CN111261256A - Insulin administration method, storage medium and system based on big data - Google Patents
Insulin administration method, storage medium and system based on big data Download PDFInfo
- Publication number
- CN111261256A CN111261256A CN202010061791.4A CN202010061791A CN111261256A CN 111261256 A CN111261256 A CN 111261256A CN 202010061791 A CN202010061791 A CN 202010061791A CN 111261256 A CN111261256 A CN 111261256A
- Authority
- CN
- China
- Prior art keywords
- insulin
- change time
- blood glucose
- time sequence
- big data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Abstract
The invention relates to a big data-based insulin administration method, which comprises the following steps: collecting and storing blood sugar change time sequence parameters in preset time; predicting the subsequent blood glucose change time sequence parameters according to the blood glucose change time sequence parameters in the preset time, and calculating the subsequent insulin change time sequence parameters; and comparing the insulin change time sequence parameter with the normal insulin secretion amount, and making a medication strategy. The invention also provides a storage medium and an insulin delivery system based on the big data, and the accurate delivery of the insulin dose is realized by executing the insulin delivery method based on the big data, so that the inaccurate insulin dose is avoided.
Description
Technical Field
The invention relates to the field of diabetes treatment scheme analysis, in particular to an insulin administration method, a storage medium and a system based on big data.
Background
The existing insulin administration method based on big data is to use an injector to inject a fixed amount of insulin, and when the disease condition changes, namely the blood sugar concentration in a patient changes after treatment, the administration amount cannot be changed in real time, and the patient needs to go to a hospital to make a new diagnosis and then change the administration amount, so that the real-time and accurate administration dosage of the insulin cannot be obtained.
Disclosure of Invention
In order to solve the problem that the insulin administration dosage based on big data cannot be accurately known in real time, the invention provides an insulin administration method, a storage medium and a system based on big data.
The technical scheme for solving the technical problem is to provide an insulin administration method based on big data, which comprises the following steps: collecting and storing blood sugar change time sequence parameters in preset time; predicting the subsequent blood glucose change time sequence parameters according to the blood glucose change time sequence parameters in the preset time, and calculating the subsequent insulin change time sequence parameters; and comparing the subsequent insulin change time sequence parameters with the normal insulin secretion amount, and making a medication strategy.
The invention also provides a storage medium having a computer program stored therein, wherein the computer program is arranged to execute a big data based insulin delivery method when running.
The invention also provides a big data based insulin delivery system, which comprises a processor and a memory, wherein the memory is stored with a computer program, and the computer program is executed by the processor to realize the big data based insulin delivery method.
Compared with the prior art, the insulin administration method, the storage medium and the system based on big data provided by the invention have the following advantages:
by collecting the blood sugar change time sequence parameters in the preset time and deducing the subsequent blood sugar change time sequence parameters, the subsequent insulin secretion amount in the body of a patient is calculated, so that the normal insulin secretion amount is used as a standard, the insulin administration dosage based on big data is accurately formulated, an accurate medication strategy is realized, and the condition of inaccurate insulin dosage is avoided.
The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention. Any other corresponding changes and modifications made according to the technical idea of the present invention should be included in the protection scope of the claims of the present invention.
Drawings
FIG. 1 is a schematic flow chart of a big data based insulin delivery method according to a first embodiment of the present invention;
FIG. 2 is a schematic view of a sub-flow of step S1 in FIG. 1;
FIG. 3 is a graph showing insulin secretion during a meal period;
FIG. 4 is a schematic view of a sub-flow chart of step S3 in FIG. 1;
fig. 5 is a sub-flowchart of step S1 in fig. 1.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the present invention provides a big data-based insulin delivery method, which includes the steps of:
s1, collecting and storing blood sugar change time sequence parameters in preset time;
specifically, the time-series parameter of blood glucose change is the blood glucose concentration corresponding to each time in the body of the diabetic. And collecting the blood sugar change time sequence parameters in the preset time, and recording and storing.
Note that the predetermined time may be one day, one week, one month, or the like, and in the present embodiment, the predetermined time is one month.
It should be noted that the corresponding time in the time series parameters of blood glucose changes can be respectively defined as minute, hour, day, week, etc. according to the required accuracy. That is, the blood glucose concentration of the patient is collected every minute, hour, day, and week, and in the present embodiment, the time is defined as time, that is, the blood glucose concentration is collected every hour.
By way of a specific example, when defining a time of day as the time of day, the collected time series parameter of the change in blood glucose is the hour-patient's blood glucose concentration for the day. That is, the collected blood glucose concentrations of the patients are sorted in chronological order and in hourly units.
It should be noted that the blood glucose variation sequence parameter is collected by drawing blood from a patient and analyzing the blood glucose concentration in the blood.
It should be noted that the collected time series of blood glucose changes are stored in the blockchain.
S2, predicting the subsequent blood sugar change time sequence parameters according to the blood sugar change time sequence parameters in the preset time, and calculating the subsequent insulin change time sequence parameters;
specifically, after the blood glucose change time series parameters in the preset time are collected, a series formed by arranging the blood glucose concentration in the blood of the patient according to the time sequence in the preset time is obtained, namely the blood glucose change time series parameters are a group of data which regularly change according to time. And according to the blood sugar change time sequence parameter in the preset time, the subsequent blood sugar change time sequence parameter can be predicted through regular change.
By way of a specific example, when the predetermined time is one month, the blood glucose concentration of the patient in one month changes regularly with time, such as a linear law or a fluctuating law. The rule is summarized by using data in a predetermined time to estimate the blood glucose concentration corresponding to each time in one or more months following the predetermined time.
After the subsequent blood sugar change time sequence parameters are obtained, the blood sugar concentration corresponding to each subsequent time is compared with the normal allowable concentration, and the required insulin change time sequence parameters corresponding to the blood sugar change time sequence parameters of the patient, namely the insulin secretion amount corresponding to each time in the body of the patient, can be obtained.
As a specific example, the fasting blood glucose concentration of a normal person is 3.9-6.1mmol/L, and in this embodiment, 6.0mmol/L is taken. While normal people secrete 24 units of insulin a day, i.e. one unit of insulin per hour, regardless of the postprandial use. Assuming that the insulin secretion amount per hour for the patient is X, 1/6.0(mmol/L) ═ X/predicted blood glucose concentration of the patient at that time. The insulin secretion of the patient in each hour can be obtained through the formula, and the insulin secretion is sequenced into a series according to the time sequence, so that the insulin change time sequence parameter is obtained.
Note that 40 units of insulin was 1 ml.
S3, comparing the insulin change time sequence parameters with the normal insulin secretion amount, and making a medication strategy;
specifically, after obtaining the time series parameter of the insulin change of the patient, the dosage of the insulin to be supplemented to the patient is obtained according to the difference between the insulin secretion amount corresponding to each moment and the actual insulin secretion amount of a normal person, and then the medication strategy is formulated according to the dosage of the insulin to be supplemented to the patient.
In a specific example, when the time is defined as the time, and the blood glucose concentration in the patient at the time is 12mmol/L, the insulin secretion amount of the patient at the time is 12 mmol/L1/6.0 mmol/L0.5 units by the above formula. That is, the insulin secretion of the patient is 0.5 unit per hour, while that of the normal person is 1 unit per hour, i.e., the patient needs to be supplemented with 1-0.5 unit of insulin per hour.
It will be appreciated that the dosing strategy may be tailored to the patient's habits, such as supplementing a bolus of insulin to be supplemented once an hour, or supplementing a bolus of insulin to be supplemented once a day.
As a specific example, assuming that the patient has an insulin secretion of 0.5 units per hour per day, if the medication strategy is taken to be 1 hour supplementation, the patient is supplemented with 0.5 units of insulin per hour. If the medication strategy is to replenish one for 1 day, the patient is replenished with the difference between the sum of their 24-hour insulin secretion and 24 units of insulin each day, i.e. the patient is replenished with 0.5 x 24 to 12 units of insulin each day.
Referring to fig. 2-3, step S2 further includes the sub-steps of:
s21, predicting the subsequent blood sugar change time sequence parameters according to the collected blood sugar change time sequence parameters in the preset time;
specifically, the time series (or called dynamic number series) refers to a number series formed by arranging the numerical values of the same statistical index according to the occurrence time sequence. The main purpose of time series analysis is to predict the future according to the existing historical data, i.e. to deduce the subsequent blood glucose concentration change from the blood glucose concentration change in a predetermined time. That is, in the present embodiment, the change in blood glucose concentration of the patient after one month is estimated from the change in blood glucose concentration of the patient collected within one month.
S22, marking the dining time periods in the subsequent blood sugar change time series parameters;
specifically, the insulin secretion amount can be divided into a basal insulin secretion amount and a meal insulin secretion amount, and the two insulin secretion amounts each account for about 50% of the basal insulin. That is, the basal insulin secretion is independent of food intake or refers to insulin secretion in the fasting state, and the main physiological actions of basal insulin are to reduce glucose production and maintain glucose utilization by peripheral tissues and organs (such as brain, muscle, etc.) by inhibiting hepatic glycogenolysis and gluconeogenesis, so that the blood glucose in the fasting state is kept at the normal level insulin secretion. The insulin secretion amount during meal is the insulin secretion amount under the stimulation of meal, the early-phase secretion controls the amplitude and duration of postprandial blood sugar rise, and the main effect is to inhibit the generation of liver endogenous glucose.
In general, the daily insulin secretion of a normal person is 48 units, wherein the basal insulin secretion is 24 units, and one unit is secreted in 1 hour on average. The insulin secretion was 24 at meals, three meals a day, with an average of 8 units per meal. And usually, three meals every day are at the same or similar time, and 3 times in a day are marked as a dining time period, so that when a medication strategy is established, the dosage of medication is adjusted at 3 times of the dining time period.
Referring to fig. 4, step S3 further includes the sub-steps of:
s31, increasing the dosage of the meal time period;
specifically, after the meal time period is marked and the medication strategy made by comparing the insulin change time sequence with the normal insulin secretion is used, if the medication time period is just the moment of the marked meal time period, the medication needs to be supplemented, so that the insulin secretion in the body of the patient reaches the insulin secretion of a normal person during meal.
As a specific example, assuming that the patient has three meals a day with meal times of 8:00, 12:00 and 18:00 respectively, and blood glucose concentrations at the three times are all 12mmol/L, the calculation in the above steps can result in that the insulin secretion of the patient at the three times is 0.5 unit, which is less than 0.5 unit compared with the normal person, so that 0.5 unit of insulin needs to be supplemented. However, since the three times are meal times, the normal person actually has 8 units more insulin secretion at each of the three times, and therefore, in addition to 0.5 units of insulin, 8 units of insulin should be supplemented in the three time periods. That is, at the time of the three meal periods, the patient needs to be replenished with 8.5 units of insulin in total.
It should be noted that 0.5 units of insulin supplemented by the patient is basal insulin, and 8 units of insulin supplemented is prandial insulin.
Further, step S3 further includes the sub-steps of:
s32, establishing a medication strategy model by using the insulin change time sequence parameter to formulate a medication strategy;
specifically, a medication strategy model is established according to the insulin secretion amount and the normal insulin secretion amount corresponding to each moment of the patient. That is, the patient's insulin secretion is subtracted from the normal insulin secretion to obtain the administered dose.
Referring to fig. 5, step S1 is preceded by the steps of:
s10, pre-storing normal blood sugar concentration and insulin secretion;
specifically, before collecting the time series parameters of the blood sugar change of the patient, the blood sugar concentration and daily insulin secretion of the normal person are obtained to be used as reference standards, so that the subsequent calculation and the formulation of medication strategies are facilitated.
The invention also provides a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the above-mentioned method steps when run. The storage medium may include, for example, a floppy disk, an optical disk, a DVD, a hard disk, a flash Memory, a usb-disk, a CF card, an SD card, an MMC card, an SM card, a Memory Stick (Memory Stick), an XD card, etc.
A computer software product is stored on a storage medium and includes instructions for causing one or more computer devices (which may be personal computer devices, servers or other network devices, etc.) to perform all or a portion of the steps of the method of the present invention.
The invention also provides a big data based insulin delivery system, which comprises a processor and a memory, wherein the memory stores a computer program, and the computer program is executed by the processor to realize the big data based insulin delivery method.
Compared with the prior art, the insulin administration method, the storage medium and the system based on big data provided by the invention have the following advantages:
by collecting the blood sugar change time sequence parameters in the preset time and deducing the subsequent blood sugar change time sequence parameters, the subsequent insulin secretion amount in the body of a patient is calculated, so that the normal insulin secretion amount is used as a standard, the insulin administration dosage based on big data is accurately formulated, an accurate medication strategy is realized, and the condition of inaccurate insulin dosage is avoided.
By marking the dining time period, the situation that the insulin secretion amount is increased rapidly during dining can be solved, so that the dosage during dining is increased on the basis of the basic dosage.
The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention. Any other corresponding changes and modifications made according to the technical idea of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A method of insulin delivery based on big data, the method comprising:
collecting and storing blood sugar change time sequence parameters in preset time;
predicting the subsequent blood glucose change time sequence parameters according to the blood glucose change time sequence parameters in the preset time, and calculating the subsequent insulin change time sequence parameters; and
and comparing the subsequent insulin change time sequence parameters with the normal insulin secretion amount, and making a medication strategy.
2. The method of claim 1, wherein the step of administering insulin comprises: the predicting the subsequent blood glucose change time series parameter according to the blood glucose change time series parameter in the predetermined time and calculating the subsequent insulin change time series parameter comprises:
predicting the subsequent blood glucose change time sequence parameters according to the collected blood glucose change time sequence parameters in the preset time; and
the meal time period in the subsequent time series of blood glucose changes parameter is marked.
3. A method of insulin administration based on big data as claimed in claim 2, wherein: the step of comparing the insulin change time sequence parameter with the normal insulin secretion amount and making a medication strategy comprises the following steps:
increasing the dosage of medication for the meal time period; and
and establishing a medication strategy model by using the insulin change time sequence parameter so as to establish a medication strategy.
4. A method of insulin administration based on big data as claimed in claim 3, wherein:
the medication strategy model is that the normal insulin secretion is subtracted by the corresponding insulin secretion at each moment in the subsequent insulin change time sequence parameters to obtain the dosage of medication.
5. The method of claim 1, wherein the step of administering insulin comprises:
the insulin secretion amount comprises a basic insulin secretion amount and an insulin secretion amount during meal, the basic insulin secretion amount is an insulin secretion amount in an empty stomach state, and the insulin secretion amount during meal is an insulin secretion amount under meal stimulation.
6. The method of claim 1, wherein the step of administering insulin comprises: before the acquiring and storing the time series parameters of the blood glucose change in the preset time, the method further comprises the following steps:
normal blood sugar concentration and insulin secretion are prestored.
7. The method of claim 1, wherein:
the method for collecting the time series parameters of the blood glucose change in the preset time is to draw blood and analyze the blood glucose concentration in the blood.
8. The method of claim 1, wherein the step of administering insulin comprises:
the blood glucose change time series parameters are stored in a blockchain.
9. A storage medium, characterized by:
the storage medium has stored therein a computer program, wherein the computer program is arranged to execute the big data based insulin delivery method according to any of the claims 1-8 when executed.
10. A big data based insulin delivery system, characterized by:
the big data based insulin delivery system comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is executed by the processor to realize the big data based insulin delivery method according to the claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010061791.4A CN111261256A (en) | 2020-01-19 | 2020-01-19 | Insulin administration method, storage medium and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010061791.4A CN111261256A (en) | 2020-01-19 | 2020-01-19 | Insulin administration method, storage medium and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111261256A true CN111261256A (en) | 2020-06-09 |
Family
ID=70954392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010061791.4A Pending CN111261256A (en) | 2020-01-19 | 2020-01-19 | Insulin administration method, storage medium and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111261256A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030028089A1 (en) * | 2001-07-31 | 2003-02-06 | Galley Paul J. | Diabetes management system |
| CN102000372A (en) * | 2010-12-09 | 2011-04-06 | 江苏华阳电器有限公司 | Intelligent insulin pump system |
| CN109564775A (en) * | 2016-08-18 | 2019-04-02 | 诺和诺德股份有限公司 | The system and method for insulin drug dose when for optimizing the meal for being directed to dining event |
| CN209154758U (en) * | 2018-08-28 | 2019-07-26 | 珠海市富立信医疗设备应用技术开发有限公司 | A kind of intelligent injection system |
| CN110582231A (en) * | 2017-05-05 | 2019-12-17 | 伊莱利利公司 | Closed loop control of physiological glucose |
-
2020
- 2020-01-19 CN CN202010061791.4A patent/CN111261256A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030028089A1 (en) * | 2001-07-31 | 2003-02-06 | Galley Paul J. | Diabetes management system |
| CN102000372A (en) * | 2010-12-09 | 2011-04-06 | 江苏华阳电器有限公司 | Intelligent insulin pump system |
| CN109564775A (en) * | 2016-08-18 | 2019-04-02 | 诺和诺德股份有限公司 | The system and method for insulin drug dose when for optimizing the meal for being directed to dining event |
| CN110582231A (en) * | 2017-05-05 | 2019-12-17 | 伊莱利利公司 | Closed loop control of physiological glucose |
| CN209154758U (en) * | 2018-08-28 | 2019-07-26 | 珠海市富立信医疗设备应用技术开发有限公司 | A kind of intelligent injection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10960137B2 (en) | Blood glucose control system with automated backup therapy protocol generation | |
| US20210361867A1 (en) | Integrated closed-loop medication delivery with error model and safety check | |
| JP5728767B2 (en) | Monitoring system, method and computer program for management of insulin delivery | |
| US6923763B1 (en) | Method and apparatus for predicting the risk of hypoglycemia | |
| Hann et al. | Integral-based parameter identification for long-term dynamic verification of a glucose–insulin system model | |
| CA2615575C (en) | Systems, methods and computer program products for recognition of patterns of hyperglycemia in a user | |
| US11957876B2 (en) | Glucose control system with automated backup therapy protocol generation | |
| WO2005084733A1 (en) | Method and device for calculating a bolus amount | |
| US20210256872A1 (en) | Devices, systems, and methods for predicting blood glucose levels based on a personalized blood glucose regulation model | |
| WO2016022989A2 (en) | Systems and methods for monitoring and controlling a cardiovascular state of a subject | |
| Chase et al. | Integral-based filtering of continuous glucose sensor measurements for glycaemic control in critical care | |
| EP4042436A1 (en) | Blood glucose control system | |
| WO2001013786A1 (en) | Method and apparatus for predicting the risk of hypoglycemia | |
| Schmidt et al. | Effects of everyday life events on glucose, insulin, and glucagon dynamics in continuous subcutaneous insulin infusion–treated type 1 diabetes: collection of clinical data for glucose modeling | |
| Ozaslan et al. | Impact of daily physical activity as measured by commonly available wearables on mealtime glucose control in type 1 diabetes | |
| CN113643820A (en) | Early warning information generation method and device, computer equipment and storage medium | |
| CN111261256A (en) | Insulin administration method, storage medium and system based on big data | |
| Georga et al. | Prediction of glucose concentration in type 1 diabetic patients using support vector regression | |
| CN117280423A (en) | Method and apparatus for postprandial blood glucose level prediction | |
| EP3586338A1 (en) | Systems and methods for communicating a dose | |
| CN111261257A (en) | Diabetes recommended medication method, storage medium and system based on big data | |
| US20240123148A1 (en) | Control device for determining a recommendation value of a control parameter of a fluid infusion device | |
| Piersanti et al. | Comparison of software packages for the analysis of continuous glucose monitoring data | |
| CN116779186B (en) | Adenosine cyclophosphate drug data information processing system for arrhythmia patients | |
| US20230138746A1 (en) | Systems and methods for a data driven framework for actionable feedback in insulin management for type 1 diabetic subjects on artificial pancreas |
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 |