Analyte sensor-based data processing method, device, system and medium

Abstract

The invention discloses a data processing method based on an analyte sensor and a device, a system and a medium thereof, the method comprises the following steps: obtaining first analyte data of a target object, the first analyte data comprising a first analyte level which changes with time and is collected by the analyte sensor when the target object wears the analyte sensor; obtaining second analyte data of the target object, the second analyte data comprising at least one second analyte level, the second analyte data not collected by the analyte sensor, the second analyte level being a single-point analyte level; and predicting fluctuation data of the analyte in the second analyte data before and / or after the acquisition time of the second analyte level based on the first analyte data. Therefore, the fluctuation data of the analyte can be obtained at lower cost.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a data processing method based on an analyte sensor and a device, system and medium thereof. Background Art

[0002] With the increasing incidence of diabetes, diabetes has become a public health problem worldwide. Diabetes is a syndrome of metabolic disorders of sugar, protein, fat, water and electrolytes. It is caused by various pathogenic factors such as genetic factors, immune dysfunction, microbial infection and its toxins acting on the body, leading to pancreatic islet dysfunction, insulin resistance, etc. If diabetes is not well controlled, it may cause some complications.

[0003] Currently, users can obtain single-point blood sugar (also called spot blood sugar) by pricking their fingers every day or continuously monitor glucose through a glucose sensor. Existing glucose sensors generally use the signal generated by the chemical reaction between the enzyme on the glucose sensor and the glucose in the body fluid to obtain the glucose concentration. Some glucose sensors can also use other methods (such as light signals) to obtain the glucose concentration. If glucose can be monitored and the fluctuation trend of glucose can be obtained, glucose can be controlled and the occurrence of complications can be reduced.

[0004] However, although glucose sensors can continuously monitor glucose, they have a limited service life. Generally, the glucose sensor or at least part of its components needs to be replaced regularly, which is a large expense for users. Isolated single-point blood glucose cannot obtain the fluctuation trend of glucose. Summary of the invention

[0005] The present disclosure is made in view of the above-mentioned prior art conditions, and its purpose is to provide a data processing method based on an analyte sensor and its device, system and medium that can obtain fluctuation data of an analyte at a relatively low cost.

[0006] To this end, the first aspect of the present disclosure provides a data processing method based on a continuous analyte sensor, the analyte sensor is used to continuously monitor the first analyte level of a target object, the data processing method includes acquiring the first analyte data of the target object, the first analyte data includes the first analyte level that changes over time collected by the analyte sensor when the target object wears the analyte sensor; acquiring the second analyte data of the target object, the second analyte data includes at least one second analyte level, the second analyte data is not collected by the analyte sensor, and the second analyte level is a single-point analyte level; and predicting the fluctuation data of the analyte before and / or after the collection time of the second analyte level in the second analyte data based on the first analyte data. In this case, the second analyte data is a single-point analyte level, and the acquisition cost is lower than that of the first analyte data, which is conducive to predicting the target fluctuation data at a lower cost. In addition, the first analyte data is collected by the analyte sensor when the target object wears it and changes over time. In this case, when the target fluctuation data is obtained in combination with the first analyte data, the fluctuation information of the first analyte level changing over time in the first analyte data can be used to predict the target fluctuation data, thereby overcoming the problem that the fluctuation trend of a single point analyte level cannot be or is difficult to predict.

[0007] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, the fluctuation data includes the fluctuation type of the analyte level, and the fluctuation type includes rising, falling and stable. Thus, the fluctuation type can basically meet the target object's demand for controlling the analyte.

[0008] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, the analyte sensor is a glucose sensor, the first analyte level is the glucose concentration in the blood obtained by the glucose sensor, and the second analyte level is the glucose concentration in the fingertip blood. This is conducive to predicting the fluctuation data of the glucose concentration at a lower cost.

[0009] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, a plurality of first time period first analyte waveforms are determined based on the first analyte data; a waveform segment related to a target daily time is identified from the first analyte waveforms of the plurality of first time periods as a target waveform segment at the acquisition moment, the target daily time being the daily time corresponding to the acquisition moment of the second analyte level, the daily time being the moment before and / or after the daily event of the target object; and the fluctuation data is predicted based on the target waveform segment. In this case, the behavior of the target object corresponding to the daily time can reflect the living habits of the target object, and the use of daily time to screen the target waveform segment is more conducive to obtaining the second analyte level of the target object on the one hand, and on the other hand, compared with randomly selected time, it can reduce the interference of the random behavior of the target object on the analyte fluctuation. In addition, it is more in line with the application scenario in which the target object controls the analyte.

[0010] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, daily time corresponding to a single first time period is obtained as historical daily time; historical daily time related to the target daily time is identified from the historical daily time of at least one first time period to obtain reference daily time; a waveform segment related to the reference daily time is intercepted from the first analyte waveform to which the reference daily time belongs as a reference waveform segment; and a reference waveform segment is selected from at least one of the reference waveform segments as the target waveform segment using the second analyte level.

[0011] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, a reference time period corresponding to a single reference daily time is determined, the reference time period is a time period before and / or after a single reference daily time, and the waveform segment associated with the reference daily time is a waveform segment within the reference time period. In this case, the reference time period is a time period before a single reference daily time, and the target fluctuation data before the acquisition moment can be obtained, so that the analyte level can be retrospectively analyzed. In addition, the reference time period is a time period after a single reference daily time, and the target fluctuation data after the acquisition moment can be obtained, which is beneficial for the target object to control the analyte to reduce abnormal analyte levels. In addition, the reference time period is a time period before and after a single reference daily time, which is beneficial for the target object to comprehensively consider the target fluctuation data before the acquisition moment when controlling the analyte according to the target fluctuation data after the acquisition moment, so as to improve the stability of analyte control.

[0012] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, the daily events include events related to meals and sleep events, and the daily time includes moments before and after events related to meals, and moments before sleep. In this case, the daily time is more consistent with the time nodes that the target object needs to monitor when controlling the analyte, which can make the predicted target fluctuation data more conducive to the analyte control of the target object.

[0013] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, the time after the event related to the meal is two hours after the event related to the meal. In this case, there are at least seven daily times that can basically cover the time nodes when the target object's daily analyte level may change.

[0014] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, it also includes generating a reminder message in response to identifying that the first analyte data needs to be updated, and the reminder message is used to remind the target object to wear a new analyte sensor again to obtain new first analyte data. In this case, the predicted target fluctuation data can be adapted to changes in the target object's living habits through updating.

[0015] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, the target waveform segments corresponding to the multiple second analyte levels within a single second time period are spliced ​​in chronological order to obtain the second analyte waveform of a single second time period, and the first analyte waveform of at least one first time period and the second analyte waveform of at least one second time period are compared to identify whether the first analyte data needs to be updated; and / or the number of failures in not identifying the target waveform segment is counted, and the first analyte data is identified based on the number of failures. Whether it is necessary to update; and / or the error rate of the fluctuation data is counted, and whether the first analyte data needs to be updated is identified based on the error rate. In this case, the gap between the second analyte waveform and the first analyte waveform can be intuitively obtained based on the analyte waveform. In addition, whether the first analyte data needs to be updated can be effectively identified based on the number of failures. In addition, whether the first analyte data needs to be updated can be objectively identified based on the error rate.

[0016] In addition, in the data processing method involved in the first aspect of the present disclosure, optionally, the fluctuation data is predicted only in response to the second analyte level being within a preset range. In this case, the prediction operation is relatively small, and the target object's need for controlling the analyte can be met with relatively small storage and computing overheads.

[0017] The second aspect of the present disclosure provides an integrated single-point analyte level measuring device, including a collection unit and a processing unit, wherein the collection unit is used to collect the single-point analyte level of the target object, and the processing unit is used to receive the single-point analyte level and determine the fluctuation data of the analyte before and / or after the collection time of the single-point analyte level by executing the data processing method involved in the first aspect of the present disclosure. In this case, the computing device of the multiplexing measurement device can reduce the communication with the outside of the measurement device on the one hand, thereby improving the stability of the measurement device, and can simplify the structural design on the other hand.

[0018] The third aspect of the present disclosure provides a monitoring system based on a single-point analyte level, including a measuring device and a processing device; the measuring device is used to measure the single-point analyte level of a target object and is connected to the processing device for communication; the processing device is used to receive the single-point analyte level and determine the fluctuation data of the analyte before and / or after the acquisition time of the single-point analyte level by executing the data processing method involved in the first aspect of the present disclosure. In this case, the coupling degree between the components of the monitoring system can be reduced by means of communication connection, which is conducive to flexible adjustment of the structural design of the monitoring system.

[0019] A fourth aspect of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the data processing method involved in the first aspect of the present disclosure is implemented.

[0020] According to the present disclosure, a data processing method based on an analyte sensor and a device, system and medium thereof are provided, which are capable of obtaining fluctuation data of an analyte at a relatively low cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Embodiments of the present disclosure will now be explained in further detail, by way of example only, with reference to the accompanying drawings.

[0022] in:

[0023] Figure 1 is a block diagram illustrating a single-point analyte level-based monitoring system to which examples of the present disclosure relate.

[0024] Figure 2 is a schematic diagram showing a fluctuation prediction environment involved in examples of the present disclosure.

[0025] Figure 3 is a block diagram showing a single-point analyte level measurement device according to examples of the present disclosure.

[0026] Figure 4 is an exemplary flow chart showing a data processing method involved in the examples of the present disclosure.

[0027] Figure 5 is an exemplary flow chart showing the predicted target fluctuation data involved in the examples of the present disclosure.

[0028] Figure 6 is a schematic diagram showing a first analyte waveform involved in examples of the present disclosure.

[0029] Figure 7 is an exemplary flow chart showing the process of identifying a target waveform segment according to an example of the present disclosure.

[0030] Figure 8 is an exemplary flow chart illustrating updating first analyte data according to examples of the present disclosure. DETAILED DESCRIPTION

[0031] Hereinafter, with reference to the accompanying drawings, the preferred embodiments of the present disclosure are described in detail. In the following description, the same symbols are given to the same parts, and repeated descriptions are omitted. In addition, the accompanying drawings are only schematic diagrams, and the ratio of the sizes of the parts to each other or the shapes of the parts, etc. may be different from the actual ones. It should be noted that the terms "including" and "having" in the present disclosure and any variations thereof, such as the processes, methods, systems, products or devices of a series of steps or units included or possessed are not necessarily limited to those steps or units clearly listed, but may include or have other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. All methods described in the present disclosure may be performed in any suitable order, unless otherwise indicated herein or clearly contradictory to the context.

[0032] The disclosed example relates to a data processing method based on an analyte sensor, which uses the continuous data of the analyte sensor to obtain the fluctuation data of the analyte corresponding to the single-point analyte level. In this way, the fluctuation data of the analyte can be obtained at a lower cost. In addition, the data processing method based on the analyte sensor involved in the disclosed example can also be referred to as a data processing method, a processing method, or a data analysis method. The data processing method involved in the disclosed example can be applied to the scene of controlling the analyte.

[0033] The analyte sensor of the disclosed examples can be used to continuously monitor the analyte level and the change of the analyte level in the body fluid of the target object over a period of time. In some examples, the analyte sensor can periodically measure and record the analyte level. For example, the analyte sensor can measure and record the analyte level every 1 minute, 2 minutes, 3 minutes, 5 minutes, 15 minutes or 20 minutes.

[0034] In addition, the analyte sensor can obtain a sensing electrical signal of the target object, the sensing electrical signal can match the actual analyte level of the target object's body fluid, and the analyte level obtained by processing the sensing electrical signal can be used as the analyte level of the target object's body fluid. In addition, the sensing electrical signal can be a signal related to an electrochemical reaction. Preferably, the sensing electrical signal can be a current signal. Thus, the sensing electrical signal can be converted into an analyte level more conveniently.

[0035] In some examples, when the analyte is glucose, the analyte sensor may be a glucose sensor, and the analyte level may be a glucose concentration. However, the examples disclosed herein may not be limited to glucose concentration. For example, by changing the analyte sensor, other body fluid component data other than glucose concentration may also be obtained. The body fluid components here may be, for example, acetylcholine, amylase, bilirubin, cholesterol, chorionic gonadotropin, creatine kinase, creatine, creatinine, DNA, fructosamine, glucose, glutamine, growth hormone, hormone, ketone body, lactate, oxygen, peroxide, prostate-specific antigen, prothrombin, RNA, thyroid stimulating hormone, troponin, etc.

[0036] Additionally, the single point analyte level may be a discrete analyte level. In some examples, the single point analyte level may be an analyte level obtained by measuring an analyte leaving a target object.

[0037] For the convenience of description, the analyte level obtained by the analyte sensor is referred to as the first analyte level, the single-point analyte level is referred to as the second analyte level, and the fluctuation data of the analyte corresponding to the acquisition time of the single-point analyte level is referred to as the target fluctuation data. In some examples, the target fluctuation data may be the fluctuation data of the analyte before and / or after the acquisition time of the single-point analyte level. Thus, the target object can be assisted in controlling the analyte according to the target fluctuation data.

[0038] For example, when the analyte level is glucose concentration, the first analyte level may be the glucose concentration in the blood obtained by the glucose sensor, and the second analyte level may be the single-point glucose concentration. For the glucose concentration in the blood, the first analyte level may also be referred to as continuous blood glucose, and the second analyte level may also be referred to as single-point blood glucose. In some examples, depending on the location of the collection, the second analyte level may be the glucose concentration in the fingertip blood (referred to as finger blood). In this case, the target fluctuation data of glucose is obtained through a single-point finger blood, which fits the scenario in which the target object monitors glucose by pricking a finger, and is conducive to improving the universality of obtaining the target fluctuation data.

[0039] In addition, the environment where the analyte sensor is located can be the body fluid of the target object. In some examples, the body fluid can be divided into intracellular fluid, plasma, and interstitial fluid, etc. Preferably, the body fluid used to continuously monitor the glucose concentration can be interstitial fluid (i.e., body fluid in the interstitial space). In this case, since the change in glucose concentration of the interstitial fluid can better reflect the situation of cell metabolism, the glucose concentration of the interstitial fluid can better reflect the change in glucose concentration in the blood.

[0040] The target object involved in the examples of the present disclosure may be an object with life characteristics. In some examples, the target object may be a patient suffering from diabetes, hypopituitarism, thyroid disease, or obesity.

[0041] For the convenience of description, some examples are described below using the analyte level as glucose concentration as an example. It should be noted that this does not limit the present disclosure. Unless there is a contradiction, the relevant description is also applicable to other analyte levels.

[0042] Examples of the present disclosure will be described in detail below with reference to the accompanying drawings. Figure 1 is a block diagram illustrating a single-point analyte level-based monitoring system 100 to which examples of the present disclosure relate. Figure 2 is a schematic diagram showing a fluctuation prediction environment involved in examples of the present disclosure.

[0043] refer to Figure 1 , the monitoring system 100 may include a measuring device 110 and a processing device 120. The measuring device 110 can be used to measure the second analyte level of the target object, and communicate with the processing device 120 to transmit the second analyte level. The processing device 120 can be used to receive the second analyte level and determine the target fluctuation data by executing the data processing method involved in the example of the present disclosure. In this case, the coupling degree between the components of the monitoring system 100 can be reduced by means of a communication connection, which is conducive to the flexible adjustment of the structural design of the monitoring system 100. Specifically, the measuring device 110 and the processing device 120 can be arranged independently in the corresponding computing device, and communicated through their respective communication components.

[0044] In some examples, the communication connection may be a wireless communication connection. Specifically, the measuring device 110 may have a wireless communication unit. For example, Bluetooth, WIFI, etc. Thus, data can be sent or received in a wireless communication manner. In this case, the measuring device 110 sends or receives data in a wireless communication manner, which can further reduce the coupling between the components of the monitoring system 100.

[0045] In some examples, the measuring device 110 can be a device for detecting an analyte leaving the target object. The measuring device 110 can have a detection port for receiving the analyte. Specifically, the analyte can be placed on a carrier medium such as a test strip, and then the carrier medium is inserted into the detection port to detect the analyte, thereby obtaining a second analyte level.

[0046] In some examples, when the analyte level is a glucose concentration, the measuring device 110 may be a fingertip blood glucose meter. The second analyte level may be a glucose concentration obtained by the fingertip blood glucose meter. For example, a fingertip is pierced with a disposable needle, a blood sample of the fingertip blood is obtained using a test strip or a straw, and the blood sample is placed in the detection port of the measuring device 110, and finally, the glucose concentration in the blood sample can be obtained.

[0047] As described above, the data processing method involved in the examples of the present disclosure can determine the target fluctuation data. Specifically, the data processing method involved in the examples of the present disclosure can obtain the target fluctuation data using the first analyte level collected by the analyte sensor 900. In some examples, after obtaining the first analyte level that changes over time within a certain period of time based on the analyte sensor 900, the data based on the analyte sensor 900 can meet the requirements of determining the target fluctuation data without wearing the analyte sensor 900. As a result, the target fluctuation data can be obtained at a lower cost.

[0048] refer to Figure 1 and Figure 2 In some examples, when the analyte level is glucose concentration, the analyte sensor 900 may be a glucose sensor, the measuring device 110 may be a finger blood collection device, and the processing device 120 may be a computing device (eg, a mobile device or a server).

[0049] Continue to refer Figure 2 In the context of glucose concentration fluctuation prediction, the target subject may wear the analyte sensor 900, and the analyte sensor 900 may continuously collect the glucose concentration of the target subject. Specifically, the analyte sensor 900 may be partially or completely placed under the skin of the target subject and react with glucose in the interstitial fluid to obtain the glucose concentration.

[0050] In some examples, after the target subject wears the analyte sensor 900 for a certain period of time, the glucose concentration collected by the analyte sensor 900 that varies with time may be obtained.

[0051] In some examples, the analyte sensor 900 can be disposed on an arm (see Figure 2 ), abdomen or thighs.

[0052] In some examples, analyte sensor 900 may be part of a continuous analyte monitoring system (e.g., a continuous glucose monitoring system), and analyte sensor 900 may continuously collect glucose concentration of a target object and transmit it to another part of the continuous analyte monitoring system (e.g., a receiving device) for processing.

[0053] Continue to refer Figure 2 In some examples, a measurement device 110 may be included in the fluctuation prediction environment. The measurement device 110 may be used to collect the second analyte level.

[0054] Continue to refer Figure 2 In some examples, a processing device 120 may be included in the fluctuation prediction environment. The processing device 120 may use the first analyte level collected by the analyte sensor 900 to obtain target fluctuation data.

[0055] Figure 3 is a block diagram showing a single-point analyte level measurement device 200 according to examples of the present disclosure.

[0056] In addition, in some examples, the measuring device 110 may also be built with a unit for acquiring target fluctuation data using the first analyte level acquired by the analyte sensor 900. That is, the measuring device 110 may acquire the second analyte level and acquire the target fluctuation data using the first analyte level acquired by the analyte sensor 900. For this reason, the example of the present disclosure also provides an integrated single-point analyte level measuring device 110, at which point, for the convenience of description, the measuring device 110 may be represented as the measuring device 200. In this case, the computing device of the multiplexing measuring device 200 can reduce the communication with the outside of the measuring device 200 on the one hand, thereby improving the stability of the measuring device 200, and on the other hand, simplify the structural design.

[0057] Specifically, refer to Figure 3 The measuring device 200 may include a collection unit 210 and a processing unit 220. The collection unit 210 may be used to collect the second analyte level of the target object, and the processing unit 220 may be used to receive the second analyte level and determine the target fluctuation data through the data processing method involved in the example of the present disclosure.

[0058] Figure 4 is an exemplary flow chart showing a data processing method involved in the examples of the present disclosure.

[0059] As described above, the data processing method involved in the example of the present disclosure can determine the target fluctuation data. The target fluctuation data can be the fluctuation data of the analyte before and / or after the collection time of the second analyte level. For this purpose, the example of the present disclosure also provides a first exemplary process of the data processing method.

[0060] refer to Figure 4 , the first exemplary process may include acquiring first analyte data of a target object (step S101), acquiring second analyte data of the target object (step S102), and predicting target fluctuation data corresponding to the second analyte level in the second analyte data based on the first analyte data (step S103). In this case, the second analyte data is a single-point analyte level, and the acquisition cost is lower than that of the first analyte data, which is conducive to predicting the target fluctuation data at a lower cost.

[0061] In some examples, in step S101, the first analyte data may include a plurality of first analyte levels collected by the analyte sensor 900. The plurality of first analyte levels may vary over time. In addition, the first analyte data may be collected by the analyte sensor 900 when the target object wears the device. In this case, when the target fluctuation data is obtained in combination with the first analyte data, the fluctuation information of the first analyte level that varies over time in the first analyte data can be used to predict the target fluctuation data, thereby overcoming the problem that the fluctuation trend of a single point analyte level cannot be or is difficult to predict.

[0062] In some examples, the first analyte data may be periodic data. Specifically, the first analyte data may include the first analyte levels of multiple first time periods. In some examples, the first time period may be 1 day. For example, if the life span of an analyte sensor 900 is 14 days, the first analyte data may include the first analyte levels of 14 days. In other examples, the first time period may also be half a day or several hours. In addition, the second time period (described later) may be the same as the first time period.

[0063] In some examples, in step S101 , the first analyte data may be preprocessed, and accordingly, subsequent steps may use the preprocessed first analyte data as input.

[0064] In some examples, in the preprocessing, random errors in the first analyte data may be filtered out by filtering, thereby reducing the interference of abnormal data on the predicted target fluctuation data.

[0065] In some examples, during preprocessing, the first analyte data may be normalized, thereby improving the stability of the first analyte data.

[0066] In some examples, in step S102, the second analyte data may include at least one second analyte level. As described above, the second analyte level is a single-point analyte level. In some examples, the second analyte data may not be collected by the analyte sensor 900. Thus, it is possible to support the prediction of target fluctuation data when the analyte sensor 900 is not worn. In some examples, the acquisition frequency of the second analyte data may be lower than the acquisition frequency of the analyte sensor 900 within the same time. For example, the analyte sensor 900 may obtain a first analyte level every 5 minutes, and for the second analyte data, up to 7 second analyte levels may be obtained per day. In some examples, the second analyte data may be collected by the measuring device 110, and the specific content is shown in the relevant description of the measuring device 110.

[0067] In some examples, the collection time of the second analyte level may be a specific time. The specific time may be a time that is conducive to monitoring the analyte to control the analyte. Specifically, the collection time of the second analyte level may have a corresponding daily time.

[0068] In other examples, the collection time of the second analyte level may not have a corresponding daily time. That is, the collection time may be random. In some examples, the daily time near the random collection time may be used to predict the target fluctuation data (described later).

[0069] In some examples, the daily time may be moments before and / or after daily events of the target object.

[0070] In some examples, the similar daily time may be close to the analyte fluctuation corresponding to the daily event. For example, assuming that the daily time is before lunch, the daily time similar to the daily time may be before dinner. In some examples, the similar daily time may be the same moment of the daily event but different distances relative to the moment of the daily event. For example, if the daily event is lunch and the moment of the daily event is after lunch, if the daily time is two hours after lunch, the daily time similar to the daily time may be one hour after lunch, three hours after lunch, etc.

[0071] In some examples, daily events may be events that may occur periodically in the daily life of the target object. That is, daily events may be any events that may occur periodically. Thus, the probability of obtaining target fluctuation data can be increased. In some examples, daily events may be selected according to the target object's own living habits. In this case, using daily events suitable for the target object to predict the target fluctuation data can make the predicted target fluctuation data more personalized and more accurate.

[0072] In some examples, daily events may include events related to meals and sleeping events. In this case, daily events are universal and can make the predicted target fluctuation data suitable for most target objects. In addition, events related to meals may include breakfast, lunch, and dinner.

[0073] In some examples, daily events may also include fasting events. That is, events when the target subject remains fasting. In this case, the fasting analyte level is an important indicator for the target subject to analyze its own analyte level, and considering fasting events can further improve the validity of the predicted target fluctuation data. In addition, fasting events can last for a period of time.

[0074] In some examples, daily events may also include exercise events and medication events. In this case, it may be helpful for target subjects who have regular exercise and medication to more accurately predict target fluctuation data.

[0075] In some examples, for the case where daily events may include events related to meals and sleep events, daily time may include the moments before and after the events related to meals, and the moments before going to bed. In this case, daily time is more in line with the time nodes that the target object needs to monitor when controlling the analyte, and can make the predicted target fluctuation data more conducive to the analyte control of the target object. In addition, as described above, events related to meals may include breakfast, lunch and dinner. In this case, if daily time includes the moments before and after the events related to meals, and the moments before going to bed, there are at least seven daily times, which can basically cover the time nodes when the target object's daily analyte level may change.

[0076] In addition, the moment before the meal-related event can be the moment of starting the meal. In addition, the moment after the meal-related event can be a moment within a certain time after the meal. In some examples, for the analyte level being glucose concentration, the moment after the meal-related event can be two hours after the meal-related event. In this case, the glucose concentration at daily time can represent the effect of the target object's meal on the glucose concentration, thereby making the predicted target fluctuation data more conducive to the target object's glucose control.

[0077] In some examples, for the analyte level being glucose concentration, daily time may include at least one of the moments in a fasting event, before breakfast, two hours after breakfast, before lunch, two hours after lunch, before dinner, two hours after dinner, and before bedtime, and the specific time may be selected based on the target subject's own situation.

[0078] As described above, the second analyte data may include at least one second analyte level.

[0079] In some examples, in step S103, when a second analyte level is obtained, the target fluctuation data corresponding to the second analyte level can be predicted. In this case, it is possible to support the prediction of the target fluctuation data using a minimum number of second analyte levels, which is beneficial to reducing the number of times the target object collects the second analyte level and reducing the inconvenience caused by collecting the second analyte level.

[0080] In addition, when obtaining a second analyte level, predicting the target fluctuation data corresponding to the second analyte level is more suitable for the scenario in which the target object obtains the second analyte level. For example, when the analyte level is glucose concentration, the target object generally obtains one finger blood by pricking the finger once. If finger blood at multiple times is to be obtained, the finger needs to be pricked multiple times at different times. Therefore, the number of times of pricking the finger does not need to be too frequent, which is more in line with the actual application scenario.

[0081] In some examples, in step S103, when a certain number of second analyte levels are obtained, the target fluctuation data corresponding to the current second analyte level may be predicted. In this case, more second analyte levels may be used to predict the target fluctuation data of the current second analyte level, which is conducive to improving the accuracy of the predicted target fluctuation data.

[0082] In some examples, in step S103, the target fluctuation data may be predicted only in response to the second analyte level being within a preset range. The preset range may be close to or equal to the abnormal range. In this case, the prediction operation is less, and the target object's need to control the analyte can be met with relatively small storage and computational overheads. For example, when the glucose concentration is approaching a low blood sugar value, whether the subsequent glucose concentration will continue to decrease, and when the glucose concentration is approaching a high blood sugar value, whether the subsequent glucose concentration will continue to increase, these are the target objects that are more concerned.

[0083] In addition, the abnormal range can be complementary to the normal range. The normal range can be the range of normal analyte levels. For example, for the analyte level being glucose concentration, the normal range can be 3.9 mmol / L (millimoles per liter) to 7.8 mmol / L.

[0084] In some examples, the target fluctuation data may include the fluctuation type of the analyte level. In this case, the target object may obtain information of the fluctuation information of the analyte that is of greater concern to the target object, which may assist the target object in analyzing the fluctuation trend of the analyte before and / or after the acquisition time.

[0085] In some examples, the fluctuation type may include rising, falling, and stable. Thus, the fluctuation type can basically meet the target object's need to control the analyte. For example, for the target fluctuation data after the acquisition time, if the fluctuation type is rising, the target object can determine whether to perform a process of lowering the analyte level (e.g., lowering blood sugar) according to the analyte level at the acquisition time, if the fluctuation type is falling, the target object can determine whether to perform a process of raising the analyte level (e.g., raising blood sugar) according to the analyte level at the acquisition time, and if the fluctuation type is stable, the target object can determine whether to continue to maintain the analyte level at the acquisition time without intervention according to the current analyte level.

[0086] In some examples, for the case where the target fluctuation data may include the type of fluctuation of the analyte level, the target fluctuation data may also include the rise time, the fall time, and the time to remain stable, thereby being able to objectively and quantitatively obtain the fluctuation of the analyte.

[0087] In other examples, the target fluctuation data may be a waveform of the analyte level, thereby enabling the fluctuation of the analyte to be more intuitively obtained.

[0088] Figure 5 is an exemplary flow chart showing the predicted target fluctuation data involved in the examples of the present disclosure. Figure 6 is a schematic diagram showing a first analyte waveform involved in examples of the present disclosure.

[0089] In addition, the disclosed example also provides a second exemplary process for predicting target fluctuation data. In the second exemplary process, daily time is used to select a waveform segment from the first analyte waveform as the target waveform segment for the collection time of the second analyte level. In this case, the behavior of the target object corresponding to the daily time can reflect the living habits of the target object. Using daily time to screen the target waveform segment is more conducive to obtaining the second analyte level of the target object on the one hand, and on the other hand, compared with randomly selected time, it can reduce the interference of the random behavior of the target object on the analyte fluctuation. In addition, it is more in line with the application scenario where the target object controls the analyte. For the convenience of description, the second analyte level of the target fluctuation data to be predicted is referred to as the analyte level to be measured.

[0090] refer to Figure 5 , a second exemplary process may include:

[0091] Step S201: Determine a first analyte waveform of a plurality of first time periods based on first analyte data.

[0092] In some examples, multiple first analyte levels within a single first time period can be fitted to form a first analyte waveform for a single first time period. As an example, Figure 6It shows that the first time period is 1 day, the analyte level is glucose concentration, and the first analyte waveform of the target object for 4 days, wherein the first analyte waveforms on the first day, second day, third day, and fourth day are curves L1, curve L2, curve L3, and curve L4, respectively.

[0093] In some examples, the first analyte waveform may be a waveform that has been smoothed, in which case the influence of local irregular changes can be weakened, thereby highlighting global analyte fluctuations.

[0094] In some examples, the first analyte waveforms of the plurality of first time periods may be screened to retain some of the first analyte waveforms. For example, the similarities of the first analyte waveforms of the plurality of first time periods may be compared, and only one of the first analyte waveforms having a similarity greater than a first preset similarity may be retained. For another example, the first analyte waveforms of the plurality of first time periods may be classified or clustered by waveform category to determine the waveform category to which each first analyte waveform belongs, and only one of the first analyte waveforms of the same waveform category may be retained. Accordingly, the subsequent related steps utilize the screened first analyte waveform for further processing.

[0095] Step S202: Identifying a waveform segment associated with a target daily time from a plurality of first analyte waveforms during a first time period as a target waveform segment for the analyte level to be measured.

[0096] In addition, the target daily time may be the daily time corresponding to the moment of collection of the analyte level to be measured.

[0097] In some examples, the waveform segment associated with the target daily time can be a waveform segment corresponding to the same daily time as the target daily time in the first analyte waveform. In some examples, the waveform segment associated with the target daily time can be a waveform segment corresponding to the daily time similar to the target daily time in the first analyte waveform. In addition, for an explanation of similar daily times, see the relevant description of daily time.

[0098] In some examples, if there are multiple target waveform segments, the multiple target waveform segments may be screened.

[0099] In some examples, input from a target object may be received to determine a target waveform segment. For example, the target object may screen multiple target waveform segments based on its current state. In some examples, if there are other second analyte levels in addition to the analyte level to be measured, multiple target waveform segments may be screened in combination with the other second analyte levels. In some examples, multiple target waveform segments may be screened in combination with the behavior of the target object. In some examples, the confidence of each target waveform segment may be determined based on the number of times each target waveform segment appears in the first analyte waveform, and the multiple target waveform segments may be screened using the confidence.

[0100] As described above, in some examples, the target fluctuation data can be predicted using the daily time near the random collection moment. Specifically, after identifying the waveform segment related to the target daily time from the first analyte waveforms of the plurality of first time periods, the waveform segment can be offset, and the offset waveform segment can be used as the target waveform segment of the analyte level to be measured. In addition, the offset distance can be the difference between the random collection moment and the nearby daily time.

[0101] Step S203: predicting target fluctuation data based on the target waveform segment.

[0102] Specifically, the fluctuation situation represented by the target waveform segment can be used to represent the fluctuation situation before and / or after the acquisition time. In some examples, the fluctuation information of the target waveform segment can be extracted, and the target fluctuation data can be determined based on the fluctuation information. As described above, the target fluctuation data can include the fluctuation type of the analyte level. In some examples, for the fluctuation type, the slope information can be obtained by differentiating multiple first analyte levels of the target waveform segment, and the fluctuation type can be obtained based on the slope information. It should be noted that for other forms of target fluctuation data, the corresponding algorithm can be selected for processing, which will not be repeated here.

[0103] Figure 7 is an exemplary flow chart showing the process of identifying a target waveform segment according to an example of the present disclosure.

[0104] In addition, with respect to step S202 (i.e., identifying waveform segments associated with target daily times from first analyte waveforms of multiple first time periods as target waveform segments of the analyte level to be measured), the disclosed example also provides a third exemplary process for identifying target waveform segments.

[0105] refer to Figure 7 , a third exemplary process may include:

[0106] Step S301: Acquire daily time corresponding to a single first time period as historical daily time.

[0107] In addition, the single first time period may include at least one daily time, and the daily time in the first time period may be used as the historical daily time.

[0108] In some examples, daily time can be automatically identified based on the first analyte waveform. In some examples, daily events can be identified based on the first analyte waveform corresponding to the first time period, thereby determining daily time.

[0109] In some examples, data from a health device may be used to assist in identifying daily time. For example, the health device may be a sports watch, a blood oxygen monitoring device, a blood pressure monitoring device, or a sleep monitoring device.

[0110] In some examples, an input of the target object may be received to obtain daily time for a single first time period. For example, when the target object wears the analyte sensor, the clock-in data of the target object is received to mark the daily time for the single first time period with the clock-in data. For another example, before predicting the target fluctuation data, the target object's marking of the first analyte data may be received to obtain the daily time for the single first time period.

[0111] Step S302: Identify historical daily time related to the target daily time from historical daily time of at least one first time period to obtain reference daily time.

[0112] In some examples, at least one first time period may be traversed, and historical daily time related to the target daily time may be screened from each first time period. The historical daily time related to the target daily time may be the same or similar historical daily time as the target daily time, and the specific content is shown in the relevant description of the daily time.

[0113] In some examples, for historical daily times similar to the target daily time, the historical daily time may be adjusted to obtain the reference daily time. For example, if the historical daily time is two hours after breakfast and the target daily time is one hour after breakfast, the collection time corresponding to the historical daily time may be moved forward by one hour to determine the collection time one hour after breakfast as the reference daily time.

[0114] In addition, if there are reference daily times, the number of reference daily times may be greater than 1. For example, assuming that the number of first time periods is 2, if there is a qualified historical daily time in each first time period, two reference daily times may be obtained when the obtained historical daily time is directly used as the reference daily time.

[0115] Step S303: extracting a waveform segment related to the reference daily time from the first analyte waveform belonging to the reference daily time as a reference waveform segment.

[0116] In some examples, a reference time period corresponding to a single reference daily time may be determined, and a waveform segment within the reference time period may be intercepted as a reference waveform segment. That is, the waveform segment associated with the reference daily time may be a waveform segment within the reference time period.

[0117] In addition, the reference time period can be set according to the analysis target. In other words, the reference time period can be set according to the target fluctuation data of the time period that the target object wants to obtain. In some examples, the time span of the reference time period can be 1 hour, 2 hours, half an hour or 20 minutes, etc.

[0118] In some examples, the reference time period may be a time period before a single reference daily time. In this case, target fluctuation data before the acquisition time can be obtained, and the analyte level can be retrospectively analyzed. In some examples, the reference time period may be a time period after a single reference daily time. In this case, target fluctuation data after the acquisition time can be obtained, which is beneficial for the target subject to control the analyte to reduce abnormal analyte levels.

[0119] In addition, in the case where the reference time period can be a time period before or after a single reference daily time, the position of the reference daily time in the reference time period can be the end position or the start position of the reference time period. In other examples, considering that the analyte will not fluctuate too much in a short period of time, the position of the reference daily time may not be within the reference time period. For example, the position of the reference daily time may be close to the end point of the reference time period.

[0120] In some examples, the reference time period may be a time period before and after a single reference daily time. In some examples, the reference time period may be a time period spanning a single reference daily time. That is, the position of the reference daily time in the reference time period may be a position (e.g., an intermediate position) between the starting position and the ending position of the reference time period. In this case, it is beneficial for the target object to control the analyte according to the target fluctuation data after the acquisition time, and the target fluctuation data before the acquisition time is comprehensively considered, thereby being able to improve the stability of the analyte control.

[0121] In some examples, for a first analyte waveform, the number of reference time periods corresponding to the reference daily time may be multiple. The time spans of the multiple reference time periods may be different. In this case, the target waveform segment can be obtained by comprehensively considering multiple reference time periods with different time spans.

[0122] In some examples, if there are multiple reference waveform segments belonging to different first analyte waveforms, the multiple reference waveform segments may be screened, and accordingly, subsequent related steps utilize the screened reference waveform segments for further processing.

[0123] For example, the similarities of multiple reference waveform segments may be compared, and only one reference waveform segment having a similarity greater than a second preset similarity is retained.

[0124] For another example, multiple reference waveform segments may be classified (for example, according to the amplitude and mode of fluctuation) or clustered to determine the band category to which each reference waveform segment belongs, and only one reference waveform segment of the same band category is retained. In some examples, at least one reference waveform segment of each classification may be merged to determine a reference waveform segment, or any reference waveform segment may be selected as a reference waveform segment.

[0125] Step S304: selecting a reference waveform segment from at least one reference waveform segment as a target waveform segment using the level of the analyte to be measured.

[0126] In some examples, if the difference between the analyte level to be measured and the corresponding first analyte level in the reference waveform segment is not greater than a preset difference, for example, the analyte level to be measured may correspond to a daily time, and the daily time may correspond to a first analyte level in the reference waveform segment, the reference waveform segment is selected by comparing the difference between the two with the preset difference.

[0127] In some examples, if a second analyte level exists before the time of collecting the analyte level to be measured, the analyte level to be measured and the previously existing second analyte level may be used to select a reference waveform segment from at least one reference waveform segment as the target waveform segment. In this case, by selecting a reference waveform segment in combination with multiple second analyte levels, a more accurate target waveform segment can be obtained.

[0128] In some examples, in step S304, the target waveform segment may also be checked to confirm whether the target waveform segment is correct.

[0129] Figure 8 is an exemplary flow chart illustrating updating first analyte data according to examples of the present disclosure.

[0130] Return to reference Figure 4 , in some examples, in addition to Figure 4 The data processing method may further include updating the first analyte data. In this case, the predicted target fluctuation data can be adapted to the changes in the target object's living habits by updating.

[0131] Specifically, refer to Figure 8 , an exemplary process for updating the first analyte data may include:

[0132] Step S401: Identify whether the first analyte data needs to be updated.

[0133] In addition, there are multiple ways to identify whether the first analyte data needs to be updated, and one of the ways or a combination of the ways can be selected to identify whether it needs to be updated. For example, due to changes in the target subject's own living habits, the first analyte data collected by the analyte sensor 900 previously worn may not be suitable as the target fluctuation data at the time of collection for predicting the second analyte level, so the target subject needs to be prompted to wear a new analyte sensor again.

[0134] In some examples, the first analyte waveform can be compared with the second analyte waveform determined by the target waveform segment to identify whether the first analyte data needs to be updated. Specifically, the first analyte waveform of at least one first time period and the second analyte waveform of at least one second time period can be compared to identify whether the first analyte data needs to be updated. In this case, the gap between the second analyte waveform and the first analyte waveform can be intuitively compared based on the analyte waveform.

[0135] In some examples, the target waveform segments corresponding to the multiple second analyte levels within a single second time period may be spliced ​​in time order to obtain the second analyte waveform of the single second time period. In some examples, waveform fitting (i.e., waveform interpolation) may be performed on the target waveform segments corresponding to the multiple second analyte levels to obtain the second analyte waveform. In some examples, the waveform fitting method may be a cubic spline interpolation method.

[0136] In some examples, the number of failures in identifying the target waveform segment can be counted, and whether the first analyte data needs to be updated can be identified based on the number of failures. In this case, it can be effectively identified whether the first analyte data needs to be updated.

[0137] In some examples, the error rate of the target fluctuation data may be counted, and whether the first analyte data needs to be updated may be identified based on the error rate. In this case, whether the first analyte data needs to be updated may be objectively identified.

[0138] Step S402: generating a reminder message in response to first analyte data needing to be updated.

[0139] In some examples, the reminder message can be used to remind the target subject to wear a new analyte sensor again to obtain new first analyte data. The target fluctuation data predicted based on the new first analyte data can adapt to the changes in the target subject's living habits.

[0140] In addition, in response to the first analyte data not needing to be updated, step S401 may continue to be executed.

[0141] The example of the present disclosure also provides an electronic device, including at least one processing circuit. The at least one processing circuit is configured to execute one or more steps in the above data processing method.

[0142] The examples of the present disclosure also provide a computer-readable storage medium, which can store at least one instruction, and when the at least one instruction is executed by a processor, one or more steps in the above-mentioned data processing method are implemented.

[0143] Although the present disclosure is specifically described above in conjunction with the accompanying drawings and embodiments, it is to be understood that the above description does not limit the present disclosure in any form. Those skilled in the art may modify and change the present disclosure as needed without departing from the essential spirit and scope of the present disclosure, and these modifications and changes all fall within the scope of the present disclosure.

Claims

1. A data processing method based on an analyte sensor, wherein the analyte sensor is used to continuously monitor the level of a first analyte of a target object, characterized in that: The data processing method includes acquiring first analyte data of a target object, the first analyte data including a first analyte level that varies over time and is collected by the analyte sensor when the target object wears the analyte sensor; acquiring second analyte data of the target object, the second analyte data including at least one second analyte level, the second analyte data is not collected by the analyte sensor, and the second analyte level is a single-point analyte level; and predicting fluctuation data of the analyte before and / or after the collection moment of the second analyte level in the second analyte data based on the first analyte data.

2. The data processing method according to claim 1, characterized in that: The fluctuation data includes the fluctuation type of the analyte level, and the fluctuation type includes rising, falling and plateauing.

3. The data processing method according to claim 1, characterized in that: The analyte sensor is a glucose sensor, the first analyte level is a glucose concentration in blood obtained by the glucose sensor, and the second analyte level is a glucose concentration in fingertip blood.

4. The data processing method according to claim 1, characterized in that: Based on the first analyte data, a first analyte waveform of multiple first time periods is determined; a waveform segment related to a target daily time is identified from the first analyte waveforms of the multiple first time periods as a target waveform segment at the collection moment, the target daily time is the daily time corresponding to the collection moment of the second analyte level, and the daily time is the time before and / or after the daily event of the target object; and the fluctuation data is predicted based on the target waveform segment.

5. The data processing method according to claim 4, characterized in that: Acquire daily time corresponding to a single first time period as historical daily time; identify historical daily time related to the target daily time from historical daily time of at least one first time period to obtain reference daily time; A waveform segment associated with the reference daily time is intercepted from the first analyte waveform to which the reference daily time belongs as a reference waveform segment; and a reference waveform segment is selected from at least one of the reference waveform segments using the second analyte level as the target waveform segment.

6. The data processing method according to claim 5, characterized in that: A reference time period corresponding to a single reference daily time is determined, wherein the reference time period is a time period before and / or after the single reference daily time, and the waveform segment associated with the reference daily time is a waveform segment within the reference time period.

7. The data processing method according to claim 4, characterized in that: The daily events include events related to meals and events related to sleep, and the daily time includes moments before and after events related to meals, and a moment before sleep.

8. The data processing method according to claim 7, characterized in that: The time after the meal-related event is two hours after the meal-related event.

9. The data processing method according to claim 4, characterized in that: The method also includes generating a reminder message in response to identifying that the first analyte data needs to be updated, wherein the reminder message is used to remind the target subject to wear a new analyte sensor again to obtain new first analyte data.

10. The data processing method according to claim 9, characterized in that: The target waveform segments corresponding to the multiple second analyte levels within a single second time period are spliced ​​in chronological order to obtain the second analyte waveform of a single second time period, and the first analyte waveform of at least one first time period and the second analyte waveform of at least one second time period are compared to identify whether the first analyte data needs to be updated; and / or the number of failures in not identifying the target waveform segment is counted, and based on the number of failures, whether the first analyte data needs to be updated is identified; and / or the error rate of the fluctuation data is counted, and based on the error rate, whether the first analyte data needs to be updated is identified.

11. The data processing method according to claim 1, characterized in that: The fluctuation data is predicted only in response to the second analyte level being within a predetermined range.

12. An integrated single-point analyte level measurement device, characterized in that: It comprises a collection unit and a processing unit, the collection unit is used to collect the single-point analyte level of the target object, and the processing unit is used to receive the single-point analyte level and determine the fluctuation data of the analyte before and / or after the collection moment of the single-point analyte level by executing the data processing method described in any one of claims 1 to 11.

13. A monitoring system based on single-point analyte levels, characterized in that: It comprises a measuring device and a processing device; the measuring device is used to measure the single-point analyte level of the target object and is communicatively connected to the processing device; the processing device is used to receive the single-point analyte level and determine the fluctuation data of the analyte before and / or after the collection time of the single-point analyte level by executing the data processing method described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the data processing method according to any one of claims 1 to 11 is implemented.

Images