CN114023418B - Insulin recommendation method and device and system for monitoring blood sugar level - Google Patents

Insulin recommendation method and device and system for monitoring blood sugar level Download PDF

Info

Publication number
CN114023418B
CN114023418B CN202210007244.7A CN202210007244A CN114023418B CN 114023418 B CN114023418 B CN 114023418B CN 202210007244 A CN202210007244 A CN 202210007244A CN 114023418 B CN114023418 B CN 114023418B
Authority
CN
China
Prior art keywords
insulin
user
recommendation
matching
blood glucose
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210007244.7A
Other languages
Chinese (zh)
Other versions
CN114023418A (en
Inventor
韩洋
蒋娟
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.)
Diascience Medical Co Ltd
Original Assignee
Diascience Medical Co Ltd
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 Diascience Medical Co Ltd filed Critical Diascience Medical Co Ltd
Priority to CN202210007244.7A priority Critical patent/CN114023418B/en
Publication of CN114023418A publication Critical patent/CN114023418A/en
Application granted granted Critical
Publication of CN114023418B publication Critical patent/CN114023418B/en
Priority to PCT/CN2022/085451 priority patent/WO2023130598A1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G16H20/17—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered via infusion or injection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage

Abstract

The invention relates to the field of physiological signal processing, and provides an insulin recommendation method and device and a system for monitoring blood sugar level, wherein the method comprises the following steps: regularizing key feature data of a user to obtain at least two matching feature values; matching in the case base based on at least two matching characteristic values; if the matching is successful, selecting a first insulin recommendation scheme based on the grading sorting; if the matching fails, outputting a second insulin recommendation scheme; updating a case base based on feedback information of the user to the recommendation, wherein when the user accepts the recommendation, the feedback information comprises a first insulin recommendation scheme and the score thereof or a second insulin recommendation scheme and the score thereof; when the user does not accept the recommendation, the feedback information includes the insulin response protocol employed by the user and its score, which is determined based on the target glycemic time fraction and/or the rate of change in glycemic concentration for the second time period. The invention enables the user to enjoy richer and more reasonable recommendations, and improves the experience of the user.

Description

Insulin recommendation method and device and system for monitoring blood sugar level
Technical Field
The invention relates to the field of physiological signal processing, in particular to an insulin recommendation method and device and a system for monitoring blood sugar level.
Background
Diabetes mellitus is a chronic metabolic disorder that results from the inability of the pancreas to produce sufficient amounts of the hormone insulin, resulting in a decrease in the body's ability to metabolize glucose. The most common form of diabetes is either diabetes due to reduced insulin secretion (type 1 diabetes, the first recognized form) or diabetes due to reduced sensitivity of body tissues to insulin (type 2 chronic diabetes, the most common form). The former treatment requires insulin injections, while the latter is generally controlled with oral medications.
With the technical development of biosensors, the appearance of a blood glucose concentration continuous monitoring system (which continuously provides real-time blood glucose concentration data according to a certain frequency) provides a blood glucose prediction user with a better understanding of the change level of the blood glucose concentration of the user, which is very useful for the management of diabetes, and further has a data base for better controlling the blood glucose concentration. The blood glucose concentration continuous monitoring system can continuously provide a sensor blood glucose measuring signal representing the real-time blood glucose concentration through an implanted or non-implanted blood glucose sensitive sensor according to a certain frequency, and the sensor measures various properties of blood, other tissues or a part of a human body, including a photoelectric sensor, an electrochemical sensor, optical absorption or optical penetration and the like. A series of measurements clearly yields more data. However, it is not always easy to convert such data into actionable information. Blood glucose concentration is the primary parameter that is normally measured for euglycemic control. Other information that may be used to determine better treatment relates to the metabolic burden caused by various activities such as taking food, performing physical activities, work related stress, etc. Insulin delivery, other drugs, and the like are further adjusting the mechanisms of targeted physiological parameters. In addition to glucose measurement, current methods are based essentially on non-scientific, non-empirical rules to determine insulin recommendations and require repeated assessments based on glucose measurements. In view of the above, there are still serious drawbacks in current clinical approaches to address the needs of diabetics in their daily lives. There is no separate solution to combine various information together to form a more reasonable insulin recommendation. Furthermore, effective insulin recommendation is not achieved in the art by simply combining the various available information, each of which has specific elements that must be developed and adjusted for the overall process to have the desired level of safety, accuracy and robustness of recommendation.
In the process of implementing the embodiment of the invention, the inventor finds that at least the following defects exist in the background art: in some existing recommendation schemes, the influence of the change rule of the blood glucose concentration on the blood glucose level in a short time caused by data input by a user is not considered, such as the current blood glucose level of the user, the usage amount of insulin, ingested or consumed carbohydrates, exercise amount, medication and the like or the occurrence of wrong data conditions, and the personalized recommendation of the user and the effect actually brought by the recommended result are not considered, so that the user experience is poor. For the purpose of treating a blood glucose monitoring user, it is urgently needed to provide more comprehensive, accurate and effective insulin recommendation service for a diabetic patient.
Disclosure of Invention
The invention provides an insulin recommendation method and device and a system for monitoring blood sugar level, which are used for solving the technical defects in the prior art.
The invention provides an insulin recommendation method, which comprises the following steps:
regularizing key characteristic data of a user to obtain at least two matching characteristic values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
matching in a case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
if the matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and a second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
The insulin recommendation method according to the present invention, wherein the method further comprises:
obtaining blood glucose monitoring data of a user from a blood glucose measuring device associated with the user through a network;
the blood glucose monitoring data comprises blood glucose monitoring data of a first time period and a second time period.
The insulin recommendation method according to the present invention, wherein the regularizing the key feature data of the user to obtain at least two matching feature values includes:
acquiring user associated data and an expected blood glucose level; the user association data comprises current user association data and historical user association data, and the current user association data and the historical blood glucose association data each comprise one or more events and one or more user characteristic data associated with blood glucose concentration; the desired blood glucose level comprises at least one of a user set point, an empirical value, an expert advice value, or a combination thereof.
The insulin recommendation method of the present invention, wherein the one or more events are associated with one or more of carbohydrate consumption, exercise, sleep, and administration of a substance; the administration of the substance comprises the type of medication, the dosage of medication, the amount of carbohydrate administered; the type of administration includes at least one of long-acting insulin, short-acting insulin, and fast-acting insulin.
The insulin recommendation method according to the invention, wherein the one or more user characteristic data are associated with at least one of basic physiological information and personal information of the user; the basic physiological information comprises at least one of an insulin sensitivity coefficient and an insulin-to-carbohydrate ratio; the personal information includes at least one of gender, location, type of diabetes, age, weight, and historical age of insulin.
The insulin recommendation method according to the present invention, wherein the case library includes an individual library and a general library, and the matching is performed in the case library based on the at least two matching feature values, and whether the matching is successful or not is determined, including:
matching in the personality library based on the at least two matching characteristic values, and judging whether the matching is successful;
if the matching fails, matching is carried out in the universal library based on the at least two matching characteristic values, and whether the matching is successful is judged;
wherein the personality library is derived based on at least one user characteristic data, and the personality library has a higher priority of use than the general library.
The insulin recommendation method according to the present invention, wherein the matching in the case base based on the at least two matching feature values and determining whether the matching is successful includes:
obtaining at least two absolute distances based on each matching feature value and a corresponding historical feature value in the historical feature value set; giving a corresponding characteristic weight value to each absolute distance, and then adding the characteristic weight values to obtain a difference score, wherein the characteristic weight value is determined based on the correlation size of the corresponding matching characteristic value and the insulin;
when the difference score is not greater than the difference threshold value, judging that the matching is successful; and when the difference score is larger than the difference threshold value, judging that the matching is failed.
The insulin recommendation method according to the invention, wherein the selecting a first insulin recommendation scheme based on the ranking of scores in the matching schemes comprises:
selecting a plurality of matching schemes with the difference scores not larger than a difference threshold value from the historical cases, and selecting a first insulin recommendation scheme with the highest score from the plurality of matching schemes;
when at least two matching schemes with the same score appear, a first insulin recommendation scheme is determined based on the difference score of the at least two matching schemes with the same score.
The insulin recommendation method according to the present invention, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule, and comprises:
the second insulin recommendation scheme comprises an insulin recommendation dose obtained based on the key feature data of the user and preset rules, and the preset rules comprise the following formula:
Figure 936959DEST_PATH_IMAGE001
wherein B represents the recommended dose of insulin; CHO denotes the amount of carbohydrate administered; ICR represents the insulin-to-carbohydrate ratio; g represents current blood glucose collection data; gt represents the desired blood glucose level; ISF denotes insulin sensitivity coefficient; IOB represents insulin present in the body.
The insulin recommendation method according to the present invention, wherein before updating the case base based on the feedback information of the user to the recommendation, the method includes:
sending the recommendation to an expert corresponding to the user through a network;
receiving an acceptance or rejection recommendation for the recommendation by the expert, the rejection recommendation including a third insulin recommendation prescribed by the expert;
accordingly, the insulin response protocol employed by the user includes the third insulin recommendation.
The insulin recommendation method according to the present invention, wherein before performing matching in the case base based on the at least two matching feature values, the method further includes:
and judging whether abnormal data exist in the key characteristic data of the user, and if the abnormal data exist, suspending the recommendation.
The insulin recommendation method according to the present invention, wherein the method further comprises:
and pre-evaluating the recommended insulin doses in the first and second insulin recommendations, and outputting only the recommended insulin doses within a safety threshold range.
The insulin recommendation method according to the present invention, wherein the updating the case base based on the feedback information of the user to the recommendation includes:
obtaining a new case based on the feedback information of the user to the recommendation, and updating the new case to the case base; the new case comprises the at least two matching characteristic values and the corresponding response schemes and scores thereof, and the corresponding response schemes and scores thereof comprise one of the first insulin recommendation scheme and the score thereof, the second insulin recommendation scheme and the score thereof, and the insulin response scheme and the score thereof.
The insulin recommendation method according to the present invention, wherein the updating the new case to the case base includes:
and pre-evaluating the scores, and updating only the new cases with the scores larger than the score threshold value into the case base.
The insulin recommendation method according to the present invention, wherein the method further comprises:
implementing a visualization of the recommendation using at least one display module;
and/or acquiring user associated data by utilizing at least one first acquisition module;
and/or collecting feedback information of the user on the recommendation by utilizing at least one second collection module.
The insulin recommendation method according to the present invention, wherein the first time period extends from a first time to a current time, the first time being before the current time, and the second time period extends from the current time to a second time, the second time being after the current time.
The insulin recommendation method according to the present invention, wherein the target blood glucose time ratio for the second time period is determined based on the desired blood glucose level and blood glucose monitoring data for the second time period, and the rate of change of blood glucose concentration for the second time period is determined based on the blood glucose monitoring data for the second time period.
The insulin recommendation method according to the present invention, wherein the scoring is determined based on a target blood glucose time ratio for the second time period and/or a blood glucose concentration change rate for the second time period, comprises:
the score is determined using the following formula:
Figure 948778DEST_PATH_IMAGE002
wherein the TIR represents a target glycemic time fraction for a second time period; rate represents a Rate of change in blood glucose concentration for a second time period, the Rate of change in blood glucose concentration being determined as a Rate of change of positive and negative values; f (TIR) and f (Rate) respectively represent functions for converting the TIR and the Rate into values between 0 and 100; a denotes a weight of TIR, b denotes a weight of Rate, and a + b =1 is satisfied.
The present invention also provides an insulin recommendation device, comprising:
the key characteristic processing module is used for regularizing key characteristic data of a user to obtain at least two matching characteristic values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
the matching module is used for matching in the case base based on the at least two matching characteristic values and judging whether the matching is successful or not; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
the first recommendation module is used for selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes if the matching is successful, wherein the matching scheme is obtained by matching the at least two matching characteristic values in the case base;
the second recommendation module is used for outputting a second insulin recommendation scheme if the matching fails, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
the updating module is used for updating the case base based on feedback information of the user on recommendation, and the recommendation comprises the first insulin recommendation scheme and a second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
The present invention also provides a system for monitoring blood glucose levels, comprising:
a sensor configured to acquire blood glucose monitoring data of a user;
a wireless transmitter to transmit the blood glucose monitoring data;
and
a mobile computing device, comprising:
a wireless receiver configured to receive the blood glucose monitoring data;
a memory to store data including the received blood glucose monitoring data;
a processor to process the data, and a software application comprising instructions stored in the memory that when executed by the processor regularize user's key feature data resulting in at least two matching feature values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
matching in a case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
if the matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and a second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
The present invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of any of the insulin recommendation methods described above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the insulin recommendation method as any of the above.
The method comprises the steps of regularizing key feature data of a user to obtain a matching feature value, matching in a case base by using the matching feature value to obtain and recommend a first insulin recommendation scheme to the user, and obtaining and recommending a second insulin recommendation scheme based on a preset rule when a scheme meeting conditions is not matched; after the recommendation is completed, based on the feedback information of the user to the recommendation, no matter the user accepts the recommendation or the user rejects the recommendation, the feedback information including the score reflecting the use effect corresponding to the new case can be based on the feedback information, and the new case with better use effect in the feedback information is updated to the case base. With the increase of the use times of the user, the more the selectable high-scoring schemes in each historical case in the case base are, the more accurate and reliable recommendation can be realized.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a block diagram of an implementation environment in accordance with various embodiments of the invention.
Fig. 2 is a schematic flow chart of an insulin recommendation method provided by the present invention.
Fig. 3 is a schematic diagram of a user interface in the insulin recommendation method provided by the present invention.
FIG. 4 is a schematic diagram of the mechanism of insulin injection evaluation provided by the present invention.
Fig. 5 is a schematic structural diagram of an insulin recommendation device provided by the invention.
Fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a schematic diagram of an implementation environment according to various embodiments of the present invention is shown. The implementation environment includes: terminal 100 and/or server 200.
The terminal 100 may be an electronic device with data processing capability, such as a mobile phone, a tablet computer, an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III, mpeg Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, mpeg Audio Layer 4), a laptop computer, a desktop computer, and so on.
The terminal 100 may have an application client installed therein, or a browser installed therein, and access to a web client of an application through the browser. The application client and the web page client are collectively referred to as the client in the embodiments of the present invention, and are not specifically stated below.
The server 200 may be a near-end or far-end server, a server cluster composed of several servers, or a cloud computing service center. When the terminal 100 and the server 200 simultaneously process the service related to the present invention, the server 200 may be used to provide the service related to the present invention in interaction with the terminal 100. The server 200 is a server corresponding to the client, and the two servers can combine to realize various functions provided by the client, and are usually set up by an internet service provider.
The terminal 100 and the server 200 may be connected through a wireless network or a wired network.
An insulin recommendation method of the present invention is described below in conjunction with fig. 2, and includes the following steps.
S1, regularizing key feature data of the user to obtain at least two matching feature values; the key characteristic data includes a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period.
The regularization comprises the steps that the key characteristic data of the non-numerical type are converted into numbers by using preset normalization rules, if the type I diabetes is taken as '0', the type II diabetes is taken as '1', if the male diabetes is taken as '0', the female diabetes is taken as '1', and the preset normalization rules such as the above are utilized to carry out regularization processing on part of the key characteristic data without quantization values. The data of blood sugar concentration (namely the blood sugar concentration value), the blood sugar change rate, the carbon water intake and the exercise amount which have quantitative values do not need to be subjected to regularization processing in the step.
The blood glucose monitoring data of the first time period includes, but is not limited to, blood glucose concentration data with time stamp, data associated with blood glucose concentration, and the blood glucose monitoring data of the first time period is obtained by a method including, but not limited to, blood glucose concentration sensor, network transmission collection or other collection methods. For example, the user blood glucose concentration data may be continuously output at a certain period and with a time stamp for a first period. The first time period extends from a first time to a current time, the first time is before the current time, for example, the first time period may be within 10 minutes to 2 hours before the current time, and the user blood glucose concentration data extending from the first time to the current time (including the current time) may be represented as a data waveform of the past first time period, wherein the horizontal axis represents time and the vertical axis represents collected data.
The user-related data is also data of the first time period, and is generally data related to blood glucose concentration, such as life event-related data of carbon water intake, motion amount, and the like, which is input by a user or by other means. The carbohydrate data may be obtained by software that automatically recognizes calories in the food picture. The at least two matching characteristic values comprise data derived from at least two of the blood glucose monitoring data for the first time period and the user-associated data for the first time period.
S2, matching in the case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme.
The at least two matching characteristic values can form a new case of the user, and the matching of the cases is carried out in the case base based on the new case. Each historical characteristic value group comprises a plurality of historical case characteristic values, in the matching process, each historical characteristic value group of each characteristic value in the new case is compared with the corresponding historical case characteristic value, the correspondence refers to data in the same category, for example, blood sugar concentration data is the same category, carbohydrate intake data is the same category, and the characteristic values in each category are compared one by one; and meanwhile, scoring the difference degree by combining the scoring weight.
And S3, if the matching is successful, selecting a first insulin recommendation scheme based on the ranking of the scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base.
The matching schemes all meet the condition that the difference score is not larger than the difference threshold value, if the matching schemes are more, the matching schemes can be ranked based on the difference score, a plurality of matching schemes (which can be 3-5) with the smallest difference score are selected for further screening, the further screening is based on the ranking of scores, and the matching scheme with the highest score can be selected as the first insulin recommendation scheme. The higher the score, the more consistent the first insulin recommendation is with the current needs and current physical condition of the user. The scores of the historical cases in the case base are screened in advance and are all larger than a score threshold value.
And S4, if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule.
If the difference score is greater than the difference threshold, no history case similar to the new case is matched. At this time, an alternative scheme is adopted, namely, a second insulin recommendation scheme is obtained by using key characteristic data of the user and preset rules.
S5, updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and the second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
And outputting the first insulin recommendation scheme or the second insulin recommendation scheme on a display interface for the user to select whether to accept the recommendation, and further updating the case base based on feedback information of the user on the recommendation (whether to accept the first insulin recommendation scheme or the second insulin recommendation scheme) after the first insulin recommendation scheme or the second insulin recommendation scheme is output. When the user accepts a first insulin recommendation, the feedback information includes the first insulin recommendation and its score; when the user accepts a second insulin recommendation, the feedback information includes the second insulin recommendation and its score; when the user refuses to recommend, the insulin response scheme adopted by the user and the grade thereof can be updated to a case library; and under the condition that the insulin response scheme adopted by the user and the score thereof are not obtained, the case base is not updated, otherwise, when the insulin recommendation method is executed each time, if the score meets the score threshold value, a new recommendation scheme and the score thereof need to be updated into the case base. With the increase of the use times of the user, the recommendation scheme in the case base is more and more accurate and personalized, and better recommendation can be realized. The score threshold may be set to not less than 90 points. Preferably, the case base is updated once each time the method of the present invention is executed, and if the data in the case base exceeds a certain range, the expired data can be deleted periodically, and the new data in a period of time can be retained. A target glycemic time ratio for the second time period is determined based on the desired glucose level and blood glucose monitoring data for a second time period, the rate of change in blood glucose concentration for the second time period being determined based on the blood glucose monitoring data for the second time period.
The method comprises the steps of regularizing key characteristic data of a user to obtain a matching characteristic value, matching in a case base by using the matching characteristic value to obtain and recommend a first insulin recommendation scheme to the user, and obtaining and recommending a second insulin recommendation scheme based on a preset rule when the scheme which meets the conditions is not matched; after the recommendation is completed, based on the feedback information of the user to the recommendation, no matter the user accepts the recommendation or the user rejects the recommendation, the feedback information including the score reflecting the use effect corresponding to the new case can be based on the feedback information, and the new case with better use effect in the feedback information is updated to the case base. With the increase of the use times of the user, the more the selectable high-scoring schemes in each historical case in the case base are, the more accurate and reliable recommendation can be realized.
Further, the insulin recommendation method further includes:
obtaining blood glucose monitoring data of a user from a blood glucose measuring device associated with the user through a network;
the network is a wired or wireless network, and the blood glucose measuring device associated with the user includes, but is not limited to, a blood glucose meter with a blood glucose sensor, a blood sampling measuring device, and other physiological data collecting devices capable of collecting blood glucose concentration data. Preferably, the blood glucose measuring device is a continuous blood glucose monitoring device capable of continuously acquiring blood glucose concentration data in real time.
The blood glucose monitoring data comprises blood glucose monitoring data of a first time period and a second time period, wherein the blood glucose monitoring data of the first time period comprises first blood glucose concentration data and a first blood glucose concentration change rate.
The first blood glucose concentration data includes: the blood glucose monitoring system comprises a first blood glucose measurement value at the current moment, a first time stamp corresponding to the first blood glucose measurement value, and historical blood glucose collection data between the first moment and the current moment, wherein the historical blood glucose collection data comprise a plurality of historical blood glucose measurement values which are continuously distributed according to a preset time interval and a plurality of historical time stamps corresponding to the historical blood glucose measurement values. The preset time interval is the interval, such as 3 minutes, during which the continuous blood glucose monitoring device produces blood glucose. The historical blood glucose collection data comprises a plurality of historical blood glucose measurement values which are continuously distributed in a first time period at the current moment and take 3 minutes as a period and a plurality of corresponding historical time stamps.
Determining the rate of change of glucose concentration based on the first glucose measurement value and its corresponding first timestamp, and a second value selected from the plurality of historical glucose measurement values and their corresponding plurality of historical timestamps; the second value includes a second blood glucose measurement and its corresponding second timestamp, the second timestamp being associated with the first timestamp.
The first rate of change of glucose concentration is derived as a rate of change of positive and negative values based on the first glucose concentration data, e.g., the rate of change of glucose concentration is calculated by: (first blood glucose measurement value-second blood glucose measurement value)/(first time stamp-second time stamp), the second value may be selected within a third time period from the current time, the third time period may be 1 minute to 30 minutes, preferably, the data at 3 minutes before the current time may be selected, and if there is data missing or abnormality, the data within the other third time period from the current time may be selected.
The blood glucose monitoring data for the second time period comprises second blood glucose concentration data and a second blood glucose concentration change rate; similarly, the second blood glucose concentration change rate is obtained based on the second blood glucose concentration data in a positive and negative value change rate manner, the positive and negative value change rate can reflect the rising, falling or stable level of the blood glucose concentration, and the positive and negative value change rate can be converted into a value between 0 and 100 through a function and then used. The second time period extends from a current time to a second time, the second time being after the current time. Specifically, the second blood glucose concentration data of the second time period may overlap with the first blood glucose concentration data of the first time period at the current time, or the second blood glucose concentration data of the second time period may not include the data of the current time.
The blood glucose monitoring data in the first time period are fully considered, and scheme recommendation is carried out; and feeding back and updating the case base based on the blood glucose monitoring data in the second time period, wherein the blood glucose monitoring data in the second time period is mainly used for grading the scheme adopted by the user, and the recommended scheme is more suitable for the user after the case base is updated for multiple times.
Further, the method for recommending insulin, before regularizing the key feature data of the user to obtain at least two matching feature values, includes:
acquiring user associated data and an expected blood glucose level; the user association data comprises current user association data and historical user association data, and the current user association data and the historical blood glucose association data each comprise one or more events and one or more user characteristic data associated with blood glucose concentration; the desired blood glucose level comprises at least one of a user set point, an empirical value, an expert advice value, or a combination thereof.
The user-associated data includes data associated with blood glucose concentration, such as carbohydrate intake and intake thereof, amount of exercise, etc., which is manually input by a user, recognized by a picture obtained using a mobile Application (APP), or obtained by other devices. The current user associated data and the historical blood glucose associated data are also time-stamped respectively. The historical blood glucose related data assists the current user related data to obtain the recommendation scheme, and when the insulin is recommended, the current user related data and the historical user related data related to the blood glucose concentration can be fully considered, so that the recommendation accuracy is ensured.
Further, the insulin recommendation method, the one or more events associated with one or more of carbohydrate consumption, exercise, sleep, and administration of a substance; the administration of the substance comprises the type of medication, the dosage of medication, the amount of carbohydrate administered; the type of administration includes at least one of long-acting insulin, short-acting insulin, and fast-acting insulin.
Considering that different events such as medication type, medication amount, and carbohydrate administration have a large influence on blood glucose concentration, for example, fast acting insulin mainly affects for 30 minutes, and long acting insulin mainly affects for 2 hours, it is necessary to consider the event at the current time.
Further, in the insulin recommendation method, the one or more user characteristic data are associated with at least one of basic physiological information and personal information of the user; the basic physiological information comprises at least one of an insulin sensitivity coefficient and an insulin-to-carbohydrate ratio; the personal information includes at least one of gender, location, type of diabetes, age, weight, and historical age of insulin.
The region, the type of diabetes, the age and the like are set individually based on the user, a more personalized case base can be obtained by considering the factors, and the recommended result is more in line with the real situation of the user. For example, the diabetes type includes type 1 diabetes, type 2 diabetes, gestational diabetes, because each diabetes type user may have similar blood sugar concentration rule, different food, drug sensitivity, etc., each diabetes type user has certain regularity for blood sugar concentration variation, therefore when recommending insulin, it is possible to obtain personalized case library which is distinguished according to the diabetes type of the user, and the recommended result is more suitable for the user with the diabetes type.
Further, the insulin recommendation method, where the case library includes an individual library and a general library, performs matching in the case library based on the at least two matching feature values, and determines whether the matching is successful, includes:
matching in the personality library based on the at least two matching characteristic values, and judging whether the matching is successful;
if the matching fails, matching is carried out in the universal library based on the at least two matching characteristic values, and whether the matching is successful is judged;
wherein the personality library is derived based on at least one user characteristic data, and the personality library has a higher priority of use than the general library.
Matching can be preferentially carried out in the individual library, if the matching is successful, a recommendation scheme in the individual library is adopted, and at the moment, a universal library is not required to be called; if the matching is not successful in the individual library, the matching can be continuously carried out in the general library. The personality library is obtained based on the personalized feature data of the user, and the personality library is gradually improved and updated based on the use of the user and can be updated in other modes. The individual library and the general library are mutually independent, and the general library is obtained based on big data and can be updated regularly. The recommendation schemes in the individual library and the general library are screened, and the scores are larger than a score threshold value.
Further, the insulin recommendation method, which performs matching in a case base based on the at least two matching feature values and determines whether the matching is successful, includes:
obtaining at least two absolute distances based on each matching feature value and a corresponding historical feature value in the historical feature value set; giving a corresponding characteristic weight value to each absolute distance, and then adding the characteristic weight values to obtain a difference score, wherein the characteristic weight value is determined based on the correlation size of the corresponding matching characteristic value and the insulin;
when the difference score is not greater than the difference threshold value, judging that the matching is successful; and when the difference score is larger than the difference threshold value, judging that the matching is failed.
Wherein, each characteristic value adopts the calculation mode of absolute distance:
Figure 37956DEST_PATH_IMAGE003
wherein F represents a characteristic value, FnewA characteristic value, F, of a certain type of data representing a new caseoldRepresenting a historical case corresponds to FnewA characteristic value of (a); d' represents the degree of difference of the characteristic value before normalization.
Then, the difference degree of each characteristic value which is not in the range of 0-1 is normalized by a preset rule and converted into a value of 0-1, for example, the difference degree normalization process of the blood glucose concentration value can be expressed as:
Figure 426212DEST_PATH_IMAGE004
dGludenotes the degree of difference, d ', in blood glucose concentration values after normalization'GluRepresenting the degree of difference in blood glucose concentration values before normalization, FNewGluIndicating the blood glucose concentration values for the new case.
The difference degrees of other values can also be normalized one by adopting a difference degree normalization processing mode with the blood sugar concentration value;
the difference between the new case and the historical case is divided into:
Figure 854920DEST_PATH_IMAGE005
wherein d is1、d2、…、dnA difference score representing the 1 st to nth characteristic values, a1、a2、…、anThe factors respectively represent the 1 st to the nth characteristic values, and the factor is higher when the correlation between the characteristic values and the insulin is large, so that the following conditions are met:
Figure 53951DEST_PATH_IMAGE006
a larger D indicates a larger difference between the two cases, i.e. a smaller similarity. When the difference score is not greater than the difference threshold value, judging that the matching is successful; and when the difference score is larger than the difference threshold value, judging that the matching is failed. The difference threshold is preset and may be user-defined or user-input. For example, the difference threshold may be set to 0.1, that is, when the difference score is not more than 0.1, that is, when the similarity is greater than or equal to 90%, it is judged that the matching is successful.
During matching, in order to accelerate the response speed and the response accuracy, pre-screening can be performed based on partial matching characteristic values. Specifically, pre-screening is carried out in the case base based on at least one matching characteristic value to obtain a pre-selection base; the historical cases in the pre-selected library include sets of historical feature values having portions in common with the at least one matching feature value. The at least one matching characteristic value may be one or both and more. For example, the medication type is screened out, only the historical cases which are consistent with the medication type of the user are screened out, and then the new cases are further matched with the historical cases which are consistent with the medication type; namely, the historical cases with inconsistent medication types are excluded. For example, the medication age can only screen out the historical cases consistent with the medication age of the user, and then further match the new cases with the historical cases consistent with the medication age; namely, the history cases with inconsistent medication age are excluded. For example, a plurality of matching characteristic values can be combined for pre-screening, only history cases consistent with the medication age and the medication type of the user can be screened, and then the new cases are further matched with the history cases consistent with the medication age and the medication type; that is, the history cases with inconsistent medication age or medication type are excluded. Of course, it is also possible to compare the matching feature values one by one without performing pre-screening, and match the matching feature values by difference scores.
Further, the method for recommending insulin selects a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, and includes:
selecting a plurality of matching schemes with the difference scores not larger than a difference threshold value from the historical cases, and selecting a first insulin recommendation scheme with the highest score from the plurality of matching schemes;
and when only one matching scheme with the highest score exists, outputting the first insulin recommendation scheme with the highest score.
When at least two matching schemes with the same score appear, a first insulin recommendation scheme is determined based on the difference score of the at least two matching schemes with the same score.
If there are more than one score, the difference score can be continued, and the comparison can be performed in one of the following two ways:
(1) selecting a matching scheme with a smaller difference score from at least two matching schemes with the same score as the first insulin recommendation scheme for output;
(2) calculating a first insulin recommendation output using a least weighted average based on the difference scores of at least two matching solutions having the same score, e.g., when there are two matching solutions having the same score and both of which are the highest, calculating the first insulin recommendation using the following equation:
Figure 630426DEST_PATH_IMAGE007
wherein, B0Represents the first insulin recommendation (insulin recommendation) calculated using the minimum weighted average method, B1Insulin recommendation, B, representing one of the matching regimens2Insulin recommendation, D, representing another matching regimen1A difference score, D, representing one of the matching schemes2Representing a difference score for another matching scheme. In one case, when the difference scores of at least two matching solutions with the same score are the same, the above formula can be used to calculate that the first insulin recommendation is the average value, i.e. any matching solution.
Further, in the insulin recommendation method, the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule, and includes: the second insulin recommendation includes an insulin recommendation dose obtained based on the key feature data of the user and a preset rule (i.e., an insulin calculation model) including the following formula:
Figure 760056DEST_PATH_IMAGE001
wherein B represents the recommended dose of insulin; CHO denotes the amount of carbohydrate administered; ICR represents the insulin-to-carbohydrate ratio; g represents current blood glucose collection data; gTIndicating a desired blood glucose level; ISF denotes insulin sensitivity coefficient; IOB represents insulin present in the body.
The desired blood glucose level comprises at least one of a user set point, an empirical value, an expert advice value, or a combination thereof; the insulin present in the body can be measured according to an insulin testing instrument. The desired blood glucose level may be a value associated with at least one of a target glycemic time proportion, a rate of change in blood glucose concentration.
Further, the method for recommending insulin, wherein the score is determined based on the target blood glucose time ratio of the second time period and/or the blood glucose concentration change rate of the second time period, comprises: the score is determined using the following formula:
Figure 840007DEST_PATH_IMAGE002
wherein the TIR represents a target glycemic time fraction for a second time period; rate represents a Rate of change in blood glucose concentration for a second time period, the Rate of change in blood glucose concentration being determined as a Rate of change of positive and negative values; f (TIR) and f (Rate) respectively represent functions for converting TIR and Rate into values between 0 and 100. If TIR is 80%, then: f (TIR) =100 TIR. The target glycemic time fraction may be functionally converted to a value between 0 and 100 for use. The resulting positive and negative change rates can be quantified in terms of change intervals, e.g., a fast decline of 100, a typical decline of 80, a plateau of 60, a typical rise of 40, and a fast rise of 20.
a denotes a weight of TIR, b denotes a weight of Rate, and a + b =1 is satisfied. Wherein a and b are both 0-1. When a =0 and b =1, only the blood glucose concentration change rate of the second time period is considered without considering the target blood glucose time proportion of the second time period; when a =1 and b =0, only the target blood glucose time proportion of the second time period is considered, and the blood glucose concentration change rate of the second time period is not considered; a. the value of b can be customized by a user or an expert corresponding to the user or preset, a and b respectively represent the scoring weights of different scoring contents, and the setting of the values of a and b with different sizes represents that the user is more concerned about the blood sugar performance after insulin injection.
Further, before updating the case base based on the feedback information of the user to the recommendation, the insulin recommendation method includes: and sending the recommendation to an expert corresponding to the user through a network.
Receiving an acceptance or rejection recommendation for the recommendation by the expert, the rejection recommendation including a third insulin recommendation prescribed by the expert.
Accordingly, the insulin response protocol employed by the user includes the third insulin recommendation.
The method sends the recommendation to the expert by using a wired or wireless network, and can further solicit the opinion of the expert corresponding to the user on the basis of the recommendation, thereby ensuring the safety, authority and effectiveness of the recommendation. When the expert corresponding to the user reads the relevant information and the recommendation, the expert can give suggestions for accepting the suggestions or rejecting the suggestions according to experience, professional knowledge and the like, and under the condition of rejection, the third insulin recommendation scheme can be given for the user to select after analysis, so that the user can enjoy richer and more reasonable scheme information, and a scheme more suitable for the self condition can be selected by combining the recommendation and the third insulin recommendation scheme.
Further, the method for recommending insulin further includes, before performing matching in the case base based on the at least two matching feature values: and judging whether abnormal data exist in the key characteristic data of the user, and if the abnormal data exist, suspending the recommendation.
The determination of whether or not there is abnormal data in the key feature data of the user is made based on the past data history and experience of the user. Specifically, the blood glucose monitoring data and the user-related data are generally judged to be abnormal according to big data, past data history and experience of the user. The blood glucose monitoring data abnormality can be caused by that the data is beyond a certain range due to sensor abnormality, network abnormality, or the like. The user-associated data anomaly may be due to a user-entered value that is outside a certain normal applicable range. Before matching is carried out in the case base, if abnormal data exists, the data are not suitable for recommendation, at the moment, the recommendation needs to be suspended, and the potential safety hazard problem caused by recommending error data to a user is avoided.
Further, the insulin recommendation method further includes:
and pre-evaluating the recommended insulin doses in the first and second insulin recommendations, and outputting only the recommended insulin doses within a safety threshold range.
Before the recommendations are presented to the user, a preset safety evaluation is needed, all output recommendations can be ensured to be subjected to the safety evaluation through a preset safety threshold, the safety threshold can be customized by the user or defined by an expert corresponding to the user due to different conditions of each user and different types of insulin to be injected, generally, the safety threshold can be set to be a default value or not, and needs to be set individually, for example, the range of the safety threshold can be 0.1-30 unit. A safety threshold is set to prevent over-injection of insulin.
Further, the method for recommending insulin updates the case base based on the feedback information of the user to the recommendation, including:
obtaining a new case based on the feedback information of the user to the recommendation, and updating the new case to the case base; the new case comprises the at least two matching characteristic values and the corresponding response schemes and scores thereof, and the corresponding response schemes and scores thereof comprise one of the first insulin recommendation scheme and the score thereof, the second insulin recommendation scheme and the score thereof, and the insulin response scheme and the score thereof.
The new case is obtained based on key feature data of the user, the new case is selected based on feedback information of the user to recommendation, and specifically, one of a first insulin recommendation scheme and a score thereof, a second insulin recommendation scheme and a score thereof, which are actually selected by the user, or an insulin response scheme and a score thereof, which are adopted by the user after the user rejects the first insulin recommendation scheme and the score thereof, the second insulin recommendation scheme and the score thereof, is selected. If the user refuses the recommendation and does not input other response schemes, no new case can be generated in the process of executing the insulin recommendation method, and accordingly, the case base is not updated. The new case is generated based on the response scheme determined by the user and the score thereof, the score can reflect the real situation of the user after actually selecting the corresponding response scheme, and the higher the score is, the better the effect is after the corresponding response scheme is used. The case base is continuously updated in the using process, so that the more and more accurate recommendation based on the case base can be ensured, and the case base is more suitable for the user.
Further, the method for recommending insulin, which updates the new case to the case base, includes: and pre-evaluating the scores, and updating only the new cases with the scores larger than the score threshold value into the case base.
And updating the new case into the case base only when the score of the new case is higher than the score threshold value. If the score is below the score threshold, no update is made. Therefore, the historical cases existing in the case base are all high-quality cases with better grading effects after screening and use.
Further, the insulin recommendation method further includes: the visualization of the recommendation is implemented using at least one display module.
Preferably, the display module may be configured to display the first insulin recommendation or the second insulin recommendation.
And/or acquiring user associated data by utilizing at least one first acquisition module.
Preferably, the first acquisition module may be configured as an input module for acquiring user associated data, in particular user associated data for a first time period, such as one or more events, one or more user characteristic data.
And/or collecting feedback information of the user on the recommendation by utilizing at least one second collection module.
Preferably, the second collecting module may be configured as an input module for obtaining feedback information of the user on the recommendation, for example, when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes the insulin response protocol and its score employed by the user.
To further illustrate the insulin recommendation method of the present invention, the following specific examples are provided in conjunction with different usage scenarios.
In a first embodiment, when the matching of the individual library fails, the matching in the general library may be continued, and if the matching in the general library still fails, the user may choose to accept the recommendation or reject the recommendation after calculating an insulin recommendation based on the key feature data of the user and the insulin calculation model, and if the recommendation is rejected, the user may continue to input the input insulin amount for determining the injection.
And evaluating the insulin input quantity according to the insulin input quantity injected by the user and continuous blood glucose monitoring data obtained after the insulin is injected. The evaluation criteria were: and taking the proportion of the blood sugar in the target blood sugar time within a period of time after the insulin is input as the score of the input.
And simultaneously learning and summarizing the following characteristic values input at this time:
1. blood glucose concentration data and rate of change of blood glucose concentration before insulin infusion;
2. the amount of food consumed during insulin infusion;
3. the time and the injection amount from the last injection of insulin.
And updating the case into the case base, wherein the case base is not empty after updating.
When the user has the requirement of next insulin calculation, searching can be performed from the historical cases to search for similar cases, and the similarity is evaluated according to the characteristic values. And after finding out a similar historical case, extracting the recommended insulin amount and the score of the user injected in the similar case. If the score is greater than the score threshold, similar insulin input amounts (insulin recommended amounts) continue to be recommended, and if the score is below the threshold, recalculation is performed according to the insulin calculation model. Re-scoring is performed based on the recommended insulin recommendation amount that the user accepts or rejects recommendations.
As the number of uses increases, the more history cases that can be searched, the more highly scored insulin recommendations in each history case stored in the system (including the terminal 100 and/or the server 200, preferably including at least the terminal 100). The insulin recommendation of the system is more accurate at the moment. Meanwhile, the system has a safety mechanism, the recommended insulin quantity recommended to the patient can be synchronously sent to the experts corresponding to the user in real time through network connection, and the experts can choose to approve or reject after checking; after rejection, the expert gives a recommendation and provides it to the user.
In a second embodiment, a method for generating an insulin recommendation case library is disclosed, which comprises the following steps:
when an insulin injection occurs, the user records the input amount of insulin through the operation interface as shown in fig. 3. And inputting corresponding information on the operation interface by the user. In FIG. 3, the first input box represents blood glucose collection data, which may be automatically generated by the system, for example, 590mg/dL is currently shown; the second input box represents the desired blood glucose level, which can be input by the user or can be customized by the system; the third input box represents the insulin sensitivity coefficient; the fourth input box represents the amount of carbohydrate administered; the fifth input box represents the insulin-to-carbohydrate ratio; the sixth input box represents the insulin present in the body and the lowest output box represents the recommended amount of insulin to output.
While recording other events while insulin is being entered (e.g., diet, exercise, last insulin infusion, user desired blood glucose target range, etc.) as well as basic physiological and personal information of the patient (e.g., age, weight, type of diabetes, age of insulin used, etc.). The real-time blood glucose data of a patient can be obtained through the continuous blood glucose monitoring sensor, and the blood glucose change rate and the blood glucose concentration value during insulin input in the first time period are obtained. The above information is used as a description of a case with recommended amounts of insulin as a result of the case. A case base is generated by collecting cases of a group of people with common characteristics, such as type I diabetes.
In one case, the system collates the current information of the user into a new case, and a search for the case is conducted in the case base. In the searching process, each characteristic value in the new case is compared with the characteristic value set of the historical cases in the case base. And simultaneously scoring the difference score by combining the factors corresponding to each characteristic value.
Each feature value in each case has a factor for evaluating the difference score between cases, where quantifiable, the factor with large correlation to insulin metabolism is high.
As one aspect of the application, a case scoring method in insulin input is disclosed, which comprises the following steps: blood glucose concentration values within a second time period after an insulin injection event occurs (the second time period is obtained based on physiological grounds or experiences of insulin effects on blood glucose) may be continuously obtained using a continuous blood glucose monitoring sensor and electronics. The result of the present insulin input amount is evaluated in various ways.
In one case, a target glycemic time fraction (fraction of blood glucose within the target glycemic range) may be the primary scoring basis. Higher occupancy in the blood glucose target range means better control of blood glucose, i.e., better amount of insulin to be input this time. The ratio of the blood sugar target range is the score of this time. In other cases, the score may be calculated by using the time until a certain blood glucose level is lowered, the lowering rate, or the like.
And selecting the cases with high similarity scores according to a threshold value. And selecting the result (the current insulin input quantity) in the case with high case score as the output of the case with high similarity, and recommending the result to the user through the user interface.
When a user just starts to use the case, the historical cases with high similarity in the case library are few, and when the similar cases cannot be found, an insulin recommended value obtained by a general insulin dose calculation formula is recommended to the patient.
The patient may choose to accept the recommendation after receiving it, or may choose to reject the recommendation, after which the patient enters his own determined insulin input.
After this insulin input, the blood glucose change of the patient is measured using a continuous blood glucose monitoring system. And scoring the insulin injection according to a scoring rule. If the score is larger than the score threshold value, the insulin injection scheme is arranged into a new case and stored in the personality library after the score is finished. When the number of cases in the personality library reaches a certain threshold value, the system searches cases with high similarity from the personality library preferentially; if no similar cases exist or scores of the similar cases are too low, searching for cases with high similarity from the general library; if no or too low scores are found, the calculation is performed using the insulin calculation model.
As one aspect of the present application, a method for preventing insulin recommendation error is disclosed, which comprises the following specific steps: insulin recommendations are suspended in four cases:
when a user's continuous blood glucose monitoring system data error results in a current blood glucose concentration value error.
When the user data entered by the user for calculation, such as physiological parameters and/or dietary intake, is significantly incorrect.
When the recommended insulin amount calculated through case analysis or an insulin calculation model is larger than a safety threshold set by a user.
When the recommended amount of insulin calculated by case analysis or insulin calculation model is less than the minimum infusion unit of the insulin infusion device.
When the four conditions occur, the system prompts that 'recommendation is wrong, and a professional doctor is required to be consulted to obtain insulin suggestion'.
Wherein the recommended amount of insulin and the characteristic value of the case may be transmitted to an associated doctor or specialist via a network when the recommended or calculated amount occurs above a safety threshold. The judgment is made by a doctor or a specialist and the result is informed to the user through the network.
In a third embodiment, as shown, an evaluation mechanism of this insulin injection is disclosed, in fig. 4, the abscissa represents time, the ordinate represents blood glucose concentration value, and 1, 2, and 3 represent case 1, case 2, and case 3, respectively. Assuming that three cases of insulin recommended amounts are injected at the time t1, the injections are respectively injected according to the recommended amounts of case 1, case 2 and case 3, and the blood glucose concentration change rate and the target blood glucose time ratio at the time t1 and t2 are evaluated, so that it can be seen that the blood glucose concentration of case 3 is reduced more rapidly after insulin is injected, the target blood glucose time ratio is also longer, and it can be determined that case 3 is better than case 2 and better than case 1, that is, the score of case 3 is the highest.
Referring to fig. 5, the following describes an insulin recommendation device provided by the present invention, and the insulin recommendation device described below and the insulin recommendation method described above may be referred to in correspondence, the insulin recommendation device including: the key feature processing module 10 is configured to regularize key feature data of a user to obtain at least two matching feature values; the key characteristic data includes a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period.
The regularization comprises the steps that the key characteristic data of the non-numerical type are converted into numbers by using preset normalization rules, if the type I diabetes is taken as '0', the type II diabetes is taken as '1', if the male diabetes is taken as '0', the female diabetes is taken as '1', and the preset normalization rules such as the above are utilized to carry out regularization processing on part of the key characteristic data without quantization values. The data of blood sugar concentration (namely the blood sugar concentration value), the blood sugar change rate, the carbon water intake and the exercise amount which have quantitative values do not need to be subjected to regularization processing in the step.
The blood glucose monitoring data of the first time period includes, but is not limited to, blood glucose concentration data with time stamp, data associated with blood glucose concentration, and the blood glucose monitoring data of the first time period is obtained by a method including, but not limited to, blood glucose concentration sensor, network transmission collection or other collection methods. For example, the user blood glucose concentration data may be continuously output at a certain period and with a time stamp for a first period. The first time period extends from a first time to a current time, the first time is before the current time, for example, the first time period may be within 10 minutes to 2 hours before the current time, and the user blood glucose concentration data extending from the first time to the current time (including the current time) may be represented as a data waveform of the past first time period, wherein the horizontal axis represents time and the vertical axis represents collected data.
The user-related data is also data of the first time period, and is generally data related to blood glucose concentration, such as life event-related data of carbon water intake, motion amount, and the like, which is input by a user or by other means. The carbohydrate data may be obtained by software that automatically recognizes calories in the food picture. The at least two matching characteristic values comprise data derived from at least two of the blood glucose monitoring data for the first time period and the user-associated data for the first time period.
The matching module 20 is configured to perform matching in the case base based on the at least two matching feature values, and determine whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme.
The at least two matching characteristic values can form a new case of the user, and the matching of the cases is carried out in the case base based on the new case. Each historical characteristic value group comprises a plurality of historical case characteristic values, in the matching process, each historical characteristic value group of each characteristic value in the new case is compared with the corresponding historical case characteristic value, the correspondence refers to data in the same category, for example, blood sugar concentration data is the same category, carbohydrate intake data is the same category, and the characteristic values in each category are compared one by one; and meanwhile, scoring the difference degree by combining the scoring weight.
The first recommendation module 30 is configured to, if matching is successful, select a first insulin recommendation scheme based on a ranking of scores among a plurality of matching schemes, where the matching scheme is obtained by matching the at least two matching feature values in the case base.
The matching schemes all meet the condition that the difference score is not larger than the difference threshold value, if the matching schemes are more, the matching schemes can be ranked based on the difference score, a plurality of matching schemes (which can be 3-5) with the smallest difference score are selected for further screening, the further screening is based on the ranking of scores, and the matching scheme with the highest score can be selected as the first insulin recommendation scheme. The higher the score, the more consistent the first insulin recommendation is with the current needs and current physical condition of the user. The scores of the historical cases in the case base are screened in advance and are all larger than a score threshold value.
And the second recommending module 40 is configured to output a second insulin recommending scheme if the matching fails, where the second insulin recommending scheme is obtained based on the key feature data of the user and a preset rule.
If the difference score is greater than the difference threshold, no history case similar to the new case is matched. At this time, an alternative scheme is adopted, namely, a second insulin recommendation scheme is obtained by using key characteristic data of the user and preset rules.
An updating module 50, configured to update the case base based on feedback information of the user on a recommendation, where the recommendation includes the first insulin recommendation scheme and the second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
And outputting the first insulin recommendation scheme or the second insulin recommendation scheme on a display interface for the user to select whether to accept the recommendation, and further updating the case base based on feedback information of the user on the recommendation (whether to accept the first insulin recommendation scheme or the second insulin recommendation scheme) after the first insulin recommendation scheme or the second insulin recommendation scheme is output. When the user accepts a first insulin recommendation, the feedback information includes the first insulin recommendation and its score; when the user accepts a second insulin recommendation, the feedback information includes the second insulin recommendation and its score; when the user refuses to recommend, the insulin response scheme adopted by the user and the grade thereof can be updated to a case library; and under the condition that the insulin response scheme adopted by the user and the score thereof are not obtained, the case base is not updated, otherwise, when the insulin recommendation method is executed each time, if the score meets the score threshold value, a new recommendation scheme and the score thereof need to be updated into the case base. With the increase of the use times of the user, the recommendation scheme in the case base is more and more accurate and personalized, and better recommendation can be realized. The score threshold may be set to not less than 90 points. Wherein a target glycemic time duty for the second time period is determined based on the desired glucose level and blood glucose monitoring data for a second time period, the rate of change in blood glucose concentration for the second time period being determined based on the blood glucose monitoring data for the second time period.
The device obtains a matching characteristic value by regularizing key characteristic data of a user, matches the matching characteristic value in a case base to obtain and recommend a first insulin recommendation scheme to the user, and can obtain and recommend a second insulin recommendation scheme based on a preset rule when the scheme which meets the conditions is not matched; after the recommendation is completed, based on the feedback information of the user to the recommendation, no matter the user accepts the recommendation or the user rejects the recommendation, the feedback information including the score reflecting the use effect corresponding to the new case can be based on the feedback information, and the new case with better use effect in the feedback information is updated to the case base. With the increase of the use times of the user, the more the selectable high-scoring schemes in each historical case in the case base are, the more accurate and reliable recommendation can be realized.
Further, the insulin recommendation device further includes a blood glucose monitoring data acquisition module, and the blood glucose monitoring data acquisition module is configured to: obtaining blood glucose monitoring data of a user from a blood glucose measuring device associated with the user through a network; the blood glucose monitoring data comprises blood glucose monitoring data of a first time period and a second time period.
The network is a wired or wireless network, and the blood glucose measuring device associated with the user includes, but is not limited to, a blood glucose meter with a blood glucose sensor, a blood sampling measuring device, and other physiological data collecting devices capable of collecting blood glucose concentration data. Preferably, the blood glucose measuring device is a continuous blood glucose monitoring device capable of continuously acquiring blood glucose concentration data in real time.
Wherein the blood glucose monitoring data for the first time period comprises first blood glucose concentration data and a first rate of change of blood glucose concentration.
The first blood glucose concentration data includes: the blood glucose monitoring system comprises a first blood glucose measurement value at the current moment, a first time stamp corresponding to the first blood glucose measurement value, and historical blood glucose collection data between the first moment and the current moment, wherein the historical blood glucose collection data comprise a plurality of historical blood glucose measurement values which are continuously distributed according to a preset time interval and a plurality of historical time stamps corresponding to the historical blood glucose measurement values. The preset time interval is the interval, such as 3 minutes, during which the continuous blood glucose monitoring device produces blood glucose. The historical blood glucose collection data comprises a plurality of historical blood glucose measurement values which are continuously distributed in a first time period at the current moment and take 3 minutes as a period and a plurality of corresponding historical time stamps.
Determining the rate of change of glucose concentration based on the first glucose measurement value and its corresponding first timestamp, and a second value selected from the plurality of historical glucose measurement values and their corresponding plurality of historical timestamps; the second value includes a second blood glucose measurement and its corresponding second timestamp, the second timestamp being associated with the first timestamp.
The first rate of change of glucose concentration is derived as a rate of change of positive and negative values based on the first glucose concentration data, e.g., the rate of change of glucose concentration is calculated by: (first blood glucose measurement value-second blood glucose measurement value)/(first time stamp-second time stamp), the second value may be selected within a third time period from the current time, the third time period may be 1 minute to 30 minutes, preferably, the data at 3 minutes before the current time may be selected, and if there is data missing or abnormality, the data within the other third time period from the current time may be selected.
The blood glucose monitoring data for the second time period comprises second blood glucose concentration data and a second blood glucose concentration change rate; similarly, the second blood glucose concentration change rate is obtained based on the second blood glucose concentration data in a positive and negative value change rate manner, the positive and negative value change rate can reflect the rising, falling or stable level of the blood glucose concentration, and the positive and negative value change rate can be converted into a value between 0 and 100 through a function and then used. The second time period extends from a current time to a second time, the second time being after the current time. Specifically, the second blood glucose concentration data of the second time period may overlap with the first blood glucose concentration data of the first time period at the current time, or the second blood glucose concentration data of the second time period may not include the data of the current time. The blood glucose monitoring data in the first time period are fully considered, and scheme recommendation is carried out; and feeding back and updating the case base based on the blood glucose monitoring data in the second time period, wherein the blood glucose monitoring data in the second time period is mainly used for grading the scheme adopted by the user, and the recommended scheme is more suitable for the user after the case base is updated for multiple times.
Further, the insulin recommendation device further includes a user data acquisition module, where the user data acquisition module is configured to: acquiring user associated data and an expected blood glucose level; the user association data comprises current user association data and historical user association data, and the current user association data and the historical blood glucose association data each comprise one or more events and one or more user characteristic data associated with blood glucose concentration; the desired blood glucose level comprises at least one of a user set point, an empirical value, an expert advice value, or a combination thereof.
The user-associated data includes data associated with blood glucose concentration, such as carbohydrate intake and intake thereof, amount of exercise, etc., which is manually input by a user, recognized by a picture obtained using a mobile Application (APP), or obtained by other devices. The current user associated data and the historical blood glucose associated data are also time-stamped respectively. The historical blood glucose related data assists the current user related data to obtain the recommendation scheme, and when the insulin is recommended, the current user related data and the historical user related data related to the blood glucose concentration can be fully considered, so that the recommendation accuracy is ensured.
Further, the insulin recommendation device, the one or more events associated with one or more of carbohydrate consumption, exercise, sleep, and administration of a substance; the administration of the substance comprises the type of medication, the dosage of medication, the amount of carbohydrate administered; the type of administration includes at least one of long-acting insulin, short-acting insulin, and fast-acting insulin.
Considering that different events such as medication type, medication amount, and carbohydrate administration have a large influence on blood glucose concentration, for example, fast acting insulin mainly affects for 30 minutes, and long acting insulin mainly affects for 2 hours, it is necessary to consider the event at the current time.
Further, the insulin recommendation device, the one or more user characteristic data are associated with at least one of basic physiological information and personal information of the user; the basic physiological information comprises at least one of an insulin sensitivity coefficient and an insulin-to-carbohydrate ratio; the personal information includes at least one of gender, location, type of diabetes, age, weight, and historical age of insulin.
The region, the type of diabetes, the age and the like are set individually based on the user, a more personalized case base can be obtained by considering the factors, and the recommended result is more in line with the real situation of the user. For example, the diabetes type includes type 1 diabetes, type 2 diabetes, gestational diabetes, because each diabetes type user may have similar blood sugar concentration rule, different food, drug sensitivity, etc., each diabetes type user has certain regularity for blood sugar concentration variation, therefore when recommending insulin, it is possible to obtain personalized case library which is distinguished according to the diabetes type of the user, and the recommended result is more suitable for the user with the diabetes type.
Further, the insulin recommendation device, the case library includes an individual library and a general library, and the matching module 20 is configured to: and matching in the personality library based on the at least two matching characteristic values, and judging whether the matching is successful.
And if the matching fails, matching in the general library based on the at least two matching characteristic values, and judging whether the matching is successful.
Wherein the personality library is derived based on at least one user characteristic data, and the personality library has a higher priority of use than the general library.
Matching can be preferentially carried out in the individual library, if the matching is successful, a recommendation scheme in the individual library is adopted, and at the moment, a universal library is not required to be called; if the matching is not successful in the individual library, the matching can be continuously carried out in the general library. The personality library is obtained based on the personalized feature data of the user, and the personality library is gradually improved and updated based on the use of the user and can be updated in other modes. The individual library and the general library are mutually independent, and the general library is obtained based on big data and can be updated regularly. The recommendation schemes in the individual library and the general library are screened, and the scores are larger than a score threshold value.
Further, in the insulin recommendation device, the matching module 20 is configured to: obtaining at least two absolute distances based on each matching feature value and a corresponding historical feature value in the historical feature value set; giving a corresponding characteristic weight value to each absolute distance, and then adding the characteristic weight values to obtain a difference score, wherein the characteristic weight value is determined based on the correlation size of the corresponding matching characteristic value and the insulin; when the difference score is not greater than the difference threshold value, judging that the matching is successful; and when the difference score is larger than the difference threshold value, judging that the matching is failed.
The calculation method of the difference score is described in the foregoing embodiments, and is not described in detail here. During matching, in order to accelerate the response speed and the response accuracy, pre-screening can be performed based on partial matching characteristic values. Specifically, pre-screening is carried out in the case base based on at least one matching characteristic value to obtain a pre-selection base; the historical cases in the pre-selected library include sets of historical feature values having portions in common with the at least one matching feature value. The at least one matching characteristic value may be one or both and more. For example, the medication type is screened out, historical cases which are consistent with the medication type of the user are screened out, and then the new cases are further matched with the historical cases which are consistent with the medication type; namely, the historical cases with inconsistent medication types are excluded. For example, the medication age can be used for screening out historical cases consistent with the medication age of the user, and then further matching the new cases with the historical cases consistent with the medication age; namely, the history cases with inconsistent medication age are excluded. For example, the history cases consistent with the medication age and the medication type of the user can be screened out by combining a plurality of matching characteristic values for pre-screening, and then the new cases are further matched with the history cases consistent with the medication age and the medication type; that is, the history cases with inconsistent medication age or medication type are excluded. Of course, it is also possible to compare the matching feature values one by one without performing pre-screening, and match the matching feature values by difference scores.
Further, the first recommending module 30 is configured to: selecting a plurality of matching schemes with the difference scores not larger than a difference threshold value from the historical cases, and selecting a first insulin recommendation scheme with the highest score from the plurality of matching schemes; when at least two matching schemes with the same score appear, a first insulin recommendation scheme is determined based on the difference score of the at least two matching schemes with the same score.
And when only one matching scheme with the highest score exists, outputting the first insulin recommendation scheme with the highest score.
If there are more than one score, the difference score can be continued, and the comparison can be performed in one of the following two ways:
selecting a matching scheme with a smaller difference score from at least two matching schemes with the same score as the first insulin recommendation scheme for output;
calculating a first insulin recommendation output using a least weighted average based on the difference scores of at least two matching solutions having the same score, e.g., when there are two matching solutions having the same score and both of which are the highest, calculating the first insulin recommendation using the following equation:
Figure 724787DEST_PATH_IMAGE007
wherein, B0Represents the first insulin recommendation (insulin recommendation) calculated using the minimum weighted average method, B1Insulin recommendation, B, representing one of the matching regimens2Insulin recommendation, D, representing another matching regimen1A difference score, D, representing one of the matching schemes2Representing a difference score for another matching scheme. In one case, when the difference scores of at least two matching solutions with the same score are the same, the above formula can be used to calculate that the first insulin recommendation is the average value, i.e. any matching solution.
Further, the insulin recommendation device, the second insulin recommendation scheme includes an insulin recommended dose, the insulin recommended dose is obtained based on the key feature data of the user and a preset rule, and the preset rule includes the following formula:
Figure 273711DEST_PATH_IMAGE001
wherein B represents the recommended dose of insulin; CHO denotes the amount of carbohydrate administered; ICR represents the insulin-to-carbohydrate ratio; g represents current blood glucose collection data; gTIndicating a desired blood glucose level; ISF denotes insulin sensitivity coefficient; IOB represents insulin present in the body.
The desired blood glucose level comprises at least one of a user set point, an empirical value, an expert advice value, or a combination thereof; the insulin present in the body can be measured according to an insulin testing instrument. The desired blood glucose level may be a value associated with at least one of a target glycemic time proportion, a rate of change in blood glucose concentration.
Further, the insulin recommendation device, wherein the score is determined based on the target blood glucose time ratio of the second time period and/or the blood glucose concentration change rate of the second time period, comprises: the score is determined using the following formula:
Figure 207032DEST_PATH_IMAGE002
wherein the TIR represents a target glycemic time fraction for a second time period; rate represents a Rate of change in blood glucose concentration for a second time period, the Rate of change in blood glucose concentration being determined as a Rate of change of positive and negative values; f (TIR) and f (Rate) respectively represent functions for converting TIR and Rate into values between 0 and 100. If TIR is 80%, then: f (TIR) =100 TIR.
a denotes a weight of TIR, b denotes a weight of Rate, and a + b =1 is satisfied. Wherein a and b are both 0-1. When a =0 and b =1, only the blood glucose concentration change rate of the second time period is considered without considering the target blood glucose time proportion of the second time period; when a =1 and b =0, only the target blood glucose time proportion of the second time period is considered, and the blood glucose concentration change rate of the second time period is not considered; a. the value of b can be customized by a user or an expert corresponding to the user or preset, a and b respectively represent the weight among different scoring contents, and the setting of the values of a and b with different sizes represents that the user is more concerned about the blood sugar performance after insulin injection.
Further, the insulin recommendation device further comprises an expert advice acquisition module, wherein the expert advice acquisition module is configured to: and sending the recommendation to an expert corresponding to the user through a network. Receiving an acceptance or rejection recommendation for the recommendation by the expert, the rejection recommendation including a third insulin recommendation prescribed by the expert. Accordingly, the insulin response protocol employed by the user includes the third insulin recommendation.
The device can send the recommendation to the expert by utilizing a wired or wireless network, and can further solicit the opinion of the expert corresponding to the user on the basis of the recommendation, thereby ensuring the safety, authority and effectiveness of the recommendation. When the expert corresponding to the user reads the relevant information and the recommendation, the expert can give suggestions for accepting the suggestions or rejecting the suggestions according to experience, professional knowledge and the like, and under the condition of rejection, the third insulin recommendation scheme can be given for the user to select after analysis, so that the user can enjoy richer and more reasonable scheme information, and a scheme more suitable for the self condition can be selected by combining the recommendation and the third insulin recommendation scheme.
Further, the insulin recommendation device further comprises a recommendation suspension module, and the recommendation suspension module is configured to: and judging whether abnormal data exist in the key characteristic data of the user, and if the abnormal data exist, suspending the recommendation.
The determination of whether or not there is abnormal data in the key feature data of the user is made based on the past data history and experience of the user. Specifically, the blood glucose monitoring data and the user-related data are generally judged to be abnormal according to big data, past data history and experience of the user. The blood glucose monitoring data abnormality can be caused by that the data is beyond a certain range due to sensor abnormality, network abnormality, or the like. The user-associated data anomaly may be due to a user-entered value that is outside a certain normal applicable range. Before matching is carried out in the case base, if abnormal data exists, the data are not suitable for recommendation, at the moment, the recommendation needs to be suspended, and the potential safety hazard problem caused by recommending error data to a user is avoided.
Further, the insulin recommendation device further comprises a safety evaluation module, and the safety evaluation module is configured to: and pre-evaluating the recommended insulin doses in the first and second insulin recommendations, and outputting only the recommended insulin doses within a safety threshold range.
Before the recommendations are presented to the user, a preset safety evaluation is needed, all output recommendations can be ensured to be subjected to the safety evaluation through a preset safety threshold, the safety threshold can be customized by the user or defined by an expert corresponding to the user due to different conditions of each user and different types of insulin to be injected, generally, the safety threshold can be set to be a default value or not, and needs to be set individually, for example, the range of the safety threshold can be 0.1-30 unit.
Further, in the insulin recommendation device, the update module 50 is configured to: obtaining a new case based on the feedback information of the user to the recommendation, and updating the new case to the case base; the new case comprises the at least two matching characteristic values and the corresponding response schemes and scores thereof, and the corresponding response schemes and scores thereof comprise one of the first insulin recommendation scheme and the score thereof, the second insulin recommendation scheme and the score thereof, and the insulin response scheme and the score thereof.
The new case is obtained based on the key characteristic data of the user, or the insulin response scheme and the grading thereof adopted by the user, the new case is selected based on the feedback information recommended by the user, and the scheme actually selected by the user is specifically selected. If the user refuses the recommendation and does not input other response schemes, no new case can be generated in the process of executing the insulin recommendation method, and accordingly, the case base is not updated. The new case is generated on the basis of the response scheme determined by the user and the score of the response scheme, the real situation of the user can be reflected, and the case base is more and more accurately recommended in the using process and is more suitable for the user.
Further, in the insulin recommendation device, the update module 50 is further configured to: and pre-evaluating the scores, and updating only the new cases with the scores larger than the score threshold value into the case base.
And updating the new case into the case base only when the score of the new case is higher than the score threshold value. If the score is below the score threshold, no update is made. Therefore, the historical cases existing in the case base are all high-quality cases with scores, screened values and high reference values.
Further, the insulin recommendation device further comprises a display module for realizing the recommendation visualization.
Preferably, the display module may be configured to display the first insulin recommendation or the second insulin recommendation.
The apparatus may also include a first acquisition module to acquire user association data.
Preferably, the first acquisition module may be configured as an input module for acquiring user associated data, in particular user associated data for a first time period, such as one or more events, one or more user characteristic data.
The device can also comprise a second acquisition module which is used for acquiring feedback information of the user on the recommendation.
Preferably, the second collecting module may be configured as an input module for obtaining feedback information of the user on the recommendation, for example, when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes the insulin response protocol and its score employed by the user.
The present invention also provides a system for monitoring blood glucose levels, comprising:
a sensor configured to acquire blood glucose monitoring data of a user;
a wireless transmitter to transmit the blood glucose monitoring data;
and
a mobile computing device, comprising:
a wireless receiver configured to receive the blood glucose monitoring data;
a memory to store data including the received blood glucose monitoring data;
a processor to process the data, and a software application comprising instructions stored in the memory that when executed by the processor regularize user's key feature data resulting in at least two matching feature values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
matching in a case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
if the matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and a second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
The system obtains a matching characteristic value by regularizing key characteristic data of a user, matches the matching characteristic value in a case base to obtain and recommend a first insulin recommendation scheme to the user, and can obtain and recommend a second insulin recommendation scheme based on a preset rule when the scheme which meets the conditions is not matched; after the recommendation is completed, based on the feedback information of the user to the recommendation, no matter the user accepts the recommendation or the user rejects the recommendation, the feedback information including the score reflecting the use effect corresponding to the new case can be based on the feedback information, and the new case with better use effect in the feedback information is updated to the case base. With the increase of the use times of the user, the more the selectable high-scoring schemes in each historical case in the case base are, the more accurate and reliable recommendation can be realized.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include: a processor (processor) 610, a communication Interface (Communications Interface) 620, a memory (memory) 630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform an insulin recommendation method comprising:
s1, regularizing key feature data of the user to obtain at least two matching feature values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
s2, matching in the case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
s3, if matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
s4, if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
s5, updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and the second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the insulin recommendation method provided by the above methods, the method comprising:
s1, regularizing key feature data of the user to obtain at least two matching feature values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
s2, matching in the case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
s3, if matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
s4, if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
s5, updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and the second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements an insulin recommendation method provided by the above methods, the method comprising:
s1, regularizing key feature data of the user to obtain at least two matching feature values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
s2, matching in the case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
s3, if matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
s4, if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
s5, updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and the second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information includes an insulin response protocol adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time fraction of a second time period and/or a blood glucose concentration change rate of the second time period.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (20)

1. An insulin recommendation method, comprising:
regularizing key feature data of a user to obtain at least two matching feature values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
matching in a case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
if the matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and a second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information comprises an insulin response scheme adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time proportion of a second time period and a blood glucose concentration change rate of the second time period;
the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule, and comprises the following steps:
the second insulin recommendation scheme comprises an insulin recommendation dose obtained based on the key feature data of the user and preset rules, and the preset rules comprise the following formula:
Figure DEST_PATH_IMAGE001
wherein B represents the recommended dose of insulin; CHO denotes the amount of carbohydrate administered; ICR represents the insulin-to-carbohydrate ratio; g represents current blood glucose collection data; gTIndicating a desired blood glucose level; ISF denotes insulin sensitivity coefficient; IOB represents insulin present in the body; the score is determined based on the target glycemic time fraction for the second time period and the rate of change in glycemic concentration for the second time period, comprising:
the score is determined using the following formula:
Figure DEST_PATH_IMAGE002
wherein the TIR represents a target glycemic time fraction for a second time period; rate represents a Rate of change in blood glucose concentration for a second time period, the Rate of change in blood glucose concentration being determined as a Rate of change of positive and negative values; f (TIR) and f (Rate) respectively represent functions for converting the TIR and the Rate into values between 0 and 100; a denotes a weight of TIR, b denotes a weight of Rate, and a + b =1 is satisfied.
2. The insulin recommendation method according to claim 1, further comprising:
obtaining blood glucose monitoring data of a user from a blood glucose measuring device associated with the user through a network;
the blood glucose monitoring data comprises blood glucose monitoring data of a first time period and a second time period.
3. The insulin recommendation method according to claim 2, wherein the regularizing the key feature data of the user to obtain at least two matching feature values comprises:
acquiring user associated data and an expected blood glucose level; the user association data comprises current user association data and historical user association data, and the current user association data and the historical blood glucose association data each comprise one or more events and one or more user characteristic data associated with blood glucose concentration; the desired blood glucose level comprises at least one of a user set point, an empirical value, an expert advice value, or a combination thereof.
4. The insulin recommendation method according to claim 3, wherein the one or more events are associated with one or more of carbohydrate consumption, exercise, sleep, and administration of a substance; the administration of the substance comprises at least one of a type of medication, a dosage of medication, an amount of carbohydrate administered; the type of administration includes at least one of long-acting insulin, short-acting insulin, and fast-acting insulin.
5. The insulin recommendation method according to claim 4, wherein the one or more user characteristic data is associated with at least one of basic physiological information, personal information of the user; the basic physiological information comprises at least one of an insulin sensitivity coefficient and an insulin-to-carbohydrate ratio; the personal information includes at least one of gender, location, type of diabetes, age, weight, and historical age of insulin.
6. The insulin recommendation method according to claim 5, wherein the case base comprises an individual base and a general base, and the matching in the case base based on the at least two matching feature values and determining whether the matching is successful comprises:
matching in the personality library based on the at least two matching characteristic values, and judging whether the matching is successful;
if the matching fails, matching is carried out in the universal library based on the at least two matching characteristic values, and whether the matching is successful is judged;
wherein the personality library is derived based on at least one user characteristic data, and the personality library has a higher priority of use than the general library.
7. The insulin recommendation method according to claim 1, wherein said matching in a case base based on said at least two matching feature values and determining whether the matching is successful comprises:
obtaining at least two absolute distances based on each matching feature value and a corresponding historical feature value in the historical feature value set; giving a corresponding characteristic weight value to each absolute distance, and then adding the characteristic weight values to obtain a difference score, wherein the characteristic weight value is determined based on the correlation size of the corresponding matching characteristic value and the insulin;
when the difference score is not greater than the difference threshold value, judging that the matching is successful; and when the difference score is larger than the difference threshold value, judging that the matching is failed.
8. The insulin recommendation method of claim 7, wherein said selecting a first insulin recommendation scheme based on a ranking of scores among a number of matching schemes comprises:
selecting a plurality of matching schemes with the difference scores not larger than a difference threshold value from the historical cases, and selecting a first insulin recommendation scheme with the highest score from the plurality of matching schemes;
when at least two matching schemes with the same score appear, a first insulin recommendation scheme is determined based on the difference score of the at least two matching schemes with the same score.
9. The insulin recommendation method according to claim 1, wherein before updating the case base based on the feedback information of the user to the recommendation, the method comprises:
sending the recommendation to an expert corresponding to the user through a network;
receiving an acceptance or rejection recommendation for the recommendation by the expert, the rejection recommendation including a third insulin recommendation prescribed by the expert;
accordingly, the insulin response protocol employed by the user includes the third insulin recommendation.
10. The insulin recommendation method according to claim 1, wherein said matching based on said at least two matching feature values in a case base further comprises:
and judging whether abnormal data exist in the key characteristic data of the user, and if the abnormal data exist, suspending the recommendation.
11. The insulin recommendation method according to claim 1, further comprising:
and pre-evaluating the recommended insulin doses in the first and second insulin recommendations, and outputting only the recommended insulin doses within a safety threshold range.
12. The insulin recommendation method according to claim 1, wherein said updating said case base based on said user feedback information on recommendations comprises:
obtaining a new case based on the feedback information of the user to the recommendation, and updating the new case to the case base; the new case comprises the at least two matching characteristic values and the corresponding response schemes and scores thereof, and the corresponding response schemes and scores thereof comprise one of the first insulin recommendation scheme and the score thereof, the second insulin recommendation scheme and the score thereof, and the insulin response scheme and the score thereof.
13. The insulin recommendation method of claim 12, wherein said updating said new case to said case base comprises:
and pre-evaluating the scores, and updating only the new cases with the scores larger than the score threshold value into the case base.
14. The insulin recommendation method according to claim 1, further comprising:
implementing a visualization of the recommendation using at least one display module;
and/or acquiring user associated data by utilizing at least one first acquisition module;
and/or collecting feedback information of the user on the recommendation by utilizing at least one second collection module.
15. The insulin recommendation method according to claim 1, characterized in that said first time period extends from a first time instant before said current time instant to a current time instant, said second time period extends from a current time instant to a second time instant after said current time instant.
16. The insulin recommendation method according to claim 1, wherein the target blood glucose time ratio for the second time period is determined based on the desired blood glucose level and blood glucose monitoring data for the second time period, the rate of change of blood glucose concentration for the second time period being determined based on the blood glucose monitoring data for the second time period.
17. An insulin recommendation device, comprising:
the key characteristic processing module is used for regularizing key characteristic data of a user to obtain at least two matching characteristic values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
the matching module is used for matching in the case base based on the at least two matching characteristic values and judging whether the matching is successful or not; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
the first recommendation module is used for selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes if the matching is successful, wherein the matching scheme is obtained by matching the at least two matching characteristic values in the case base;
the second recommendation module is used for outputting a second insulin recommendation scheme if the matching fails, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
the updating module is used for updating the case base based on feedback information of the user on recommendation, and the recommendation comprises the first insulin recommendation scheme and a second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information comprises an insulin response scheme adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time proportion of a second time period and a blood glucose concentration change rate of the second time period;
the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule, and comprises the following steps:
the second insulin recommendation scheme comprises an insulin recommendation dose obtained based on the key feature data of the user and preset rules, and the preset rules comprise the following formula:
Figure 928860DEST_PATH_IMAGE001
wherein B represents the recommended dose of insulin; CHO denotes the amount of carbohydrate administered; ICR represents the insulin-to-carbohydrate ratio; g represents current blood glucose collection data; gTIndicating a desired blood glucose level; ISF denotes insulin sensitivity coefficient; IOB represents insulin present in the body; the score is determined based on the target glycemic time fraction for the second time period and the rate of change in glycemic concentration for the second time period, comprising:
the score is determined using the following formula:
Figure 314842DEST_PATH_IMAGE002
wherein the TIR represents a target glycemic time fraction for a second time period; rate represents a Rate of change in blood glucose concentration for a second time period, the Rate of change in blood glucose concentration being determined as a Rate of change of positive and negative values; f (TIR) and f (Rate) respectively represent functions for converting the TIR and the Rate into values between 0 and 100; a denotes a weight of TIR, b denotes a weight of Rate, and a + b =1 is satisfied.
18. A system for monitoring blood glucose levels, comprising:
a sensor configured to acquire blood glucose monitoring data of a user;
a wireless transmitter to transmit the blood glucose monitoring data;
and
a mobile computing device, comprising:
a wireless receiver configured to receive the blood glucose monitoring data;
a memory to store data including the blood glucose monitoring data;
a processor to process the data, and a software application comprising instructions stored in the memory that when executed by the processor regularize user's key feature data resulting in at least two matching feature values; the key characteristic data comprises a desired blood glucose level, blood glucose monitoring data for a first time period, and user association data for the first time period;
matching in a case base based on the at least two matching characteristic values, and judging whether the matching is successful; the case base stores a plurality of historical cases, and each historical case comprises a historical characteristic value set, a historical insulin recommendation scheme associated with the historical characteristic value set and a score of the historical insulin recommendation scheme;
if the matching is successful, selecting a first insulin recommendation scheme based on the ranking of scores in a plurality of matching schemes, wherein the matching schemes are obtained by matching the at least two matching characteristic values in the case base;
if the matching fails, outputting a second insulin recommendation scheme, wherein the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule;
updating the case base based on feedback information of the user on recommendation, wherein the recommendation comprises the first insulin recommendation scheme and a second insulin recommendation scheme; when the user accepts the recommendation, the feedback information includes the first insulin recommendation and its score or the second insulin recommendation and its score; when the user does not accept the recommendation, the feedback information comprises an insulin response scheme adopted by the user and a score thereof, wherein the score is determined based on a target blood glucose time proportion of a second time period and a blood glucose concentration change rate of the second time period;
the second insulin recommendation scheme is obtained based on the key feature data of the user and a preset rule, and comprises the following steps:
the second insulin recommendation scheme comprises an insulin recommendation dose obtained based on the key feature data of the user and preset rules, and the preset rules comprise the following formula:
Figure 829000DEST_PATH_IMAGE001
wherein B represents the recommended dose of insulin; CHO denotes the amount of carbohydrate administered; ICR represents the insulin-to-carbohydrate ratio; g represents current blood glucose collection data; gTIndicating a desired blood glucose level; ISF denotes insulin sensitivity coefficient; IOB represents insulin present in the body; the score is determined based on the target glycemic time fraction for the second time period and the rate of change in glycemic concentration for the second time period, comprising:
the score is determined using the following formula:
Figure 693051DEST_PATH_IMAGE002
wherein the TIR represents a target glycemic time fraction for a second time period; rate represents a Rate of change in blood glucose concentration for a second time period, the Rate of change in blood glucose concentration being determined as a Rate of change of positive and negative values; f (TIR) and f (Rate) respectively represent functions for converting the TIR and the Rate into values between 0 and 100; a denotes a weight of TIR, b denotes a weight of Rate, and a + b =1 is satisfied.
19. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the insulin recommendation method according to any one of claims 1 to 16 when executing the program.
20. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the insulin recommendation method according to any one of claims 1 to 16.
CN202210007244.7A 2022-01-06 2022-01-06 Insulin recommendation method and device and system for monitoring blood sugar level Active CN114023418B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202210007244.7A CN114023418B (en) 2022-01-06 2022-01-06 Insulin recommendation method and device and system for monitoring blood sugar level
PCT/CN2022/085451 WO2023130598A1 (en) 2022-01-06 2022-04-07 Insulin recommendation method and device and system for monitoring blood sugar level

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210007244.7A CN114023418B (en) 2022-01-06 2022-01-06 Insulin recommendation method and device and system for monitoring blood sugar level

Publications (2)

Publication Number Publication Date
CN114023418A CN114023418A (en) 2022-02-08
CN114023418B true CN114023418B (en) 2022-04-01

Family

ID=80069617

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210007244.7A Active CN114023418B (en) 2022-01-06 2022-01-06 Insulin recommendation method and device and system for monitoring blood sugar level

Country Status (2)

Country Link
CN (1) CN114023418B (en)
WO (1) WO2023130598A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114023418B (en) * 2022-01-06 2022-04-01 苏州百孝医疗科技有限公司 Insulin recommendation method and device and system for monitoring blood sugar level
CN114374946B (en) * 2022-03-17 2022-06-21 苏州百孝医疗科技有限公司 Communication method and device for analyte concentration data monitoring system
CN116439698B (en) * 2023-03-31 2023-12-15 中南大学 Blood glucose monitoring and early warning method, system and equipment for intensive care unit
CN116721733B (en) * 2023-08-10 2023-11-07 武汉联影智融医疗科技有限公司 Blood glucose level adjustment method, blood glucose level adjustment device, and storage medium
CN116807464B (en) * 2023-08-30 2024-01-26 武汉联影智融医疗科技有限公司 Blood sugar control device based on artificial pancreas system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102500013A (en) * 2011-11-22 2012-06-20 北京化工大学 Fully automatic intelligent infusion method and device based on model predictive control for large doses of insulin
CN105912881A (en) * 2016-06-14 2016-08-31 华南师范大学 Individual-based treatment scheme recommendation system based on big data knowledge base
CN107715230A (en) * 2017-10-12 2018-02-23 微泰医疗器械(杭州)有限公司 Insulin pump individuation configuration optimization system and method based on high in the clouds big data
CN112017747A (en) * 2020-09-04 2020-12-01 四川大学 Intelligent recommendation method for enhanced CT contrast agent injection scheme
CN113035319A (en) * 2021-04-26 2021-06-25 南通大学 Automatic recommendation method and system for lifestyle management path of diabetic patient

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9990581B2 (en) * 2012-07-11 2018-06-05 Roche Diabetes Care, Inc. Insulin dosage assessment and recommendation system
US20170053084A1 (en) * 2015-08-21 2017-02-23 Medtronic Minimed, Inc. Data analytics and reporting of glucose-related information
WO2020139699A1 (en) * 2018-12-28 2020-07-02 Dexcom, Inc. Evaluation and visualization of glycemic dysfunction
US11935637B2 (en) * 2019-09-27 2024-03-19 Insulet Corporation Onboarding and total daily insulin adaptivity
CN111048178A (en) * 2019-12-30 2020-04-21 杭州知盛数据科技有限公司 Insulin control method, device and equipment
AU2021221966A1 (en) * 2020-02-18 2022-09-08 Eli Lilly And Company Methods and systems for generating behavioral insights using survey instruments and diabetes treatment information
CN112908445A (en) * 2021-02-20 2021-06-04 上海市第四人民医院 Diabetes patient blood sugar management method, system, medium and terminal based on reinforcement learning
CN114023418B (en) * 2022-01-06 2022-04-01 苏州百孝医疗科技有限公司 Insulin recommendation method and device and system for monitoring blood sugar level

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102500013A (en) * 2011-11-22 2012-06-20 北京化工大学 Fully automatic intelligent infusion method and device based on model predictive control for large doses of insulin
CN105912881A (en) * 2016-06-14 2016-08-31 华南师范大学 Individual-based treatment scheme recommendation system based on big data knowledge base
CN107715230A (en) * 2017-10-12 2018-02-23 微泰医疗器械(杭州)有限公司 Insulin pump individuation configuration optimization system and method based on high in the clouds big data
CN112017747A (en) * 2020-09-04 2020-12-01 四川大学 Intelligent recommendation method for enhanced CT contrast agent injection scheme
CN113035319A (en) * 2021-04-26 2021-06-25 南通大学 Automatic recommendation method and system for lifestyle management path of diabetic patient

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于电子病历的典型诊疗模式挖掘方法研究;陈静锋;《中国博士学位论文全文数据库-医药卫生科技辑》;20200630(第6期);E053-12 *
糖尿病饮食推荐系统设计与实现;司慧枫;《中国优秀硕士学位论文全文数据库-信息科技辑》;20160331(第3期);I138-7668 *

Also Published As

Publication number Publication date
WO2023130598A1 (en) 2023-07-13
CN114023418A (en) 2022-02-08

Similar Documents

Publication Publication Date Title
CN114023418B (en) Insulin recommendation method and device and system for monitoring blood sugar level
US11200988B2 (en) Diabetes management therapy advisor
US11309089B2 (en) Human metabolic condition management
US20200077931A1 (en) Forecasting blood glucose concentration
US9990581B2 (en) Insulin dosage assessment and recommendation system
US20170076630A1 (en) Optimizing Messages Sent to Diabetic Patients in an Interactive System Based on Estimated HbA1c Levels
US20110184754A1 (en) System and method for remote health care management
US8185412B1 (en) Method and apparatus for chronic care treatment control with custom named-type factors and user estimation error correction
CN110753967A (en) Insulin titration algorithm based on patient profile
US20230110814A1 (en) Systems and methods for analyzing, interpreting, and acting on continuous glucose monitoring data
US20210151189A1 (en) Joint state estimation prediction that evaluates differences in predicted vs. corresponding received data
WO2021165747A1 (en) Devices, systems, and methods for predicting blood glucose levels based on a personalized blood glucose regulation model
CN114021672B (en) Label generation method and device and system for monitoring blood sugar level
US20230338654A1 (en) System and method for titrating basal insulin doses
US20240058532A1 (en) System and method for titrating basal insulin doses
Skrøvseth et al. Statistical modeling of aggregated lifestyle and blood glucose data in type 1 diabetes patients
Fiaidhi et al. Clinical Pathways Inference from Decision Rules by Hybrid Stream Mining and Fuzzy Unordered Rule Induction Strategy

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant