350 - GLYCEMIA VARIABILITY INDICES AS A BASIS FOR BUILDING A NETWORK MODEL FOR PREDICTING THE COMPENSATION OF TYPE 1 DIABETES
Abstract
Background and Aims
Standard methods for determining the compensation of the disease don’t always reliably reflect the level of the glycemic control of the patient, which leads to decompensation diabetes and reduce the quality and duration of life for patients. Evaluation of glycemic variability indices allows the physicians to predict the risk of developing life-threatening conditions and compensate the diabetes
Aim: Identify the relationship of HbA1c and glycemic variability indexes to predict the compensation of diabetes
Methods
The study included 120 patients with diabetes type 1. Through the technology of CGM all patients transmitted data to the doctor for recommendations and done analysis of HbA1c. Using the EasyGV calculator, we calculated the glycemic variability indices, on the basis of which the regression neural network model was built in the statistical computing environment R using the neuralnet.
Results
Using CGM in patients with diabetes type 1, there was a significant improvement in the glycemic variability indices by the end of the study. HbA1c in the remote monitoring group decreased by 1.95% (p=0,016), in the outpatient observation group decreased by 0.7% (p≤0,001), in the standard therapy group increased by 0.05% with p=0.546.
Conclusions
The neural network model with a high index of determination based on glycemic variability indexes demonstrates a significantly higher accuracy in predicting the level of HbA1c in diabetes patients, which makes it possible to assess the degree of compensation for the disease and provide a personalized approach in treating these patients