CN117542476A - Insulin injection dosage supervision method and system based on self-learning - Google Patents
Insulin injection dosage supervision method and system based on self-learning Download PDFInfo
- Publication number
- CN117542476A CN117542476A CN202311291878.0A CN202311291878A CN117542476A CN 117542476 A CN117542476 A CN 117542476A CN 202311291878 A CN202311291878 A CN 202311291878A CN 117542476 A CN117542476 A CN 117542476A
- Authority
- CN
- China
- Prior art keywords
- patient
- meal
- insulin injection
- short
- injection dosage
- 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
- 238000002347 injection Methods 0.000 title claims abstract description 207
- 239000007924 injection Substances 0.000 title claims abstract description 207
- 238000000034 method Methods 0.000 title claims abstract description 24
- NOESYZHRGYRDHS-UHFFFAOYSA-N insulin Chemical compound N1C(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(NC(=O)CN)C(C)CC)CSSCC(C(NC(CO)C(=O)NC(CC(C)C)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CCC(N)=O)C(=O)NC(CC(C)C)C(=O)NC(CCC(O)=O)C(=O)NC(CC(N)=O)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CSSCC(NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2C=CC(O)=CC=2)NC(=O)C(CC(C)C)NC(=O)C(C)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2NC=NC=2)NC(=O)C(CO)NC(=O)CNC2=O)C(=O)NCC(=O)NC(CCC(O)=O)C(=O)NC(CCCNC(N)=N)C(=O)NCC(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC(O)=CC=3)C(=O)NC(C(C)O)C(=O)N3C(CCC3)C(=O)NC(CCCCN)C(=O)NC(C)C(O)=O)C(=O)NC(CC(N)=O)C(O)=O)=O)NC(=O)C(C(C)CC)NC(=O)C(CO)NC(=O)C(C(C)O)NC(=O)C1CSSCC2NC(=O)C(CC(C)C)NC(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CC(N)=O)NC(=O)C(NC(=O)C(N)CC=1C=CC=CC=1)C(C)C)CC1=CN=CN1 NOESYZHRGYRDHS-UHFFFAOYSA-N 0.000 title claims description 189
- 229940125396 insulin Drugs 0.000 title claims description 97
- 102000004877 Insulin Human genes 0.000 title claims description 92
- 108090001061 Insulin Proteins 0.000 title claims description 92
- 239000008280 blood Substances 0.000 claims abstract description 132
- 210000004369 blood Anatomy 0.000 claims abstract description 132
- 235000012054 meals Nutrition 0.000 claims abstract description 124
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims abstract description 105
- 239000008103 glucose Substances 0.000 claims abstract description 104
- 108010026951 Short-Acting Insulin Proteins 0.000 claims abstract description 85
- 229940123958 Short-acting insulin Drugs 0.000 claims abstract description 85
- 239000003814 drug Substances 0.000 claims abstract description 72
- 229940079593 drug Drugs 0.000 claims abstract description 71
- 150000001720 carbohydrates Chemical class 0.000 claims abstract description 16
- 235000014633 carbohydrates Nutrition 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 230000008859 change Effects 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 19
- 235000013305 food Nutrition 0.000 claims description 19
- 238000013524 data verification Methods 0.000 claims description 17
- 230000000291 postprandial effect Effects 0.000 claims description 14
- 206010012601 diabetes mellitus Diseases 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 11
- 238000012790 confirmation Methods 0.000 claims description 7
- 229940090044 injection Drugs 0.000 description 144
- 201000001421 hyperglycemia Diseases 0.000 description 9
- 230000002218 hypoglycaemic effect Effects 0.000 description 9
- 235000005911 diet Nutrition 0.000 description 8
- 208000013016 Hypoglycemia Diseases 0.000 description 7
- 230000037213 diet Effects 0.000 description 7
- 201000010099 disease Diseases 0.000 description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 6
- 239000003925 fat Substances 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 230000001419 dependent effect Effects 0.000 description 4
- 230000003914 insulin secretion Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000011002 quantification Methods 0.000 description 4
- 230000007812 deficiency Effects 0.000 description 3
- 230000036961 partial effect Effects 0.000 description 3
- 230000002829 reductive effect Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 208000001380 Diabetic Ketoacidosis Diseases 0.000 description 2
- 229920002527 Glycogen Polymers 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- WQZGKKKJIJFFOK-VFUOTHLCSA-N beta-D-glucose Chemical compound OC[C@H]1O[C@@H](O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-VFUOTHLCSA-N 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 235000008242 dietary patterns Nutrition 0.000 description 2
- 230000037406 food intake Effects 0.000 description 2
- 229940096919 glycogen Drugs 0.000 description 2
- 230000004116 glycogenolysis Effects 0.000 description 2
- 229940088597 hormone Drugs 0.000 description 2
- 239000005556 hormone Substances 0.000 description 2
- 210000005229 liver cell Anatomy 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 208000030159 metabolic disease Diseases 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 208000001072 type 2 diabetes mellitus Diseases 0.000 description 2
- VOUAQYXWVJDEQY-QENPJCQMSA-N 33017-11-7 Chemical compound OC(=O)CC[C@H](N)C(=O)N[C@@H](C)C(=O)N[C@@H](CCC(O)=O)C(=O)N[C@@H](CC(O)=O)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](C(C)C)C(=O)NCC(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CCC(O)=O)C(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)NCC(=O)NCC(=O)N1CCC[C@H]1C(=O)NCC(=O)N[C@@H](C)C(=O)NCC(=O)N[C@@H](CO)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCC(N)=O)C(=O)N1[C@H](C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCC(O)=O)C(=O)NCC(=O)N[C@@H](CO)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CCC(N)=O)C(O)=O)CCC1 VOUAQYXWVJDEQY-QENPJCQMSA-N 0.000 description 1
- 108010075254 C-Peptide Proteins 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010008479 Chest Pain Diseases 0.000 description 1
- 206010010071 Coma Diseases 0.000 description 1
- 208000002249 Diabetes Complications Diseases 0.000 description 1
- 206010012655 Diabetic complications Diseases 0.000 description 1
- 102000017011 Glycated Hemoglobin A Human genes 0.000 description 1
- 108010014663 Glycated Hemoglobin A Proteins 0.000 description 1
- 208000008454 Hyperhidrosis Diseases 0.000 description 1
- 206010022489 Insulin Resistance Diseases 0.000 description 1
- 102000016261 Long-Acting Insulin Human genes 0.000 description 1
- 108010092217 Long-Acting Insulin Proteins 0.000 description 1
- 229940100066 Long-acting insulin Drugs 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 206010033307 Overweight Diseases 0.000 description 1
- 206010033557 Palpitations Diseases 0.000 description 1
- 208000037273 Pathologic Processes Diseases 0.000 description 1
- 208000017442 Retinal disease Diseases 0.000 description 1
- 206010038923 Retinopathy Diseases 0.000 description 1
- 206010044565 Tremor Diseases 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 150000007513 acids Chemical class 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 210000000577 adipose tissue Anatomy 0.000 description 1
- 150000001413 amino acids Chemical class 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000000227 basophil cell of anterior lobe of hypophysis Anatomy 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000005842 biochemical reaction Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 230000032823 cell division Effects 0.000 description 1
- 230000010261 cell growth Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 235000014113 dietary fatty acids Nutrition 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229930195729 fatty acid Natural products 0.000 description 1
- 239000000194 fatty acid Substances 0.000 description 1
- 150000004665 fatty acids Chemical class 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004110 gluconeogenesis Effects 0.000 description 1
- 229940093181 glucose injection Drugs 0.000 description 1
- 230000004190 glucose uptake Effects 0.000 description 1
- 230000002641 glycemic effect Effects 0.000 description 1
- 230000012010 growth Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002757 inflammatory effect Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000004153 islets of langerhan Anatomy 0.000 description 1
- 150000002576 ketones Chemical class 0.000 description 1
- 208000017169 kidney disease Diseases 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 150000002632 lipids Chemical class 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 230000003908 liver function Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000007102 metabolic function Effects 0.000 description 1
- VUZPPFZMUPKLLV-UHFFFAOYSA-N methane;hydrate Chemical compound C.O VUZPPFZMUPKLLV-UHFFFAOYSA-N 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 210000000663 muscle cell Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 201000001119 neuropathy Diseases 0.000 description 1
- 230000007823 neuropathy Effects 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 210000000496 pancreas Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000009054 pathological process Effects 0.000 description 1
- 208000033808 peripheral neuropathy Diseases 0.000 description 1
- 230000004962 physiological condition Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000022558 protein metabolic process Effects 0.000 description 1
- 238000001243 protein synthesis Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000017854 proteolysis Effects 0.000 description 1
- 210000003705 ribosome Anatomy 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000035900 sweating Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000014616 translation Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
-
- 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
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present application provides a method and system for calculating and supervising pre-meal short-acting insulin injections for diabetics by adjusting and calculating the short-acting insulin injections from a dynamic multiple regression model comprising (i) pre-meal blood glucose values for the patient, (ii) post-meal blood glucose values for the patient, and (iii) quantified data for the patient's meal carbohydrates. The method and the system can relieve the pressure of medical staff on monitoring the blood sugar of the patient in real time, and can provide more accurate medication guidance for the patient so as to ensure the patient to control the blood sugar more stably for a long time and adjust the blood sugar in a short time.
Description
Technical Field
The invention relates to a self-learning-based insulin injection dosage supervision method and system, in particular to a personalized self-learning-based method and related system for collecting symptom data of diabetics and calculating feedback insulin injection dosage.
Background
Diabetes is a major health challenge worldwide. Diabetes is a group of heterogeneous metabolic diseases characterized by chronic hyperglycemia, which are caused by insulin secretion defects and/or insulin action defects and by chronic hyperglycemia accompanied by metabolic disorders of carbohydrates, fats and proteins. Over 95% of the population with diabetes mellitus is type 2 diabetes, and the risk of developing it is mainly related to age, overweight or obesity, unhealthy diet and lack of exercise.
Insulin is the most important hormone for the body to maintain blood glucose stable, and is a hormone secreted, produced and released by the beta cells of the islets of langerhans in the pancreas. It plays a key role in regulating blood sugar level in human body, and mainly reduces liver sugar output by promoting glucose uptake and utilization, glycogen synthesis, inhibiting gluconeogenesis and glycogenolysis, thereby reducing blood sugar. When the human body eats, the food is absorbed by digestion, the blood sugar level rises, the insulin secretion increases rapidly, all tissues of the whole body can accelerate the ingestion and storage of glucose, especially the ingestion of glucose by liver cells and muscle cells can be accelerated, the glucose is converted into glycogen to be stored, or the glucose is converted into fatty acid in the liver cells to be transported to the fatty tissue to be stored, and thus the blood sugar concentration is reduced. Thus, insulin can lower blood glucose levels and prevent hyperglycemia. Insulin secretion is reduced when the human is fasted or starved, so that stored glycogenolysis re-enters the blood, and blood glucose is kept stable. Insulin can promote amino acids to enter cells, directly act on ribosomes, and promote protein synthesis. It also inhibits protein degradation. In addition, insulin plays a very important role in promoting fat synthesis and storage. At the same time, insulin also inhibits fat breakdown. Insulin also plays a role in the growth and division of cells. Insulin signals can affect a range of biochemical reactions that affect cell growth, division, and survival. In general, insulin maintains the stability of blood glucose levels by regulating glucose, fat and protein metabolism, and balances the utilization and storage of energy among tissues in the body. Insulin is an important regulator, critical to the body's energy balance and normal metabolic function.
Most type 2 diabetics do not have sufficient endogenous insulin to provide a physical warranty. The impact of endogenous insulin deficiency on the body can be very severe, as insulin is primarily responsible for regulating blood glucose levels. In the absence of sufficient insulin. Insulin deficiency results in the body not being able to use or store blood glucose effectively, resulting in an elevated blood glucose level, so-called hyperglycemia. Severe hyperglycemia or low insulin will result in the body not being able to use glucose effectively or will turn to fat storage as an energy source. This results in the breakdown of fat into ketone bodies, which acids the blood, leading to the onset of Diabetic Ketoacidosis (DKA), a life threatening disease. Long-term insulin deficiency may lead to a range of complications including retinopathy, nephropathy, neuropathy (leading to skin, muscle, vascular and neural lesions), cardiovascular disease and the like.
Insulin injection is an important treatment means for controlling blood sugar of diabetics with poor blood sugar control after dietary control, oral medicine intervention and other measures. As shown in fig. 1, accounting adjustment should be performed according to the blood sugar state of the patient and the related physiological conditions such as pathological process, so as to determine reasonable injection dosage, accuracy, injection time, injection mode and the like of insulin.
Among diabetics, elderly people have a high percentage, and the elderly people are generally unable to well adjust insulin injection dosage according to their current blood glucose condition and disease course during the period of illness. Meanwhile, since the injection dose of insulin needs to be comprehensively calculated in consideration of the current diet state and food type of the patient, the patient cannot normally accurately adjust the injection dose of insulin according to his own experience. In the case of hyperglycemia, if the amount of insulin injected in a short period exceeds the body's required amount, serious side effects including dizziness, chest distress, palpitation, sweating, tremor may occur, and serious cases may lead to abnormal mental behavior, blurred consciousness, and even coma death. When people often have a hypoglycemic condition, the body may no longer exhibit typical hypoglycemic symptoms, which may lead to more severe hypoglycemia, as people may not be aware that their blood glucose level is decreasing. Insufficient insulin injection causes hyperglycemia to be difficult to control. The regulation of the insulin injection amount requires reasonable adjustment management with the help of a professional specialist, and the amount of the dosage depends on the individual difference of the patients, the course of the disease and the current state of the patients. Reasonable adjustment of the dose of insulin injections is also a therapeutic challenge for the physician.
Depending on the physiological characteristics of insulin secretion, diabetics often need to inject more than 3 times per day of short-acting insulin to ensure reasonable levels of blood glucose during a meal.
Meanwhile, in order to ensure the stability of blood sugar throughout the day, it is also generally required to inject a long-acting insulin to ensure the control of daily blood sugar in the body. The patient's physician in charge needs to track the patient's diet, course and current blood glucose level for proper insulin dosage adjustments to ensure control of the patient's body blood glucose level, as shown in the diabetic blood glucose-insulin injection dosage intervention result graph of fig. 2.
Multiple daily injections of short-acting insulin and lack of accurate administration of the injected dose may result in poor glycemic control in the patient and an increased risk of developing short-term hyperglycemia or hypoglycemia in the patient. And prolonged hyperglycemia or hypoglycemia tends to increase the risk of developing and developing diabetic complications.
The physician in charge of the patient is often not guaranteed to synchronize advice and guidance of the blood glucose level of a large number of patients more than three times a day due to regional, temporal and other factors.
Disclosure of Invention
The present application provides a method and system for calculating and supervising pre-meal short-acting insulin injections for diabetics by adjusting and calculating the short-acting insulin injections from a dynamic multiple regression model comprising (i) pre-meal blood glucose values for the patient, (ii) post-meal blood glucose values for the patient, and (iii) quantified data for the patient's meal carbohydrates, resulting in a reasonable pre-meal short-acting insulin injections for the patient.
According to the technical scheme, the pre-meal blood glucose value FBS (x mmol/L), the two-hour postprandial blood glucose value PBG (y mmol/L) and the quantized value GIn of the food carbohydrate of a meal of a diabetic patient are obtained in real time through a continuous blood glucose monitoring system (CGM). And continuously performing multiple regression model data training on the parameters to obtain a dynamic medication adjustment model for long-term medication. The computing device controls the blood sugar of the patient according to the dynamic medication adjustment model and the medication standard range, and utilizes the dynamic medication adjustment model to generate pre-meal short-acting insulin injection (RIV) for medication dosage prompt.
When the pre-meal short-acting insulin injection dose (RIV) calculated using the recommended blood glucose standard and the dynamic medication adjustment model is within the reasonable range of the order (i.v. max-i.v. min), the system will notify the patient to inject according to the order medication standard without intervention by medical personnel. When the calculated pre-meal short-acting insulin injection dose (RIV) exceeds a reasonable range of orders (i.v. max-i.v. min) or the change ratio Δvr relative to the last insulin injection dose is greater than a set change ratio threshold value Δv VRd, the system transmits the real-time blood glucose status and disease course data of the patient to a cloud server and/or a handheld device of medical personnel through the internet. In some examples, the cloud server transmits the real-time blood glucose status of the patient, the course data, and the patient's profile to a handheld device of the medical personnel. Medical staff properly adjusts pre-meal short-acting insulin injection (RIV) prescription data according to the confirmed insulin injection standard, the real-time blood sugar state of the patient and the disease course data, and then sends the adjusted pre-meal short-acting insulin injection (RIV) prescription data to the patient through the Internet. The patient performs insulin injections based on the received adjusted pre-meal short-acting insulin injection (RIV) prescription data. Therefore, the pressure of medical staff for monitoring the blood sugar of the patient in real time can be reduced, and more accurate medication guidance can be provided for the patient so as to ensure the patient to control the blood sugar more stably for a long time and adjust the blood sugar in a short time.
In one aspect of the invention, an insulin injection dosage monitoring system is provided that acquires patient data and self-learns. The insulin injection dose monitoring system may include: a patient mobile terminal configured to obtain a real-time blood glucose value of a patient; an injection data verification service system; and a physician mobile terminal. In some examples, the patient mobile terminal and the physician mobile terminal are each communicatively connected to the injection data verification service system. The patient mobile terminal may include a calculation module configured to learn data logic between a pre-meal blood glucose value, a quantified value of food carbohydrates for a meal, a 2-hour post-meal blood glucose, a pre-meal short-acting insulin injection dose, and a normal blood glucose range of a diabetic patient, and generate a dynamic medication adjustment model associated with an individual patient from the statistical logic between the data, the dynamic medication adjustment model configured to dynamically calculate and adjust the pre-meal short-acting insulin injection dose of the patient.
In another aspect of the invention, a system is provided that includes one or more computer processors and computer readable memory. The computer readable memory includes machine executable code that when executed by the one or more computer processors implements an insulin injection dosage administration method that obtains patient data and self-learns. In some examples, the insulin injection dose monitoring method comprises: acquiring the real-time blood glucose value of a patient and the current pre-meal short-acting insulin injection dosage of the doctor's advice; acquiring a dynamic medication adjustment model of a patient; calculating the pre-meal short-acting insulin injection dosage of the patient by using the dynamic medication adjustment model; and if the pre-meal short-acting insulin injection dosage calculated by the dynamic medication adjustment model is within a reasonable range of a medical order, notifying the patient to perform injection according to the medical order medication standard; and if the pre-meal short-acting insulin injection dosage calculated by the dynamic medication adjustment model exceeds the reasonable range of the medical advice or the change proportion relative to the latest insulin injection dosage is larger than a preset change proportion threshold value, generating an overrun injection dosage verification request. In some examples, the dynamic medication adjustment model is configured to dynamically calculate and adjust the pre-meal short-acting insulin injection dose of the patient by learning and generating from statistical logic between pre-meal blood glucose values, quantified food carbohydrate values of meals, 2 hours postprandial blood glucose, pre-meal short-acting insulin injection doses, and normal blood glucose ranges of diabetics.
In one aspect of the invention, a method of insulin injection dosage supervision is provided that acquires patient data and self-learns. The insulin injection dose monitoring method may include: acquiring the real-time blood glucose value of a patient and the current pre-meal short-acting insulin injection dosage of the doctor's advice; acquiring a dynamic medication adjustment model of a patient; calculating the pre-meal short-acting insulin injection dosage of the patient by using the dynamic medication adjustment model; and if the pre-meal short-acting insulin injection dosage calculated by the dynamic medication adjustment model is within a reasonable range of a medical order, notifying the patient to perform injection according to the medical order medication standard; and if the pre-meal short-acting insulin injection dosage calculated by the dynamic medication adjustment model exceeds the reasonable range of the medical advice or the change proportion relative to the latest insulin injection dosage is larger than a preset change proportion threshold value, generating an overrun injection dosage verification request. In some examples, the dynamic medication adjustment model is configured to dynamically calculate and adjust the pre-meal short-acting insulin injection dose of the patient by learning and generating from statistical logic between pre-meal blood glucose values, quantified food carbohydrate values of meals, 2 hours postprandial blood glucose, pre-meal short-acting insulin injection doses, and normal blood glucose ranges of diabetics.
Drawings
FIG. 1 is a graph of the progression of diabetes in a patient showing the change in blood glucose, fasting blood glucose, insulin resistance and insulin levels of the patient as a function of the patient's progression.
FIG. 2 is a graph of blood glucose-insulin injection dose change for a diabetic patient, showing changes in patient blood glucose, insulin dose, and patient blood glucose after injection of insulin as the patient progresses through a meal.
Fig. 3 is a schematic diagram showing the self-learning based insulin injection dose management system for diabetics of the present invention.
Fig. 4-6 are flowcharts showing the self-learning based insulin injection dose management method for diabetics of the present invention.
Detailed Description
The application provides an insulin injection dosage supervision method and system for acquiring patient data and performing self-learning. As shown in fig. 3, the system of the present application may include a patient mobile terminal 301, an injection data verification service system 311, and a physician mobile terminal 321. The patient mobile terminal 301 and the physician mobile terminal 321 are respectively connected in two-way communication with the injection data verification service system 311.
The patient mobile terminal 301 may be a smart device capable of running a software program or App, such as a smart phone, tablet, notebook, or the like. The patient mobile terminal 301 may communicate with an online blood glucose monitoring sensor 302 (e.g., CGM continuous blood glucose monitoring system) via a communication link (e.g., infrared, bluetooth, zigbee near field communication link) to obtain real-time blood glucose values for diabetics from the online blood glucose monitoring sensor 302. The patient mobile terminal 301 may also obtain real-time blood glucose values for diabetics from an offline blood glucose monitoring device 305 (e.g., a blood glucose meter). For example, the patient may manually input the blood glucose measurement into the patient mobile terminal 301. For example, the offline blood glucose monitoring device 305 may input blood glucose measurements into the patient mobile terminal 301 over a bluetooth link. The patient mobile terminal 301 may include a computing module 303. The calculation module 303 is configured to learn data logic between the pre-meal blood glucose value (FBG) of a diabetic patient, the quantified value of food carbohydrates (GIN) of a meal, the 2-hour Postprandial Blood Glucose (PBG), the pre-meal short-acting insulin injection dose (RIV) and the normal blood glucose range and to generate a dynamic medication adjustment model related to the individual patient from the statistical logic between the above data. The pre-meal short acting insulin injection (RIV) of the patient is calculated and adjusted by the dynamic medication adjustment model of the patient.
When the pre-meal short-acting insulin injection dose (RIV) calculated by the patient mobile terminal 301 using the dynamic medication adjustment model is within the reasonable range of the order (i.v. max-i.v. min), the calculation module 303 will inform the patient to inject according to the order medication standard without intervention by medical personnel. When the pre-meal short-acting insulin injection dose (RIV) calculated by the patient mobile terminal 301 using the dynamic medication adjustment model exceeds the order reasonable range (i.v. max-i.v. min) or the change ratio Δvr with respect to the last insulin injection dose is greater than the set change ratio threshold value Δ VRd, the calculation module 303 will generate an over-limit injection dose check request 304 and send the over-limit injection dose check request 304 to the injection data check service system 311 via a communication link (e.g. internet, local area network, 4G communication network, 5G communication network). In one example, the calculation module 303 also sends the pre-meal short-acting insulin injection dose (RIV) calculated using the dynamic medication adjustment model to the injection data verification service system 311.
The injection data verification service system 311 may be a system implemented on a cloud server. The injection data verification service system 311 may include a patient injection metering verification server 312 for verifying, storing, etc. the over-limit injection dose verification request 304 sent from the patient mobile terminal 301. In one example, when checking the request 304 for an over-limit injection dose sent from the patient mobile terminal 301, the patient injection metering check server 312 generates and sends a physician metering prescription request 313 to the physician mobile terminal 321 over the communication link. In one example, the injection data verification service system 311 may also send the real-time blood glucose status of the patient and the pre-meal short-acting insulin injection dose (RIV) calculated using the dynamic medication adjustment model to the physician mobile terminal 321.
The physician mobile terminal 321 may be a smart device, such as a smart phone, tablet, notebook, etc., capable of running a software program or App. In one example, upon receiving a physician metering prescription request 313 from the patient injection metering verification server 312, the physician mobile terminal 321 may generate a physician metering prescription confirmation 322 based on the patient's real-time blood glucose status, course data, pre-meal short-acting insulin injection doses (RIVs) calculated using the dynamic medication adjustment model, and make appropriate adjustments to the pre-meal short-acting insulin injection doses (RIVs) calculated using the dynamic medication adjustment model with reference to the pre-meal short-acting insulin injection doses previously determined, and send the physician metering prescription confirmation 322 back to the injection data verification service system 311 over the communication link. Upon receipt of the physician metered prescription confirmation 322, the injection data verification service system 311 generates and transmits an over-limit injection dose physician confirmation 314 to the patient mobile terminal 301, thereby allowing the patient to perform an injection of insulin based on the received physician-adjusted pre-meal short-acting insulin injection dose (RIV) prescription data. In the above example, the patient's course data may be provided to the physician mobile terminal 321 from the injection data verification service system 311, or may be obtained from another server.
Fig. 4-6 are flowcharts showing the self-learning based insulin injection dose management method for diabetics of the present invention. In step 401, the method of the present invention is initiated. Subsequently, a series of initialization operations are performed. For example, in step 402, the patient's underlying data is initialized. In one example, patient base data may be read from a server or a patient mobile terminal. The patient base data may include the age, sex, type of diabetes, time of illness, etc. of the patient. In step 403, patient course data is initialized. In one example, the course data may be read from a hospital database. The course data may include patient daily pathological examination data such as patient daily C-peptide levels, glycosylated hemoglobin, blood lipid levels, blood pressure, body weight, inflammatory markers, liver function markers, and the like. In step 404, the current physician prescribed insulin injection dose may be initialized. In one example, the current physician prescribed insulin injection dose may be a range of insulin injection doses.
In step 405, a real-time blood glucose value of the patient is obtained. In one example, the real-time blood glucose value of a patient may be read from a continuous blood glucose monitoring system (CGM). In another example, the patient may manually input the blood glucose measurement into the patient mobile terminal 301. In step 406, a determination is made as to whether a dynamic medication adjustment model exists for the patient. If the patient does not have a dynamic medication adjustment model, a blood glucose-insulin injection dose regression model is generated for the patient and a blood glucose-insulin injection dose regression model library for the patient is stored in step 407. If the patient has a dynamic medication adjustment model, a blood glucose-insulin injection dose regression model library is read in step 408 and the dynamic medication adjustment model is used to generate pre-meal short-acting insulin injection doses in step 409.
Subsequently, in step 410, a determination is made as to whether the pre-meal short-acting insulin injection calculated using the dynamic medication adjustment model is within the prescribed injection dosage range. If it is determined in step 410 that the calculated pre-meal short-acting insulin injection dose is within the prescribed injection dose range, it is further determined in step 411 whether the rate of change of the insulin injection amount with respect to the last insulin injection dose or with respect to the same time of the previous day is greater than the set rate of change threshold. If it is determined in step 411 that the rate of change of the injected dose is not greater than the set rate of change threshold, then in step 412 the calculation module obtains the current patient's prescribed pre-meal insulin injection dose and in step 413 the patient is notified to inject according to the prescribed medication standard without intervention by medical personnel. The current pre-meal short-acting insulin bolus and associated time point may then optionally be saved in step 414 and transferred to step 420.
If it is determined in step 410 that the calculated pre-meal short-acting insulin injection dose is not within the prescribed injection dose range and/or if it is determined in step 411 that the rate of change of the injection dose is greater than the set rate of change threshold, then in step 415 the patient current data and model calculation results are sent to the cloud server over the network. For example, the computing module of the patient's mobile terminal will generate an overrun injection dose check request and send the overrun injection dose check request to the injection data check service system via a communication link (e.g., internet, lan, 4G communication network, 5G communication network). The real-time blood glucose status of the patient and the pre-meal bolus insulin dosage calculated using the dynamic medication adjustment model are then sent to the physician mobile terminal at step 416. Additionally, patient course record data and the like may also be sent to the physician mobile terminal. Optionally, at step 417, the physician first determines whether an urgent risk intervention for hypoglycemia needs to be undertaken for the patient. If it is determined at step 417 that an urgent risk intervention for hypoglycemia is required for the patient, the method proceeds to step 418 for a manual urgent risk intervention. For example, a warning of hypoglycemia may be sent to the patient's mobile terminal or the physician may directly call the patient for medication guidance. If it is determined at step 417 that no urgent risk intervention for hypoglycemia is required for the patient, then at step 419 the physician may appropriately adjust the pre-meal short-acting insulin injection calculated using the dynamic medication adjustment model based on the patient's real-time blood glucose status, disease course data, 2 hours post-meal blood glucose, basal insulin prescription, pre-meal short-acting insulin injection calculated using the dynamic medication adjustment model (RIV), and prompt the patient to inject insulin in accordance with the adjusted pre-meal short-acting insulin injection. Flow then proceeds to step 414 where the current pre-meal bolus insulin injection and associated time point is saved and proceeds to step 420.
In steps 420 and 421, the dynamic medication adjustment model of the patient is adjusted and updated. In step 420, the patient's real-time blood glucose value is read from the continuous blood glucose monitoring system (CGM) 2 hours after the patient has eaten, or the patient may manually input blood glucose measurements into the patient's mobile terminal. In step 421, the oldest patient data is removed again, the latest patient data is added, and the superposition calculation of the insulin injection dose regression model is performed again on the patient data, thereby updating the dynamic medication adjustment model of the patient. Subsequently, at step 422, the self-learning based insulin injection dosage management method of the diabetic patient of the present invention ends.
In some embodiments of the invention, the calculation module uses a multivariate adaptive regression model to perform regression calculations on pre-meal blood glucose, diet patterns, pre-meal short-acting insulin injections, and post-meal blood glucose data for a patient in a normal range, and eliminates abnormal data from the daily data that exceeds a normal threshold. The food quantity which is not easy to calculate is coded and converted by engineering glucose value through a food carbohydrate ingredient comparison table. And taking the pre-meal blood sugar, the diet mode, the pre-meal short-acting insulin injection dosage and the postprandial blood sugar data as input multiple self-adaptive regression models.
And classifying and quantifying the food according to the main types of the catering by using the food classification carbon-water ratio. The method comprises the steps of constructing interactive items of a multiple regression model by using daily pre-meal blood sugar, diet mode, pre-meal short-acting insulin injection dose and postprandial blood sugar data, taking postprandial blood sugar as dependent variables, taking the pre-meal blood sugar, diet mode, pre-meal short-acting insulin injection dose and reasonable blood sugar data of two hours after meal as independent variables, and modeling by adopting a multiple parameter regression method, so that an optimal multiple self-adaptive regression model suitable for a patient is obtained.
Before meals, the patient adjusts the pre-meal short-acting insulin injection dosage through the insulin injection dosage model. For example, the insulin injection dosage model is used to reversely calculate the insulin injection dosage required for maintaining normal postprandial blood glucose according to the latest preprandial blood glucose value and diet pattern.
Multiple parameter regression model
Let us assume dependent variable Y and independent variable X 1, X 2 …X m The following relationship is satisfied:
Y＝β 0 +β 1 X 1 +β 2 X 2 +…+β m X m +μm＝1,2…n
wherein m is the number of independent variables; beta 0 Is a constant term; beta 1 ,β 2 …β m For partial regression coefficients, meaning the independent variable X under the condition that the other independent variable remains unchanged m Changing the average change amount of the strain amount Y at one unit time; mu is a random error (residual) which represents the inability to be represented by the argument X in the variation m Part of the explanation.
In the present invention, the dependent variable Y is the postprandial blood glucose value PBG after two hours after the injection of the short acting insulin dose.
X 1 Preprandial fasting glycemia FBG representing multiple times n ，X 2 The glucose content GI representing a meal calculated from a carbohydrate comparison table n 。X 3 RIV representing multiple preprandial short-acting insulin injections n 。n＝1,2,3…
Calculating RIV of short-acting insulin injection before meal of each injection by using least square method n Blood glucose value PBG after two hours after meal n Each partial regression coefficient beta of the constructed patient multiple parameter regression model 1 β 2 …β n n= (1, 2..n.). Estimation of dependent variablesAnd the sum of squares qmin of the difference between the final actual result Y:
calculating beta such that Q is a minimum 0 ,β 1 ,…,β 0 。
Calculating to obtain parameters
Finally obtaining the partial regression coefficient beta 1 ,β 2 …β m 。
Finally, a multiple linear regression equation is obtained
I.e.
PBG＝β 1 FBG n +β 2 GI n +β 3 RIV n
Taking the expected data PBG within a reasonable blood glucose control range expected to be achieved by the patient after 2 hours, the pre-meal short-acting insulin injection dosage can be calculated.
RIV n ＝(PBG-β 1 FBG n -β 2 GI n )/β 3
Substituting the upper limit range of the desired value PBG of the postprandial blood glucose level of the patient for two hours after meal into the FBC of the preprandial fasting blood glucose of the related preprandial blood glucose n Values and glucose content GI of food calculated by carbohydrate control Table n Can calculate and obtain the RIV of the pre-meal short-acting insulin injection dosage n Is a recommended value for (1).
If the calculated dose RIV of pre-meal short-acting insulin injection n The recommended value of (2) is within the range of the doctor's order set for the current patient, and the pre-meal short-acting insulin injection dose RIV is calculated n The recommended value of (1) is informed to the patient by means of the calculation module of the patient's mobile terminal. Meanwhile, the computing module of the patient mobile terminal submits the current blood glucose value to a cloud server (for example, an injection data verification service system) for storing historical blood glucose data.
If the calculated dose RIV of pre-meal short-acting insulin injection n If the recommended value of (1) is out of the doctor's prescribed range set for the current patient, or the variation of the insulin injection exceeds the threshold variation range set by the doctor in advance compared with the last insulin injection or the same time of the previous day, the calculation module of the patient mobile terminal calculates the current pre-meal blood sugar data, the food status quantification engineering data (the food quantification value corresponding to the food passing through the carbohydrate comparison table when the meal is taken) and the pre-meal short-acting insulin injection RIV calculated according to the dynamic medication adjustment model n The recommended value of (1) is sent to a cloud server (for example, an injection data verification service system) for storage, and meanwhile, the data is sent to a doctor mobile terminal for alarming of adjusting the super-threshold blood sugar injection dosage. The physician receives the calculated pre-meal short-acting insulin injection RIV prompted by the alarm of the super-threshold blood glucose injection adjustment n According to the current value of the patient, the blood sugar data before and after meal of the patient and the insulin dosage data after the patient is prescribed to inject continuously for a plurality of daysDisease analysis and the resulting pre-meal short-acting insulin injection dose RIV n Generates an adjusted insulin injection dosage prescription. The physician's adjusted new prescription is transmitted to a cloud server (e.g., an injection data verification service system) for patient injection record storage. At the same time, the cloud server (e.g., injection data verification service system) sends the adjusted insulin injection dose prescription to the computing module of the patient's mobile terminal. The calculation module of the patient's mobile terminal informs the patient of the adjusted insulin injection dosage prescription prescribed by the physician. The calculation module of the patient mobile terminal can store the injected insulin dose into the local data storage, perform parameter calculation of a new multi-element self-adaptive regression model and update parameters of the multi-element self-adaptive regression model, and be used for calculating the injected dose of the short-acting insulin before the next meal of the patient.
Two hours after the patient completes the insulin injection, the patient's two hours postprandial blood glucose data is collected into the computing module of the patient's mobile terminal by, for example, a continuous blood glucose monitoring system. And the calculation module of the patient mobile terminal takes the received pre-meal blood glucose value, diet quantification data (quantification value of food carbohydrate of meal), pre-meal short-term insulin injection dosage and reasonable blood glucose data of two hours after meal as independent variables, and updates the multi-element self-adaptive regression model for calculating more reasonable pre-meal short-term insulin injection dosage next time.
The invention can provide the diabetes patient with reasonable recommended dose value of pre-meal insulin injection matched with the self blood sugar condition of the patient. The calculation module of the patient mobile terminal, the cloud server and the doctor mobile terminal reduce the workload of a patient in charge of a doctor in adjusting the insulin injection dosage for the patient and the pressure of the patient in short-acting insulin injection adjustment.
Claims (10)
1. An insulin injection dosage monitoring system that obtains patient data and self-learns, the insulin injection dosage monitoring system comprising:
a patient mobile terminal configured to obtain a real-time blood glucose value of a patient;
an injection data verification service system; and
the physician can move the terminal in a way that,
wherein the patient mobile terminal and the physician mobile terminal are respectively in communication with the injection data verification service system,
the patient mobile terminal comprises a calculation module, wherein the calculation module is configured to learn data logic between a pre-meal blood glucose value, a quantified value of food carbohydrate of a meal, a 2-hour postprandial blood glucose, a pre-meal short-acting insulin injection dosage and a normal blood glucose range of a diabetic patient, and generate a dynamic medication adjustment model related to an individual patient from the data logic, and the dynamic medication adjustment model is configured to dynamically calculate and adjust the pre-meal short-acting insulin injection dosage of the patient.
2. The insulin injection dosage administration system of claim 1, wherein the calculation module notifies the patient to inject according to an order medication standard when the pre-meal short-acting insulin injection dosage calculated by the patient mobile terminal using the dynamic medication adjustment model is within an order reasonable range, and generates an overrun injection dosage check request and transmits the overrun injection dosage check request to the injection data check service system when the pre-meal short-acting insulin injection dosage calculated by the patient mobile terminal using the dynamic medication adjustment model exceeds the order reasonable range or a variation ratio with respect to a last insulin injection dosage is greater than a preset variation ratio threshold.
3. The insulin injection dosage administration system of claim 2, wherein upon receiving the over-run injection dosage verification request sent from the patient mobile terminal, the patient injection dosage verification server generates a physician dosage prescription request and sends the physician dosage prescription request to the physician mobile terminal.
4. The insulin injection dosage administration system according to claim 3, wherein upon receiving the physician metering prescription request from the patient injection metering verification server, the physician mobile terminal adjusts the pre-meal short-acting insulin injection dosage calculated using the dynamic medication adjustment model based on the pre-meal blood glucose value of the patient and the pre-meal short-acting insulin injection dosage calculated using the dynamic medication adjustment model, thereby generating a physician metering prescription confirmation.
5. A system comprising one or more computer processors and a computer readable memory, the computer readable memory comprising machine executable code that when executed by the one or more computer processors implements an insulin injection dosage administration method of obtaining patient data and self-learning, the insulin injection dosage administration method comprising:
acquiring the real-time blood glucose value of a patient and the current pre-meal short-acting insulin injection dosage of the doctor's advice;
acquiring a dynamic medication adjustment model of a patient;
calculating the pre-meal short-acting insulin injection dosage of the patient by using the dynamic medication adjustment model; and
if the pre-meal short-acting insulin injection dosage calculated by using the dynamic medication adjustment model is within a reasonable range of a medical advice, notifying the patient to perform injection according to the medical advice medication standard; if the pre-meal short-acting insulin injection dosage calculated by the dynamic medication adjustment model exceeds the reasonable range of the medical advice or the change proportion relative to the latest insulin injection dosage is larger than a preset change proportion threshold value, an overrun injection dosage verification request is generated;
wherein the dynamic medication adjustment model is configured to dynamically calculate and adjust the pre-meal short-acting insulin injection dose of the patient, the dynamic medication adjustment model being generated by learning and from data logic between pre-meal blood glucose values of diabetics, quantified values of meal food carbohydrates, 2-hour postprandial blood glucose, pre-meal short-acting insulin injection dose, and normal blood glucose ranges.
6. The system of claim 5, wherein the method further comprises generating a physician metering prescription request based on the over-injection dose check request and transmitting the physician metering prescription request to a physician mobile terminal.
7. The system of claim 6, wherein upon receiving the physician order request, the physician mobile terminal adjusts the pre-meal short-acting insulin injection dosage calculated using the dynamic medication adjustment model based on the pre-meal blood glucose value of the patient and the pre-meal short-acting insulin injection dosage calculated using the dynamic medication adjustment model, thereby generating a physician order confirmation.
8. An insulin injection dosage administration method for acquiring patient data and self-learning, the insulin injection dosage administration method comprising:
acquiring the real-time blood glucose value of a patient and the current pre-meal short-acting insulin injection dosage of the doctor's advice;
acquiring a dynamic medication adjustment model of a patient;
calculating the pre-meal short-acting insulin injection dosage of the patient by using the dynamic medication adjustment model; and
if the pre-meal short-acting insulin injection dosage calculated by using the dynamic medication adjustment model is within a reasonable range of a medical advice, notifying the patient to perform injection according to the medical advice medication standard; if the pre-meal short-acting insulin injection dosage calculated by the dynamic medication adjustment model exceeds the reasonable range of the medical advice or the change proportion relative to the latest insulin injection dosage is larger than a preset change proportion threshold value, an overrun injection dosage verification request is generated;
wherein the dynamic medication adjustment model is configured to dynamically calculate and adjust the pre-meal short-acting insulin injection dose of the patient, the dynamic medication adjustment model being generated by learning and from data logic between pre-meal blood glucose values of diabetics, quantified values of meal food carbohydrates, 2-hour postprandial blood glucose, pre-meal short-acting insulin injection dose, and normal blood glucose ranges.
9. The insulin injection dosage administration method of claim 8, further comprising generating a physician metering prescription request based on the over-limit injection dosage verification request and transmitting the physician metering prescription request to a physician mobile terminal.
10. The insulin injection dose administration method according to claim 9, wherein upon receiving the physician metered prescription request, the physician mobile terminal adjusts the pre-meal short-acting insulin injection dose calculated using the dynamic medication adjustment model based on the pre-meal blood glucose value of the patient and the pre-meal short-acting insulin injection dose calculated using the dynamic medication adjustment model, thereby generating a physician metered prescription confirmation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311291878.0A CN117542476A (en) | 2023-10-08 | 2023-10-08 | Insulin injection dosage supervision method and system based on self-learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311291878.0A CN117542476A (en) | 2023-10-08 | 2023-10-08 | Insulin injection dosage supervision method and system based on self-learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117542476A true CN117542476A (en) | 2024-02-09 |
Family
ID=89786878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311291878.0A Pending CN117542476A (en) | 2023-10-08 | 2023-10-08 | Insulin injection dosage supervision method and system based on self-learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117542476A (en) |
-
2023
- 2023-10-08 CN CN202311291878.0A patent/CN117542476A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Harvey et al. | Quest for the artificial pancreas: combining technology with treatment | |
| US10646650B2 (en) | Multivariable artificial pancreas method and system | |
| Khodaei et al. | Physiological closed-loop control (PCLC) systems: Review of a modern frontier in automation | |
| JP6066499B2 (en) | Insulin pump | |
| Turksoy et al. | Multivariable adaptive identification and control for artificial pancreas systems | |
| Miller et al. | Automatic learning algorithm for the MD-logic artificial pancreas system | |
| CN110289094B (en) | Expert rule-based insulin accurate administration decision method | |
| JP2012519018A (en) | Method and system for automatically monitoring diabetes related therapy | |
| US20210256872A1 (en) | Devices, systems, and methods for predicting blood glucose levels based on a personalized blood glucose regulation model | |
| Rodriguez-Rodriguez et al. | Variables to Be Monitored via Biomedical Sensors for Complete Type 1 Diabetes Mellitus Management: An Extension of the “On‐Board” Concept | |
| DE112020004780T5 (en) | BLOOD SUGAR CONTROL SYSTEM | |
| Hassan et al. | Closed loop blood glucose control in diabetics | |
| CA3011231A1 (en) | Predictive control model for the artificial pancreas using past predictions | |
| Vettoretti et al. | Patient decision-making of CGM sensor driven insulin therapies in type 1 diabetes: In silico assessment | |
| Piemonte et al. | A novel three‐compartmental model for artificial pancreas: development and validation | |
| KR102527404B1 (en) | Method of Controlling Insulin Dose | |
| Cescon et al. | Linear modeling and prediction in diabetes physiology | |
| CN117542476A (en) | Insulin injection dosage supervision method and system based on self-learning | |
| Campos-Delgado et al. | Self-tuning insulin adjustment algorithm for type 1 diabetic patients based on multi-doses regime | |
| He et al. | Blood glucose concentration prediction based on canonical correlation analysis | |
| Albisser | Analysis: Toward algorithms in diabetes self-management | |
| Winkler et al. | Patient-specific performance evaluation for insulin control systems | |
| Ata et al. | Model based control of artificial pancreas under meal disturbances | |
| Acedo et al. | Swarm hybrid optimization for a piecewise model fitting applied to a glucose model | |
| CN115445022B (en) | Intelligent insulin pump control system |
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 |