CN119833121B - An automatic detection system for diabetes symptoms - Google Patents
An automatic detection system for diabetes symptomsInfo
- Publication number
- CN119833121B CN119833121B CN202510035455.5A CN202510035455A CN119833121B CN 119833121 B CN119833121 B CN 119833121B CN 202510035455 A CN202510035455 A CN 202510035455A CN 119833121 B CN119833121 B CN 119833121B
- Authority
- CN
- China
- Prior art keywords
- data
- patient
- blood glucose
- organ
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
本发明涉及生理测量技术领域，具体为一种糖尿病症状自动检测系统，系统包括：血糖波动分析模块、多饮多尿症状检测模块、衰退水平评估模块、进展阶段识别模块。本发明中，通过实时血糖监测和患者饮食状态的关联分析，精准捕捉血糖水平变化，预测病情的发展趋势，增强病情监控的实时性，使医疗干预更为及时有效，通过对患者饮水量和尿量的连续监测，及时发现糖尿病患者多饮多尿的症状，并通过数据分析确定目标症状与糖尿病进展的相关性，增强对早期糖尿病并发症的识别能力，结合对于器官功能水平的评估，识别器官受损的迹象，帮助调整治疗策略，预防并发症发展，提高了疾病监控的实时性和准确性，降低长期治疗的复杂性和成本。
The present invention relates to the field of physiological measurement technology, and specifically to an automatic detection system for diabetes symptoms. The system includes: a blood glucose fluctuation analysis module, a polydipsia and polyuria symptom detection module, a decline level assessment module, and a progression stage identification module. In the present invention, through real-time blood glucose monitoring and correlation analysis of the patient's dietary status, changes in blood glucose levels are accurately captured, the development trend of the disease is predicted, the real-time nature of disease monitoring is enhanced, and medical intervention is made more timely and effective. By continuously monitoring the patient's water intake and urine output, the symptoms of polydipsia and polyuria in diabetic patients are promptly discovered, and the correlation between the target symptoms and the progression of diabetes is 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 are identified, helping to adjust treatment strategies and prevent the development of complications. This improves the real-time nature and accuracy of disease monitoring and reduces the complexity and cost of long-term treatment.
Description
Technical Field
The invention relates to the technical field of physiological measurement, in particular to an automatic detection system for diabetes symptoms.
Background
The technical field of physiological measurement is focused on detecting, recording and explaining various physiological signals of a human body, is applied to monitoring heart activities, blood pressure, blood sugar, blood oxygen saturation, body temperature and various important physiological parameters, helps medical professionals to acquire health conditions of patients in real time by using sensors, wearable equipment and a non-invasive monitoring system, assists diagnosis and monitoring disease processes, monitors treatment effects and prevents development of chronic diseases, extracts various useful information from complex data by combining data processing and analysis technologies, and realizes long-term health management and acute pathology monitoring.
The automatic detection system for diabetes symptoms is focused on automatically monitoring and identifying various related symptoms of diabetes, and comprises the steps of tracking blood sugar level, body response and various physiological indexes indicating disease changes of a patient in real time, helping to know the blood sugar state of the patient in real time, realizing automatic data collection and analysis through an integrated sensing technology and an intelligent algorithm, timely providing key information for doctors and the patient, assisting medical decision, helping to manage diabetes and prevent complications, realizing early intervention, reducing health risks, and improving the treatment effect and life quality of the patient.
The traditional diabetes automatic detection system has steps in the aspects of diabetes management and prevention, focuses on single index monitoring or data provision at specific time points, lacks deep analysis of correlation between data and prediction capability of long-term trend, cannot analyze trend of blood sugar change and interaction with various physiological parameters including food and urine volume change, causes medical professionals to be unable to make optimal medical decision under the condition that comprehensive information cannot be obtained in real time, relies on regular medical examination in aspects of monitoring organ decline, delays diagnosis of early stage of organ damage, misses optimal treatment time, and has insufficient disease progression prevention measures.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides an automatic detection system for the symptoms of diabetes.
In order to achieve the above purpose, the invention adopts the following technical scheme that the diabetes symptom automatic detection system comprises:
the blood glucose fluctuation analysis module is used for analyzing the blood glucose fluctuation mode of a patient based on the real-time blood glucose monitoring data, analyzing the influence of nutrition intake on blood glucose fluctuation by combining the dietary state of the patient, predicting the blood glucose level development trend of the patient, and generating a blood glucose characteristic data set;
Based on the blood sugar characteristic data set, the polydipsia and diuresis symptom detection module evaluates the diuresis symptom level of the patient by collecting the water intake and urine volume data of the patient, calculates the correlation between the diuresis symptom characteristic and the diabetes progress stage according to the correlation between the urine level and the blood sugar characteristic, and outputs a diuresis symptom analysis result;
The decay level evaluation module acquires various physiological characteristic data of a target patient by utilizing the urine symptom analysis result, calculates the matching degree of the various physiological characteristic data by comparing the physiological characteristic data with the known organ decay pattern characteristic data, evaluates the organ decay level of the patient and generates organ decay monitoring information;
the progress stage identification module is used for identifying the development stage of the patient according to the blood sugar value, urine level and organ function level data of the patient based on the organ decline monitoring information and generating a diabetes stage classification result.
As a further aspect of the present invention, the step of obtaining the blood glucose excursion mode specifically includes:
based on real-time blood glucose monitoring data, the formula is used:
Calculating a blood glucose excursion degree score;
Wherein x i is the blood glucose value of the ith measurement, i represents the measurement index, N is the number of blood glucose measurements in a day, k is an adjustment coefficient for adjusting the sensitivity of the fluctuation score, σ represents the daily blood glucose fluctuation degree score;
and analyzing the daily blood sugar fluctuation degree of the target patient based on the blood sugar fluctuation degree score, and identifying a blood sugar fluctuation mode by combining the fluctuation period of the blood sugar data of the patient.
As a further aspect of the present invention, the step of obtaining the blood glucose feature data set specifically includes:
based on the blood sugar fluctuation mode, diet record information of a target patient is collected, blood sugar measured values and corresponding nutrition intake corresponding to multiple diet events are extracted, and the formula is adopted:
The coefficient of the effect of nutrient intake on blood glucose was calculated,
Wherein Δx j is the difference between postprandial blood glucose and the previous measurement, C j is the corresponding nutrient intake, α represents the extent of the effect of the nutrient intake level on the blood glucose change, X j represents the postprandial measured blood glucose value, j is the index for marking the eating event;
Analyzing the glycemic response at a plurality of nutritional intake levels based on the coefficient of the nutritional intake impact on blood glucose, assessing expected blood glucose fluctuations under a plurality of dietary conditions, and generating a sensitivity analysis result;
And predicting the blood glucose level development trend of the patient according to the dietary habit and the nutrition intake level of the patient according to the sensitivity analysis result, and generating a blood glucose characteristic data set.
As a further aspect of the present invention, the step of obtaining the level of the polyuria specifically includes:
based on the blood glucose characteristic data set, collecting drinking water and urination data of a patient, recording urination frequency and urination volume of the patient, and generating urine volume data of the patient;
Based on the patient urine volume data, the following formula:
calculating a severity score for the hallow condition;
Wherein U o is the urine volume of each urination, ul is the ratio of the actual urine volume to the ideal urine volume for quantifying the severity of the urination, ub is the basal urine volume, k a is the adjustment factor for age, k w is the adjustment factor for body weight, k s is the adjustment factor for sex, a is the actual age of the patient, w is the body weight of the patient, s is the sex of the patient, o is the index of urination events;
and classifying the target patient's severity score of the polyuria according to the severity score of the polyuria, thereby generating a level of the polyuria.
As a further aspect of the present invention, the step of obtaining the result of the polyuria analysis specifically includes:
Based on the polyuria-like level, by extracting daily urine volume data and blood glucose data of the target patient, the following formula is used:
calculating the correlation between the daily urine volume and the blood sugar data of the patient to obtain a correlation coefficient;
Wherein Y l represents the daily urine volume measured once, Mean value of daily urine volume data is represented, S l represents blood glucose value measured once,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 the diabetes mellitus progress stage is evaluated, and the polydipsia analysis result is output in combination with the severity of the polydipsia of the patient.
As a further aspect of the present invention, the step of obtaining the matching degree of the plurality of physiological characteristic data specifically includes:
Based on the analysis result of the polyuria, collecting various physiological parameter data of a target patient, including blood pressure, electrocardiogram and kidney function indexes, calculating variation trend and fluctuation mode of various parameters, including average variation rate and fluctuation index, and generating a data variation characteristic value;
Based on the data change characteristic value, the formula is as follows:
calculating the similarity between the measured physiological data and the characteristic data of the known organ decay mode to obtain a physiological characteristic similarity value;
Wherein S pq is the similarity index between the measured data and the standard mode, V p is the average change rate of the measured data, F p is the fluctuation index of the measured data, V q is the average change rate of the known standard data, F q is the fluctuation index of the known standard data, p represents the index of the measured data feature, and q represents the index of the known organ decline mode feature data;
And based on the physiological characteristic similarity values, summarizing similarity calculation results of the physiological parameter characteristic values to generate matching degrees of the physiological characteristic data.
As a further aspect of the present invention, the step of obtaining the organ deterioration monitoring information specifically includes:
based on the matching degree of the physiological characteristic data, assigning influence weights for the physiological parameters, reflecting the actual influence of the physiological parameters on the health state of the patient, and generating characteristic weight matching degree data;
Based on the feature weight matching degree data, the formula is as follows:
calculating the organ degradation degree of the patient to obtain organ degradation degree prediction data;
Wherein R represents the predicted organ decline degree, beta 0 is the intercept of a regression model, beta z is the regression coefficient of the Z-th physiological feature, Q z is the matching degree value of the Z-th physiological feature, Z represents the index of the specific physiological feature, and Z represents the total physiological feature quantity;
And based on the organ recession degree prediction data, evaluating the organ recession level of the target diabetes evaluation patient in real time, and generating organ recession monitoring information.
As a further aspect of the present invention, the step of obtaining the classification result of the diabetes stage specifically includes:
Based on the organ decline monitoring information, extracting blood glucose value, urine level and organ function level data of a patient, and generating diabetes progress feature data;
Based on the diabetes progression feature data, the following formula is used:
P′=a′1·D1+a′2·D2+a′3·D3;
calculating a condition score for the target patient;
P 'represents the comprehensive score of the illness, D 1 represents the normalized score of the blood sugar level, D 2 represents the normalized score of the urine volume, D 3 represents the normalized score of the organ function, a' 1 is the weight coefficient of the blood sugar level, a '2 is the weight coefficient of the urine volume, a' 3 is the weight coefficient of the organ function;
Based on the disease scores of the target patients, the disease development stages of the target diabetics are evaluated in real time by combining the doctor opinion, and a diabetes stage classification result is generated.
Compared with the prior art, the invention has the advantages and positive effects that:
According to the invention, through the real-time blood sugar monitoring and the associated analysis of the diet state of the patient, the change of the blood sugar 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, the symptoms of the diabetes patient, such as polydipsia and polyuria, are timely found through the continuous monitoring of the water intake and urine intake of the patient, the correlation between the target symptoms and the diabetes progress is determined through the data analysis, the identification capability of early diabetic complications is enhanced, the damaged signs of the organs are identified in combination with the assessment of the organ function level, the treatment strategy is helped to be adjusted, the complication development is prevented, the real-time performance and the accuracy of the illness monitoring are improved, and the complexity and the cost of long-term treatment are reduced.
Drawings
FIG. 1 is a system flow diagram of the present invention;
FIG. 2 is a flow chart of the analysis of blood glucose excursion pattern of the present invention;
FIG. 3 is a flow chart of the present invention for obtaining a blood glucose feature data set;
FIG. 4 is a flow chart of the calculated diuresis pattern level of the present invention;
FIG. 5 is a flow chart of the results of the analysis for producing a polyuria according to the present invention;
FIG. 6 is a flow chart of calculating the matching degree of various physiological characteristic data according to the present invention;
FIG. 7 is a flow chart of the method for obtaining organ deterioration monitoring information according to the present invention;
FIG. 8 is a flow chart of the invention for obtaining a classification result of a diabetes stage.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Referring to fig. 1, an automatic detection system for diabetes mellitus comprises:
the blood glucose fluctuation analysis module is used for analyzing the blood glucose fluctuation mode of a patient based on the real-time blood glucose monitoring data, analyzing the influence of nutrition intake on blood glucose fluctuation by combining the dietary state of the patient, predicting the blood glucose level development trend of the patient, and generating a blood glucose characteristic data set;
The polydipsia and polyuria detection module is used for estimating the polyuria level of a patient by collecting the water intake and urine volume data of the patient based on the blood sugar characteristic data set, calculating the correlation between the polyuria characteristic and the diabetes progression stage according to the correlation between the urine level and the blood sugar characteristic, and outputting a polyuria analysis result;
The decay level evaluation module acquires various physiological characteristic data of a target patient by utilizing a polyuria analysis result, calculates the matching degree of the various physiological characteristic data by comparing the physiological characteristic data with the known organ decay pattern characteristic data, evaluates the organ decay level of the patient and generates organ decay monitoring information;
The progress stage identification module identifies the development stage of the patient disease based on the organ decline monitoring information according to the blood sugar value, urine level and organ function level data of the patient, and generates a diabetes stage classification result.
The blood sugar characteristic data set is specifically a blood sugar peak-valley value, a blood sugar fluctuation period and a nutrition intake influence analysis result, the urination symptom analysis result is specifically a urination symptom level, a diabetes progression stage correlation index, water intake and urine volume data of a patient, the organ decline monitoring information is specifically an organ decline level calculation result, a data characteristic matching degree and a patient physiological characteristic data set, and the diabetes stage classification result is specifically a disease progression classification, a patient disease risk score and patient disease development trend information.
Referring to fig. 2, the steps for obtaining the blood glucose excursion mode specifically include:
based on real-time blood glucose monitoring data, the formula is used:
Calculating a blood glucose excursion degree score;
Wherein x i is the blood glucose value of the ith measurement, i represents the measurement index, N is the number of blood glucose measurements in a day, k is an adjustment coefficient for adjusting the sensitivity of the fluctuation score, σ represents the daily blood glucose fluctuation degree score;
the formula:
parameter meaning and acquisition mode:
x i, the blood glucose value measured at the ith time is obtained in real time through blood glucose monitoring equipment;
The number of times of blood glucose measurement in one day is obtained through daily record setting of blood glucose monitoring equipment;
The adjustment coefficient is used for adjusting the sensitivity of the fluctuation score;
sigma, represents daily blood glucose excursion degree score;
calculation example:
A total of 5 blood glucose measurements were set, i.e., n=5, and the measured values x i were 100, 105, 98, 103, 110, respectively, the adjustment coefficient k was 1.5, and the degree of blood glucose fluctuation was calculated:
σ=1.5×4.66;
σ=6.99;
the calculated result σ=6.99 indicates that the patient's blood glucose excursion score is 6.99 for that day, the value providing an assessment of increased sensitivity to blood glucose excursion for understanding the volatility of the patient's blood glucose control.
Based on the blood sugar fluctuation degree score, analyzing the blood sugar fluctuation degree of a target patient every day, and identifying a blood sugar fluctuation mode by combining the fluctuation period of blood sugar data of the patient;
The method comprises the steps of collecting blood glucose monitoring data of a target patient within a certain period, analyzing the data by using a time sequence analysis method, determining the fluctuation frequency and amplitude of blood glucose, identifying the main modes of blood glucose fluctuation, such as periodic peaks and valleys, performing frequency domain conversion on the time sequence data by using a Fourier transform analysis method through a mathematical modeling technology, extracting the periodic characteristics of the blood glucose data, analyzing the fluctuation rules which help medical providers to understand the illness state deeply, providing a basis for adjusting a treatment plan, and generating an exhaustive blood glucose fluctuation report for optimizing a disease management strategy and improving the treatment response of the patient.
Referring to fig. 3, the steps for obtaining the blood glucose feature data set specifically include:
based on the blood sugar fluctuation mode, diet record information of a target patient is acquired, blood sugar measurement values and corresponding nutrition intake corresponding to multiple diet events are extracted, and the formula is adopted:
The coefficient of the effect of nutrient intake on blood glucose was calculated,
Wherein Δx j is the difference between postprandial blood glucose and the previous measurement, C j is the corresponding nutrient intake, α represents the extent of the effect of the nutrient intake level on the blood glucose change, X j represents the postprandial measured blood glucose value, j is the index for marking the eating event;
the formula:
parameter meaning and acquisition mode:
c j carbohydrate intake for the j-th dietary event, obtained from a food intake and nutrition database recorded in the diet journal;
X j, obtaining the blood glucose value which is measured after the jth eating event through blood glucose monitoring equipment;
DeltaX j is the change in blood glucose between the last and last measurement of the jth diet;
alpha is a coefficient of the effect of nutrient intake on blood glucose for assessing the average effect of diet on blood glucose changes;
calculation example:
Let C j be 50, 60, 40, Δx j be 20, 15, 10, calculate the influence coefficient:
calculate Σ (C j×ΔXj):
Σ (C j×ΔXj) =50×20+60× 15+40×10=1000+900+400=2300; calculation of
And (3) calculating alpha:
α= 0.2987 indicates an average induced glycemic change per unit carbohydrate of 0.2987, a value reflecting the average intensity of the food effect on blood glucose, and a coefficient used to evaluate the effect of dietary adjustments on glycemic control.
Analyzing the glycemic response at a plurality of nutritional intake levels based on the factors of the nutritional intake impact on blood glucose, assessing expected blood glucose fluctuations under a plurality of dietary conditions, and generating a sensitivity analysis result;
The method comprises the steps of analyzing past diet records and corresponding blood glucose response data of a patient, quantitatively evaluating the relationship between food intake and blood glucose response by using a regression analysis technology, determining blood glucose influence coefficients of foods of all types in the analysis, calculating correlation coefficients between nutrients and blood glucose changes, displaying influences of food components on blood glucose control by a sensitivity analysis result, constructing a diet blood glucose response model by dynamically simulating blood glucose responses under different diet situations, providing personalized diet suggestions for the patient, guiding the patient to adjust daily diet, and optimizing a blood glucose control strategy.
According to the sensitivity analysis result, predicting the blood glucose level development trend of the patient according to the dietary habit and the nutrition intake level of the patient, and generating a blood glucose characteristic data set;
The linear regression model in the machine learning technology is applied to predict future blood glucose level trend of the patient, historical diet and blood glucose data of the patient are collected and tidied, the prediction model is trained by utilizing the data, the model can accurately reflect the blood glucose change rule of the patient, the generated blood glucose characteristic data set is adjusted and optimized through an algorithm, a scientific basis is provided for medical decision, and the accuracy of diabetes management and the life quality of the patient are improved.
Referring to fig. 4, the steps for acquiring the level of the polyuria specifically include:
based on the blood sugar characteristic data set, collecting drinking water and urination data of a patient, recording urination frequency and urination volume of the patient, and generating urine volume data of the patient;
Setting an automatic acquisition system to record the water intake and subsequent urination volume of a patient once per hour, recording detailed water intake and urine output data by using a sensor and a mobile application, performing quality inspection on the acquired data, eliminating any abnormal value such as abnormally high urine volume or unrecorded drinking water event, calculating the total daily urine volume and fluctuation of the urine volume by using statistical software, evaluating the daily and daytime urine volume changes, generating detailed urine volume data of the patient, converting the data into a trend chart and a periodic chart which are easy to read after the data are processed by an algorithm, and assisting medical professionals to monitor and evaluate the water metabolism health and diabetes condition changes of the patient.
Based on patient urine volume data, the following formula:
calculating a severity score for the hallow condition;
Wherein U o is the urine volume of each urination, ul is the ratio of the actual urine volume to the ideal urine volume for quantifying the severity of the urination, ub is the basal urine volume, k a is the adjustment factor for age, k w is the adjustment factor for body weight, k s is the adjustment factor for sex, a is the actual age of the patient, w is the body weight of the patient, s is the sex of the patient, o is the index of urination events;
the formula:
Parameter meaning and acquisition mode
U o, urine volume of each urination of a patient is obtained by urine volume measuring equipment of a hospital;
ub, basal urine volume, average urine volume standard representing healthy adults, determined based on medical studies;
k a an age adjustment factor, determined from clinical studies, for adjusting urine volume based on age of the patient;
k w a weight adjustment coefficient, which is determined according to clinical studies, for adjusting urine volume according to the weight of the patient;
k s, sex adjustment coefficient, obtained based on research of sex difference;
a, acquiring the actual age of a patient from a medical record of the patient;
the actual weight of the patient is obtained from the medical records of the patient;
s, the sex of the patient, and acquiring from the medical records of the patient;
Computing examples
The actual urine volume per time U o data for the target patient was set to [500,550,520,540]mL,Ub＝1500mL/day,ka＝0.5mL/day/year,kw＝1mL/day/kg,ks＝100mL/day,a＝55years,w＝70kg,s＝1, to calculate symptom severity:
the result ul=1.243 indicates that the actual urine volume is 124.3% of the ideal urine volume, indicating that the patient is in a significant hyperuricemia state, a value that is used to assist the physician in assessing the condition and adjusting the treatment strategy.
Classifying the target patient's severity score of the polyuria to produce a level of the polyuria;
Comparing the urine volume data of the patient with the clinical symptom records, quantifying the severity of each symptom by adopting a standardized scoring table, determining the contribution degree of each symptom to the total score by utilizing a statistical analysis tool such as factor analysis, objectively classifying the urination of the patient, generating a urination grade report for each patient according to the scoring result and related medical guidelines, wherein the report lists the concrete manifestation and the recommended medical response of the urination of the patient, and providing basis for formulating a targeted treatment plan.
Referring to fig. 5, the steps for obtaining the analysis result of the polyuria specifically include:
based on the polyuria-like level, by extracting daily urine volume data and blood glucose data of the target patient, the following formula is used:
calculating the correlation between the daily urine volume and the blood sugar data of the patient to obtain a correlation coefficient;
Wherein Y l represents the daily urine volume measured once, Mean value of daily urine volume data is represented, S l represents blood glucose value measured once,Representing the average value of blood glucose data, r representing a correlation coefficient for measuring the strength of a linear correlation between daily urine volume Y and blood glucose S, l representing an index of data points;
the formula:
parameter meaning and acquisition mode:
y l specific measurement of daily urine volume;
Average daily urine volume;
s l specific measured values of blood glucose;
an average of blood glucose data;
The correlation coefficient is used for measuring the linear correlation strength between the daily urine quantity Y and the blood sugar S;
Computing examples
Setting daily urine volume data of the target patient to be [500,600,550,580,610], Blood glucose data is [5.0,5.5,5.3,5.2,5.6], Calculating a correlation coefficient:
r≈0.901;
The calculation result r=0.901 shows that there is a positive correlation between urine volume and blood glucose, and it is explained that as blood glucose increases, urine volume increases, and the numerical value reflects the close correlation between the polyuria and the stage of diabetes progression.
Based on the correlation coefficient, evaluating the correlation between the polydipsia and diuresis symptom level and the diabetes progression stage, and outputting a polydipsia analysis result by combining the severity of the polydipsia and diuresis symptom of the patient;
The method comprises the steps of adopting multivariate regression analysis to evaluate the correlation between the polydipsia and the diabetes mellitus progress stage, integrating urine volume data and blood sugar monitoring results of a patient, adopting a statistical model to analyze target data, identifying potential correlation modes, and outputting detailed polydipsia analysis results by judging the interaction between urine volume change and blood sugar abnormality, thereby providing important insight about the disease progress of the patient, supporting clinical decision, and helping doctors to adjust treatment schemes for the patient, including aspects of diabetes management and complications prevention.
Referring to fig. 6, the steps for obtaining the matching degree of the multiple physiological characteristic data specifically include:
Based on the analysis result of the polyuria, collecting various physiological parameter data of a target patient, including blood pressure, electrocardiogram and kidney function indexes, calculating the variation trend and fluctuation mode of various parameters, including average variation rate and fluctuation index, and generating a data variation characteristic value;
The method comprises the steps of comprehensively collecting various physiological parameters of a target patient, covering data collected by a sphygmomanometer, an electrocardiograph and kidney function testing equipment, calibrating each equipment, ensuring data accuracy, systematically recording daily blood pressure, electrocardiogram and kidney function indexes of the patient, evaluating the variation trend and fluctuation of each physiological parameter by adopting a sliding window average method and a standard deviation calculation method through data analysis software, identifying key health variation signals, and calculating data variation characteristic values comprising average variation rate and fluctuation index, wherein the characteristic values are used as important basis for evaluating the health state and illness state variation of the patient.
Based on the data change characteristic value, the method comprises the following steps of:
calculating the similarity between the measured physiological data and the characteristic data of the known organ decay mode to obtain a physiological characteristic similarity value;
Wherein S pq is the similarity index between the measured data and the standard mode, V p is the average change rate of the measured data, F p is the fluctuation index of the measured data, V q is the average change rate of the known standard data, F q is the fluctuation index of the known standard data, p represents the index of the characteristics of the measured data, including blood pressure, electrocardiogram and renal function level, and q represents the index of the characteristic data of the known organ recession mode;
the formula:
parameter meaning and acquisition mode:
v p, the average change rate of the measured physiological data;
F p, measuring fluctuation index of physiological data;
v q average rate of change of known organ failure mode data;
F q fluctuation index of known organ failure mode data:
calculation example:
The measured physiological data point is set as [100,105,95,110,90], the known organ recession pattern data point is set as [95,100,105,95,100], and V p＝-2.5,Vq＝1.25,Fp＝7.35,Fq =3.74, and the similarity is calculated:
the calculation result shows that the similarity of the measured value and the characteristic data of the known organ decay pattern is 0.795, the numerical value reflects the higher similarity between the measured data and the known decay pattern, and the calculation process is used for evaluating the matching degree of various physiological characteristics and pathological models.
Based on the physiological characteristic similarity values, the similarity calculation results of the physiological parameter characteristic values are summarized to generate the matching degree of the physiological characteristic data;
The method comprises the steps of performing similarity calculation on characteristic values of physiological parameters by using a multivariate data analysis technology, such as principal component analysis and cluster analysis, standardizing the physiological parameters to eliminate dimension influence, extracting main variation trend and mode by using PCA, further determining similarity among the parameters by using the cluster analysis, revealing the relevance among different physiological parameters in the calculation process, providing scientific basis for comprehensively judging the health state of a patient, summarizing similarity calculation results, generating comprehensive multiple physiological characteristic data matching degree, and providing accurate health assessment and disease monitoring tools for medical professionals.
Referring to fig. 7, the steps for obtaining the organ degradation monitoring information specifically include:
Based on the matching degree of the physiological characteristic data, influence weights are distributed for the physiological parameters, the actual influence of the physiological parameters on the health state of the patient is reflected, and characteristic weight matching degree data are generated;
A weight distribution model, such as weighted linear regression analysis, is adopted to distribute corresponding influence weights for different physiological parameters, such as blood pressure, electrocardio and kidney function indexes, a baseline influence model of each parameter on the health condition of a patient is established through historical data, the weights of the parameters are adjusted according to the current matching data, the actual influence of the parameters in the current health state evaluation is reflected, the characteristic weight of each physiological parameter is calculated, comprehensive characteristic weight matching degree data is generated by summarizing the weights, the data helps medical professionals to understand the importance of each physiological index on the influence of the illness state, and the treatment and monitoring strategies are optimized.
Based on the feature weight matching degree data, the formula is as follows:
calculating the organ degradation degree of the patient to obtain organ degradation degree prediction data;
Wherein R represents the predicted organ decline degree, beta 0 is the intercept of a regression model, beta z is the regression coefficient of the Z-th physiological feature, Q z is the matching degree value of the Z-th physiological feature, Z represents the index of the specific physiological feature, and Z represents the total physiological feature quantity;
the formula:
parameter meaning and acquisition mode:
predicted organ recession;
Beta 0 the intercept of the regression model, obtained by analyzing historical health data, represents the level of basal decay in the absence of any physiological parameter effects;
Beta z, the regression coefficient of the z-th physiological parameter reflects the influence weight of the physiological parameter on the fading degree;
q z, the matching degree value of the z-th physiological parameter is obtained from the physiological characteristic matching degree data and is used for inputting linear regression analysis;
z, physiological parameter index;
z is the total physiological parameter number;
calculation example:
setting Q1＝0.8,Q2＝0.6,Q3＝0.9,β0＝0.5,β1＝0.3,β2＝0.2,β3＝0.4,Z＝3, calculates organ decline:
R=0.5+(0.3·0.8+0.2·0.6+0.4·0.9);
R=0.5+(0.24+0.12+0.36);
R=0.5+0.72;
R=1.22;
The calculation result shows that the predicted organ degradation degree is 1.22, the numerical value reflects the comprehensive degradation state based on the matching degree of the given physiological parameters, and the formula is used for evaluating the organ degradation level of the patient and helping doctors to make diagnosis and treatment decisions.
Based on the organ recession degree prediction data, estimating the organ recession level of a target diabetes estimated patient in real time, and generating organ recession monitoring information;
By using a dynamic model, such as a dynamic system model, and combining the latest physiological parameter data and historical decline trend of a patient, real-time data analysis and prediction are carried out, decline rate and decline degree of organ functions are calculated and updated in real time through the model, detailed organ decline monitoring information is generated, the information provides real-time clinical data for doctors, more accurate treatment decisions are supported to be made, and meanwhile important information about the disease progress of the patients is provided for the patients, so that the adjustment of personal health management plans and the prevention of potential complications are facilitated.
Referring to fig. 8, the steps for obtaining the classification result of the diabetes stage specifically include:
based on the organ decline monitoring information, extracting blood glucose value, urine level and organ function level data of the patient, and generating diabetes progress feature data;
The key physiological indexes including blood sugar level, urine level and organ function level data of a patient are extracted by adopting a data extraction technology, collected blood sugar and urine level monitoring results are integrated through an automatic data processing system, latest organ function detection reports of the patient are synchronized, the change trend of various indexes on time sequence is estimated by data integration analysis, the fluctuation mode of blood sugar and urine level and the correlation thereof with organ function decline are determined by using a time sequence analysis technology such as a moving average or an index smoothing technology, diabetes progress characteristic data is generated in the process, and accurate basic information is provided for subsequent disease analysis and stage classification.
Based on the diabetes progression feature data, the following formula is adopted:
P′=a′1·D1+a′2·D2+a′3·D3;
calculating a condition score for the target patient;
P 'represents the comprehensive score of the illness, D 1 represents the normalized score of the blood sugar level, D 2 represents the normalized score of the urine volume, D 3 represents the normalized score of the organ function, a' 1 is the weight coefficient of the blood sugar level, a '2 is the weight coefficient of the urine volume, a' 3 is the weight coefficient of the organ function;
the formula:
P′=a′1·D1+a′2·D2+a′3·D3;
parameter meaning and acquisition mode:
P' represents a composite score for the condition;
D 1 represents a normalized score of the blood glucose level, and is obtained by performing normalized processing on blood glucose data obtained by actual medical detection;
D 2 represents the standardized fraction of the urine volume, and is obtained by performing standardized processing on urine volume data obtained through actual medical detection;
D 3 represents the standardized score of organ functions, and the standardized score is obtained by performing standardized processing on organ function test data obtained through actual medical detection;
a' 1 is a weight coefficient of the blood glucose value, and is obtained by analyzing historical health data and reflects the influence of the blood glucose value in disease assessment;
a' 2 is a weight coefficient of urine volume, obtained by analyzing historical health data, reflecting the influence of urine volume in disease assessment;
a' 3 is a weight coefficient of organ function, obtained by analyzing historical health data, reflecting influence of organ function in disease assessment;
calculation example:
Set D 1＝0.85,D2＝0.75,D3＝0.65,a′1＝0.4,a′2＝0.3,a′3 = 0.3, calculate the disease complex score:
P′=0.4·0.85+0.3·0.75+0.3·0.65;
P′=0.34+0.225+0.195;
P′=0.76;
The calculated result shows that the comprehensive disease score of the target patient is 0.76, the numerical value reflects the disease development stage evaluation score obtained after the comprehensive blood sugar value, urine volume and organ function, and the numerical value is used for helping doctors to determine the disease stage of the diabetes patient and providing basis for making a treatment plan.
Based on the disease score of the target patient, combining the doctor opinion, evaluating the disease development stage of the target diabetes patient in real time, and generating a diabetes stage classification result;
The blood sugar control condition, urine volume change and organ function index of the patient are comprehensively evaluated by integrating scores and comments provided by doctors and adopting a decision support system and combining logistic regression analysis, the disease development stage of the diabetes patient is evaluated in real time, the correlation of various physiological data and diabetes development and the influence on the disease stage are considered by model calculation, the output diabetes stage classification result provides clear information about the current disease stage for the doctors and the patient, and personalized treatment decisions and disease management strategies are supported.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (3)
1. An automated diabetes condition detection system, the system comprising:
the blood glucose fluctuation analysis module is used for analyzing the blood glucose fluctuation mode of a patient based on the real-time blood glucose monitoring data, analyzing the influence of nutrition intake on blood glucose fluctuation by combining the dietary state of the patient, predicting the blood glucose level development trend of the patient, and generating a blood glucose characteristic data set;
Based on the blood sugar characteristic data set, the polydipsia and diuresis symptom detection module evaluates the diuresis symptom level of the patient by collecting the water intake and urine volume data of the patient, calculates the correlation between the diuresis symptom characteristic and the diabetes progress stage according to the correlation between the urine level and the blood sugar characteristic, and outputs a diuresis symptom analysis result;
The decay level evaluation module acquires various physiological characteristic data of a target patient by utilizing the urine symptom analysis result, calculates the matching degree of the various physiological characteristic data by comparing the physiological characteristic data with the known organ decay pattern characteristic data, evaluates the organ decay level of the patient and generates organ decay monitoring information;
The progress stage identification module is used for identifying the development stage of the patient according to the blood sugar value, urine level and organ function level data of the patient based on the organ decline monitoring information and generating a diabetes stage classification result;
the blood glucose characteristic data set is obtained by the following steps:
based on the blood sugar fluctuation mode, diet record information of a target patient is collected, blood sugar measured values and corresponding nutrition intake corresponding to multiple diet events are extracted, and the formula is adopted:
;
The coefficient of the effect of nutrient intake on blood glucose was calculated,
Wherein, the Is the difference between blood glucose after eating and the previous measurement,Is the corresponding nutrient intake quantity, and the nutrient intake quantity,Indicating the extent to which the level of nutritional intake affects the change in blood glucose,The blood glucose value measured after the diet is indicated,Is an index for marking dietary events;
Analyzing the glycemic response at a plurality of nutritional intake levels based on the coefficient of the nutritional intake impact on blood glucose, assessing expected blood glucose fluctuations under a plurality of dietary conditions, and generating a sensitivity analysis result;
according to the sensitivity analysis result, predicting the blood glucose level development trend of the patient according to the dietary habit and the nutrition intake level of the patient, and generating a blood glucose characteristic data set;
The step of obtaining the level of the polyuria specifically comprises the following steps:
based on the blood glucose characteristic data set, collecting drinking water and urination data of a patient, recording urination frequency and urination volume of the patient, and generating urine volume data of the patient;
Based on the patient urine volume data, the following formula:
;
calculating a severity score for the hallow condition;
Wherein, the For the urine volume of each urination,To quantify the severity of the polyuria, the ratio of actual urine volume to ideal urine volume,As a basis for the amount of urine,As the adjustment coefficient for the age of the patient,Is used for adjusting the coefficient of the weight,Is an adjustment coefficient for the sex of the person,For the actual age of the patient,For the weight of the patient,For the sex of the patient,Is an index of urination events;
Classifying the target patient's severity score according to the severity score of the polyuria, generating a level of the polyuria;
the step of obtaining the result of the polyuria analysis specifically comprises the following steps:
Based on the polyuria-like level, by extracting daily urine volume data and blood glucose data of the target patient, the following formula is used:
;
calculating the correlation between the daily urine volume and the blood sugar data of the patient to obtain a correlation coefficient;
Wherein, the Represents the daily urine volume measured a single time,Mean values of daily urine volume data are shown,Indicating the blood glucose level of a single measurement,The average value of the blood glucose data is represented,The correlation coefficient is represented by a correlation coefficient,An index representing data points;
Based on the correlation coefficient, evaluating the correlation between the polydipsia and diuresis symptom level and the diabetes progression stage, and outputting a polydipsia analysis result by combining the severity of the polydipsia and diuresis symptom of the patient;
The step of obtaining the matching degree of the physiological characteristic data comprises the following steps:
Based on the analysis result of the polyuria, collecting various physiological parameter data of a target patient, including blood pressure, electrocardiogram and kidney function indexes, calculating variation trend and fluctuation mode of various parameters, including average variation rate and fluctuation index, and generating a data variation characteristic value;
Based on the data change characteristic value, the formula is as follows:
;
calculating the similarity between the measured physiological data and the characteristic data of the known organ decay mode to obtain a physiological characteristic similarity value;
Wherein, the For the similarity index between the measured data and the standard pattern,For the average rate of change of the measured data,For the fluctuation index of the measured data,As the average rate of change of the known standard data,As the fluctuation index of the known standard data,An index representing a characteristic of the measured data,An index representing characteristic data of a known organ failure mode;
Based on the physiological characteristic similarity values, generating matching degrees of various physiological characteristic data by summarizing similarity calculation results of various physiological parameter characteristic values;
The organ decline monitoring information is obtained by the following steps:
based on the matching degree of the physiological characteristic data, assigning influence weights for the physiological parameters, reflecting the actual influence of the physiological parameters on the health state of the patient, and generating characteristic weight matching degree data;
Based on the feature weight matching degree data, the formula is as follows:
;
calculating the organ degradation degree of the patient to obtain organ degradation degree prediction data;
Wherein, the Representing a predicted degree of organ deterioration,Is the intercept of the regression model,Is the regression coefficient of the z-th physiological feature,Is the matching degree value of the z-th physiological characteristic,An index representing a particular physiological characteristic,Representing the total physiological characteristic quantity;
And based on the organ recession degree prediction data, evaluating the organ recession level of the target diabetes evaluation patient in real time, and generating organ recession monitoring information.
2. The automatic detection system for diabetic condition according to claim 1, wherein the step of acquiring the pattern of blood glucose fluctuations specifically comprises:
based on real-time blood glucose monitoring data, the formula is used:
;
Calculating a blood glucose excursion degree score;
Wherein, the Is the firstThe blood glucose value of the secondary measurement is,Representing the index of the measurement,Is the number of blood glucose measurements in a day,Is an adjustment factor that adjusts the sensitivity of the fluctuation score,A score representing the degree of daily blood glucose excursions;
and analyzing the daily blood sugar fluctuation degree of the target patient based on the blood sugar fluctuation degree score, and identifying a blood sugar fluctuation mode by combining the fluctuation period of the blood sugar data of the patient.
3. The automatic detection system for diabetic condition according to claim 1, wherein the step of obtaining the classification result of the stage of diabetes is specifically:
Based on the organ decline monitoring information, extracting blood glucose value, urine level and organ function level data of a patient, and generating diabetes progress feature data;
Based on the diabetes progression feature data, the following formula is used:
;
calculating a condition score for the target patient;
indicating the comprehensive score of the condition of the patient, Represents a normalized score of the blood glucose level,A normalized score representing the urine volume is presented,A normalized score representing the function of the organ,Is the weight coefficient of the blood sugar level,Is a weight coefficient of the urine volume,Is a weight coefficient of organ function;
Based on the disease scores of the target patients, the disease development stages of the target diabetics are evaluated in real time by combining the doctor opinion, and a diabetes stage classification result is generated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510035455.5A CN119833121B (en) | 2025-01-09 | 2025-01-09 | An automatic detection system for diabetes symptoms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510035455.5A CN119833121B (en) | 2025-01-09 | 2025-01-09 | An automatic detection system for diabetes symptoms |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119833121A CN119833121A (en) | 2025-04-15 |
| CN119833121B true CN119833121B (en) | 2025-10-24 |
Family
ID=95293876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510035455.5A Active CN119833121B (en) | 2025-01-09 | 2025-01-09 | An automatic detection system for diabetes symptoms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119833121B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120299743B (en) * | 2025-06-13 | 2025-10-21 | 中国人民解放军空军军医大学 | System and method for analyzing the effects of diabetes cognitive impairment based on brain functional imaging |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111683591A (en) * | 2018-02-22 | 2020-09-18 | 京瓷株式会社 | Electronic equipment, estimation system, estimation method and estimation procedure |
| CN117116482A (en) * | 2023-08-09 | 2023-11-24 | 北京雪扬科技有限公司 | Blood sugar disease risk analysis system based on multidimensional blood sugar trend analysis and early warning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5956501A (en) * | 1997-01-10 | 1999-09-21 | Health Hero Network, Inc. | Disease simulation system and method |
| GB0309154D0 (en) * | 2003-01-14 | 2003-05-28 | Aventis Pharma Inc | Use of insulin glargine to reduce or prevent cardiovascular events in patients being treated for dysglycemia |
| US20210319887A1 (en) * | 2015-05-20 | 2021-10-14 | Amuseneering Technologies, Llc | Method of treating diabetes informed by social determinants of health |
| KR20220124942A (en) * | 2021-03-04 | 2022-09-14 | 주식회사 유투메드텍 | Real-time health monitoring system using continuous blood glucose meter |
-
2025
- 2025-01-09 CN CN202510035455.5A patent/CN119833121B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111683591A (en) * | 2018-02-22 | 2020-09-18 | 京瓷株式会社 | Electronic equipment, estimation system, estimation method and estimation procedure |
| CN117116482A (en) * | 2023-08-09 | 2023-11-24 | 北京雪扬科技有限公司 | Blood sugar disease risk analysis system based on multidimensional blood sugar trend analysis and early warning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119833121A (en) | 2025-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118737447A (en) | Diabetes risk assessment system | |
| CN118173253B (en) | System and method for analyzing and managing based on patient data | |
| CN114943629A (en) | A health management health care service system and its health management method | |
| WO2022099668A1 (en) | Method and system for precise health management and risk early warning based on association between familial genetic disease and sign data | |
| CN119626556A (en) | A health status assessment system for disease follow-up | |
| CN119943398B (en) | Diabetes Management System Based on Big Data | |
| CN118526198A (en) | Pregnancy mental health remote monitoring method and system | |
| CN119833121B (en) | An automatic detection system for diabetes symptoms | |
| CN120048428B (en) | Nursing plan selection assistance system for orthopedic patients | |
| CN118824541A (en) | A health warning method based on meteorological environment and vital signs monitoring | |
| CN118800473A (en) | A model construction method for predicting postoperative complications in patients with gastrointestinal tumors | |
| CN119541875A (en) | A method and system for predicting sepsis deterioration based on TCM big data | |
| CN119446507A (en) | A patient pain prediction method and device based on wearable device | |
| CN119541840A (en) | Intelligent remote follow-up method and system for tumor patients | |
| CN119480083A (en) | A health monitoring system based on wearable devices | |
| CN117174291A (en) | A method and system for predicting the risk of diabetes in pre-diabetic people | |
| CN116705316A (en) | Method, medium and system for evaluating risk index of atherosclerosis | |
| CN120148861B (en) | Construction method for predicting risk model of hyperglycemia-related ovarian cancer | |
| CN119905265A (en) | A health examination data management method and system | |
| CN120674064A (en) | Construction method of glucocorticoid-induced diabetes risk prediction model based on LASSO algorithm | |
| CN119964841A (en) | A risk detection method and system for adverse events in drug clinical trials | |
| CN119423704A (en) | A multi-parameter fusion blood sugar prediction method and system | |
| CN120015301A (en) | AI-based chronic disease risk prediction and early intervention methods | |
| CN120236772B (en) | Method and system for evaluating nutritional symptoms of tumor chemoradiotherapy patients based on multidimensional data | |
| CN120766925A (en) | Comprehensive diagnostic system for diabetic nephropathy based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |