Determination of glucose and Hba1c values in blood from human breath by using Radial Basis Function Neural Network via electronic nose

Abstract

In this study, it is aimed to be determined glucose and HbA1c values in blood from the human breath by using electronic nose. It is known that the rate of acetone in human breath changes in diabetes. Electronic nose data is compared against glucose and HbA1c parameters in blood by using Radial Basis Function Neural Network. The minimum error rate is %24,62 for glucose parameter predictions and the minimum error rate is %14,92 for HbA1c parameter predictions. The work has been conducted in the scope of TUBITAK Project, No: 104E053.