Determination of glucose and HbA1c values in blood from human breath by using electronic nose

In this study, it is aimed to be determined glucose and HbA1c values in blood from the human breath by using electronic nose. The organs in the human body produces different gases. The gases which septicaemia from the organs in the course of purification of blood, transmit to breath via alveoli. It is known that the rate of acetone in human breath changes in the diabetes. Acetone concentration in human breath is the lowest level like 0.1-10 ppm. Therefore, it is used condensing substance including chemical absorbent material in the testing apparatus. By this means, it is kept breath samples including acetone with low concentration and it is supplied to electronic nose by acquiring high concentration.OCM sensor data is compared against glucose and HbA1c parameters in blood by using Radial Basis Function Neural Network. When breath data is implemented to the Radial Basis Function Neural Network, the minimum error rate is %14,92 for HbA1c parameter predictions and the minimum error rate is %24,62 for glucose parameter predictions.The work has been conducted in the scope of TUBITAK Project, No: 104E053: (Diagnosing System Design for Medical Applications Using by QCM-SSC Gas Sensor Array).