Automatic cough segmentation from non-contact sound recordings in pediatric wards. (August 2015)

• Record Type: Journal Article
• Authors: Amrulloh, Yusuf A.; Abeyratne, Udantha R.; Swarnkar, Vinayak; Triasih, Rina; Setyati, Amalia
• Is Part Of: Biomedical signal processing and control. Volume 21(2015)
• Page Start: 126
• Page End: 136
• Publication Date: 2015-08
• Subjects: Pediatric respiratory diseases -- Cough -- Automatic cough segmentation; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2015.05.001
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: We develop an automated system to detect cough sounds from continuous sound recording. We design our algorithms to target the pediatric population (age <6 years), addressing a fundamental gap in current technology. Proposed technique is robust against the variation of cough sound intensity levels and waveform-shapes. Working on a clinical dataset, consisting of 14 pediatric subjects, proposed algorithm achieved a classification sensitivity of 93% and specificity of 97.5%. 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 min), proposed method achieved sensitivity, specificity, and Cohen's Kappa of 93%, 98%, and 0.65, respectively. These results indicate that the proposed method has the potential to be developed as an automated pediatric cough counting device as well as the front-end of a cough analysis system.