Movatterモバイル変換


[0]ホーム

URL:


CN120616515A - A device for predicting diabetes using big data from a diabetes system - Google Patents

A device for predicting diabetes using big data from a diabetes system

Info

Publication number
CN120616515A
CN120616515ACN202510670811.0ACN202510670811ACN120616515ACN 120616515 ACN120616515 ACN 120616515ACN 202510670811 ACN202510670811 ACN 202510670811ACN 120616515 ACN120616515 ACN 120616515A
Authority
CN
China
Prior art keywords
diabetes
user
data
sensor
blood sugar
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
Application number
CN202510670811.0A
Other languages
Chinese (zh)
Inventor
全会标
李德霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hainan Medical University Hainan Academy Of Medical Sciences
Original Assignee
Hainan Medical University Hainan Academy Of Medical Sciences
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hainan Medical University Hainan Academy Of Medical SciencesfiledCriticalHainan Medical University Hainan Academy Of Medical Sciences
Priority to CN202510670811.0ApriorityCriticalpatent/CN120616515A/en
Publication of CN120616515ApublicationCriticalpatent/CN120616515A/en
Pendinglegal-statusCriticalCurrent

Links

Landscapes

Abstract

The invention relates to the field of medical equipment, in particular to a device for predicting diabetes by utilizing big data of a diabetes system, which comprises a wearing device and a controller, wherein the wearing device comprises a wearing carrier, a plurality of physical sign sensors are arranged on the wearing carrier, a receiving box is arranged on the wearing carrier, an opening is arranged on the receiving box, an isolating film is arranged in the opening, a telescopic piece is arranged in the receiving box, a subcutaneous soft needle sensor is arranged on the telescopic piece, the controller is provided with a trained neural network, the neural network is used for outputting the blood sugar change rule of a diabetes cause, when the blood sugar change rule accords with a preset judging value, the controller controls the telescopic piece to drive the subcutaneous soft needle sensor to break the isolating film, and the neural network is used for outputting the probability of a user to diagnose diabetes based on the acquired blood sugar data. By adopting the technical scheme of the invention, big data is analyzed through the collected sign data, and when a user has enough possibility of diabetes, the soft needle is ejected, the collected data is expanded, and the prediction result is analyzed.

Description

Device for predicting diabetes by utilizing big data of diabetes system
Technical Field
The invention relates to the field of medical equipment, in particular to a device for predicting diabetes by utilizing big data of a diabetes system.
Background
Diabetes is a chronic metabolic disease, mainly due to insulin hyposecretion or dysfunction resulting in long-term elevation of blood glucose. It is classified into type 1 (autoimmune insulin deficiency), type 2 (insulin resistance is dominant, associated with obesity and lifestyle), gestational diabetes, etc., and typical symptoms include polydipsia, diuresis, polyphagia, and weight loss. Long-term hyperglycemia may cause serious complications such as cardiovascular and cerebrovascular diseases, renal failure, blindness, etc. The diagnosis needs to be carried out through blood sugar detection (for example, fasting blood sugar is more than or equal to 7.0mmol/L or glycosylated hemoglobin is more than or equal to 6.5%). Treatment relies on personalized protocols including lifestyle modification, oral hypoglycemic agents or insulin injections, and novel techniques such as continuous blood glucose monitoring (CGM) and artificial pancreas significantly improve management efficiency. Early screening and health intervention are particularly important in preventing type 2 diabetes.
Conventional blood glucose tests require the user to take a blood sample from his/her finger, and are painful, with less willingness for most users to perform a blood glucose test before an undiagnosed diagnosis. However, for example, the method provides a novel prediction method for a smart Watch or a wristband such as Watch 4, and uses long-term detection of sign information of a user, such as abnormal heart rate rising at rest, blood oxygen fluctuation at night and the like, and analyzes the probability of diabetes of the user through big data. However, the devices such as Watch 4 and the like do not measure blood sugar per se, so that the pain is avoided, the detection will of a user is improved, but the most important judgment parameters are lacked, and the prediction accuracy is still to be improved.
The near infrared spectrum can detect blood sugar without pain, but the current technology for detecting blood sugar by near infrared spectrum is still not mature and is difficult to effectively apply. CGM is another approach to painless detection mode, and its principle is to use a tiny soft needle to probe into subcutaneous fat layer to monitor interstitial fluid glucose, which has high portability, can be attached to the body of the user for a long time, and monitor blood sugar change. However, due to the life of the soft needle, a single installation can only provide detection for about 7-14 days, and the cost is high, which is far greater than that of fingertip blood sampling, and the detection will of most users by adopting CGM before undiagnosed diagnosis is still low.
Disclosure of Invention
In order to solve the problems, the invention provides a device for predicting diabetes by utilizing big data of a diabetes system, which analyzes the big data by collecting the characteristic data, selects a marked period when a user has enough possibility of diabetes, ejects a soft needle, expands the collected data and analyzes a prediction result.
In order to achieve the above purpose, the technical scheme of the invention is that the device for predicting diabetes by utilizing big data of a diabetes system comprises a wearing device and a controller;
The wearing device comprises a wearing carrier, a plurality of physical sign sensors are arranged on the wearing carrier, a receiving box is arranged on the wearing carrier, an opening is formed in the receiving box, an isolating film is arranged in the opening, a telescopic piece is arranged in the receiving box, and a subcutaneous soft needle sensor is arranged on an output shaft of the telescopic piece;
The controller is preset with a trained neural network, the neural network is trained based on the sign data of the sample population and the blood sugar change rule of the diabetes cause, the neural network is trained based on the sign data of the sample population, the blood sugar change rule and the diagnosis relation of diabetes, the neural network is used for inputting the user sign data acquired by the sign sensor and outputting the blood sugar change rule of the diabetes cause, and when the blood sugar change rule accords with a preset judgment value, the controller controls the telescopic piece to drive the subcutaneous soft needle sensor to break the isolating membrane so that the soft needle of the subcutaneous soft needle sensor is implanted into the subcutaneous fat layer of the user;
the neural network is used for inputting user sign data and blood sugar change data acquired by the subcutaneous soft needle sensor and outputting the probability of the user diagnosing diabetes.
The adoption of the scheme has the following beneficial effects:
1. in this scheme, divide into two stages with the prediction of diabetes, the one stage is with the help of the sign sensor, gathers conventional sign information in order to feed back user's health, and this part is gone on by the sign sensor, need not to consume the consumptive material, and long-term average stand with low costs is also the state that average holding time is longest in the data acquisition. The controller performs big data learning through the neural network to build three-dimensional data and a blood sugar change rule of a diabetes cause for training, and enters a two-stage process when the change state of the three-dimensional data of a user can lead to an obvious blood sugar change rule of diabetes.
2. In this scheme, the two stages can be through ejecting soft needle sensor under skin, carries out the persistence monitoring to user's blood sugar. In one stage, the subcutaneous soft needle sensor is stored in the accommodating box, so that the effectiveness of the subcutaneous soft needle sensor can be ensured for a long time, and the external environment is isolated through the isolating film so as to prevent the subcutaneous soft needle sensor from being polluted. When the two phases are entered, the output shaft of the telescopic piece is stretched, so that the subcutaneous soft needle sensor breaks through the isolating membrane to be in contact with the skin of the user, and the subcutaneous soft needle sensor pierces the subcutaneous fat layer of the user, so that blood glucose data of the user can be obtained. The two stages are derived by utilizing the first stage, so that the blood sugar change rule with diabetes characteristics of a user can be monitored with higher probability, the consumption times of the subcutaneous soft needle sensor are fewer, the time for entering the CGM is shorter, and the consumable consumption caused by the subcutaneous soft needle sensor is greatly reduced. The controller presumes the probability of the user suffering from diabetes according to the sign data of the user and the blood sugar change data acquired by the subcutaneous soft needle sensor. A low pain level and low cost long-term detection and prediction process is achieved and a higher accuracy is achieved.
Further, the physical sign sensor comprises a blood oxygen saturation sensor, a heart rate pulse sensor and a bioelectrical impedance sensor.
The beneficial effects are that the insulin resistance of diabetes can produce long-term hypoxia condition, and heart rate is reduced or is changed due to the abnormal function of autonomic nerves. The bioelectrical impedance sensor can judge the probability of diabetes occurrence from obesity by feeding back body fat rate through electric impedance.
Further, the wearing carrier is also provided with an inertial sensor and a gyroscope, and the controller is used for judging the quantity of the user motion according to the acquired data of the inertial sensor and the gyroscope.
The intelligent diabetes mellitus control device has the beneficial effects that insufficient quantity of motion is one of factors causing diabetes mellitus, and the quantity of motion of a user can be fed back by utilizing the shaking amplitude frequency and the like of the body or limbs of the user through the inertial sensor and the gyroscope, so that the probability of occurrence of diabetes mellitus of the user is reflected on a motion level.
Further, the neural network is used for training based on the sign data, the movement quantity data and the blood sugar change rule of the diabetes cause of the sample crowd, the neural network is used for training based on the sign data, the movement quantity data, the blood sugar change rule and the diabetes diagnosis relation of the sample crowd, the neural network is used for inputting the user sign data and the movement quantity data acquired by the sign sensor and outputting the blood sugar change rule of the diabetes cause, and the neural network is used for inputting the user sign data, the movement quantity data and the blood sugar change data acquired by the subcutaneous soft needle sensor and outputting the probability of the user diagnosis of diabetes.
The neural network has the beneficial effects that after the exercise amount data of the user is obtained, the neural network can be added with the exercise amount data for training, so that the blood sugar change rule and the probability of diagnosing diabetes are predicted based on the comprehensive effects of the sign data and the exercise amount data.
Further, the controller is also used to enter the user's demographic characteristics, medical history, and medical history.
The method has the beneficial effects that basic demographic characteristics, medical history and medicine history of a user can influence the probability of the user suffering from diabetes besides physical sign data and movement quantity data, but related information is difficult to acquire by using a sensor, so that the information is acquired by inputting by using a controller.
Further, demographic characteristics include age, sex, height, weight, family genetic lineage.
The method has the beneficial effects that the age, the sex, the height, the weight and the family genetic pedigree can feed back the probability of the user suffering from diabetes, the age and the sex can feed back the functional aging condition and the general body structure of the user, the body height and the weight can feed back the obesity degree of the user, and the family genetic pedigree can feed back whether the user is a potential type II diabetes gene carrier or not.
Further, the neural network is trained based on the physical sign data, demographic characteristics, medical history, medicine history, exercise quantity data and the blood sugar change rule of the diabetes cause of the sample crowd, the neural network is trained based on the physical sign data, demographic characteristics, medical history, medicine history, exercise quantity data, the blood sugar change rule and the diabetes diagnosis relation of the sample crowd, the neural network is used for inputting the physical sign data, demographic characteristics, medical history, medicine history and exercise quantity data of a user collected by the physical sign sensor and outputting the blood sugar change rule of the diabetes cause, and the neural network is used for inputting the physical sign data, demographic characteristics, medical history, medicine history, exercise quantity data and the blood sugar change data collected by the subcutaneous soft needle sensor and outputting the probability of the user to diagnose the diabetes.
The method has the beneficial effects that after demographic characteristics, medical history and medicine history data of a user are obtained, the neural network can be trained by adding the demographic characteristics, the medical history and the medicine history data, so that the blood sugar change rule and the probability of diagnosing diabetes are predicted based on the comprehensive effects of the sign data, the demographic characteristics, the medical history, the medicine history and the exercise quantity data.
Further, a skin-friendly layer is arranged on one side of the wearing carrier, which is contacted with the skin of the user, and a plurality of ventilation holes are formed in the skin-friendly layer.
The soft needle sensor has the beneficial effects that as the soft needle of the soft needle sensor can penetrate into the subcutaneous fat layer of a user, the wearing carrier can be in direct contact with the skin of the user, the skin-friendly layer can improve the contact experience of the wearing carrier and the user, the ventilation holes can improve ventilation property, and the comfort level of the user is improved.
Further, one side of the subcutaneous soft needle sensor, which is far away from the telescopic piece, is provided with an adhesive dressing, one side of the isolating film, which is close to the telescopic piece, is provided with an anti-adhesive layer, the subcutaneous soft needle sensor is detachably connected with the telescopic piece, and the telescopic piece is in a non-self-locking state after the soft needle of the subcutaneous soft needle sensor is implanted into the subcutaneous fat layer of a user.
The subcutaneous soft needle sensor has the beneficial effects that although the wearing carrier is fixed on the body or limb of a user, the wearing carrier still can move with the skin of the user to a certain extent, and the detection of the subcutaneous soft needle sensor is easily affected. The adhesive dressing can fix the skin of a user after the soft needle is pierced so as to stabilize the state of the soft needle, the anti-sticking layer can reduce the probability that the adhesive dressing is stuck to the isolating membrane when the isolating membrane is broken, the subcutaneous soft needle sensor is detachably connected with the telescopic piece, and the telescopic piece can be reused by replacing the subcutaneous soft needle sensor and the isolating membrane. The telescopic piece is in a non-self-locking state after the soft needle of the subcutaneous soft needle sensor is implanted into the subcutaneous fat layer of a user, so that the influence of the movement of the wearing carrier on the subcutaneous soft needle sensor can be reduced.
Further, the wearing carrier is one of a waistband, a leg ring, an arm ring and a wrist strap.
The portable electronic device has the beneficial effects that the wearing carrier can be one of a waistband, a leg ring, an arm ring and a wrist strap according to the adaptation environment of each sensor so as to provide a good detection basis.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is an isometric view of an embodiment of an apparatus for predicting diabetes using diabetes system big data according to the present invention;
FIG. 2 is a schematic view of the inside of a wearable device according to an embodiment of the present invention using diabetes system big data to predict diabetes;
Fig. 3 is a schematic cross-sectional view of a housing box of an embodiment of the apparatus for predicting diabetes using big data of a diabetes system according to the present invention.
The reference numerals in the attached drawings of the specification comprise a wearer 1, a subcutaneous soft needle sensor 2, a physical sign sensor 3, a receiving box 4, a separation film 5, a telescopic piece 6, an adhesive dressing 7, a skin-friendly layer 8.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. 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.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, unless explicitly stated or limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected, mechanically connected, electrically connected, directly connected, indirectly connected via an intervening medium, or in communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
The following is a further detailed description of the embodiments:
example 1:
As shown in figures 1-3, the device for predicting diabetes by using big data of a diabetes system comprises a wearer 1 and a controller, wherein the controller can be connected with signals in a wired or wireless mode.
The wearing device 1 comprises a wearing carrier, the wearing carrier is a waistband, the waistband is an elastic belt, a plurality of sign sensors 3 are fixedly bonded on the wearing carrier, the sign sensors 3 comprise blood oxygen saturation sensors, heart rate pulse sensors and bioelectrical impedance sensors, an inertial sensor and a gyroscope are fixedly bonded on the wearing carrier, and a controller is used for judging the user exercise amount according to collected data of the inertial sensor and the gyroscope.
The controller is also used to enter the user's demographic characteristics, medical history, and medical history. Demographic characteristics include age, sex, height, weight, familial genetic lineage.
The wearing carrier is fixedly adhered with a receiving box 4, an opening is formed in the receiving box 4, an isolating film 5 is fixedly adhered in the opening, a telescopic piece 6 is fixedly adhered in the receiving box 4, the telescopic piece 6 is a miniature electric push rod, and a subcutaneous soft needle sensor 2 is detachably connected to an output shaft of the telescopic piece 6.
The controller is internally preset with a trained neural network, the neural network is trained based on physical sign data, demographic characteristics, medical history, medicine history, exercise quantity data and blood sugar change rules of diabetes causes of sample groups, the neural network is trained based on physical sign data, demographic characteristics, medical history, medicine history, exercise quantity data, blood sugar change rules and diabetes diagnosis confirming relations of the sample groups, the neural network is used for inputting the physical sign data, demographic characteristics, medical history, medicine history and exercise quantity data of users collected by the physical sign sensor 3 and outputting the blood sugar change rules of the diabetes causes, and when the blood sugar change rules meet preset judging values, the controller controls the telescopic piece 6 to drive the subcutaneous soft needle sensor 2 to break the isolating membrane 5, so that the soft needle of the subcutaneous soft needle sensor 2 is implanted into the subcutaneous fat layer of the users.
The neural network is used for inputting physical sign data, demographic characteristics, medical history, medicine history, exercise quantity data and blood sugar change data acquired by the subcutaneous soft needle sensor 2 of the user and outputting the probability of the user diagnosing diabetes.
The prediction of diabetes is divided into two stages, one stage collects conventional sign information by means of the sign sensor 3 to feed back the physical condition of a user, the part is carried out by the sensors such as the sign sensor 3, consumable materials are not required to be consumed, long-term average spreading cost is low, and the state with the longest average maintaining time in data collection is also achieved.
Insulin resistance in diabetes may produce a long-term hypoxic condition and result in decreased heart rate or a change in the heart rate due to abnormal autonomic nerve function. The bioelectrical impedance sensor can judge the probability of diabetes occurrence from obesity by feeding back body fat rate through electric impedance.
The insufficient quantity of motion is one of the factors causing diabetes, and the quantity of motion of the user can be fed back by using the shaking amplitude frequency of the body or the limbs of the user through the inertial sensor and the gyroscope, so that the probability of occurrence of diabetes of the user is reflected on the motion level.
After the exercise amount data of the user is obtained, the neural network can be added with the exercise amount data for training, so that the blood sugar change rule and the probability of diagnosing diabetes are predicted based on the comprehensive effect of the sign data and the exercise amount data.
The controller performs big data learning through the neural network to build three-dimensional data, demographic characteristics, medical history, medicine history, exercise quantity data and blood sugar change rules of diabetes cause for training, and when the physical sign data change state of a user can lead to obvious diabetes blood sugar change rules, the controller enters two stages.
The two stages can continuously monitor the blood sugar of the user by ejecting the subcutaneous soft needle sensor 2. The soft needle is short and thin compared with the fingertip blood taking needle, the pain feeling of the soft needle is approximately between no pain feeling and mosquito biting pain feeling according to different users, so that the user has lower detection willingness due to pain, and the risk of infection is extremely low and the safety is higher because the soft needle only reaches the subcutaneous fat layer of the user. In one stage, the subcutaneous soft needle sensor 2 is stored in the storage box 4, so that the effectiveness of the subcutaneous soft needle sensor 2 can be ensured for a long time, and the external environment is isolated through the isolating membrane 5 to prevent the subcutaneous soft needle sensor 2 from being polluted. When the two phases are entered, the output shaft of the telescopic member 6 is extended, so that the subcutaneous soft needle sensor 2 breaks the isolating membrane 5 to be in contact with the skin of the user and pierces the subcutaneous fat layer of the user to acquire blood glucose data of the user. The two stages are derived by utilizing the first stage, so that the blood sugar change rule with diabetes characteristics of a user can be monitored with higher probability, the effectiveness is higher, the consumption times of the subcutaneous soft needle sensor 2 are fewer, the time for entering the CGM is shorter, and the consumable consumption caused by the subcutaneous soft needle sensor 2 is greatly reduced. The controller presumes the probability of the user suffering from diabetes based on the user's physical sign data, demographic characteristics, medical history, exercise amount data, and blood glucose change data collected by the subcutaneous soft needle sensor 2. A low pain level and low cost long-term detection and prediction process is achieved and a higher accuracy is achieved.
Example 2:
the difference from the above embodiment is that the skin-friendly layer 8 is provided on the side of the wearing carrier contacting the skin of the user, and a plurality of ventilation holes are provided on the skin-friendly layer 8.
Because soft needle of soft needle sensor can pierce user's subcutaneous fat layer, consequently wear the carrier and can with user's skin direct contact, skin layer 8 can improve and wear the contact experience of carrier and user, and the bleeder vent can promote the gas permeability, promotes user's comfort level.
Example 3:
The difference from the above embodiment is that the controller is also used to control the retraction of the retraction member 6 to withdraw the subcutaneous soft needle sensor 2 before the expiration of the subcutaneous soft needle sensor 2 has been reached.
There is a failure period for the subcutaneous soft needle sensor 2, but the user may not know that the soft needle of the subcutaneous soft needle sensor 2 is still in the subcutaneous fat layer, so the controller will withdraw the subcutaneous soft needle sensor 2 with the telescoping member 6 before the failure period has arrived, to reduce the risk of complications.
Example 4:
The difference from the above embodiment is that the side of the subcutaneous soft needle sensor 2 far away from the telescopic member 6 is provided with an adhesive dressing 7, the side of the isolating film 5 near the telescopic member 6 is provided with an anti-adhesive layer, the subcutaneous soft needle sensor 2 is detachably connected with the telescopic member 6, and the telescopic member 6 is in a non-self-locking state after the soft needle of the subcutaneous soft needle sensor 2 is implanted into the subcutaneous fat layer of a user.
Although the wearing carrier is fixed on the body or limb of the user, the wearing carrier may still move with the skin of the user, and the detection of the subcutaneous soft needle sensor 2 is easily affected. The adhesive dressing 7 can fix the skin of a user after the soft needle is pierced so as to stabilize the state of the soft needle, the anti-sticking layer can reduce the probability that the adhesive dressing 7 is stuck to the isolation film 5 when the isolation film 5 is burst, the subcutaneous soft needle sensor 2 is detachably connected with the telescopic piece 6, and the telescopic piece 6 can be reused by replacing the subcutaneous soft needle sensor 2 with the isolation film 5. The telescopic member 6 is in a non-self-locking state after the soft needle of the subcutaneous soft needle sensor 2 is implanted into the subcutaneous fat layer of the user, so that the influence of the movement of the wearing carrier on the subcutaneous soft needle sensor 2 can be reduced.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the invention.

Claims (10)

Translated fromChinese
1.一种利用糖尿病系统大数据预测糖尿病的装置,其特征在于,包括佩戴器(1)和控制器;1. A device for predicting diabetes using big data from a diabetes system, comprising a wearer (1) and a controller;佩戴器(1)包括佩戴载体,佩戴载体上设有若干体征传感器(3),佩戴载体上设有收置盒(4),收置盒(4)上设有开口,开口内设有隔离膜(5),收置盒(4)内设有伸缩件(6),伸缩件(6)的输出轴上设有皮下软针传感器(2);The wearer (1) comprises a wear carrier, a plurality of vital sign sensors (3) are provided on the wear carrier, a storage box (4) is provided on the wear carrier, an opening is provided on the storage box (4), an isolation membrane (5) is provided in the opening, a telescopic member (6) is provided in the storage box (4), and a subcutaneous soft needle sensor (2) is provided on the output shaft of the telescopic member (6);控制器内预设有训练后的神经网络,神经网络基于样本人群的体征数据与糖尿病致因的血糖变化规律进行训练,神经网络基于样本人群的体征数据、血糖变化规律与糖尿病确诊关系进行训练;神经网络用于输入体征传感器(3)采集的用户体征数据,输出糖尿病致因的血糖变化规律;当血糖变化规律符合预设判断值后,控制器控制伸缩件(6)驱动皮下软针传感器(2)顶破隔离膜(5),使皮下软针传感器(2)的软针植入用户皮下脂肪层;A trained neural network is preset in the controller, and the neural network is trained based on the physical sign data of a sample population and the blood sugar change pattern caused by diabetes. The neural network is trained based on the physical sign data of the sample population, the blood sugar change pattern and the relationship between the diagnosis of diabetes; the neural network is used to input the user's physical sign data collected by the physical sign sensor (3) and output the blood sugar change pattern caused by diabetes; when the blood sugar change pattern meets the preset judgment value, the controller controls the telescopic member (6) to drive the subcutaneous soft needle sensor (2) to break through the isolation membrane (5), so that the soft needle of the subcutaneous soft needle sensor (2) is implanted into the user's subcutaneous fat layer;神经网络用于输入用户体征数据、皮下软针传感器(2)采集的血糖变化数据,输出用户确诊糖尿病的概率。The neural network is used to input the user's physical sign data and the blood sugar change data collected by the subcutaneous soft needle sensor (2), and output the probability of the user being diagnosed with diabetes.2.根据权利要求1所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,体征传感器(3)包括血氧饱和度传感器、心率脉搏传感器、生物电阻抗传感器。2. The device for predicting diabetes using diabetes system big data according to claim 1 is characterized in that the physical sign sensor (3) includes a blood oxygen saturation sensor, a heart rate and pulse sensor, and a bioelectrical impedance sensor.3.根据权利要求2所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,佩戴载体上还设有惯性传感器和陀螺仪,控制器用于根据惯性传感器和陀螺仪的采集数据判断用户运动量。3. The device for predicting diabetes using diabetes system big data according to claim 2 is characterized in that an inertial sensor and a gyroscope are also provided on the wearable carrier, and the controller is used to determine the user's exercise amount based on the data collected by the inertial sensor and the gyroscope.4.根据权利要求3所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,神经网络基于样本人群的体征数据、运动量数据与糖尿病致因的血糖变化规律进行训练,神经网络基于样本人群的体征数据、运动量数据、血糖变化规律与糖尿病确诊关系进行训练;神经网络用于输入体征传感器(3)采集的用户体征数据和运动量数据,输出糖尿病致因的血糖变化规律;神经网络用于输入用户体征数据、运动量数据、皮下软针传感器(2)采集的血糖变化数据,输出用户确诊糖尿病的概率。4. The device for predicting diabetes using diabetes system big data according to claim 3 is characterized in that the neural network is trained based on the physical sign data, exercise data and blood sugar change patterns of the sample population, and the relationship between the physical sign data, exercise data, blood sugar change patterns and diabetes diagnosis of the sample population; the neural network is used to input the user's physical sign data and exercise data collected by the physical sign sensor (3) and output the blood sugar change patterns of the diabetes cause; the neural network is used to input the user's physical sign data, exercise data, and blood sugar change data collected by the subcutaneous soft needle sensor (2) and output the probability of the user being diagnosed with diabetes.5.根据权利要求4所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,控制器还用于录入用户的人口学特征、病史和药史。5. The device for predicting diabetes using diabetes system big data according to claim 4, wherein the controller is further used to input the user's demographic characteristics, medical history, and medication history.6.根据权利要求5所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,人口学特征包括年龄、性别、身高、体重、家族遗传谱系。6. The device for predicting diabetes using diabetes system big data according to claim 5, wherein the demographic characteristics include age, gender, height, weight, and family genetic pedigree.7.根据权利要求6所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,神经网络基于样本人群的体征数据、人口学特征、病史、药史、运动量数据与糖尿病致因的血糖变化规律进行训练,神经网络基于样本人群的体征数据、人口学特征、病史、药史、运动量数据、血糖变化规律与糖尿病确诊关系进行训练;神经网络用于输入体征传感器(3)采集的用户体征数据、人口学特征、病史、药史和运动量数据,输出糖尿病致因的血糖变化规律;神经网络用于输入用户体征数据、人口学特征、病史、药史、运动量数据、皮下软针传感器(2)采集的血糖变化数据,输出用户确诊糖尿病的概率。7. The device for predicting diabetes using diabetes system big data according to claim 6 is characterized in that the neural network is trained based on the physical sign data, demographic characteristics, medical history, medication history, exercise data of the sample population and the blood sugar change pattern caused by diabetes, and the neural network is trained based on the physical sign data, demographic characteristics, medical history, medication history, exercise data, blood sugar change pattern and the relationship between diabetes diagnosis; the neural network is used to input the user's physical sign data, demographic characteristics, medical history, medication history and exercise data collected by the physical sign sensor (3), and output the blood sugar change pattern caused by diabetes; the neural network is used to input the user's physical sign data, demographic characteristics, medical history, medication history, exercise data, and blood sugar change data collected by the subcutaneous soft needle sensor (2), and output the probability of the user being diagnosed with diabetes.8.根据权利要求7所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,佩戴载体与用户皮肤接触的一侧设有亲肤层(8),亲肤层(8)上开设有若干透气孔。8. The device for predicting diabetes using diabetes system big data according to claim 7 is characterized in that a skin-friendly layer (8) is provided on the side of the wearable carrier that contacts the user's skin, and a plurality of air holes are provided on the skin-friendly layer (8).9.根据权利要求8所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,皮下软针传感器(2)远离伸缩件(6)的一侧设有粘性敷料(7),隔离膜(5)靠近伸缩件(6)的一侧设有防粘层,皮下软针传感器(2)与伸缩件(6)可拆卸连接,伸缩件(6)在皮下软针传感器(2)的软针植入用户皮下脂肪层后为非自锁状态。9. The device for predicting diabetes using big data of a diabetes system according to claim 8 is characterized in that a sticky dressing (7) is provided on the side of the subcutaneous soft needle sensor (2) away from the telescopic part (6), and an anti-sticking layer is provided on the side of the isolation membrane (5) close to the telescopic part (6). The subcutaneous soft needle sensor (2) and the telescopic part (6) are detachably connected, and the telescopic part (6) is in a non-self-locking state after the soft needle of the subcutaneous soft needle sensor (2) is implanted into the subcutaneous fat layer of the user.10.根据权利要求9所述的利用糖尿病系统大数据预测糖尿病的装置,其特征在于,佩戴载体为腰带、腿环、臂环、腕带中的一种。10. The device for predicting diabetes using diabetes system big data according to claim 9, wherein the wearable carrier is one of a waist belt, a leg ring, an arm ring, and a wristband.
CN202510670811.0A2025-05-232025-05-23 A device for predicting diabetes using big data from a diabetes systemPendingCN120616515A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202510670811.0ACN120616515A (en)2025-05-232025-05-23 A device for predicting diabetes using big data from a diabetes system

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202510670811.0ACN120616515A (en)2025-05-232025-05-23 A device for predicting diabetes using big data from a diabetes system

Publications (1)

Publication NumberPublication Date
CN120616515Atrue CN120616515A (en)2025-09-12

Family

ID=96950939

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202510670811.0APendingCN120616515A (en)2025-05-232025-05-23 A device for predicting diabetes using big data from a diabetes system

Country Status (1)

CountryLink
CN (1)CN120616515A (en)

Similar Documents

PublicationPublication DateTitle
EP3664702B1 (en)Systems and methods for collecting physiological information of a user
US10182748B2 (en)System for the self-monitoring and regulation of blood glucose
CN104093358B (en)Method and apparatus for detecting hypoglycemic episodes
EP1841476B1 (en)Fluid delivery device with integrated monitoring of physiological characteristics
CN102281816B (en)Method and apparatus for determining critical care parameters
KR102349961B1 (en)Health care apparatus and method of operating of the apparatus
KR102325887B1 (en)System and Method for Blood Glucose Control
US12318206B2 (en)Blood glucose states based on sensed brain activity
US11992310B2 (en)Personal health monitoring system, multiple user health monitoring system, and method
CN113413143A (en)Insulin infusion self-adaptive control system
US11284816B2 (en)Multi-analyte continuous glucose monitoring
US20210177313A1 (en)Continuous health monitoring system
CN120616515A (en) A device for predicting diabetes using big data from a diabetes system
KR102564501B1 (en)Wearable device and method for controlling the same
WO2022180184A1 (en)Continuous health monitoring system
CN215017485U (en)Health management device for diabetic patients
KR20220124942A (en) Real-time health monitoring system using continuous blood glucose meter
EP4461217A1 (en)Monitoring a kidney-related condition
CN108095707A (en)Four high population health nursing remote monitoring systems
KR20130047077A (en)Personalized blood pressure management system
Ładyżyński et al.Preventive systems for the late complications of diabetes
WO2025064934A1 (en)Methods, systems, and apparatuses for distinguishing electrical biosignals
TR2025012893A1 (en) SMART BREATHING DEVICE THAT DIAGNOSES DIABETES BY SMELL
CN117598685A (en)Respiration detection device, method and system acting on nerve regulation and control

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication

[8]ページ先頭

©2009-2025 Movatter.jp