CN113113142A - Method for predicting diabetes risk by using intelligent analysis technology - Google Patents
Method for predicting diabetes risk by using intelligent analysis technology Download PDFInfo
- Publication number
- CN113113142A CN113113142A CN202110382624.4A CN202110382624A CN113113142A CN 113113142 A CN113113142 A CN 113113142A CN 202110382624 A CN202110382624 A CN 202110382624A CN 113113142 A CN113113142 A CN 113113142A
- Authority
- CN
- China
- Prior art keywords
- risk
- sample
- similarity
- diabetes
- preset
- 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.)
- Pending
Links
- 206010012601 diabetes mellitus Diseases 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000004458 analytical method Methods 0.000 title claims abstract description 40
- 238000005516 engineering process Methods 0.000 title claims abstract description 24
- 238000011161 development Methods 0.000 claims abstract description 28
- 201000010099 disease Diseases 0.000 claims abstract description 20
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 20
- 230000003902 lesion Effects 0.000 claims abstract description 19
- 239000008280 blood Substances 0.000 claims description 33
- 210000004369 blood Anatomy 0.000 claims description 33
- 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 description 30
- 239000008103 glucose Substances 0.000 claims description 30
- 230000003068 static effect Effects 0.000 claims description 16
- 238000003745 diagnosis Methods 0.000 claims description 11
- 206010020772 Hypertension Diseases 0.000 claims description 8
- 208000024891 symptom Diseases 0.000 claims description 7
- 238000007446 glucose tolerance test Methods 0.000 claims description 6
- 230000037396 body weight Effects 0.000 claims description 4
- 230000035488 systolic blood pressure Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 9
- 208000017667 Chronic Disease Diseases 0.000 description 4
- 229920002527 Glycogen Polymers 0.000 description 3
- 206010067584 Type 1 diabetes mellitus Diseases 0.000 description 3
- 208000004104 gestational diabetes Diseases 0.000 description 3
- 229940096919 glycogen Drugs 0.000 description 3
- 210000004185 liver Anatomy 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 208000001072 type 2 diabetes mellitus Diseases 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000003925 fat Substances 0.000 description 2
- 235000015097 nutrients Nutrition 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000036285 pathological change Effects 0.000 description 2
- 231100000915 pathological change Toxicity 0.000 description 2
- 102000004169 proteins and genes Human genes 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 208000037157 Azotemia Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 241000283153 Cetacea Species 0.000 description 1
- 208000008960 Diabetic foot Diseases 0.000 description 1
- 206010022489 Insulin Resistance Diseases 0.000 description 1
- 241000272168 Laridae Species 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 241000287127 Passeridae Species 0.000 description 1
- 208000017442 Retinal disease Diseases 0.000 description 1
- 206010038923 Retinopathy Diseases 0.000 description 1
- 241000251555 Tunicata Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 235000019577 caloric intake Nutrition 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 208000016097 disease of metabolism Diseases 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229940088597 hormone Drugs 0.000 description 1
- 239000005556 hormone Substances 0.000 description 1
- 201000001421 hyperglycemia Diseases 0.000 description 1
- 210000004153 islets of langerhan Anatomy 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 208000030159 metabolic disease Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000000955 neuroendocrine Effects 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001590 oxidative effect Effects 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000004617 sleep duration Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 208000009852 uremia Diseases 0.000 description 1
Images
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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a method for predicting the risk of diabetes by using an intelligent analysis technology, which comprises the following steps: selecting a sample, and acquiring characteristic information of the sample according to a preset frequency; dividing the sample into a diseased group sample and a normal group sample according to whether the diabetes is diagnosed; calculating and obtaining lesion trends of various dynamic indexes in the characteristic information according to the characteristic information of preset times before the patients are diagnosed; calculating to obtain the development trend of each dynamic index in the characteristic information according to the characteristic information of the normal group of samples which is the latest by the preset times; and comparing and calculating the similarity of the development trend and the lesion trend, and obtaining the corresponding disease risk degree of the normal group sample according to the similarity. The data source time span of the invention is large, the stability is strong, and the predictability is far higher than the prior art, thus the accuracy can be more effectively improved.
Description
Technical Field
The invention relates to the technical field of intelligent analysis, in particular to a method for predicting the risk of diabetes by using an intelligent analysis technology.
Background
Diabetes Mellitus (DM) is a lifelong metabolic disease caused by multiple causes and characterized by chronic hyperglycemia, is listed as one of ten difficult and complicated diseases by the world health organization and occupies the first five causes of death. The diabetic patients can have typical symptoms of more than three and one less, and can occur in all systems of the whole body in the later period, such as retinopathy, cardiovascular and cerebrovascular diseases, uremia and serious complications of diabetic feet, so that great pain is brought to the patients. The incidence of diabetes is particularly high and tends to rise year by year. The international diabetes alliance releases data in 2015, the number of Chinese diabetics is about 1.10 hundred million, the Chinese diabetics first occupy the world, and the number of the Chinese diabetics is predicted to reach 1.51 hundred million by 2040 years according to the current development trend. Diabetes can be divided into two types: type 1 diabetes, also known as juvenile diabetes, commonly occurs in adolescents or children and has an obvious familial inheritance tendency; type 2 diabetes, which is a common form of diabetes, is most commonly found in adults. Obesity and excess energy intake are the major causative factors of type 2 diabetes, and the major causes of type 1 diabetes are genetic mutations and familial inheritance. Gestational Diabetes (GDM) is defined as the manifestation of insulin resistance first found during pregnancy. Gestational diabetes is 1-3% in western women and 5-10% in asian women.
The development of diabetes is not without help, removing genetic factors, often associated with poor lifestyle habits, which means that people can reduce their risk by changing lifestyle habits. However, the physical condition of each person is different, and the probability of suffering from the same or similar living habits of people with different physical conditions is different, that is, no absolutely uniform living habit standard can prevent the formation of diabetes. If can be according to the sick risk of individual characteristic accurate prediction everybody, just can let people correspond control habit according to the height of the sick risk grade of self to reduce the probability of morbidity, in other words, be exactly that the higher people of risk grade will manage the habit of oneself more strictly, the lower people of risk grade can suitably relax the management and control yardstick. The existing prediction means usually adopts a static data comparison mode, namely, the characteristic data of the diabetic patient is used as a reference, and the long-term dynamic characteristic data of the diabetic patient before the diabetic patient is ill is ignored, so that the static data comparison mode cannot reflect the dynamic process of the pathological change, and the accuracy of the prediction result is low.
Disclosure of Invention
The invention mainly aims to provide a method for predicting the risk of diabetes by using an intelligent analysis technology, and aims to solve the problem that the accuracy is low because the existing method for predicting the risk of diabetes only adopts static data comparison.
In order to achieve the above object, the method for predicting the risk of diabetes by using an intelligent analysis technology provided by the invention comprises the following steps:
selecting a sample, and acquiring characteristic information of the sample according to a preset frequency;
dividing the sample into a diseased group sample and a normal group sample according to whether the diabetes is diagnosed;
calculating and obtaining lesion trends of various dynamic indexes in the characteristic information according to the characteristic information of preset times before the patients are diagnosed;
calculating to obtain the development trend of each dynamic index in the characteristic information according to the characteristic information of the normal group of samples which is the latest by the preset times;
and comparing and calculating the similarity of the development trend and the lesion trend, and obtaining the corresponding disease risk degree of the normal group sample according to the similarity.
Preferably, the step of dividing the sample into a diseased group sample and a normal group sample according to whether the diabetes is diagnosed or not is preceded by the step of:
acquiring random blood glucose concentration information, diabetes symptom information, fasting blood glucose concentration information and 75 g glucose tolerance test result information of the sample;
judging whether the sample meets at least one of preset diagnosis standards, wherein the preset diagnosis standards comprise: the random blood glucose concentration is more than or equal to 11.1mmol/L and accords with the symptoms of diabetes, the fasting blood glucose concentration is more than or equal to 7mmol/L, and the 75 g glucose tolerance test result is that the blood glucose concentration at two hours is more than or equal to 11.1 mmol/L;
if so, judging whether the patient meets at least one of the preset diagnosis standards again on another subsequent day;
if yes, the patient is diagnosed with diabetes.
Preferably, the characteristic information is divided into static index information and dynamic index information;
the static index information includes: at least one of gender, age, race, family history of hypertension, family history of diabetes;
the dynamic index information includes: fasting blood glucose value, waist-hip ratio, body quality index, body weight, and systolic pressure.
Preferably, the step of dividing the sample into a diseased group sample and a normal group sample according to whether the diabetes is diagnosed or not is followed by:
and dividing the samples into preset groups according to the static indexes.
Preferably, the step of calculating, according to the feature information of the diseased group sample for a preset number of times before diagnosis, lesion trends of various dynamic indexes in the feature information includes:
respectively calculating the average value of each dynamic index data of the samples of the diseased groups in the same group;
and respectively fitting the average value of each dynamic index data of the disease group samples of the same group into a disease trend function relative to time.
Preferably, the step of calculating the development trend of each dynamic index in the feature information according to the feature information of the normal group of samples in the last preset number of times includes:
respectively calculating the average value of each item of dynamic index data of each normal group sample in the same group;
fitting the average value of each dynamic index data of the normal group samples of the same group into a development trend function with respect to time.
Preferably, the step of comparing and calculating the similarity between the trend of development and the trend of lesion comprises:
sequentially analyzing the similarity between the development trend function of each dynamic index and the lesion trend function corresponding to the same group, and expressing the similarity by percentage;
the percentage representing the similarity is averaged.
Preferably, the step of obtaining the degree of risk of the normal group of samples according to the similarity includes:
determining the corresponding relation between the similarity and the risk degree; wherein a similarity of [ 0%, 50%) corresponds to low risk, a similarity of [ 51%, 75%) corresponds to medium risk, and a similarity of [ 75%, 100% ] corresponds to high risk;
and calculating the risk degree according to the numerical value of the similarity.
Preferably, the predetermined frequency is 1 month/time, 2 months/time or 3 months/time.
Preferably, when the preset frequency is 1 month/time, the preset number of times is 12 times; when the preset frequency is 2 months/time, the preset times are 6 times; when the preset frequency is 3 months/time, the preset times are 4 times.
In the technical scheme of the invention, the characteristic information of the samples is acquired for multiple times, and the change trend of the characteristic information of each sample relative to time can be obtained according to the acquisition time and the change of the characteristic information. And dividing the sample into the diseased group sample and the normal group sample according to whether the diabetes is diagnosed or not, wherein the change commonalities of the characteristic information of the diseased group sample can be known by analyzing the change trend of the characteristic information of the diseased group sample, and the commonalities can be used as standard reference for judging the diseased probability. The characteristic information of each individual in the normal group sample is compared with the change trend of the characteristic information of the diseased group sample to obtain the similarity information of the characteristic information and the normal group sample, when the similarity is higher, the trend that the sample suffers from diabetes is more obvious, and accordingly the person can be reminded to correct the life and rest to avoid diseases. When the similarity is smaller, the tendency of the sample to suffer from diabetes is less obvious, so that the person can be reminded to keep the current working and resting state, and the disease can be avoided. The method for predicting the diabetes risk by using the intelligent analysis technology adopts dynamic data comparison, the data of both the diseased group sample and the normal group sample are the characteristic information acquired at intervals for a plurality of times to form a time-related change trend, and the change trends of the diseased group sample and the normal group sample are compared. As is known, diabetes is a chronic disease, the disease process is very long, and the influence factors suffered in the period are very numerous and diverse, the evolution process of the disease can be more accurately reflected by adopting the dynamic comparison mode of the invention, and the future development momentum is predicted according to the change trend, so that the disease probability is judged. Compared with a static data comparison mode in the prior art, the method for predicting the diabetes suffering risk by using the intelligent analysis technology has the advantages of large data source time span, strong stability and high predictability which are far higher than those of the prior art, so that the accuracy can be more effectively improved.
Drawings
FIG. 1 is a schematic flow chart of a first embodiment of a method for predicting risk of diabetes by using intelligent analysis technology according to the present invention.
The objects, features and advantages of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, in a first embodiment of the method for predicting the risk of diabetes by using intelligent analysis technology of the present invention, the method includes the following steps:
step S10, selecting a sample, and collecting characteristic information of the sample according to a preset frequency;
step S20, dividing the sample into a diseased group sample and a normal group sample according to whether the diabetes is diagnosed;
step S30, calculating and obtaining the lesion trend of each dynamic index in the characteristic information according to the characteristic information of the lesion group sample for preset times before diagnosis;
step S40, calculating and obtaining the development trend of each dynamic index in the feature information according to the feature information of the normal group of samples which is the latest by the preset times;
and step S50, comparing and calculating the similarity of the development trend and the lesion trend, and obtaining the corresponding disease risk degree of the normal group sample according to the similarity.
In the technical scheme of the invention, the characteristic information of the samples is acquired for multiple times, and the change trend of the characteristic information of each sample relative to time can be obtained according to the acquisition time and the change of the characteristic information. And dividing the sample into the diseased group sample and the normal group sample according to whether the diabetes is diagnosed or not, wherein the change commonalities of the characteristic information of the diseased group sample can be known by analyzing the change trend of the characteristic information of the diseased group sample, and the commonalities can be used as standard reference for judging the diseased probability. The characteristic information of each individual in the normal group sample is compared with the change trend of the characteristic information of the diseased group sample to obtain the similarity information of the characteristic information and the normal group sample, when the similarity is higher, the trend that the sample suffers from diabetes is more obvious, and accordingly the person can be reminded to correct the life and rest to avoid diseases. When the similarity is smaller, the tendency of the sample to suffer from diabetes is less obvious, so that the person can be reminded to keep the current working and resting state, and the disease can be avoided. The method for predicting the diabetes risk by using the intelligent analysis technology adopts dynamic data comparison, the data of both the diseased group sample and the normal group sample are the characteristic information acquired at intervals for a plurality of times to form a time-related change trend, and the change trends of the diseased group sample and the normal group sample are compared. As is known, diabetes is a chronic disease, the disease process is very long, and the influence factors suffered in the period are very numerous and diverse, the evolution process of the disease can be more accurately reflected by adopting the dynamic comparison mode of the invention, and the future development momentum is predicted according to the change trend, so that the disease probability is judged. Compared with a static data comparison mode in the prior art, the method for predicting the diabetes suffering risk by using the intelligent analysis technology has the advantages of large data source time span, strong stability and high predictability which are far higher than those of the prior art, so that the accuracy can be more effectively improved.
Further, the method adopts any one of a gcForest model, a LightGBM model or a Catboost model to predict;
further, the gcForest model, the LightGBM model, or the CatBoost model is optimized based on any one of a goblet sea squirt algorithm, a moth fire suppression algorithm, a sparrow search algorithm, a gull optimization algorithm, or a whale optimization algorithm.
Based on the first embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, the second embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique further includes, before step S20:
step S60, obtaining random blood sugar concentration information, diabetes symptom information, fasting blood sugar concentration information and 75 g glucose tolerance test result information of the sample;
step S70, determining whether the sample meets at least one of preset diagnostic criteria, where the preset diagnostic criteria include: the random blood glucose concentration is more than or equal to 11.1mmol/L and accords with the symptoms of diabetes, the fasting blood glucose concentration is more than or equal to 7mmol/L, and the 75 g glucose tolerance test result is that the blood glucose concentration at two hours is more than or equal to 11.1 mmol/L;
step S80, if yes, judging again whether the patient meets at least one of the preset diagnosis standards on another day;
and step S90, if yes, determining that the patient is suffered from diabetes.
Glucose in the blood is called blood glucose (Glu). Glucose is an important component of a human body and also an important source of energy, and a normal human body needs a lot of sugar every day to provide energy and provide power for normal operation of various tissues and organs, so that the blood sugar needs to be kept at a certain level to maintain the needs of various organs and tissues in the body. The production and utilization of normal human blood glucose is in a state of dynamic equilibrium, maintained at a relatively stable level, due to the fact that the source and the way of blood glucose are approximately the same. Sources of blood glucose include: firstly, digesting and absorbing food; the glycogen stored in the liver is decomposed; (iii) conversion of fats and proteins. The blood sugar way of going includes: firstly, oxidizing and converting into energy; ② the glycogen is stored in the liver, kidney and muscle; and converting the nutrient components into fat, protein and other nutrient components for storage. The islets of langerhans are the main organs that regulate the blood glucose concentration of blood glucose in the body, and the liver stores glycogen. In addition, blood glucose concentration is also regulated by neuroendocrine hormones. Blood glucose fluctuates within a certain range, and when glucose is ingested, blood glucose rises relatively, and when glucose is consumed too much, blood glucose concentration decreases relatively. Because of the fluctuation of blood sugar, in order to more accurately judge whether the patient suffers from diabetes, two detection methods are required, and the diagnosis can be confirmed only when the two detection results exceed the normal blood sugar concentration range.
Based on the first embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technology, the third embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technology, the characteristic information is divided into static index information and dynamic index information;
the static index information includes: at least one of gender, age, race, family history of hypertension, family history of diabetes;
the dynamic index information includes: fasting blood glucose value, waist-hip ratio, body quality index, body weight, and systolic pressure.
The static index information is an index which does not change along with time but has influence on the probability of the diabetes, and can be used for classifying samples; the dynamic index information is an index which changes along with time and has influence on the probability of the diabetes, reflects a change trend and can be used for predicting the data possibility of a sample after a period of time. Meanwhile, the information such as waist-hip ratio, body quality index, body weight and the like in the dynamic index information can be adjusted and changed by changing the life work and rest habits, and can be manually intervened, so that the subsequent development trend is changed.
Preferably, the dynamic index information further includes a movement duration and a sleep duration.
Based on the third embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, the fourth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique further includes, after step S20:
and S100, dividing the samples into preset groups according to the static indexes.
Preferably, the step S100 includes:
a step S110 of dividing the sample into males and females according to gender;
step S120, dividing the sample into young, middle and old age according to age;
step S130, dividing the sample into east Asian, Caucasian, Niger and Australian according to ethnicity;
step S140, dividing the sample into a family history of hypertension and a family history of non-hypertension according to the family history of hypertension;
step S150, dividing the sample into a family history of diabetes and a family history of non-diabetes according to the family history of diabetes;
step S160, selecting from male and female, selecting from young, middle-aged and old, selecting from east Asian, Caucasian, Niger and Australian, selecting from family history of hypertension and family history of non-hypertension, selecting from family history of diabetes and family history of non-diabetes, and combining to form a plurality of groups.
The samples in each same group have the same or similar static indicators, and comparison between them will result in a more accurate prediction.
Based on the fourth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, in the fifth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, the step S30 includes:
step S31, calculating the average value of each dynamic index data of each diseased group sample in the same group;
step S32, fitting the average value of each dynamic index data of the same group of the diseased group samples into a diseased trend function with respect to time.
The lesion trend function can reflect the correlation values of various dynamic index data at different time by changing the time parameters, and the correlation degree of the index value of the sample to be predicted and the correlation value can be analyzed by comparing the difference degree between the two correlation values, wherein the higher the correlation degree is, the closer the description is to the characteristics of the sick people, namely, the more likely the sick people suffer from diabetes.
Based on the fifth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, in the sixth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, the step S40 includes:
step S41, calculating the average value of each item of dynamic index data of each normal group sample in the same group;
step S42, fitting the average value of each item of the dynamic index data of the normal group samples of the same group into a development trend function with respect to time.
The development trend function can predict the future development trend within a certain range by changing the time parameter, because the diabetes is a chronic disease, the pathological change process is very long, and because the prediction is based on early data, the predicted trend can truly reflect the development process within a certain time range.
Based on the sixth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, in the seventh embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, the step of comparing and calculating the similarity between the development trend and the lesion trend in the step S50 includes:
step S51, the similarity between the development trend function of each dynamic index and the lesion trend function corresponding to the same group is analyzed in sequence and expressed by percentage;
step S52, an average of the percentages representing the similarity is found.
The similarity of the development trend function of each dynamic index and the lesion trend function corresponding to the same group reflects the closeness of the index, and the closer the closeness is, the higher the probability of illness is. However, the indexes affecting the disease are very many, and a single index cannot accurately reflect the real situation, so the approach degree of each index must be counted, each similarity is converted into a percentage for convenient expression in a numerical form, and the percentages are summarized and averaged to obtain the final numerical value which is the comprehensive judgment basis.
Based on the seventh embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, in the eighth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technique, the step of obtaining the risk degree of developing diabetes of the corresponding normal group sample according to the similarity in the step S50 includes:
step S53, determining the corresponding relation between the similarity and the risk degree; wherein a similarity of [ 0%, 50%) corresponds to low risk, a similarity of [ 51%, 75%) corresponds to medium risk, and a similarity of [ 75%, 100% ] corresponds to high risk;
and step S54, calculating the risk degree according to the similarity value.
Will the similarity is changed into the risk degree can demonstrate to people more directly perceivedly, conveniently, and people can be according to oneself the risk degree makes corresponding adjustment to the life work and rest of self to avoid sickening as far as possible.
In a ninth embodiment of the method for predicting a risk of developing diabetes by using an intelligent analysis technique according to the present invention, the preset frequency is 1 month/time, 2 months/time, or 3 months/time, based on any one of the first to eighth embodiments of the method for predicting a risk of developing diabetes by using an intelligent analysis technique according to the present invention.
The preset frequency is a frequency for acquiring the characteristic information of the sample. Since diabetes is a chronic disease, the development process is slow, and long-term observation is needed to obtain effective data, a sampling frequency of 1 month/time, 2 months/time or 3 months/time is set to obtain a data value of a longer period.
Based on the ninth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technology, in the tenth embodiment of the method for predicting the risk of developing diabetes by using the intelligent analysis technology, when the preset frequency is 1 month/time, the preset times are 12 times; when the preset frequency is 2 months/time, the preset times are 6 times; when the preset frequency is 3 months/time, the preset times are 4 times.
The preset times are determined according to the preset frequency, in order to obtain long-term analysis data to improve the accuracy of prediction, the acquisition period of the data must be ensured to be not less than one year, and when the preset frequency is 1 month/time, the preset times are 12 times; when the preset frequency is 2 months/time, the preset times are 6 times; when the preset frequency is 3 months/time, the preset times are 4 times, and the data acquisition period can meet the requirements no matter what way.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for predicting the risk of diabetes by using an intelligent analysis technology is characterized by comprising the following steps:
selecting a sample, and acquiring characteristic information of the sample according to a preset frequency;
dividing the sample into a diseased group sample and a normal group sample according to whether the diabetes is diagnosed;
calculating and obtaining lesion trends of various dynamic indexes in the characteristic information according to the characteristic information of preset times before the patients are diagnosed;
calculating to obtain the development trend of each dynamic index in the characteristic information according to the characteristic information of the normal group of samples which is the latest by the preset times;
and comparing and calculating the similarity of the development trend and the lesion trend, and obtaining the corresponding disease risk degree of the normal group sample according to the similarity.
2. The method for predicting the risk of developing diabetes mellitus using intelligent analysis technology as claimed in claim 1, wherein said step of dividing the sample into diseased group sample and normal group sample according to whether the diabetes mellitus is diagnosed is preceded by the steps of:
acquiring random blood glucose concentration information, diabetes symptom information, fasting blood glucose concentration information and 75 g glucose tolerance test result information of the sample;
judging whether the sample meets at least one of preset diagnosis standards, wherein the preset diagnosis standards comprise: the random blood glucose concentration is more than or equal to 11.1mmol/L and accords with the symptoms of diabetes, the fasting blood glucose concentration is more than or equal to 7mmol/L, and the 75 g glucose tolerance test result is that the blood glucose concentration at two hours is more than or equal to 11.1 mmol/L;
if so, judging whether the patient meets at least one of the preset diagnosis standards again on another subsequent day;
if yes, the patient is diagnosed with diabetes.
3. The method for predicting the risk of developing diabetes mellitus by using intelligent analysis technology as claimed in claim 1, wherein the characteristic information is divided into static index information and dynamic index information;
the static index information includes: at least one of gender, age, race, family history of hypertension, family history of diabetes;
the dynamic index information includes: fasting blood glucose value, waist-hip ratio, body quality index, body weight, and systolic pressure.
4. The method for predicting the risk of developing diabetes mellitus using intelligent analysis technology as claimed in claim 3, wherein said step of dividing the sample into diseased group sample and normal group sample according to whether the diabetes mellitus is diagnosed is followed by:
and dividing the samples into preset groups according to the static indexes.
5. The method according to claim 4, wherein the step of calculating the lesion trend of each dynamic index in the feature information according to the feature information of the group of patients for a predetermined number of times before diagnosis includes:
respectively calculating the average value of each dynamic index data of the samples of the diseased groups in the same group;
and respectively fitting the average value of each dynamic index data of the disease group samples of the same group into a disease trend function relative to time.
6. The method according to claim 5, wherein the step of calculating the trend of each dynamic indicator in the feature information according to the feature information of the normal group of samples in the preset number of times recently comprises:
respectively calculating the average value of each item of dynamic index data of each normal group sample in the same group;
fitting the average value of each dynamic index data of the normal group samples of the same group into a development trend function with respect to time.
7. The method for predicting the risk of developing diabetes by using intelligent analysis technology as claimed in claim 6, wherein the step of comparing and calculating to obtain the similarity of the development trend and the lesion trend comprises:
sequentially analyzing the similarity between the development trend function of each dynamic index and the lesion trend function corresponding to the same group, and expressing the similarity by percentage;
the percentage representing the similarity is averaged.
8. The method for predicting the risk of developing diabetes mellitus by using intelligent analysis technology as claimed in claim 7, wherein the step of obtaining the degree of risk of developing the corresponding normal group of samples according to the similarity comprises:
determining the corresponding relation between the similarity and the risk degree; wherein a similarity of [ 0%, 50%) corresponds to low risk, a similarity of [ 51%, 75%) corresponds to medium risk, and a similarity of [ 75%, 100% ] corresponds to high risk;
and calculating the risk degree according to the numerical value of the similarity.
9. The method for predicting the risk of developing diabetes mellitus using intelligent analysis technology according to any one of claims 1 to 8, wherein the preset frequency is 1 month/time, 2 months/time or 3 months/time.
10. The method for predicting the risk of developing diabetes mellitus using intelligent analysis technology according to claim 9, wherein when the preset frequency is 1 month/time, the preset number of times is 12 times; when the preset frequency is 2 months/time, the preset times are 6 times; when the preset frequency is 3 months/time, the preset times are 4 times.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110382624.4A CN113113142A (en) | 2021-04-09 | 2021-04-09 | Method for predicting diabetes risk by using intelligent analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110382624.4A CN113113142A (en) | 2021-04-09 | 2021-04-09 | Method for predicting diabetes risk by using intelligent analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113113142A true CN113113142A (en) | 2021-07-13 |
Family
ID=76715015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110382624.4A Pending CN113113142A (en) | 2021-04-09 | 2021-04-09 | Method for predicting diabetes risk by using intelligent analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113113142A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658704A (en) * | 2021-09-17 | 2021-11-16 | 平安国际智慧城市科技股份有限公司 | Diabetes risk prediction device, apparatus and storage medium |
| CN116159208A (en) * | 2021-11-24 | 2023-05-26 | 上海微创生命科技有限公司 | Artificial pancreas control method, readable storage medium and blood glucose management system |
| CN117854676A (en) * | 2024-01-17 | 2024-04-09 | 泰昊乐生物科技有限公司 | Health management plan customization method and system |
| CN117854732A (en) * | 2024-03-08 | 2024-04-09 | 微脉技术有限公司 | Chronic disease management method and system based on big data analysis |
| CN118299041A (en) * | 2024-04-22 | 2024-07-05 | 济南圣力科技有限公司 | Physical examination data information acquisition and analysis method |
| CN117854732B (en) * | 2024-03-08 | 2024-09-24 | 微脉技术有限公司 | Chronic disease management method and system based on big data analysis |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103154272A (en) * | 2010-08-25 | 2013-06-12 | 香港中文大学 | Methods and kits for predicting the risk of diabetes associated complications using genetic markers and arrays |
| CN104063583A (en) * | 2014-06-06 | 2014-09-24 | 北京工业大学 | Gestation diabetes risk monitoring system based on dynamic physics and physical and chemical factors |
| JP2019027885A (en) * | 2017-07-28 | 2019-02-21 | 国立大学法人千葉大学 | Diagnostic biomarker of onset risk of pregnancy diabetes mellitus |
| CN110085318A (en) * | 2019-03-12 | 2019-08-02 | 平安科技（深圳）有限公司 | Predict the method, apparatus and computer equipment of future blood glucose value |
| CN110197724A (en) * | 2019-03-12 | 2019-09-03 | 平安科技（深圳）有限公司 | Predict the method, apparatus and computer equipment in diabetes illness stage |
| CN110808097A (en) * | 2019-10-30 | 2020-02-18 | 中国福利会国际和平妇幼保健院 | Gestational diabetes prediction system and method |
| CN111312399A (en) * | 2020-02-24 | 2020-06-19 | 南京鼓楼医院 | Method for establishing model for early prediction of gestational diabetes |
| CN111297329A (en) * | 2020-02-24 | 2020-06-19 | 苏州大学 | Method and system for predicting dynamic morbidity risk of cardiovascular complications of diabetic patients |
| CN112289437A (en) * | 2020-10-28 | 2021-01-29 | 南通市第一人民医院 | Diabetes adjuvant therapy cloud platform system based on edge computing framework |
-
2021
- 2021-04-09 CN CN202110382624.4A patent/CN113113142A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103154272A (en) * | 2010-08-25 | 2013-06-12 | 香港中文大学 | Methods and kits for predicting the risk of diabetes associated complications using genetic markers and arrays |
| CN104063583A (en) * | 2014-06-06 | 2014-09-24 | 北京工业大学 | Gestation diabetes risk monitoring system based on dynamic physics and physical and chemical factors |
| JP2019027885A (en) * | 2017-07-28 | 2019-02-21 | 国立大学法人千葉大学 | Diagnostic biomarker of onset risk of pregnancy diabetes mellitus |
| CN110085318A (en) * | 2019-03-12 | 2019-08-02 | 平安科技（深圳）有限公司 | Predict the method, apparatus and computer equipment of future blood glucose value |
| CN110197724A (en) * | 2019-03-12 | 2019-09-03 | 平安科技（深圳）有限公司 | Predict the method, apparatus and computer equipment in diabetes illness stage |
| CN110808097A (en) * | 2019-10-30 | 2020-02-18 | 中国福利会国际和平妇幼保健院 | Gestational diabetes prediction system and method |
| CN111312399A (en) * | 2020-02-24 | 2020-06-19 | 南京鼓楼医院 | Method for establishing model for early prediction of gestational diabetes |
| CN111297329A (en) * | 2020-02-24 | 2020-06-19 | 苏州大学 | Method and system for predicting dynamic morbidity risk of cardiovascular complications of diabetic patients |
| CN112289437A (en) * | 2020-10-28 | 2021-01-29 | 南通市第一人民医院 | Diabetes adjuvant therapy cloud platform system based on edge computing framework |
Non-Patent Citations (1)
| Title |
|---|
| ROBERTM.KLIEGMAN等: "尼尔逊儿科学", vol. 19, 30 September 2017, 世界图书出版西安有限公司, pages: 26 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658704A (en) * | 2021-09-17 | 2021-11-16 | 平安国际智慧城市科技股份有限公司 | Diabetes risk prediction device, apparatus and storage medium |
| CN116159208A (en) * | 2021-11-24 | 2023-05-26 | 上海微创生命科技有限公司 | Artificial pancreas control method, readable storage medium and blood glucose management system |
| CN116159208B (en) * | 2021-11-24 | 2024-03-15 | 上海微创生命科技有限公司 | Artificial pancreas control method, readable storage medium and blood glucose management system |
| CN117854676A (en) * | 2024-01-17 | 2024-04-09 | 泰昊乐生物科技有限公司 | Health management plan customization method and system |
| CN117854732A (en) * | 2024-03-08 | 2024-04-09 | 微脉技术有限公司 | Chronic disease management method and system based on big data analysis |
| CN117854732B (en) * | 2024-03-08 | 2024-09-24 | 微脉技术有限公司 | Chronic disease management method and system based on big data analysis |
| CN118299041A (en) * | 2024-04-22 | 2024-07-05 | 济南圣力科技有限公司 | Physical examination data information acquisition and analysis method |
| CN118299041B (en) * | 2024-04-22 | 2024-09-20 | 济南圣力科技有限公司 | Physical examination data information acquisition and analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113113142A (en) | Method for predicting diabetes risk by using intelligent analysis technology | |
| de Simone et al. | Echocardiographic left ventricular mass and electrolyte intake predict arterial hypertension | |
| US20200375549A1 (en) | Systems for biomonitoring and blood glucose forecasting, and associated methods | |
| Jonker et al. | Physical activity and life expectancy with and without diabetes: life table analysis of the Framingham Heart Study | |
| Li et al. | Life-time socio-economic position and cortisol patterns in mid-life | |
| Shields et al. | An update on mammography use in Canada | |
| Fonseca et al. | Association between dietary patterns and metabolic syndrome in a sample of Portuguese adults | |
| JP5261026B2 (en) | Blood glucose level measuring apparatus and postprandial average blood glucose level measuring method | |
| CN110379488A (en) | A kind of pair of postprandial hyperglycemia carries out the device and method of early warning | |
| WO2021158796A1 (en) | Forecasting and explaining user health metrics | |
| Omboni et al. | Standards for ambulatory blood pressure monitoring clinical reporting in daily practice: recommendations from the Italian Society of Hypertension | |
| Toledo-Corral et al. | Blunted nocturnal cortisol rise is associated with higher carotid artery intima-media thickness (CIMT) in overweight African American and Latino youth | |
| Silva et al. | Anthropometric measures change and incidence of high blood pressure levels among adults: a population-based prospective study in Southern Brazil | |
| Graue et al. | Assessing fear of hypoglycemia among adults with type 1 diabetes–psychometric properties of the Norwegian version of the Hypoglycemia Fear Survey II questionnaire | |
| Chiu et al. | BMI trajectories as a harbinger of pre-diabetes or underdiagnosed diabetes: an 18-year retrospective cohort study in Taiwan | |
| Montano | Depressive symptoms and blood pressure | |
| U Osuji et al. | Prevalence of diabetes mellitus in a group of women attending “August meeting” at Naze South East Nigeria | |
| CN117672445A (en) | Diabetes mellitus debilitation current situation analysis method and system based on big data | |
| CN117153416A (en) | Diabetes screening data processing and management system | |
| Kuzawa et al. | Ankle brachial index (ABI) in a cohort of older women in the Philippines: Prevalence of peripheral artery disease and predictors of ABI | |
| Prado‐Nóvoa et al. | Body composition helps: differences in energy expenditure between pregnant and nonpregnant females | |
| CN106570346B (en) | Physiological condition evaluation factor determination method and physiological condition evaluation factor determination system | |
| CN110993109A (en) | Device for noninvasive cardiovascular function health evaluation method | |
| KR20200078180A (en) | Method for measuring oxidative stress level | |
| Al Quwaidhi | Epidemiological modelling of type 2 diabetes in Saudi Arabia: predicted trends and public health implications |
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 |