Using Acoustic Sensors to Discriminate between Nasal and Mouth Breathing
In the 1990’s Buteyko identified the need for asthmatics to breathe through their nose to prevent against over-breathing caused by mouth breathing (McHugh et al., 2003). There are currently a number of clinical studies being undertaken to prove the clinical significance of the Buteyko breathing technique. It is also well recognised that nasal breathing warms, humidifies and releases endogenous nitric oxide into inhaled air. These all play an important role in conditioning the lungs. Unfortunately breaking the habit of mouth breathing is difficult, and asthmatics practising the Buteyko breathing technique will often revert to mouth breathing automatically. Asthmatics attempting to adopt this technique to gain better control over their condition need to be constantly reminded to breathe correctly. It is well known that normal lung sounds show interpersonal variations. In addition to this, it has to be taken into account that both a same-day variability and a between-day variability exist in lung sounds (Mahagna and Gavriely, 1994).
On the basis of these large variations, concrete changes in nasal and mouth will be seen only with investigation of a larger number of subjects. The purpose of computer-supported analysis of breathing sounds is for objective understanding and archiving. Because the sensitivity of human hearing is reduced, particularly in the lower frequency ranges, an objective electronic recording for recognizing deviations within these ranges could be helpful. Since the procedure for doing this is not costly, invasive, or particularly intensive, it would be suitable as an examination method for high-risk groups such as pneumonia patients. A daily or even more frequent analysis of lung-sound spectra could help to identify patients with say, incipient pneumonia before the appearance of any radiologic abnormality.
Task
The overall purpose is to investigate the possibility of identifying the differences in patterns between nasal and mouth breathing in order to integrate this information into a decision support system which will form the basis of a patient monitoring and motivational feedback system to recommend the change from mouth to nasal breathing. We have already shown in previous work that the breath pattern can be discriminated in certain places of the body both by visual spectrum analysis and with a Back Propagation neural network classifier. The sound file recoded from the sensor placed on the hollow in the neck shows the most promising accuracy which is as high as 90%.
This project therefore will focus on trying to provide visualisations and interpretations of the breathing patterns in real time on a mobile device (smart phone or laptop).