Big data-based automatic dose recommendation method and device for insulin intravenous injection system, processor and storage medium thereof

Abstract

The invention relates to an automatic dose recommendation method for an insulin intravenous injection system based on a big data AI algorithm. The method comprises the steps that patient information is added into the insulin intravenous injection system; selecting an insulin treatment mode as intravenous injection, and setting intravenous treatment parameters; calculating the next blood glucose detection time and an insulin regulatory factor according to the currently collected blood glucose value of the patient; on the basis of the calculation result, according to a system big data AI recommended insulin dosage algorithm, modeling processing is carried out, the insulin recommended dosage (infusion speed) of the current patient is calculated, and the patient is guided to accept medication and related matters needing attention to be reminded; and circulating the steps until the blood sugar of the patient reaches the target range. The invention further relates to a corresponding device, a processor and a storage medium thereof. By adopting the method, the device, the processor and the storage medium, an individualized, accurate and dynamic insulin regulation and control strategy can be customized for a patient, and the method, the device, the processor and the storage medium have important significance.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and particularly to the field of medical systems. Specifically, it refers to a method, device, processor and computer-readable storage medium for automatically recommending doses in an intravenous insulin injection system based on big data. Background Art

[0002] In real life, when a patient needs to receive intravenous insulin injection, the general method is as follows:

[0003] 1. The doctor evaluates the patient's blood glucose condition and gives medication advice based on the doctor's experience;

[0004] 2. To prevent the occurrence of hypoglycemia, the initial dose is generally conservative;

[0005] 3. Nurses manually record the patient's blood glucose and cannot manage multiple patients simultaneously.

[0006] As described above, the prior art usually has the following defects:

[0007] (1) The dose adjustment is not timely;

[0008] (2) The control of hyperglycemia and hypoglycemia is not ideal;

[0009] (3) It takes a relatively long time to reach the target control range;

[0010] (4) Medical resources are relatively tense, and it is difficult for a doctor to promptly pay attention to the insulin responses of multiple patients;

[0011] (5) When the patient has hypoglycemia, the patient's needs cannot be promptly responded to;

[0012] (6) For patients across clinics who need to consult an endocrinologist, they often need to make an appointment with the doctor in advance, which is time-consuming, laborious and inefficient.

[0013] In summary, in view of the defects commonly existing in the current prior art, it is necessary to propose a reasonable, convenient and accurate insulin dose control method. Summary of the Invention

[0014] The purpose of the present invention is to overcome the above-mentioned defects of the prior art and provide a method, device, processor and computer-readable storage medium for automatically recommending doses in an intravenous insulin injection system based on big data.

[0015] To achieve the above purpose, the method, device, processor and computer-readable storage medium for automatically recommending doses in the intravenous insulin injection system based on big data of the present invention are as follows:

[0016] The method for automatically recommending doses of the intravenous insulin system based on big data AI algorithms is mainly characterized in that the method comprises the following steps:

[0017] (1) Add patient information to the intravenous insulin system;

[0018] (2) Select the insulin treatment method as intravenous injection and set personalized intravenous treatment parameters;

[0019] (3) According to the currently collected blood glucose value of the patient, calculate the next blood glucose detection time and the insulin adjustment factor;

[0020] (4) Based on the above calculation results, build a model according to the system big data AI recommended insulin dose algorithm, calculate the insulin recommended dose (infusion rate) of the current patient, and guide the patient to receive medication and reminder of relevant precautions;

[0021] (5) Loop the above steps until the patient's blood glucose reaches the target range.

[0022] Preferably, step (3) specifically comprises the following steps:

[0023] (3.1) Collect the current patient's blood glucose;

[0024] (3.2) According to the target blood glucose of the patient, the previous blood glucose value, the current blood glucose, and the time difference between the current blood glucose and the previous blood glucose, calculate the time interval for the next blood glucose detection;

[0025] (3.3) According to the target blood glucose, the current blood glucose, and the previous blood glucose value of the patient, calculate the insulin adjustment factor in the following manner:

[0026] Insulin adjustment factor = previous adjustment factor × 1.25 or 0.8.

[0027] Preferably, step (4) is specifically to calculate the insulin recommended dose in the following manner:

[0028] Insulin recommended dose (unit: units / hr) = (current blood glucose - hypoglycemic threshold) × current insulin adjustment factor

[0029] Or insulin recommended dose (unit: units / hr) = (current blood glucose - hypoglycemic threshold) × current insulin adjustment factor / insulin concentration.

[0030] Preferably, the target blood glucose includes the highest blood glucose value and the lowest blood glucose value.

[0031] Preferably, if the current patient's blood glucose value ≤ 4.4 mmol / l, stop injecting insulin and consider supplementing glucose or carbohydrates.

[0032] The device for automatically recommending doses in the intravenous insulin injection system based on big data AI algorithms, its main feature is that the device includes:

[0033] A processor configured to execute computer-executable instructions;

[0034] A memory storing one or more computer-executable instructions, when the computer-executable instructions are executed by the processor, the steps of the method for automatically recommending doses in the intravenous insulin injection system based on big data AI algorithms described above are implemented.

[0035] This computer-readable storage medium, its main feature is that a computer program is stored thereon, and the computer program can be executed by a processor to implement the steps of the method for automatically recommending doses in the intravenous insulin injection system based on big data AI algorithms described above.

[0036] By adopting the method, device, processor and its computer-readable storage medium for automatically recommending doses in the intravenous insulin injection system based on big data of the present invention, by tailoring an individualized, precise and dynamic insulin regulation strategy for patients, the probability of patients having hypoglycemia or hyperglycemia events is effectively reduced, and in terms of the time for patients to meet blood glucose standards, the time efficiency is also greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flowchart of the method for automatically recommending doses in the intravenous insulin injection system based on big data AI algorithms of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] In order to be able to more clearly describe the technical content of the present invention, the following will be further described in combination with specific embodiments.

[0039] Before detailing the embodiments according to the present invention, it should be noted that hereinafter, the terms "comprising", "including" or any other variation are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes these elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0040] Please refer to Figure 1 As shown, the method for automatically recommending doses in the intravenous insulin injection system based on big data AI algorithms, wherein the method includes the following steps:

[0041] (1) Add patient information to the intravenous insulin injection system;

[0042] (2) Select the insulin treatment method as intravenous injection and set personalized intravenous treatment parameters, including: date of birth, A1c, height, weight, and personalized treatment parameters: initialization adjustment factor, blood glucose target control range targetLowBG and targetHighBG, insulin concentration used, carbohydrates per meal, saline used when blood glucose is greater than or equal to 13.9 mmol / l, saline used when blood glucose is less than 13.9 mmol / l, diagnosis and other basic patient data.

[0043] (3) Calculate the next blood glucose detection time and insulin adjustment factor based on the currently collected blood glucose value of the patient;

[0044] (4) Based on the above calculation results, build a model of the insulin recommendation algorithm according to the system big data AI, calculate the insulin recommended dose (infusion rate) of the current patient, and guide the patient to receive medication and reminder of relevant precautions;

[0045] (5) Loop the above steps until the patient's blood glucose reaches the target range.

[0046] As a preferred embodiment of the present invention, the step (3) specifically includes the following steps:

[0047] (3.1) Collect the blood glucose of the current patient;

[0048] (3.2) Calculate the time interval for the next blood glucose detection according to the target blood glucose of the patient, the previous blood glucose value, the current blood glucose and the time difference between the current blood glucose and the previous blood glucose;

[0049] (3.3) Calculate the insulin adjustment factor according to the target blood glucose of the patient, the current blood glucose and the previous blood glucose value in the following way:

[0050] Insulin adjustment factor = previous adjustment factor × 1.25 or 0.8.

[0051] As a preferred embodiment of the present invention, the step (4) is specifically to calculate the insulin recommended dose in the following way:

[0052] Insulin recommended dose (infusion rate) = (current blood glucose - hypoglycemic threshold) × current insulin adjustment factor (the hypoglycemic threshold is defaulted to 3.3 mmol / l);

[0053] If the insulin unit is not units / hr:

[0054] Insulin recommended dose (infusion rate) = (current blood glucose - hypoglycemic threshold) × current insulin adjustment factor / insulin concentration;

[0055] As a preferred embodiment of the present invention, the target blood glucose includes the highest blood glucose value and the lowest blood glucose value.

[0056] As a preferred embodiment of the present invention, if the current blood glucose value of the patient ≤ 4.4 mmol / l, stop injecting insulin and consider supplementing glucose or carbohydrates.

[0057] In practical applications, the method for automatically recommending doses of the intravenous insulin injection system based on the big data AI algorithm of the present technical solution is as follows:

[0058] (1.1) Add the patient to the system, select the insulin treatment method as intravenous injection, and set the intravenous treatment parameters;

[0059] (1.2) Through big data analysis, based on the current blood glucose value of the patient, respectively recommend insulin dose modeling and insulin adjustment factor modeling for the time of the next blood glucose check.

[0060] (2.1) Collect the current blood glucose currentBG;

[0061] (2.2) According to factors such as the target blood glucose (target high value and target low value), the previous blood glucose value, the time difference between the current blood glucose and the previous blood glucose, etc., calculate the time for the next blood glucose test (timer countdown):

[0062] timer = 20 minutes when currentBG ≥ targetLowBG and (previous blood glucose PBG - currentBG) / previous blood glucose PBG ≥ 66%;

[0063] timer = 20 minutes when currentBG is less than or equal to the hypoglycemia threshold;

[0064] timer = 20 minutes when hypoglycemia threshold < currentBG < targetLowBG and (previous blood glucose PBG - currentBG) / previous blood glucose PBG ≥ 0.25;

[0065] timer = 120 minutes when targetLowBG ≤ currentBG ≤ targetHighBG and it exceeds 2.5 hours within the target range;

[0066] time = 30 minutes when (previous blood glucose PBG – currentBG)(currentTime – previous blood glucose time) >

[0067] 5.5 mmol / l / hr;

[0068] time = 60 minutes for other conditions other than the above.

[0069] (2.3) Adjust the current adjustment factor calculation: Based on the blood glucose target (target high value and target low value), current blood glucose, and previous blood glucose conditions, when currentBG > targetHighBG and currentBG / previous blood glucose > 85%, the adjustment factor = previous adjustment factor × 1.25; when currentBG < targetLowBG, the adjustment factor = previous adjustment factor × 0.8; except for the above two cases, the adjustment factor remains unchanged;

[0070] (2.4) Calculate the insulin recommended dose (in units / hr) = (current blood glucose - hypoglycemic threshold) × adjust the current adjustment factor (the hypoglycemic threshold is defaulted to 3.3 mmol / l) or calculate the insulin recommended dose (not in units / hr) = (current blood glucose - hypoglycemic threshold) × adjust the current adjustment factor (the hypoglycemic threshold is defaulted to 3.3 mmol / l) / insulin concentration; if the current blood glucose is less than or equal to 4.4 mmol / l, stop injecting insulin, and at the same time consider giving the patient glucose or carbohydrates;

[0071] (2.5) Loop and execute (2.1) and (2.4), and the patient's blood glucose will reach the target range within a relatively short time.

[0072] The device for automatically recommending doses of the intravenous insulin system based on the big data AI algorithm has the main feature that the device includes:

[0073] A processor configured to execute computer-executable instructions;

[0074] A memory storing one or more computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the method for automatically recommending doses of the intravenous insulin system based on the big data AI algorithm as described above are implemented.

[0075] The processor of the intravenous insulin system for automatically recommending doses based on the big data AI algorithm has the main feature that the processor is configured to execute computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the method for automatically recommending doses of the intravenous insulin system based on the big data AI algorithm as described above are implemented.

[0076] The computer-readable storage medium has the main feature that a computer program is stored thereon, and the computer program can be executed by a processor to implement the steps of the method for automatically recommending doses of the intravenous insulin system based on the big data AI algorithm as described above.

[0077] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0078] It should be understood that each part of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device.

[0079] A person of ordinary skill in the art may understand that all or part of the steps of the method for implementing the above-mentioned embodiment may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0080] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0081] In the description of this specification, the description with reference to the terms "an embodiment", "some embodiments", "example", "specific example", or "embodiment" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0082] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

[0083] The method, device, processor and computer-readable storage medium for automatically recommending dosages of the intravenous insulin system based on big data of the present invention are adopted to effectively reduce the probability of hypoglycemia or hyperglycemia events in patients by tailoring an individualized, accurate and dynamic insulin regulation strategy for patients, and greatly improve the time efficiency in allowing patients to meet blood sugar standards.

[0084] In this specification, the invention has been described with reference to specific embodiments thereof. However, it will be apparent that various modifications and variations can be made without departing from the spirit and scope of the invention. Accordingly, the specification and drawings are to be regarded as illustrative rather than restrictive.

Claims

1. A method for automatically recommending doses of an intravenous insulin injection system based on big data AI algorithms, characterized in that, The method described above includes the following steps: (1) Add patient information to the intravenous insulin injection system; (2) Select the insulin treatment method as intravenous injection and set personalized intravenous treatment parameters; (3) Calculate the next blood glucose detection time and insulin adjustment factor based on the currently collected blood glucose value of the patient; (4) Based on the above calculation results, perform modeling processing according to the insulin dose algorithm recommended by the system's big data AI, calculate the insulin recommended dose for the current patient, that is, the infusion rate, and guide the patient to receive medication and reminders of relevant precautions; (5) Loop the above steps until the patient's blood glucose reaches the target range.

2. The method for automatically recommending a dose of an intravenous insulin injection system based on a big data AI algorithm according to claim 1, characterized in that, The specific steps of step (3) include the following steps: (3.1) Collect the current patient's blood glucose; (3.2) Calculate the time interval for the next blood glucose detection according to the patient's target blood glucose, the previous blood glucose value, the current blood glucose, and the time difference between the current blood glucose and the previous blood glucose; (3.3) Calculate the insulin adjustment factor according to the patient's target blood glucose, the current blood glucose, and the previous blood glucose value in the following manner: Insulin adjustment factor = previous adjustment factor × 1.25 or 0.

8.

3. The method for automatically recommending a dose of the intravenous insulin injection system based on the big data AI algorithm according to claim 2, wherein The specific step of step (4) is to calculate the insulin recommended dose in the following manner: Insulin recommended dose (unit: units / hr) = (current blood glucose - hypoglycemic threshold) × current insulin adjustment factor (the hypoglycemic threshold is defaulted to 3.3 mmol / l); Or, Insulin recommended dose (unit: non-units / hr) = (current blood glucose - hypoglycemic threshold) × current insulin adjustment factor / insulin concentration.

4. The method for automatically recommending doses of an intravenous insulin injection system based on a big data AI algorithm according to claim 3, characterized in that, The target blood glucose includes the highest blood glucose value and the lowest blood glucose value.

5. The method for automatically recommending a dose of an intravenous insulin injection system based on a big data AI algorithm according to claim 3, wherein If the current patient's blood glucose value ≤ 4.4 mmol / l, stop injecting insulin and consider supplementing glucose or carbohydrates.

6. A device for automatically recommending doses in an intravenous insulin injection system based on a big data AI algorithm, characterized in that, The device includes: A processor configured to execute computer-executable instructions; A memory storing one or more computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the method for automatically recommending a dose of the intravenous insulin injection system based on the big data AI algorithm as described in any one of claims 1 to 5 are implemented.

7. A processor for automatically recommending doses of an intravenous insulin injection system based on big data AI algorithms, characterized in that, The processor is configured to execute computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the method for automatically recommending a dose of the intravenous insulin injection system based on the big data AI algorithm as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and the computer program can be executed by the processor to implement the steps of the method for automatically recommending a dose of the intravenous insulin injection system based on the big data AI algorithm as described in any one of claims 1 to 5.

Images