease stage of diabetic patients and provide a basis for formulating treatment plans.

[0238] Based on the target patient's disease score and combined with the physician's opinion, the target diabetic patient's disease progression stage is evaluated in real time to generate a diabetes stage classification result;

[0239] By integrating the scores and opinions provided by physicians, using a decision support system and combining logistic regression analysis, a comprehensive assessment of the patient's blood sugar control, urine volume changes and organ function indicators is conducted, and the disease progression stage of diabetic patients is assessed in real time. The model calculation takes into account the correlation between various physiological data and diabetes progression and the influence on the disease stage, and outputs the diabetes stage classification result. The classification result provides doctors and patients with clear information about the current stage of the disease, supporting personalized treatment decisions and disease management strategies.

[0240] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A diabetes symptom automatic detection system, characterized in that: The system comprises: The blood sugar fluctuation analysis module analyzes the patient's blood sugar fluctuation pattern based on real-time blood sugar monitoring data. Combined with the patient's dietary status, it analyzes the impact of nutritional intake on blood sugar fluctuations, predicts the patient's blood sugar level development trend, and generates a blood sugar feature data set. The polyuria and polyuria symptom detection module is based on the blood sugar characteristic data set, collects the patient's water intake and urine volume data, evaluates the patient's polyuria symptom level, and calculates the correlation between the polyuria symptom characteristics and the diabetes progression stage according to the relationship between the urine volume level and the blood sugar characteristics, and outputs the polyuria symptom analysis results; The decline level assessment module uses the polyuria symptom analysis results to collect multiple physiological characteristic data of the target patient, compares them with known organ decline pattern characteristic data, calculates the matching degree of the multiple physiological characteristic data, assesses the patient's organ decline level, and generates organ decline monitoring information; The progression stage identification module identifies the development stage of the patient's condition based on the organ decline monitoring information and the patient's blood sugar level, urine volume level and organ function level data, and generates a diabetes stage classification result.

2. The automatic diabetes symptom detection system according to claim 1, characterized in that: The steps for obtaining the blood sugar fluctuation pattern are specifically as follows: Based on real-time blood glucose monitoring data, use the formula: Calculate the blood sugar fluctuation score; Among them, x i is the blood glucose value measured at the ith time, i represents the measurement index, N is the number of blood glucose measurements in a day, k is the adjustment coefficient for adjusting the sensitivity of the fluctuation score, and σ represents the daily blood glucose fluctuation score; Based on the blood sugar fluctuation degree score, the target patient's daily blood sugar fluctuation degree is analyzed, and the blood sugar fluctuation pattern is identified in combination with the fluctuation cycle of the patient's blood sugar data.

3. The automatic diabetes symptom detection system according to claim 2, characterized in that: The steps for obtaining the blood sugar characteristic data set are specifically as follows: Based on the blood sugar fluctuation pattern, the target patient's dietary record information is collected, and the blood sugar measurement values ​​and corresponding nutrient intake corresponding to multiple dietary events are extracted. The formula is: Calculate the coefficient of the effect of nutrient intake on blood sugar, Where ΔX j is the difference between the blood sugar level after eating and the previous measurement, C j is the corresponding nutritional intake, α represents the influence of nutritional intake level on blood sugar changes, X j represents the blood glucose value measured after eating, and j is the index used to mark the eating event; Based on the coefficient of the effect of the nutrient intake on blood sugar, analyze the blood sugar response under various nutrient intake levels, evaluate the expected blood sugar fluctuations under various dietary conditions, and generate sensitivity analysis results; According to the sensitivity analysis results, the patient's blood sugar level development trend is predicted based on the patient's eating habits and nutritional intake level, and a blood sugar characteristic data set is generated.

4. The automatic diabetes symptom detection system according to claim 1, characterized in that: The steps for obtaining the polyuria symptom level are specifically as follows: Based on the blood sugar characteristic data set, collecting the patient's drinking and urination data, recording the patient's urination frequency and urine volume, and generating the patient's urine volume data; Based on the patient's urine volume data, the formula: The severity score of polyuria symptoms was calculated; Among them, U o is the urine volume per urination, Ul is the ratio of actual urine volume to ideal urine volume, which is used to quantify the severity of polyuria symptoms, Ub is the basal urine volume, and k a is the adjustment coefficient for age, k w is the adjustment factor for body weight, k s is the adjustment coefficient for sex, a is the actual age of the patient, w is the weight of the patient, s is the sex of the patient, and o is the index of urination events; According to the severity score of the polyuria symptom, the polyuria symptom level of the target patient is classified to generate a polyuria symptom level.

5. The automatic diabetes symptom detection system according to claim 4, characterized in that: The steps for obtaining the polyuria symptom analysis result are specifically as follows: Based on the polyuria symptom level, by extracting the daily urine volume data and blood glucose data of the target patient, the formula is: Calculate the correlation between daily urine volume and patient blood glucose data to obtain the correlation coefficient; Among them, Y l represents a single measurement of daily urine volume, represents the average value of daily urine volume data, S l Indicates the blood sugar value of a single measurement. represents the average value of blood glucose data, r represents the correlation coefficient, and l represents the index of the data point; Based on the correlation coefficient, the correlation between the polydipsia and polyuria symptom level and the stage of diabetes progression is evaluated, and the polyuria symptom analysis result is output in combination with the severity of the polydipsia and polyuria symptoms of the patient.

6. The automatic diabetes symptom detection system according to claim 1, characterized in that: The steps for obtaining the matching degree of the multiple physiological characteristic data are specifically as follows: Based on the polyuria symptom analysis results, multiple physiological parameter data of the target patient are collected, including blood pressure, electrocardiogram, and renal function index, and the change trends and fluctuation patterns of the multiple parameters, including the average change rate and fluctuation index, are calculated to generate data change characteristic values; Based on the data change characteristic value, through the formula: Calculate the similarity between the measured physiological data and the known organ decline pattern characteristic data to obtain the physiological characteristic similarity value; Among them, S pq is the similarity index between the measured data and the standard pattern, V p is the average rate of change of the measured data, F p is the volatility index of the measured data, V q is the average rate of change of known standard data, F q is the fluctuation index of known standard data, p represents the index of measured data characteristics, and q represents the index of known organ decline pattern characteristic data; Based on the physiological characteristic similarity value, the similarity calculation results of multiple physiological parameter characteristic values ​​are summarized to generate the matching degree of multiple physiological characteristic data.

7. The automatic diabetes symptom detection system according to claim 6, characterized in that: The steps for obtaining the organ decline monitoring information are specifically as follows: Based on the matching degree of the multiple physiological characteristic data, influence weights are assigned to the multiple physiological parameters to reflect the actual influence of the multiple physiological parameters on the patient's health status, and characteristic weight matching degree data is generated; Based on the feature weight matching data, the formula is: Calculate the degree of organ decline of the patient and obtain the predicted data of organ decline; Among them, R represents the predicted organ decline, β0 is the intercept of the regression model, and β z is the regression coefficient of the zth physiological characteristic, Q z is the matching value of the zth physiological feature, z represents the index of a specific physiological feature, and Z represents the total number of physiological features; Based on the organ decline prediction data, the organ decline level of the target diabetic patient is evaluated in real time to generate organ decline monitoring information.

8. The automatic diabetes symptom detection system according to claim 1, characterized in that: The steps for obtaining the diabetes stage classification result are specifically as follows: Based on the organ decline monitoring information, extracting the patient's blood sugar level, urine volume level and organ function level data to generate diabetes progression characteristic data; Based on the diabetes progression characteristic data, the formula: P′=a′1·D1+a′2·D2+a′3·D3; Calculate the condition score of the target patient; P′ represents the comprehensive score of the disease condition, D1 represents the standardized score of blood glucose value, D2 represents the standardized score of urine volume, D3 represents the standardized score of organ function, a′1 is the weight coefficient of blood glucose value, a′2 is the weight coefficient of urine volume, and a′3 is the weight coefficient of organ function; Based on the target patient's disease condition score and combined with the physician's opinion, the target diabetic patient's disease condition development stage is evaluated in real time to generate a diabetes stage classification result.

Images