Skip to Main Content
It is known that the rate of acetone in human breath changes in diabetics. The organs in the human body produce different gases. During cleaning of the blood, which is transmitted to the lungs and into the blood gases, the breath passes through the alveoli. Human breath acetone concentration is very low (0.1-10 ppm). This paper aims to determine human blood glucose and HbA1c levels from exhaled breath as a non-invasive method with the help of an electronic nose system based on quartz crystal microbalance (QCM) sensors. The amount of acetone vapor, which is the marker of blood glucose, is 0.1-10 ppm in human expiration. Data of the QCM sensor used in the electronic nose are compared against glucose and HbA1c parameters in blood by using a radial basis function neural network (RBFNN). When breath data are implemented to the RBFNN, the average accuracy rate is 83.03% and 74.76% for HbA1c parameter predictions and glucose parameter predictions, respectively.