Life-long chronic inflammatory diseases of the airways, such as asthma and Chronic Obstructive Pulmonary Disease, are very common worldwide, affecting people of all ages, race and gender. One of the most important aspects for the effective management of asthma is medication adherence which is defined as the extent to which patients follow their prescribed action plan and use their inhaler correctly. Wireless telemonitoring of the medication adherence can facilitate early diagnosis and management of these diseases through the use of an accurate and energy efficient mHealth system. Therefore, low complexity audio compression schemes need to be integrated with high accuracy classification approaches for the assessment of adherence of patients that use of pressurized Metered Dose Inhalers (pMDIs). To this end, we propose a novel solution that enables the energy efficient monitoring of metered dose inhaler usage, by exploiting the specific characteristics of the reconstructed audio features at the receiver. Simulation studies, carried out with a large dataset of indoor & outdoor measurements have led to high levels of accuracy (98 %) utilizing only 2 % of the recorded audio samples at the receiver, demonstrating the potential of this method for the development of novel energy efficient inhalers and medical devices in the area of respiratory medicine.
Keywords: AdaBoost; Compressed sensing; Support vector machines; Time-frequency analysis.