Automatic cough segmentation from non-contact sound recordings in pediatric wards

Abstract

Cough is a common symptom of almost all childhood respiratory diseases. In a typical consultation session, physicians may seek for qualitative information (e.g. wetness) and quantitative information (e.g. cough frequency) either by listening to voluntary coughs or by interviewing the patients/carers. This information is useful in the differential diagnosis and in assessing the treatment outcome of the disease. The manual cough assessment is tedious, subjective, and not suitable for long-term recording. Researchers have attempted to develop automated systems for cough assessment but none of the existing systems have specifically targeted the pediatric population. In this paper we address these issues and develop a method to automatically identify cough segments from the pediatric sound recordings. Our method is based on extracting mathematical features such as non-Gaussianity, Shannon entropy, and cepstral coefficients to describe cough characteristics. These features were then used to train an Artificial Neural Network to detect coughs segment in the sound recordings. Working on a prospective data set of 14 subjects (sound recording length 840 minutes), proposed method achieved sensitivity, specificity, and Cohen's Kappa of 93%, as an automated pediatric cough counting device as well as the front-end of a cough analysis system.

A Machine Hearing System for Robust Cough Detection Based on a High-Level Representation of Band-Specific Audio Features

“…Smartphone-recorded data in different noisy scenarios (including when the device was carried in a pocket or bag) was used to validate the method. This work also demonstrated that classical feature sets such as the MFCC employed in [10], [14], [16] failed to perform on challenging noisy environments.…”

“…The operation of these devices relies on pattern recognition engines primarily based on features extracted from cough sounds and complementary signals like electromyography of chest movement. However, many of these systems have only been tested in controlled environments where patients did not perform any movement or physical activity [9], [10] or force the users to wear complex recording systems [9], [11]. A portable cough monitor relying on audio recordings and able to cope with noisy real-life environments could be implemented on a smartphone for continuous real-time monitoring of respiratory patients.…”

“…Recall values around 74% were reported on real data (classification of each subband separately) with an overall 82% performance after integration. Amrulloh et al [10] employed MFCC together with entropy and non-gaussianity measures for cough segmentation in pediatric wards. They used an artificial neural network for classification, achieving 93% sensitivity (SEN).…”

Theory and Application of Audio-Based Assessment of Cough

“…Their system is hence able to protect personal privacy. Amrulloh et al attempted to design an automated method to automatically identify cough segments from the pediatric sound recordings and achieved a sensitivity and specificity of 93% and 98%, respectively [5].…”

“…This symptom is also the very reason why people seek medical advice in America and China [1,2]. Even though the importance of cough diagnosis is well admitted by academic organizations [2][3][4] in recent years, there is no gold standard to assess cough due to the lack of objective and accurate measures of cough frequency and severity [5]. When cough becomes chronic, it is so extremely unpleasant and distressing that the life quality of chronic cough patients has significant reductions [6].…”