According to research published in Respiratory Research, an investigational algorithm used to detect sounds in a child’s cough could help to diagnose pediatric respiratory disorders.
Researchers contend that “pathophysiological changes caused by different respiratory conditions modulate the sound quality,” and these variations could be used to differentiate between common respiratory disorders. According to the study, they used a proprietary software app developed by ResApp Health — which is similar to speech recognition technology — to analyze cough and associated sound streams.
Researchers recorded audio of pediatric coughing from 585 patients using the iPhone 6. Between five and ten spontaneous or voluntary coughs were recorded from each child and data were analyzed via an automatic cough detector that identifies cough sounds.
The algorithm produced a binary Yes/No diagnosis for: LRTD, Asthma/RAD (reactive airway disease), Croup, Pnemonia, URTD, or Bronchiolitis.
According to results, the asthma/RAD, pneumonia, and croup diagnostic algorithms achieved excellent agreement results for all children (29?days to 12?years old).
Researchers concluded that “results show that the performance of the automated algorithm was not inferior to pre-specified endpoints for diagnosing asthma, croup, pneumonia and lower respiratory tract disease from a group of mixed pediatric respiratory disorders.”