CN117153416B - Diabetes screening data processing and management system - Google Patents
Diabetes screening data processing and management system Download PDFInfo
- Publication number
- CN117153416B CN117153416B CN202311393990.5A CN202311393990A CN117153416B CN 117153416 B CN117153416 B CN 117153416B CN 202311393990 A CN202311393990 A CN 202311393990A CN 117153416 B CN117153416 B CN 117153416B
- Authority
- CN
- China
- Prior art keywords
- blood sugar
- data
- patient
- diabetes
- value
- 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
- 206010012601 diabetes mellitus Diseases 0.000 title claims abstract description 122
- 238000012216 screening Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 title claims abstract description 11
- 239000008280 blood Substances 0.000 claims abstract description 237
- 210000004369 blood Anatomy 0.000 claims abstract description 236
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims abstract description 63
- 239000008103 glucose Substances 0.000 claims abstract description 63
- 230000002159 abnormal effect Effects 0.000 claims abstract description 32
- 230000002641 glycemic effect Effects 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims description 47
- 235000012054 meals Nutrition 0.000 claims description 43
- 230000008569 process Effects 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 15
- 208000001072 type 2 diabetes mellitus Diseases 0.000 claims description 13
- 206010067584 Type 1 diabetes mellitus Diseases 0.000 claims description 12
- 230000000087 stabilizing effect Effects 0.000 claims description 9
- 230000037406 food intake Effects 0.000 claims description 7
- 235000012631 food intake Nutrition 0.000 claims description 7
- 238000007726 management method Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000013523 data management Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 5
- 230000001019 normoglycemic effect Effects 0.000 claims description 5
- 238000003745 diagnosis Methods 0.000 claims description 4
- 230000037396 body weight Effects 0.000 claims description 3
- 230000002688 persistence Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 230000036541 health Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 8
- 230000005856 abnormality Effects 0.000 description 6
- 235000013305 food Nutrition 0.000 description 6
- 201000001421 hyperglycemia Diseases 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- NOESYZHRGYRDHS-UHFFFAOYSA-N insulin Chemical compound N1C(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(NC(=O)CN)C(C)CC)CSSCC(C(NC(CO)C(=O)NC(CC(C)C)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CCC(N)=O)C(=O)NC(CC(C)C)C(=O)NC(CCC(O)=O)C(=O)NC(CC(N)=O)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CSSCC(NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2C=CC(O)=CC=2)NC(=O)C(CC(C)C)NC(=O)C(C)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2NC=NC=2)NC(=O)C(CO)NC(=O)CNC2=O)C(=O)NCC(=O)NC(CCC(O)=O)C(=O)NC(CCCNC(N)=N)C(=O)NCC(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC(O)=CC=3)C(=O)NC(C(C)O)C(=O)N3C(CCC3)C(=O)NC(CCCCN)C(=O)NC(C)C(O)=O)C(=O)NC(CC(N)=O)C(O)=O)=O)NC(=O)C(C(C)CC)NC(=O)C(CO)NC(=O)C(C(C)O)NC(=O)C1CSSCC2NC(=O)C(CC(C)C)NC(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CC(N)=O)NC(=O)C(NC(=O)C(N)CC=1C=CC=CC=1)C(C)C)CC1=CN=CN1 NOESYZHRGYRDHS-UHFFFAOYSA-N 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000002218 hypoglycaemic effect Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 208000024891 symptom Diseases 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000013016 Hypoglycemia Diseases 0.000 description 2
- 102000004877 Insulin Human genes 0.000 description 2
- 108090001061 Insulin Proteins 0.000 description 2
- 210000000227 basophil cell of anterior lobe of hypophysis Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000021152 breakfast Nutrition 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 210000000750 endocrine system Anatomy 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 229940125396 insulin Drugs 0.000 description 2
- 230000007170 pathology Effects 0.000 description 2
- 230000000291 postprandial effect Effects 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 206010022489 Insulin Resistance Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 150000001720 carbohydrates Chemical class 0.000 description 1
- 235000014633 carbohydrates Nutrition 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 208000004104 gestational diabetes Diseases 0.000 description 1
- 229940088597 hormone Drugs 0.000 description 1
- 239000005556 hormone Substances 0.000 description 1
- 230000003345 hyperglycaemic effect Effects 0.000 description 1
- 210000000987 immune system Anatomy 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000028327 secretion Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the technical field of medical health care informatics, and provides a diabetes screening data processing and management system, which comprises: acquiring relevant data of a diabetic patient; marking the data segments according to heart rate variation, and classifying the data by using the marked data segments; calculating a blood glucose regulation characteristic value according to the glycemic index and the area under the blood glucose curve; calculating the blood sugar consumption coefficient of the organism according to the heart rate variation and the blood sugar reserve amount; calculating the blood sugar consumption residual quantity of the organism according to the blood sugar consumption coefficient and the blood sugar storage quantity of the organism; calculating abnormal blood sugar deviation value according to the blood sugar consumption residual quantity of the organism and the area under the blood sugar curve; and classifying results of the patient-related data according to the abnormal blood sugar deviation value, the blood sugar regulation characteristic value, the weight characteristic value, the age characteristic value and the medical history marking value. The invention judges the type of diabetes by extracting the monitoring data characteristics of the diabetes patient, and improves the accuracy of judging the type of diabetes.
Description
Technical Field
The invention relates to the technical field of medical health care informatics, in particular to a diabetes screening data processing and management system.
Background
With the improvement of the living standard of people, the incidence rate of diabetes mellitus is gradually increased, and how to screen, process and manage the data of diabetes mellitus patients is an important subject in the field of medical care informatics. Currently, diabetes mellitus can be classified into four types of diabetes mellitus according to the pathology of diabetes mellitus: type 1 diabetes, type 2 diabetes, gestational diabetes, and other specific types of diabetes. The incidence rate of type 1 diabetes and type 2 diabetes is high, and the type 1 diabetes is caused by the fact that insulin cannot be secreted due to the fact that an immune system attacks islet beta cells; type 2 diabetes is caused by insulin resistance of peripheral cells or insufficient secretion of insulin by islet beta cells, and the treatment means adopted in the course of treatment may be different due to the difference in pathology of these two diabetes.
In clinical diagnosis of type 1 diabetes or type 2 diabetes, a doctor usually diagnoses the patient by means of age, weight, family history, and related detection indexes such as autoantibody detection, and comprehensively judges whether the patient is type 1 diabetes or type 2 diabetes. In actual clinic, as two diabetes symptoms are highly similar, a plurality of biochemical indexes are also needed to be detected to assist in judging the type of diabetes, the process is complex, misjudgment is easy to be caused, the treatment of patients is delayed, and medical resources are wasted.
Disclosure of Invention
The invention provides a diabetes screening data processing and management system, which aims to solve the problem of larger diagnosis error of a diabetic patient according to screening data, and adopts the following technical scheme:
the invention relates to a diabetes screening data processing and management system, which comprises the following modules:
the data acquisition module is used for acquiring screening data of diabetics;
the characteristic extraction module is used for dividing data segments according to blood sugar data and heart rate data in the screening data of the diabetics, and classifying the data segments by utilizing the divided data segments; obtaining glycemic indexes of patients in different time periods, and calculating blood glucose regulation and control characteristic values of the patients according to areas under blood glucose curves in different time periods and the glycemic indexes; obtaining the blood sugar reserve of the organism in different time periods, and calculating the blood sugar consumption coefficients of the organism in different types of data periods according to the blood sugar reserve of the organism in different time periods and the heart rate variation; calculating the blood sugar consumption residual quantity of the organism in the different types of data segments according to the blood sugar reserve quantity of the organism in the different time segments and the blood sugar consumption coefficient of the organism in the different types of data segments; calculating abnormal blood sugar deviation values of different types of data segments according to the areas under blood sugar curves of the different types of data segments and the blood sugar consumption and residual quantity of the organism; calculating the abnormal blood sugar deviation characteristic values of the different types of data segments according to the abnormal blood sugar deviation values of the different types of data segments; obtaining blood sugar stability time characteristic values of different types of data segments according to the blood sugar stability persistence analysis results of the different types of data segments; acquiring weight characteristic values, age characteristic values and medical history marking values according to the weight, medical history and age data in the screening data of the diabetics;
the type analysis module is used for constructing a diabetes type characteristic vector according to the blood sugar regulation characteristic value, the blood sugar abnormal deviation characteristic value, the blood sugar stabilizing time characteristic value, the weight characteristic value, the age characteristic value and the medical history marking value of the diabetes patient, and acquiring the diabetes type of the diabetes patient according to the diabetes type characteristic vector;
and the data management module is used for assisting the diagnosis of the diabetics according to the type classification result of the diabetics.
Preferably, the method for classifying the data segments by using the divided data segments according to blood sugar data and heart rate data in the screening data of the diabetics comprises the following steps:
acquiring a meal time period and a non-meal time period of a diabetic patient in one day according to meal time data in screening data of the diabetic patient, acquiring data periods of the diabetic patient in the non-meal time period according to heart rate data and blood sugar data of the diabetic patient in a preset time range of the non-meal time period of the diabetic patient, and classifying the data periods of the diabetic patient in the non-meal time period according to the heart rate data and the blood sugar data in the data periods of the diabetic patient in the non-meal time period.
Preferably, the method for obtaining glycemic indexes of a patient in different time periods and calculating the blood glucose regulation characteristic value of the patient according to the area under a blood glucose curve and the glycemic indexes in different time periods comprises the following steps:
and acquiring a glycemic index of the diabetic patient in a dining time period according to the screening data of the diabetic patient, taking the ratio of the area under a blood sugar-time curve in the dining time period of the diabetic patient to the glycemic index as a first regulation characteristic value of the patient, and taking the sum of the first regulation characteristic value of the patient in the dining time period in one day as the blood sugar regulation characteristic value of the patient.
Preferably, the method for obtaining the blood glucose reserve of the organism in different time periods and calculating the blood glucose consumption coefficient of the organism in different types of data periods according to the blood glucose reserve of the organism in different time periods and the heart rate variation comprises the following steps:
obtaining the body blood sugar reserve of the diabetic patient in the dining time period according to the screening data of the diabetic patient, taking the product of the accumulated sum of the body blood sugar reserve of the diabetic patient in the dining time period in one day and the area under the heart rate-time curve of any one data period as a numerator, taking the area under the heart rate-time curve of the diabetic patient in one day as a denominator, and taking the ratio of the numerator to the denominator as the body blood sugar consumption coefficient of any one data period.
Preferably, the method for calculating the remaining blood sugar consumption of the organism in the different types of data segments according to the blood sugar reserve of the organism in the different time segments and the blood sugar consumption coefficient of the organism in the different types of data segments comprises the following steps:
；
in the method, in the process of the invention,a patient's day time period of non-dining>Blood glucose consumption remaining of the individual data segments; />Indicating>Food intake during individual meal time period, < >>Indicating the expiration of the non-meal time period of the dayThe number of dining time periods contained in the time period in which the individual data periods are located; />First time period of non-meal time period of dayThe blood glucose consumption coefficient of the body for each data segment.
Preferably, the method for calculating the abnormal blood glucose deviation value of the different types of data segments according to the area under the blood glucose curve of the different types of data segments and the blood glucose consumption residual quantity of the organism comprises the following steps:
；
in the method, in the process of the invention,a patient's day time period of non-dining>Abnormal blood glucose deviations for the individual data segments;indicating +.f. in non-dining time period of patient in one day>The area under the blood glucose-time curve for each data segment; />Indicating +.f. in non-dining time period in day>A normoglycemic threshold for the type of data segment; />Patient's No. during non-dining time period in one day>The corresponding acquisition time length of the data segments; />A patient's day time period of non-dining>Normalization of the blood glucose consumption remaining amount for each data segment.
Preferably, the method for calculating the abnormal blood sugar deviation characteristic value of the data segments of different types according to the abnormal blood sugar deviation value of the data segments of different types comprises the following steps:
taking the average value of the abnormal blood sugar deviation values of all the data segments of any one type of data segment as the abnormal blood sugar deviation characteristic value of any one type of data segment.
Preferably, the method for obtaining the characteristic value of the blood glucose stability time of the data segments of different types according to the continuous analysis result of the blood glucose stability of the data segments of different types comprises the following steps:
and taking the ratio of the sum of the time occupied by any one normal blood glucose type data segment to the total time in the day as the blood glucose stabilizing time characteristic value of the any one normal blood glucose type data segment.
Preferably, the method for obtaining the weight characteristic value, the age characteristic value and the medical history marking value according to the weight, the medical history and the age data in the screening data of the diabetes patient comprises the following steps:
calculating a body mass index as a body weight characteristic value of the patient according to the height and the weight of the patient; taking the age data of the patient as an age characteristic value of the patient; the patient in the family having no history of diabetes is marked with a medical history flag value of 0, the patient in the family having type 1 diabetes is marked with a medical history flag value of 1, the patient in the family having type 2 diabetes is marked with a medical history flag value of 2, and the patient in the family having type 1 diabetes or type 2 diabetes is marked with a medical history flag value of 3.
Preferably, the method for constructing the diabetes type feature vector according to the blood sugar regulation feature value, the blood sugar abnormal deviation feature value, the blood sugar stable time feature value, the weight feature value, the age feature value and the medical history mark value of the diabetes patient comprises the following steps:
sequentially taking a blood sugar regulation characteristic value, a blood sugar abnormal deviation characteristic value, a blood sugar stabilizing time characteristic value, a weight characteristic value, an age characteristic value and a medical history marking value of a diabetic patient as elements in a diabetes type characteristic vector of the diabetic patient, acquiring the diabetes type characteristic vector of the diabetic patient, and inputting the diabetes type characteristic vector of the patient into a trained neural network model to obtain the diabetes type of the patient.
The beneficial effects of the invention are as follows: the behavior time period of the patient is divided by monitoring the heart rate condition, and the current blood sugar storage residual quantity is calculated by combining the related indexes of the edible food, so that the interference of the behavior of the patient or the self energy storage to the blood sugar monitoring is avoided when the type of diabetes of the patient is judged through the blood sugar monitoring curve. Obtaining a blood sugar regulation characteristic value by monitoring the change of blood sugar within 2 hours after meals; and the condition that the complex behaviors of the patient interfere with blood sugar monitoring is eliminated by calculating the abnormal deviation characteristic value and the stable time characteristic value of the blood sugar in the non-dining time period. The method has the beneficial effects that the characteristic value of the diabetes type of the patient in the screening data is extracted by mining the screening data information of the diabetes patient, and a neural network model is constructed to assist a doctor in diagnosing the diabetes type of the patient, so that the diagnosis accuracy is improved, and medical resources are saved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of a system for processing and managing diabetes screening data according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating different data segment types according to an embodiment of the present invention;
fig. 3 is a schematic view of the area under the blood glucose-time curve according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a diabetes screening data processing and management system according to an embodiment of the present invention is shown, the system includes: the device comprises a data acquisition module, a characteristic extraction module, a type analysis module and a data management module.
The data acquisition module is used for acquiring data, wherein the target crowd for data acquisition is a patient with diabetes, and the patient has no other diseases affecting heart rate and blood sugar, does not use medicines affecting blood sugar level on the same day, and has three meals on the same day (the type and weight of food eaten on the same day can be known). Acquiring screening data of the target crowd in a diabetes information management system, wherein the screening data comprise age, weight, height and family diabetes history; daily blood glucose data, daily heart rate data, daily meal time data (time when a patient starts and ends a specific meal), type and weight data of food consumed for each meal time period, where the time period in a day is counted as one day starting from one natural daily breakfast starting time until the second natural daily breakfast starting time as the end; the type of diabetes of each patient is also used as a label for the data collected by each patient.
Screening data of the diabetic patients meeting the conditions are obtained, and the obtained screening data of the diabetic patients meeting the conditions are used as a training data set of the neural network.
To this end, screening data and neural network training data sets for each diabetic patient may be obtained.
The characteristic extraction module is used for greatly influencing the monitoring of the blood sugar of the patient by the dining behavior of the diabetic patient, so that the dining time period and the non-dining time period of the diabetic patient are required to be respectively analyzed. The glycemic index of the patient 2 hours after the end of the meal of the diabetic is obtained, the time period from the beginning of the meal of the diabetic to 2 hours after the end of the meal is taken as the meal time period, and the process of obtaining the glycemic index is a known technology and is not repeated.
The heart rate data of each patient is collected at a frequency of 1 time per second, the blood glucose data of each patient is collected at a frequency of 1 time per minute, and the heart rate data in 30s before and after the time of collecting each blood glucose data in the non-dining time period of one day of the patient is taken as a data period of the non-dining time period, so that each data period in the non-dining time period of each patient contains one blood glucose data and 60 heart rate data. Calculating the mean value of the heart rate of each data segmentAccording to clinical experience, adult resting heart rates are typically between 60 and 100. Therefore will->The data segment of the data is marked as a low heart rate data segment, and the data segment corresponds to low heart rate conditions such as sleeping and the like, and the body consumes low blood sugar; />The data section of the (2) is marked as a stable heart rate data section, and corresponds to the general conditions of sitting, walking and the like of a patient, and the blood sugar consumption level of the body is stable at the moment; />The data segment of the (2) is marked as a high heart rate data segment, which corresponds to the conditions of intense exercise and the like, and the blood sugar consumption of the body is high at the moment.
Further, according to clinical experience, the normal blood sugar level of a diabetic patient in a resting state is set to be 4.4-7.0mmol/L, the normal blood sugar level is set to be 4.4-9.0mmol/L due to the fact that a large amount of energy is required to be supplied to the body during exercise, and the blood sugar can be reduced in a short time after exercise due to the fact that the hormone regulation level of the body needs to be recovered, so that the normal blood sugar level is set to be 3.4-7.0mmol/L.
In the high heart rate data section of the non-dining time period, the blood sugar level is 4.4-9.0mmol/L, which is regarded as a normal blood sugar data section, the blood sugar higher than 9.0mmol/L is a high blood sugar data section, and the blood sugar lower than 4.4mmol/L is a low blood sugar data section; the blood sugar level in the low heart rate data section of the non-dining time period is 3.4-7.0mmol/L, which is regarded as a normal blood sugar data section, the blood sugar higher than 7.0mmol/L is a high blood sugar data section, and the blood sugar lower than 3.4mmol/L is a low blood sugar data section; blood glucose levels at 4.4-7.0mmol/L in the plateau heart rate data segment of the above-described non-meal period are considered normoglycemic data segments, blood glucose above 7.0mmol/L being hyperglycemic data segments and blood glucose below 4.4mmol/L being hypoglycemic data segments. The data sheets during the non-meal time period of the patient's day can be classified into 9 types according to the above-described division, as shown in fig. 2.
In clinic, the influence of food on human blood sugar is quantified by adopting the glycemic index and the content of carbohydrate in the food, so that the glycemic index of each eating period of a patient is calculated according to the type and weight of the food in the eating period of a patient in one day, and the specific calculation process of the glycemic index is a known technology and is not repeated. Taking blood sugar in each dining time period of the patient as an ordinate, taking time for collecting blood sugar data in each dining time period of the patient as an abscissa, obtaining a blood sugar-time curve in each dining time period of the patient, and taking the area under the blood sugar-time curve in each dining time period of the patient as the dining time period of the patientThe values, and the specific acquisition process, are shown in fig. 3. According to glycemic index of each patient and the time period of patient's meal +.>The specific calculation formula of the blood sugar regulating characteristic value is as follows:
；
in the method, in the process of the invention,representing a blood glucose regulation characteristic value of the patient; />Indicating the patient's day->+.>Value of->Indicating the patient's day->Glycemic index for individual meal time periods; />Indicating the number of meal time periods within a day for the patient. If the patient has a weaker ability to self-regulate postprandial blood glucose by the endocrine system, the calculated +.>The greater the value of +.>The smaller the value of (2), the resulting +.>The greater the value, the more likely the patient is to have type 1 diabetes; the greater the patient's ability to self-regulate postprandial blood glucose by the endocrine system, the calculated +.>The smaller the value of +.>The greater the value of (2), the greater the ∈>The smaller the value, the more likely the patient is to suffer from type 2 diabetes.
Further, the patient is analyzed for glycemic anomalies based on the patient's food intake and the patient's heart rate data. In particular, since the diabetic patients themselves have poor storage and regulation of substances, the food intake of the diabetic patients can be used as the blood sugar reserve of the body of the patient. Taking the heart rate of each data segment of the patient non-dining time period as an ordinate, and taking the acquisition time of the central rate data of each data segment of the patient non-dining time period as an abscissa, so as to obtain a heart rate-time curve of each data segment of the patient non-dining time period. The body blood sugar consumption coefficient of the patient is calculated according to the body blood sugar reserve quantity and the area under the heart rate-time curve of the diabetic patient, and the specific calculation formula is as follows:
；
in the method, in the process of the invention,no. I representing the period of non-dining in a day>The blood glucose consumption coefficient of the organism of each data segment; />Indicating>Food intake during individual meal time period, < >>Representing patient oneNumber of dining time periods within a day;no. I representing the period of non-dining in a day>Area under the heart rate-time curve of the individual data segments,/->The area under the heart rate-time curve for the patient during the day is indicated.
If the patient does not have a meal during the dayThe heart rate value of the data segment is higher, calculated +.>The larger the value of (2), the higher the blood glucose consumption coefficient of the body is>The larger the value of (c) is, the faster the patient's blood glucose consumption is during the period of time that the data segment is.
Further, the remaining blood sugar consumption is calculated according to the blood sugar consumption coefficient of the body of each data segment of the non-dining time segment in one day of the patient, and the specific calculation formula is as follows:
；
in the method, in the process of the invention,a patient's day time period of non-dining>Blood glucose consumption remaining of the individual data segments;indicating>Food intake during individual meal time period, < >>Indicating the stop to the non-dining time period of the day +.>The number of dining time periods contained in the time period in which the individual data periods are located; />No. I representing the period of non-dining in a day>The blood glucose consumption coefficient of the body for each data segment.
If the patient ends in the day to the time of non-meal time periodThe time period of the data section is longer than the time period from the time of the blood sugar consumption of the organism to the time of the day>The total food intake during the time period of the individual data segment is calculated +.>The smaller the value of (c) indicates that the patient needs to consume other energy substances to power the body, but the diabetes patient has poor blood glucose regulation ability, and is more likely to develop hypoglycemia symptoms.
Further, a value range of the blood glucose consumption remaining amount of each data segment of the patient in the non-meal time segment of the day is mapped to. Specifically, a sequence formed by sorting the blood glucose consumption residual amounts of all data segments of a patient in a non-meal time period from small to large is used as a blood glucose consumption residual amount sequence, and the data in the blood glucose consumption residual amount sequence is maximizedAnd (3) carrying out minimum normalization processing, obtaining a normalization result of the blood glucose consumption residual quantity of each data segment according to the blood glucose consumption residual quantity sequence after normalization processing, wherein the specific calculation process of maximum and minimum normalization is a known technology and is not repeated.
Taking a sequence formed by the blood glucose values of each type of data segment according to the ascending order of time as a blood glucose change sequence of each type of data segment, taking the data of the blood glucose change sequence of each type of data segment as an ordinate, taking the acquisition time of each data in the blood glucose change sequence of each type of data segment as an abscissa, and obtaining a blood glucose-time curve of each type of data segment according to the abscissa and the ordinate. Calculating the abnormal blood sugar deviation value of each data segment according to the blood sugar consumption residual quantity of each data segment of the patient in the non-meal time segment of the day and the blood sugar difference of the patient in each data segment, wherein the specific calculation formula is as follows:
；
in the method, in the process of the invention,a patient's day time period of non-dining>Abnormal blood glucose deviations for the individual data segments; />Indicating +.f. in non-dining time period of patient in one day>The area under the blood glucose-time curve for each data segment;indicating +.f. in non-dining time period in day>A normoglycemic threshold for the type of data segment; />Patient's No. during non-dining time period in one day>The corresponding acquisition time length of the data segments; />A patient's day time period of non-dining>Normalization of the blood glucose consumption remaining amount for each data segment.
If the patient does not have a meal during the dayThe greater the blood glucose consumption remaining amount in the period in which the individual data segments are located, i.e. +.>The greater the value of (2), the calculated +.f. for the period of non-dining of the patient during the day>The greater the blood glucose abnormality deviation value of the data segment, the more +.>Blood glucose abnormality characteristic values for the individual data segments. The influence of the blood sugar reserve on the blood sugar deviation analysis can be eliminated by the blood sugar consumption remaining amount of each data segment of the patient in the non-meal time segment in one day, specifically, according to clinical experience, for example, in the time segment which is closer to the time segment of the meal, the severity of the symptoms of hypoglycemia occurring in the patient is lower than in the time segment which is farther from the time segment of the meal, and in the case of the blood sugar reserve, the blood sugar deviation value of the blood sugar data segment is lower than the blood sugar deviation value of the blood sugar reserve in the case of the blood sugar reserve through the calculation, so that the influence of the blood sugar reserve on the blood sugar deviation analysis is eliminated.
Further, calculating the average value of the abnormal blood sugar deviation values of all the data segments of the hyperglycemia high heart rate type as the abnormal blood sugar deviation characteristic value of the data segments of the hyperglycemia high heart rate typeThe method comprises the steps of carrying out a first treatment on the surface of the The blood sugar abnormality deviation characteristic values of the hyperglycemia and the high heart rate type data section, the hyperglycemia and the low heart rate type data section, the low blood sugar and the high heart rate type data section, the low blood sugar and the normal heart rate type data section and the low blood sugar and the low heart rate type data section can be obtained in the same way as the blood sugar abnormality deviation characteristic values of the hyperglycemia and the high heart rate type data section, and the blood sugar abnormality deviation characteristic values are respectively->、/>、/>、/>、/>. Further, calculating the percentage of the sum of the collection time of the normoglycemic hyperrate type data segment to the time of day as the blood glucose stabilizing time characteristic value +.>The method comprises the steps of carrying out a first treatment on the surface of the The calculation mode is the same as that of the blood sugar stability time characteristic value of the normal blood sugar and high heart rate type data segment, and the blood sugar stability time characteristic values of the normal blood sugar and normal heart rate type data segment and the blood sugar stability time characteristic value of the normal blood sugar and low heart rate type data segment which can be obtained are respectively +.>、/>。
Further, calculating a body mass index as a body weight characteristic value of the patient according to the height and the weight of the patientThe method comprises the steps of carrying out a first treatment on the surface of the Age data of a patient as age characteristic value +.>The method comprises the steps of carrying out a first treatment on the surface of the Obtaining a patient's medical history marker value from the patient's family diabetes history>Specifically, the patient in the family having no history of diabetes is marked with a history flag value of 0, the patient in the family having type 1 diabetes is marked with a history flag value of 1, the patient in the family having type 2 diabetes is marked with a history flag value of 2, and the patient in the family having type 1 diabetes or type 2 diabetes is marked with a history flag value of 3.
Thus, 13 characteristic values of the diabetic patient, namely blood sugar regulating characteristic values, are obtainedBlood glucose abnormality deviation feature value +.>Blood glucose stability time characteristic value +.>Weight characteristic value->Age characteristic value->Medical history flag value->。
And the type analysis module can obtain 13 characteristic values of the diabetics according to analysis of the diabetics screening data. According to diabetes patientsThe 13 characteristic values of the patient acquire a diabetes type characteristic vector of the diabetic patient, wherein elements in the diabetes type characteristic vector are blood sugar regulating characteristic values, abnormal blood sugar deviation characteristic values of different types of data segments, blood sugar stabilizing time characteristic values of different types of data segments, weight characteristic values, age characteristic values and medical history marking values in sequence, namely the diabetes type characteristic vector。
The diabetes type of a patient is obtained by adopting a multi-layer perceptron neural network model, the input layer is a diabetes type characteristic vector of the patient, the loss function is a cross entropy loss function, the optimization algorithm is a Adam (Adaptive Moment Estimation) algorithm, and the diabetes type of the patient is output. The process of training the neural network is a well-known technology, and the specific implementation process is not repeated.
The data management module is used for adding the diabetes type analysis neural network model obtained according to the diabetes screening data of the diabetes patient into the diabetes screening data management system, acquiring the diabetes type feature vector of the patient according to the feature extraction module when in use, inputting the diabetes type feature vector of the patient into the type analysis module to obtain the analysis result of the diabetes type of the patient, and further, assisting a doctor in diagnosing the illness state of the patient according to the analysis result of the diabetes type of the patient.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (1)
1. A diabetes screening data processing and management system, comprising the following modules:
the data acquisition module is used for acquiring screening data of diabetics;
the characteristic extraction module is used for dividing data segments according to blood sugar data and heart rate data in the screening data of the diabetics, and classifying the data segments by utilizing the divided data segments; obtaining glycemic indexes of patients in different time periods, and calculating blood glucose regulation and control characteristic values of the patients according to areas under blood glucose curves in different time periods and the glycemic indexes; obtaining the blood sugar reserve of the organism in different time periods, and calculating the blood sugar consumption coefficients of the organism in different types of data periods according to the blood sugar reserve of the organism in different time periods and the heart rate variation; calculating the blood sugar consumption residual quantity of the organism in the different types of data segments according to the blood sugar reserve quantity of the organism in the different time segments and the blood sugar consumption coefficient of the organism in the different types of data segments; calculating abnormal blood sugar deviation values of different types of data segments according to the areas under blood sugar curves of the different types of data segments and the blood sugar consumption and residual quantity of the organism; calculating the abnormal blood sugar deviation characteristic values of the different types of data segments according to the abnormal blood sugar deviation values of the different types of data segments; obtaining blood sugar stability time characteristic values of different types of data segments according to the blood sugar stability persistence analysis results of the different types of data segments; acquiring weight characteristic values, age characteristic values and medical history marking values according to the weight, medical history and age data in the screening data of the diabetics;
the type analysis module is used for constructing a diabetes type characteristic vector according to the blood sugar regulation characteristic value, the blood sugar abnormal deviation characteristic value, the blood sugar stabilizing time characteristic value, the weight characteristic value, the age characteristic value and the medical history marking value of the diabetes patient, and acquiring the diabetes type of the diabetes patient according to the diabetes type characteristic vector;
the data management module is used for assisting the diagnosis of the diabetics according to the type classification result of the diabetics;
the method for classifying the data segments by utilizing the divided data segments comprises the following steps of:
acquiring a meal time period and a non-meal time period of a diabetic patient in one day according to meal time data in screening data of the diabetic patient, acquiring data periods of the diabetic patient in the non-meal time period according to heart rate data and blood sugar data of the diabetic patient in a preset time range of the non-meal time period of the diabetic patient, and classifying the data periods of the diabetic patient in the non-meal time period according to the heart rate data and the blood sugar data in the data periods of the diabetic patient in the non-meal time period;
the method for obtaining the glycemic index of the patient in different time periods and calculating the blood sugar regulation and control characteristic value of the patient according to the area under the blood sugar curve and the glycemic index in different time periods comprises the following steps:
acquiring a glycemic index of a diabetic patient in a dining time period according to screening data of the diabetic patient, taking the ratio of the area under a blood sugar-time curve in the dining time period of the diabetic patient to the glycemic index as a first regulation characteristic value of the patient, and taking the sum of the first regulation characteristic value of the patient in the dining time period in one day as the blood sugar regulation characteristic value of the patient;
the method for obtaining the blood sugar reserve of the organism in different time periods and calculating the blood sugar consumption coefficients of the organism in different types of data periods according to the blood sugar reserve of the organism in different time periods and the heart rate variation comprises the following steps:
obtaining the body blood sugar reserve of a diabetic patient in a dining time period according to screening data of the diabetic patient, taking the product of the accumulated sum of the body blood sugar reserve of the diabetic patient in the dining time period in one day and the area under the heart rate-time curve of any one data period as a numerator, taking the area under the heart rate-time curve of the diabetic patient in one day as a denominator, and taking the ratio of the numerator to the denominator as the body blood sugar consumption coefficient of any one data period;
the method for calculating the blood sugar consumption residual quantity of the organism in the different types of data segments according to the blood sugar reserve quantity of the organism in the different time segments and the blood sugar consumption coefficients of the organism in the different types of data segments comprises the following steps:
；
in the method, in the process of the invention,a patient's day time period of non-dining>Blood glucose consumption remaining of the individual data segments; />Indicating>Food intake during individual meal time period, < >>Indicating the stop to the non-dining time period of the day +.>The number of dining time periods contained in the time period in which the individual data periods are located; />No. I representing the period of non-dining in a day>The blood glucose consumption coefficient of the organism of each data segment;
the method for calculating the abnormal blood sugar deviation value of the different types of data segments according to the area under the blood sugar curve of the different types of data segments and the blood sugar consumption and residual quantity of the organism comprises the following steps:
；
in the method, in the process of the invention,a patient's day time period of non-dining>Abnormal blood glucose deviations for the individual data segments;indicating +.f. in non-dining time period of patient in one day>The area under the blood glucose-time curve for each data segment; />Indicating +.f. in non-dining time period in day>A normoglycemic threshold for the type of data segment; />Patient's No. during non-dining time period in one day>The corresponding acquisition time length of the data segments; />A patient's day time period of non-dining>Normalization result of blood glucose consumption residual quantity of each data segment;
the method for calculating the abnormal blood sugar deviation characteristic value of the data segments of different types according to the abnormal blood sugar deviation value of the data segments of different types comprises the following steps:
taking the average value of the abnormal blood glucose deviation values of all the data segments of any one type of data segment as the abnormal blood glucose deviation characteristic value of any one type of data segment;
the method for acquiring the blood sugar stability time characteristic values of the data segments of different types according to the blood sugar stability persistence analysis results of the data segments of different types comprises the following steps:
taking the ratio of the sum of the time occupied by any one normal blood sugar type data segment to the total time in the day as the blood sugar stabilizing time characteristic value of the any one normal blood sugar type data segment;
the method for acquiring the weight characteristic value, the age characteristic value and the medical history marking value according to the weight, the medical history and the age data in the screening data of the diabetes patient comprises the following steps:
calculating a body mass index as a body weight characteristic value of the patient according to the height and the weight of the patient; taking the age data of the patient as an age characteristic value of the patient; the patient in the family having no history of diabetes is marked with a medical history flag value of 0, the patient in the family having type 1 diabetes is marked with a medical history flag value of 1, the patient in the family having type 2 diabetes is marked with a medical history flag value of 2, and the patient in the family having type 1 diabetes or type 2 diabetes is marked with a medical history flag value of 3;
the method for constructing the diabetes type feature vector according to the blood sugar regulation feature value, the blood sugar abnormal deviation feature value, the blood sugar stabilizing time feature value, the weight feature value, the age feature value and the medical history mark value of the diabetes patient comprises the following steps of:
sequentially taking a blood sugar regulation characteristic value, a blood sugar abnormal deviation characteristic value, a blood sugar stabilizing time characteristic value, a weight characteristic value, an age characteristic value and a medical history marking value of a diabetic patient as elements in a diabetes type characteristic vector of the diabetic patient, acquiring the diabetes type characteristic vector of the diabetic patient, and inputting the diabetes type characteristic vector of the patient into a trained neural network model to obtain the diabetes type of the patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311393990.5A CN117153416B (en) | 2023-10-26 | 2023-10-26 | Diabetes screening data processing and management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311393990.5A CN117153416B (en) | 2023-10-26 | 2023-10-26 | Diabetes screening data processing and management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117153416A CN117153416A (en) | 2023-12-01 |
| CN117153416B true CN117153416B (en) | 2024-01-26 |
Family
ID=88884563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311393990.5A Active CN117153416B (en) | 2023-10-26 | 2023-10-26 | Diabetes screening data processing and management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117153416B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103472010A (en) * | 2013-09-17 | 2013-12-25 | 苏州凯恩医药科技有限公司 | Diabetes detection device |
| CN104382582A (en) * | 2014-11-10 | 2015-03-04 | 哈尔滨医科大学 | Device for classifying dynamic electrocardio data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150347708A1 (en) * | 2014-05-30 | 2015-12-03 | Anthony Michael Albisser | Blood Glucose Meter And Computer-Implemented Method For Improving Glucose Management Through Modeling Of Circadian Profiles |
-
2023
- 2023-10-26 CN CN202311393990.5A patent/CN117153416B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103472010A (en) * | 2013-09-17 | 2013-12-25 | 苏州凯恩医药科技有限公司 | Diabetes detection device |
| CN104382582A (en) * | 2014-11-10 | 2015-03-04 | 哈尔滨医科大学 | Device for classifying dynamic electrocardio data |
Non-Patent Citations (4)
| Title |
|---|
| Dietary potato intake and risks of type 2 diabetes and gestational diabetes mellitus;Guo, F (Guo, Fang)等;《Web of Science》;全文 * |
| Pattern Recognition Reveals Characteristic Postprandial Glucose Changes: Non-Individualized Meal Detection in Diabetes Mellitus Type 1;Konstanze Kölle等;《IEEE》;全文 * |
| The Association Between Food Prices and the Blood Glucose Level of US Adults With Type 2 Diabetes-All Databases;Anekwe, TD等;《Web of Science》;全文 * |
| 糖尿病与非视网膜眼部并发症相关性的研究进展;何蓓蕾，何媛;《国际眼科杂志》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117153416A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR20220016487A (en) | Systems, and associated methods, for bio-monitoring and blood glucose prediction | |
| Pappada et al. | Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes | |
| CN103959291B (en) | Glucose predictions device based on the regularization network with adaptively selected core and regularization parameter | |
| CN110289094B (en) | Expert rule-based insulin accurate administration decision method | |
| CN110021437B (en) | Diabetes management method and system | |
| WO2021158796A1 (en) | Forecasting and explaining user health metrics | |
| Marling et al. | The 4 diabetes support system: A case study in CBR research and development | |
| CN112117004A (en) | Diabetes risk prediction model based on multi-source medical data | |
| CN112133398B (en) | Blood glucose management and control method, system and storage medium | |
| CN117153416B (en) | Diabetes screening data processing and management system | |
| Rosli et al. | Design of meal intake prediction for gestational diabetes mellitus using genetic algorithm | |
| CN117116462A (en) | Method, system and device for predicting glycosylated hemoglobin value | |
| Ahmed et al. | Recent trends and techniques of blood glucose level prediction for diabetes control | |
| CN114093518B (en) | Diabetes risk assessment system and method based on obesity degree | |
| Abed et al. | Sleep Apnea Events Detection Using Deep Learning Techniques | |
| Hsu | A Neurocommunication Model between the Brain and Liver Regarding Glucose Production and Secretion in Early Morning Using GH-Method: Math-Physical Medicine (No. 324) | |
| US20220230751A1 (en) | Decision support system, and method in relation thereto | |
| CN117672531A (en) | Diabetes risk evaluation system based on multiple parameters | |
| MUTUA et al. | Comparative Analysis of Machine Learning Classification Techniques for Neonatal Postprandial Hypoglycemia Symptoms Screening. | |
| Hui et al. | Research on diabetes prediction method based on electronic medical record data analysis | |
| Lado-Baleato et al. | Optimal Cut-Point Estimation for functional digital biomarkers: Application to Continuous Glucose Monitoring | |
| Priyadarshini et al. | A Cloud-Connected Digital System for Type-1 Diabetes Prediction using Time Series LSTM Model | |
| CN117672445A (en) | Diabetes mellitus debilitation current situation analysis method and system based on big data | |
| Sotiriou | Predicting optimal insulin dose for diabetes inpatients by using reinforcement learning | |
| Gutierrez-Martinez et al. | Neural Network-Based Intelligent System for Glucose Spike Prediction and Type 2 Diabetes Mellitus Risk Assessment |
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 |