Determination method, device, storage medium and electronic device for insulin resistance index

Abstract

The invention discloses a method, device, storage medium and electronic equipment for determining an insulin resistance index. The method includes: obtaining a plurality of sample data, and recording the test indicators corresponding to insulin resistance in the sample data; constructing an evaluation model, and the evaluation model includes a first An initial model and a second initial model, there are multiple first initial models; each first initial model is trained through a plurality of sample data, and multiple first models are screened from the first initial model according to the training results; according to the first model Train the second initial model with a plurality of sample data to obtain the second model; determine the insulin of the target user through the first model and the second model, the fasting insulin concentration and the fasting blood glucose concentration according to the test index corresponding to the target user's insulin resistance resistance index. The characterization effect of the insulin resistance index determined by the method of the invention is good, and the time and cost are low.

Description

technical field [0001] The present invention relates to the technical field of big data, in particular to a method, device, storage medium and electronic equipment for determining an insulin resistance index. Background technique [0002] Insulin resistance means that the sensitivity of insulin decreases, and the body is not sensitive to insulin. At this time, no matter how much insulin is secreted, it will not achieve a good hypoglycemic effect, which will lead to diabetes. Therefore, insulin resistance is one of the important pathogenic factors of diabetes. At the same time, based on research, insulin resistance has a certain relationship with high blood pressure, fatty liver, polycystic ovary syndrome, and Alzheimer's disease. Therefore, determining the degree of insulin resistance in patients is becoming more and more important in clinical practice. The degree of insulin resistance is often characterized by quantitative insulin resistance index. [0003] HOMA-IR, Li Gu...

AI Technical Summary

Problems solved by technology

Static indicators further simplify the test cost and reduce the waiting time of patients, but the effect of such static indicators is poor. The reason may be that metabolism is a process, and information will be missing only through static indicators, which will affect the effect.

[0004] The Matsuda index is a dynamic index. The Matsuda index is determined by obtaining the test data of fasting insulin, fasting blood sugar, insulin mean value and blood sugar mean value. The Matsuda index simplifies the complicated test process and the time cost of medical staff, but it usually takes 2 hours for the subjects. - 3 hours to determine insulin mean and blood sugar mean

[0005] In summary, the current insulin resistance index has disadvantages such as poor characterization effect and high time cost for obtaining insulin resistance index

Images