Objective recognition of cough sound as biomarker for aerial pollutants.

Abstract

A relationship among air quality, respiratory health, and comfort in man and animal is widely shown. In general, a state of respiratory discomfort is prevailed by an increase in acoustic audible symptoms. The general concept of sound analysis as an objective contactless non-invasive biomarker for aerial pollution is studied on free-field cough sound of 12 Belgian Landrace piglets. A citric-acid-induced cough sound recognition algorithm with recognition rate of 95% is applied to cough sounds registered in the presence of distinct types of aerial pollutants: irritating gas (ammonia), respirable particles (dust), and temperature. The recognition performance for all aerial pollutants was >90% and maintained 94% on average. It is concluded that sound analysis allows an effective biomarker for all three types of aerial pollution. The generality of the biomarker is hypothesized to be due to the common mechanism involved in protective cough. As a consequence, it is suggested to use sound analysis as a biomarker for respiratory state in studies of exposure to air pollutants.