Role of breath phase and breath boundaries for the classification between asthmatic and healthy subjects.

Asthma is an inflammatory disease of the airways which causes cough, chest tightness, wheezing and other distinct sounds during breathing. Spirometry is a golden standard lung function test, is used to monitor and diagnose asthma. Spirometry is very time-consuming and requires a lot of patient's efforts. Therefore, an alternate method which can overcome spirometry limitations is required. Sound based method can be one such alternative as it is less tedious, less time consuming and suitable for patients of all ages. It has been shown in the past that breath, among other vocal sounds, performs the best for an asthma vs healthy subject classification task. Breath consists of two phases, namely, inhale and exhale. Experiments in this work show, exhale performs better for classification task compared to the entire breath cycle as well as the inhale. However, this requires manual marking of the breath boundaries, which is a very time-consuming task. We, in this work, investigate how critical are the breath cycle and breath phase boundaries for the classification task. Experiments with chunks of random duration shows that they perform on par or better than the exhale. However, a segment comprising the second and third quarters of a breath cycle results in the highest classification accuracy of 80.64%. This suggests that, while breath phase boundaries may not be important, breath cycle boundaries could benefit in the classification task.

Comparison of Cough, Wheeze and Sustained Phonations for Automatic Classification Between Healthy Subjects and Asthmatic Patients.

In this work, we consider the task of automatic classification of asthmatic patients and healthy subjects using voice stimuli. Cough and wheeze have been used as voice stimuli for this classification task in the past. In this work, we focus on sustained phonations, namely /aː/, /iː/, /uː/, /eɪ/, /o℧/ and compare their classification performances with the cough and wheeze. Classification experiments using 35 asthmatic patients and 36 healthy subjects show that sustained vowel /iː/ achieves the highest classification accuracy of 80.79% among five vowels considered. However, it is found to be higher and lower than the classification accuracies of 78.72% and 90.25% obtained using cough and wheeze respectively. This suggests that for speech-based asthma classification, /iː/ would be a better choice compared to other vowels considered in this work. However, when non-speech sounds are included for classification, wheeze is a better choice than sustained /iː/.