InspirationThe human breath contains several hundred volatile organic compounds (VOCs) with concentrations ranging from part-per-trillion (ppt) to part-per-million (ppm). The cellular and biochemical origin of many of these VOCs has not been determined and some of them might be of exogenous origin. The acetone concentration in the breath varies from 300 to 900 ppb in healthy people to more than 1800 ppb in individuals with diabetes. Therefore, acetone can act as a biomarker for metabolic conditions in the bloodstream.In certain cases such as fasting, exercising and being diabetic, the liver produces ketones to act as an additional energy source, which are then metabolized into acetone and other ketone bodies. Using breath analysis techniques, acetone concentrations in exhaled breath have been shown to correlate with the acetone concentrations in the blood as well as with other ketones such as beta-hydroxybutyrate. In addition, it is also found that the level of blood glucose can be correlated to the volatile organic compound levels such as acetone. Measurement of acetone from breath can allow a better diagnostic control of a patient’s diabetic condition than through the use of blood glucose measurements alone.
For analysis of glucose levels from the breath, a mouthpiece is designed and the sensors can be placed inside the mouth piece for calculating voltage, resistance, pressure, temperature and humidity. Flow rate and volume of breath blow into the mouthpiece can’t be controlled andare different for each person. To compensate this, the effects of pressure, temperature and humidity levels have been considered for each and every person apart from the actual parameters. The basic principle of operation of these gas sensors is the change in their conductivities due to interactions with oxidizing and reducing gas molecules. A data set of 1000 samples has been created which contains the comparison between the glucose content estimation using acetone gas and the glucose content estimation using invasive Technology. The sensor data obtained is now transmitted into an artificial neural network model to estimate the exact glucose content. The calculated Glucose content can be displayed in the watch and sent to the network for storage.
Log in or sign up for Devpost to join the conversation.