June 28, 2013
Cough Sound Analysis Could Improve Pneumonia Diagnoses In Remote Areas
redOrbit Staff & Wire Reports - Your Universe Online
Studying a child's cough could soon be used as a reliable way to diagnose pneumonia in youngsters living in underdeveloped and remote regions of the world, according to new research appearing in the online edition of the journal Annals of Biomedical Engineering.
Pneumonia is one of the leading killers of young children throughout the world, with the majority of those deaths coming in resource-poor regions such as sub-Saharan Africa, South Asia and remote areas of China, the researchers said. In these areas, it can be difficult to diagnose pneumonia in a timely fashion, due to the lack of laboratory testing facilities and trained healthcare workers.
Currently, local workers rely upon the World Health Organization's (WHO) simple clinical algorithm to diagnose the condition. However, the WHO method has some limitations. For one thing, it leads to a high number of false positives, which in turn results in the over-prescription of difficult-to-obtain antibiotics.
The new method developed by Abeyratne's team is said to be an easy-to-use alternative to the WHO algorithm. It analyzes cough sounds to diagnose pneumonia. The symptom carries essential information on the lower respiratory tract, especially consolidation of the lungs and secretions, the researchers said. These infection indicators alter the acoustic property of coughs, making it possible to identify pneumonia-specific features.
Abeyratne and his associates analyzed 815 cough events originating from a total of 91 hospitalized children, at the Sardjito Hospital of Gadjah Mada University in Indonesia. Some of those kids had pneumonia, some did not. The sounds of their coughs were collected via bedside microphones, and were then either classified as either pneumonic or non-pneumonic in nature.
The study authors used the overall clinical diagnosis of pediatric respiratory clinicians, as well as routine diagnostic technology, in order to verify their sound analysis. By analyzing the coughs, they were able to correctly identify pneumonia cases with over 90 percent sensitivity, meaning they were able to correctly diagnose the ailment in nearly all pneumonia patients. Their technique was found to have a low false positive rate, and outperformed the existing WHO test in resource poor regions, according to the study.
"Our results indicate the feasibility of taking a cough-centered approach to the diagnosis of childhood pneumonia in resource-poor regions," the authors said. "The technology, in its simplest version, will require between 5-10 cough sounds and will automatically and immediately provide a diagnosis without requiring physical contact with patients. Such a system, if successful, is expected to be a paradigm-shifting novelty in the field of pneumonia diagnosis in remote regions."