Authors:
Anthony Windmon
;
Mona Minakshi
;
Sriram Chellappan
;
Ponrathi R. Athilingam
;
Marcia Johansson
and
Bradlee A. Jenkins
Affiliation:
University of South Florida, United States
Keyword(s):
Chronic Obstructive Pulmonary Disease, COPD, Cough, Machine Learning, Algorithms, Classification.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Cloud Computing
;
Distributed and Mobile Software Systems
;
e-Health
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Mobile Technologies
;
Mobile Technologies for Healthcare Applications
;
Neural Rehabilitation
;
Neurotechnology, Electronics and Informatics
;
Pervasive Health Systems and Services
;
Platforms and Applications
;
Software Engineering
Abstract:
Chronic Obstructive Pulmonary Disease (COPD) is a lung disease that makes breathing a strenuous task with
chronic cough. Millions of adults, worldwide, suffer from COPD, and in many cases, they are not diagnosed
at all. In this paper, we present the feasibility of leveraging cough samples recorded using a smart-phone’s
microphone, and processing the associated audio signals via machine learning algorithms, to detect cough
patterns indicative of COPD. Using 39 adult cough samples evenly spread across both genders, that included
23 subjects infected with COPD and 16 Controls, not infected with COPD, our system, using Random Forest
classification techniques, yielded a detection accuracy of 85:4% with very good Precision, Recall and FMeasures.
To the best of our knowledge, this is the first work that designs a smart-phone based learning
technique for detecting COPD via processing cough.