AI-Smartphone App ‘Listens’ to Cough to Diagnose Disease

A group of Australian researchers have recently developed an AI-powered smartphone app that can diagnose respiratory disorders by “listening” to the user’s cough. This technology was developed by researchers at Curtin University and The University of Queensland, Australia, whose findings were published June 6 in the journal Respiratory Research.

The researchers created an algorithm that can analyze coughs for features that are unique to five different diseases. This technique is similar to speech recognition technologies in that the software examines the auditory cough for characteristics specific to these conditions.

This is typically done by a physician during a clinical exam, with a stethoscope being used to listen to sound produced while breathing or coughing (auscultation). The downside to this is that the patient must be in the presence of a trained professional to have their respiration sounds analyzed. By empowering the smartphone with this machine learning technology; however, these researchers have created a possible means of remote diagnosis through auditory cough analysis.

“It can be difficult to differentiate between respiratory disorders in children, even for experienced doctors,” said corresponding author Dr Paul Porter. “This study demonstrates how new technology, mathematical concepts, machine learning and clinical medicine can be successfully combined to produce completely new diagnostic tests utilising the expertise of several disciplines.”

Background of the Smartphone Study

The researchers conducted a prospective, multi-centre study to compare the app’s diagnoses to those of trained physicians. Recordings were taken on an iPhone 6 by a pediatric nurse in a realistic environment, with background noises like talking, crying, and medical devices present. 5-10 coughs were recorded per child. Participants included were children aged 29 days to 12 years who had at least one of the following:cough

  • Rhinorrhoea
  • Cough
  • Wheeze
  • Stridor
  • Increased work of breathing
  • Shortness of Breath

After analyzing over 500 subjects, the researchers found the smartphone app to be 81-97% accurate in detecting asthma, pneumonia, bronchiolitis, croup, and lower respiratory tract infections.

“Coughs can be described as wet or dry, brassy or raspy, ringing or barking; they can whistle, whoop or wheeze; but experts cannot always agree on the description or how to use cough sounds for diagnosis,” said Dr. Abeyratne, a biomedical engineer at the University of Queensland who helped develop the app. “We believe the technology can lead to earlier diagnosis and better patient outcomes throughout the world, including in remote locations with limited access to doctors.”

The app used in this study was developed by ResApp Health, a company specializing in digital healthcare solutions. In addition to diagnosing respiratory disease through cough analysis, ResApp also offers smartphone solutions for tracking COPD, asthma and sleep apnea as well.

The researchers concluded that their app displayed sufficient diagnostic accuracy in detecting these childhood respiratory tract disorders, and called for further evaluation of the technology in settings such as hospitals and telehealth interactions.

Earlier this year, news emerged of a similar innovative technology that can detect illness from biomarkers in the user’s exhaled breath. In their research, scientists found the device successfully detected 17 different diseases with 86% accuracy. Dubbed the “SniffPhone”, this technology was awarded the 2018 Innovation Award by the European Commission’s Horizon 2020.

Sources: Respiratory Research, Science Daily, The University of Queensland